system

Abstract

The system according to this embodiment aims to efficiently extract suitable bids from local governments and automatically generate proposals. [Solution] The system according to the embodiment comprises a recognition unit, an acquisition unit, an extraction unit, an adjustment unit, and a creation unit. The recognition unit recognizes the company's product information. The acquisition unit crawls publicly available information from each local government based on the information recognized by the recognition unit and acquires bidding project data. The extraction unit extracts projects that the company can propose based on the data acquired by the acquisition unit. The adjustment unit organizes the proposal content for the projects extracted by the extraction unit, and performs coordination with the relevant department and cost estimation. The creation unit, based on the proposal content organized by the adjustment unit, writes the proposal content in a format specified for each bidding project and creates a response document.

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 conventional technology, there is a problem that the process of efficiently extracting cases suitable for the company from the bidding cases of local governments and creating a proposal is complicated and time-consuming and labor-intensive.

[0005] The system according to the embodiment aims to efficiently extract bidding cases of local governments suitable for the company and automatically create a proposal.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a recognition unit, an acquisition unit, an extraction unit, an adjustment unit, and a creation unit. The recognition unit recognizes the company's product information. The acquisition unit crawls publicly available information from each local government based on the information recognized by the recognition unit and acquires bidding project data. The extraction unit extracts projects that the company can propose based on the data acquired by the acquisition unit. The adjustment unit organizes the proposal content for the projects extracted by the extraction unit, coordinates with the relevant departments, and performs cost estimations. The creation unit, based on the proposal content organized by the adjustment unit, writes the proposal content in a format specified for each bidding project and creates a response document. [Effects of the Invention]

[0007] The system according to this embodiment can efficiently extract suitable bids from local governments and automatically generate proposals. [Brief explanation of the drawing]

[0008] [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. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] 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 only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] As shown in FIG. 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.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 comprises a computer 36, a receiving 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 receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice 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 unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (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.

[0022] 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.

[0023] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 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.

[0025] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The AI ​​agent system according to an embodiment of the present invention is a system that, after understanding its own services and strengths, autonomously extracts projects that it can propose to from among the 1 million municipal bidding projects nationwide annually, compiles proposals, and submits them. First, this AI agent system receives input from the company's product information (such as proposals and specifications), and the AI ​​agent recognizes the company's services. Next, the AI ​​agent crawls publicly available information from each municipality and obtains bidding project data. Based on the acquired data, the AI ​​agent extracts projects that the company can propose to. For the extracted projects, the AI ​​agent organizes the proposal content and performs tasks such as coordinating with the relevant department and estimating costs. Furthermore, it writes the proposal content into a format specified for each bidding project and creates a response document. Based on the created response document, the AI ​​agent creates presentation materials and talk scripts and performs presentations as needed. Finally, it analyzes the reasons for success and failure from the bidding results and uses this information to improve future actions. For example, the AI ​​agent system recognizes the company's product information and crawls publicly available information from each municipality to obtain bidding project data. Next, the AI ​​agent system extracts projects that the company can propose based on the acquired data and organizes the proposal content. Furthermore, the AI ​​agent system coordinates with the relevant departments and performs cost estimations, writes the proposal content in the format specified for each bidding project, and creates a response document. Finally, the AI ​​agent system creates presentation materials and talk scripts based on the created response document and delivers a presentation as needed. In this way, the AI ​​agent system can efficiently handle bidding by reducing the enormous amount of time and effort required to find bidding projects and create response documents. Thus, the AI ​​agent system can recognize the company's product information, acquire bidding project data, extract projects that can be proposed, organize the proposal content, and create a response document.

[0029] The AI ​​agent system according to this embodiment comprises a recognition unit, an acquisition unit, an extraction unit, an adjustment unit, and a creation unit. The recognition unit recognizes the company's product information. This product information includes, but is not limited to, product information, service information, and technical information. The recognition unit recognizes product information using, for example, image recognition technology. The recognition unit can also recognize product information using text recognition technology. The recognition unit can also recognize product information using speech recognition technology. For example, the recognition unit recognizes an image of a product using image recognition technology and acquires product information. Text recognition technology is effective when product information is provided in text format, for example, to recognize the contents of a proposal or specification. Speech recognition technology is effective when product information is provided in speech format, for example, to recognize the contents of a presentation. Based on the information recognized by the recognition unit, the acquisition unit crawls publicly available information from each local government and acquires bidding data. Crawling is performed using, for example, a web crawler, but is not limited to this example. The acquisition unit acquires bidding data from the websites of each local government using, for example, a web crawler. Furthermore, the acquisition unit can also obtain bidding project data from each local government's database using APIs. The acquisition unit can also obtain bidding project data from web pages using scraping techniques. For example, the acquisition unit periodically visits each local government's website using a web crawler to obtain new bidding project data. APIs are a method of directly accessing databases provided by each local government; for example, the acquisition unit can obtain bidding project data in real time using APIs. Scraping techniques are a method of extracting data by analyzing the content of web pages; for example, the acquisition unit can obtain bidding project data from web pages using scraping techniques. The extraction unit extracts projects that the company can propose based on the data acquired by the acquisition unit. Proposable projects are extracted based on, for example, the size and type of the project, the conditions for the proposal, etc., but are not limited to these examples. The extraction unit can extract projects that can be proposed based on, for example, the size of the project. The extraction unit can also extract projects that can be proposed based on the type of project.The extraction unit can also extract projects that can be proposed based on the proposal conditions. For example, the extraction unit determines whether the scale of the project is within the company's capabilities and extracts projects that can be proposed. Project types include, for example, product provision, service provision, and technology provision, and the extraction unit extracts projects of the type that the company can handle. Proposal conditions include, for example, deadlines and budgets, and the extraction unit extracts projects with conditions that the company can handle. The coordination unit organizes the proposal content for the projects extracted by the extraction unit and performs coordination with the relevant departments and cost estimation. For example, the coordination unit holds meetings with the relevant departments to organize the proposal content. The coordination unit can also collect the necessary data to perform cost estimation. The coordination unit can also use project management tools to organize the proposal content. For example, the coordination unit examines the proposal content in detail through meetings with the relevant departments and makes necessary adjustments. Cost estimation is performed based on data such as material costs and labor costs, and the coordination unit collects this data and performs the estimation. Project management tools are effective for organizing proposals and managing progress. For example, the coordination department uses project management tools to organize proposals. The creation department, based on the proposals organized by the coordination department, writes the proposals in a format specified for each bidding project and prepares a response document. The response document may include, but is not limited to, the proposal details, conditions, and past performance. For example, the creation department prepares the response document according to a specified format to include the proposal details. The creation department can also collect necessary data to include the conditions. The creation department can also refer to past project data to include past performance. For example, the creation department writes the proposal details and prepares the response document according to a specified format. Conditions may include, for example, deadlines and budgets, and the creation department collects this data and includes it in the response document. Past performance may include, for example, successful case studies of past projects and customer evaluations, and the creation department refers to this data and includes it in the response document.As a result, the AI ​​agent system according to the embodiment can recognize its own product information, acquire bidding project data, extract projects for which it can make proposals, organize the proposal content, and create a response document.

[0030] The recognition unit recognizes the company's product information. This product information includes, but is not limited to, product information, service information, and technical information. The recognition unit recognizes product information using, for example, image recognition technology. Specifically, image recognition technology utilizes computer vision algorithms using deep learning to analyze product images and extract product features. This allows for the automatic recognition of detailed information such as product type, model, and specifications. Text recognition technology is effective when product information is provided in text format, for example, recognizing the contents of proposals and specifications. Text recognition technology includes optical character recognition (OCR) technology, which can convert text in scanned documents and images into digital data. Furthermore, natural language processing (NLP) technology can be used to analyze the meaning of the recognized text and extract important information. Speech recognition technology is effective when product information is provided in audio format, for example, recognizing the contents of presentations. Speech recognition technology uses algorithms to convert audio signals into text and extract product information from audio data. This allows for the automatic acquisition of important information from recordings of presentations and meetings. The recognition unit combines these technologies to comprehensively recognize the company's product information and store it in a database. This allows the recognition unit to handle diverse formats of product information and recognize the information efficiently and accurately.

[0031] The acquisition unit crawls publicly available information from each local government based on the information recognized by the recognition unit and obtains bidding project data. Crawling is performed using, for example, a web crawler, but is not limited to such an example. A web crawler is a program that automatically visits websites on the internet and collects specified information. The acquisition unit obtains bidding project data from each local government's website using, for example, a web crawler. Specifically, the web crawler analyzes the structure of each local government's website, identifies pages related to bidding projects, and extracts the necessary data. The acquisition unit can also obtain bidding project data from each local government's database using an API. An API is an interface for exchanging data between different systems, and the acquisition unit can obtain bidding project data in real time through the API. Furthermore, the acquisition unit can also obtain bidding project data from web pages using scraping technology. Scraping technology is a method of analyzing the HTML structure of a web page and extracting specific data, and the acquisition unit uses scraping technology to efficiently obtain the necessary data from web pages. For example, the acquisition unit periodically visits each local government's website using a web crawler and obtains new bidding project data. APIs are a method of directly accessing databases provided by each local government. For example, the data acquisition unit can use APIs to obtain bidding project data in real time. Web scraping is a method of extracting data by analyzing the content of web pages. For example, the data acquisition unit can use web scraping to obtain bidding project data from web pages. This allows the data acquisition unit to efficiently collect bidding project data using diverse methods, improving the overall information gathering capability of the system.

[0032] The extraction unit extracts projects that the company can propose to based on the data acquired by the acquisition unit. Projects that can be proposed to are extracted based on, for example, the size and type of the project, the conditions of the proposal, etc., but are not limited to these examples. For example, the extraction unit extracts projects that can be proposed to based on the size of the project. Specifically, it determines whether the size of the project is within the range that the company can handle and extracts projects that can be proposed to. Project types include, for example, product provision, service provision, technology provision, etc., and the extraction unit extracts projects of the type that the company can handle. Conditions of the proposal include, for example, deadlines and budgets, and the extraction unit extracts projects that meet the conditions that the company can handle. The extraction unit uses AI to analyze this data and identify the most suitable projects. Specifically, it uses machine learning algorithms to learn from past proposal data and success stories and models the characteristics of projects that can be proposed to. This makes it possible to extract projects that can be proposed to with high accuracy even for new projects. Furthermore, the extraction unit can continuously extract projects that can be proposed to based on data that is updated in real time and respond to the latest situation. For example, when the acquisition unit acquires new bidding project data, the extraction unit immediately analyzes the data and identifies projects that can be proposed to. The extraction unit also evaluates the priority of the projects and can propose to the most important ones first. This allows the extraction unit to efficiently and effectively extract projects that can be proposed to, maximizing its business opportunities.

[0033] The Coordination Department organizes the proposals for the projects selected by the Selection Department, coordinates with the relevant departments, and performs cost estimations. For example, the Coordination Department holds meetings with the relevant departments to organize the proposals. Specifically, the Coordination Department collaborates with each department to confirm the details of the proposals and make necessary adjustments. The Coordination Department can also collect the necessary data to perform cost estimations. Cost estimations are based on data such as material costs and labor costs, and the Coordination Department collects this data and performs the estimations. Furthermore, the Coordination Department can use project management tools to organize the proposals. Project management tools are effective for organizing proposals and managing progress, and for example, the Coordination Department uses project management tools to organize proposals. In addition to organizing proposals, the Coordination Department also evaluates the feasibility of the proposals and makes adjustments to secure the necessary resources. For example, based on the proposals, it arranges the necessary personnel and equipment and develops a project execution plan. The Coordination Department also introduces quality control processes to ensure the quality of the proposals and improve their accuracy and reliability. This allows the coordination department to efficiently organize proposals, strengthen collaboration with the relevant departments, and increase the success rate of proposals.

[0034] The drafting department, based on the proposals organized by the coordination department, prepares a response document by writing the proposal content in the format specified for each bid. The response document may, but is not limited to, include the proposal content, conditions, and track record. For example, the drafting department prepares the response document according to the specified format to include the proposal content. Specifically, the drafting department writes the proposal content in detail and prepares the response document according to the specified format. Conditions include, for example, deadlines and budgets, and the drafting department collects this data and includes it in the response document. Track record includes, for example, past project success stories and customer evaluations, and the drafting department refers to this data and includes it in the response document. Furthermore, the drafting department can also proofread and review the response document to ensure its quality. For example, multiple staff members can review the content of the response document to check for errors or deficiencies. The drafting department also manages the deadline for submitting the response document and adjusts the schedule to ensure submission within the deadline. This allows the drafting department to accurately and effectively write the proposal content and quickly prepare a response document for each bid. Furthermore, the creation department can build a database of past responses and utilize it for future proposal creation. This allows the creation department to efficiently produce responses and improve the success rate of proposals.

[0035] The description section can include elements that support the proposal, such as strengths, differentiation from competitors, conditions, and track record, depending on the content of the proposal. For example, depending on the content of the proposal, the description section can describe technical strengths. For example, it can emphasize unique technologies or patents. The description section can also describe business strengths. For example, it can emphasize competitive advantages or market share. The description section can also describe differentiation from competitors. For example, it can emphasize unique services or business models. The description section can also describe the conditions of the proposal. For example, it can clarify conditions such as deadlines and budgets. The description section can also describe track record. For example, it can emphasize past project achievements or customer evaluations. In this way, the content of the proposal can be strengthened by including elements that support it. Some or all of the above processing in the description section may be performed using AI, for example, or not using AI. For example, depending on the content of the proposal, strengths and differentiating elements may be input into a generating AI, and the generating AI may generate elements that support the proposal.

[0036] The presentation unit can create presentation materials and talk scripts, and deliver presentations as needed. For example, the presentation unit can create slides based on the proposal. For example, the presentation unit can use graphs and charts to highlight key points of the proposal. The presentation unit can also create talk scripts. For example, the presentation unit can clarify the order of what to say and the keywords to use. Furthermore, the presentation unit can deliver presentations. For example, the presentation unit can deliver a presentation to effectively communicate the proposal. This allows for the creation of presentation materials and talk scripts, and the delivery of presentations. Some or all of the above processes in the presentation unit may be performed using AI, or not. For example, the presentation unit can input the proposal into a generation AI, which can then generate presentation materials and talk scripts.

[0037] The analysis department can analyze the reasons for success and failure from the bidding results and use this information to improve future actions. For example, the analysis department can analyze the bidding results and identify the strengths and weaknesses of the proposals. For example, the analysis department can collect data to highlight the strengths of the proposals. It can also collect data to improve the weaknesses of the proposals. Furthermore, the analysis department can formulate strategies to improve future actions. For example, the analysis department can formulate strategies to further strengthen the strengths of the proposals. It can also formulate strategies to improve the weaknesses of the proposals. This allows the analysis of bidding results to be used to improve future actions. Some or all of the above processes in the analysis department may be performed using AI, for example, or not. For example, the analysis department can input the bidding results into a generating AI and have the generating AI analyze the reasons for success and failure.

[0038] The recognition unit can improve recognition accuracy by referring to the history of past proposals and specifications when recognizing product information. For example, the recognition unit can analyze the content of past proposals and recognize similar product information. For example, the recognition unit can improve the recognition accuracy of product information by referring to the history of past specifications. The recognition unit can also recognize product information based on the history of past proposals and specifications. For example, the recognition unit can analyze the content of past proposals and recognize similar product information. This allows for improved recognition accuracy of product information by referring to the history of past proposals and specifications. Some or all of the above processing in the recognition unit may be performed using AI, for example, or without AI. For example, the recognition unit can input data from past proposals and specifications into a generating AI, and the generating AI can improve the recognition accuracy of product information.

[0039] The recognition unit can broaden its recognition scope by referencing product information from different industries when recognizing product information. For example, the recognition unit can broaden its recognition scope by analyzing product information from different industries. For example, the recognition unit can improve the accuracy of product information recognition by referring to proposals and specifications from different industries. The recognition unit can also perform product information recognition based on product information from different industries. For example, the recognition unit can broaden its recognition scope by analyzing product information from different industries. This allows the recognition scope of product information to be broadened by referencing product information from different industries. Some or all of the above processing in the recognition unit may be performed using AI, for example, or without AI. For example, the recognition unit can input product information from different industries into a generating AI, and the generating AI can broaden the recognition scope of product information.

[0040] The recognition unit can prioritize the recognition of highly relevant information by considering the user's geographical location when recognizing product information. For example, the recognition unit can prioritize the recognition of highly relevant product information based on the user's geographical location. For example, the recognition unit can recognize the most relevant product information based on the user's current location. The recognition unit can also improve the accuracy of product information recognition by considering the user's geographical location. For example, the recognition unit can prioritize the recognition of highly relevant product information based on the user's geographical location. This allows for the priority recognition of highly relevant product information by considering the user's geographical location. Some or all of the above processing in the recognition unit may be performed using AI, for example, or without AI. For example, the recognition unit can input the user's geographical location information into a generating AI, which can then prioritize the recognition of highly relevant product information.

[0041] The recognition unit can analyze the user's social media activity and recognize relevant information when recognizing product information. For example, the recognition unit can analyze the user's social media activity and recognize relevant product information. For example, the recognition unit can improve the accuracy of product information recognition based on the content of the user's social media posts. The recognition unit can also refer to the user's social media activity to recognize product information. For example, the recognition unit can analyze the user's social media activity and recognize relevant product information. In this way, relevant product information can be recognized by analyzing the user's social media activity. Some or all of the above processing in the recognition unit may be performed using AI, for example, or without using AI. For example, the recognition unit can input the user's social media activity data into a generating AI and have the generating AI recognize relevant product information.

[0042] The acquisition unit can improve the accuracy of acquisition by referring to past bidding results when acquiring bidding project data. For example, the acquisition unit can analyze past bidding results and acquire similar bidding project data. For example, the acquisition unit can improve the accuracy of acquisition by referring to past bidding results. The acquisition unit can also acquire bidding project data based on past bidding results. For example, the acquisition unit can analyze past bidding results and acquire similar bidding project data. This allows the acquisition accuracy of bidding project data to be improved by referring to past bidding results. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without using AI. For example, the acquisition unit can input past bidding result data into a generating AI, and the generating AI can improve the accuracy of acquiring bidding project data.

[0043] The acquisition unit can broaden the scope of acquisition by referring to publicly available information from different municipalities when acquiring bidding project data. For example, the acquisition unit can broaden the scope of acquisition by analyzing publicly available information from different municipalities. For example, the acquisition unit can improve the acquisition accuracy by referring to bidding project data from different municipalities. The acquisition unit can also acquire bidding project data based on publicly available information from different municipalities. For example, the acquisition unit can broaden the scope of acquisition by analyzing publicly available information from different municipalities. This allows the acquisition of bidding project data to be broadened by referring to publicly available information from different municipalities. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without using AI. For example, the acquisition unit can input publicly available information from different municipalities into a generating AI, and the generating AI can broaden the scope of acquisition of bidding project data.

[0044] The acquisition unit can prioritize the acquisition of highly relevant data by considering the user's geographical location information when acquiring bidding project data. For example, the acquisition unit can prioritize the acquisition of highly relevant bidding project data based on the user's geographical location information. For example, the acquisition unit can acquire the most relevant bidding project data based on the user's current location. The acquisition unit can also improve the accuracy of acquiring bidding project data by considering the user's geographical location information. For example, the acquisition unit can prioritize the acquisition of highly relevant bidding project data based on the user's geographical location information. This allows for the priority acquisition of highly relevant bidding project data by considering the user's geographical location information. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input the user's geographical location information into a generating AI, which can then prioritize the acquisition of highly relevant bidding project data.

[0045] The acquisition unit can analyze the user's social media activity and acquire relevant data when acquiring bidding project data. For example, the acquisition unit can analyze the user's social media activity and acquire relevant bidding project data. For example, the acquisition unit can improve the accuracy of acquiring bidding project data based on the content of the user's social media posts. The acquisition unit can also acquire bidding project data by referring to the user's social media activity. For example, the acquisition unit can analyze the user's social media activity and acquire relevant bidding project data. In this way, relevant bidding project data can be acquired by analyzing the user's social media activity. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without using AI. For example, the acquisition unit can input the user's social media activity data into a generating AI and have the generating AI acquire relevant bidding project data.

[0046] The extraction unit can improve the extraction accuracy by referring to past proposal results when extracting potential proposals. For example, the extraction unit can analyze past proposal results and extract similar potential proposals. For example, the extraction unit can improve the extraction accuracy by referring to past proposal results. The extraction unit can also extract potential proposals based on past proposal results. For example, the extraction unit can analyze past proposal results and extract similar potential proposals. This allows the extraction accuracy of potential proposals to be improved by referring to past proposal results. Some or all of the above processing in the extraction unit may be performed using AI, for example, or without AI. For example, the extraction unit can input past proposal result data into a generating AI, and the generating AI can improve the extraction accuracy of potential proposals.

[0047] The extraction unit can broaden the scope of its extraction by referring to project information from different industries when extracting potential projects. For example, the extraction unit can broaden the scope of its extraction by analyzing project information from different industries. For example, the extraction unit can improve the extraction accuracy by referring to potential projects from different industries. The extraction unit can also extract potential projects based on project information from different industries. For example, the extraction unit can broaden the scope of its extraction by analyzing project information from different industries. This allows the extraction of potential projects to be broadened by referring to project information from different industries. Some or all of the above processing in the extraction unit may be performed using AI, for example, or without AI. For example, the extraction unit can input project information from different industries into a generating AI, and the generating AI can broaden the scope of projects to be extracted.

[0048] The extraction unit can prioritize extracting highly relevant cases by considering the user's geographical location information when extracting potential cases. For example, the extraction unit can prioritize extracting highly relevant cases based on the user's geographical location information. For example, the extraction unit can extract the most suitable cases based on the user's current location. The extraction unit can also improve the accuracy of extracting potential cases by considering the user's geographical location information. For example, the extraction unit can prioritize extracting highly relevant cases based on the user's geographical location information. This allows for the priority extraction of highly relevant cases by considering the user's geographical location information. Some or all of the above processing in the extraction unit may be performed using AI, for example, or without AI. For example, the extraction unit can input the user's geographical location information into a generating AI, which can then prioritize extracting highly relevant cases.

[0049] The extraction unit can analyze the user's social media activity and extract relevant cases when extracting potential cases. For example, the extraction unit can analyze the user's social media activity and extract relevant potential cases. For example, the extraction unit can improve the accuracy of extracting potential cases based on the content of the user's social media posts. The extraction unit can also extract potential cases by referring to the user's social media activity. For example, the extraction unit can analyze the user's social media activity and extract relevant potential cases. This allows for the extraction of relevant cases by analyzing the user's social media activity. Some or all of the above processing in the extraction unit may be performed using AI, for example, or without AI. For example, the extraction unit can input the user's social media activity data into a generating AI and have the generating AI extract relevant potential cases.

[0050] The adjustment unit can improve the accuracy of adjustments when adjusting the proposed content by referring to past adjustment history. For example, the adjustment unit can analyze past adjustment history and adjust similar proposed content. For example, the adjustment unit can improve the accuracy of adjustments by referring to past adjustment history. The adjustment unit can also adjust the proposed content based on past adjustment history. For example, the adjustment unit can analyze past adjustment history and adjust similar proposed content. In this way, the accuracy of adjusting the proposed content can be improved by referring to past adjustment history. Some or all of the above processing in the adjustment unit may be performed using AI, for example, or without using AI. For example, the adjustment unit can input past adjustment history data into a generating AI, and the generating AI can improve the accuracy of adjusting the proposed content.

[0051] The adjustment unit can broaden the scope of adjustments when adjusting the proposed content by referring to adjustment methods from different industries. For example, the adjustment unit can broaden the scope of adjustments by analyzing adjustment methods from different industries. For example, the adjustment unit can improve the accuracy of adjustments by referring to adjustment methods from different industries. The adjustment unit can also adjust the proposed content based on adjustment methods from different industries. For example, the adjustment unit can broaden the scope of adjustments by analyzing adjustment methods from different industries. This allows the adjustment scope of the proposed content to be broadened by referring to adjustment methods from different industries. Some or all of the above processing in the adjustment unit may be performed using AI, for example, or without using AI. For example, the adjustment unit can input adjustment methods from different industries into a generating AI, and the generating AI can broaden the scope of adjustments to the proposed content.

[0052] The adjustment unit can prioritize adjusting the content to be highly relevant by considering the user's geographical location information when adjusting the proposed content. For example, the adjustment unit can prioritize adjusting the proposed content to be highly relevant based on the user's geographical location information. For example, the adjustment unit can adjust the optimal proposed content based on the user's current location. The adjustment unit can also improve the accuracy of adjusting the proposed content by considering the user's geographical location information. For example, the adjustment unit can prioritize adjusting the proposed content to be highly relevant based on the user's geographical location information. This allows for prioritizing the adjustment of highly relevant proposed content by considering the user's geographical location information. Some or all of the above processing in the adjustment unit may be performed using AI, for example, or without using AI. For example, the adjustment unit can input the user's geographical location information into a generating AI, and have the generating AI prioritize adjusting the proposed content to be highly relevant.

[0053] The adjustment unit can analyze the user's social media activity and adjust relevant content when adjusting the proposed content. For example, the adjustment unit can analyze the user's social media activity and adjust the relevant proposed content. For example, the adjustment unit can improve the accuracy of adjusting the proposed content based on the user's social media posts. The adjustment unit can also refer to the user's social media activity and adjust the proposed content. For example, the adjustment unit can analyze the user's social media activity and adjust the relevant proposed content. In this way, the relevant proposed content can be adjusted by analyzing the user's social media activity. Some or all of the above processing in the adjustment unit may be performed using AI, for example, or without AI. For example, the adjustment unit can input the user's social media activity data into a generating AI and have the generating AI adjust the relevant proposed content.

[0054] The creation unit can improve the accuracy of its response document creation by referring to past creation history. For example, the creation unit can analyze past creation history and create similar response documents. For example, the creation unit can improve the accuracy of its response document creation by referring to past creation history. The creation unit can also create response documents based on past creation history. For example, the creation unit can analyze past creation history and create similar response documents. This allows the accuracy of response document creation to be improved by referring to past creation history. Some or all of the above processes in the creation unit may be performed using AI, for example, or without AI. For example, the creation unit can input past creation history data into a generation AI, and the generation AI can improve the accuracy of response document creation.

[0055] The creation unit can broaden its range of creation by referencing creation methods from different industries when creating response documents. For example, the creation unit can broaden its range by analyzing creation methods from different industries. For example, the creation unit can improve the accuracy of creation by referencing creation methods from different industries. The creation unit can also create response documents based on creation methods from different industries. For example, the creation unit can broaden its range by analyzing creation methods from different industries. This allows the creation of response documents to be broadened by referencing creation methods from different industries. Some or all of the above processes in the creation unit may be performed using AI, for example, or without AI. For example, the creation unit can input creation methods from different industries into a generation AI, and the generation AI can broaden the range of response documents it can create.

[0056] The creation unit can prioritize creating highly relevant response documents by considering the user's geographical location information when creating response documents. For example, the creation unit can prioritize creating highly relevant response documents based on the user's geographical location information. For example, the creation unit can create the optimal response document based on the user's current location. The creation unit can also improve the accuracy of response document creation by considering the user's geographical location information. For example, the creation unit can prioritize creating highly relevant response documents based on the user's geographical location information. This allows for the prioritization of highly relevant response documents by considering the user's geographical location information. Some or all of the above processing in the creation unit may be performed using AI, for example, or without AI. For example, the creation unit can input the user's geographical location information into a generation AI, which can then prioritize creating highly relevant response documents.

[0057] The creation unit can analyze the user's social media activity and create relevant response documents when creating response documents. For example, the creation unit can analyze the user's social media activity and create relevant response documents. For example, the creation unit can improve the accuracy of response document creation based on the user's social media posts. The creation unit can also create response documents by referring to the user's social media activity. For example, the creation unit can analyze the user's social media activity and create relevant response documents. In this way, relevant response documents can be created by analyzing the user's social media activity. Some or all of the above processing in the creation unit may be performed using AI, for example, or without AI. For example, the creation unit can input the user's social media activity data into a generation AI and have the generation AI create relevant response documents.

[0058] The description section can improve the accuracy of descriptions by referring to past description history when describing elements that support the proposal. For example, the description section can analyze past description history and describe elements that support similar proposals. For example, the description section can improve the accuracy of descriptions by referring to past description history. The description section can also describe elements that support the proposal based on past description history. For example, the description section can analyze past description history and describe elements that support similar proposals. This allows the description section to improve the accuracy of descriptions of elements that support the proposal by referring to past description history. Some or all of the above processing in the description section may be performed using AI, for example, or without AI. For example, the description section can input past description history data into a generating AI, and the generating AI can improve the accuracy of descriptions of elements that support the proposal.

[0059] The description section can prioritize the inclusion of highly relevant elements when describing elements that support the proposal, taking into account the user's geographical location information. For example, the description section can prioritize the inclusion of highly relevant elements based on the user's geographical location information. For example, the description section can describe the most relevant elements based on the user's current location. The description section can also improve the accuracy of element description by considering the user's geographical location information. For example, the description section can prioritize the inclusion of highly relevant elements based on the user's geographical location information. This allows for the prioritization of highly relevant elements by considering the user's geographical location information. Some or all of the above processing in the description section may be performed using AI, for example, or without AI. For example, the description section can input the user's geographical location information into a generating AI, which can then prioritize the inclusion of highly relevant elements.

[0060] The presentation unit can improve the accuracy of creating presentation materials and talk scripts by referring to past creation history. For example, the presentation unit can analyze past creation history and create similar presentation materials and talk scripts. For example, the presentation unit can improve the accuracy of creating presentation materials and talk scripts by referring to past creation history. The presentation unit can also create presentation materials and talk scripts based on past creation history. For example, the presentation unit can analyze past creation history and create similar presentation materials and talk scripts. This allows the accuracy of creating presentation materials and talk scripts to be improved by referring to past creation history. Some or all of the above processes in the presentation unit may be performed using AI, for example, or without AI. For example, the presentation unit can input past creation history data into a generation AI, and the generation AI can improve the accuracy of creating presentation materials and talk scripts.

[0061] The presentation unit can prioritize the creation of presentation materials and scripts that are highly relevant, taking into account the user's geographical location information when creating presentation materials and scripts. For example, the presentation unit can prioritize the creation of highly relevant presentation materials and scripts based on the user's geographical location information. For example, the presentation unit can create optimal presentation materials and scripts based on the user's current location. The presentation unit can also improve the accuracy of presentation material and script creation by considering the user's geographical location information. For example, the presentation unit can prioritize the creation of highly relevant presentation materials and scripts based on the user's geographical location information. This allows for the priority creation of highly relevant presentation materials and scripts by considering the user's geographical location information. Some or all of the above processing in the presentation unit may be performed using AI, or not. For example, the presentation unit can input the user's geographical location information into a generating AI, which can then prioritize the creation of highly relevant presentation materials and scripts.

[0062] The analysis unit can improve the accuracy of its analysis of bid results by referring to past analysis history. For example, the analysis unit can analyze past analysis history and analyze similar bid results. For example, the analysis unit can improve the accuracy of its analysis by referring to past analysis history. The analysis unit can also analyze bid results based on past analysis history. For example, the analysis unit can analyze past analysis history and analyze similar bid results. This allows the analysis unit to improve the accuracy of its bid result analysis by referring to past analysis history. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input past analysis history data into a generating AI, and the generating AI can improve the accuracy of its bid result analysis.

[0063] The analysis unit can prioritize the analysis of highly relevant results by considering the user's geographical location information when analyzing bidding results. For example, the analysis unit can prioritize the analysis of highly relevant bidding results based on the user's geographical location information. For example, the analysis unit can analyze the optimal bidding results based on the user's current location. The analysis unit can also improve the accuracy of the bidding result analysis by considering the user's geographical location information. For example, the analysis unit can prioritize the analysis of highly relevant bidding results based on the user's geographical location information. This allows for the prioritization of highly relevant bidding results by considering the user's geographical location information. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the user's geographical location information into a generating AI, and have the generating AI prioritize the analysis of highly relevant bidding results.

[0064] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0065] The AI ​​agent system can also be equipped with a feedback function. This function can collect feedback from relevant departments and stakeholders after proposals and responses have been created, and incorporate this feedback into future proposals. For example, the feedback function can collect evaluations and suggestions for improvement regarding the content of proposals, and consider these when creating future proposals. Furthermore, the feedback function can analyze the results after proposal submission to identify success and failure factors. Additionally, the feedback function can collect customer reactions and evaluations after proposal submission and utilize this information in future proposals. In this way, incorporating a feedback function can improve the quality of proposals and responses, which can be used to enhance future proposal activities.

[0066] The AI ​​agent system can also be equipped with a learning unit. This unit can learn from past proposals and responses to improve the accuracy of proposal creation. For example, it can analyze the characteristics of past successful proposals and use this information when creating future proposals. It can also identify the causes of past failed proposals and prevent the same mistakes from being repeated. Furthermore, the learning unit can optimize the proposal creation process and learn how to create proposals efficiently. Thus, incorporating a learning unit can improve both the accuracy and efficiency of proposal creation.

[0067] The AI ​​agent system can also be equipped with a notification function. This notification function can inform the person in charge about the status of proposals and responses, as well as their submission deadlines. For example, the notification function can send a reminder to the person in charge if the proposal is behind schedule. It can also issue an alert when the submission deadline is approaching. Furthermore, the notification function can notify the person in charge when the results are available after the proposal has been submitted. In this way, by incorporating a notification function, the status of proposals and responses can be monitored, and submission deadlines can be met.

[0068] The AI ​​agent system can also be equipped with a simulation unit. This simulation unit can simulate the content of a proposal and predict its success rate. For example, it can calculate the success rate based on the proposal's content and referencing past data. It can also simulate how the success rate changes when the proposal's content is modified. Furthermore, the simulation unit can perform simulations to optimize the proposal's content. Thus, by incorporating a simulation unit, the success rate of the proposal can be increased.

[0069] The AI ​​agent system can also include a collaboration section. This section provides an environment where multiple team members can work together during proposal creation. For example, it can share proposal drafts and allow team members to edit them in real time. It can also support communication between team members, facilitating the exchange of ideas and feedback. Furthermore, it can visualize the progress of proposal creation, enabling team members to work efficiently. In this way, incorporating a collaboration section can improve the efficiency and quality of proposal creation.

[0070] The following briefly describes the processing flow for example form 1.

[0071] Step 1: The recognition unit recognizes the company's product information. This product information includes product information, service information, and technical information. The recognition unit uses image recognition technology, text recognition technology, and speech recognition technology to recognize product information. For example, image recognition technology is used to recognize product images and obtain product information. Text recognition technology recognizes the contents of proposals and specifications. Speech recognition technology recognizes the contents of presentations. Step 2: The acquisition unit crawls publicly available information from each local government based on the information recognized by the recognition unit and obtains bidding project data. The acquisition unit uses web crawlers, APIs, and scraping techniques to obtain bidding project data from each local government's website and database. For example, it may periodically visit each local government's website using a web crawler to obtain new bidding project data. It may use APIs to obtain bidding project data in real time. It may use scraping techniques to obtain bidding project data from web pages. Step 3: The extraction unit extracts projects that the company can propose based on the data acquired by the acquisition unit. Projects that can be proposed are extracted based on factors such as the size and type of the project and the conditions of the proposal. For example, it determines whether the size of the project is within the company's capabilities and extracts projects that can be proposed. Project types include product provision, service provision, technology provision, etc., and the company extracts projects of the type it can handle. Proposal conditions include deadlines and budgets, and the company extracts projects that meet the conditions it can meet. Step 4: The Coordination Department organizes the proposals for the projects selected by the Extraction Department, coordinates with the relevant departments, and performs cost estimations. The Coordination Department holds meetings with the relevant departments to organize the proposals. It collects the necessary data to perform cost estimations. It uses project management tools to organize the proposals. For example, it reviews the proposals in detail through meetings with the relevant departments and makes necessary adjustments. It performs cost estimations based on data such as material costs and labor costs. Step 5: The creation team, based on the proposals organized by the coordination team, will write the proposals in the format specified for each bidding project and create a response document. The response document will include the proposal details, conditions, and track record. For example, the proposal details will be described in detail, and the response document will be created according to the specified format. Conditions include deadlines and budgets, and this data will be collected and included in the response document. Track record includes past project success stories and customer evaluations, and this data will be referenced and included in the response document.

[0072] (Example of form 2) The AI ​​agent system according to an embodiment of the present invention is a system that, after understanding its own services and strengths, autonomously extracts projects that it can propose to from among the 1 million municipal bidding projects nationwide annually, compiles proposals, and submits them. First, this AI agent system receives input from the company's product information (such as proposals and specifications), and the AI ​​agent recognizes the company's services. Next, the AI ​​agent crawls publicly available information from each municipality and obtains bidding project data. Based on the acquired data, the AI ​​agent extracts projects that the company can propose to. For the extracted projects, the AI ​​agent organizes the proposal content and performs tasks such as coordinating with the relevant department and estimating costs. Furthermore, it writes the proposal content into a format specified for each bidding project and creates a response document. Based on the created response document, the AI ​​agent creates presentation materials and talk scripts and performs presentations as needed. Finally, it analyzes the reasons for success and failure from the bidding results and uses this information to improve future actions. For example, the AI ​​agent system recognizes the company's product information and crawls publicly available information from each municipality to obtain bidding project data. Next, the AI ​​agent system extracts projects that the company can propose based on the acquired data and organizes the proposal content. Furthermore, the AI ​​agent system coordinates with the relevant departments and performs cost estimations, writes the proposal content in the format specified for each bidding project, and creates a response document. Finally, the AI ​​agent system creates presentation materials and talk scripts based on the created response document and delivers a presentation as needed. In this way, the AI ​​agent system can efficiently handle bidding by reducing the enormous amount of time and effort required to find bidding projects and create response documents. Thus, the AI ​​agent system can recognize the company's product information, acquire bidding project data, extract projects that can be proposed, organize the proposal content, and create a response document.

[0073] The AI ​​agent system according to this embodiment comprises a recognition unit, an acquisition unit, an extraction unit, an adjustment unit, and a creation unit. The recognition unit recognizes the company's product information. This product information includes, but is not limited to, product information, service information, and technical information. The recognition unit recognizes product information using, for example, image recognition technology. The recognition unit can also recognize product information using text recognition technology. The recognition unit can also recognize product information using speech recognition technology. For example, the recognition unit recognizes an image of a product using image recognition technology and acquires product information. Text recognition technology is effective when product information is provided in text format, for example, to recognize the contents of a proposal or specification. Speech recognition technology is effective when product information is provided in speech format, for example, to recognize the contents of a presentation. Based on the information recognized by the recognition unit, the acquisition unit crawls publicly available information from each local government and acquires bidding data. Crawling is performed using, for example, a web crawler, but is not limited to this example. The acquisition unit acquires bidding data from the websites of each local government using, for example, a web crawler. Furthermore, the acquisition unit can also obtain bidding project data from each local government's database using APIs. The acquisition unit can also obtain bidding project data from web pages using scraping techniques. For example, the acquisition unit periodically visits each local government's website using a web crawler to obtain new bidding project data. APIs are a method of directly accessing databases provided by each local government; for example, the acquisition unit can obtain bidding project data in real time using APIs. Scraping techniques are a method of extracting data by analyzing the content of web pages; for example, the acquisition unit can obtain bidding project data from web pages using scraping techniques. The extraction unit extracts projects that the company can propose based on the data acquired by the acquisition unit. Proposable projects are extracted based on, for example, the size and type of the project, the conditions for the proposal, etc., but are not limited to these examples. The extraction unit can extract projects that can be proposed based on, for example, the size of the project. The extraction unit can also extract projects that can be proposed based on the type of project.The extraction unit can also extract projects that can be proposed based on the proposal conditions. For example, the extraction unit determines whether the scale of the project is within the company's capabilities and extracts projects that can be proposed. Project types include, for example, product provision, service provision, and technology provision, and the extraction unit extracts projects of the type that the company can handle. Proposal conditions include, for example, deadlines and budgets, and the extraction unit extracts projects with conditions that the company can handle. The coordination unit organizes the proposal content for the projects extracted by the extraction unit and performs coordination with the relevant departments and cost estimation. For example, the coordination unit holds meetings with the relevant departments to organize the proposal content. The coordination unit can also collect the necessary data to perform cost estimation. The coordination unit can also use project management tools to organize the proposal content. For example, the coordination unit examines the proposal content in detail through meetings with the relevant departments and makes necessary adjustments. Cost estimation is performed based on data such as material costs and labor costs, and the coordination unit collects this data and performs the estimation. Project management tools are effective for organizing proposals and managing progress. For example, the coordination department uses project management tools to organize proposals. The creation department, based on the proposals organized by the coordination department, writes the proposals in a format specified for each bidding project and prepares a response document. The response document may include, but is not limited to, the proposal details, conditions, and past performance. For example, the creation department prepares the response document according to a specified format to include the proposal details. The creation department can also collect necessary data to include the conditions. The creation department can also refer to past project data to include past performance. For example, the creation department writes the proposal details and prepares the response document according to a specified format. Conditions may include, for example, deadlines and budgets, and the creation department collects this data and includes it in the response document. Past performance may include, for example, successful case studies of past projects and customer evaluations, and the creation department refers to this data and includes it in the response document.As a result, the AI ​​agent system according to the embodiment can recognize its own product information, acquire bidding project data, extract projects for which it can make proposals, organize the proposal content, and create a response document.

[0074] The recognition unit recognizes the company's product information. This product information includes, but is not limited to, product information, service information, and technical information. The recognition unit recognizes product information using, for example, image recognition technology. Specifically, image recognition technology utilizes computer vision algorithms using deep learning to analyze product images and extract product features. This allows for the automatic recognition of detailed information such as product type, model, and specifications. Text recognition technology is effective when product information is provided in text format, for example, recognizing the contents of proposals and specifications. Text recognition technology includes optical character recognition (OCR) technology, which can convert text in scanned documents and images into digital data. Furthermore, natural language processing (NLP) technology can be used to analyze the meaning of the recognized text and extract important information. Speech recognition technology is effective when product information is provided in audio format, for example, recognizing the contents of presentations. Speech recognition technology uses algorithms to convert audio signals into text and extract product information from audio data. This allows for the automatic acquisition of important information from recordings of presentations and meetings. The recognition unit combines these technologies to comprehensively recognize the company's product information and store it in a database. This allows the recognition unit to handle diverse formats of product information and recognize the information efficiently and accurately.

[0075] The acquisition unit crawls publicly available information from each local government based on the information recognized by the recognition unit and obtains bidding project data. Crawling is performed using, for example, a web crawler, but is not limited to such an example. A web crawler is a program that automatically visits websites on the internet and collects specified information. The acquisition unit obtains bidding project data from each local government's website using, for example, a web crawler. Specifically, the web crawler analyzes the structure of each local government's website, identifies pages related to bidding projects, and extracts the necessary data. The acquisition unit can also obtain bidding project data from each local government's database using an API. An API is an interface for exchanging data between different systems, and the acquisition unit can obtain bidding project data in real time through the API. Furthermore, the acquisition unit can also obtain bidding project data from web pages using scraping technology. Scraping technology is a method of analyzing the HTML structure of a web page and extracting specific data, and the acquisition unit uses scraping technology to efficiently obtain the necessary data from web pages. For example, the acquisition unit periodically visits each local government's website using a web crawler and obtains new bidding project data. APIs are a method of directly accessing databases provided by each local government. For example, the data acquisition unit can use APIs to obtain bidding project data in real time. Web scraping is a method of extracting data by analyzing the content of web pages. For example, the data acquisition unit can use web scraping to obtain bidding project data from web pages. This allows the data acquisition unit to efficiently collect bidding project data using diverse methods, improving the overall information gathering capability of the system.

[0076] The extraction unit extracts projects that the company can propose to based on the data acquired by the acquisition unit. Projects that can be proposed to are extracted based on, for example, the size and type of the project, the conditions of the proposal, etc., but are not limited to these examples. For example, the extraction unit extracts projects that can be proposed to based on the size of the project. Specifically, it determines whether the size of the project is within the range that the company can handle and extracts projects that can be proposed to. Project types include, for example, product provision, service provision, technology provision, etc., and the extraction unit extracts projects of the type that the company can handle. Conditions of the proposal include, for example, deadlines and budgets, and the extraction unit extracts projects that meet the conditions that the company can handle. The extraction unit uses AI to analyze this data and identify the most suitable projects. Specifically, it uses machine learning algorithms to learn from past proposal data and success stories and models the characteristics of projects that can be proposed to. This makes it possible to extract projects that can be proposed to with high accuracy even for new projects. Furthermore, the extraction unit can continuously extract projects that can be proposed to based on data that is updated in real time and respond to the latest situation. For example, when the acquisition unit acquires new bidding project data, the extraction unit immediately analyzes the data and identifies projects that can be proposed to. The extraction unit also evaluates the priority of the projects and can propose to the most important ones first. This allows the extraction unit to efficiently and effectively extract projects that can be proposed to, maximizing its business opportunities.

[0077] The Coordination Department organizes the proposals for the projects selected by the Selection Department, coordinates with the relevant departments, and performs cost estimations. For example, the Coordination Department holds meetings with the relevant departments to organize the proposals. Specifically, the Coordination Department collaborates with each department to confirm the details of the proposals and make necessary adjustments. The Coordination Department can also collect the necessary data to perform cost estimations. Cost estimations are based on data such as material costs and labor costs, and the Coordination Department collects this data and performs the estimations. Furthermore, the Coordination Department can use project management tools to organize the proposals. Project management tools are effective for organizing proposals and managing progress, and for example, the Coordination Department uses project management tools to organize proposals. In addition to organizing proposals, the Coordination Department also evaluates the feasibility of the proposals and makes adjustments to secure the necessary resources. For example, based on the proposals, it arranges the necessary personnel and equipment and develops a project execution plan. The Coordination Department also introduces quality control processes to ensure the quality of the proposals and improve their accuracy and reliability. This allows the coordination department to efficiently organize proposals, strengthen collaboration with the relevant departments, and increase the success rate of proposals.

[0078] The drafting department, based on the proposals organized by the coordination department, prepares a response document by writing the proposal content in the format specified for each bid. The response document may, but is not limited to, include the proposal content, conditions, and track record. For example, the drafting department prepares the response document according to the specified format to include the proposal content. Specifically, the drafting department writes the proposal content in detail and prepares the response document according to the specified format. Conditions include, for example, deadlines and budgets, and the drafting department collects this data and includes it in the response document. Track record includes, for example, past project success stories and customer evaluations, and the drafting department refers to this data and includes it in the response document. Furthermore, the drafting department can also proofread and review the response document to ensure its quality. For example, multiple staff members can review the content of the response document to check for errors or deficiencies. The drafting department also manages the deadline for submitting the response document and adjusts the schedule to ensure submission within the deadline. This allows the drafting department to accurately and effectively write the proposal content and quickly prepare a response document for each bid. Furthermore, the creation department can build a database of past responses and utilize it for future proposal creation. This allows the creation department to efficiently produce responses and improve the success rate of proposals.

[0079] The description section can include elements that support the proposal, such as strengths, differentiation from competitors, conditions, and track record, depending on the content of the proposal. For example, depending on the content of the proposal, the description section can describe technical strengths. For example, it can emphasize unique technologies or patents. The description section can also describe business strengths. For example, it can emphasize competitive advantages or market share. The description section can also describe differentiation from competitors. For example, it can emphasize unique services or business models. The description section can also describe the conditions of the proposal. For example, it can clarify conditions such as deadlines and budgets. The description section can also describe track record. For example, it can emphasize past project achievements or customer evaluations. In this way, the content of the proposal can be strengthened by including elements that support it. Some or all of the above processing in the description section may be performed using AI, for example, or not using AI. For example, depending on the content of the proposal, strengths and differentiating elements may be input into a generating AI, and the generating AI may generate elements that support the proposal.

[0080] The presentation unit can create presentation materials and talk scripts, and deliver presentations as needed. For example, the presentation unit can create slides based on the proposal. For example, the presentation unit can use graphs and charts to highlight key points of the proposal. The presentation unit can also create talk scripts. For example, the presentation unit can clarify the order of what to say and the keywords to use. Furthermore, the presentation unit can deliver presentations. For example, the presentation unit can deliver a presentation to effectively communicate the proposal. This allows for the creation of presentation materials and talk scripts, and the delivery of presentations. Some or all of the above processes in the presentation unit may be performed using AI, or not. For example, the presentation unit can input the proposal into a generation AI, which can then generate presentation materials and talk scripts.

[0081] The analysis department can analyze the reasons for success and failure from the bidding results and use this information to improve future actions. For example, the analysis department can analyze the bidding results and identify the strengths and weaknesses of the proposals. For example, the analysis department can collect data to highlight the strengths of the proposals. It can also collect data to improve the weaknesses of the proposals. Furthermore, the analysis department can formulate strategies to improve future actions. For example, the analysis department can formulate strategies to further strengthen the strengths of the proposals. It can also formulate strategies to improve the weaknesses of the proposals. This allows the analysis of bidding results to be used to improve future actions. Some or all of the above processes in the analysis department may be performed using AI, for example, or not. For example, the analysis department can input the bidding results into a generating AI and have the generating AI analyze the reasons for success and failure.

[0082] The recognition unit can estimate the user's emotions and adjust the accuracy of product information recognition based on the estimated emotions. For example, if the user is stressed, the recognition unit can provide a simple interface to improve the accuracy of product information recognition. For example, if the user is relaxed, the recognition unit can provide detailed information to improve the accuracy of product information recognition. Also, if the user is in a hurry, the recognition unit can quickly recognize product information and adjust the accuracy of recognition. For example, the recognition unit can estimate the user's emotions and change the interface based on the estimated emotions. This improves recognition accuracy by adjusting the accuracy of product information recognition based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the recognition unit may be performed using AI, for example, or without AI. For example, the recognition unit can input user emotion data into the generative AI and have the generative AI adjust the accuracy of product information recognition.

[0083] The recognition unit can improve recognition accuracy by referring to the history of past proposals and specifications when recognizing product information. For example, the recognition unit can analyze the content of past proposals and recognize similar product information. For example, the recognition unit can improve the recognition accuracy of product information by referring to the history of past specifications. The recognition unit can also recognize product information based on the history of past proposals and specifications. For example, the recognition unit can analyze the content of past proposals and recognize similar product information. This allows for improved recognition accuracy of product information by referring to the history of past proposals and specifications. Some or all of the above processing in the recognition unit may be performed using AI, for example, or without AI. For example, the recognition unit can input data from past proposals and specifications into a generating AI, and the generating AI can improve the recognition accuracy of product information.

[0084] The recognition unit can broaden its recognition scope by referencing product information from different industries when recognizing product information. For example, the recognition unit can broaden its recognition scope by analyzing product information from different industries. For example, the recognition unit can improve the accuracy of product information recognition by referring to proposals and specifications from different industries. The recognition unit can also perform product information recognition based on product information from different industries. For example, the recognition unit can broaden its recognition scope by analyzing product information from different industries. This allows the recognition scope of product information to be broadened by referencing product information from different industries. Some or all of the above processing in the recognition unit may be performed using AI, for example, or without AI. For example, the recognition unit can input product information from different industries into a generating AI, and the generating AI can broaden the recognition scope of product information.

[0085] The recognition unit can estimate the user's emotions and determine the priority of product information to recognize based on the estimated emotions. For example, if the user is stressed, the recognition unit will prioritize recognizing important product information. For example, if the user is relaxed, the recognition unit can prioritize recognizing detailed product information. The recognition unit can also determine the priority of product information to recognize quickly if the user is in a hurry. For example, the recognition unit can estimate the user's emotions and determine the priority of product information based on the estimated emotions. This allows for the priority recognition of important product information by determining the priority of product information based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the recognition unit may be performed using AI, for example, or without AI. For example, the recognition unit can input user emotion data into a generative AI and have the generative AI determine the priority of product information.

[0086] The recognition unit can prioritize the recognition of highly relevant information by considering the user's geographical location when recognizing product information. For example, the recognition unit can prioritize the recognition of highly relevant product information based on the user's geographical location. For example, the recognition unit can recognize the most relevant product information based on the user's current location. The recognition unit can also improve the accuracy of product information recognition by considering the user's geographical location. For example, the recognition unit can prioritize the recognition of highly relevant product information based on the user's geographical location. This allows for the priority recognition of highly relevant product information by considering the user's geographical location. Some or all of the above processing in the recognition unit may be performed using AI, for example, or without AI. For example, the recognition unit can input the user's geographical location information into a generating AI, which can then prioritize the recognition of highly relevant product information.

[0087] The recognition unit can analyze the user's social media activity and recognize relevant information when recognizing product information. For example, the recognition unit can analyze the user's social media activity and recognize relevant product information. For example, the recognition unit can improve the accuracy of product information recognition based on the content of the user's social media posts. The recognition unit can also refer to the user's social media activity to recognize product information. For example, the recognition unit can analyze the user's social media activity and recognize relevant product information. In this way, relevant product information can be recognized by analyzing the user's social media activity. Some or all of the above processing in the recognition unit may be performed using AI, for example, or without using AI. For example, the recognition unit can input the user's social media activity data into a generating AI and have the generating AI recognize relevant product information.

[0088] The acquisition unit can estimate the user's emotions and adjust the timing of acquiring bidding data based on the estimated emotions. For example, if the user is stressed, the acquisition unit can adjust the acquisition timing to reduce the user's burden. For example, if the user is relaxed, the acquisition unit can acquire bidding data at the optimal time. Also, if the user is in a hurry, the acquisition unit can acquire bidding data quickly. For example, the acquisition unit can estimate the user's emotions and adjust the acquisition timing based on the estimated emotions. This reduces the user's burden by adjusting the timing of acquiring bidding data based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input user emotion data into a generative AI and have the generative AI adjust the timing of acquiring bidding data.

[0089] The acquisition unit can improve the accuracy of acquisition by referring to past bidding results when acquiring bidding project data. For example, the acquisition unit can analyze past bidding results and acquire similar bidding project data. For example, the acquisition unit can improve the accuracy of acquisition by referring to past bidding results. The acquisition unit can also acquire bidding project data based on past bidding results. For example, the acquisition unit can analyze past bidding results and acquire similar bidding project data. This allows the acquisition accuracy of bidding project data to be improved by referring to past bidding results. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without using AI. For example, the acquisition unit can input past bidding result data into a generating AI, and the generating AI can improve the accuracy of acquiring bidding project data.

[0090] The acquisition unit can broaden the scope of acquisition by referring to publicly available information from different municipalities when acquiring bidding project data. For example, the acquisition unit can broaden the scope of acquisition by analyzing publicly available information from different municipalities. For example, the acquisition unit can improve the acquisition accuracy by referring to bidding project data from different municipalities. The acquisition unit can also acquire bidding project data based on publicly available information from different municipalities. For example, the acquisition unit can broaden the scope of acquisition by analyzing publicly available information from different municipalities. This allows the acquisition of bidding project data to be broadened by referring to publicly available information from different municipalities. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without using AI. For example, the acquisition unit can input publicly available information from different municipalities into a generating AI, and the generating AI can broaden the scope of acquisition of bidding project data.

[0091] The acquisition unit can estimate the user's emotions and determine the priority of the bid data to acquire based on the estimated user emotions. For example, if the user is stressed, the acquisition unit will prioritize acquiring important bid data. For example, if the user is relaxed, the acquisition unit can prioritize acquiring detailed bid data. The acquisition unit can also determine the priority of the bid data to acquire quickly if the user is in a hurry. For example, the acquisition unit can estimate the user's emotions and determine the priority of the bid data based on the estimated emotions. This allows for the priority acquisition of important bid data by determining the priority of the bid data based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or not using AI. For example, the acquisition unit can input user emotion data into a generative AI and have the generative AI determine the priority of the bid data.

[0092] The acquisition unit can prioritize the acquisition of highly relevant data by considering the user's geographical location information when acquiring bidding project data. For example, the acquisition unit can prioritize the acquisition of highly relevant bidding project data based on the user's geographical location information. For example, the acquisition unit can acquire the most relevant bidding project data based on the user's current location. The acquisition unit can also improve the accuracy of acquiring bidding project data by considering the user's geographical location information. For example, the acquisition unit can prioritize the acquisition of highly relevant bidding project data based on the user's geographical location information. This allows for the priority acquisition of highly relevant bidding project data by considering the user's geographical location information. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input the user's geographical location information into a generating AI, which can then prioritize the acquisition of highly relevant bidding project data.

[0093] The acquisition unit can analyze the user's social media activity and acquire relevant data when acquiring bidding project data. For example, the acquisition unit can analyze the user's social media activity and acquire relevant bidding project data. For example, the acquisition unit can improve the accuracy of acquiring bidding project data based on the content of the user's social media posts. The acquisition unit can also acquire bidding project data by referring to the user's social media activity. For example, the acquisition unit can analyze the user's social media activity and acquire relevant bidding project data. In this way, relevant bidding project data can be acquired by analyzing the user's social media activity. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without using AI. For example, the acquisition unit can input the user's social media activity data into a generating AI and have the generating AI acquire relevant bidding project data.

[0094] The extraction unit can estimate the user's emotions and adjust the extraction criteria for suggested items based on the estimated user emotions. For example, if the user is stressed, the extraction unit can provide simple extraction criteria and extract suggested items. For example, if the user is relaxed, the extraction unit can provide detailed extraction criteria and extract suggested items. Also, if the user is in a hurry, the extraction unit can quickly extract suggested items. For example, the extraction unit can estimate the user's emotions and adjust the extraction criteria for suggested items based on the estimated emotions. This allows for efficient extraction of suggested items by adjusting the extraction criteria based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the extraction unit may be performed using AI, for example, or not using AI. For example, the extraction unit can input user emotion data into a generative AI and have the generative AI adjust the extraction criteria for suggested items.

[0095] The extraction unit can improve the extraction accuracy by referring to past proposal results when extracting potential proposals. For example, the extraction unit can analyze past proposal results and extract similar potential proposals. For example, the extraction unit can improve the extraction accuracy by referring to past proposal results. The extraction unit can also extract potential proposals based on past proposal results. For example, the extraction unit can analyze past proposal results and extract similar potential proposals. This allows the extraction accuracy of potential proposals to be improved by referring to past proposal results. Some or all of the above processing in the extraction unit may be performed using AI, for example, or without AI. For example, the extraction unit can input past proposal result data into a generating AI, and the generating AI can improve the extraction accuracy of potential proposals.

[0096] The extraction unit can broaden the scope of its extraction by referring to project information from different industries when extracting potential projects. For example, the extraction unit can broaden the scope of its extraction by analyzing project information from different industries. For example, the extraction unit can improve the extraction accuracy by referring to potential projects from different industries. The extraction unit can also extract potential projects based on project information from different industries. For example, the extraction unit can broaden the scope of its extraction by analyzing project information from different industries. This allows the extraction of potential projects to be broadened by referring to project information from different industries. Some or all of the above processing in the extraction unit may be performed using AI, for example, or without AI. For example, the extraction unit can input project information from different industries into a generating AI, and the generating AI can broaden the scope of projects to be extracted.

[0097] The extraction unit can estimate the user's emotions and determine the priority of cases to extract based on the estimated emotions. For example, if the user is stressed, the extraction unit can prioritize extracting important cases. For example, if the user is relaxed, the extraction unit can prioritize extracting detailed cases. Also, if the user is in a hurry, the extraction unit can determine the priority of cases to extract quickly. For example, the extraction unit can estimate the user's emotions and determine the priority of cases based on the estimated emotions. This allows for the priority extraction of important cases by determining the priority of cases based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the extraction unit may be performed using AI, for example, or not using AI. For example, the extraction unit can input user emotion data into a generative AI and have the generative AI determine the priority of cases.

[0098] The extraction unit can prioritize extracting highly relevant cases by considering the user's geographical location information when extracting potential cases. For example, the extraction unit can prioritize extracting highly relevant cases based on the user's geographical location information. For example, the extraction unit can extract the most suitable cases based on the user's current location. The extraction unit can also improve the accuracy of extracting potential cases by considering the user's geographical location information. For example, the extraction unit can prioritize extracting highly relevant cases based on the user's geographical location information. This allows for the priority extraction of highly relevant cases by considering the user's geographical location information. Some or all of the above processing in the extraction unit may be performed using AI, for example, or without AI. For example, the extraction unit can input the user's geographical location information into a generating AI, which can then prioritize extracting highly relevant cases.

[0099] The extraction unit can analyze the user's social media activity and extract relevant cases when extracting potential cases. For example, the extraction unit can analyze the user's social media activity and extract relevant potential cases. For example, the extraction unit can improve the accuracy of extracting potential cases based on the content of the user's social media posts. The extraction unit can also extract potential cases by referring to the user's social media activity. For example, the extraction unit can analyze the user's social media activity and extract relevant potential cases. This allows for the extraction of relevant cases by analyzing the user's social media activity. Some or all of the above processing in the extraction unit may be performed using AI, for example, or without AI. For example, the extraction unit can input the user's social media activity data into a generating AI and have the generating AI extract relevant potential cases.

[0100] The adjustment unit can estimate the user's emotions and change the method of adjusting the suggested content based on the estimated emotions. For example, if the user is stressed, the adjustment unit can provide a simple adjustment method and adjust the suggested content. For example, if the user is relaxed, the adjustment unit can provide a detailed adjustment method and adjust the suggested content. The adjustment unit can also quickly adjust the suggested content if the user is in a hurry. For example, the adjustment unit can estimate the user's emotions and change the method of adjusting the suggested content based on the estimated emotions. This allows for efficient adjustment of the suggested content by changing the adjustment method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the adjustment unit may be performed using AI, for example, or without AI. For example, the adjustment unit can input user emotion data into the generative AI and have the generative AI change the method of adjusting the suggested content.

[0101] The adjustment unit can improve the accuracy of adjustments when adjusting the proposed content by referring to past adjustment history. For example, the adjustment unit can analyze past adjustment history and adjust similar proposed content. For example, the adjustment unit can improve the accuracy of adjustments by referring to past adjustment history. The adjustment unit can also adjust the proposed content based on past adjustment history. For example, the adjustment unit can analyze past adjustment history and adjust similar proposed content. In this way, the accuracy of adjusting the proposed content can be improved by referring to past adjustment history. Some or all of the above processing in the adjustment unit may be performed using AI, for example, or without using AI. For example, the adjustment unit can input past adjustment history data into a generating AI, and the generating AI can improve the accuracy of adjusting the proposed content.

[0102] The adjustment unit can broaden the scope of adjustments when adjusting the proposed content by referring to adjustment methods from different industries. For example, the adjustment unit can broaden the scope of adjustments by analyzing adjustment methods from different industries. For example, the adjustment unit can improve the accuracy of adjustments by referring to adjustment methods from different industries. The adjustment unit can also adjust the proposed content based on adjustment methods from different industries. For example, the adjustment unit can broaden the scope of adjustments by analyzing adjustment methods from different industries. This allows the adjustment scope of the proposed content to be broadened by referring to adjustment methods from different industries. Some or all of the above processing in the adjustment unit may be performed using AI, for example, or without using AI. For example, the adjustment unit can input adjustment methods from different industries into a generating AI, and the generating AI can broaden the scope of adjustments to the proposed content.

[0103] The adjustment unit can estimate the user's emotions and determine the priority of suggestions to adjust based on the estimated emotions. For example, if the user is stressed, the adjustment unit will prioritize important suggestions. For example, if the user is relaxed, the adjustment unit can prioritize detailed suggestions. The adjustment unit can also determine the priority of suggestions to adjust quickly if the user is in a hurry. For example, the adjustment unit can estimate the user's emotions and determine the priority of suggestions based on the estimated emotions. This allows for prioritizing important suggestions based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the adjustment unit may be performed using AI, for example, or without AI. For example, the adjustment unit can input user emotion data into a generative AI and have the generative AI determine the priority of suggestions.

[0104] The adjustment unit can prioritize adjusting the content to be highly relevant by considering the user's geographical location information when adjusting the proposed content. For example, the adjustment unit can prioritize adjusting the proposed content to be highly relevant based on the user's geographical location information. For example, the adjustment unit can adjust the optimal proposed content based on the user's current location. The adjustment unit can also improve the accuracy of adjusting the proposed content by considering the user's geographical location information. For example, the adjustment unit can prioritize adjusting the proposed content to be highly relevant based on the user's geographical location information. This allows for prioritizing the adjustment of highly relevant proposed content by considering the user's geographical location information. Some or all of the above processing in the adjustment unit may be performed using AI, for example, or without using AI. For example, the adjustment unit can input the user's geographical location information into a generating AI, and have the generating AI prioritize adjusting the proposed content to be highly relevant.

[0105] The adjustment unit can analyze the user's social media activity and adjust relevant content when adjusting the proposed content. For example, the adjustment unit can analyze the user's social media activity and adjust the relevant proposed content. For example, the adjustment unit can improve the accuracy of adjusting the proposed content based on the user's social media posts. The adjustment unit can also refer to the user's social media activity and adjust the proposed content. For example, the adjustment unit can analyze the user's social media activity and adjust the relevant proposed content. In this way, the relevant proposed content can be adjusted by analyzing the user's social media activity. Some or all of the above processing in the adjustment unit may be performed using AI, for example, or without AI. For example, the adjustment unit can input the user's social media activity data into a generating AI and have the generating AI adjust the relevant proposed content.

[0106] The creation unit can estimate the user's emotions and adjust the method of creating the response document based on the estimated emotions. For example, if the user is stressed, the creation unit can provide a simple method and create the response document. For example, if the user is relaxed, the creation unit can provide a detailed method and create the response document. The creation unit can also quickly create the response document if the user is in a hurry. For example, the creation unit can estimate the user's emotions and adjust the method of creating the response document based on the estimated emotions. This allows for efficient creation of the response document by adjusting the method of creation based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the creation unit may be performed using AI, for example, or without AI. For example, the creation unit can input user emotion data into a generative AI and have the generative AI adjust the method of creating the response document.

[0107] The creation unit can improve the accuracy of its response document creation by referring to past creation history. For example, the creation unit can analyze past creation history and create similar response documents. For example, the creation unit can improve the accuracy of its response document creation by referring to past creation history. The creation unit can also create response documents based on past creation history. For example, the creation unit can analyze past creation history and create similar response documents. This allows the accuracy of response document creation to be improved by referring to past creation history. Some or all of the above processes in the creation unit may be performed using AI, for example, or without AI. For example, the creation unit can input past creation history data into a generation AI, and the generation AI can improve the accuracy of response document creation.

[0108] The creation unit can broaden its range of creation by referencing creation methods from different industries when creating response documents. For example, the creation unit can broaden its range by analyzing creation methods from different industries. For example, the creation unit can improve the accuracy of creation by referencing creation methods from different industries. The creation unit can also create response documents based on creation methods from different industries. For example, the creation unit can broaden its range by analyzing creation methods from different industries. This allows the creation of response documents to be broadened by referencing creation methods from different industries. Some or all of the above processes in the creation unit may be performed using AI, for example, or without AI. For example, the creation unit can input creation methods from different industries into a generation AI, and the generation AI can broaden the range of response documents it can create.

[0109] The creation unit can estimate the user's emotions and determine the priority of the response documents to be created based on the estimated emotions. For example, if the user is stressed, the creation unit can prioritize creating important response documents. For example, if the user is relaxed, the creation unit can prioritize creating detailed response documents. Also, if the user is in a hurry, the creation unit can prioritize creating response documents quickly. For example, the creation unit can estimate the user's emotions and determine the priority of the response documents based on the estimated emotions. This allows for the prioritization of important response documents based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the creation unit may be performed using AI, for example, or not using AI. For example, the creation unit can input user emotion data into a generative AI and have the generative AI determine the priority of the response documents.

[0110] The creation unit can prioritize creating highly relevant response documents by considering the user's geographical location information when creating response documents. For example, the creation unit can prioritize creating highly relevant response documents based on the user's geographical location information. For example, the creation unit can create the optimal response document based on the user's current location. The creation unit can also improve the accuracy of response document creation by considering the user's geographical location information. For example, the creation unit can prioritize creating highly relevant response documents based on the user's geographical location information. This allows for the prioritization of highly relevant response documents by considering the user's geographical location information. Some or all of the above processing in the creation unit may be performed using AI, for example, or without AI. For example, the creation unit can input the user's geographical location information into a generation AI, which can then prioritize creating highly relevant response documents.

[0111] The creation unit can analyze the user's social media activity and create relevant response documents when creating response documents. For example, the creation unit can analyze the user's social media activity and create relevant response documents. For example, the creation unit can improve the accuracy of response document creation based on the user's social media posts. The creation unit can also create response documents by referring to the user's social media activity. For example, the creation unit can analyze the user's social media activity and create relevant response documents. In this way, relevant response documents can be created by analyzing the user's social media activity. Some or all of the above processing in the creation unit may be performed using AI, for example, or without AI. For example, the creation unit can input the user's social media activity data into a generation AI and have the generation AI create relevant response documents.

[0112] The description section can estimate the user's emotions and adjust the way it presents elements that support the suggestion based on the estimated emotions. For example, if the user is stressed, the description section can provide a simple description and include elements that support the suggestion. For example, if the user is relaxed, the description section can provide a detailed description and include elements that support the suggestion. Also, if the user is in a hurry, the description section can quickly include elements that support the suggestion. For example, the description section can estimate the user's emotions and adjust the way it presents elements that support the suggestion based on the estimated emotions. This allows for efficient presentation of the suggestion by adjusting the way it presents elements that support the suggestion based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the description section may be performed using AI, for example, or without AI. For example, the description section can input user emotion data into a generating AI, which can then adjust how elements that support the suggestion are described.

[0113] The description section can improve the accuracy of descriptions by referring to past description history when describing elements that support the proposal. For example, the description section can analyze past description history and describe elements that support similar proposals. For example, the description section can improve the accuracy of descriptions by referring to past description history. The description section can also describe elements that support the proposal based on past description history. For example, the description section can analyze past description history and describe elements that support similar proposals. This allows the description section to improve the accuracy of descriptions of elements that support the proposal by referring to past description history. Some or all of the above processing in the description section may be performed using AI, for example, or without AI. For example, the description section can input past description history data into a generating AI, and the generating AI can improve the accuracy of descriptions of elements that support the proposal.

[0114] The writing unit can estimate the user's emotions and determine the priority of elements to be written based on the estimated emotions. For example, if the user is stressed, the writing unit will prioritize important elements. For example, if the user is relaxed, the writing unit can prioritize detailed elements. Also, if the user is in a hurry, the writing unit can determine the priority of elements to be written quickly. For example, the writing unit can estimate the user's emotions and determine the priority of elements to be written based on the estimated emotions. This allows important elements to be written preferentially by determining the priority of elements to be written based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the writing unit may be performed using AI, for example, or not using AI. For example, the writing unit can input user emotion data into a generative AI and have the generative AI determine the priority of elements to be written.

[0115] The description section can prioritize the inclusion of highly relevant elements when describing elements that support the proposal, taking into account the user's geographical location information. For example, the description section can prioritize the inclusion of highly relevant elements based on the user's geographical location information. For example, the description section can describe the most relevant elements based on the user's current location. The description section can also improve the accuracy of element description by considering the user's geographical location information. For example, the description section can prioritize the inclusion of highly relevant elements based on the user's geographical location information. This allows for the prioritization of highly relevant elements by considering the user's geographical location information. Some or all of the above processing in the description section may be performed using AI, for example, or without AI. For example, the description section can input the user's geographical location information into a generating AI, which can then prioritize the inclusion of highly relevant elements.

[0116] The presentation unit can estimate the user's emotions and adjust the creation method of presentation materials and talk scripts based on the estimated emotions. For example, if the user is stressed, the presentation unit can provide a simple creation method to generate presentation materials and talk scripts. For example, if the user is relaxed, the presentation unit can provide a detailed creation method to generate presentation materials and talk scripts. The presentation unit can also quickly create presentation materials and talk scripts if the user is in a hurry. For example, the presentation unit can estimate the user's emotions and adjust the creation method of presentation materials and talk scripts based on the estimated emotions. This allows for the efficient creation of presentation materials and talk scripts by adjusting the creation method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the presentation unit may be performed using AI, for example, or without AI. For example, the presentation department can input user emotion data into a generating AI, which can then adjust how presentation materials and talk scripts are created.

[0117] The presentation unit can improve the accuracy of creating presentation materials and talk scripts by referring to past creation history. For example, the presentation unit can analyze past creation history and create similar presentation materials and talk scripts. For example, the presentation unit can improve the accuracy of creating presentation materials and talk scripts by referring to past creation history. The presentation unit can also create presentation materials and talk scripts based on past creation history. For example, the presentation unit can analyze past creation history and create similar presentation materials and talk scripts. This allows the accuracy of creating presentation materials and talk scripts to be improved by referring to past creation history. Some or all of the above processes in the presentation unit may be performed using AI, for example, or without AI. For example, the presentation unit can input past creation history data into a generation AI, and the generation AI can improve the accuracy of creating presentation materials and talk scripts.

[0118] The presentation unit can estimate the user's emotions and prioritize the presentation materials and talk scripts to be created based on those estimated emotions. For example, if the user is stressed, the presentation unit will prioritize creating important presentation materials and talk scripts. For example, if the user is relaxed, the presentation unit can prioritize creating detailed presentation materials and talk scripts. Also, if the user is in a hurry, the presentation unit can prioritize creating presentation materials and talk scripts quickly. For example, the presentation unit can estimate the user's emotions and prioritize the presentation materials and talk scripts based on those estimated emotions. This allows for the prioritization of important presentation materials and talk scripts based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the presentation unit may be performed using AI, for example, or without AI. For example, the presentation department can input user emotion data into a generating AI, which can then determine the priority of presentation materials and talk scripts.

[0119] The presentation unit can prioritize the creation of presentation materials and scripts that are highly relevant, taking into account the user's geographical location information when creating presentation materials and scripts. For example, the presentation unit can prioritize the creation of highly relevant presentation materials and scripts based on the user's geographical location information. For example, the presentation unit can create optimal presentation materials and scripts based on the user's current location. The presentation unit can also improve the accuracy of presentation material and script creation by considering the user's geographical location information. For example, the presentation unit can prioritize the creation of highly relevant presentation materials and scripts based on the user's geographical location information. This allows for the priority creation of highly relevant presentation materials and scripts by considering the user's geographical location information. Some or all of the above processing in the presentation unit may be performed using AI, or not. For example, the presentation unit can input the user's geographical location information into a generating AI, which can then prioritize the creation of highly relevant presentation materials and scripts.

[0120] The analysis unit can estimate the user's emotions and adjust the bidding result analysis method based on the estimated user emotions. For example, if the user is stressed, the analysis unit can provide a simple analysis method to analyze the bidding results. For example, if the user is relaxed, the analysis unit can provide a detailed analysis method to analyze the bidding results. The analysis unit can also quickly analyze the bidding results if the user is in a hurry. For example, the analysis unit can estimate the user's emotions and adjust the bidding result analysis method based on the estimated emotions. This allows for efficient analysis of bidding results by adjusting the bidding result analysis method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input user emotion data into a generative AI and have the generative AI adjust the bidding result analysis method.

[0121] The analysis unit can improve the accuracy of its analysis of bid results by referring to past analysis history. For example, the analysis unit can analyze past analysis history and analyze similar bid results. For example, the analysis unit can improve the accuracy of its analysis by referring to past analysis history. The analysis unit can also analyze bid results based on past analysis history. For example, the analysis unit can analyze past analysis history and analyze similar bid results. This allows the analysis unit to improve the accuracy of its bid result analysis by referring to past analysis history. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input past analysis history data into a generating AI, and the generating AI can improve the accuracy of its bid result analysis.

[0122] The analysis unit can estimate the user's emotions and determine the priority of bid results to analyze based on the estimated emotions. For example, if the user is stressed, the analysis unit may prioritize analyzing important bid results. For example, if the user is relaxed, the analysis unit may prioritize analyzing detailed bid results. The analysis unit may also determine the priority of bid results to analyze quickly if the user is in a hurry. For example, the analysis unit can estimate the user's emotions and determine the priority of bid results based on the estimated emotions. This allows for the prioritization of important bid results by determining the priority of bid results based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or not using AI. For example, the analysis unit can input user emotion data into a generative AI and have the generative AI determine the priority of bid results.

[0123] The analysis unit can prioritize the analysis of highly relevant results by considering the user's geographical location information when analyzing bidding results. For example, the analysis unit can prioritize the analysis of highly relevant bidding results based on the user's geographical location information. For example, the analysis unit can analyze the optimal bidding results based on the user's current location. The analysis unit can also improve the accuracy of the bidding result analysis by considering the user's geographical location information. For example, the analysis unit can prioritize the analysis of highly relevant bidding results based on the user's geographical location information. This allows for the prioritization of highly relevant bidding results by considering the user's geographical location information. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the user's geographical location information into a generating AI, and have the generating AI prioritize the analysis of highly relevant bidding results.

[0124] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0125] The AI ​​agent system can also be equipped with a feedback function. This function can collect feedback from relevant departments and stakeholders after proposals and responses have been created, and incorporate this feedback into future proposals. For example, the feedback function can collect evaluations and suggestions for improvement regarding the content of proposals, and consider these when creating future proposals. Furthermore, the feedback function can analyze the results after proposal submission to identify success and failure factors. Additionally, the feedback function can collect customer reactions and evaluations after proposal submission and utilize this information in future proposals. In this way, incorporating a feedback function can improve the quality of proposals and responses, which can be used to enhance future proposal activities.

[0126] The AI ​​agent system can also be equipped with a learning unit. This unit can learn from past proposals and responses to improve the accuracy of proposal creation. For example, it can analyze the characteristics of past successful proposals and use this information when creating future proposals. It can also identify the causes of past failed proposals and prevent the same mistakes from being repeated. Furthermore, the learning unit can optimize the proposal creation process and learn how to create proposals efficiently. Thus, incorporating a learning unit can improve both the accuracy and efficiency of proposal creation.

[0127] The AI ​​agent system can also be equipped with a notification function. This notification function can inform the person in charge about the status of proposals and responses, as well as their submission deadlines. For example, the notification function can send a reminder to the person in charge if the proposal is behind schedule. It can also issue an alert when the submission deadline is approaching. Furthermore, the notification function can notify the person in charge when the results are available after the proposal has been submitted. In this way, by incorporating a notification function, the status of proposals and responses can be monitored, and submission deadlines can be met.

[0128] The AI ​​agent system can also be equipped with a simulation unit. This simulation unit can simulate the content of a proposal and predict its success rate. For example, it can calculate the success rate based on the proposal's content and referencing past data. It can also simulate how the success rate changes when the proposal's content is modified. Furthermore, the simulation unit can perform simulations to optimize the proposal's content. Thus, by incorporating a simulation unit, the success rate of the proposal can be increased.

[0129] The AI ​​agent system can also include a collaboration section. This section provides an environment where multiple team members can work together during proposal creation. For example, it can share proposal drafts and allow team members to edit them in real time. It can also support communication between team members, facilitating the exchange of ideas and feedback. Furthermore, it can visualize the progress of proposal creation, enabling team members to work efficiently. In this way, incorporating a collaboration section can improve the efficiency and quality of proposal creation.

[0130] The AI ​​agent system can further use emotion estimation capabilities to estimate the emotions of the person creating the proposal and adjust the work environment accordingly. For example, if the person is stressed, the system will break down tasks to reduce the workload. If the person is relaxed, the system can provide detailed information to improve the quality of the proposal. Furthermore, if the person is in a hurry, the system can provide support to help them work quickly. In this way, by using emotion estimation capabilities, the system can provide a work environment tailored to the person's emotions, improving the efficiency and quality of proposal creation.

[0131] The AI ​​agent system can further adjust the content of proposals using its emotion estimation function. For example, if the content of a proposal is stressful for the person in charge, the system will simplify it to reduce the burden on the person. Conversely, if the content of the proposal is relaxing for the person in charge, the system can add detailed information to improve the quality of the proposal. Furthermore, if the content of the proposal needs to be prepared urgently for the person in charge, the system can support them in creating it quickly. In this way, by using the emotion estimation function, proposals can be provided that are tailored to the emotions of the person in charge, improving the efficiency and quality of proposal creation.

[0132] The AI ​​agent system can further adjust the timing of proposal submissions using emotion estimation capabilities. For example, if the person in charge is feeling stressed, the system will negotiate for an extension of the submission deadline. Conversely, if the person in charge is relaxed, the system will submit the proposal earlier, allowing for a more relaxed response. Furthermore, if the person in charge is in a hurry, the system can provide support to help them submit the proposal quickly. In this way, by using emotion estimation capabilities, the system can adjust the timing of proposal submissions according to the person in charge's emotions, improving the efficiency and quality of proposal creation.

[0133] The AI ​​agent system can further adjust the proposal review process using emotion estimation capabilities. For example, if the reviewer is stressed, the system can provide a simplified review method to reduce their burden. Conversely, if the reviewer is relaxed, the system can provide a more detailed review method to improve the quality of the proposal. Furthermore, if the reviewer is in a hurry, the system can provide support for a quick review. In this way, by using emotion estimation capabilities, the system can provide a proposal review method tailored to the reviewer's emotions, improving the efficiency and quality of proposal creation.

[0134] The AI ​​agent system can further adjust the feedback method for proposals using emotion estimation capabilities. For example, if the person in charge is stressed, the system will provide a simpler feedback method to reduce their burden. Conversely, if the person in charge is relaxed, the system will provide a more detailed feedback method to improve the quality of the proposal. Furthermore, if the person in charge is in a hurry, the system can provide support for providing feedback quickly. In this way, by using emotion estimation capabilities, the system can provide proposal feedback methods tailored to the person in charge's emotions, improving the efficiency and quality of proposal creation.

[0135] The following briefly describes the processing flow for example form 2.

[0136] Step 1: The recognition unit recognizes the company's product information. This product information includes product information, service information, and technical information. The recognition unit uses image recognition technology, text recognition technology, and speech recognition technology to recognize product information. For example, image recognition technology is used to recognize product images and obtain product information. Text recognition technology recognizes the contents of proposals and specifications. Speech recognition technology recognizes the contents of presentations. Step 2: The acquisition unit crawls publicly available information from each local government based on the information recognized by the recognition unit and obtains bidding project data. The acquisition unit uses web crawlers, APIs, and scraping techniques to obtain bidding project data from each local government's website and database. For example, it may periodically visit each local government's website using a web crawler to obtain new bidding project data. It may use APIs to obtain bidding project data in real time. It may use scraping techniques to obtain bidding project data from web pages. Step 3: The extraction unit extracts projects that the company can propose based on the data acquired by the acquisition unit. Projects that can be proposed are extracted based on factors such as the size and type of the project and the conditions of the proposal. For example, it determines whether the size of the project is within the company's capabilities and extracts projects that can be proposed. Project types include product provision, service provision, technology provision, etc., and the company extracts projects of the type it can handle. Proposal conditions include deadlines and budgets, and the company extracts projects that meet the conditions it can meet. Step 4: The Coordination Department organizes the proposals for the projects selected by the Extraction Department, coordinates with the relevant departments, and performs cost estimations. The Coordination Department holds meetings with the relevant departments to organize the proposals. It collects the necessary data to perform cost estimations. It uses project management tools to organize the proposals. For example, it reviews the proposals in detail through meetings with the relevant departments and makes necessary adjustments. It performs cost estimations based on data such as material costs and labor costs. Step 5: The creation team, based on the proposals organized by the coordination team, will write the proposals in the format specified for each bidding project and create a response document. The response document will include the proposal details, conditions, and track record. For example, the proposal details will be described in detail, and the response document will be created according to the specified format. Conditions include deadlines and budgets, and this data will be collected and included in the response document. Track record includes past project success stories and customer evaluations, and this data will be referenced and included in the response document.

[0137] 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.

[0138] Data generation model 58 is a form of 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> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. 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 (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0139] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0140] Each of the multiple elements described above, including the recognition unit, acquisition unit, extraction unit, adjustment unit, and creation unit, is implemented in at least one of the smart device 14 and the data processing device 12. For example, the recognition unit is implemented by the control unit 46A of the smart device 14 and recognizes the company's product information. The acquisition unit is implemented by the specific processing unit 290 of the data processing device 12 and obtains bidding project data by crawling publicly available information from each local government. The extraction unit is implemented by the specific processing unit 290 of the data processing device 12 and extracts projects that the company can propose based on the acquired data. The adjustment unit is implemented by the control unit 46A of the smart device 14 and organizes the proposal content, coordinates with the relevant department, and calculates costs. The creation unit is implemented by the specific processing unit 290 of the data processing device 12 and writes the proposal content in a format specified for each bidding project and creates a response document. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0141] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0142] 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.

[0143] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0144] 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.

[0145] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0146] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0147] 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.

[0148] 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 by the processor 28. The storage 32 stores the specific processing program 56.

[0149] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0150] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0151] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0152] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0153] 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.

[0154] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0155] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0156] Each of the multiple elements described above, including the recognition unit, acquisition unit, extraction unit, adjustment unit, and creation unit, is implemented in at least one of the smart glasses 214 and the data processing device 12. For example, the recognition unit is implemented by the control unit 46A of the smart glasses 214 and recognizes the company's product information. The acquisition unit is implemented by the specific processing unit 290 of the data processing device 12 and obtains bidding project data by crawling publicly available information from each local government. The extraction unit is implemented by the specific processing unit 290 of the data processing device 12 and extracts projects that the company can propose based on the acquired data. The adjustment unit is implemented by the control unit 46A of the smart glasses 214 and organizes the proposal content, coordinates with the relevant department, and performs cost estimation. The creation unit is implemented by the specific processing unit 290 of the data processing device 12 and writes the proposal content in a format specified for each bidding project and creates a response document. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0157] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0158] 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.

[0159] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0160] 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.

[0161] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0162] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0163] 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.

[0164] 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.

[0165] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0166] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0167] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0168] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0169] 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.

[0170] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0171] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0172] Each of the multiple elements described above, including the recognition unit, acquisition unit, extraction unit, adjustment unit, and creation unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the recognition unit is implemented by the control unit 46A of the headset terminal 314 and recognizes the company's product information. The acquisition unit is implemented by the specific processing unit 290 of the data processing unit 12 and acquires bidding project data by crawling publicly available information from each local government. The extraction unit is implemented by the specific processing unit 290 of the data processing unit 12 and extracts projects that the company can propose based on the acquired data. The adjustment unit is implemented by the control unit 46A of the headset terminal 314 and organizes the proposal content, coordinates with the relevant department, and calculates costs. The creation unit is implemented by the specific processing unit 290 of the data processing unit 12 and writes the proposal content in a format specified for each bidding project and creates a response document. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0173] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0174] 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.

[0175] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0176] 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.

[0177] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0178] 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 image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0179] 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.

[0180] 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. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0181] 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.

[0182] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0183] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0184] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0185] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0186] 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.

[0187] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0188] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0189] Each of the multiple elements described above, including the recognition unit, acquisition unit, extraction unit, adjustment unit, and creation unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the recognition unit is implemented by the control unit 46A of the robot 414 and recognizes the company's product information. The acquisition unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and acquires bidding project data by crawling publicly available information from each local government. The extraction unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and extracts projects that the company can propose based on the acquired data. The adjustment unit is implemented by, for example, the control unit 46A of the robot 414 and organizes the proposal content, coordinates with the relevant department, and calculates costs. The creation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and writes the proposal content in a format specified for each bidding project and creates a response document. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0190] 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.

[0191] Figure 9 shows the 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.

[0192] 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.

[0193] 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.

[0194] 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, and motorcycles, 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 based, for example, 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.

[0195] 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."

[0196] 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.

[0197] 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 method for the specific process may be used, which includes computer 22 and multiple other computers.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0206] 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 other things 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.

[0207] 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.

[0208] (Note 1) A recognition unit that recognizes the company's product information, Based on the information recognized by the aforementioned recognition unit, the acquisition unit crawls publicly available information of each local government and obtains bidding project data. Based on the data acquired by the aforementioned acquisition unit, an extraction unit extracts projects that the company can propose, For the cases extracted by the aforementioned extraction unit, the coordination unit organizes the proposed content, coordinates with the relevant departments, and performs cost estimations. The system includes a creation unit that, based on the proposal content organized by the aforementioned adjustment unit, records the proposal content in a format specified for each bidding project and creates a response document. A system characterized by the following features. (Note 2) The proposal includes sections for describing strengths, differentiation from competitors, conditions, and achievements that support the proposal, depending on the content. The system described in Appendix 1, characterized by the features described herein. (Note 3) It includes a presentation unit that creates presentation materials and talk scripts, and delivers the presentation as needed. The system described in Appendix 1, characterized by the features described herein. (Note 4) We have an analysis department that examines the reasons for success and failure based on the bidding results and uses that information to improve future strategies. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned recognition unit, The system estimates the user's emotions and adjusts the accuracy of product information recognition based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned recognition unit, When recognizing product information, we improve recognition accuracy by referring to the history of past proposals and specifications. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned recognition unit, When recognizing product information, referencing product information from different industries broadens the scope of understanding. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned recognition unit, It estimates the user's emotions and determines the priority of product information to recognize based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned recognition unit, When recognizing product information, the system prioritizes recognizing highly relevant information by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned recognition unit, When recognizing product information, the system analyzes the user's social media activity and identifies relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 11) The acquisition unit is, The system estimates user sentiment and adjusts the timing of acquiring bidding data based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 12) The acquisition unit is, When acquiring bidding project data, we improve the accuracy of the acquisition by referring to past bidding results. The system described in Appendix 1, characterized by the features described herein. (Note 13) The acquisition unit is, When acquiring bidding project data, broaden the scope of acquisition by referring to publicly available information from different municipalities. The system described in Appendix 1, characterized by the features described herein. (Note 14) The acquisition unit is, The system estimates user sentiment and determines the priority of bid data to acquire based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 15) The acquisition unit is, When acquiring bidding data, the system prioritizes the acquisition of highly relevant data by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 16) The acquisition unit is, When acquiring bidding project data, we analyze users' social media activity and obtain relevant data. The system described in Appendix 1, characterized by the features described herein. (Note 17) The extraction unit is We estimate the user's emotions and adjust the criteria for selecting suitable offers based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The extraction unit is When extracting potential projects, we improve extraction accuracy by referring to past proposal results. The system described in Appendix 1, characterized by the features described herein. (Note 19) The extraction unit is When extracting potential projects, refer to project information from different industries to broaden the scope of the selection. The system described in Appendix 1, characterized by the features described herein. (Note 20) The extraction unit is It estimates user sentiment and determines the priority of cases to extract based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 21) The extraction unit is When extracting potential projects, the system prioritizes selecting projects that are highly relevant, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 22) The extraction unit is When extracting potential projects, the system analyzes the user's social media activity to identify relevant projects. The system described in Appendix 1, characterized by the features described herein. (Note 23) The adjustment unit is, The system estimates the user's emotions and modifies how the suggestions are adjusted based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The adjustment unit is, When adjusting the proposed content, refer to past adjustment history to improve the accuracy of the adjustments. The system described in Appendix 1, characterized by the features described herein. (Note 25) The adjustment unit is, When refining the proposal, refer to adjustment methods from different industries to broaden the scope of adjustments. The system described in Appendix 1, characterized by the features described herein. (Note 26) The adjustment unit is, It estimates the user's emotions and prioritizes suggestions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The adjustment unit is, When refining the proposal, prioritize adjusting content that is highly relevant, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 28) The adjustment unit is, When refining the proposal, we analyze the user's social media activity and adjust the content accordingly. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned creation unit, We estimate the user's emotions and adjust the response format based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned creation unit, When creating a response, refer to past creation history to improve accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned creation unit, When preparing a response, broaden your approach by referencing response methods from different industries. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned creation unit, The system estimates the user's emotions and determines the priority of the response documents to be created based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned creation unit, When creating response documents, the system prioritizes creating highly relevant documents by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned creation unit, When creating response documents, we analyze users' social media activity and create relevant response documents. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned section is, We estimate the user's emotions and adjust how we describe elements that support the suggestion based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 36) The aforementioned section is, When describing elements that support the proposal, refer to past descriptions to improve the accuracy of the description. The system described in Appendix 2, characterized by the features described herein. (Note 37) The aforementioned section is, The system estimates the user's emotions and determines the priority of elements to include based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 38) The aforementioned section is, When listing elements that support the proposal, prioritize listing elements that are highly relevant, taking into account the user's geographical location. The system described in Appendix 2, characterized by the features described herein. (Note 39) The aforementioned presentation section is, It estimates user emotions and adjusts how presentation materials and talk scripts are created based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 40) The aforementioned presentation section is, When creating presentation materials or talk scripts, refer to your past creation history to improve accuracy. The system described in Appendix 3, characterized by the features described herein. (Note 41) The aforementioned presentation section is, It estimates user emotions and prioritizes presentation materials and talk scripts based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 42) The aforementioned presentation section is, When creating presentation materials and talk scripts, prioritize creating highly relevant materials and scripts by considering the user's geographical location. The system described in Appendix 3, characterized by the features described herein. (Note 43) The aforementioned analysis unit is We estimate user sentiment and adjust the bidding result analysis method based on the estimated user sentiment. The system described in Appendix 4, characterized by the features described herein. (Note 44) The aforementioned analysis unit is When analyzing bidding results, refer to past analysis history to improve analysis accuracy. The system described in Appendix 4, characterized by the features described herein. (Note 45) The aforementioned analysis unit is It estimates user sentiment and prioritizes bid results based on the estimated user sentiment. The system described in Appendix 4, characterized by the features described herein. (Note 46) The aforementioned analysis unit is When analyzing bidding results, the system prioritizes analyzing results that are highly relevant, taking into account the user's geographical location. The system described in Appendix 4, characterized by the features described herein. [Explanation of Symbols]

[0209] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A recognition unit that recognizes the company's product information, Based on the information recognized by the aforementioned recognition unit, the acquisition unit crawls publicly available information of each local government and obtains bidding project data. Based on the data acquired by the aforementioned acquisition unit, an extraction unit extracts projects that the company can propose, For the cases extracted by the aforementioned extraction unit, the coordination unit organizes the proposed content, coordinates with the relevant departments, and performs cost estimations. The system includes a creation unit that, based on the proposal content organized by the aforementioned adjustment unit, records the proposal content in a format specified for each bidding project and creates a response document. A system characterized by the following features.

2. The proposal includes sections for describing strengths, differentiation from competitors, conditions, and achievements that support the proposal, depending on the content. The system according to feature 1.

3. It includes a presentation unit that creates presentation materials and talk scripts, and delivers the presentation as needed. The system according to feature 1.

4. We have an analysis department that examines the reasons for success and failure based on the bidding results and uses that information to improve future strategies. The system according to feature 1.

5. The aforementioned recognition unit, The system estimates the user's emotions and adjusts the accuracy of product information recognition based on the estimated user emotions. The system according to feature 1.

6. The aforementioned recognition unit, When recognizing product information, we improve recognition accuracy by referring to the history of past proposals and specifications. The system according to feature 1.

7. The aforementioned recognition unit, When recognizing product information, referencing product information from different industries broadens the scope of understanding. The system according to feature 1.

8. The aforementioned recognition unit, It estimates the user's emotions and determines the priority of product information to recognize based on the estimated user emotions. The system according to feature 1.

9. The aforementioned recognition unit, When recognizing product information, the system prioritizes recognizing highly relevant information by considering the user's geographical location. The system according to feature 1.

10. The aforementioned recognition unit, When recognizing product information, the system analyzes the user's social media activity and identifies relevant information. The system according to feature 1.

Images