system

Abstract

We provide the system. [Solution] A means of automatically collecting bidding information, A means of analyzing the collected bidding information and extracting the specification requirements, A means of determining whether a proposal is acceptable by referring to past bidding results, A means of selecting the most suitable product for projects deemed feasible, A means of automatically generating a quote based on the selected products, A means of automatically creating the generated proposal documents, An information processing system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Bidding and proposal operations for local governments require a great deal of time and effort for detailed reading of specifications and creation of proposal materials, which places a heavy burden on sales staff. Also, when information sharing across the organization is insufficient, successful and failed cases of past projects are not fully utilized, and the winning rate of proposals tends to decrease. Furthermore, since individual handling of each project is required, there is a problem that efficient business execution is difficult.

Means for Solving the Problems

[0005] This invention solves the above problems by providing a system that automatically collects and analyzes bidding information. This system analyzes the collected data and automatically extracts the specification requirements. Based on the analysis results, it can determine whether or not to propose to a project by referring to past bidding results, and efficiently select the most suitable products. Furthermore, for projects that are deemed eligible for proposal, it automatically generates an estimate and creates proposal materials based on the generated data. By optimizing the content based on past successful projects, the system can improve the success rate. In addition, by automatically requesting assignments for proposal creation, the overall business process can be made more efficient.

[0006] "Bidding information" refers to detailed information about bidding projects announced by local governments, and includes elements such as specifications, conditions, deadlines, and budgets.

[0007] "Analysis means" refers to a method or apparatus for analyzing collected bidding information using natural language processing technology or the like to extract specification requirements.

[0008] "Proposal feasibility" refers to an evaluation of whether or not a proposal can be submitted for a particular bidding project, and this is determined based on past data and comparisons with similar cases.

[0009] "Methods for selecting products and services" refer to methods or devices for selecting the most suitable products or services for a given project, taking into account factors such as technical suitability, cost, and delivery time.

[0010] "Automated generation" refers to the creation of processes or documents by a program without requiring manual intervention.

[0011] A "proposal document" is a document submitted when submitting a bid proposal to a local government, and it includes content that clearly explains the necessary specifications, products, and conditions.

[0012] An "assignment request" refers to the process of assigning the appropriate person to a specific task or project, and this process can be automated by a system. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, a processor with a reference numeral (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, a RAM (Random Access Memory) with a reference numeral is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, a storage with a reference numeral is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0019] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] 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.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] This invention is an information processing system for efficiently handling proposal work for local government bidding projects. The system consists of a server, terminals, and users, and each component works together to automate a series of business processes.

[0035] The server first periodically patrols websites and databases published by local governments to obtain new bidding information. This collection process is automated, allowing the server to register the bidding information in the database in real time.

[0036] Subsequently, the server analyzes the collected bidding information using natural language processing technology. It automatically extracts relevant items such as "delivery date," "budget," and "required technology" from the bidding specifications and saves them as structured data. This allows the analysis results to be effectively utilized in the next stage.

[0037] The terminal uses data analyzed by the server to determine whether or not to submit a proposal, referencing past bidding results and evaluation information. This allows for the prediction of success rates for each project and the efficient determination of which projects to submit proposals for.

[0038] If a proposal is deemed feasible, the terminal automatically searches the company's product database and selects the most suitable product for the proposal. This selection is based on factors such as technical specifications and available conditions. Furthermore, a quotation is automatically generated using a pre-configured template based on the selected product information.

[0039] Next, the server uses a generative AI model to create a proposal document. The proposal content is optimized using a model that has learned from past successes. The user reviews this document and makes adjustments if necessary.

[0040] Finally, once the user has finished reviewing the proposal, the system automatically assigns it to the relevant sales team. This ensures quick and accurate work execution, leading to an improved success rate in proposal activities.

[0041] As a concrete example, let's consider a new IT infrastructure project announced by a local government. The server immediately retrieves this information, analyzes the necessary technologies such as "cloud solutions" and "security features," and notifies the relevant team members. If the project matches past success patterns, the terminal automatically selects the relevant cloud solution products and creates a quotation. The user then performs a final check, ensuring a smooth handover to the sales team. This process is expected to significantly streamline the proposal process and improve the success rate.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The server periodically crawls the public websites and related databases of local governments to detect new bidding opportunities and collect information. Data obtained via scraping or APIs is stored in the database.

[0045] Step 2:

[0046] The server applies natural language processing (NLP) techniques to the stored bid information, extracting key details such as "delivery date," "budget," and "required technology" from the specifications. This structures the information, making it easier to use in subsequent stages.

[0047] Step 3:

[0048] The terminal receives the analysis results from the server and compares them with past bidding and evaluation data. At this point, the proposal feasibility algorithm is activated to evaluate the feasibility of proposing a proposal for the project and determine whether it is acceptable or not.

[0049] Step 4:

[0050] For projects deemed feasible, the terminal selects the most suitable product by referring to the company's internal product database. It evaluates the technical suitability, cost, and delivery time of the product to determine the most appropriate one.

[0051] Step 5:

[0052] The terminal automatically generates a quotation based on the information of the selected products. Using a pre-configured quotation template, it prepares a quotation that includes the quantity, unit price, total amount, etc.

[0053] Step 6:

[0054] The server automatically generates proposal documents using a generation AI model based on the proposed content and quotation information. This process utilizes data from past successful proposals to increase the likelihood of the proposal being accepted.

[0055] Step 7:

[0056] The user receives the automatically generated proposal document from the server and reviews its contents. If necessary, they revise and adjust the document to finalize it.

[0057] Step 8:

[0058] Once the user has finished reviewing and refining the proposal, the system automatically requests its assignment to a sales representative. This ensures a smooth handover of tasks and enables a quick response.

[0059] (Example 1)

[0060] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0061] This invention aims to provide a process for efficiently collecting and analyzing local government bidding information, and for making highly accurate and rapid decisions in proposal work. Conventional methods require significant time and effort for manual information collection, analysis, and decision-making, limiting the success rate of proposal work. To solve this problem, an automated series of business processes via an information processing system is required.

[0062] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0063] In this invention, the server includes means for activating an information processing device for periodically collecting bid information, means for analyzing the collected bid information and extracting specification requirements using a natural language processing tool, and means for using a machine learning algorithm to determine the feasibility of a proposal by referring to past case results. This enables the entire process, from collecting bid information to optimizing proposal content and handing it over to the sales department, to be automated, thereby improving the efficiency and success rate of proposal work.

[0064] "Bidding information" refers to information published by public institutions that describes the requirements and conditions for a transaction, and is data necessary for a proposing company to win a contract.

[0065] "Means for activating the information processing device" refers to a function that allows the system to automatically start a periodic collection process, thereby streamlining the acquisition of bidding information.

[0066] "Natural language processing" is a technology that allows computers to extract useful information from human language. By using this technology to extract necessary requirements from the bidding specifications, the data is structured.

[0067] A "machine learning algorithm" is a computational method that learns from past data and makes predictions and judgments about future data, and is used to determine the feasibility of a proposal.

[0068] "Means of generating quotes" refers to a function in the system that automatically creates a quote based on detailed information about the product, thereby improving time efficiency and accuracy.

[0069] A "generative AI model" is an artificial intelligence technology that can automatically generate appropriate output by learning from a large amount of data in advance, and is used to optimize proposal documents.

[0070] An "assignment request" refers to a notification or instruction from the system to assign a specific task to a person, thereby enabling a smooth transition of tasks.

[0071] Modes for carrying out the invention

[0072] The information processing system of this invention aims to improve operational efficiency and success rates by automating proposal work through the efficient collection and analysis of bidding information. The system mainly consists of three elements: a server, a terminal, and a user, each playing a different role.

[0073] First, the server periodically collects bidding information from websites and databases published by local governments. This involves web crawling using Python libraries such as Beautiful Soup and Scrapy. Next, the server utilizes natural language processing techniques to extract specification requirements such as "delivery date," "budget," and "required technology" from the collected bidding information. This process involves text analysis using NLTK and spaCy.

[0074] The terminal is responsible for determining whether a proposal is feasible by referring to a database of past cases based on analyzed data provided by the server. Here, machine learning algorithms such as random forest and linear regression are used to predict the success rate of the proposed cases. Based on the results, the terminal automatically selects the most suitable products for the cases deemed feasible and generates a quotation according to a template based on the selection results.

[0075] Furthermore, the server utilizes a generative AI model to create proposal documents. This generative AI model employs advanced artificial intelligence technologies such as OpenAI's GPT, generating optimal proposal documents based on the input prompt text.

[0076] As a concrete example, consider a case where a local government publishes a new IT infrastructure project. The server acquires this project information, automatically analyzes the necessary technologies such as "cloud solutions" and "security features," and notifies the relevant members. If this information matches past success patterns, the terminal automatically selects the relevant cloud solution products and creates a quotation. The user can then perform a final check and smoothly hand over the project to the sales team.

[0077] An example of a prompt message is: "Please prepare the following proposal document: Project name is New IT Infrastructure Implementation, Required technologies are Cloud Solutions and Security Features, and the key points of the proposal are XX and YY." Instructions are then given to the AI ​​model in this format.

[0078] In this way, the various components of the invention work together to achieve consistent automation and efficiency in the proposed tasks.

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

[0080] Step 1:

[0081] The server periodically crawls public websites and databases of local governments to collect bidding information. This process uses Python libraries such as Beautiful Soup and Scrapy, taking a list of URLs as input and generating the acquired HTML data as output. Web scraping techniques are applied to extract useful information from this data.

[0082] Step 2:

[0083] The server analyzes the collected HTML data using natural language processing techniques. The input is HTML data, and the output is structured data such as "delivery date," "budget," and "required technology." It utilizes Python's NLTK and spaCy to perform specific operations such as text analysis and regular expressions to extract necessary requirements.

[0084] Step 3:

[0085] The server stores the analyzed data in a database and provides it to the terminal. At this stage, the input is structured data, and the output is a record stored in the database. This makes the necessary information easily accessible to the user or other processes within the system.

[0086] Step 4:

[0087] The terminal accesses a database of past cases based on the provided analysis data and determines the feasibility of the proposal. It receives structured data as input and applies machine learning algorithms based on that data to calculate the success rate. The output includes a decision on whether or not the proposal is valid. This involves specific operations using random forests and linear regression.

[0088] Step 5:

[0089] The terminal automatically selects the most suitable products for projects deemed feasible and generates a quotation. The input is data for projects deemed feasible, and the output is the selected product information and a quotation generated according to a template. Product selection involves specific actions such as condition matching using an ERP system.

[0090] Step 6:

[0091] The server uses a generative AI model to create proposal documents. The input consists of prompts and product information, and the output is a completed proposal document. The generative AI model utilizes learning results based on past successes to generate an ideal proposal document.

[0092] Step 7:

[0093] The user reviews the generated proposals and quotations and makes revisions as needed. The input is the proposal and quotation, and the output is the final, completed document. The user's actions include reviewing the document content and making revisions or additions.

[0094] Step 8:

[0095] The server automatically sends assignment requests to the sales department based on the final version of the proposal document. The input is the finalized proposal document, and the output is an assignment request notification. Specific actions are included to ensure a smooth handover to the responsible person using an internal messaging application or email system.

[0096] (Application Example 1)

[0097] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0098] The process of preparing proposals for local government tenders typically requires a significant amount of time and effort. This is because it involves a wide range of manual tasks, including acquiring and analyzing tender information, drafting proposals, and selecting appropriate products and services. The challenge lies in executing these processes quickly and efficiently, and concentrating resources on projects with a high probability of success. Furthermore, the diverse nature of the proposals makes it difficult for staff to address every single one without overlooking anything.

[0099] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0100] In this invention, the server includes means for automatically collecting bidding information, means for analyzing the collected bidding information and extracting conditions, and means for determining whether a proposal is feasible based on past bids. This makes it possible to process information efficiently and improve the efficiency of proposal work. Furthermore, by providing information to user terminals in real time, it is possible to support rapid decision-making regarding proposal cases, enabling quick responses to cases with a high probability of being selected.

[0101] "Bidding information" refers to information released by local governments or organizations to solicit proposals and contributions for specific tasks or projects.

[0102] "Means of automatic collection" refers to processes or systems that have the function of periodically acquiring and recording information from designated sources based on specific conditions.

[0103] "Means of analysis and condition extraction" refer to the processes and technologies used to analyze collected data and find effective requirements and criteria from it.

[0104] "Means for determining the feasibility of a proposal based on past bids" refers to methods and techniques for evaluating the possibility and likelihood of success of a proposal for a new project based on past data and performance.

[0105] "Methods for selecting products" refers to the process of identifying and selecting the most suitable products or services for a proposal, using criteria and algorithms.

[0106] "Methods for automatically generating quotes" refer to systems that generate proposals and quotes according to templates based on selected products and services.

[0107] "Means for automatically creating generated proposal documents" refers to automated processes or software for documenting proposal content based on collected and analyzed information.

[0108] "Means for providing information to user terminals and notifying users of the addition of proposed cases" refers to communication means and interfaces for immediately notifying and displaying users when important information or new cases are registered.

[0109] To implement this invention, a server is configured as the central component of an information processing system. The server first automatically retrieves bidding information from the websites and data stores of specific local governments or organizations. This is achieved using web scraping libraries such as Python's requests or BeautifulSoup.

[0110] The server then analyzes the collected bid information using natural language processing techniques. This process utilizes libraries such as NLTK and Transformers to extract important conditions and requirements from the information. This yields entities such as specific specifications, deadlines, and budgets.

[0111] The analyzed information then moves to a phase where the feasibility of a proposal is determined by referencing past bidding data. The server uses past success stories and evaluation information to assess the probability of success for a proposal for a specific project. Based on this evaluation, projects that are eligible for proposals are selected.

[0112] For projects deemed feasible, the terminal searches the company's product database and selects the most suitable product. Based on this, the system automatically generates a quotation according to a template and makes it available for presentation to the user. Furthermore, using a generation AI model, the final proposal document is automatically created and completed after review by the user.

[0113] In this process, information is provided to the user's device in real time, and they are notified of the addition of new proposals. This allows the user to quickly review the proposals and make adjustments as needed.

[0114] For example, if a local government starts a bidding process for a new traffic management system, the server will collect this information and analyze the relevant data. In creating proposal documents using a generative AI model, an example of a prompt message would be, "Please optimize and create the proposal content for the traffic system bidding announced by the city." This allows the system to efficiently support the task.

[0115] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0116] Step 1:

[0117] The server uses a web scraping library to automatically retrieve bidding information from the websites of local governments and organizations. It accepts a list of web URLs as input and generates HTML data of the retrieved bidding information as output. This data is organized by analyzing the structure of the web pages.

[0118] Step 2:

[0119] Based on the parsed HTML data, the server utilizes natural language processing technology to extract conditions from the bidding information. The input is HTML data, and the output is structured text data such as "specifications," "delivery date," and "budget." This process involves tokenization of information and extraction of important keywords.

[0120] Step 3:

[0121] The server references a database of past bids and determines the feasibility of a proposal based on the extracted criteria. Inputs are text data related to the criteria and past successful bid data; output is an evaluation of the proposal's potential. An evaluation algorithm is then applied to select projects with a high probability of success.

[0122] Step 4:

[0123] The terminal receives information on potential projects from the server and searches the company's product database. It then selects the most suitable product. Here, the input is information on potential projects, and the output is information on the selected product. This selection is based on the product's suitability.

[0124] Step 5:

[0125] The terminal automatically generates a quotation based on the selected product information, following a template. The input is product information, and the output is a completed quotation. This step utilizes a template engine to automatically create the document.

[0126] Step 6:

[0127] The server uses a generation AI model to create the final proposal document, referencing past successful cases. The input consists of selected product information and success case data, and the output is a proposal document. During this process, the AI ​​model analyzes the information and uses prompts to create the optimal proposal.

[0128] Step 7:

[0129] The user reviews the proposal document generated by the server and adjusts its content as needed. The input is the proposal document, and the output is the final, adjusted version of the proposal document. At this stage, the user verifies the accuracy and appropriateness of the document.

[0130] Step 8:

[0131] The terminal notifies the sales team of the final proposal document and provides real-time updates on new proposals. Here, the input is the final proposal document, and the output is a notification to the sales team. This notification allows for a quick response to new proposals.

[0132] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0133] This invention is an information processing system that streamlines the proposal process for local government bidding projects, and by integrating an emotion engine, it optimizes proposal content based on the user's emotions. This system consists of a server, a terminal, a user, and an emotion engine that performs emotion recognition.

[0134] The server first automatically collects bidding information published by local governments and stores it in a database. The collected data is analyzed using natural language processing (NLP) technology, and necessary information is extracted from the specifications. The results of the analysis are structured into elements necessary for proposal formulation (e.g., deadline, budget, technical requirements).

[0135] Based on this analysis, the terminal can refer to past bidding results and determine whether or not to submit a proposal. Furthermore, for projects deemed feasible, it uses the company's internal product database to select the most suitable products and automatically generates a quotation.

[0136] The generated proposal documents are dynamically adjusted by the server, utilizing data from past success stories and employing an emotion engine to match the user's expectations in terms of expression and content. The emotion engine determines emotions from user feedback and data, optimizing the tone and structure of the proposal documents.

[0137] Users review the proposal materials provided by the server and perform manual reviews and adjustments as needed. Based on input from the emotion engine, the materials can be refined to become more persuasive.

[0138] Furthermore, assignment requests to sales representatives are optimized in terms of timing and priority based on the analysis results of the emotion engine. For example, if user anxiety or doubt is identified, assignments are adjusted to quickly follow up, thereby building even greater trust.

[0139] As a concrete example, consider a case where the system handles an IT infrastructure development project from a local government. The server retrieves project information and analyzes the requirements. The terminal refers to similar past success stories, proposes cloud solutions to determine their feasibility, and creates an estimate. Finally, the proposal document is adjusted through emotion engine analysis to be persuasive and considerate of the feelings of the local government official. Users are expected to use this document to make effective proposals to local governments, improving the consistency and success rate of their proposal activities.

[0140] The following describes the processing flow.

[0141] Step 1:

[0142] The server automatically collects the latest publicly available bidding information by patrolling the official websites and related databases of each local government. The collected data is immediately saved to the database in preparation for the next analysis step.

[0143] Step 2:

[0144] The server applies natural language processing (NLP) techniques to the collected bid information, extracting key requirements such as "delivery date," "budget," and "required technology" from the specification text. This analysis structures the data, making it more user-friendly.

[0145] Step 3:

[0146] The terminal refers to the analysis results received from the server and compares them with past bidding data and win / loss data to determine whether the proposal is feasible. In this process, the possibility of the proposal is evaluated based on successful past cases and the conditions of the current project.

[0147] Step 4:

[0148] The terminal searches the company's product database for projects deemed feasible and automatically selects the most suitable product for each project. During the selection process, it verifies the product's compatibility with technical requirements and its terms of service.

[0149] Step 5:

[0150] The terminal automatically generates a quotation using a predetermined template based on the selected product information. The quotation includes detailed information such as the required quantity, price, and delivery date.

[0151] Step 6:

[0152] The server creates proposal documents from product information and quotation information automatically generated using a generative AI model. During this process, it incorporates the analysis results of the emotion engine, adjusting the content to be sensitive to the emotions of the target audience.

[0153] Step 7:

[0154] Users receive and review proposal materials provided by the server, making necessary adjustments based on feedback from the sentiment engine. This process refines the materials to make them more persuasive.

[0155] Step 8:

[0156] Once the user has finished reviewing the proposal, the system automatically optimizes and sends assignment requests to sales representatives. The assignment priority and timing are adjusted based on the results of the emotion engine's recognition.

[0157] (Example 2)

[0158] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0159] In traditional proposal processes, the stages of gathering bidding information, creating proposal materials, and making adjustments that take emotions into consideration were fragmented, resulting in significant time and effort being required for each stage. Furthermore, determining the optimal timing for follow-up that takes user emotions into account was difficult, raising concerns that the efficiency and effectiveness of proposals would not be fully realized.

[0160] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0161] In this invention, the server includes a device for automatically collecting bidding information, a device for processing the information and detecting requirements, and a device for referring to past data and determining whether a proposal is acceptable. This enables the integrated processing of each process, improving the efficiency and accuracy of the proposal process. Furthermore, by using an emotion engine to adjust proposal materials and optimizing the timing of follow-ups based on user emotion information, the success rate of proposals can be improved.

[0162] "Bidding information" refers to data related to bids that are made public by public or private organizations for the purpose of conducting transactions.

[0163] "Collection equipment" refers to a combination of software and hardware used to collect bidding information, primarily through automated methods.

[0164] "Devices for processing information and detecting requirements" refers to technologies and devices used to analyze collected information and identify relevant specifications and requirements.

[0165] "A device that uses past data to determine the feasibility of a proposal" refers to a device and technology used to analyze past successes and failures and predict the success or failure of a new proposal.

[0166] An "emotion engine" refers to a technology or algorithm used to analyze a user's emotional state and adjust information and expressions accordingly.

[0167] "Optimizing the timing of follow-up" refers to a technique of adjusting the timing of the next action to be implemented at the most effective point, based on the needs and emotions of the recipient of the proposal.

[0168] The invention will now be described in terms of its implementation. This system provides an information processing method that supports efficient proposal work for responding to local government bidding projects. The system mainly consists of a server, terminals, users, and an engine that performs sentiment analysis.

[0169] The server automatically collects bidding information from local government websites on a regular basis using web scraping tools (e.g., Scrapy or BeautifulSoup). This information is stored in a database management system (e.g., PostgreSQL or MySQL®). After collection, the server analyzes the data using natural language processing techniques (e.g., NLTK or SpaCy) to extract necessary requirements from the bidding specifications. This enables accurate proposals based on established structured data.

[0170] The terminal compares the analysis results received from the server with past datasets to determine whether a proposal is feasible. This determination uses algorithms designed with machine learning libraries such as Scikit-learn. If a proposal is deemed feasible, it selects the most suitable products using the ERP system and product database, and automatically generates a quotation using Excel or PDF generation libraries.

[0171] The user reviews the final generated proposal document and makes adjustments as needed. This document is then dynamically adjusted using an emotion engine (e.g., a generative AI model using BERT) to match the tone and content of the target audience. This is expected to make the document more persuasive and improve the success rate of the proposal.

[0172] As a concrete example, let's consider a case where we handle IT infrastructure-related bidding projects from local governments. The server acquires and analyzes project information, while the terminal proposes cloud solutions based on past success stories and automatically generates estimates. Finally, the proposal materials become more persuasive through sentiment analysis, enabling more effective proposal activities.

[0173] An example of a prompt message is: "Please create a compelling proposal document for the latest bidding project by the local government. Please adjust the tone of the document, taking into account the feelings of the person in charge at the target organization."

[0174] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0175] Step 1:

[0176] The server automatically collects bidding information from local government websites. The input is the URL of the local government's webpage, and the output is HTML data. Specifically, it uses a web scraping library such as Scrapy to periodically crawl webpages according to a specified schedule. The collected HTML data is stored in a database.

[0177] Step 2:

[0178] The server analyzes the collected HTML data and extracts the requirements for the bidding specifications. The input is raw data in HTML format, and the output is structured database entries. Specifically, NLTK and SpaCy are used for natural language processing to extract keywords and specific phrases from the text data and structure them. This process determines the deadline, budget, technical requirements, etc.

[0179] Step 3:

[0180] The terminal receives structured data from the server, references past bidding results, and determines whether to approve the proposal. The input is structured data and a history of past successes and failures, and the output is the decision on whether to approve the proposal. A Scikit-learn machine learning model is used to determine the similarity to past datasets and predict the likelihood of the proposal's success.

[0181] Step 4:

[0182] The terminal automatically selects the most suitable products for projects deemed eligible for proposals and generates quotations. Input consists of a database of eligible projects and products, while output is a quotation. It selects the most suitable product based on the conditions by referring to an ERP system or product database. Quotations are generated and formatted using Excel or PDF generation libraries.

[0183] Step 5:

[0184] The server uses an emotion engine to refine the generated proposal document. The input is the generated proposal document, and the output is the refined document. By inputting prompt sentences into a BERT-based generative AI model, the document's persuasiveness is improved by dynamically adjusting the tone and content to take into account the emotions the recipient will receive.

[0185] Step 6:

[0186] The user reviews the finalized proposal document and makes manual revisions as needed. The input is the revised document, and the output is the final version of the proposal document. Specifically, the user can use Microsoft® Word or Google® Docs to highlight important parts of the proposal document or add new information.

[0187] Step 7:

[0188] The server optimizes the timing of follow-ups with sales representatives based on user sentiment information. The input is user sentiment data, and the output is optimized assignments and notifications. The sentiment engine's analysis results are used to prompt sales representatives to take immediate action as needed, using the Google Calendar API.

[0189] (Application Example 2)

[0190] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0191] Proposal work for local government bidding projects is inefficient, requiring a great deal of manual work from information gathering to the creation of proposal documents. Furthermore, proposals tend to be uniform, making it difficult to consider the expectations and feelings of the 담당자 (person in charge). Moreover, improving the persuasiveness of proposal documents requires adjustments tailored to the emotions of each user. As a result, the success rate of proposals is low, and the process is time-consuming and laborious.

[0192] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0193] In this invention, the server includes means for automatically collecting information related to bids, means for analyzing the collected information and extracting requirements, and means for using emotion recognition technology to optimize the generated proposal materials based on the user's emotions. This improves the efficiency of the proposal process and enables the creation of optimal proposal materials that take the user's emotions into consideration.

[0194] "Information regarding bidding" refers to information related to public tenders for public works projects and contracts, etc., published by local governments.

[0195] "Analysis of collected information" refers to the process of extracting and organizing necessary requirements and conditions from acquired bidding information.

[0196] "Determining whether a proposal is feasible" is the process of evaluating whether a proposal is feasible for a particular project by referring to past bidding results and successful examples.

[0197] "Selecting the appropriate product" refers to the act of choosing the most suitable product or service for a project that has been deemed feasible.

[0198] "Automatic quotation generation" refers to the process of automatically generating a quotation by calculating prices and conditions based on selected products and services.

[0199] "Emotion recognition technology" is a technology that analyzes and determines a user's emotions from data, and is used to optimize proposal materials.

[0200] "Display and adjustment via smart devices" refers to the function of displaying generated proposal materials using devices such as smartphones and smart glasses, and making adjustments as needed.

[0201] This invention is an information processing system that streamlines the proposal process for local government bidding projects and optimizes proposal content based on emotions. This system primarily consists of a server, terminals, and users, which are detailed below.

[0202] The server automatically collects information on bids published by local governments via the internet. The collected information is analyzed using natural language processing (NLP) technology to extract necessary requirements. NLP libraries such as spaCy and NLTK are used for this analysis. Next, the server refers to past bid results in the database to determine whether a proposal is feasible for a given project. In this process, historical success stories of bids are an important indicator. If it is determined that a proposal is feasible, the server selects the most suitable product and generates an automated estimate based on it.

[0203] The generated proposal documents are optimized based on the user's emotions using emotion recognition technology. For this purpose, emotion analysis engines such as IBM Watson® and Google Cloud Natural Language API are used. This results in proposal documents that better meet user expectations and are more persuasive.

[0204] The terminal displays proposal materials generated using smart devices such as smartphones and smart glasses to the user. The user can review the content based on this information and make manual adjustments if necessary. This process is crucial for the proposal to meet a wider range of expectations.

[0205] For example, when proposing a design for a new urban park, the application creates an optimal proposal based on past successes and feedback from citizens. This proposal is then refined to reflect citizens' expectations through sentiment analysis.

[0206] Examples of prompts for the generating AI model include: "Please create a proposal for a newly planned urban park design. Consider past successes and citizen feedback, and include specific suggestions regarding budget and deadlines. Finally, incorporate elements that will increase citizen satisfaction."

[0207] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0208] Step 1:

[0209] The server automatically collects bidding information from local government websites and APIs. Inputs include URLs of bidding information and API endpoints. The server uses this information to perform web scraping or API calls to obtain raw data of the bidding information. This data is then output.

[0210] Step 2:

[0211] The server analyzes the collected raw data based on natural language processing (NLP) techniques. The input is the raw data obtained in step 1. The server uses an NLP library (e.g., spaCy, NLTK) to extract the specification requirements and obtains the output as structured data.

[0212] Step 3:

[0213] The server accesses a database of past bidding results and refers to the structured data obtained in step 2 to determine whether the proposal is acceptable or not. The input is structured data, and by searching the database, it finds similar past examples and obtains an output as a determination of whether the proposal is acceptable or not.

[0214] Step 4:

[0215] For cases where a proposal is deemed feasible, the server selects the most suitable product from the company's product database. The input is the result of the proposal feasibility assessment, and the server selects and outputs the most appropriate product information by referring to the product database.

[0216] Step 5:

[0217] The server automatically generates quotes based on the selected products. The input is the selected product information, and the server uses a price calculation algorithm to create and output quote data.

[0218] Step 6:

[0219] The server creates proposal documents based on the generated estimate data and optimizes them using sentiment recognition technology. The input consists of estimate data and user sentiment feedback. The sentiment analysis engine adjusts the tone and content of the documents and outputs them as the final proposal document.

[0220] Step 7:

[0221] The terminal displays the final proposal document to the user using a smartphone or smart glasses. The user reviews the proposal based on this document and makes manual adjustments as needed. The input is the final proposal document, and the output is the proposal document adjusted through the user's actions.

[0222] 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.

[0223] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0224] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0225] [Second Embodiment]

[0226] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0227] 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.

[0228] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0229] 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.

[0230] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0231] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0232] 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.

[0233] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0234] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0235] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0236] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0237] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0238] This invention is an information processing system for efficiently handling proposal work for local government bidding projects. The system consists of a server, terminals, and users, and each component works together to automate a series of business processes.

[0239] The server first periodically patrols websites and databases published by local governments to obtain new bidding information. This collection process is automated, allowing the server to register the bidding information in the database in real time.

[0240] Subsequently, the server analyzes the collected bidding information using natural language processing technology. It automatically extracts relevant items such as "delivery date," "budget," and "required technology" from the bidding specifications and saves them as structured data. This allows the analysis results to be effectively utilized in the next stage.

[0241] The terminal uses data analyzed by the server to determine whether or not to submit a proposal, referencing past bidding results and evaluation information. This allows for the prediction of success rates for each project and the efficient determination of which projects to submit proposals for.

[0242] If a proposal is deemed feasible, the terminal automatically searches the company's product database and selects the most suitable product for the proposal. This selection is based on factors such as technical specifications and available conditions. Furthermore, a quotation is automatically generated using a pre-configured template based on the selected product information.

[0243] Next, the server uses a generative AI model to create a proposal document. The proposal content is optimized using a model that has learned from past successes. The user reviews this document and makes adjustments if necessary.

[0244] Finally, once the user has finished reviewing the proposal, the system automatically assigns it to the relevant sales team. This ensures quick and accurate work execution, leading to an improved success rate in proposal activities.

[0245] As a concrete example, let's consider a new IT infrastructure project announced by a local government. The server immediately retrieves this information, analyzes the necessary technologies such as "cloud solutions" and "security features," and notifies the relevant team members. If the project matches past success patterns, the terminal automatically selects the relevant cloud solution products and creates a quotation. The user then performs a final check, ensuring a smooth handover to the sales team. This process is expected to significantly streamline the proposal process and improve the success rate.

[0246] The following describes the processing flow.

[0247] Step 1:

[0248] The server periodically crawls the public websites and related databases of local governments to detect new bidding opportunities and collect information. Data obtained via scraping or APIs is stored in the database.

[0249] Step 2:

[0250] The server applies natural language processing (NLP) techniques to the stored bid information, extracting key details such as "delivery date," "budget," and "required technology" from the specifications. This structures the information, making it easier to use in subsequent stages.

[0251] Step 3:

[0252] The terminal receives the analysis results from the server and compares them with past bidding and evaluation data. At this point, the proposal feasibility algorithm is activated to evaluate the feasibility of proposing a proposal for the project and determine whether it is acceptable or not.

[0253] Step 4:

[0254] For projects deemed feasible, the terminal selects the most suitable product by referring to the company's internal product database. It evaluates the technical suitability, cost, and delivery time of the product to determine the most appropriate one.

[0255] Step 5:

[0256] The terminal automatically generates a quotation based on the information of the selected products. Using a pre-configured quotation template, it prepares a quotation that includes the quantity, unit price, total amount, etc.

[0257] Step 6:

[0258] The server automatically generates proposal documents using a generation AI model based on the proposed content and quotation information. This process utilizes data from past successful proposals to increase the likelihood of the proposal being accepted.

[0259] Step 7:

[0260] The user receives the automatically generated proposal document from the server and reviews its contents. If necessary, they revise and adjust the document to finalize it.

[0261] Step 8:

[0262] Once the user has finished reviewing and refining the proposal, the system automatically requests its assignment to a sales representative. This ensures a smooth handover of tasks and enables a quick response.

[0263] (Example 1)

[0264] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0265] This invention aims to provide a process for efficiently collecting and analyzing local government bidding information, and for making highly accurate and rapid decisions in proposal work. Conventional methods require significant time and effort for manual information collection, analysis, and decision-making, limiting the success rate of proposal work. To solve this problem, an automated series of business processes via an information processing system is required.

[0266] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0267] In this invention, the server includes means for activating an information processing device for periodically collecting bid information, means for analyzing the collected bid information and extracting specification requirements using a natural language processing tool, and means for using a machine learning algorithm to determine the feasibility of a proposal by referring to past case results. This enables the entire process, from collecting bid information to optimizing proposal content and handing it over to the sales department, to be automated, thereby improving the efficiency and success rate of proposal work.

[0268] "Bidding information" refers to information published by public institutions that describes the requirements and conditions for a transaction, and is data necessary for a proposing company to win a contract.

[0269] "Means for activating the information processing device" refers to a function that allows the system to automatically start a periodic collection process, thereby streamlining the acquisition of bidding information.

[0270] "Natural language processing" is a technology that allows computers to extract useful information from human language. By using this technology to extract necessary requirements from bidding specifications, the data is structured.

[0271] A "machine learning algorithm" is a computational method that learns from past data and makes predictions and judgments about future data, and is used to determine the feasibility of a proposal.

[0272] "Means of generating quotes" refers to a function in the system that automatically creates a quote based on detailed information about the product, thereby improving time efficiency and accuracy.

[0273] A "generative AI model" is an artificial intelligence technology that can automatically generate appropriate output by learning from a large amount of data in advance, and is used to optimize proposal documents.

[0274] An "assignment request" refers to a notification or instruction from the system to assign a specific task to a person, thereby enabling a smooth transition of tasks.

[0275] Modes for carrying out the invention

[0276] The information processing system of this invention aims to improve operational efficiency and success rates by automating proposal work through the efficient collection and analysis of bidding information. The system mainly consists of three elements: a server, a terminal, and a user, each playing a different role.

[0277] First, the server periodically collects bidding information from websites and databases published by local governments. This involves web crawling using Python libraries such as Beautiful Soup and Scrapy. Next, the server utilizes natural language processing techniques to extract specification requirements such as "delivery date," "budget," and "required technology" from the collected bidding information. This process involves text analysis using NLTK and spaCy.

[0278] The terminal is responsible for determining whether a proposal is feasible by referring to a database of past cases based on analyzed data provided by the server. Here, machine learning algorithms such as random forest and linear regression are used to predict the success rate of the proposed cases. Based on the results, the terminal automatically selects the most suitable products for the cases deemed feasible and generates a quotation according to a template based on the selection results.

[0279] Furthermore, the server utilizes a generative AI model to create proposal documents. This generative AI model employs advanced artificial intelligence technologies such as OpenAI's GPT to generate optimal proposal documents based on the input prompt text.

[0280] As a concrete example, consider a case where a local government publishes a new IT infrastructure project. The server acquires this project information, automatically analyzes the necessary technologies such as "cloud solutions" and "security features," and notifies the relevant members. If this information matches past success patterns, the terminal automatically selects the relevant cloud solution products and creates a quotation. The user can then perform a final check and smoothly hand over the project to the sales team.

[0281] As an example of a prompt sentence, instructions are given to the AI model in a form such as "Please create the following proposal document: The project name is for the introduction of a new IT infrastructure, the required technologies are cloud solutions and security functions, and the key points of the proposal are XX and XX."

[0282] In this way, by the cooperative operation of each component of the invention, consistent automation and efficiency improvement of the proposal work are realized.

[0283] The flow of the specific process in Example 1 will be described using FIG. 11.

[0284] Step 1:

[0285] The server periodically patrols the public websites and databases of local governments to collect bidding information. In this process, libraries of Python such as Beautiful Soup and Scrapy are used, which receive a URL list as input and generate the obtained HTML data as output. Web scraping technology is applied to extract useful information from this data.

[0286] Step 2:

[0287] The server analyzes the collected HTML data using natural language processing technology. The input here is HTML data, and the output is structured data such as "delivery date", "budget", "required technology", etc. Specific operations are performed to extract the necessary requirements by utilizing NLTK and spaCy of Python through text analysis and regular expressions.

[0288] Step 3:

[0289] The server saves the analyzed data in the database and provides it to the terminal. At this stage, the input is structured data, and the output is the records stored in the database. As a result, the necessary information becomes easily accessible to the user or other processes within the system.

[0290] Step 4:

[0291] The terminal accesses a database of past cases based on the provided analysis data and determines the feasibility of the proposal. It receives structured data as input and applies machine learning algorithms based on that data to calculate the success rate. The output includes a decision on whether or not the proposal is valid. This involves specific operations using random forests and linear regression.

[0292] Step 5:

[0293] The terminal automatically selects the most suitable products for projects deemed feasible and generates a quotation. The input is data for projects deemed feasible, and the output is the selected product information and a quotation generated according to a template. Product selection involves specific actions such as condition matching using an ERP system.

[0294] Step 6:

[0295] The server uses a generative AI model to create proposal documents. The input consists of prompts and product information, and the output is a completed proposal document. The generative AI model utilizes learning results based on past successes to generate an ideal proposal document.

[0296] Step 7:

[0297] The user reviews the generated proposals and quotations and makes revisions as needed. The input is the proposal and quotation, and the output is the final, completed document. The user's actions include reviewing the document content and making revisions or additions.

[0298] Step 8:

[0299] The server automatically sends assignment requests to the sales department based on the final version of the proposal document. The input is the finalized proposal document, and the output is an assignment request notification. Specific actions are included to ensure a smooth handover to the responsible person using an internal messaging application or email system.

[0300] (Application Example 1)

[0301] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0302] The process of preparing proposals for local government tenders typically requires a significant amount of time and effort. This is because it involves a wide range of manual tasks, including acquiring and analyzing tender information, drafting proposals, and selecting appropriate products and services. The challenge lies in executing these processes quickly and efficiently, and concentrating resources on projects with a high probability of success. Furthermore, the diverse nature of the proposals makes it difficult for staff to address every single one without overlooking anything.

[0303] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0304] In this invention, the server includes means for automatically collecting bidding information, means for analyzing the collected bidding information and extracting conditions, and means for determining whether a proposal is feasible based on past bids. This makes it possible to process information efficiently and improve the efficiency of proposal work. Furthermore, by providing information to user terminals in real time, it is possible to support rapid decision-making regarding proposal cases, enabling quick responses to cases with a high probability of being selected.

[0305] "Bidding information" refers to information released by local governments or organizations to solicit proposals and contributions for specific tasks or projects.

[0306] The "means for automatically collecting" is a process or system that has the function of periodically acquiring and recording information from a specified information source based on specific conditions.

[0307] The "means for analyzing and extracting conditions" is a process or technology for analyzing the collected data and finding effective requirements and criteria therefrom.

[0308] The "means for judging the feasibility of a proposal based on past bids" is a method or technology for evaluating the possibility and prospects of success of a proposal for a new project based on past data and performance.

[0309] The "means for selecting a product" is a process that uses criteria or algorithms for identifying and selecting the most suitable commercial materials and services for a proposal.

[0310] The "means for automatically generating a quotation" is a system that generates a proposal or quotation according to a template based on the selected product or service.

[0311] The "means for automatically creating the generated proposal materials" is an automatic process or software for documenting the proposal content based on the collected and analyzed information.

[0312] The "means for providing information to the user terminal and notifying the addition of a proposed project" is a communication means and interface for immediately notifying and displaying to the user when important information or a new project is registered.

[0313] To implement this invention, an information processing system in which a server plays a central role is configured. First, the server automatically acquires bidding information from the websites or data stores of specific local governments or organizations. This is realized by using web scraping libraries such as Python's requests and BeautifulSoup.

[0314] The server then analyzes the collected bid information using natural language processing techniques. This process utilizes libraries such as NLTK and Transformers to extract important conditions and requirements from the information. This yields entities such as specific specifications, deadlines, and budgets.

[0315] The analyzed information then moves to a phase where the feasibility of a proposal is determined by referencing past bidding data. The server uses past success stories and evaluation information to assess the probability of success for a proposal for a specific project. Based on this evaluation, projects that are eligible for proposals are selected.

[0316] For projects deemed feasible, the terminal searches the company's product database and selects the most suitable product. Based on this, the system automatically generates a quotation according to a template and makes it available for presentation to the user. Furthermore, using a generation AI model, the final proposal document is automatically created and completed after review by the user.

[0317] In this process, information is provided to the user's device in real time, and they are notified of the addition of new proposals. This allows the user to quickly review the proposals and make adjustments as needed.

[0318] For example, if a local government starts a bidding process for a new traffic management system, the server will collect this information and analyze the relevant data. In creating proposal documents using a generative AI model, an example of a prompt message would be, "Please optimize and create the proposal content for the traffic system bidding announced by the city." This allows the system to efficiently support the task.

[0319] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0320] Step 1:

[0321] The server uses a web scraping library to automatically retrieve bidding information from the websites of local governments and organizations. It accepts a list of web URLs as input and generates HTML data of the retrieved bidding information as output. This data is organized by analyzing the structure of the web pages.

[0322] Step 2:

[0323] Based on the parsed HTML data, the server utilizes natural language processing technology to extract conditions from the bidding information. The input is HTML data, and the output is structured text data such as "specifications," "delivery date," and "budget." This process involves tokenization of information and extraction of important keywords.

[0324] Step 3:

[0325] The server references a database of past bids and determines the feasibility of a proposal based on the extracted criteria. Inputs are text data related to the criteria and past successful bid data; output is an evaluation of the proposal's potential. An evaluation algorithm is then applied to select projects with a high probability of success.

[0326] Step 4:

[0327] The terminal receives information on potential projects from the server and searches the company's product database. It then selects the most suitable product. Here, the input is information on potential projects, and the output is information on the selected product. This selection is based on the product's suitability.

[0328] Step 5:

[0329] The terminal automatically generates a quotation based on the selected product information, following a template. The input is product information, and the output is a completed quotation. This step utilizes a template engine to automatically create the document.

[0330] Step 6:

[0331] The server uses a generation AI model to create the final proposal document, referencing past successful cases. The input consists of selected product information and success case data, and the output is a proposal document. During this process, the AI ​​model analyzes the information and uses prompts to create the optimal proposal.

[0332] Step 7:

[0333] The user reviews the proposal document generated by the server and adjusts its content as needed. The input is the proposal document, and the output is the final, adjusted version of the proposal document. At this stage, the user verifies the accuracy and appropriateness of the document.

[0334] Step 8:

[0335] The terminal notifies the sales team of the final proposal document and provides real-time updates on new proposals. Here, the input is the final proposal document, and the output is a notification to the sales team. This notification allows for a quick response to new proposals.

[0336] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0337] This invention is an information processing system that streamlines the proposal process for local government bidding projects, and by integrating an emotion engine, it optimizes proposal content based on the user's emotions. This system consists of a server, a terminal, a user, and an emotion engine that performs emotion recognition.

[0338] The server first automatically collects bidding information published by local governments and stores it in a database. The collected data is analyzed using natural language processing (NLP) technology, and necessary information is extracted from the specifications. The results of the analysis are structured into elements necessary for proposal formulation (e.g., deadline, budget, technical requirements).

[0339] Based on this analysis, the terminal can refer to past bidding results and determine whether or not to submit a proposal. Furthermore, for projects deemed feasible, it uses the company's internal product database to select the most suitable products and automatically generates a quotation.

[0340] The generated proposal documents are dynamically adjusted by the server, utilizing data from past success stories and employing an emotion engine to match the user's expectations in terms of expression and content. The emotion engine determines emotions from user feedback and data, optimizing the tone and structure of the proposal documents.

[0341] Users review the proposal materials provided by the server and perform manual reviews and adjustments as needed. Based on input from the emotion engine, the materials can be refined to become more persuasive.

[0342] Furthermore, assignment requests to sales representatives are optimized in terms of timing and priority based on the analysis results of the emotion engine. For example, if user anxiety or doubt is identified, assignments are adjusted to quickly follow up, thereby building even greater trust.

[0343] As a concrete example, consider a case where the system handles an IT infrastructure development project from a local government. The server retrieves project information and analyzes the requirements. The terminal refers to similar past success stories, proposes cloud solutions to determine their feasibility, and creates an estimate. Finally, the proposal document is adjusted through emotion engine analysis to be persuasive and considerate of the feelings of the local government official. Users are expected to use this document to make effective proposals to local governments, improving the consistency and success rate of their proposal activities.

[0344] The following describes the processing flow.

[0345] Step 1:

[0346] The server automatically collects the latest publicly available bidding information by patrolling the official websites and related databases of each local government. The collected data is immediately saved to the database in preparation for the next analysis step.

[0347] Step 2:

[0348] The server applies natural language processing (NLP) techniques to the collected bid information, extracting key requirements such as "delivery date," "budget," and "required technology" from the specification text. This analysis structures the data, making it more user-friendly.

[0349] Step 3:

[0350] The terminal refers to the analysis results received from the server and compares them with past bidding data and win / loss data to determine whether the proposal is feasible. In this process, the possibility of the proposal is evaluated based on successful past cases and the conditions of the current project.

[0351] Step 4:

[0352] The terminal searches the company's product database for projects deemed feasible and automatically selects the most suitable product for each project. During the selection process, it verifies the product's compatibility with technical requirements and its terms of service.

[0353] Step 5:

[0354] The terminal automatically generates a quotation using a predetermined template based on the selected product information. The quotation includes detailed information such as the required quantity, price, and delivery date.

[0355] Step 6:

[0356] The server creates proposal documents from product information and quotation information automatically generated using a generative AI model. During this process, it incorporates the analysis results of the emotion engine, adjusting the content to be sensitive to the emotions of the target audience.

[0357] Step 7:

[0358] Users receive and review proposal materials provided by the server, making necessary adjustments based on feedback from the sentiment engine. This process refines the materials to make them more persuasive.

[0359] Step 8:

[0360] Once the user has finished reviewing the proposal, the system automatically optimizes and sends assignment requests to sales representatives. The assignment priority and timing are adjusted based on the results of the emotion engine's recognition.

[0361] (Example 2)

[0362] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0363] In traditional proposal processes, the stages of gathering bidding information, creating proposal materials, and making adjustments that take emotions into consideration were fragmented, resulting in significant time and effort being required for each stage. Furthermore, determining the optimal timing for follow-up that takes user emotions into account was difficult, raising concerns that the efficiency and effectiveness of proposals would not be fully realized.

[0364] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0365] In this invention, the server includes a device for automatically collecting bidding information, a device for processing the information and detecting requirements, and a device for referring to past data and determining whether a proposal is acceptable. This enables the integrated processing of each process, improving the efficiency and accuracy of the proposal process. Furthermore, by using an emotion engine to adjust proposal materials and optimizing the timing of follow-ups based on user emotion information, the success rate of proposals can be improved.

[0366] "Bidding information" refers to data related to bids that are made public by public or private organizations for the purpose of conducting transactions.

[0367] "Collection equipment" refers to a combination of software and hardware used to collect bidding information, primarily through automated methods.

[0368] "Devices for processing information and detecting requirements" refers to technologies and devices used to analyze collected information and identify relevant specifications and requirements.

[0369] "A device that uses past data to determine the feasibility of a proposal" refers to a device and technology used to analyze past successes and failures and predict the success or failure of a new proposal.

[0370] An "emotion engine" refers to a technology or algorithm used to analyze a user's emotional state and adjust information and expressions accordingly.

[0371] "Optimizing the timing of follow-up" refers to a technique of adjusting the timing of the next action to be implemented at the most effective point, based on the needs and emotions of the recipient of the proposal.

[0372] The invention will now be described in terms of its implementation. This system provides an information processing method that supports efficient proposal work for responding to local government bidding projects. The system mainly consists of a server, terminals, users, and an engine that performs sentiment analysis.

[0373] The server automatically collects bidding information from local government websites on a regular basis using web scraping tools (e.g., Scrapy or BeautifulSoup). This information is stored in a database management system (e.g., PostgreSQL or MySQL). After collection, the server analyzes the data using natural language processing techniques (e.g., NLTK or SpaCy) and extracts necessary requirements from the bidding specifications. This enables accurate proposals based on established structured data.

[0374] The terminal compares the analysis results received from the server with past datasets to determine whether a proposal is feasible. This determination uses algorithms designed with machine learning libraries such as Scikit-learn. If a proposal is deemed feasible, it selects the most suitable products using the ERP system and product database, and automatically generates a quotation using Excel or PDF generation libraries.

[0375] The user reviews the final generated proposal document and makes adjustments as needed. This document is then dynamically adjusted using an emotion engine (e.g., a generative AI model using BERT) to match the tone and content of the target audience. This is expected to make the document more persuasive and improve the success rate of the proposal.

[0376] As a concrete example, let's consider a case where we handle IT infrastructure-related bidding projects from local governments. The server acquires and analyzes project information, while the terminal proposes cloud solutions based on past success stories and automatically generates estimates. Finally, the proposal materials become more persuasive through sentiment analysis, enabling more effective proposal activities.

[0377] An example of a prompt message is: "Please create a compelling proposal document for the latest bidding project by the local government. Please adjust the tone of the document, taking into account the feelings of the person in charge at the target organization."

[0378] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0379] Step 1:

[0380] The server automatically collects bidding information from local government websites. The input is the URL of the local government's webpage, and the output is HTML data. Specifically, it uses a web scraping library such as Scrapy to periodically crawl webpages according to a specified schedule. The collected HTML data is stored in a database.

[0381] Step 2:

[0382] The server analyzes the collected HTML data and extracts the requirements for the bidding specifications. The input is raw data in HTML format, and the output is structured database entries. Specifically, NLTK and SpaCy are used for natural language processing to extract keywords and specific phrases from the text data and structure them. This process determines the deadline, budget, technical requirements, etc.

[0383] Step 3:

[0384] The terminal receives structured data from the server, references past bidding results, and determines whether to approve the proposal. The input is structured data and a history of past successes and failures, and the output is the decision on whether to approve the proposal. A Scikit-learn machine learning model is used to determine the similarity to past datasets and predict the likelihood of the proposal's success.

[0385] Step 4:

[0386] The terminal automatically selects the most suitable products for projects deemed eligible for proposals and generates quotations. Input consists of a database of eligible projects and products, while output is a quotation. It selects the most suitable product based on the conditions by referring to an ERP system or product database. Quotations are generated and formatted using Excel or PDF generation libraries.

[0387] Step 5:

[0388] The server uses an emotion engine to refine the generated proposal document. The input is the generated proposal document, and the output is the refined document. By inputting prompt sentences into a BERT-based generative AI model, the document's persuasiveness is improved by dynamically adjusting the tone and content to take into account the emotions the recipient will receive.

[0389] Step 6:

[0390] The user reviews the finalized proposal document and makes manual revisions as needed. The input is the revised document, and the output is the final version of the proposal document. Specifically, the user uses Microsoft Word or Google Docs to highlight important parts of the proposal document or add new information.

[0391] Step 7:

[0392] The server optimizes the timing of follow-ups with sales representatives based on user sentiment information. The input is user sentiment data, and the output is optimized assignments and notifications. The sentiment engine's analysis results are used to prompt sales representatives to take immediate action as needed, using the Google Calendar API.

[0393] (Application Example 2)

[0394] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0395] Proposal work for local government bidding projects is inefficient, requiring a great deal of manual work from information gathering to the creation of proposal documents. Furthermore, proposals tend to be uniform, making it difficult to consider the expectations and feelings of the 담당자 (person in charge). Moreover, improving the persuasiveness of proposal documents requires adjustments tailored to the emotions of each user. As a result, the success rate of proposals is low, and the process is time-consuming and laborious.

[0396] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0397] In this invention, the server includes means for automatically collecting information related to bids, means for analyzing the collected information and extracting requirements, and means for using emotion recognition technology to optimize the generated proposal materials based on the user's emotions. This improves the efficiency of the proposal process and enables the creation of optimal proposal materials that take the user's emotions into consideration.

[0398] "Information regarding bidding" refers to information related to public tenders for public works projects and contracts, etc., published by local governments.

[0399] "Analysis of collected information" refers to the process of extracting and organizing necessary requirements and conditions from acquired bidding information.

[0400] "Determining whether a proposal is feasible" is the process of evaluating whether a proposal is feasible for a particular project by referring to past bidding results and successful examples.

[0401] "Selecting the appropriate product" refers to the act of choosing the most suitable product or service for a project that has been deemed feasible.

[0402] "Automatic quotation generation" refers to the process of automatically generating a quotation by calculating prices and conditions based on selected products and services.

[0403] "Emotion recognition technology" is a technology that analyzes and determines a user's emotions from data, and is used to optimize proposal materials.

[0404] "Display and adjustment via smart devices" refers to the function of displaying generated proposal materials using devices such as smartphones and smart glasses, and making adjustments as needed.

[0405] This invention is an information processing system that streamlines the proposal process for local government bidding projects and optimizes proposal content based on emotions. This system primarily consists of a server, terminals, and users, which are detailed below.

[0406] The server automatically collects information on bids published by local governments via the internet. The collected information is analyzed using natural language processing (NLP) technology to extract necessary requirements. NLP libraries such as spaCy and NLTK are used for this analysis. Next, the server refers to past bid results in the database to determine whether a proposal is feasible for a given project. In this process, historical success stories of bids are an important indicator. If it is determined that a proposal is feasible, the server selects the most suitable product and generates an automated estimate based on it.

[0407] The generated proposal documents are optimized based on user emotions using emotion recognition technology. For this purpose, emotion analysis engines such as IBM Watson and Google Cloud Natural Language API are used. This makes the proposal documents more aligned with user expectations and more persuasive.

[0408] The terminal displays proposal materials generated using smart devices such as smartphones and smart glasses to the user. The user can review the content based on this information and make manual adjustments if necessary. This process is crucial for the proposal to meet a wider range of expectations.

[0409] For example, when proposing a design for a new urban park, the application creates an optimal proposal based on past successes and feedback from citizens. This proposal is then refined to reflect citizens' expectations through sentiment analysis.

[0410] Examples of prompts for the generating AI model include: "Please create a proposal for a newly planned urban park design. Consider past successes and citizen feedback, and include specific suggestions regarding budget and deadlines. Finally, incorporate elements that will increase citizen satisfaction."

[0411] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0412] Step 1:

[0413] The server automatically collects bidding information from local government websites and APIs. Inputs include URLs of bidding information and API endpoints. The server uses this information to perform web scraping or API calls to obtain raw data of the bidding information. This data is then output.

[0414] Step 2:

[0415] The server analyzes the collected raw data based on natural language processing (NLP) techniques. The input is the raw data obtained in step 1. The server uses an NLP library (e.g., spaCy, NLTK) to extract the specification requirements and obtains the output as structured data.

[0416] Step 3:

[0417] The server accesses a database of past bidding results and refers to the structured data obtained in step 2 to determine whether the proposal is acceptable or not. The input is structured data, and by searching the database, it finds similar past examples and obtains an output as a determination of whether the proposal is acceptable or not.

[0418] Step 4:

[0419] For cases where a proposal is deemed feasible, the server selects the most suitable product from the company's product database. The input is the result of the proposal feasibility assessment, and the server selects and outputs the most appropriate product information by referring to the product database.

[0420] Step 5:

[0421] The server automatically generates quotes based on the selected products. The input is the selected product information, and the server uses a price calculation algorithm to create and output quote data.

[0422] Step 6:

[0423] The server creates proposal documents based on the generated estimate data and optimizes them using sentiment recognition technology. The input consists of estimate data and user sentiment feedback. The sentiment analysis engine adjusts the tone and content of the documents and outputs them as the final proposal document.

[0424] Step 7:

[0425] The terminal displays the final proposal document to the user using a smartphone or smart glasses. The user reviews the proposal based on this document and makes manual adjustments as needed. The input is the final proposal document, and the output is the proposal document adjusted through the user's actions.

[0426] 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.

[0427] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0428] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0429] [Third Embodiment]

[0430] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0431] 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.

[0432] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0433] 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.

[0434] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0435] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0436] 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.

[0437] 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.

[0438] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0439] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0440] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0441] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0442] This invention is an information processing system for efficiently handling proposal work for local government bidding projects. The system consists of a server, terminals, and users, and each component works together to automate a series of business processes.

[0443] The server first periodically patrols websites and databases published by local governments to obtain new bidding information. This collection process is automated, allowing the server to register the bidding information in the database in real time.

[0444] Subsequently, the server analyzes the collected bidding information using natural language processing technology. It automatically extracts relevant items such as "delivery date," "budget," and "required technology" from the bidding specifications and saves them as structured data. This allows the analysis results to be effectively utilized in the next stage.

[0445] The terminal uses data analyzed by the server to determine whether or not to submit a proposal, referencing past bidding results and evaluation information. This allows for the prediction of success rates for each project and the efficient determination of which projects to submit proposals for.

[0446] If a proposal is deemed feasible, the terminal automatically searches the company's product database and selects the most suitable product for the proposal. This selection is based on factors such as technical specifications and available conditions. Furthermore, a quotation is automatically generated using a pre-configured template based on the selected product information.

[0447] Next, the server uses a generative AI model to create a proposal document. The proposal content is optimized using a model that has learned from past successes. The user reviews this document and makes adjustments if necessary.

[0448] Finally, once the user has finished reviewing the proposal, the system automatically assigns it to the relevant sales team. This ensures quick and accurate work execution, leading to an improved success rate in proposal activities.

[0449] As a concrete example, let's consider a new IT infrastructure project announced by a local government. The server immediately retrieves this information, analyzes the necessary technologies such as "cloud solutions" and "security features," and notifies the relevant team members. If the project matches past success patterns, the terminal automatically selects the relevant cloud solution products and creates a quotation. The user then performs a final check, ensuring a smooth handover to the sales team. This process is expected to significantly streamline the proposal process and improve the success rate.

[0450] The following describes the processing flow.

[0451] Step 1:

[0452] The server periodically crawls the public websites and related databases of local governments to detect new bidding opportunities and collect information. Data obtained via scraping or APIs is stored in the database.

[0453] Step 2:

[0454] The server applies natural language processing (NLP) techniques to the stored bid information, extracting key details such as "delivery date," "budget," and "required technology" from the specifications. This structures the information, making it easier to use in subsequent stages.

[0455] Step 3:

[0456] The terminal receives the analysis results from the server and compares them with past bidding and evaluation data. At this point, the proposal feasibility algorithm is activated to evaluate the feasibility of proposing a proposal for the project and determine whether it is acceptable or not.

[0457] Step 4:

[0458] For projects deemed feasible, the terminal selects the most suitable product by referring to the company's internal product database. It evaluates the technical suitability, cost, and delivery time of the product to determine the most appropriate one.

[0459] Step 5:

[0460] The terminal automatically generates a quotation based on the information of the selected products. Using a pre-configured quotation template, it prepares a quotation that includes the quantity, unit price, total amount, etc.

[0461] Step 6:

[0462] The server automatically generates proposal documents using a generation AI model based on the proposed content and quotation information. This process utilizes data from past successful proposals to increase the likelihood of the proposal being accepted.

[0463] Step 7:

[0464] The user receives the automatically generated proposal document from the server and reviews its contents. If necessary, they revise and adjust the document to finalize it.

[0465] Step 8:

[0466] Once the user has finished reviewing and refining the proposal, the system automatically requests its assignment to a sales representative. This ensures a smooth handover of tasks and enables a quick response.

[0467] (Example 1)

[0468] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0469] This invention aims to provide a process for efficiently collecting and analyzing local government bidding information, and for making highly accurate and rapid decisions in proposal work. Conventional methods require significant time and effort for manual information collection, analysis, and decision-making, limiting the success rate of proposal work. To solve this problem, an automated series of business processes via an information processing system is required.

[0470] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0471] In this invention, the server includes means for activating an information processing device for periodically collecting bid information, means for analyzing the collected bid information and extracting specification requirements using a natural language processing tool, and means for using a machine learning algorithm to determine the feasibility of a proposal by referring to past case results. This enables the entire process, from collecting bid information to optimizing proposal content and handing it over to the sales department, to be automated, thereby improving the efficiency and success rate of proposal work.

[0472] "Bidding information" refers to information published by public institutions that describes the requirements and conditions for a transaction, and is data necessary for a proposing company to win a contract.

[0473] "Means for activating the information processing device" refers to a function that allows the system to automatically start a periodic collection process, thereby streamlining the acquisition of bidding information.

[0474] "Natural language processing" is a technology that allows computers to extract useful information from human language. By using this technology to extract necessary requirements from bidding specifications, the data is structured.

[0475] A "machine learning algorithm" is a computational method that learns from past data and makes predictions and judgments about future data, and is used to determine the feasibility of a proposal.

[0476] "Means of generating quotes" refers to a function in the system that automatically creates a quote based on detailed information about the product, thereby improving time efficiency and accuracy.

[0477] A "generative AI model" is an artificial intelligence technology that can automatically generate appropriate output by learning from a large amount of data in advance, and is used to optimize proposal documents.

[0478] An "assignment request" refers to a notification or instruction from the system to assign a specific task to a person, thereby enabling a smooth transition of tasks.

[0479] Modes for carrying out the invention

[0480] The information processing system of this invention aims to improve operational efficiency and success rates by automating proposal work through the efficient collection and analysis of bidding information. The system mainly consists of three elements: a server, a terminal, and a user, each playing a different role.

[0481] First, the server periodically collects bidding information from websites and databases published by local governments. This involves web crawling using Python libraries such as Beautiful Soup and Scrapy. Next, the server utilizes natural language processing techniques to extract specification requirements such as "delivery date," "budget," and "required technology" from the collected bidding information. This process involves text analysis using NLTK and spaCy.

[0482] The terminal is responsible for determining whether a proposal is feasible by referring to a database of past cases based on analyzed data provided by the server. Here, machine learning algorithms such as random forest and linear regression are used to predict the success rate of the proposed cases. Based on the results, the terminal automatically selects the most suitable products for the cases deemed feasible and generates a quotation according to a template based on the selection results.

[0483] Furthermore, the server utilizes a generative AI model to create proposal documents. This generative AI model employs advanced artificial intelligence technologies such as OpenAI's GPT to generate optimal proposal documents based on the input prompt text.

[0484] As a concrete example, consider a case where a local government publishes a new IT infrastructure project. The server acquires this project information, automatically analyzes the necessary technologies such as "cloud solutions" and "security features," and notifies the relevant members. If this information matches past success patterns, the terminal automatically selects the relevant cloud solution products and creates a quotation. The user can then perform a final check and smoothly hand over the project to the sales team.

[0485] An example of a prompt message is: "Please prepare the following proposal document: Project name is New IT Infrastructure Implementation, Required technologies are Cloud Solutions and Security Features, and the key points of the proposal are XX and YY." Instructions are then given to the AI ​​model in this format.

[0486] In this way, the various components of the invention work together to achieve consistent automation and efficiency in the proposed tasks.

[0487] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0488] Step 1:

[0489] The server periodically crawls public websites and databases of local governments to collect bidding information. This process uses Python libraries such as Beautiful Soup and Scrapy, taking a list of URLs as input and generating the acquired HTML data as output. Web scraping techniques are applied to extract useful information from this data.

[0490] Step 2:

[0491] The server analyzes the collected HTML data using natural language processing techniques. The input is HTML data, and the output is structured data such as "delivery date," "budget," and "required technology." It utilizes Python's NLTK and spaCy to perform specific operations such as text analysis and regular expressions to extract necessary requirements.

[0492] Step 3:

[0493] The server stores the analyzed data in a database and provides it to the terminal. At this stage, the input is structured data, and the output is a record stored in the database. This makes the necessary information easily accessible to the user or other processes within the system.

[0494] Step 4:

[0495] The terminal accesses a database of past cases based on the provided analysis data and determines the feasibility of the proposal. It receives structured data as input and applies machine learning algorithms based on that data to calculate the success rate. The output includes a decision on whether or not the proposal is valid. This involves specific operations using random forests and linear regression.

[0496] Step 5:

[0497] The terminal automatically selects the most suitable products for projects deemed feasible and generates a quotation. The input is data for projects deemed feasible, and the output is the selected product information and a quotation generated according to a template. Product selection involves specific actions such as condition matching using an ERP system.

[0498] Step 6:

[0499] The server uses a generative AI model to create proposal documents. The input consists of prompts and product information, and the output is a completed proposal document. The generative AI model utilizes learning results based on past successes to generate an ideal proposal document.

[0500] Step 7:

[0501] The user reviews the generated proposals and quotations and makes revisions as needed. The input is the proposal and quotation, and the output is the final, completed document. The user's actions include reviewing the document content and making revisions or additions.

[0502] Step 8:

[0503] The server automatically sends assignment requests to the sales department based on the final version of the proposal document. The input is the finalized proposal document, and the output is an assignment request notification. Specific actions are included to ensure a smooth handover to the responsible person using an internal messaging application or email system.

[0504] (Application Example 1)

[0505] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0506] The process of preparing proposals for local government tenders typically requires a significant amount of time and effort. This is because it involves a wide range of manual tasks, including acquiring and analyzing tender information, drafting proposals, and selecting appropriate products and services. The challenge lies in executing these processes quickly and efficiently, and concentrating resources on projects with a high probability of success. Furthermore, the diverse nature of the proposals makes it difficult for staff to address every single one without overlooking anything.

[0507] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0508] In this invention, the server includes means for automatically collecting bidding information, means for analyzing the collected bidding information and extracting conditions, and means for determining whether a proposal is feasible based on past bids. This makes it possible to process information efficiently and improve the efficiency of proposal work. Furthermore, by providing information to user terminals in real time, it is possible to support rapid decision-making regarding proposal cases, enabling quick responses to cases with a high probability of being selected.

[0509] "Bidding information" refers to information released by local governments or organizations to solicit proposals and submissions for specific tasks or projects.

[0510] "Means of automatic collection" refers to processes or systems that have the function of periodically acquiring and recording information from designated sources based on specific conditions.

[0511] "Means of analysis and condition extraction" refer to the processes and technologies used to analyze collected data and find effective requirements and criteria from it.

[0512] "Means for determining the feasibility of a proposal based on past bids" refers to methods and techniques for evaluating the possibility and likelihood of success of a proposal for a new project based on past data and performance.

[0513] "Methods for selecting products" refers to the process of identifying and selecting the most suitable products or services for a proposal, using criteria and algorithms.

[0514] "Methods for automatically generating quotes" refer to systems that generate proposals and quotes according to templates based on selected products and services.

[0515] "Means for automatically creating generated proposal documents" refers to automated processes or software for documenting proposal content based on collected and analyzed information.

[0516] "Means for providing information to user terminals and notifying users of the addition of proposed projects" refers to communication means and interfaces for immediately notifying and displaying users when important information or new projects are registered.

[0517] To implement this invention, a server is configured as the central component of an information processing system. The server first automatically retrieves bidding information from the websites and data stores of specific local governments or organizations. This is achieved using web scraping libraries such as Python's requests or BeautifulSoup.

[0518] The server then analyzes the collected bid information using natural language processing techniques. This process utilizes libraries such as NLTK and Transformers to extract important conditions and requirements from the information. This yields entities such as specific specifications, deadlines, and budgets.

[0519] The analyzed information then moves to a phase where the feasibility of a proposal is determined by referencing past bidding data. The server uses past success stories and evaluation information to assess the probability of success for a proposal in a particular project. Based on this evaluation, projects that are eligible for proposals are selected.

[0520] For projects deemed feasible, the terminal searches the company's product database and selects the most suitable product. Based on this, the system automatically generates a quotation according to a template and makes it available for presentation to the user. Furthermore, using a generation AI model, the final proposal document is automatically created and completed after review by the user.

[0521] In this process, information is provided to the user's device in real time, and they are notified of the addition of new proposals. This allows the user to quickly review the proposals and make adjustments as needed.

[0522] For example, if a local government starts a bidding process for a new traffic management system, the server will collect this information and analyze the relevant data. In creating proposal documents using a generative AI model, an example of a prompt message would be, "Please optimize and create the proposal content for the traffic system bidding announced by the city." This allows the system to efficiently support the task.

[0523] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0524] Step 1:

[0525] The server uses a web scraping library to automatically retrieve bidding information from the websites of local governments and organizations. It accepts a list of web URLs as input and generates HTML data of the retrieved bidding information as output. This data is organized by analyzing the structure of the web pages.

[0526] Step 2:

[0527] Based on the parsed HTML data, the server utilizes natural language processing technology to extract conditions from the bidding information. The input is HTML data, and the output is structured text data such as "specifications," "delivery date," and "budget." This process involves tokenization of information and extraction of important keywords.

[0528] Step 3:

[0529] The server references a database of past bids and determines the feasibility of a proposal based on the extracted criteria. Inputs are text data related to the criteria and past successful bid data; output is an evaluation of the proposal's potential. An evaluation algorithm is then applied to select projects with a high probability of success.

[0530] Step 4:

[0531] The terminal receives information on potential projects from the server and searches the company's product database. It then selects the most suitable product. Here, the input is information on potential projects, and the output is information on the selected product. This selection is based on the product's suitability.

[0532] Step 5:

[0533] The terminal automatically generates a quotation based on the selected product information, following a template. The input is product information, and the output is a completed quotation. This step utilizes a template engine to automatically create the document.

[0534] Step 6:

[0535] The server uses a generation AI model to create the final proposal document, referencing past successful cases. The input consists of selected product information and success case data, and the output is a proposal document. During this process, the AI ​​model analyzes the information and uses prompts to create the optimal proposal.

[0536] Step 7:

[0537] The user reviews the proposal document generated by the server and adjusts its content as needed. The input is the proposal document, and the output is the final, adjusted version of the proposal document. At this stage, the user verifies the accuracy and appropriateness of the document.

[0538] Step 8:

[0539] The terminal notifies the sales team of the final proposal document and provides real-time updates on new proposals. Here, the input is the final proposal document, and the output is a notification to the sales team. This notification allows for a quick response to new proposals.

[0540] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0541] This invention is an information processing system that streamlines the proposal process for local government bidding projects, and by integrating an emotion engine, it optimizes proposal content based on the user's emotions. This system consists of a server, a terminal, a user, and an emotion engine that performs emotion recognition.

[0542] The server first automatically collects bidding information published by local governments and stores it in a database. The collected data is analyzed using natural language processing (NLP) technology, and necessary information is extracted from the specifications. The results of the analysis are structured into elements necessary for proposal formulation (e.g., deadline, budget, technical requirements).

[0543] Based on this analysis, the terminal can refer to past bidding results and determine whether or not to submit a proposal. Furthermore, for projects deemed feasible, it uses the company's internal product database to select the most suitable products and automatically generates a quotation.

[0544] The generated proposal documents are dynamically adjusted by the server, utilizing data from past success stories and employing an emotion engine to match the user's expectations in terms of expression and content. The emotion engine determines emotions from user feedback and data, optimizing the tone and structure of the proposal documents.

[0545] Users review the proposal materials provided by the server and perform manual reviews and adjustments as needed. Based on input from the emotion engine, the materials can be refined to become more persuasive.

[0546] Furthermore, assignment requests to sales representatives are optimized in terms of timing and priority based on the analysis results of the emotion engine. For example, if user anxiety or doubt is identified, assignments are adjusted to quickly follow up, thereby building even greater trust.

[0547] As a concrete example, consider a case where the system handles an IT infrastructure development project from a local government. The server retrieves project information and analyzes the requirements. The terminal refers to similar past success stories, proposes cloud solutions to determine their feasibility, and creates an estimate. Finally, the proposal document is adjusted through emotion engine analysis to be persuasive and considerate of the feelings of the local government official. Users are expected to use this document to make effective proposals to local governments, improving the consistency and success rate of their proposal activities.

[0548] The following describes the processing flow.

[0549] Step 1:

[0550] The server automatically collects the latest publicly available bidding information by patrolling the official websites and related databases of each local government. The collected data is immediately saved to the database in preparation for the next analysis step.

[0551] Step 2:

[0552] The server applies natural language processing (NLP) techniques to the collected bid information, extracting key requirements such as "delivery date," "budget," and "required technology" from the specification text. This analysis structures the data, making it more user-friendly.

[0553] Step 3:

[0554] The terminal refers to the analysis results received from the server and compares them with past bidding data and win / loss data to determine whether the proposal is feasible. In this process, the possibility of the proposal is evaluated based on successful past cases and the conditions of the current project.

[0555] Step 4:

[0556] The terminal searches the company's product database for projects deemed feasible and automatically selects the most suitable product for each project. During the selection process, it verifies the product's compatibility with technical requirements and its terms of service.

[0557] Step 5:

[0558] The terminal automatically generates a quotation using a predetermined template based on the selected product information. The quotation includes detailed information such as the required quantity, price, and delivery date.

[0559] Step 6:

[0560] The server creates proposal documents from product information and quotation information automatically generated using a generative AI model. During this process, it incorporates the analysis results of the emotion engine, adjusting the content to be sensitive to the emotions of the target audience.

[0561] Step 7:

[0562] Users receive and review proposal materials provided by the server, making necessary adjustments based on feedback from the sentiment engine. This process refines the materials to make them more persuasive.

[0563] Step 8:

[0564] Once the user has finished reviewing the proposal, the system automatically optimizes and sends assignment requests to sales representatives. The assignment priority and timing are adjusted based on the results of the emotion engine's recognition.

[0565] (Example 2)

[0566] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0567] In traditional proposal processes, the stages of gathering bidding information, creating proposal materials, and making adjustments that take emotions into consideration were fragmented, resulting in significant time and effort being required for each stage. Furthermore, determining the optimal timing for follow-up that takes user emotions into account was difficult, raising concerns that the efficiency and effectiveness of proposals would not be fully realized.

[0568] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0569] In this invention, the server includes a device for automatically collecting bidding information, a device for processing the information and detecting requirements, and a device for referring to past data and determining whether a proposal is acceptable. This enables the integrated processing of each process, improving the efficiency and accuracy of the proposal process. Furthermore, by using an emotion engine to adjust proposal materials and optimizing the timing of follow-ups based on user emotion information, the success rate of proposals can be improved.

[0570] "Bidding information" refers to data related to bids that are made public by public or private institutions for the purpose of conducting transactions.

[0571] "Collection equipment" refers to a combination of software and hardware used to collect bidding information, primarily through automated methods.

[0572] "Devices that process information and detect requirements" refer to technologies and devices used to analyze collected information and identify relevant specifications and requirements.

[0573] "A device that uses past data to determine the feasibility of a proposal" refers to a device and technology used to analyze past successes and failures and predict the success or failure of a new proposal.

[0574] An "emotion engine" refers to a technology or algorithm used to analyze a user's emotional state and adjust information and expressions accordingly.

[0575] "Optimizing the timing of follow-up" refers to a technique of adjusting the timing of the next action to be implemented at the most effective point, based on the needs and emotions of the recipient of the proposal.

[0576] The invention will now be described in terms of its implementation. This system provides an information processing method that supports efficient proposal work for responding to local government bidding projects. The system mainly consists of a server, terminals, users, and an engine that performs sentiment analysis.

[0577] The server automatically collects bidding information from local government websites on a regular basis using web scraping tools (e.g., Scrapy or BeautifulSoup). This information is stored in a database management system (e.g., PostgreSQL or MySQL). After collection, the server analyzes the data using natural language processing techniques (e.g., NLTK or SpaCy) and extracts necessary requirements from the bidding specifications. This enables accurate proposals based on established structured data.

[0578] The terminal compares the analysis results received from the server with past datasets to determine whether a proposal is feasible. This determination uses algorithms designed with machine learning libraries such as Scikit-learn. If a proposal is deemed feasible, it selects the most suitable products using the ERP system and product database, and automatically generates a quotation using Excel or PDF generation libraries.

[0579] The user reviews the final generated proposal document and makes adjustments as needed. This document is then dynamically adjusted using an emotion engine (e.g., a generative AI model using BERT) to match the tone and content of the target audience. This is expected to make the document more persuasive and improve the success rate of the proposal.

[0580] As a concrete example, let's consider a case where we handle IT infrastructure-related bidding projects from local governments. The server acquires and analyzes project information, while the terminal proposes cloud solutions based on past success stories and automatically generates estimates. Finally, the proposal materials become more persuasive through sentiment analysis, enabling more effective proposal activities.

[0581] An example of a prompt message is: "Please create a compelling proposal document for the latest bidding project by the local government. Please adjust the tone of the document, taking into account the feelings of the person in charge at the receiving organization."

[0582] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0583] Step 1:

[0584] The server automatically collects bidding information from local government websites. The input is the URL of the local government's webpage, and the output is HTML data. Specifically, it uses a web scraping library such as Scrapy to periodically crawl webpages according to a specified schedule. The collected HTML data is stored in a database.

[0585] Step 2:

[0586] The server analyzes the collected HTML data and extracts the requirements for the bidding specifications. The input is raw data in HTML format, and the output is structured database entries. Specifically, NLTK and SpaCy are used for natural language processing to extract keywords and specific phrases from the text data and structure them. This process determines the deadline, budget, technical requirements, etc.

[0587] Step 3:

[0588] The terminal receives structured data from the server, references past bidding results, and determines whether to approve the proposal. The input is structured data and a history of past successes and failures, and the output is the decision on whether to approve the proposal. A Scikit-learn machine learning model is used to determine the similarity to past datasets and predict the likelihood of the proposal's success.

[0589] Step 4:

[0590] The terminal automatically selects the most suitable products for projects deemed eligible for proposals and generates quotations. Input consists of a database of eligible projects and products, while output is a quotation. It selects the most suitable product based on the conditions by referring to an ERP system or product database. Quotations are generated and formatted using Excel or PDF generation libraries.

[0591] Step 5:

[0592] The server uses an emotion engine to refine the generated proposal document. The input is the generated proposal document, and the output is the refined document. By inputting prompt sentences into a BERT-based generative AI model, the document's persuasiveness is improved by dynamically adjusting the tone and content to take into account the emotions the recipient will receive.

[0593] Step 6:

[0594] The user reviews the finalized proposal document and makes manual revisions as needed. The input is the revised document, and the output is the final version of the proposal document. Specifically, the user uses Microsoft Word or Google Docs to highlight important parts of the proposal document or add new information.

[0595] Step 7:

[0596] The server optimizes the timing of follow-ups with sales representatives based on user sentiment information. The input is user sentiment data, and the output is optimized assignments and notifications. The sentiment engine's analysis results are used to prompt sales representatives to take immediate action as needed, using the Google Calendar API.

[0597] (Application Example 2)

[0598] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0599] Proposal work for local government bidding projects is inefficient, requiring a great deal of manual work from information gathering to the creation of proposal documents. Furthermore, proposals tend to be uniform, making it difficult to consider the expectations and feelings of the 담당자 (person in charge). Moreover, improving the persuasiveness of proposal documents requires adjustments tailored to the emotions of each user. As a result, the success rate of proposals is low, and the process is time-consuming and laborious.

[0600] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0601] In this invention, the server includes means for automatically collecting information related to bids, means for analyzing the collected information and extracting requirements, and means for using emotion recognition technology to optimize the generated proposal materials based on the user's emotions. This improves the efficiency of the proposal process and enables the creation of optimal proposal materials that take the user's emotions into consideration.

[0602] "Information regarding bidding" refers to information related to public tenders for public works projects and contracts, etc., published by local governments.

[0603] "Analysis of collected information" refers to the process of extracting and organizing necessary requirements and conditions from acquired bidding information.

[0604] "Determining whether a proposal is feasible" is the process of evaluating whether a proposal is feasible for a particular project by referring to past bidding results and successful examples.

[0605] "Selecting the appropriate product" refers to the act of choosing the most suitable product or service for a project that has been deemed feasible.

[0606] "Automatic quotation generation" refers to the process of automatically generating a quotation by calculating prices and conditions based on selected products and services.

[0607] "Emotion recognition technology" is a technology that analyzes and determines a user's emotions from data, and is used to optimize proposal materials.

[0608] "Display and adjustment via smart devices" refers to the function of displaying generated proposal materials using devices such as smartphones and smart glasses, and making adjustments as needed.

[0609] This invention is an information processing system that streamlines the proposal process for local government bidding projects and optimizes proposal content based on emotions. This system primarily consists of a server, terminals, and users, which are detailed below.

[0610] The server automatically collects information on bids published by local governments via the internet. The collected information is analyzed using natural language processing (NLP) technology to extract necessary requirements. NLP libraries such as spaCy and NLTK are used for this analysis. Next, the server refers to past bid results in the database to determine whether a proposal is feasible for a given project. In this process, historical success stories of bids are an important indicator. If it is determined that a proposal is feasible, the server selects the most suitable product and generates an automated estimate based on it.

[0611] The generated proposal documents are optimized based on user emotions using emotion recognition technology. For this purpose, emotion analysis engines such as IBM Watson and Google Cloud Natural Language API are used. This makes the proposal documents more aligned with user expectations and more persuasive.

[0612] The terminal displays proposal materials generated using smart devices such as smartphones and smart glasses to the user. The user can review the content and make manual adjustments if necessary. This process is crucial for the proposal to meet a wider range of expectations.

[0613] For example, when proposing a design for a new urban park, the application creates an optimal proposal based on past successes and feedback from citizens. This proposal is then refined to reflect citizens' expectations through sentiment analysis.

[0614] Examples of prompts for the generating AI model include: "Please create a proposal for a newly planned urban park design. Consider past successes and citizen feedback, and include specific suggestions regarding budget and deadlines. Finally, incorporate elements that will increase citizen satisfaction."

[0615] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0616] Step 1:

[0617] The server automatically collects bidding information from local government websites and APIs. Inputs include URLs of bidding information and API endpoints. The server uses this information to perform web scraping or API calls to obtain raw data of the bidding information. This data is then output.

[0618] Step 2:

[0619] The server analyzes the collected raw data based on natural language processing (NLP) techniques. The input is the raw data obtained in step 1. The server uses an NLP library (e.g., spaCy, NLTK) to extract the specification requirements and obtains the output as structured data.

[0620] Step 3:

[0621] The server accesses a database of past bidding results and refers to the structured data obtained in step 2 to determine whether the proposal is acceptable or not. The input is structured data, and by searching the database, it finds similar past examples and obtains an output as a determination of whether the proposal is acceptable or not.

[0622] Step 4:

[0623] For cases where a proposal is deemed feasible, the server selects the most suitable product from the company's product database. The input is the result of the proposal feasibility assessment, and the server selects and outputs the most appropriate product information by referring to the product database.

[0624] Step 5:

[0625] The server automatically generates quotes based on the selected products. The input is the selected product information, and the server uses a price calculation algorithm to create and output quote data.

[0626] Step 6:

[0627] The server creates proposal documents based on the generated estimate data and optimizes them using sentiment recognition technology. The input consists of estimate data and user sentiment feedback. The sentiment analysis engine adjusts the tone and content of the documents and outputs them as the final proposal document.

[0628] Step 7:

[0629] The terminal displays the final proposal document to the user using a smartphone or smart glasses. The user reviews the proposal based on this document and makes manual adjustments as needed. The input is the final proposal document, and the output is the proposal document adjusted through the user's actions.

[0630] 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.

[0631] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0632] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0633] [Fourth Embodiment]

[0634] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0635] 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.

[0636] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0637] 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.

[0638] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0639] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0640] 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.

[0641] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0642] 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.

[0643] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0644] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0645] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0646] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0647] This invention is an information processing system for efficiently handling proposal work for local government bidding projects. The system consists of a server, terminals, and users, and each component works together to automate a series of business processes.

[0648] The server first periodically patrols websites and databases published by local governments to obtain new bidding information. This collection process is automated, allowing the server to register the bidding information in the database in real time.

[0649] Subsequently, the server analyzes the collected bidding information using natural language processing technology. It automatically extracts relevant items such as "delivery date," "budget," and "required technology" from the bidding specifications and saves them as structured data. This allows the analysis results to be effectively utilized in the next stage.

[0650] The terminal uses data analyzed by the server to determine whether or not to submit a proposal, referencing past bidding results and evaluation information. This allows for the prediction of success rates for each project and the efficient determination of which projects to submit proposals for.

[0651] If a proposal is deemed feasible, the terminal automatically searches the company's product database and selects the most suitable product for the proposal. This selection is based on factors such as technical specifications and available conditions. Furthermore, a quotation is automatically generated using a pre-configured template based on the selected product information.

[0652] Next, the server uses a generative AI model to create a proposal document. The proposal content is optimized using a model that has learned from past successes. The user reviews this document and makes adjustments if necessary.

[0653] Finally, once the user has finished reviewing the proposal, the system automatically assigns it to the relevant sales team. This ensures quick and accurate work execution, leading to an improved success rate in proposal activities.

[0654] As a concrete example, let's consider a new IT infrastructure project announced by a local government. The server immediately retrieves this information, analyzes the necessary technologies such as "cloud solutions" and "security features," and notifies the relevant team members. If the project matches past success patterns, the terminal automatically selects the relevant cloud solution products and creates a quotation. The user then performs a final check, ensuring a smooth handover to the sales team. This process is expected to significantly streamline the proposal process and improve the success rate.

[0655] The following describes the processing flow.

[0656] Step 1:

[0657] The server periodically crawls the public websites and related databases of local governments to detect new bidding opportunities and collect information. Data obtained via scraping or APIs is stored in the database.

[0658] Step 2:

[0659] The server applies natural language processing (NLP) techniques to the stored bid information, extracting key details such as "delivery date," "budget," and "required technology" from the specifications. This structures the information, making it easier to use in subsequent stages.

[0660] Step 3:

[0661] The terminal receives the analysis results from the server and compares them with past bidding and evaluation data. At this point, the proposal feasibility algorithm is activated to evaluate the feasibility of proposing a proposal for the project and determine whether it is acceptable or not.

[0662] Step 4:

[0663] For projects deemed feasible, the terminal selects the most suitable product by referring to the company's internal product database. It evaluates the technical suitability, cost, and delivery time of the product to determine the most appropriate one.

[0664] Step 5:

[0665] The terminal automatically generates a quotation based on the information of the selected products. Using a pre-configured quotation template, it prepares a quotation that includes the quantity, unit price, total amount, etc.

[0666] Step 6:

[0667] The server automatically generates proposal documents using a generation AI model based on the proposed content and quotation information. This process utilizes data from past successful proposals to increase the likelihood of the proposal being accepted.

[0668] Step 7:

[0669] The user receives the automatically generated proposal document from the server and reviews its contents. If necessary, they revise and adjust the document to finalize it.

[0670] Step 8:

[0671] Once the user has finished reviewing and refining the proposal, the system automatically requests its assignment to a sales representative. This ensures a smooth handover of tasks and enables a quick response.

[0672] (Example 1)

[0673] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0674] This invention aims to provide a process for efficiently collecting and analyzing local government bidding information, and for making highly accurate and rapid decisions in proposal work. Conventional methods require significant time and effort for manual information collection, analysis, and decision-making, limiting the success rate of proposal work. To solve this problem, an automated series of business processes via an information processing system is required.

[0675] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0676] In this invention, the server includes means for activating an information processing device for periodically collecting bid information, means for analyzing the collected bid information and extracting specification requirements using a natural language processing tool, and means for using a machine learning algorithm to determine the feasibility of a proposal by referring to past case results. This enables the entire process, from collecting bid information to optimizing proposal content and handing it over to the sales department, to be automated, thereby improving the efficiency and success rate of proposal work.

[0677] "Bidding information" refers to information published by public institutions that describes the requirements and conditions for a transaction, and is data necessary for a proposing company to win a contract.

[0678] "Means for activating the information processing device" refers to a function that allows the system to automatically start a periodic collection process, thereby streamlining the acquisition of bidding information.

[0679] "Natural language processing" is a technology that allows computers to extract useful information from human language. By using this technology to extract necessary requirements from bidding specifications, the data is structured.

[0680] A "machine learning algorithm" is a computational method that learns from past data and makes predictions and judgments about future data, and is used to determine the feasibility of a proposal.

[0681] "Means of generating quotes" refers to a function in the system that automatically creates a quote based on detailed information about the product, thereby improving time efficiency and accuracy.

[0682] A "generative AI model" is an artificial intelligence technology that can automatically generate appropriate output by learning from a large amount of data in advance, and is used to optimize proposal documents.

[0683] An "assignment request" refers to a notification or instruction from the system to assign a specific task to a person, thereby enabling a smooth transition of tasks.

[0684] Modes for carrying out the invention

[0685] The information processing system of this invention aims to improve operational efficiency and success rates by automating proposal work through the efficient collection and analysis of bidding information. The system mainly consists of three elements: a server, a terminal, and a user, each playing a different role.

[0686] First, the server periodically collects bidding information from websites and databases published by local governments. This involves web crawling using Python libraries such as Beautiful Soup and Scrapy. Next, the server utilizes natural language processing techniques to extract specification requirements such as "delivery date," "budget," and "required technology" from the collected bidding information. This process involves text analysis using NLTK and spaCy.

[0687] The terminal is responsible for determining whether a proposal is feasible by referring to a database of past cases based on analyzed data provided by the server. Here, machine learning algorithms such as random forest and linear regression are used to predict the success rate of the proposed cases. Based on the results, the terminal automatically selects the most suitable products for the cases deemed feasible and generates a quotation according to a template based on the selection results.

[0688] Furthermore, the server utilizes a generative AI model to create proposal documents. This generative AI model employs advanced artificial intelligence technologies such as OpenAI's GPT to generate optimal proposal documents based on the input prompt text.

[0689] As a concrete example, consider a case where a local government publishes a new IT infrastructure project. The server acquires this project information, automatically analyzes the necessary technologies such as "cloud solutions" and "security features," and notifies the relevant members. If this information matches past success patterns, the terminal automatically selects the relevant cloud solution products and creates a quotation. The user can then perform a final check and smoothly hand over the project to the sales team.

[0690] An example of a prompt message is: "Please prepare the following proposal document: Project name is New IT Infrastructure Implementation, Required technologies are Cloud Solutions and Security Features, and the key points of the proposal are XX and YY." Instructions are then given to the AI ​​model in this format.

[0691] In this way, the various components of the invention work together to achieve consistent automation and efficiency in the proposed tasks.

[0692] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0693] Step 1:

[0694] The server periodically crawls public websites and databases of local governments to collect bidding information. This process uses Python libraries such as Beautiful Soup and Scrapy, taking a list of URLs as input and generating the acquired HTML data as output. Web scraping techniques are applied to extract useful information from this data.

[0695] Step 2:

[0696] The server analyzes the collected HTML data using natural language processing techniques. The input is HTML data, and the output is structured data such as "delivery date," "budget," and "required technology." It utilizes Python's NLTK and spaCy to perform specific operations such as text analysis and regular expressions to extract necessary requirements.

[0697] Step 3:

[0698] The server stores the analyzed data in a database and provides it to the terminal. At this stage, the input is structured data, and the output is a record stored in the database. This makes the necessary information easily accessible to the user or other processes within the system.

[0699] Step 4:

[0700] The terminal accesses a database of past cases based on the provided analysis data and determines the feasibility of the proposal. It receives structured data as input and applies machine learning algorithms based on that data to calculate the success rate. The output includes a decision on whether or not the proposal is valid. This involves specific operations using random forests and linear regression.

[0701] Step 5:

[0702] The terminal automatically selects the most suitable products for projects deemed feasible and generates a quotation. The input is data for projects deemed feasible, and the output is the selected product information and a quotation generated according to a template. Product selection involves specific actions such as condition matching using an ERP system.

[0703] Step 6:

[0704] The server uses a generative AI model to create proposal documents. The input consists of prompts and product information, and the output is a completed proposal document. The generative AI model utilizes learning results based on past successes to generate an ideal proposal document.

[0705] Step 7:

[0706] The user reviews the generated proposals and quotations and makes revisions as needed. The input is the proposal and quotation, and the output is the final, completed document. The user's actions include reviewing the document content and making revisions or additions.

[0707] Step 8:

[0708] The server automatically sends assignment requests to the sales department based on the final version of the proposal document. The input is the finalized proposal document, and the output is an assignment request notification. Specific actions are included to ensure a smooth handover to the responsible person using an internal messaging application or email system.

[0709] (Application Example 1)

[0710] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0711] The process of preparing proposals for local government tenders typically requires a significant amount of time and effort. This is because it involves a wide range of manual tasks, including acquiring and analyzing tender information, drafting proposals, and selecting appropriate products and services. The challenge lies in executing these processes quickly and efficiently, and concentrating resources on projects with a high probability of success. Furthermore, the diverse nature of the proposals makes it difficult for staff to address every single one without overlooking anything.

[0712] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0713] In this invention, the server includes means for automatically collecting bidding information, means for analyzing the collected bidding information and extracting conditions, and means for determining whether a proposal is feasible based on past bids. This makes it possible to process information efficiently and improve the efficiency of proposal work. Furthermore, by providing information to user terminals in real time, it is possible to support rapid decision-making regarding proposal cases, enabling quick responses to cases with a high probability of being selected.

[0714] "Bidding information" refers to information released by local governments or organizations to solicit proposals and submissions for specific tasks or projects.

[0715] "Means of automatic collection" refers to processes or systems that have the function of periodically acquiring and recording information from designated sources based on specific conditions.

[0716] "Means of analysis and condition extraction" refer to the processes and technologies used to analyze collected data and find effective requirements and criteria from it.

[0717] "Means for determining the feasibility of a proposal based on past bids" refers to methods and techniques for evaluating the possibility and likelihood of success of a proposal for a new project based on past data and performance.

[0718] "Methods for selecting products" refers to the process of identifying and selecting the most suitable products or services for a proposal, using criteria and algorithms.

[0719] "Methods for automatically generating quotes" refer to systems that generate proposals and quotes according to templates based on selected products and services.

[0720] "Means for automatically creating generated proposal documents" refers to automated processes or software for documenting proposal content based on collected and analyzed information.

[0721] "Means for providing information to user terminals and notifying users of the addition of proposed projects" refers to communication means and interfaces for immediately notifying and displaying users when important information or new projects are registered.

[0722] To implement this invention, a server is configured as the central component of an information processing system. The server first automatically retrieves bidding information from the websites and data stores of specific local governments or organizations. This is achieved using web scraping libraries such as Python's requests or BeautifulSoup.

[0723] The server then analyzes the collected bid information using natural language processing techniques. This process utilizes libraries such as NLTK and Transformers to extract important conditions and requirements from the information. This yields entities such as specific specifications, deadlines, and budgets.

[0724] The analyzed information then moves to a phase where the feasibility of a proposal is determined by referencing past bidding data. The server uses past success stories and evaluation information to assess the probability of success for a proposal in a particular project. Based on this evaluation, projects that are eligible for proposals are selected.

[0725] For projects deemed feasible, the terminal searches the company's product database and selects the most suitable product. Based on this, the system automatically generates a quotation according to a template and makes it available for presentation to the user. Furthermore, using a generation AI model, the final proposal document is automatically created and completed after review by the user.

[0726] In this process, information is provided to the user's device in real time, and they are notified of the addition of new proposals. This allows the user to quickly review the proposals and make adjustments as needed.

[0727] For example, if a local government starts a bidding process for a new traffic management system, the server will collect this information and analyze the relevant data. In creating proposal documents using a generative AI model, an example of a prompt message would be, "Please optimize and create the proposal content for the traffic system bidding announced by the city." This allows the system to efficiently support the task.

[0728] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0729] Step 1:

[0730] The server uses a web scraping library to automatically retrieve bidding information from the websites of local governments and organizations. It accepts a list of web URLs as input and generates HTML data of the retrieved bidding information as output. This data is organized by analyzing the structure of the web pages.

[0731] Step 2:

[0732] Based on the parsed HTML data, the server utilizes natural language processing technology to extract conditions from the bidding information. The input is HTML data, and the output is structured text data such as "specifications," "delivery date," and "budget." This process involves tokenization of information and extraction of important keywords.

[0733] Step 3:

[0734] The server references a database of past bids and determines the feasibility of a proposal based on the extracted criteria. Inputs are text data related to the criteria and past successful bid data; output is an evaluation of the proposal's potential. An evaluation algorithm is then applied to select projects with a high probability of success.

[0735] Step 4:

[0736] The terminal receives information on potential projects from the server and searches the company's product database. It then selects the most suitable product. Here, the input is information on potential projects, and the output is information on the selected product. This selection is based on the product's suitability.

[0737] Step 5:

[0738] The terminal automatically generates a quotation based on the selected product information, following a template. The input is product information, and the output is a completed quotation. This step utilizes a template engine to automatically create the document.

[0739] Step 6:

[0740] The server uses a generation AI model to create the final proposal document, referencing past successful cases. The input consists of selected product information and success case data, and the output is a proposal document. During this process, the AI ​​model analyzes the information and uses prompts to create the optimal proposal.

[0741] Step 7:

[0742] The user reviews the proposal document generated by the server and adjusts its content as needed. The input is the proposal document, and the output is the final, adjusted version of the proposal document. At this stage, the user verifies the accuracy and appropriateness of the document.

[0743] Step 8:

[0744] The terminal notifies the sales team of the final proposal document and provides real-time updates on new proposals. Here, the input is the final proposal document, and the output is a notification to the sales team. This notification allows for a quick response to new proposals.

[0745] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0746] This invention is an information processing system that streamlines the proposal process for local government bidding projects, and by integrating an emotion engine, it optimizes proposal content based on the user's emotions. This system consists of a server, a terminal, a user, and an emotion engine that performs emotion recognition.

[0747] The server first automatically collects bidding information published by local governments and stores it in a database. The collected data is analyzed using natural language processing (NLP) technology, and necessary information is extracted from the specifications. The results of the analysis are structured into elements necessary for proposal formulation (e.g., deadline, budget, technical requirements).

[0748] Based on this analysis, the terminal can refer to past bidding results and determine whether or not to submit a proposal. Furthermore, for projects deemed feasible, it uses the company's internal product database to select the most suitable products and automatically generates a quotation.

[0749] The generated proposal documents are dynamically adjusted by the server, utilizing data from past success stories and employing an emotion engine to match the user's expectations in terms of expression and content. The emotion engine determines emotions from user feedback and data, optimizing the tone and structure of the proposal documents.

[0750] Users review the proposal materials provided by the server and perform manual reviews and adjustments as needed. Based on input from the emotion engine, the materials can be refined to become more persuasive.

[0751] Furthermore, assignment requests to sales representatives are optimized in terms of timing and priority based on the analysis results of the emotion engine. For example, if user anxiety or doubt is identified, assignments are adjusted to quickly follow up, thereby building even greater trust.

[0752] As a concrete example, consider a case where the system handles an IT infrastructure development project from a local government. The server retrieves project information and analyzes the requirements. The terminal refers to similar past success stories, proposes cloud solutions to determine their feasibility, and creates an estimate. Finally, the proposal document is adjusted through emotion engine analysis to be persuasive and considerate of the feelings of the local government official. Users are expected to use this document to make effective proposals to local governments, improving the consistency and success rate of their proposal activities.

[0753] The following describes the processing flow.

[0754] Step 1:

[0755] The server automatically collects the latest publicly available bidding information by patrolling the official websites and related databases of each local government. The collected data is immediately saved to the database in preparation for the next analysis step.

[0756] Step 2:

[0757] The server applies natural language processing (NLP) techniques to the collected bid information, extracting key requirements such as "delivery date," "budget," and "required technology" from the specification text. This analysis structures the data, making it more user-friendly.

[0758] Step 3:

[0759] The terminal refers to the analysis results received from the server and compares them with past bidding data and win / loss data to determine whether the proposal is feasible. In this process, the possibility of the proposal is evaluated based on successful past cases and the conditions of the current project.

[0760] Step 4:

[0761] The terminal searches the company's product database for projects deemed feasible and automatically selects the most suitable product for each project. During the selection process, it verifies the product's compatibility with technical requirements and its terms of service.

[0762] Step 5:

[0763] The terminal automatically generates a quotation using a predetermined template based on the selected product information. The quotation includes detailed information such as the required quantity, price, and delivery date.

[0764] Step 6:

[0765] The server creates proposal documents from product information and quotation information automatically generated using a generative AI model. During this process, it incorporates the analysis results of the emotion engine, adjusting the content to be sensitive to the emotions of the target audience.

[0766] Step 7:

[0767] Users receive and review proposal materials provided by the server, making necessary adjustments based on feedback from the sentiment engine. This process refines the materials to make them more persuasive.

[0768] Step 8:

[0769] Once the user has finished reviewing the proposal, the system automatically optimizes and sends assignment requests to sales representatives. The assignment priority and timing are adjusted based on the results of the emotion engine's recognition.

[0770] (Example 2)

[0771] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0772] In traditional proposal processes, the stages of gathering bidding information, creating proposal materials, and making adjustments that take emotions into consideration were fragmented, resulting in significant time and effort being required for each stage. Furthermore, determining the optimal timing for follow-up that takes user emotions into account was difficult, raising concerns that the efficiency and effectiveness of proposals would not be fully realized.

[0773] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0774] In this invention, the server includes a device for automatically collecting bidding information, a device for processing the information and detecting requirements, and a device for referring to past data and determining whether a proposal is acceptable. This enables the integrated processing of each process, improving the efficiency and accuracy of the proposal process. Furthermore, by using an emotion engine to adjust proposal materials and optimizing the timing of follow-ups based on user emotion information, the success rate of proposals can be improved.

[0775] "Bidding information" refers to data related to bids that are made public by public or private institutions for the purpose of conducting transactions.

[0776] "Collection equipment" refers to a combination of software and hardware used to collect bidding information, primarily through automated methods.

[0777] "Devices that process information and detect requirements" refer to technologies and devices used to analyze collected information and identify relevant specifications and requirements.

[0778] "A device that uses past data to determine the feasibility of a proposal" refers to a device and technology used to analyze past successes and failures and predict the success or failure of a new proposal.

[0779] An "emotion engine" refers to a technology or algorithm used to analyze a user's emotional state and adjust information and expressions accordingly.

[0780] "Optimizing the timing of follow-up" refers to a technique of adjusting the timing of the next action to be implemented at the most effective point, based on the needs and emotions of the recipient of the proposal.

[0781] The invention will now be described in terms of its implementation. This system provides an information processing method that supports efficient proposal work for responding to local government bidding projects. The system mainly consists of a server, terminals, users, and an engine that performs sentiment analysis.

[0782] The server automatically collects bidding information from local government websites on a regular basis using web scraping tools (e.g., Scrapy or BeautifulSoup). This information is stored in a database management system (e.g., PostgreSQL or MySQL). After collection, the server analyzes the data using natural language processing techniques (e.g., NLTK or SpaCy) and extracts necessary requirements from the bidding specifications. This enables accurate proposals based on established structured data.

[0783] The terminal compares the analysis results received from the server with past datasets to determine whether a proposal is feasible. This determination uses algorithms designed with machine learning libraries such as Scikit-learn. If a proposal is deemed feasible, it selects the most suitable products using the ERP system and product database, and automatically generates a quotation using Excel or PDF generation libraries.

[0784] The user reviews the final generated proposal document and makes adjustments as needed. This document is then dynamically adjusted using an emotion engine (e.g., a generative AI model using BERT) to match the tone and content of the target audience. This is expected to make the document more persuasive and improve the success rate of the proposal.

[0785] As a concrete example, let's consider a case where we handle IT infrastructure-related bidding projects from local governments. The server acquires and analyzes project information, while the terminal proposes cloud solutions based on past success stories and automatically generates estimates. Finally, the proposal materials become more persuasive through sentiment analysis, enabling more effective proposal activities.

[0786] An example of a prompt message is: "Please create a compelling proposal document for the latest bidding project by the local government. Please adjust the tone of the document, taking into account the feelings of the person in charge at the receiving organization."

[0787] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0788] Step 1:

[0789] The server automatically collects bidding information from local government websites. The input is the URL of the local government's webpage, and the output is HTML data. Specifically, it uses a web scraping library such as Scrapy to periodically crawl webpages according to a specified schedule. The collected HTML data is stored in a database.

[0790] Step 2:

[0791] The server analyzes the collected HTML data and extracts the requirements for the bidding specifications. The input is raw data in HTML format, and the output is structured database entries. Specifically, NLTK and SpaCy are used for natural language processing to extract keywords and specific phrases from the text data and structure them. This process determines the deadline, budget, technical requirements, etc.

[0792] Step 3:

[0793] The terminal receives structured data from the server, references past bidding results, and determines whether to approve the proposal. The input is structured data and a history of past successes and failures, and the output is the decision on whether to approve the proposal. A Scikit-learn machine learning model is used to determine the similarity to past datasets and predict the likelihood of the proposal's success.

[0794] Step 4:

[0795] The terminal automatically selects the most suitable products for projects deemed eligible for proposals and generates quotations. Input consists of a database of eligible projects and products, while output is a quotation. It selects the most suitable product based on the conditions by referring to an ERP system or product database. Quotations are generated and formatted using Excel or PDF generation libraries.

[0796] Step 5:

[0797] The server uses an emotion engine to refine the generated proposal document. The input is the generated proposal document, and the output is the refined document. By inputting prompt sentences into a BERT-based generative AI model, the document's persuasiveness is improved by dynamically adjusting the tone and content to take into account the emotions the recipient will receive.

[0798] Step 6:

[0799] The user reviews the finalized proposal document and makes manual revisions as needed. The input is the revised document, and the output is the final version of the proposal document. Specifically, the user uses Microsoft Word or Google Docs to highlight important parts of the proposal document or add new information.

[0800] Step 7:

[0801] The server optimizes the timing of follow-ups with sales representatives based on user sentiment information. The input is user sentiment data, and the output is optimized assignments and notifications. The sentiment engine's analysis results are used to prompt sales representatives to take immediate action as needed, using the Google Calendar API.

[0802] (Application Example 2)

[0803] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0804] Proposal work for local government bidding projects is inefficient, requiring a great deal of manual work from information gathering to the creation of proposal documents. Furthermore, proposals tend to be uniform, making it difficult to consider the expectations and feelings of the 담당자 (person in charge). Moreover, improving the persuasiveness of proposal documents requires adjustments tailored to the emotions of each user. As a result, the success rate of proposals is low, and the process is time-consuming and laborious.

[0805] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0806] In this invention, the server includes means for automatically collecting information related to bids, means for analyzing the collected information and extracting requirements, and means for using emotion recognition technology to optimize the generated proposal materials based on the user's emotions. This improves the efficiency of the proposal process and enables the creation of optimal proposal materials that take the user's emotions into consideration.

[0807] "Information regarding bidding" refers to information related to public tenders for public works projects and contracts, etc., published by local governments.

[0808] "Analysis of collected information" refers to the process of extracting and organizing necessary requirements and conditions from acquired bidding information.

[0809] "Determining whether a proposal is feasible" is the process of evaluating whether a proposal is feasible for a particular project by referring to past bidding results and successful examples.

[0810] "Selecting the appropriate product" refers to the act of choosing the most suitable product or service for a project that has been deemed feasible.

[0811] "Automatic quotation generation" refers to the process of automatically generating a quotation by calculating prices and conditions based on selected products and services.

[0812] "Emotion recognition technology" is a technology that analyzes and determines a user's emotions from data, and is used to optimize proposal materials.

[0813] "Display and adjustment via smart devices" refers to the function of displaying generated proposal materials using devices such as smartphones and smart glasses, and making adjustments as needed.

[0814] This invention is an information processing system that streamlines the proposal process for local government bidding projects and optimizes proposal content based on emotions. This system primarily consists of a server, terminals, and users, which are detailed below.

[0815] The server automatically collects information on bids published by local governments via the internet. The collected information is analyzed using natural language processing (NLP) technology to extract necessary requirements. NLP libraries such as spaCy and NLTK are used for this analysis. Next, the server refers to past bid results in the database to determine whether a proposal is feasible for a given project. In this process, historical success stories of bids are an important indicator. If it is determined that a proposal is feasible, the server selects the most suitable product and generates an automated estimate based on it.

[0816] The generated proposal documents are optimized based on user emotions using emotion recognition technology. For this purpose, emotion analysis engines such as IBM Watson and Google Cloud Natural Language API are used. This makes the proposal documents more aligned with user expectations and more persuasive.

[0817] The terminal displays proposal materials generated using smart devices such as smartphones and smart glasses to the user. The user can review the content and make manual adjustments if necessary. This process is crucial for the proposal to meet a wider range of expectations.

[0818] For example, when proposing a design for a new urban park, the application creates an optimal proposal based on past successes and feedback from citizens. This proposal is then refined to reflect citizens' expectations through sentiment analysis.

[0819] Examples of prompts for the generating AI model include: "Please create a proposal for a newly planned urban park design. Consider past successes and citizen feedback, and include specific suggestions regarding budget and deadlines. Finally, incorporate elements that will increase citizen satisfaction."

[0820] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0821] Step 1:

[0822] The server automatically collects bidding information from local government websites and APIs. Inputs include URLs of bidding information and API endpoints. The server uses this information to perform web scraping or API calls to obtain raw data of the bidding information. This data is then output.

[0823] Step 2:

[0824] The server analyzes the collected raw data based on natural language processing (NLP) techniques. The input is the raw data obtained in step 1. The server uses an NLP library (e.g., spaCy, NLTK) to extract the specification requirements and obtains the output as structured data.

[0825] Step 3:

[0826] The server accesses a database of past bidding results and refers to the structured data obtained in step 2 to determine whether the proposal is acceptable or not. The input is structured data, and by searching the database, it finds similar past examples and obtains an output as a determination of whether the proposal is acceptable or not.

[0827] Step 4:

[0828] For cases where a proposal is deemed feasible, the server selects the most suitable product from the company's product database. The input is the result of the proposal feasibility assessment, and the server selects and outputs the most appropriate product information by referring to the product database.

[0829] Step 5:

[0830] The server automatically generates quotes based on the selected products. The input is the selected product information, and the server uses a price calculation algorithm to create and output quote data.

[0831] Step 6:

[0832] The server creates proposal documents based on the generated estimate data and optimizes them using sentiment recognition technology. The input consists of estimate data and user sentiment feedback. The sentiment analysis engine adjusts the tone and content of the documents and outputs them as the final proposal document.

[0833] Step 7:

[0834] The terminal displays the final proposal document to the user using a smartphone or smart glasses. The user reviews the proposal based on this document and makes manual adjustments as needed. The input is the final proposal document, and the output is the proposal document adjusted through the user's actions.

[0835] 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.

[0836] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0837] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0838] 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.

[0839] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0840] 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.

[0841] 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.

[0842] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0843] 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."

[0844] 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.

[0845] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0846] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0847] 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.

[0848] 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.

[0849] 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.

[0850] 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 this memory.

[0851] 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.

[0852] 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.

[0853] 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.

[0854] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0855] 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.

[0856] The following is further disclosed regarding the embodiments described above.

[0857] (Claim 1)

[0858] A means of automatically collecting bidding information,

[0859] A means of analyzing the collected bidding information and extracting the specification requirements,

[0860] A means of determining whether a proposal is acceptable by referring to past bidding results,

[0861] A means of selecting the most suitable product for projects deemed feasible,

[0862] A means of automatically generating a quote based on the selected products,

[0863] A means of automatically creating the generated proposal documents,

[0864] An information processing system that includes this.

[0865] (Claim 2)

[0866] The information processing system according to claim 1, which includes means for optimizing the content of proposal documents based on data from past successful projects.

[0867] (Claim 3)

[0868] The information processing system according to claim 1, comprising means for automatically issuing assignment requests for proposal preparation.

[0869] "Example 1"

[0870] (Claim 1)

[0871] A means for activating an information processing device for periodically collecting bidding information,

[0872] A method for analyzing collected bidding information and extracting specification requirements using natural language processing tools,

[0873] A method of using machine learning algorithms to determine the feasibility of a proposal by referring to the results of past projects,

[0874] A means for automatically selecting the most suitable product for projects deemed acceptable and generating an estimate based on the product specifications,

[0875] A method for automatically creating proposal documents using a generative AI model,

[0876] A system that includes this.

[0877] (Claim 2)

[0878] The system according to claim 1, comprising means for optimizing the content of proposal documents using a generative AI model that has learned from data of past successful projects.

[0879] (Claim 3)

[0880] The system according to claim 1, including means for automatically requesting assignment to the sales department after a proposal has been prepared.

[0881] "Application Example 1"

[0882] (Claim 1)

[0883] A means of automatically collecting bidding information,

[0884] A means of analyzing the collected bidding information and extracting conditions,

[0885] A means of determining whether a proposal is acceptable based on past bids,

[0886] A means of selecting the most suitable product for projects deemed feasible,

[0887] A means of automatically generating a quote based on the selected product,

[0888] A means of automatically creating the generated proposal documents,

[0889] A means of providing information to user terminals in real time and notifying them of the addition of proposed projects,

[0890] Information systems including

[0891] (Claim 2)

[0892] The system according to claim 1, which includes means for optimizing the content of proposal documents based on data from past successful cases.

[0893] (Claim 3)

[0894] The system according to claim 1, comprising means for automatically making assignment requests for proposal preparation.

[0895] "Example 2 of combining an emotion engine"

[0896] (Claim 1)

[0897] A device that automatically collects bidding information,

[0898] A device that processes collected information and detects requirements,

[0899] A device that refers to past data to determine whether a proposal is acceptable or not,

[0900] A device for selecting the most suitable product for projects deemed feasible,

[0901] A device that automatically generates quotes based on selected products,

[0902] A device that uses an emotion engine to adjust the generated material,

[0903] A system that includes this.

[0904] (Claim 2)

[0905] The system according to claim 1, which includes sentiment analysis to optimize content based on past success stories and adjust the tone of the material.

[0906] (Claim 3)

[0907] The system according to claim 1, comprising a device that makes assignment requests to optimize the timing of follow-up based on the user's emotional information.

[0908] "Application example 2 when combining with an emotional engine"

[0909] (Claim 1)

[0910] A means of automatically collecting information related to bidding,

[0911] A means of analyzing the collected information and extracting requirements,

[0912] A means of determining whether a proposal is acceptable or not by referring to past bidding results,

[0913] A means of selecting appropriate products for projects that are deemed feasible to propose,

[0914] A means of automatically generating a quote based on the selected product,

[0915] A means of optimizing generated proposal materials based on the user's emotions using emotion recognition technology,

[0916] A means of displaying and adjusting proposal materials via a smart device,

[0917] A system that includes this.

[0918] (Claim 2)

[0919] The system according to claim 1, which includes means for optimizing the content of proposal documents based on data from past successful projects and for making them more persuasive using sentiment analysis.

[0920] (Claim 3)

[0921] The system according to claim 1, comprising means for automatically making a request for personnel allocation for proposal preparation at the optimal timing based on sentiment analysis. [Explanation of Symbols]

[0922] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of automatically collecting bidding information, A means of analyzing the collected bidding information and extracting the specification requirements, A means of determining whether a proposal is acceptable by referring to past bidding results, A means of selecting the most suitable product for projects deemed feasible, A means of automatically generating a quote based on the selected products, A means of automatically creating the generated proposal documents, An information processing system that includes this.

2. The information processing system according to claim 1, which includes means for optimizing the content of proposal documents based on data from past successful projects.

3. The information processing system according to claim 1, including means for automatically making assignment requests for proposal creation.

Images