system

Abstract

Provide a system. 【Solution means】 A device for automatically aggregating information from public information sources, A device for processing the aggregated information to identify a project target, A device for creating optimized proposed content by referring to past history data, A device for automatically calculating a cost estimate, A device for automatically creating materials for a proposal, A device for improving the proposed content by learning evaluations from users, A device for visually checking and modifying the proposed content using a mobile terminal or an information display device, A system including.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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] In the bidding cases of local governments, due to the complexity of the specifications and the wide range of related information, it is a problem that sales staff face an excessive workload when creating proposal materials. In particular, it is difficult to effectively utilize the information of past similar cases, and strategic countermeasures for increasing the winning rate of proposals are required. However, there are limitations to performing such operations manually, and the need for a system that automates efficient and effective proposals is increasing.

Means for Solving the Problems

[0005] This invention provides a means to streamline the proposal process for municipal tenders by first automatically collecting public notice information, analyzing that information using natural language processing technology, and identifying the target and products of the proposal. Furthermore, it incorporates a means to generate optimal proposal content by referring to past data and automatically calculate an estimate based on that. Proposal materials are automatically created, and users can review them and provide feedback, allowing a machine learning algorithm to continuously improve the accuracy of the proposals. This entire process reduces the burden of proposal work and realizes a system that improves the success rate.

[0006] "Publicly announced information" refers to information that has been officially released regarding the details of bidding and contracts, and serves as the basis for proposals.

[0007] "Analysis" is the process of examining collected information in detail and evaluating its relevance and importance, and is necessary to identify the target of the proposal.

[0008] "Proposal items" refer to the content or products that have been deemed appropriate to propose in a bidding project.

[0009] "Past data" refers to records and performance information from similar bidding projects handled in the past, and is used as reference material when making new proposals.

[0010] "Generation" refers to the process of automatically creating new proposals based on analysis results and past data.

[0011] "Quotation" refers to calculating the cost of the goods and services included in a proposal and determining the price to be presented to the customer.

[0012] A "proposal document" is a document that specifically outlines the proposed content and is created to provide a detailed and clear proposal to the customer.

[0013] A "user" refers to the person who operates the system and reviews and modifies the generated proposals and estimates.

[0014] "Feedback" refers to user opinions and suggestions regarding proposed documents, and is information used to improve the system.

[0015] A "machine learning algorithm" is a computer program technique that analyzes data, learns from experience, and automatically makes predictions and decisions. [Brief explanation of the drawing]

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

Mode for Carrying Out the Invention

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

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

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

[0020] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0021] In the following embodiments, the 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.

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

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

[0024] [First Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0037] This invention is implemented as a system to streamline the proposal process for local government bidding projects and increase the success rate. The entire system is configured to generate optimal proposal content through the processes of data collection, analysis, proposal creation, and evaluation.

[0038] First, the server is responsible for automatically collecting bidding information announced by local governments and related organizations. It periodically retrieves new information via internet-based database access and stores it as structured data. During this process, unnecessary information is filtered out, and only the data necessary for creating proposals is stored.

[0039] Next, the collected data is analyzed using natural language processing (NLP) technology installed on the server. The analysis extracts the necessary items and requirements for the proposal, identifying appropriate products and services. This allows for an initial evaluation of the project and a decision on whether or not to proceed with the proposal.

[0040] In generating proposals, the server references data from similar past projects to select patterns and products with a high success rate. The proposals generated using AI algorithms then proceed to cost calculation, where the cost of the proposed items is calculated based on a pre-configured pricing model within the system.

[0041] The system then automatically generates the proposal document. Necessary information is automatically entered into the template, ensuring consistency and accuracy of the proposal. Users operating the terminal can review this proposal document and make corrections or annotations as needed.

[0042] Ultimately, once user feedback is input into the system, a machine learning algorithm built into the server learns from it and uses it to improve future suggestions. This loop allows the system to evolve and continuously improve the accuracy of its suggestions.

[0043] As a concrete example, if a local government puts up a tender for the introduction of a new IT system, the server extracts relevant technical requirements and budget information from the public notice and proposes the optimal combination of hardware and software. This proposal is automatically generated based on past success stories, and the user submits the proposal document after final review and adjustments. This process significantly improves the quality and efficiency of proposals.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The server accesses an online database that provides local government bidding information and automatically collects new announcements on a regular basis. The collected data is formatted, and only the elements necessary for proposal generation are extracted and stored in the database.

[0047] Step 2:

[0048] The server performs natural language processing (NLP) on the stored data to analyze important keywords and requirements for proposal preparation. This analysis allows for an initial evaluation of the project, determining whether a proposal is feasible and identifying the actual products or services needed.

[0049] Step 3:

[0050] The server automatically constructs proposals by referencing successful patterns and historical data from similar past projects. AI analyzes the proposals and selects the most suitable products and services. It also automatically calculates estimates based on the proposed content.

[0051] Step 4:

[0052] The server automatically inputs proposal details and product information into a proposal template to create the proposal document. This document is generated in a consistent format and is designed to minimize errors.

[0053] Step 5:

[0054] Users review the generated proposal documents and estimates using their devices. They can modify and annotate the documents as needed. This is a crucial step in improving the accuracy of the proposal.

[0055] Step 6:

[0056] The server receives feedback from users and incorporates it into its machine learning algorithms. Based on this feedback, more accurate automated generation becomes possible for future suggestions, and the system continues to improve.

[0057] (Example 1)

[0058] 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."

[0059] The process of preparing proposals for bidding projects is generally manual and time-consuming, requiring considerable effort. Therefore, the quality and success rate of proposals significantly impact operational efficiency. However, traditional methods often fail to quickly gather and analyze necessary information and generate appropriate proposals, making proposal activities with limited resources difficult. To address these challenges, new methods are needed.

[0060] 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.

[0061] In this invention, the server includes means for automatically acquiring publicly announced information, means for analyzing the acquired data to identify the target of the proposal, and means for referencing past data sets to generate the optimal proposal content. This enables efficient collection and analysis of bidding information and the generation of optimized proposal content.

[0062] "Publicly announced information" refers to detailed information about bidding projects that government agencies and public organizations make publicly available.

[0063] "Acquiring" refers to the process of automatically gathering and storing necessary information.

[0064] "Data" refers to information that has been structured, stored, and made into a form that can be analyzed and used.

[0065] "Analysis" is the process of examining collected data and extracting important elements and trends.

[0066] "Proposal target" refers to the set of items and related information necessary for submitting a proposal for a bidding project.

[0067] "Past data sets" refer to a collection of information that has been collected previously, and serve as foundational data for analysis and proposals.

[0068] "Generating" refers to creating new content or results based on existing data or conditions.

[0069] "Cost calculation" is the process of determining the costs and prices included in the proposed content.

[0070] A "proposal document" is a document that outlines the proposed content and is presented to the recipient of the proposal.

[0071] A "user" is an individual or organization that uses this system to create, revise, and finalize proposals.

[0072] "Feedback" refers to the evaluations and suggestions for improvement that users provide regarding proposal activities and their results.

[0073] "Learning" is the process by which a machine improves its performance based on past data and feedback.

[0074] A "machine learning algorithm" is a program that allows a computer to learn from data and make decisions and predictions.

[0075] This system aims to streamline the proposal process for local government tenders and improve the success rate of proposals. The specific implementation of this system is described below.

[0076] The server's primary role is to automatically retrieve bidding information publicly available over the internet and store it in a database. This process utilizes specific APIs and web scraping techniques. Subsequently, the server analyzes the retrieved data using natural language processing (NLP) techniques. The analysis extracts important items from the text and uses them to identify potential bidders. The NLP techniques used include morphological analysis and text mining.

[0077] In generating proposals, the server references successful case studies from similar past projects and utilizes AI algorithms to create optimal proposals. This AI algorithm employs machine learning techniques to construct new proposals based on past success patterns. Furthermore, the server automatically calculates costs based on a pre-configured model and automatically generates proposal documents. These documents are automatically populated into templates, ensuring consistency and accuracy in the proposals.

[0078] Users operating the terminal can review the generated proposal document and make corrections or annotations as needed. Afterward, user feedback is entered into the server, which uses a machine learning algorithm to learn from it and utilize it to improve future proposals. This iterative process allows the system to continuously improve the quality of its proposals.

[0079] As a concrete example, consider a case where a local government conducts a tender for the introduction of a new IT system. The server extracts relevant technical requirements and budget information from the public notice and proposes the optimal solution. This proposal, based on past success stories, is automatically generated, and the user submits the proposal document after final review and adjustments. This system improves the quality of proposals and the efficiency of operations.

[0080] An example of a prompt for a generative AI model might be the question, "Please provide the necessary conditions and success stories for making the best proposal regarding IT system implementation projects for local governments."

[0081] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0082] Step 1:

[0083] The server automatically retrieves bidding information publicly available over the internet. Specifically, it uses APIs and web scraping techniques to periodically access the databases of various organizations and extract the necessary information. Inputs include the URL of the target website and API parameter information. Outputs include structuring the collected bidding data in JSON or XML format and saving it to storage.

[0084] Step 2:

[0085] Based on the acquired data, the server performs data analysis using natural language processing (NLP) techniques. This analysis uses morphological analysis tools to extract important items from the text data. The input is the structured data saved in Step 1. The output is a list of items and keywords necessary for the proposal. In addition, specific actions such as information filtering and tagging of important items are performed.

[0086] Step 3:

[0087] The server searches for similar cases from past data sets and uses AI algorithms to generate optimal proposals. Inputs include the item list organized in Step 2 and past case data. The output is an automatically generated draft proposal by the AI. At this stage, the AI ​​model has learned past success patterns, and this knowledge is reflected in the proposal. Specific actions include structural design of the proposal and evaluation of success factors.

[0088] Step 4:

[0089] Based on the generated proposal content, the server automatically calculates the estimate and generates the proposal document. The inputs are the proposal content and pricing model obtained in step 3. The output is a completed proposal document including the estimate. Specific operations include inputting information into a template and calculating costs. This ensures a consistent and accurate proposal document.

[0090] Step 5:

[0091] The user operating the terminal reviews the generated proposal document and makes corrections and annotations as needed. The input is the proposal document generated in step 4. The output is the final version of the proposal document, modified and added by the user. Specific actions include reviewing the document and entering additional information.

[0092] Step 6:

[0093] After a user completes their proposal, feedback is input into the system, and the server learns from this using a machine learning algorithm. Input includes evaluation comments and success rate data regarding the proposal results. Output is the learning results reflected in the AI ​​model, improving future proposals. Specific actions include collecting and analyzing feedback data and subsequently adjusting the AI ​​model. This continuous learning process ensures that the system's proposal accuracy continues to improve.

[0094] (Application Example 1)

[0095] 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."

[0096] There is a need to streamline the proposal process for local government bidding projects and improve the accuracy and success rate of proposals. However, conventional methods require a great deal of time and effort for information gathering and analysis, and it is difficult to quickly generate optimal proposal content. Furthermore, there is insufficient technology to effectively utilize user feedback and continuously improve proposal content. To solve these problems, it is necessary to develop a system that realizes an efficient and highly accurate proposal process.

[0097] 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.

[0098] In this invention, the server includes a device for automatically aggregating information from public information sources, a device for processing the aggregated information to identify project targets, and a device for referencing historical data to create optimized proposal content. This streamlines the entire process from information gathering to proposal content generation and proposal quality improvement, making it possible to quickly generate highly accurate proposals.

[0099] "Official sources of information" refer to official information released by local governments, government agencies, etc.

[0100] A "device for automatically aggregating information" is a device that has the function of automatically collecting and organizing necessary information.

[0101] A "device for identifying project targets" is a device that analyzes collected information to select data related to specific cases or projects.

[0102] "Historical data" refers to a collection of information about proposals and projects accumulated to date.

[0103] A "device for generating optimized proposals" is a device that utilizes accumulated data to automatically generate the most effective proposals.

[0104] A "device that learns from user feedback and improves its suggestions" is a device that incorporates user feedback to improve the system's ability to make suggestions.

[0105] "Mobile terminal or information display device" refers to a portable electronic device or a device that visually displays information, used by a user to view and manipulate information.

[0106] The system that realizes this application example includes a process that automatically aggregates necessary information from public sources, identifies project targets, generates optimized proposals, and improves the proposals based on user feedback.

[0107] The server periodically collects public information via the internet and stores it in a database. It utilizes web scraping techniques to structure and store this information. Additionally, it uses SpaCy as a natural language processing engine to extract important project items from text data.

[0108] This extracted data is analyzed using a machine learning algorithm based on TENSORFLOW®, and optimal suggestions are generated based on historical data. The generated suggestions can be visually reviewed and modified by the user on mobile devices such as smartphones and smart glasses. This enables efficient and highly accurate suggestions.

[0109] For example, if a local government is undertaking a project to install a new lighting system, this system will automatically suggest the most suitable products and service providers based on budget and technical requirements.

[0110] As an example of a prompt, you can give instructions to the generating AI model in the form of, "Generate the best proposal for the latest smart city lighting system bidding. Requirements are high efficiency, low maintenance, and within budget."

[0111] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0112] Step 1:

[0113] The server automatically collects necessary information from public sources using web scraping techniques. The input is a list of URLs of public sources, and the output is data stored in a structured format. At this stage, the server categorizes the information and stores it in a database.

[0114] Step 2:

[0115] The server uses SpaCy, a natural language processing engine, to analyze the stored data. The input is the text data collected in step 1, and the output is a list of important items and keywords. Through this analysis, the server extracts requirements and conditions related to the project.

[0116] Step 3:

[0117] The server uses the analysis results to refer to historical data and generates optimal suggestions using a machine learning algorithm with TensorFlow. The input is the list of key items obtained in step 2 and historical data, and the output is the suggestions. The server analyzes successful patterns and creates suggestions with high accuracy.

[0118] Step 4:

[0119] The terminal provides the user with the generated suggestions. The input is the suggestions generated on the server, and the output is a display screen for the user. The terminal provides an interface that allows the user to intuitively review and modify the suggestions through an application on their mobile device.

[0120] Step 5:

[0121] The user reviews the proposal and adds any necessary corrections or annotations. The input is the proposal displayed on the device, and the output is the revised proposal. At this stage, user feedback is collected and used to improve future proposals.

[0122] Step 6:

[0123] The server collects user feedback and updates its machine learning algorithm to improve the accuracy of its suggestions. The input is user feedback information, and the output is the updated algorithm. This improves the performance of the generative AI model and the quality of future suggestions.

[0124] 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.

[0125] This invention is implemented as a system that integrates an emotion engine to streamline the proposal process for local government tenders and further improve the quality of proposals. Its main components include data collection, analysis, proposal generation, emotion evaluation, and user feedback.

[0126] First, the server automatically collects bidding information via the internet. This process analyzes public notices from local governments and saves the content in the format required for proposals. By using natural language processing technology, important items and requirements are extracted, and the basic materials for proposals are generated.

[0127] Next, past project data is compared to structure the proposal. Here, an AI algorithm works to identify the combination of products and services that best matches the user's needs. Furthermore, the data obtained during this process is used to automatically calculate an estimate, which is then incorporated into the proposal document.

[0128] The server uses an emotion engine to analyze emotional information extracted through user input and interactions. This emotional information is used to evaluate the potential impression that the proposal will have on the user and to adjust the proposal content and expression based on the results. For example, the wording and design within the proposal document are optimized according to the target user's expectations and preferences.

[0129] Users can review the generated proposal documents on their devices, and, while also viewing the evaluation results from the sentiment engine, can make adjustments and revisions as needed. During this process, user feedback is input into the system, and machine learning algorithms on the server process it. This feedback helps improve the system's subsequent proposals, allowing the system to evolve and produce more refined proposals.

[0130] For example, if a local government is conducting a bidding process for a regional tourism promotion project, the server collects and analyzes public information related to tourism-related products and services, and uses an emotion engine to determine the proposal style that the user expects. A proposal created based on these results is submitted, increasing its influence on potential clients and thus increasing the likelihood of winning the bid.

[0131] The following describes the processing flow.

[0132] Step 1:

[0133] The server accesses official local government bidding information websites and related databases to automatically collect new bidding announcements. The collected data is formatted and then stored in an internal database.

[0134] Step 2:

[0135] The server applies natural language processing (NLP) to the collected public information to analyze important keywords and requirements. Based on these analysis results, it identifies the most suitable products and services for proposal.

[0136] Step 3:

[0137] The server references past bidding data and uses an AI algorithm to analyze successful patterns in similar cases. This analysis determines the best configuration to apply to the generated proposal.

[0138] Step 4:

[0139] The server automatically calculates an estimate using the configured pricing model based on the proposed content. The calculation results are reflected in the proposal document, ensuring an economical proposal.

[0140] Step 5:

[0141] The server uses an emotion engine to analyze the user's past activity history and input data to estimate the user's emotional state. Based on this emotional information, it adjusts the presentation and wording of suggestions, optimizing them to expressions that the user will prefer.

[0142] Step 6:

[0143] Users review the generated proposals and quotes using their devices. They then make adjustments and revisions to the materials as needed, taking into account the evaluation results from the sentiment engine.

[0144] Step 7:

[0145] The server receives feedback from users and uses machine learning algorithms to improve the accuracy of its suggestions. This feedback loop allows the system to continuously improve and maintain its ability to generate highly accurate suggestion materials.

[0146] (Example 2)

[0147] 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 will be referred to as the "terminal."

[0148] In modern proposal development, gathering and analyzing information on bidding projects is often time-consuming and inefficient. Furthermore, it is difficult to accurately grasp the content and provide unique value in constructing proposals. Additionally, the inability to effectively utilize user feedback makes it challenging to improve the quality of proposals.

[0149] 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.

[0150] In this invention, the server includes means for automatically collecting information obtained from public institutions, means for analyzing the collected information to identify the target of the proposal, means for generating appropriate proposal content using past history, means for automatically calculating fees, means for automatically creating proposal documents, means for learning user feedback to improve the proposal content, and means for analyzing sentiment information to adjust the proposal content. This makes it possible to create efficient and precise bid proposals.

[0151] "Means of automatically collecting information obtained from public institutions" refers to a function or mechanism for automatically obtaining bidding-related information published by administrative agencies and local governments from the internet.

[0152] "Means for analyzing the collected information to identify the target of the proposal" refers to techniques for analyzing the collected information and clarifying the specific requirements and needs that should be the target of the proposal.

[0153] "Means for generating appropriate proposals using past history" refers to a method or process for generating new and effective proposals based on previously recorded information.

[0154] "Method for automatically calculating fees" refers to a system for automatically calculating costs based on the proposed content.

[0155] "Methods for automatically generating proposal documents" refers to a function that mechanically generates documents for proposals by combining the necessary information.

[0156] "Methods for improving proposals by learning from user feedback" refers to a learning process that uses feedback information provided by users to improve the quality of proposals.

[0157] "Methods for analyzing emotional information and adjusting proposal content" refers to technologies that analyze emotional information obtained from users and optimize the content and expression of proposals based on the results.

[0158] This invention aims to create a system that streamlines the proposal process for local government bidding projects and improves the quality of those proposals. An embodiment of this system is described below.

[0159] The server automatically collects necessary bidding information from public institution websites. This process uses web crawling technology, specifically leveraging software such as BeautifulSoup and Selenium. The collected information is stored in a database and used as the basis for analysis.

[0160] Next, the server analyzes the collected information using natural language processing techniques to identify items that should be proposed. Libraries such as spaCy and NLTK are often used for language processing. This clarifies important conditions and needs.

[0161] Furthermore, the server references past proposal data and uses an AI algorithm to generate the most suitable proposal for the current project. In this process, machine learning libraries such as Scikit-learn and TensorFlow are used to combine products and services according to the user's needs.

[0162] The server also has a function that automatically calculates the price based on the generated proposal. The calculation results of the estimate are reflected in the proposal document.

[0163] After the proposal document is created, users evaluate the impression the proposal gives through an emotion engine. Sentiment analysis tools such as TextBlob and VADER are used, and the wording and design are optimized based on this evaluation.

[0164] Users review the generated proposal materials and evaluation results on their devices and make adjustments to the materials as needed. User feedback is entered into the system, which is processed by a server using machine learning algorithms, and the feedback is used to improve future proposals.

[0165] As a concrete example, when a local government is conducting a bidding process for a regional tourism promotion project, the server collects tourism-related information and generates appropriate proposals. An example of a prompt message might be, "Please create a proposal document for a tourism promotion project. The target audience is assumed to be families." When this prompt is input into the AI ​​model, a specific and detailed proposal is generated.

[0166] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0167] Step 1:

[0168] The server automatically collects bidding information from public institution websites. It obtains the necessary URLs and queries as input and uses a web crawler to download this information. Specifically, it uses BeautifulSoup or Selenium to parse HTML data and extract the relevant bidding information in text format. The output of this process is a dataset of organized public notices.

[0169] Step 2:

[0170] The server analyzes the collected bid information using natural language processing technology. Text data is provided as input, and important keywords and requirements are extracted from the text using libraries such as spaCy and NLTK. This organizes and concretizes the bid requirements. The output of this process is a list of key items to be proposed.

[0171] Step 3:

[0172] The server references past proposal data and uses an AI algorithm to generate optimal proposals. Historical data and key items obtained in step 2 are used as input. Analysis is performed using Scikit-learn and TensorFlow to select products and services that meet the user's needs. The output of this process is a list of products and services included in the proposal document.

[0173] Step 4:

[0174] The server automatically calculates the price based on the proposed content. It uses the cost information of the goods and services selected in Step 3 as input and applies a calculation logic to determine the price. This calculation result is reflected in the proposal document. The output is the estimated price.

[0175] Step 5:

[0176] The user reviews the proposal document generated on their device and obtains evaluation results from the sentiment engine. Inputs include the proposal document and the user's past operation logs and feedback. Sentiment analysis and evaluation are performed using TextBlob and VADER. The output is feedback regarding the impression of the proposal.

[0177] Step 6:

[0178] Users adjust their proposal documents as needed based on evaluation results and feedback. They edit the proposal document on their terminal and input improvements. This improves the quality of the proposal. The output of this process is the revised final proposal document.

[0179] Step 7:

[0180] The server processes user feedback using a machine learning algorithm to improve the suggestions. User feedback data is used as input. The learning algorithm automatically improves the accuracy of the suggestions and incorporates the feedback results into the next suggestions. The output of this process is the improved suggestion generation process.

[0181] (Application Example 2)

[0182] 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".

[0183] In today's information-saturated world, accurately analyzing information and quickly providing optimal suggestions is crucial. However, conventional systems offer uniform suggestions to users, lacking sufficient customization to address individual user emotions and needs. Furthermore, the inability to effectively utilize user feedback limits the improvement of suggestion accuracy. There is a need for a system that can solve these problems and enable more accurate and personalized suggestions.

[0184] 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.

[0185] In this invention, the server includes means for automatically collecting information, means for analyzing and identifying targets, means for providing a user interface, and means for analyzing emotions and adjusting the suggestion style. This enables highly accurate and personalized suggestions that meet the individual needs and emotions of the user.

[0186] "Means for automatically collecting publicly available information" refers to systems and processes that mechanically collect information published on the internet and aggregate it as usable data.

[0187] "Means of analysis to identify targets" refers to systems and algorithms for analyzing collected data and identifying the optimal target based on specific purposes or conditions.

[0188] "Means of generating optimal content by referring to past data" refers to technologies and processes that generate data and content suitable for a specific purpose by referring to existing historical information and related information.

[0189] "Methods for automatically calculating estimates" refer to systems and algorithms that automatically calculate costs and expenses based on collected data and generated content.

[0190] "Means of automatically generating documents" refer to systems and processes for automatically generating documents and reports suitable for specific purposes based on collected and analyzed data.

[0191] "Means of providing a user interface through a data terminal" refers to technologies and environments that provide an interface on an electronic device for users to manipulate information.

[0192] "Means for analyzing emotions and adjusting proposal style" refers to a system and algorithm for analyzing a user's emotional state and optimizing proposal content and presentation style based on the results.

[0193] "Means of learning from user feedback and improving content" refers to systems and algorithms that learn from opinions and evaluations provided by users and reflect them in future data generation and suggestions.

[0194] To implement this invention, the system must include the following components. First, the server automatically collects publicly available information from local governments and public organizations on the internet and stores it in a specified data format. This can be done using specific APIs or scraping tools. Then, natural language processing techniques are used to extract important information from the documents. For this process, APIs such as OpenAI® or other NLP libraries are effective.

[0195] Next, the server compares the collected information by referencing past databases and generates optimal suggestions. Machine learning algorithms can be used here, and models can be built using frameworks such as TensorFlow or PyTorch.

[0196] The server then displays the suggestions on the user's device. The user interface is built using React Native and other cross-platform frameworks, making it intuitive and easy for users to use.

[0197] The server further utilizes an emotion analysis engine to collect and analyze emotional data from user feedback and actions. Based on this analysis, it personalizes the suggestions and style, resulting in the most suitable suggestions for the user.

[0198] Users input feedback on the screen, and this information is learned by the server and used to improve the accuracy of future suggestions. This process contributes to the evolution of the system through continuous learning and improvement.

[0199] For example, if a user is considering purchasing a new smartphone, the system will suggest smartphones with features and price ranges that are likely to interest the user, based on their past purchase history and recent browsing history. The emotion engine then customizes these suggestions to best suit the user's interests.

[0200] Examples of prompts to input into a generative AI model:

[0201] "When it comes to the latest smartphones, if users tend to be price-conscious, suggest products that have the features they are most interested in."

[0202] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0203] Step 1:

[0204] The server automatically collects publicly announced information from local governments and public institutions via the internet. The input is publicly available data from the web, and the output is records in a database converted into a specific format. It performs operations such as formatting and storing information obtained from data scraping tools and APIs. Filtering based on date and keywords is performed during this process.

[0205] Step 2:

[0206] The server analyzes the collected data using natural language processing (NLP) techniques to extract important items and requirements. The input is the formalized data obtained in step 1, and the output is a list of key information extracted from the document. This process utilizes an NLP library to identify important elements while scrutinizing the content of the information.

[0207] Step 3:

[0208] The server generates optimal suggestions by referencing a historical database. The input is the list of key information obtained in step 2, and the output is a summary of the suggestions. A machine learning algorithm is applied to select the most effective content by referring to similar past cases.

[0209] Step 4:

[0210] The server automatically calculates the estimate and generates the proposal document. The input is the proposal content formulated in step 3, and the output is a text document containing comprehensive cost information. It performs calculations based on the pricing model and formats the proposal.

[0211] Step 5:

[0212] The server uses an emotion engine to collect emotional information from user feedback and actions. The input is user response data, and the output is a report of the emotional analysis results. The emotion engine analyzes the input data, identifies the user's emotional state, and suggests recommended adjustments.

[0213] Step 6:

[0214] The user reviews the proposed document on their device and enters feedback. The input is the generated proposal document, and the output is the information sent to the server as feedback. The user views the proposal through the UI and records their opinions as needed.

[0215] Step 7:

[0216] The server receives feedback from users and uses a machine learning algorithm to learn and improve its suggestions. The input is the feedback data obtained in step 6, and the output is the improved accuracy of the next suggestion. The collected information is fed back into the model to make adjustments that improve the system's accuracy.

[0217] 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.

[0218] 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.

[0219] 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.

[0220] [Second Embodiment]

[0221] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0222] 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.

[0223] 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).

[0224] 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.

[0225] 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.

[0226] 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).

[0227] 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.

[0228] 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.

[0229] 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.

[0230] 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.

[0231] 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.

[0232] 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".

[0233] This invention is implemented as a system to streamline the proposal process for local government bidding projects and increase the success rate. The entire system is configured to generate optimal proposal content through the processes of data collection, analysis, proposal creation, and evaluation.

[0234] First, the server is responsible for automatically collecting bidding information announced by local governments and related organizations. It periodically retrieves new information via internet-based database access and stores it as structured data. During this process, unnecessary information is filtered out, and only the data necessary for creating proposals is stored.

[0235] Next, the collected data is analyzed using natural language processing (NLP) technology installed on the server. The analysis extracts the necessary items and requirements for the proposal, identifying appropriate products and services. This allows for an initial evaluation of the project and a decision on whether or not to proceed with the proposal.

[0236] In generating proposals, the server references data from similar past projects to select patterns and products with a high success rate. The proposals generated using AI algorithms then proceed to cost calculation, where the cost of the proposed items is calculated based on a pre-configured pricing model within the system.

[0237] The system then automatically generates the proposal document. Necessary information is automatically entered into the template, ensuring consistency and accuracy of the proposal. Users operating the terminal can review this proposal document and make corrections or annotations as needed.

[0238] Ultimately, once user feedback is input into the system, a machine learning algorithm built into the server learns from it and uses it to improve future suggestions. This loop allows the system to evolve and continuously improve the accuracy of its suggestions.

[0239] As a concrete example, if a local government puts up a tender for the introduction of a new IT system, the server extracts relevant technical requirements and budget information from the public notice and proposes the optimal combination of hardware and software. This proposal is automatically generated based on past success stories, and the user submits the proposal document after final review and adjustments. This process significantly improves the quality and efficiency of proposals.

[0240] The following describes the processing flow.

[0241] Step 1:

[0242] The server accesses an online database that provides local government bidding information and automatically collects new announcements on a regular basis. The collected data is formatted, and only the elements necessary for proposal generation are extracted and stored in the database.

[0243] Step 2:

[0244] The server performs natural language processing (NLP) on the stored data to analyze important keywords and requirements for proposal preparation. This analysis allows for an initial evaluation of the project, determining whether a proposal is feasible and identifying the actual products or services needed.

[0245] Step 3:

[0246] The server automatically constructs proposals by referencing successful patterns and historical data from similar past projects. AI analyzes the proposals and selects the most suitable products and services. It also automatically calculates estimates based on the proposed content.

[0247] Step 4:

[0248] The server automatically inputs proposal details and product information into a proposal template to create the proposal document. This document is generated in a consistent format and is designed to minimize errors.

[0249] Step 5:

[0250] Users review the generated proposal documents and estimates using their devices. They can modify and annotate the documents as needed. This is a crucial step in improving the accuracy of the proposal.

[0251] Step 6:

[0252] The server receives feedback from users and incorporates it into its machine learning algorithms. Based on this feedback, more accurate automated generation becomes possible for future suggestions, and the system continues to improve.

[0253] (Example 1)

[0254] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0255] The process of preparing proposals for bidding projects is generally manual and time-consuming, requiring considerable effort. Therefore, the quality and success rate of proposals significantly impact operational efficiency. However, traditional methods often fail to quickly gather and analyze necessary information and generate appropriate proposals, making proposal activities with limited resources difficult. To address these challenges, new methods are needed.

[0256] 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.

[0257] In this invention, the server includes means for automatically acquiring publicly announced information, means for analyzing the acquired data to identify the target of the proposal, and means for referencing past data sets to generate the optimal proposal content. This enables efficient collection and analysis of bidding information and the generation of optimized proposal content.

[0258] "Publicly announced information" refers to detailed information about bidding projects that government agencies and public organizations make publicly available.

[0259] "Acquiring" refers to the process of automatically gathering and storing necessary information.

[0260] "Data" refers to information that has been structured, stored, and made into a form that can be analyzed and used.

[0261] "Analysis" is the process of examining collected data and extracting important elements and trends.

[0262] "Proposal target" refers to the set of items and related information necessary for submitting a proposal for a bidding project.

[0263] "Past data sets" refer to a collection of information that has been collected previously, and serve as foundational data for analysis and proposals.

[0264] "Generating" refers to creating new content or results based on existing data or conditions.

[0265] "Cost calculation" is the process of determining the costs and prices included in the proposed content.

[0266] A "proposal document" is a document that outlines the proposed content and is presented to the recipient of the proposal.

[0267] A "user" is an individual or organization that uses this system to create, revise, and finalize proposals.

[0268] "Feedback" refers to the evaluations and suggestions for improvement that users provide regarding proposal activities and their results.

[0269] "Learning" is the process by which a machine improves its performance based on past data and feedback.

[0270] A "machine learning algorithm" is a program that allows a computer to learn from data and make decisions and predictions.

[0271] This system aims to streamline the proposal process for local government tenders and improve the success rate of proposals. The specific implementation of this system is described below.

[0272] The server's primary role is to automatically retrieve bidding information publicly available over the internet and store it in a database. This process utilizes specific APIs and web scraping techniques. Subsequently, the server analyzes the retrieved data using natural language processing (NLP) techniques. The analysis extracts important items from the text and uses them to identify potential bidders. The NLP techniques used include morphological analysis and text mining.

[0273] In generating proposals, the server references successful case studies from similar past projects and utilizes AI algorithms to create optimal proposals. This AI algorithm employs machine learning techniques to construct new proposals based on past success patterns. Furthermore, the server automatically calculates costs based on a pre-configured model and automatically generates proposal documents. These documents are automatically populated into templates, ensuring consistency and accuracy in the proposals.

[0274] Users operating the terminal can review the generated proposal document and make corrections or annotations as needed. Afterward, user feedback is entered into the server, which uses a machine learning algorithm to learn from it and utilize it to improve future proposals. This iterative process allows the system to continuously improve the quality of its proposals.

[0275] As a concrete example, consider a case where a local government conducts a tender for the introduction of a new IT system. The server extracts relevant technical requirements and budget information from the public notice and proposes the optimal solution. This proposal, based on past success stories, is automatically generated, and the user submits the proposal document after final review and adjustments. This system improves the quality of proposals and the efficiency of operations.

[0276] An example of a prompt for a generative AI model might be the question, "Please provide the necessary conditions and success stories for making the best proposal regarding IT system implementation projects for local governments."

[0277] The flow of the specific process in Example 1 will be described using FIG. 11.

[0278] Step 1:

[0279] The server automatically obtains the tender information published via the Internet. Specifically, it uses API or web scraping technology to regularly access the databases of each institution and extract the necessary information. The inputs include the URL of the target website and the parameter information of the API. As output, the collected tender data is structured and stored in the storage in JSON or XML format.

[0280] Step 2:

[0281] Based on the obtained data, the server performs data analysis using natural language processing (NLP) technology. In this analysis, a morphological analysis tool is used to extract important items from the text data. The input is the structured data saved in Step 1. As output, the items and keywords necessary for the proposal are listed. Also, as specific operations, information filtering and tagging of important items are performed.

[0282] Step 3:

[0283] The server searches for similar cases from the past data group and uses AI algorithms to generate the optimal proposal content. The inputs are the item list organized in Step 2 and the past case data. As output, a draft of the proposal content is automatically generated by the AI. At this stage, since the AI model is learning from past successful patterns, that knowledge is reflected in the proposal content. Specific operations include the structural design of the proposal and the evaluation of success factors.

[0284] Step 4:

[0285] Based on the generated proposed content, the server automatically calculates the estimate and generates the proposal document. The inputs are the proposed content obtained in Step 3 and the price setting model. As the output, a completed proposal document including the estimate is generated. Specific operations include information input to the template and cost calculation. This results in a proposal document with consistency and accuracy.

[0286] Step 5:

[0287] The user operating the terminal checks the generated proposal document and makes corrections and annotations as necessary. The input is the proposal document generated in Step 4. As the output, the final version of the proposal document revised and added to by the user is obtained. Specific operations include reviewing the document and inputting additional information.

[0288] Step 6:

[0289] After the user completes the proposal, feedback is input into the system, and the server learns this using a machine learning algorithm. The inputs are evaluation comments regarding the proposal result and data on the success rate. As the output, the learning result is reflected in the AI model, and the proposed content for subsequent times is improved. Specific operations include collecting and analyzing the feedback data and then adjusting the AI model. Through this continuous learning process, the proposal accuracy of the system continues to improve.

[0290] (Application Example 1)

[0291] Next, Application 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".

[0292] There is a need to streamline the proposal process for local government bidding projects and improve the accuracy and success rate of proposals. However, conventional methods require a great deal of time and effort for information gathering and analysis, and it is difficult to quickly generate optimal proposal content. Furthermore, there is insufficient technology to effectively utilize user feedback and continuously improve proposal content. To solve these problems, it is necessary to develop a system that realizes an efficient and highly accurate proposal process.

[0293] 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.

[0294] In this invention, the server includes a device for automatically aggregating information from public information sources, a device for processing the aggregated information to identify project targets, and a device for referencing historical data to create optimized proposal content. This streamlines the entire process from information gathering to proposal content generation and proposal quality improvement, making it possible to quickly generate highly accurate proposals.

[0295] "Official sources of information" refer to official information released by local governments, government agencies, etc.

[0296] A "device for automatically aggregating information" is a device that has the function of automatically collecting and organizing necessary information.

[0297] A "device for identifying project targets" is a device that analyzes collected information to select data related to specific cases or projects.

[0298] "Historical data" refers to a collection of information about proposals and projects accumulated to date.

[0299] A "device for generating optimized proposals" is a device that utilizes accumulated data to automatically generate the most effective proposals.

[0300] A "device that learns from user feedback and improves its suggestions" is a device that incorporates user feedback to improve the system's ability to make suggestions.

[0301] "Mobile terminal or information display device" refers to a portable electronic device or a device that visually displays information, used by a user to view and manipulate information.

[0302] The system that realizes this application example includes a process that automatically aggregates necessary information from public sources, identifies project targets, generates optimized proposals, and improves the proposals based on user feedback.

[0303] The server periodically collects public information via the internet and stores it in a database. It utilizes web scraping techniques to structure and store this information. Additionally, it uses SpaCy as a natural language processing engine to extract important project items from text data.

[0304] This extracted data is analyzed using a machine learning algorithm based on TensorFlow, and optimal suggestions are generated based on historical data. The generated suggestions can be visually reviewed and modified by the user on mobile devices such as smartphones and smart glasses. This enables efficient and highly accurate suggestions.

[0305] For example, if a local government is undertaking a project to install a new lighting system, this system will automatically suggest the most suitable products and service providers based on budget and technical requirements.

[0306] As an example of a prompt, you can give instructions to the generating AI model in the form of, "Generate the best proposal for the latest smart city lighting system bidding. Requirements are high efficiency, low maintenance, and within budget."

[0307] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0308] Step 1:

[0309] The server automatically collects the necessary information from public information sources using web scraping technology. The input is a list of URLs of public information sources, and the output is data saved in a structured format. At this stage, the server categorizes the information and saves it in the database.

[0310] Step 2:

[0311] The server analyzes the saved data using SpaCy, a natural language processing engine. The input is the text data collected in Step 1, and the output is a list of important items and keywords. Through this analysis, the server extracts the requirements and conditions related to the project.

[0312] Step 3:

[0313] The server refers to the past historical data using the analysis results and generates the optimal proposed content by a machine learning algorithm using TensorFlow. The input is the list of important items obtained in Step 2 and the past data, and the output is the proposed content. The server analyzes the successful patterns and creates proposals with high accuracy.

[0314] Step 4:

[0315] The terminal provides the generated proposed content to the user. The input is the proposed content generated by the server, and the output is the display screen for the user. The terminal provides an interface through an application on the mobile device that allows the user to intuitively view and modify the proposed content.

[0316] Step 5:

[0317] The user reviews the proposal and adds any necessary corrections or annotations. The input is the proposal displayed on the device, and the output is the revised proposal. At this stage, user feedback is collected and used to improve future proposals.

[0318] Step 6:

[0319] The server collects user feedback and updates its machine learning algorithm to improve the accuracy of its suggestions. The input is user feedback information, and the output is the updated algorithm. This improves the performance of the generative AI model and the quality of future suggestions.

[0320] 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.

[0321] This invention is implemented as a system that integrates an emotion engine to streamline the proposal process for local government tenders and further improve the quality of proposals. Its main components include data collection, analysis, proposal generation, emotion evaluation, and user feedback.

[0322] First, the server automatically collects bidding information via the internet. This process analyzes public notices from local governments and saves the content in the format required for proposals. By using natural language processing technology, important items and requirements are extracted, and the basic materials for proposals are generated.

[0323] Next, past project data is compared to structure the proposal. Here, an AI algorithm works to identify the combination of products and services that best matches the user's needs. Furthermore, the data obtained during this process is used to automatically calculate an estimate, which is then incorporated into the proposal document.

[0324] The server uses an emotion engine to analyze emotional information extracted through user input and interactions. This emotional information is used to evaluate the potential impression that the proposal will have on the user and to adjust the proposal content and expression based on the results. For example, the wording and design within the proposal document are optimized according to the target user's expectations and preferences.

[0325] Users can review the generated proposal documents on their devices, and, while also viewing the evaluation results from the sentiment engine, can make adjustments and revisions as needed. During this process, user feedback is input into the system, and machine learning algorithms on the server process it. This feedback helps improve the system's subsequent proposals, allowing the system to evolve and produce more refined proposals.

[0326] For example, if a local government is conducting a bidding process for a regional tourism promotion project, the server collects and analyzes public information related to tourism-related products and services, and uses an emotion engine to determine the proposal style that the user expects. A proposal created based on these results is submitted, increasing its influence on potential clients and thus increasing the likelihood of winning the bid.

[0327] The following describes the processing flow.

[0328] Step 1:

[0329] The server accesses official local government bidding information websites and related databases to automatically collect new bidding announcements. The collected data is formatted and then stored in an internal database.

[0330] Step 2:

[0331] The server applies natural language processing (NLP) to the collected public information to analyze important keywords and requirements. Based on these analysis results, it identifies the most suitable products and services for proposal.

[0332] Step 3:

[0333] The server references past bidding data and uses an AI algorithm to analyze successful patterns in similar cases. This analysis determines the best configuration to apply to the generated proposal.

[0334] Step 4:

[0335] The server automatically calculates an estimate using the configured pricing model based on the proposed content. The calculation results are reflected in the proposal document, ensuring an economical proposal.

[0336] Step 5:

[0337] The server uses an emotion engine to analyze the user's past activity history and input data to estimate the user's emotional state. Based on this emotional information, it adjusts the presentation and wording of suggestions, optimizing them to expressions that the user will prefer.

[0338] Step 6:

[0339] Users review the generated proposals and quotes using their devices. They then make adjustments and revisions to the materials as needed, taking into account the evaluation results from the sentiment engine.

[0340] Step 7:

[0341] The server receives feedback from users and uses machine learning algorithms to improve the accuracy of its suggestions. This feedback loop allows the system to continuously improve and maintain its ability to generate highly accurate suggestion materials.

[0342] (Example 2)

[0343] 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".

[0344] In modern proposal development, gathering and analyzing information on bidding projects is often time-consuming and inefficient. Furthermore, it is difficult to accurately grasp the content and provide unique value in constructing proposals. Additionally, the inability to effectively utilize user feedback makes it challenging to improve the quality of proposals.

[0345] 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.

[0346] In this invention, the server includes means for automatically collecting information obtained from public institutions, means for analyzing the collected information to identify the target of the proposal, means for generating appropriate proposal content using past history, means for automatically calculating fees, means for automatically creating proposal documents, means for learning user feedback to improve the proposal content, and means for analyzing sentiment information to adjust the proposal content. This makes it possible to create efficient and precise bid proposals.

[0347] "Means of automatically collecting information obtained from public institutions" refers to a function or mechanism for automatically obtaining bidding-related information published by administrative agencies and local governments from the internet.

[0348] "Means for analyzing the collected information to identify the target of the proposal" refers to techniques for analyzing the collected information and clarifying the specific requirements and needs that should be the target of the proposal.

[0349] "Means for generating appropriate proposals using past history" refers to a method or process for generating new and effective proposals based on previously recorded information.

[0350] "Method for automatically calculating fees" refers to a system for automatically calculating costs based on the proposed content.

[0351] "Methods for automatically generating proposal documents" refers to a function that mechanically generates documents for proposals by combining the necessary information.

[0352] "Methods for improving proposals by learning from user feedback" refers to a learning process that uses feedback information provided by users to improve the quality of proposals.

[0353] "Methods for analyzing emotional information and adjusting proposal content" refers to technologies that analyze emotional information obtained from users and optimize the content and expression of proposals based on the results.

[0354] This invention aims to create a system that streamlines the proposal process for local government bidding projects and improves the quality of those proposals. An embodiment of this system is described below.

[0355] The server automatically collects necessary bidding information from public institution websites. This process uses web crawling technology, specifically leveraging software such as BeautifulSoup and Selenium. The collected information is stored in a database and used as the basis for analysis.

[0356] Next, the server analyzes the collected information using natural language processing techniques to identify items that should be proposed. Libraries such as spaCy and NLTK are often used for language processing. This clarifies important conditions and needs.

[0357] Furthermore, the server references past proposal data and uses an AI algorithm to generate the most suitable proposal for the current project. In this process, machine learning libraries such as Scikit-learn and TensorFlow are used to combine products and services according to the user's needs.

[0358] The server also has a function that automatically calculates the price based on the generated proposal. The calculation results of the estimate are reflected in the proposal document.

[0359] After the proposal document is created, users evaluate the impression the proposal gives through an emotion engine. Sentiment analysis tools such as TextBlob and VADER are used, and the wording and design are optimized based on this evaluation.

[0360] Users review the generated proposal materials and evaluation results on their devices and make adjustments to the materials as needed. User feedback is entered into the system, which is processed by a server using machine learning algorithms, and the feedback is used to improve future proposals.

[0361] As a concrete example, when a local government is conducting a bidding process for a regional tourism promotion project, the server collects tourism-related information and generates appropriate proposals. An example of a prompt message might be, "Please create a proposal document for a tourism promotion project. The target audience is assumed to be families." When this prompt is input into the AI ​​model, a specific and detailed proposal is generated.

[0362] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0363] Step 1:

[0364] The server automatically collects bidding information from public institution websites. It obtains the necessary URLs and queries as input and uses a web crawler to download this information. Specifically, it uses BeautifulSoup or Selenium to parse HTML data and extract the relevant bidding information in text format. The output of this process is a dataset of organized public notices.

[0365] Step 2:

[0366] The server analyzes the collected bid information using natural language processing technology. Text data is provided as input, and important keywords and requirements are extracted from the text using libraries such as spaCy and NLTK. This organizes and concretizes the bid requirements. The output of this process is a list of key items to be proposed.

[0367] Step 3:

[0368] The server references past proposal data and uses an AI algorithm to generate optimal proposals. Historical data and key items obtained in step 2 are used as input. Analysis is performed using Scikit-learn and TensorFlow to select products and services that meet the user's needs. The output of this process is a list of products and services included in the proposal document.

[0369] Step 4:

[0370] The server automatically calculates the price based on the proposed content. It uses the cost information of the goods and services selected in Step 3 as input and applies a calculation logic to determine the price. This calculation result is reflected in the proposal document. The output is the estimated price.

[0371] Step 5:

[0372] The user reviews the proposal document generated on their device and obtains evaluation results from the sentiment engine. Inputs include the proposal document and the user's past operation logs and feedback. Sentiment analysis and evaluation are performed using TextBlob and VADER. The output is feedback regarding the impression of the proposal.

[0373] Step 6:

[0374] Users adjust their proposal documents as needed based on evaluation results and feedback. They edit the proposal document on their terminal and input improvements. This improves the quality of the proposal. The output of this process is the revised final proposal document.

[0375] Step 7:

[0376] The server processes user feedback using a machine learning algorithm to improve the suggestions. User feedback data is used as input. The learning algorithm automatically improves the accuracy of the suggestions and incorporates the feedback results into the next suggestions. The output of this process is the improved suggestion generation process.

[0377] (Application Example 2)

[0378] 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 as the "terminal".

[0379] In today's information-saturated world, accurately analyzing information and quickly providing optimal suggestions is crucial. However, conventional systems offer uniform suggestions to users, lacking sufficient customization to address individual user emotions and needs. Furthermore, the inability to effectively utilize user feedback limits the improvement of suggestion accuracy. There is a need for a system that can solve these problems and enable more accurate and personalized suggestions.

[0380] 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.

[0381] In this invention, the server includes means for automatically collecting information, means for analyzing and identifying targets, means for providing a user interface, and means for analyzing emotions and adjusting the suggestion style. This enables highly accurate and personalized suggestions that meet the individual needs and emotions of the user.

[0382] "Means for automatically collecting publicly available information" refers to systems and processes that mechanically collect information published on the internet and aggregate it as usable data.

[0383] "Means of analysis to identify targets" refers to systems and algorithms for analyzing collected data and identifying the optimal target based on specific purposes or conditions.

[0384] "Means of generating optimal content by referring to past data" refers to technologies and processes that generate data and content suitable for a specific purpose by referring to existing historical information and related information.

[0385] "Methods for automatically calculating estimates" refer to systems and algorithms that automatically calculate costs and expenses based on collected data and generated content.

[0386] "Means of automatically generating documents" refer to systems and processes for automatically generating documents and reports suitable for specific purposes based on collected and analyzed data.

[0387] "Means of providing a user interface through a data terminal" refers to technologies and environments that provide an interface on an electronic device for users to manipulate information.

[0388] "Means for analyzing emotions and adjusting proposal style" refers to a system and algorithm for analyzing a user's emotional state and optimizing proposal content and presentation style based on the results.

[0389] "Means of learning from user feedback and improving content" refers to systems and algorithms that learn from opinions and evaluations provided by users and reflect them in future data generation and suggestions.

[0390] To implement this invention, the system must include the following components. First, the server automatically collects publicly available information from local governments and public organizations on the internet and stores it in a specified data format. This can be done using specific APIs or scraping tools. Then, natural language processing techniques are used to extract important information from the documents. For this process, for example, the OpenAI API or other NLP libraries are effective.

[0391] Next, the server compares the collected information by referencing past databases and generates optimal suggestions. Machine learning algorithms can be used here, and models can be built using frameworks such as TensorFlow or PyTorch.

[0392] The server then displays the suggestions on the user's device. The user interface is built using React Native and other cross-platform frameworks, making it intuitive and easy for users to use.

[0393] The server further utilizes an emotion analysis engine to collect and analyze emotional data from user feedback and actions. Based on this analysis, it personalizes the suggestions and style, resulting in the most suitable suggestions for the user.

[0394] Users input feedback on the screen, and this information is learned by the server and used to improve the accuracy of future suggestions. This process contributes to the evolution of the system through continuous learning and improvement.

[0395] For example, if a user is considering purchasing a new smartphone, the system will suggest smartphones with features and price ranges that are likely to interest the user, based on their past purchase history and recent browsing history. The emotion engine then customizes these suggestions to best suit the user's interests.

[0396] Examples of prompts to input into a generative AI model:

[0397] "When it comes to the latest smartphones, if users tend to be price-conscious, suggest products that have the features they are most interested in."

[0398] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0399] Step 1:

[0400] The server automatically collects publicly announced information from local governments and public institutions via the internet. The input is publicly available data from the web, and the output is records in a database converted into a specific format. It performs operations such as formatting and storing information obtained from data scraping tools and APIs. Filtering based on date and keywords is performed during this process.

[0401] Step 2:

[0402] The server analyzes the collected data using natural language processing (NLP) techniques to extract important items and requirements. The input is the formalized data obtained in step 1, and the output is a list of key information extracted from the document. This process utilizes an NLP library to identify important elements while scrutinizing the content of the information.

[0403] Step 3:

[0404] The server generates optimal suggestions by referencing a historical database. The input is the list of key information obtained in step 2, and the output is a summary of the suggestions. A machine learning algorithm is applied to select the most effective content by referring to similar past cases.

[0405] Step 4:

[0406] The server automatically calculates the estimate and generates the proposal document. The input is the proposal content formulated in step 3, and the output is a text document containing comprehensive cost information. It performs calculations based on the pricing model and formats the proposal.

[0407] Step 5:

[0408] The server uses an emotion engine to collect emotional information from user feedback and actions. The input is user response data, and the output is a report of the emotional analysis results. The emotion engine analyzes the input data, identifies the user's emotional state, and suggests recommended adjustments.

[0409] Step 6:

[0410] The user reviews the proposed document on their device and enters feedback. The input is the generated proposal document, and the output is the information sent to the server as feedback. The user views the proposal through the UI and records their opinions as needed.

[0411] Step 7:

[0412] The server receives feedback from users and uses a machine learning algorithm to learn and improve its suggestions. The input is the feedback data obtained in step 6, and the output is the improved accuracy of the next suggestion. The collected information is fed back into the model to make adjustments that improve the system's accuracy.

[0413] 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.

[0414] 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.

[0415] 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.

[0416] [Third Embodiment]

[0417] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0418] 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.

[0419] 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).

[0420] 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.

[0421] 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.

[0422] 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).

[0423] 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.

[0424] 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.

[0425] 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.

[0426] 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.

[0427] 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.

[0428] 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".

[0429] This invention is implemented as a system to streamline the proposal process for local government bidding projects and increase the success rate. The entire system is configured to generate optimal proposal content through the processes of data collection, analysis, proposal creation, and evaluation.

[0430] First, the server is responsible for automatically collecting bidding information announced by local governments and related organizations. It periodically retrieves new information via internet-based database access and stores it as structured data. During this process, unnecessary information is filtered out, and only the data necessary for creating proposals is stored.

[0431] Next, the collected data is analyzed using natural language processing (NLP) technology installed on the server. The analysis extracts the necessary items and requirements for the proposal, identifying appropriate products and services. This allows for an initial evaluation of the project and a decision on whether or not to proceed with the proposal.

[0432] In generating proposals, the server references data from similar past projects to select patterns and products with a high success rate. The proposals generated using AI algorithms then proceed to cost calculation, where the cost of the proposed items is calculated based on a pre-configured pricing model within the system.

[0433] The system then automatically generates the proposal document. Necessary information is automatically entered into the template, ensuring consistency and accuracy of the proposal. Users operating the terminal can review this proposal document and make corrections or annotations as needed.

[0434] Ultimately, once user feedback is input into the system, a machine learning algorithm built into the server learns from it and uses it to improve future suggestions. This loop allows the system to evolve and continuously improve the accuracy of its suggestions.

[0435] As a concrete example, if a local government puts up a tender for the introduction of a new IT system, the server extracts relevant technical requirements and budget information from the public notice and proposes the optimal combination of hardware and software. This proposal is automatically generated based on past success stories, and the user submits the proposal document after final review and adjustments. This process significantly improves the quality and efficiency of proposals.

[0436] The following describes the processing flow.

[0437] Step 1:

[0438] The server accesses an online database that provides local government bidding information and automatically collects new announcements on a regular basis. The collected data is formatted, and only the elements necessary for proposal generation are extracted and stored in the database.

[0439] Step 2:

[0440] The server performs natural language processing (NLP) on the stored data to analyze important keywords and requirements for proposal preparation. This analysis allows for an initial evaluation of the project, determining whether a proposal is feasible and identifying the actual products or services needed.

[0441] Step 3:

[0442] The server automatically constructs proposals by referencing successful patterns and historical data from similar past projects. AI analyzes the proposals and selects the most suitable products and services. It also automatically calculates estimates based on the proposed content.

[0443] Step 4:

[0444] The server automatically inputs proposal details and product information into a proposal template to create the proposal document. This document is generated in a consistent format and is designed to minimize errors.

[0445] Step 5:

[0446] Users review the generated proposal documents and estimates using their devices. They can modify and annotate the documents as needed. This is a crucial step in improving the accuracy of the proposal.

[0447] Step 6:

[0448] The server receives feedback from users and incorporates it into its machine learning algorithms. Based on this feedback, more accurate automated generation becomes possible for future suggestions, and the system continues to improve.

[0449] (Example 1)

[0450] 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."

[0451] The process of preparing proposals for bidding projects is generally manual and time-consuming, requiring considerable effort. Therefore, the quality and success rate of proposals significantly impact operational efficiency. However, traditional methods often fail to quickly gather and analyze necessary information and generate appropriate proposals, making proposal activities with limited resources difficult. To address these challenges, new methods are needed.

[0452] 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.

[0453] In this invention, the server includes means for automatically acquiring publicly announced information, means for analyzing the acquired data to identify the target of the proposal, and means for referencing past data sets to generate the optimal proposal content. This enables efficient collection and analysis of bidding information and the generation of optimized proposal content.

[0454] "Publicly announced information" refers to detailed information about bidding projects that government agencies and public organizations make publicly available.

[0455] "Acquiring" refers to the process of automatically gathering and storing necessary information.

[0456] "Data" refers to information that has been structured, stored, and made into a form that can be analyzed and used.

[0457] "Analysis" is the process of examining collected data and extracting important elements and trends.

[0458] "Proposal target" refers to the set of items and related information necessary for submitting a proposal for a bidding project.

[0459] "Past data sets" refer to a collection of information that has been collected previously, and serve as foundational data for analysis and proposals.

[0460] "Generating" refers to creating new content or results based on existing data or conditions.

[0461] "Cost calculation" is the process of determining the costs and prices included in the proposed content.

[0462] A "proposal document" is a document that outlines the proposed content and is presented to the recipient of the proposal.

[0463] A "user" is an individual or organization that uses this system to create, revise, and finalize proposals.

[0464] "Feedback" refers to the evaluations and suggestions for improvement that users provide regarding proposal activities and their results.

[0465] "Learning" is the process by which a machine improves its performance based on past data and feedback.

[0466] A "machine learning algorithm" is a program that allows a computer to learn from data and make decisions and predictions.

[0467] This system aims to streamline the proposal process for local government tenders and improve the success rate of proposals. The specific implementation of this system is described below.

[0468] The server's primary role is to automatically retrieve bidding information publicly available over the internet and store it in a database. This process utilizes specific APIs and web scraping techniques. Subsequently, the server analyzes the retrieved data using natural language processing (NLP) techniques. The analysis extracts important items from the text and uses them to identify potential bidders. The NLP techniques used include morphological analysis and text mining.

[0469] In generating proposals, the server references successful case studies from similar past projects and utilizes AI algorithms to create optimal proposals. This AI algorithm employs machine learning techniques to construct new proposals based on past success patterns. Furthermore, the server automatically calculates costs based on a pre-configured model and automatically generates proposal documents. These documents are automatically populated into templates, ensuring consistency and accuracy in the proposals.

[0470] Users operating the terminal can review the generated proposal document and make corrections or annotations as needed. Afterward, user feedback is entered into the server, which uses a machine learning algorithm to learn from it and utilize it to improve future proposals. This iterative process allows the system to continuously improve the quality of its proposals.

[0471] As a concrete example, consider a case where a local government conducts a tender for the introduction of a new IT system. The server extracts relevant technical requirements and budget information from the public notice and proposes the optimal solution. This proposal, based on past success stories, is automatically generated, and the user submits the proposal document after final review and adjustments. This system improves the quality of proposals and the efficiency of operations.

[0472] An example of a prompt for a generative AI model might be the question, "Please provide the necessary conditions and success stories for making the best proposal regarding IT system implementation projects for local governments."

[0473] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0474] Step 1:

[0475] The server automatically retrieves bidding information publicly available over the internet. Specifically, it uses APIs and web scraping techniques to periodically access the databases of various organizations and extract the necessary information. Inputs include the URL of the target website and API parameter information. Outputs include structuring the collected bidding data in JSON or XML format and saving it to storage.

[0476] Step 2:

[0477] Based on the acquired data, the server performs data analysis using natural language processing (NLP) techniques. This analysis uses morphological analysis tools to extract important items from the text data. The input is the structured data saved in Step 1. The output is a list of items and keywords necessary for the proposal. In addition, specific actions such as information filtering and tagging of important items are performed.

[0478] Step 3:

[0479] The server searches for similar cases from past data sets and uses AI algorithms to generate optimal proposals. Inputs include the item list organized in Step 2 and past case data. The output is an automatically generated draft proposal by the AI. At this stage, the AI ​​model has learned past success patterns, and this knowledge is reflected in the proposal. Specific actions include structural design of the proposal and evaluation of success factors.

[0480] Step 4:

[0481] Based on the generated proposal content, the server automatically calculates the estimate and generates the proposal document. The inputs are the proposal content and pricing model obtained in step 3. The output is a completed proposal document including the estimate. Specific operations include inputting information into a template and calculating costs. This ensures a consistent and accurate proposal document.

[0482] Step 5:

[0483] The user operating the terminal reviews the generated proposal document and makes corrections and annotations as needed. The input is the proposal document generated in step 4. The output is the final version of the proposal document, modified and added by the user. Specific actions include reviewing the document and entering additional information.

[0484] Step 6:

[0485] After a user completes their proposal, feedback is input into the system, and the server learns from this using a machine learning algorithm. Input includes evaluation comments and success rate data regarding the proposal results. Output is the learning results reflected in the AI ​​model, improving future proposals. Specific actions include collecting and analyzing feedback data and subsequently adjusting the AI ​​model. This continuous learning process ensures that the system's proposal accuracy continues to improve.

[0486] (Application Example 1)

[0487] 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."

[0488] There is a need to streamline the proposal process for local government bidding projects and improve the accuracy and success rate of proposals. However, conventional methods require a great deal of time and effort for information gathering and analysis, and it is difficult to quickly generate optimal proposal content. Furthermore, there is insufficient technology to effectively utilize user feedback and continuously improve proposal content. To solve these problems, it is necessary to develop a system that realizes an efficient and highly accurate proposal process.

[0489] 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.

[0490] In this invention, the server includes a device for automatically aggregating information from public information sources, a device for processing the aggregated information to identify project targets, and a device for referencing historical data to create optimized proposal content. This streamlines the entire process from information gathering to proposal content generation and proposal quality improvement, making it possible to quickly generate highly accurate proposals.

[0491] "Official sources of information" refer to official information released by local governments, government agencies, etc.

[0492] A "device for automatically aggregating information" is a device that has the function of automatically collecting and organizing necessary information.

[0493] A "device for identifying project targets" is a device that analyzes collected information to select data related to specific cases or projects.

[0494] "Historical data" refers to a collection of information about proposals and projects accumulated to date.

[0495] A "device for generating optimized proposals" is a device that utilizes accumulated data to automatically generate the most effective proposals.

[0496] A "device that learns from user feedback and improves its suggestions" is a device that incorporates user feedback to improve the system's ability to make suggestions.

[0497] "Mobile terminal or information display device" refers to a portable electronic device or a device that visually displays information, used by a user to view and manipulate information.

[0498] The system that realizes this application example includes a process that automatically aggregates necessary information from public sources, identifies project targets, generates optimized proposals, and improves the proposals based on user feedback.

[0499] The server periodically collects public information via the internet and stores it in a database. It utilizes web scraping techniques to structure and store this information. Additionally, it uses SpaCy as a natural language processing engine to extract important project items from text data.

[0500] This extracted data is analyzed using a machine learning algorithm based on TensorFlow, and optimal suggestions are generated based on historical data. The generated suggestions can be visually reviewed and modified by the user on mobile devices such as smartphones and smart glasses. This enables efficient and highly accurate suggestions.

[0501] For example, if a local government is undertaking a project to install a new lighting system, this system will automatically suggest the most suitable products and service providers based on budget and technical requirements.

[0502] As an example of a prompt, you can give instructions to the generating AI model in the form of, "Generate the best proposal for the latest smart city lighting system bidding. Requirements are high efficiency, low maintenance, and within budget."

[0503] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0504] Step 1:

[0505] The server automatically collects necessary information from public sources using web scraping techniques. The input is a list of URLs of public sources, and the output is data stored in a structured format. At this stage, the server categorizes the information and stores it in a database.

[0506] Step 2:

[0507] The server uses SpaCy, a natural language processing engine, to analyze the stored data. The input is the text data collected in step 1, and the output is a list of important items and keywords. Through this analysis, the server extracts requirements and conditions related to the project.

[0508] Step 3:

[0509] The server uses the analysis results to refer to historical data and generates optimal suggestions using a machine learning algorithm with TensorFlow. The input is the list of key items obtained in step 2 and historical data, and the output is the suggestions. The server analyzes successful patterns and creates suggestions with high accuracy.

[0510] Step 4:

[0511] The terminal provides the user with the generated suggestions. The input is the suggestions generated on the server, and the output is a display screen for the user. The terminal provides an interface that allows the user to intuitively review and modify the suggestions through an application on their mobile device.

[0512] Step 5:

[0513] The user reviews the proposal and adds any necessary corrections or annotations. The input is the proposal displayed on the device, and the output is the revised proposal. At this stage, user feedback is collected and used to improve future proposals.

[0514] Step 6:

[0515] The server collects user feedback and updates its machine learning algorithm to improve the accuracy of its suggestions. The input is user feedback information, and the output is the updated algorithm. This improves the performance of the generative AI model and the quality of future suggestions.

[0516] 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.

[0517] This invention is implemented as a system that integrates an emotion engine to streamline the proposal process for local government tenders and further improve the quality of proposals. Its main components include data collection, analysis, proposal generation, emotion evaluation, and user feedback.

[0518] First, the server automatically collects bidding information via the internet. This process analyzes public notices from local governments and saves the content in the format required for proposals. By using natural language processing technology, important items and requirements are extracted, and the basic materials for proposals are generated.

[0519] Next, past project data is compared to structure the proposal. Here, an AI algorithm works to identify the combination of products and services that best matches the user's needs. Furthermore, the data obtained during this process is used to automatically calculate an estimate, which is then incorporated into the proposal document.

[0520] The server uses an emotion engine to analyze emotional information extracted through user input and interactions. This emotional information is used to evaluate the potential impression that the proposal will have on the user and to adjust the proposal content and expression based on the results. For example, the wording and design within the proposal document are optimized according to the target user's expectations and preferences.

[0521] Users can review the generated proposal documents on their devices, and, while also viewing the evaluation results from the sentiment engine, can make adjustments and revisions as needed. During this process, user feedback is input into the system, and machine learning algorithms on the server process it. This feedback helps improve the system's subsequent proposals, allowing the system to evolve and produce more refined proposals.

[0522] For example, if a local government is conducting a bidding process for a regional tourism promotion project, the server collects and analyzes public information related to tourism-related products and services, and uses an emotion engine to determine the proposal style that the user expects. A proposal created based on these results is submitted, increasing its influence on potential clients and thus increasing the likelihood of winning the bid.

[0523] The following describes the processing flow.

[0524] Step 1:

[0525] The server accesses official local government bidding information websites and related databases to automatically collect new bidding announcements. The collected data is formatted and then stored in an internal database.

[0526] Step 2:

[0527] The server applies natural language processing (NLP) to the collected public information to analyze important keywords and requirements. Based on these analysis results, it identifies the most suitable products and services for proposal.

[0528] Step 3:

[0529] The server references past bidding data and uses an AI algorithm to analyze successful patterns in similar cases. This analysis determines the best configuration to apply to the generated proposal.

[0530] Step 4:

[0531] The server automatically calculates an estimate using the configured pricing model based on the proposed content. The calculation results are reflected in the proposal document, ensuring an economical proposal.

[0532] Step 5:

[0533] The server uses an emotion engine to analyze the user's past activity history and input data to estimate the user's emotional state. Based on this emotional information, it adjusts the presentation and wording of suggestions, optimizing them to expressions that the user will prefer.

[0534] Step 6:

[0535] Users review the generated proposals and quotes using their devices. They then make adjustments and revisions to the materials as needed, taking into account the evaluation results from the sentiment engine.

[0536] Step 7:

[0537] The server receives feedback from users and uses machine learning algorithms to improve the accuracy of its suggestions. This feedback loop allows the system to continuously improve and maintain its ability to generate highly accurate suggestion materials.

[0538] (Example 2)

[0539] 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."

[0540] In modern proposal development, gathering and analyzing information on bidding projects is often time-consuming and inefficient. Furthermore, it is difficult to accurately grasp the content and provide unique value in constructing proposals. Additionally, the inability to effectively utilize user feedback makes it challenging to improve the quality of proposals.

[0541] 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.

[0542] In this invention, the server includes means for automatically collecting information obtained from public institutions, means for analyzing the collected information to identify the target of the proposal, means for generating appropriate proposal content using past history, means for automatically calculating fees, means for automatically creating proposal documents, means for learning user feedback to improve the proposal content, and means for analyzing sentiment information to adjust the proposal content. This makes it possible to create efficient and precise bid proposals.

[0543] "Means of automatically collecting information obtained from public institutions" refers to a function or mechanism for automatically obtaining bidding-related information published by administrative agencies and local governments from the internet.

[0544] "Means for analyzing the collected information to identify the target of the proposal" refers to techniques for analyzing the collected information and clarifying the specific requirements and needs that should be the target of the proposal.

[0545] "Means for generating appropriate proposals using past history" refers to a method or process for generating new and effective proposals based on previously recorded information.

[0546] "Method for automatically calculating fees" refers to a system for automatically calculating costs based on the proposed content.

[0547] "Methods for automatically generating proposal documents" refers to a function that mechanically generates documents for proposals by combining the necessary information.

[0548] "Methods for improving proposals by learning from user feedback" refers to a learning process that uses feedback information provided by users to improve the quality of proposals.

[0549] "Methods for analyzing emotional information and adjusting proposal content" refers to technologies that analyze emotional information obtained from users and optimize the content and expression of proposals based on the results.

[0550] This invention aims to create a system that streamlines the proposal process for local government bidding projects and improves the quality of those proposals. An embodiment of this system is described below.

[0551] The server automatically collects necessary bidding information from public institution websites. This process uses web crawling technology, specifically leveraging software such as BeautifulSoup and Selenium. The collected information is stored in a database and used as the basis for analysis.

[0552] Next, the server analyzes the collected information using natural language processing techniques to identify items that should be proposed. Libraries such as spaCy and NLTK are often used for language processing. This clarifies important conditions and needs.

[0553] Furthermore, the server references past proposal data and uses an AI algorithm to generate the most suitable proposal for the current project. In this process, machine learning libraries such as Scikit-learn and TensorFlow are used to combine products and services according to the user's needs.

[0554] The server also has a function that automatically calculates the price based on the generated proposal. The calculation results of the estimate are reflected in the proposal document.

[0555] After the proposal document is created, users evaluate the impression the proposal gives through an emotion engine. Sentiment analysis tools such as TextBlob and VADER are used, and the wording and design are optimized based on this evaluation.

[0556] Users review the generated proposal materials and evaluation results on their devices and make adjustments to the materials as needed. User feedback is entered into the system, which is processed by a server using machine learning algorithms, and the feedback is used to improve future proposals.

[0557] As a concrete example, when a local government is conducting a bidding process for a regional tourism promotion project, the server collects tourism-related information and generates appropriate proposals. An example of a prompt message might be, "Please create a proposal document for a tourism promotion project. The target audience is assumed to be families." When this prompt is input into the AI ​​model, a specific and detailed proposal is generated.

[0558] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0559] Step 1:

[0560] The server automatically collects bidding information from public institution websites. It obtains the necessary URLs and queries as input and uses a web crawler to download this information. Specifically, it uses BeautifulSoup or Selenium to parse HTML data and extract the relevant bidding information in text format. The output of this process is a dataset of organized public notices.

[0561] Step 2:

[0562] The server analyzes the collected bid information using natural language processing technology. Text data is provided as input, and important keywords and requirements are extracted from the text using libraries such as spaCy and NLTK. This organizes and concretizes the bid requirements. The output of this process is a list of key items to be proposed.

[0563] Step 3:

[0564] The server references past proposal data and uses an AI algorithm to generate optimal proposals. Historical data and key items obtained in step 2 are used as input. Analysis is performed using Scikit-learn and TensorFlow to select products and services that meet the user's needs. The output of this process is a list of products and services included in the proposal document.

[0565] Step 4:

[0566] The server automatically calculates the price based on the proposed content. It uses the cost information of the goods and services selected in Step 3 as input and applies a calculation logic to determine the price. This calculation result is reflected in the proposal document. The output is the estimated price.

[0567] Step 5:

[0568] The user reviews the proposal document generated on their device and obtains evaluation results from the sentiment engine. Inputs include the proposal document and the user's past operation logs and feedback. Sentiment analysis and evaluation are performed using TextBlob and VADER. The output is feedback regarding the impression of the proposal.

[0569] Step 6:

[0570] Users adjust their proposal documents as needed based on evaluation results and feedback. They edit the proposal document on their terminal and input improvements. This improves the quality of the proposal. The output of this process is the revised final proposal document.

[0571] Step 7:

[0572] The server processes user feedback using a machine learning algorithm to improve the suggestions. User feedback data is used as input. The learning algorithm automatically improves the accuracy of the suggestions and incorporates the feedback results into the next suggestions. The output of this process is the improved suggestion generation process.

[0573] (Application Example 2)

[0574] 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."

[0575] In today's information-saturated world, accurately analyzing information and quickly providing optimal suggestions is crucial. However, conventional systems offer uniform suggestions to users, lacking sufficient customization to address individual user emotions and needs. Furthermore, the inability to effectively utilize user feedback limits the improvement of suggestion accuracy. There is a need for a system that can solve these problems and enable more accurate and personalized suggestions.

[0576] 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.

[0577] In this invention, the server includes means for automatically collecting information, means for analyzing and identifying targets, means for providing a user interface, and means for analyzing emotions and adjusting the suggestion style. This enables highly accurate and personalized suggestions that meet the individual needs and emotions of the user.

[0578] "Means for automatically collecting publicly available information" refers to systems and processes that mechanically collect information published on the internet and aggregate it as usable data.

[0579] "Means of analysis to identify targets" refers to systems and algorithms for analyzing collected data and identifying the optimal target based on specific purposes or conditions.

[0580] "Means of generating optimal content by referring to past data" refers to technologies and processes that generate data and content suitable for a specific purpose by referring to existing historical information and related information.

[0581] "Methods for automatically calculating estimates" refer to systems and algorithms that automatically calculate costs and expenses based on collected data and generated content.

[0582] "Means of automatically generating documents" refer to systems and processes for automatically generating documents and reports suitable for specific purposes based on collected and analyzed data.

[0583] "Means of providing a user interface through a data terminal" refers to technologies and environments that provide an interface on an electronic device for users to manipulate information.

[0584] "Means for analyzing emotions and adjusting proposal style" refers to a system and algorithm for analyzing a user's emotional state and optimizing proposal content and presentation style based on the results.

[0585] "Means of learning from user feedback and improving content" refers to systems and algorithms that learn from opinions and evaluations provided by users and reflect them in future data generation and suggestions.

[0586] To implement this invention, the system must include the following components. First, the server automatically collects publicly available information from local governments and public organizations on the internet and stores it in a specified data format. This can be done using specific APIs or scraping tools. Then, natural language processing techniques are used to extract important information from the documents. For this process, for example, the OpenAI API or other NLP libraries are effective.

[0587] Next, the server compares the collected information by referencing past databases and generates optimal suggestions. Machine learning algorithms can be used here, and models can be built using frameworks such as TensorFlow or PyTorch.

[0588] The server then displays the suggestions on the user's device. The user interface is built using React Native and other cross-platform frameworks, making it intuitive and easy for users to use.

[0589] The server further utilizes an emotion analysis engine to collect and analyze emotional data from user feedback and actions. Based on this analysis, it personalizes the suggestions and style, resulting in the most suitable suggestions for the user.

[0590] Users input feedback on the screen, and this information is learned by the server and used to improve the accuracy of future suggestions. This process contributes to the evolution of the system through continuous learning and improvement.

[0591] For example, if a user is considering purchasing a new smartphone, the system will suggest smartphones with features and price ranges that are likely to interest the user, based on their past purchase history and recent browsing history. The emotion engine then customizes these suggestions to best suit the user's interests.

[0592] Examples of prompts to input into a generative AI model:

[0593] "When it comes to the latest smartphones, if users tend to be price-conscious, suggest products that have the features they are most interested in."

[0594] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0595] Step 1:

[0596] The server automatically collects publicly announced information from local governments and public institutions via the internet. The input is publicly available data from the web, and the output is records in a database converted into a specific format. It performs operations such as formatting and storing information obtained from data scraping tools and APIs. Filtering based on date and keywords is performed during this process.

[0597] Step 2:

[0598] The server analyzes the collected data using natural language processing (NLP) techniques to extract important items and requirements. The input is the formalized data obtained in step 1, and the output is a list of key information extracted from the document. This process utilizes an NLP library to identify important elements while scrutinizing the content of the information.

[0599] Step 3:

[0600] The server generates optimal suggestions by referencing a historical database. The input is the list of key information obtained in step 2, and the output is a summary of the suggestions. A machine learning algorithm is applied to select the most effective content by referring to similar past cases.

[0601] Step 4:

[0602] The server automatically calculates the estimate and generates the proposal document. The input is the proposal content formulated in step 3, and the output is a text document containing comprehensive cost information. It performs calculations based on the pricing model and formats the proposal.

[0603] Step 5:

[0604] The server uses an emotion engine to collect emotional information from user feedback and actions. The input is user response data, and the output is a report of the emotional analysis results. The emotion engine analyzes the input data, identifies the user's emotional state, and suggests recommended adjustments.

[0605] Step 6:

[0606] The user reviews the proposed document on their device and enters feedback. The input is the generated proposal document, and the output is the information sent to the server as feedback. The user views the proposal through the UI and records their opinions as needed.

[0607] Step 7:

[0608] The server receives feedback from users and uses a machine learning algorithm to learn and improve its suggestions. The input is the feedback data obtained in step 6, and the output is the improved accuracy of the next suggestion. The collected information is fed back into the model to make adjustments that improve the system's accuracy.

[0609] 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.

[0610] 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.

[0611] 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.

[0612] [Fourth Embodiment]

[0613] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0614] 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.

[0615] 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).

[0616] 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.

[0617] 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.

[0618] 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).

[0619] 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.

[0620] 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.

[0621] 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.

[0622] 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.

[0623] 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.

[0624] 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.

[0625] 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".

[0626] This invention is implemented as a system to streamline the proposal process for local government bidding projects and increase the success rate. The entire system is configured to generate optimal proposal content through the processes of data collection, analysis, proposal creation, and evaluation.

[0627] First, the server is responsible for automatically collecting bidding information announced by local governments and related organizations. It periodically retrieves new information via internet-based database access and stores it as structured data. During this process, unnecessary information is filtered out, and only the data necessary for creating proposals is stored.

[0628] Next, the collected data is analyzed using natural language processing (NLP) technology installed on the server. The analysis extracts the necessary items and requirements for the proposal, identifying appropriate products and services. This allows for an initial evaluation of the project and a decision on whether or not to proceed with the proposal.

[0629] In generating proposals, the server references data from similar past projects to select patterns and products with a high success rate. The proposals generated using AI algorithms then proceed to cost calculation, where the cost of the proposed items is calculated based on a pre-configured pricing model within the system.

[0630] The system then automatically generates the proposal document. Necessary information is automatically entered into the template, ensuring consistency and accuracy of the proposal. Users operating the terminal can review this proposal document and make corrections or annotations as needed.

[0631] Ultimately, once user feedback is input into the system, a machine learning algorithm built into the server learns from it and uses it to improve future suggestions. This loop allows the system to evolve and continuously improve the accuracy of its suggestions.

[0632] As a concrete example, if a local government puts up a tender for the introduction of a new IT system, the server extracts relevant technical requirements and budget information from the public notice and proposes the optimal combination of hardware and software. This proposal is automatically generated based on past success stories, and the user submits the proposal document after final review and adjustments. This process significantly improves the quality and efficiency of proposals.

[0633] The following describes the processing flow.

[0634] Step 1:

[0635] The server accesses an online database that provides local government bidding information and automatically collects new announcements on a regular basis. The collected data is formatted, and only the elements necessary for proposal generation are extracted and stored in the database.

[0636] Step 2:

[0637] The server performs natural language processing (NLP) on the stored data to analyze important keywords and requirements for proposal preparation. This analysis allows for an initial evaluation of the project, determining whether a proposal is feasible and identifying the actual products or services needed.

[0638] Step 3:

[0639] The server automatically constructs proposals by referencing successful patterns and historical data from similar past projects. AI analyzes the proposals and selects the most suitable products and services. It also automatically calculates estimates based on the proposed content.

[0640] Step 4:

[0641] The server automatically inputs proposal details and product information into a proposal template to create the proposal document. This document is generated in a consistent format and is designed to minimize errors.

[0642] Step 5:

[0643] Users review the generated proposal documents and estimates using their devices. They can modify and annotate the documents as needed. This is a crucial step in improving the accuracy of the proposal.

[0644] Step 6:

[0645] The server receives feedback from users and incorporates it into its machine learning algorithms. Based on this feedback, more accurate automated generation becomes possible for future suggestions, and the system continues to improve.

[0646] (Example 1)

[0647] 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".

[0648] The process of preparing proposals for bidding projects is generally manual and time-consuming, requiring considerable effort. Therefore, the quality and success rate of proposals significantly impact operational efficiency. However, traditional methods often fail to quickly gather and analyze necessary information and generate appropriate proposals, making proposal activities with limited resources difficult. To address these challenges, new methods are needed.

[0649] 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.

[0650] In this invention, the server includes means for automatically acquiring publicly announced information, means for analyzing the acquired data to identify the target of the proposal, and means for referencing past data sets to generate the optimal proposal content. This enables efficient collection and analysis of bidding information and the generation of optimized proposal content.

[0651] "Publicly announced information" refers to detailed information about bidding projects that government agencies and public organizations make publicly available.

[0652] "Acquiring" refers to the process of automatically gathering and storing necessary information.

[0653] "Data" refers to information that has been structured, stored, and made into a form that can be analyzed and used.

[0654] "Analysis" is the process of examining collected data and extracting important elements and trends.

[0655] "Proposal target" refers to the set of items and related information necessary for submitting a proposal for a bidding project.

[0656] "Past data sets" refer to a collection of information that has been collected previously, and serve as foundational data for analysis and proposals.

[0657] "Generating" refers to creating new content or results based on existing data or conditions.

[0658] "Cost calculation" is the process of determining the costs and prices included in the proposed content.

[0659] A "proposal document" is a document that outlines the proposed content and is presented to the recipient of the proposal.

[0660] A "user" is an individual or organization that uses this system to create, revise, and finalize proposals.

[0661] "Feedback" refers to the evaluations and suggestions for improvement that users provide regarding proposal activities and their results.

[0662] "Learning" is the process by which a machine improves its performance based on past data and feedback.

[0663] A "machine learning algorithm" is a program that allows a computer to learn from data and make decisions and predictions.

[0664] This system aims to streamline the proposal process for local government tenders and improve the success rate of proposals. The specific implementation of this system is described below.

[0665] The server's primary role is to automatically retrieve bidding information publicly available over the internet and store it in a database. This process utilizes specific APIs and web scraping techniques. Subsequently, the server analyzes the retrieved data using natural language processing (NLP) techniques. The analysis extracts important items from the text and uses them to identify potential bidders. The NLP techniques used include morphological analysis and text mining.

[0666] In generating proposals, the server references successful case studies from similar past projects and utilizes AI algorithms to create optimal proposals. This AI algorithm employs machine learning techniques to construct new proposals based on past success patterns. Furthermore, the server automatically calculates costs based on a pre-configured model and automatically generates proposal documents. These documents are automatically populated into templates, ensuring consistency and accuracy in the proposals.

[0667] Users operating the terminal can review the generated proposal document and make corrections or annotations as needed. Afterward, user feedback is entered into the server, which uses a machine learning algorithm to learn from it and utilize it to improve future proposals. This iterative process allows the system to continuously improve the quality of its proposals.

[0668] As a concrete example, consider a case where a local government conducts a tender for the introduction of a new IT system. The server extracts relevant technical requirements and budget information from the public notice and proposes the optimal solution. This proposal, based on past success stories, is automatically generated, and the user submits the proposal document after final review and adjustments. This system improves the quality of proposals and the efficiency of operations.

[0669] An example of a prompt for a generative AI model might be the question, "Please provide the necessary conditions and success stories for making the best proposal regarding IT system implementation projects for local governments."

[0670] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0671] Step 1:

[0672] The server automatically retrieves bidding information publicly available over the internet. Specifically, it uses APIs and web scraping techniques to periodically access the databases of various organizations and extract the necessary information. Inputs include the URL of the target website and API parameter information. Outputs include structuring the collected bidding data in JSON or XML format and saving it to storage.

[0673] Step 2:

[0674] Based on the acquired data, the server performs data analysis using natural language processing (NLP) techniques. This analysis uses morphological analysis tools to extract important items from the text data. The input is the structured data saved in Step 1. The output is a list of items and keywords necessary for the proposal. In addition, specific actions such as information filtering and tagging of important items are performed.

[0675] Step 3:

[0676] The server searches for similar cases from past data sets and uses AI algorithms to generate optimal proposals. Inputs include the item list organized in Step 2 and past case data. The output is an automatically generated draft proposal by the AI. At this stage, the AI ​​model has learned past success patterns, and this knowledge is reflected in the proposal. Specific actions include structural design of the proposal and evaluation of success factors.

[0677] Step 4:

[0678] Based on the generated proposal content, the server automatically calculates the estimate and generates the proposal document. The inputs are the proposal content and pricing model obtained in step 3. The output is a completed proposal document including the estimate. Specific operations include inputting information into a template and calculating costs. This ensures a consistent and accurate proposal document.

[0679] Step 5:

[0680] The user operating the terminal reviews the generated proposal document and makes corrections and annotations as needed. The input is the proposal document generated in step 4. The output is the final version of the proposal document, modified and added by the user. Specific actions include reviewing the document and entering additional information.

[0681] Step 6:

[0682] After a user completes their proposal, feedback is input into the system, and the server learns from this using a machine learning algorithm. Input includes evaluation comments and success rate data regarding the proposal results. Output is the learning results reflected in the AI ​​model, improving future proposals. Specific actions include collecting and analyzing feedback data and subsequently adjusting the AI ​​model. This continuous learning process ensures that the system's proposal accuracy continues to improve.

[0683] (Application Example 1)

[0684] 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".

[0685] There is a need to streamline the proposal process for local government bidding projects and improve the accuracy and success rate of proposals. However, conventional methods require a great deal of time and effort for information gathering and analysis, and it is difficult to quickly generate optimal proposal content. Furthermore, there is insufficient technology to effectively utilize user feedback and continuously improve proposal content. To solve these problems, it is necessary to develop a system that realizes an efficient and highly accurate proposal process.

[0686] 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.

[0687] In this invention, the server includes a device for automatically aggregating information from public information sources, a device for processing the aggregated information to identify project targets, and a device for referencing historical data to create optimized proposal content. This streamlines the entire process from information gathering to proposal content generation and proposal quality improvement, making it possible to quickly generate highly accurate proposals.

[0688] "Official sources of information" refer to official information released by local governments, government agencies, etc.

[0689] A "device for automatically aggregating information" is a device that has the function of automatically collecting and organizing necessary information.

[0690] A "device for identifying project targets" is a device that analyzes collected information to select data related to specific cases or projects.

[0691] "Historical data" refers to a collection of information about proposals and projects accumulated to date.

[0692] A "device for generating optimized proposals" is a device that utilizes accumulated data to automatically generate the most effective proposals.

[0693] A "device that learns from user feedback and improves its suggestions" is a device that incorporates user feedback to improve the system's ability to make suggestions.

[0694] "Mobile terminal or information display device" refers to a portable electronic device or a device that visually displays information, used by a user to view and manipulate information.

[0695] The system that realizes this application example includes a process that automatically aggregates necessary information from public sources, identifies project targets, generates optimized proposals, and improves the proposals based on user feedback.

[0696] The server periodically collects public information via the internet and stores it in a database. It utilizes web scraping techniques to structure and store this information. Additionally, it uses SpaCy as a natural language processing engine to extract important project items from text data.

[0697] This extracted data is analyzed using a machine learning algorithm based on TensorFlow, and optimal suggestions are generated based on historical data. The generated suggestions can be visually reviewed and modified by the user on mobile devices such as smartphones and smart glasses. This enables efficient and highly accurate suggestions.

[0698] For example, if a local government is undertaking a project to install a new lighting system, this system will automatically suggest the most suitable products and service providers based on budget and technical requirements.

[0699] As an example of a prompt, you can give instructions to the generating AI model in the form of, "Generate the best proposal for the latest smart city lighting system bidding. Requirements are high efficiency, low maintenance, and within budget."

[0700] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0701] Step 1:

[0702] The server automatically collects necessary information from public sources using web scraping techniques. The input is a list of URLs of public sources, and the output is data stored in a structured format. At this stage, the server categorizes the information and stores it in a database.

[0703] Step 2:

[0704] The server uses SpaCy, a natural language processing engine, to analyze the stored data. The input is the text data collected in step 1, and the output is a list of important items and keywords. Through this analysis, the server extracts requirements and conditions related to the project.

[0705] Step 3:

[0706] The server uses the analysis results to refer to historical data and generates optimal suggestions using a machine learning algorithm with TensorFlow. The input is the list of key items obtained in step 2 and historical data, and the output is the suggestions. The server analyzes successful patterns and creates suggestions with high accuracy.

[0707] Step 4:

[0708] The terminal provides the user with the generated suggestions. The input is the suggestions generated on the server, and the output is a display screen for the user. The terminal provides an interface that allows the user to intuitively review and modify the suggestions through an application on their mobile device.

[0709] Step 5:

[0710] The user reviews the proposal and adds any necessary corrections or annotations. The input is the proposal displayed on the device, and the output is the revised proposal. At this stage, user feedback is collected and used to improve future proposals.

[0711] Step 6:

[0712] The server collects user feedback and updates its machine learning algorithm to improve the accuracy of its suggestions. The input is user feedback information, and the output is the updated algorithm. This improves the performance of the generative AI model and the quality of future suggestions.

[0713] 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.

[0714] This invention is implemented as a system that integrates an emotion engine to streamline the proposal process for local government tenders and further improve the quality of proposals. Its main components include data collection, analysis, proposal generation, emotion evaluation, and user feedback.

[0715] First, the server automatically collects bidding information via the internet. This process analyzes public notices from local governments and saves the content in the format required for proposals. By using natural language processing technology, important items and requirements are extracted, and the basic materials for proposals are generated.

[0716] Next, past project data is compared to structure the proposal. Here, an AI algorithm works to identify the combination of products and services that best matches the user's needs. Furthermore, the data obtained during this process is used to automatically calculate an estimate, which is then incorporated into the proposal document.

[0717] The server uses an emotion engine to analyze emotional information extracted through user input and interactions. This emotional information is used to evaluate the potential impression that the proposal will have on the user and to adjust the proposal content and expression based on the results. For example, the wording and design within the proposal document are optimized according to the target user's expectations and preferences.

[0718] Users can review the generated proposal documents on their devices, and, while also viewing the evaluation results from the sentiment engine, can make adjustments and revisions as needed. During this process, user feedback is input into the system, and machine learning algorithms on the server process it. This feedback helps improve the system's subsequent proposals, allowing the system to evolve and produce more refined proposals.

[0719] For example, if a local government is conducting a bidding process for a regional tourism promotion project, the server collects and analyzes public information related to tourism-related products and services, and uses an emotion engine to determine the proposal style that the user expects. A proposal created based on these results is submitted, increasing its influence on potential clients and thus increasing the likelihood of winning the bid.

[0720] The following describes the processing flow.

[0721] Step 1:

[0722] The server accesses official local government bidding information websites and related databases to automatically collect new bidding announcements. The collected data is formatted and then stored in an internal database.

[0723] Step 2:

[0724] The server applies natural language processing (NLP) to the collected public information to analyze important keywords and requirements. Based on these analysis results, it identifies the most suitable products and services for proposal.

[0725] Step 3:

[0726] The server references past bidding data and uses an AI algorithm to analyze successful patterns in similar cases. This analysis determines the best configuration to apply to the generated proposal.

[0727] Step 4:

[0728] The server automatically calculates an estimate using the configured pricing model based on the proposed content. The calculation results are reflected in the proposal document, ensuring an economical proposal.

[0729] Step 5:

[0730] The server uses an emotion engine to analyze the user's past activity history and input data to estimate the user's emotional state. Based on this emotional information, it adjusts the presentation and wording of suggestions, optimizing them to expressions that the user will prefer.

[0731] Step 6:

[0732] Users review the generated proposals and quotes using their devices. They then make adjustments and revisions to the materials as needed, taking into account the evaluation results from the sentiment engine.

[0733] Step 7:

[0734] The server receives feedback from users and uses machine learning algorithms to improve the accuracy of its suggestions. This feedback loop allows the system to continuously improve and maintain its ability to generate highly accurate suggestion materials.

[0735] (Example 2)

[0736] 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".

[0737] In modern proposal development, gathering and analyzing information on bidding projects is often time-consuming and inefficient. Furthermore, it is difficult to accurately grasp the content and provide unique value in constructing proposals. Additionally, the inability to effectively utilize user feedback makes it challenging to improve the quality of proposals.

[0738] 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.

[0739] In this invention, the server includes means for automatically collecting information obtained from public institutions, means for analyzing the collected information to identify the target of the proposal, means for generating appropriate proposal content using past history, means for automatically calculating fees, means for automatically creating proposal documents, means for learning user feedback to improve the proposal content, and means for analyzing sentiment information to adjust the proposal content. This makes it possible to create efficient and precise bid proposals.

[0740] "Means of automatically collecting information obtained from public institutions" refers to a function or mechanism for automatically obtaining bidding-related information published by administrative agencies and local governments from the internet.

[0741] "Means for analyzing the collected information to identify the target of the proposal" refers to techniques for analyzing the collected information and clarifying the specific requirements and needs that should be the target of the proposal.

[0742] "Means for generating appropriate proposals using past history" refers to a method or process for generating new and effective proposals based on previously recorded information.

[0743] "Method for automatically calculating fees" refers to a system for automatically calculating costs based on the proposed content.

[0744] "Methods for automatically generating proposal documents" refers to a function that mechanically generates documents for proposals by combining the necessary information.

[0745] "Methods for improving proposals by learning from user feedback" refers to a learning process that uses feedback information provided by users to improve the quality of proposals.

[0746] "Methods for analyzing emotional information and adjusting proposal content" refers to technologies that analyze emotional information obtained from users and optimize the content and expression of proposals based on the results.

[0747] This invention aims to create a system that streamlines the proposal process for local government bidding projects and improves the quality of those proposals. An embodiment of this system is described below.

[0748] The server automatically collects necessary bidding information from public institution websites. This process uses web crawling technology, specifically leveraging software such as BeautifulSoup and Selenium. The collected information is stored in a database and used as the basis for analysis.

[0749] Next, the server analyzes the collected information using natural language processing techniques to identify items that should be proposed. Libraries such as spaCy and NLTK are often used for language processing. This clarifies important conditions and needs.

[0750] Furthermore, the server references past proposal data and uses an AI algorithm to generate the most suitable proposal for the current project. In this process, machine learning libraries such as Scikit-learn and TensorFlow are used to combine products and services according to the user's needs.

[0751] The server also has a function that automatically calculates the price based on the generated proposal. The calculation results of the estimate are reflected in the proposal document.

[0752] After the proposal document is created, users evaluate the impression the proposal gives through an emotion engine. Sentiment analysis tools such as TextBlob and VADER are used, and the wording and design are optimized based on this evaluation.

[0753] Users review the generated proposal materials and evaluation results on their devices and make adjustments to the materials as needed. User feedback is entered into the system, which is processed by a server using machine learning algorithms, and the feedback is used to improve future proposals.

[0754] As a concrete example, when a local government is conducting a bidding process for a regional tourism promotion project, the server collects tourism-related information and generates appropriate proposals. An example of a prompt message might be, "Please create a proposal document for a tourism promotion project. The target audience is assumed to be families." When this prompt is input into the AI ​​model, a specific and detailed proposal is generated.

[0755] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0756] Step 1:

[0757] The server automatically collects bidding information from public institution websites. It obtains the necessary URLs and queries as input and uses a web crawler to download this information. Specifically, it uses BeautifulSoup or Selenium to parse HTML data and extract the relevant bidding information in text format. The output of this process is a dataset of organized public notices.

[0758] Step 2:

[0759] The server analyzes the collected bid information using natural language processing technology. Text data is provided as input, and important keywords and requirements are extracted from the text using libraries such as spaCy and NLTK. This organizes and concretizes the bid requirements. The output of this process is a list of key items to be proposed.

[0760] Step 3:

[0761] The server references past proposal data and uses an AI algorithm to generate optimal proposals. Historical data and key items obtained in step 2 are used as input. Analysis is performed using Scikit-learn and TensorFlow to select products and services that meet the user's needs. The output of this process is a list of products and services included in the proposal document.

[0762] Step 4:

[0763] The server automatically calculates the price based on the proposed content. It uses the cost information of the goods and services selected in Step 3 as input and applies a calculation logic to determine the price. This calculation result is reflected in the proposal document. The output is the estimated price.

[0764] Step 5:

[0765] The user reviews the proposal document generated on their device and obtains evaluation results from the sentiment engine. Inputs include the proposal document and the user's past operation logs and feedback. Sentiment analysis and evaluation are performed using TextBlob and VADER. The output is feedback regarding the impression of the proposal.

[0766] Step 6:

[0767] Users adjust their proposal documents as needed based on evaluation results and feedback. They edit the proposal document on their terminal and input improvements. This improves the quality of the proposal. The output of this process is the revised final proposal document.

[0768] Step 7:

[0769] The server processes user feedback using a machine learning algorithm to improve the suggestions. User feedback data is used as input. The learning algorithm automatically improves the accuracy of the suggestions and incorporates the feedback results into the next suggestions. The output of this process is the improved suggestion generation process.

[0770] (Application Example 2)

[0771] 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".

[0772] In today's information-saturated world, accurately analyzing information and quickly providing optimal suggestions is crucial. However, conventional systems offer uniform suggestions to users, lacking sufficient customization to address individual user emotions and needs. Furthermore, the inability to effectively utilize user feedback limits the improvement of suggestion accuracy. There is a need for a system that can solve these problems and enable more accurate and personalized suggestions.

[0773] 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.

[0774] In this invention, the server includes means for automatically collecting information, means for analyzing and identifying targets, means for providing a user interface, and means for analyzing emotions and adjusting the suggestion style. This enables highly accurate and personalized suggestions that meet the individual needs and emotions of the user.

[0775] "Means for automatically collecting publicly available information" refers to systems and processes that mechanically collect information published on the internet and aggregate it as usable data.

[0776] "Means of analysis to identify targets" refers to systems and algorithms for analyzing collected data and identifying the optimal target based on specific purposes or conditions.

[0777] "Means of generating optimal content by referring to past data" refers to technologies and processes that generate data and content suitable for a specific purpose by referring to existing historical information and related information.

[0778] "Methods for automatically calculating estimates" refer to systems and algorithms that automatically calculate costs and expenses based on collected data and generated content.

[0779] "Means of automatically generating documents" refer to systems and processes for automatically generating documents and reports suitable for specific purposes based on collected and analyzed data.

[0780] "Means of providing a user interface through a data terminal" refers to technologies and environments that provide an interface on an electronic device for users to manipulate information.

[0781] "Means for analyzing emotions and adjusting proposal style" refers to a system and algorithm for analyzing a user's emotional state and optimizing proposal content and presentation style based on the results.

[0782] "Means of learning from user feedback and improving content" refers to systems and algorithms that learn from opinions and evaluations provided by users and reflect them in future data generation and suggestions.

[0783] To implement this invention, the system must include the following components. First, the server automatically collects publicly available information from local governments and public organizations on the internet and stores it in a specified data format. This can be done using specific APIs or scraping tools. Then, natural language processing techniques are used to extract important information from the documents. For this process, for example, the OpenAI API or other NLP libraries are effective.

[0784] Next, the server compares the collected information by referencing past databases and generates optimal suggestions. Machine learning algorithms can be used here, and models can be built using frameworks such as TensorFlow or PyTorch.

[0785] The server then displays the suggestions on the user's device. The user interface is built using React Native and other cross-platform frameworks, making it intuitive and easy for users to use.

[0786] The server further utilizes an emotion analysis engine to collect and analyze emotional data from user feedback and actions. Based on this analysis, it personalizes the suggestions and style, resulting in the most suitable suggestions for the user.

[0787] Users input feedback on the screen, and this information is learned by the server and used to improve the accuracy of future suggestions. This process contributes to the evolution of the system through continuous learning and improvement.

[0788] For example, if a user is considering purchasing a new smartphone, the system will suggest smartphones with features and price ranges that are likely to interest the user, based on their past purchase history and recent browsing history. The emotion engine then customizes these suggestions to best suit the user's interests.

[0789] Examples of prompts to input into a generative AI model:

[0790] "When it comes to the latest smartphones, if users tend to be price-conscious, suggest products that have the features they are most interested in."

[0791] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0792] Step 1:

[0793] The server automatically collects publicly announced information from local governments and public institutions via the internet. The input is publicly available data from the web, and the output is records in a database converted into a specific format. It performs operations such as formatting and storing information obtained from data scraping tools and APIs. Filtering based on date and keywords is performed during this process.

[0794] Step 2:

[0795] The server analyzes the collected data using natural language processing (NLP) techniques to extract important items and requirements. The input is the formalized data obtained in step 1, and the output is a list of key information extracted from the document. This process utilizes an NLP library to identify important elements while scrutinizing the content of the information.

[0796] Step 3:

[0797] The server generates optimal suggestions by referencing a historical database. The input is the list of key information obtained in step 2, and the output is a summary of the suggestions. A machine learning algorithm is applied to select the most effective content by referring to similar past cases.

[0798] Step 4:

[0799] The server automatically calculates the estimate and generates the proposal document. The input is the proposal content formulated in step 3, and the output is a text document containing comprehensive cost information. It performs calculations based on the pricing model and formats the proposal.

[0800] Step 5:

[0801] The server uses an emotion engine to collect emotional information from user feedback and actions. The input is user response data, and the output is a report of the emotional analysis results. The emotion engine analyzes the input data, identifies the user's emotional state, and suggests recommended adjustments.

[0802] Step 6:

[0803] The user reviews the proposed document on their device and enters feedback. The input is the generated proposal document, and the output is the information sent to the server as feedback. The user views the proposal through the UI and records their opinions as needed.

[0804] Step 7:

[0805] The server receives feedback from users and uses a machine learning algorithm to learn and improve its suggestions. The input is the feedback data obtained in step 6, and the output is the improved accuracy of the next suggestion. The collected information is fed back into the model to make adjustments that improve the system's accuracy.

[0806] 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.

[0807] 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.

[0808] 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.

[0809] 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.

[0810] 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.

[0811] 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.

[0812] 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.

[0813] 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.

[0814] 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."

[0815] 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.

[0816] 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.

[0817] 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.

[0818] 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.

[0819] 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.

[0820] 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.

[0821] 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.

[0822] 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.

[0823] 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.

[0824] 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.

[0825] 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.

[0826] 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.

[0827] The following is further disclosed regarding the embodiments described above.

[0828] (Claim 1)

[0829] A means of automatically collecting public information,

[0830] A means for analyzing the collected information to identify the target of the proposal,

[0831] A means of generating optimal proposals by referring to past data,

[0832] A method for automatically calculating estimates,

[0833] A method for automatically generating proposal documents,

[0834] A means of improving the proposed content by learning from user feedback,

[0835] A system that includes this.

[0836] (Claim 2)

[0837] The system according to claim 1, which uses natural language processing technology to extract important items from a document when generating the aforementioned proposed content.

[0838] (Claim 3)

[0839] The system according to claim 1, wherein the user feedback is used to improve the accuracy of the suggestions using a machine learning algorithm.

[0840] "Example 1"

[0841] (Claim 1)

[0842] A means of automatically acquiring public information,

[0843] A means for analyzing the acquired data to identify the proposed target,

[0844] A means of generating optimal proposals by referring to past data sets,

[0845] A means of automatically calculating costs,

[0846] A means of automatically generating proposal documents,

[0847] A means of improving the proposed content by learning from user feedback,

[0848] A system that includes this.

[0849] (Claim 2)

[0850] The system according to claim 1, which uses natural language processing technology to extract important elements from a document when generating the aforementioned proposed content.

[0851] (Claim 3)

[0852] The system according to claim 1, wherein the feedback from the user is used to improve the accuracy of the suggestions using a machine learning algorithm.

[0853] "Application Example 1"

[0854] (Claim 1)

[0855] A device for automatically aggregating information from public sources,

[0856] A device that processes the aggregated information and identifies the project target,

[0857] A device that generates optimized proposals by referring to past historical data,

[0858] A device that automatically calculates cost estimates,

[0859] A device that automatically creates proposal materials,

[0860] A device that learns from user feedback and improves its suggestions,

[0861] A device for visually confirming and modifying proposed content using a mobile terminal or information display device,

[0862] A system that includes this.

[0863] (Claim 2)

[0864] The system according to claim 1, which uses language processing technology to extract important elements from text information when generating the aforementioned proposed content.

[0865] (Claim 3)

[0866] The system according to claim 1, which uses the evaluations from the aforementioned users to improve the quality of the proposals using a learning algorithm.

[0867] "Example 2 of combining an emotion engine"

[0868] (Claim 1)

[0869] A means of automatically collecting information obtained from public institutions,

[0870] A means for analyzing the collected information to identify the target of the proposal,

[0871] A means of generating appropriate proposals using past history,

[0872] A method for automatically calculating the fee,

[0873] A method for automatically generating proposal documents,

[0874] A means of learning from user feedback and improving the proposed content,

[0875] A means of analyzing emotional information and adjusting the proposed content,

[0876] A system that includes this.

[0877] (Claim 2)

[0878] The system according to claim 1, which uses language processing technology to extract important information from a document when generating the aforementioned proposed content.

[0879] (Claim 3)

[0880] The system according to claim 1, wherein the user's feedback is used to improve the accuracy of the suggestions using machine learning.

[0881] "Application example 2 when combining with an emotional engine"

[0882] (Claim 1)

[0883] A means of automatically collecting public information,

[0884] A means for analyzing the collected information to identify the target,

[0885] A means of generating optimal content by referring to past data,

[0886] A method for automatically calculating estimates,

[0887] Methods for automatically creating documents,

[0888] A means of providing a user interface through a data terminal,

[0889] A means of analyzing human emotions and adjusting the suggestion style,

[0890] A means of learning from user feedback and improving the content,

[0891] A system that includes this.

[0892] (Claim 2)

[0893] The system according to claim 1, which uses natural language processing technology to extract important items from information when generating the aforementioned content.

[0894] (Claim 3)

[0895] The system according to claim 1, wherein the user feedback is used to improve accuracy using a machine learning algorithm. [Explanation of Symbols]

[0896] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A device for automatically aggregating information from public sources, A device that processes the aggregated information and identifies the project target, A device that generates optimized proposals by referring to past historical data, A device that automatically calculates cost estimates, A device that automatically creates proposal materials, A device that learns from user feedback and improves its suggestions, A device for visually confirming and modifying proposed content using a mobile terminal or information display device, A system that includes this.

2. The system according to claim 1, which uses language processing technology to extract important elements from text information when generating the aforementioned proposed content.

3. The system according to claim 1, which uses the evaluation from the aforementioned users to improve the quality of the proposal using a learning algorithm.

Images