system

Abstract

We provide the system. [Solution] A means of analyzing a received document using natural language processing technology and extracting important elements, A means to automatically generate optimal suggestions by referencing past relevant data based on the analyzed information, A means to create a plan based on the generated proposals and monitor progress in real time, Means of issuing notifications or warnings as needed, A means of providing an interface for uploading bidding specifications from a mobile device, A means of providing optimized proposals that show appropriate resource and time allocation based on specification analysis and past examples, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern bidding processes, it is a very time-consuming and laborious task to create a proposal that quickly and effectively responds to the specifications required by public institutions and corporate enterprises. In particular, when the proposal content is complex, it is generally difficult to quickly refer to past successful cases and effectively reflect their content. Also, in project management after winning an order, it is required to appropriately monitor the progress of the project and detect and address unexpected risks in advance. There is a need for a system that solves these problems and efficiently manages the entire process from bidding to project completion.

Means for Solving the Problems

[0005] This invention provides a means to rapidly analyze bid specifications after receiving them and extract key elements using natural language processing technology. Based on these analysis results, a system is built that automatically generates an optimal proposal by referring to past bid data. Furthermore, it includes a function to formulate a project management plan based on the generated proposal and monitor progress in real time. This allows users to receive timely reminders and warnings necessary for project execution and to make quick decisions. It also provides an interface that dynamically adjusts the proposal content in response to user feedback, enabling the creation of competitive proposals.

[0006] "Natural language processing technology" is a technology that enables computers to understand and analyze human language.

[0007] "Analysis" is the process of extracting important elements and patterns from complex documents and data to reveal their meaning.

[0008] "Key elements" are the most relevant and necessary information within a document or data for a specific purpose.

[0009] A "proposal" is a collection of plans and ideas presented to meet the requirements of a bid or project.

[0010] "Automated generation" refers to the process by which a system creates specific results or data without requiring human intervention.

[0011] Project management is the process of systematically directing, planning, and controlling the resources, time, and activities necessary to achieve a specific objective.

[0012] "Progress monitoring" is the act of checking and managing whether the current status of a project or task is progressing according to plan.

[0013] A "reminder" is a notification or alert set to encourage you to perform a task that you tend to forget.

[0014] A "warning" is a signal for alerting and prompting action regarding potential risks and problems.

[0015] An "interface" is a point of contact or means for information exchange between a user and a computer system.

Brief Description of Drawings

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

Mode for Carrying Out the Invention

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

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

[0019] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be one 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.

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

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

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

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

[0024] [First Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0037] Embodiments of the present invention will now be described. This system operates primarily through a server and a user's terminal.

[0038] First, the user submits the bid specification from their terminal to the server. Upon receiving the specification, the server immediately begins analysis using natural language processing technology. Specifically, the server extracts important keywords and requirements from the specification and stores them in a database as structured data. This converts the information within the document into a format that is easy for the system to handle.

[0039] Next, the server references similar past bidding data to generate a proposal best suited to the specifications. This process examines specific countermeasures and resource allocations for each requirement based on past successful proposals. The generated proposal is then sent to the user's terminal for review.

[0040] Users send feedback on the proposal to the server via their device, and the proposal is automatically revised based on that feedback. This process is repeated until the user is completely satisfied with the proposal.

[0041] In project management after receiving an order, the server automatically generates a Work Breakdown Structure (WBS) based on the proposal. This divides the project into easily understandable work units, allowing for appropriate allocation of resources and time. Subsequently, the server monitors the project's progress in real time, and if deviations from the plan occur, it sends reminders and warnings to the user's terminal. This allows the user to detect problems early and take appropriate measures.

[0042] For example, in a large-scale IT system implementation project, utilizing a WBS (Work Breakdown Structure) generated by the server and progress monitoring functions allows for timely understanding of the progress of each phase, enabling smooth project execution. In this way, the present invention streamlines the entire process from bidding to project management, contributing to improved competitiveness for users.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The server receives the bid specifications submitted by the user. The specifications are sent in digital format and stored securely on the server's storage.

[0046] Step 2:

[0047] The server analyzes the received specifications using natural language processing technology. Specifically, it extracts keywords and requirements from the document and converts them into structured data.

[0048] Step 3:

[0049] The server searches for similar projects in the past bidding database based on the analysis results of the specifications. It analyzes data from successful past proposals and picks out important elements.

[0050] Step 4:

[0051] The server automatically generates the optimal proposal that meets the requirements of the specification document, referencing historical data. The proposal will include specific countermeasures and cost estimates.

[0052] Step 5:

[0053] The server generates a proposal and sends it to the user's terminal. The user reviews the proposal details via their terminal and provides feedback as needed.

[0054] Step 6:

[0055] Based on user feedback, the server automatically adjusts the proposal. This process is repeated until the user is satisfied.

[0056] Step 7:

[0057] After receiving an order, the server automatically generates a Work Breakdown Structure (WBS) based on the proposal. Each work item of the project is clearly defined, and the necessary resources and time are allocated to them.

[0058] Step 8:

[0059] The server monitors project progress in real time. Progress data is updated periodically and kept as a buffer to notify users in case of unexpected events.

[0060] Step 9:

[0061] When a deviation from the project schedule is detected, the server sends reminders or warnings to the user's device. This allows the user to take the necessary action immediately.

[0062] (Example 1)

[0063] 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."

[0064] Current project management and bid proposal generation systems rely on manual or partially automated processes for extracting key elements from specifications, generating proposals based on historical data, refining proposals, and real-time monitoring of project progress. This leads to inefficiencies and a high likelihood of human error. A system is needed to perform these processes more efficiently and accurately.

[0065] 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.

[0066] This invention includes a server that receives specifications submitted from a user's terminal, analyzes the specifications using natural language processing technology, and extracts important elements; a generative AI model that automatically generates optimal proposals by referencing relevant historical data based on the analyzed information; a system that automatically creates a project work breakdown structure based on the generated proposals and formulates a plan; and a system that monitors progress in real time if it deviates from predictions and notifies the user of reminders or warnings as needed. This improves efficiency and accuracy throughout project management and enhances the user's competitiveness.

[0067] "User terminal" refers to the computing resources used by the user to submit specifications, review proposals, and input feedback.

[0068] "Natural language processing technology" refers to the technology of using computers to analyze natural language and extract useful information from language data.

[0069] "Key elements" refer to keywords and conditions within the specifications that are essential for project proposal and management.

[0070] A "generative AI model" refers to an artificial intelligence model that automatically generates optimal suggestions based on past data.

[0071] "Related past data" refers to information compiled from past bidding processes and project execution data.

[0072] "Optimal proposal content" refers to a plan generated to meet the requirements of the specifications and increase the chances of project success.

[0073] A "work breakdown structure" refers to a structure that clearly defines the specific work units of a project and shows the workflow and resource allocation.

[0074] "Monitoring progress in real time" means immediately understanding the current status of a project and continuously confirming that it is progressing according to plan.

[0075] "Reminders or warnings" refer to information that informs users of important matters in the progress of a project or to notify them of abnormal situations.

[0076] In implementing this invention, two main computing resources are used: a server and a user's terminal. The server begins processing upon receiving a specification document submitted from the user's terminal. The server utilizes natural language processing technology to analyze the specification document and extract important elements. The natural language processing technology used here is a generative AI model. This model includes, for example, natural language processing libraries such as SpaCy and NLTK, as well as more advanced models such as BERT and GPT-based models.

[0077] The extracted key elements are stored in a database as structured data. Next, the server uses this analysis result to refer to relevant past databases and utilizes a generative AI model to automatically generate optimal suggestions. The generated suggestions are sent to the user's terminal for review.

[0078] The terminal provides an interface where the user can review the proposal and enter feedback. This feedback is sent to the server and used to refine the proposal. This process is repeated until the user is satisfied.

[0079] Once the proposal is finalized, the server automatically creates a Work Breakdown Structure (WBS) for the project based on the generated proposal. This WBS defines specific work units and helps in the appropriate allocation of resources. The server monitors project progress in real time and supports early problem resolution by immediately sending reminders or warnings to the user's terminal if there are any deviations from the plan.

[0080] As a concrete example, in a large-scale IT system implementation project, a possible prompt used by the server might be, "Based on the requirements described in the specifications, refer to past success stories and generate the optimal proposal." This prompt allows the server to connect relevant historical data with different situations and provide the user with appropriate suggestions.

[0081] In this way, the present invention can streamline the process from bidding to project management, contributing to improved competitiveness for users.

[0082] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0083] Step 1:

[0084] The user's device uploads the bid specifications and submits them to the server. The input here is the specifications prepared by the user, in formats such as text files or PDFs. The output is a notification indicating that the file has been successfully sent to the server. Specifically, the device provides an interface that allows the user to select the desired file using a file selection function.

[0085] Step 2:

[0086] The server analyzes the received specification using natural language processing technology and extracts important elements. The input is the specification file received in step 1. The server uses a generative AI model (e.g., BERT, GPT) to extract keywords and requirements from the specification and organize them as structured data. The output is a database entry containing the extracted important elements.

[0087] Step 3:

[0088] The server references relevant historical data and automatically generates optimal proposals using a generative AI model. The input consists of the structured data generated in step 2 and historical project data. Here, the AI ​​model performs the analysis according to the prompt "Based on the requirements described in the specification, refer to past success stories and generate optimal proposals." The output is a document containing the generated proposals.

[0089] Step 4:

[0090] The server sends the generated proposal to the user's device and requests the user's review. The input is the proposal created in step 3. The output is the proposal displayed on the user's device. The device provides an interface that makes it easy for the user to review the content and includes a form for providing feedback.

[0091] Step 5:

[0092] Users send feedback on the proposed content to the server via their device. Input is user feedback, including comments and change requests. Output is the feedback data received by the server. The device provides a feedback submission button, allowing users to easily record their revisions.

[0093] Step 6:

[0094] The server adjusts the suggestions based on the feedback and updates them automatically. The input is the feedback received in step 5. The generating AI model analyzes the feedback and appropriately modifies the suggestions. The output is the new suggestions that reflect the feedback. This process is repeated until the user is satisfied with the suggestions.

[0095] Step 7:

[0096] The server automatically generates a Work Breakdown Structure (WBS) for the project based on the final proposal and constructs the project plan. The input is the proposal finalized in step 6. The server clarifies the hierarchical structure of tasks and efficiently allocates resources and schedules. The output is the completed WBS and project plan.

[0097] Step 8:

[0098] The server monitors project progress in real time and sends reminders or alerts to the user's terminal if there are deviations from the plan. The input is the current project progress information. The server analyzes the progress data using monitoring tools and detects anomalies. The output is support for quick action by sending necessary notifications to the user's terminal.

[0099] (Application Example 1)

[0100] 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."

[0101] The entire process of construction projects, from the bidding process to project management, presents challenges due to the significant time and effort required for manual document analysis, proposal creation, and progress monitoring. This can lead to project delays and wasted resources, thus creating a need for efficient and automated systems.

[0102] 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.

[0103] This invention includes a server that analyzes received documents using natural language processing technology and extracts key elements, a server that automatically generates optimal proposals by referencing relevant past data based on the analyzed information, and a server that provides an interface for uploading bidding specifications from a mobile device. This streamlines the process from bidding to management of construction projects, enabling optimal resource allocation and real-time monitoring of progress.

[0104] "Natural language processing technology" refers to technologies that enable computers to understand, analyze, and generate human language.

[0105] "Documents" refers to text data related to a project, such as bidding specifications.

[0106] "Key elements" are essential information and requirements for a project that are extracted through document analysis.

[0107] "Related past data" refers to information about records and results of similar projects that have been carried out in the past.

[0108] "Optimal proposal content" refers to information that presents the most effective solutions or plans for the project's requirements.

[0109] A "plan" is a schedule that outlines the specific steps and resource allocation required to carry out a project.

[0110] "Progress" is a measure that indicates whether project activities are proceeding according to plan.

[0111] A "notification or warning" is information issued when the project's progress deviates from the schedule.

[0112] "Mobile devices" refer to portable information processing devices such as smartphones and tablets.

[0113] An "interface" is the means or environment through which a user interacts with a system.

[0114] "Resources" refer to all available elements necessary for a project, including personnel, materials, and time.

[0115] The system for realizing this invention primarily operates using a server and a mobile terminal. The server uses natural language processing technology to analyze bid specifications uploaded by users and extract key elements. The software library spaCy is used to analyze the text data, and the extracted keywords are stored in a database as structured data.

[0116] The server also uses Pandas to manage historical bidding data and generates optimal proposals using a machine learning model with Scikit-learn. The generated proposals are sent to mobile devices, where users review them and provide feedback. This feedback is analyzed by TENSORFLOW® and used to refine the proposals.

[0117] Furthermore, the server uses NetworkX to create project management plans and has the capability to monitor progress in real time. If project progress deviates from the plan, it uses Twilio to send notifications or warnings to the user's mobile device. This notification feature allows the user to immediately understand the situation and take appropriate action.

[0118] As a concrete example, in the construction industry, when bidding takes place for a new bridge construction project, this system analyzes the bidding specifications and makes optimal proposals based on past successes. Furthermore, if delays occur in the foundation work as the project progresses, it immediately sends notifications to mobile devices to support early detection and countermeasures for the problem.

[0119] An example of a prompt is, "Analyze the bidding specifications for the new bridge construction project and generate the optimal proposal based on past success stories." This prompt provides the foundation for the server to perform appropriate analysis and make proposals.

[0120] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0121] Step 1:

[0122] Users upload bid specifications from their mobile devices. On the device, they select the bid specifications, and the data is transferred via a form submitted to the server. Input is text data, and output is confirmation of the successful upload to the server.

[0123] Step 2:

[0124] The server analyzes the received bid specifications using natural language processing techniques. It uses the spaCy library to analyze the text data and extract key elements. The input is the uploaded text data, and the output consists of extracted keywords and structured data.

[0125] Step 3:

[0126] The server automatically generates optimal suggestions using an AI model based on the extracted information and references relevant historical data. Relevant data is retrieved from a database managed with Pandas, and a machine learning model using Scikit-learn generates the suggestions. The input consists of structured data and historical data, and the output is the newly generated suggestions.

[0127] Step 4:

[0128] The server sends the generated proposal to the user's mobile device. The user reviews the proposal via their device. The input is the generated proposal, and the output is what is presented to the user.

[0129] Step 5:

[0130] Users provide feedback on the proposed content. This feedback is sent to the server via an interface on the device. The input is the user's feedback, and the output is the feedback data sent to the server.

[0131] Step 6:

[0132] The server adjusts the proposal based on the feedback received. It analyzes the feedback data using TensorFlow and reconstructs the proposal by applying a generative AI model. The input is the feedback data, and the output is the adjusted proposal.

[0133] Step 7:

[0134] The server creates a project management plan based on the adjusted proposal. NetworkX automatically generates a work breakdown diagram based on the hierarchical structure, preparing for project progress management. The input is the adjusted proposal, and the output is the project management plan.

[0135] Step 8:

[0136] The server monitors project progress in real time and, as needed, sends notifications or alerts to the user's mobile device using Twilio. The input is project progress data, and the output is notifications or alerts to the user.

[0137] 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.

[0138] Specific embodiments of the present invention will now be described. This system consists of a server, a terminal, and a user interface using an emotion engine.

[0139] First, the user sends the bid specifications to the server using their device. The server analyzes the contents of the received specifications using natural language processing technology and extracts important elements from them. Based on this analysis information, the server then proceeds to a process of referencing a database of past bids and generating the optimal proposal.

[0140] The generated suggestions are sent to the user's device for review. This is where the emotion engine comes into play. When the user provides emotion-based feedback, the device analyzes emotion data from the user's input data and the content of the conversation. The server retrieves this emotion information and further adjusts the suggestions, taking the user's emotional state into consideration. For example, if the user feels uneasy about the suggestions, the server may add more detailed information or specify risk mitigation measures.

[0141] The emotion engine is also utilized in the project management phase. The server collects user feedback during the project, analyzes the emotion data, and incorporates it into the project management plan. For example, if a user's stress level is high, the project schedule is re-evaluated and optimized to reduce the burden.

[0142] As a concrete example, suppose an initial proposal for a project is presented to a user, and the user expresses dissatisfaction through the system. In this case, the server automatically adds more specific proposal details and supplementary materials to the proposal based on information from the emotion engine, and then re-presents it to the user's terminal. In this way, integrating an emotion engine makes it possible to increase user satisfaction and improve the quality of proposals.

[0143] This invention utilizes emotional data throughout the entire process, from bidding to project management, to enhance user decision-making support. This system enables flexible and effective process management that takes user emotions into account.

[0144] The following describes the processing flow.

[0145] Step 1:

[0146] The user sends the bid specifications from their terminal to the server. The terminal prepares the specifications in digital format and transfers the data to the server via secure communication.

[0147] Step 2:

[0148] The server analyzes the received specifications using a natural language processing engine and extracts key elements. These key elements include technical requirements, budget constraints, and deadlines. This information is recorded in the database as structured data.

[0149] Step 3:

[0150] Based on the analysis results, the server references a database of past bids and automatically generates the optimal proposal content corresponding to the specifications. The proposal content learns patterns from past successful cases and is provided to the user as a rational plan.

[0151] Step 4:

[0152] The server generates a proposal and sends it to the user's terminal. The user reviews it and evaluates the proposal to suit their needs.

[0153] Step 5:

[0154] The emotion engine receives user feedback and analyzes the emotions contained within it. The device generates emotion data from the ratings and comments entered by the user and sends it to the server.

[0155] Step 6:

[0156] The server utilizes the emotion engine's analysis results to revise or adjust the proposal's content. Additional information or changes are added to the proposal based on the issues indicated by the user's emotions.

[0157] Step 7:

[0158] After receiving an order, the server creates a Work Breakdown Structure (WBS) based on the proposal and monitors its progress in real time. The emotion engine analyzes user feedback and emotions throughout the project to help adjust the plan.

[0159] Step 8:

[0160] The server monitors project progress and sends reminders and alerts to users. In particular, it takes into account user sentiment analysis results to provide appropriate notifications at the right time.

[0161] The above describes the processing flow of this system incorporating an emotion engine.

[0162] (Example 2)

[0163] 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".

[0164] Traditional systems fail to consider user emotions in generating proposals and managing projects, resulting in decreased user satisfaction and project efficiency. In particular, the inability to adequately incorporate user feedback leads to rigid proposals and a lack of flexibility in project progress.

[0165] 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.

[0166] In this invention, the server includes means for analyzing received documents and extracting important elements using natural language processing technology, means for automatically generating optimal suggestions by referring to relevant past data based on the analyzed information, and means for adjusting the suggestions based on the generated suggestions by analyzing emotional data and providing information that takes into account the user's emotional state. This enables dynamic adjustment of suggestions according to the user's emotional state and optimization of project management.

[0167] "Natural language processing technology" is a technique that enables computers to understand and analyze human language, and is a means of structuring information within documents and extracting important elements.

[0168] "Key elements" are valuable pieces of information or keywords that should be extracted from the data within a document as a result of analysis, and are useful for generating proposals.

[0169] "Proposed content" refers to information including recommendations and plans generated by the server based on the analyzed information and relevant historical data.

[0170] "Emotional data" refers to data that indicates the emotional state and reactions extracted from user feedback, and is used by the system to make adjustments that take the user's emotions into account.

[0171] Project management is a set of tasks that involve planning, executing, monitoring, and controlling activities to achieve specific goals, including managing and coordinating progress.

[0172] This invention relates to a system comprising a server, a terminal, and a user interface that utilizes sentiment data. The user sends a bid specification from the terminal to the server. The server analyzes the received specification using natural language processing technology and extracts key elements. This process typically employs a "natural language processing tool." Based on the analysis results, the server references relevant historical data and automatically generates the optimal proposal. "Data management software" is likely to be used for database management.

[0173] The proposal is sent to the user's device, where the user reviews it. When the user provides feedback on the proposal, the emotion engine is utilized. The device analyzes the user's feedback and generates emotion data. An "emotion analysis tool" is used to analyze this emotion data and understand the user's emotional state.

[0174] The server acquires sentiment data and further adjusts the suggestions based on the user's emotions. For example, if the user feels anxious, the server may add more detailed information to the suggestion or suggest risk mitigation measures. A possible example of a specific prompt might be, "If the user has expressed dissatisfaction with the suggestion, please advise on how to improve the suggestion considering their emotions."

[0175] Through this system, users can provide emotion-based, interactive feedback, which contributes to the refinement of proposals. This is expected to improve user satisfaction and increase the efficiency of project management.

[0176] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0177] Step 1:

[0178] User: Use the terminal to create the bid specifications and send them to the server.

[0179] Input: Bidding specifications (text data) created by the user on their device.

[0180] Output: Specification data sent to the server.

[0181] Specific operation: When the user enters the specifications on their device and clicks the "Submit" button, the specifications are uploaded to the server.

[0182] Step 2:

[0183] Server: Analyzes the received specifications using natural language processing technology.

[0184] Input: Specification data received by the server.

[0185] Data processing: Use natural language processing tools to perform syntactic analysis and extract key phrases from documents.

[0186] Output: A list of the extracted key elements.

[0187] Specific operation: The analysis engine on the server starts up, analyzes the text of the specification document, and identifies important keywords and phrases.

[0188] Step 3:

[0189] Server: Based on the extracted elements, it references relevant past data to generate the most suitable suggestions.

[0190] Input: A list of the key elements extracted.

[0191] Data Calculation: Refer to historical bidding data through database queries and select recommendations from similar cases.

[0192] Output: The generated suggestions.

[0193] Specific operation: The server retrieves relevant information from the database and combines it to generate the optimal suggestions.

[0194] Step 4:

[0195] Server: Sends the generated suggestions to the user's terminal.

[0196] Input: The generated suggestions.

[0197] Output: The proposed content delivered to the user's device.

[0198] Specific operation: The server sends the suggestion to the user via the network, and a notification is displayed on the user's device screen.

[0199] Step 5:

[0200] User: Review the proposal and provide feedback.

[0201] Input: The submitted proposal.

[0202] Output: User sentiment feedback (text or selection format).

[0203] Specific actions: The user reads the proposal, selects buttons to express anxiety or reassurance, or enters comments.

[0204] Step 6:

[0205] Terminal: Analyzes feedback using an emotion engine.

[0206] Input: User emotional feedback.

[0207] Data processing: Using emotion analysis tools, quantify or classify the user's emotional state from feedback.

[0208] Output: Sentiment data.

[0209] Specific operation: The sentiment analysis engine analyzes the text or selection data of the feedback and generates a sentiment score.

[0210] Step 7:

[0211] Server: Adjusts suggestions based on sentiment data.

[0212] Input: Sentiment data and initial proposal content.

[0213] Data processing: Data processing is performed to add additional information and detailed explanations to the proposal, taking into account emotional states.

[0214] Output: Revised proposal.

[0215] Specific actions: Referencing sentiment data to supplement unclear points in the proposal and add information that will reassure the user.

[0216] Step 8:

[0217] Server: Analyzes emotional feedback during project progress and optimizes the plan.

[0218] Input: Project progress information and sentiment data.

[0219] Data processing: Compare progress and sentiment scores to re-evaluate schedules and tasks.

[0220] Output: Adjusted project plan.

[0221] Specific action: A schedule optimization algorithm is activated, adjusting the project in response to increasing stress levels.

[0222] (Application Example 2)

[0223] 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".

[0224] In the past, on-site work management of machinery has often relied on experience and intuition, leading to challenges in improving worker satisfaction, safety, and work efficiency. Furthermore, insufficient adjustments to work processes that take into account workers' emotional states have resulted in a tendency for stress and fatigue to accumulate.

[0225] 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.

[0226] In this invention, the server includes means for analyzing received documents and extracting important elements using natural language processing technology, means for automatically generating optimal suggestions by referring to relevant past data based on the analyzed information, and means for obtaining emotion-based feedback from workers and adjusting work plans according to the emotion information. This makes it possible to improve the efficiency of work planning and enhance worker satisfaction and safety on site.

[0227] "Natural language processing technology" is a technology that enables computers to understand and analyze human language.

[0228] "Document analysis" means deciphering the content of a received document and understanding its meaning and structure.

[0229] "Extracting key elements" means extracting information that is considered particularly important from an analyzed document.

[0230] "Referring to related data" means searching past databases to find similar information.

[0231] "Automatically generating proposals" means that a computer creates the optimal actions and plans based on the analysis results.

[0232] "Obtaining emotion-based feedback from workers" means collecting information about the emotional state of the workers.

[0233] "Adjusting work plans based on emotional information" means re-evaluating work schedules and workloads by considering workers' emotional data.

[0234] "Efficiency improvement" means reviewing work processes, reducing waste, and increasing effectiveness.

[0235] "Enhancing safety" means reducing accidents and risks, and ensuring that work is carried out safely.

[0236] "Satisfaction level" refers to the degree of satisfaction that users feel with a service or product.

[0237] In realizing this invention, the server handles the main processing. First, the server analyzes the document sent from the user's terminal using natural language processing technology and extracts important elements. The analyzed information is compared with past data stored on the server, and optimal suggestions are automatically generated based on the content. The user receives the generated suggestions using a terminal such as a smartphone or smart glasses and provides feedback based on their own feelings.

[0238] For obtaining emotional feedback, an emotion analysis engine called EmotionAnalyzer is used to analyze the user's emotional state from their feedback. The emotional data is sent to a server, and a task optimization engine known as TaskOptimizer dynamically adjusts the work schedules of workers and machines based on the emotional information. This process leads to improved work efficiency and safety, and ultimately, increased user satisfaction.

[0239] As a concrete example, suppose one task in a factory's manufacturing process places a greater burden on the team than others. When a leader wearing smart glasses perceives this burden, the server generates new suggestions for distributing the workload based on their feedback and notifies the team on-site.

[0240] By utilizing a generative AI model, prompts can be presented to the user as follows: "Based on the feedback received through the smart glasses, please tell me how to safely adjust the work speed of the factory robot."

[0241] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0242] Step 1:

[0243] The server analyzes documents received from the user's terminal using natural language processing techniques. The input documents contain user requests and specifications. Based on this input, the server extracts important elements. The output is a list of the elements extracted from the document.

[0244] Step 2:

[0245] The server uses the elements obtained in Step 1 to refer to the historical database and search for relevant data. This process uses a similarity matching algorithm to search for data. The input is a list of extracted elements, and the output generates relevant suggestions.

[0246] Step 3:

[0247] The generated suggestions are sent to the user's device. On the device, the user reviews the suggestions provided via their smartphone or smart glasses. Based on the suggestions, the user provides feedback that reflects their own feelings.

[0248] Step 4:

[0249] The device uses EmotionAnalyzer to analyze user feedback based on emotions. The analyzed emotional data is extracted from the user's feedback. The input is emotional feedback, and the output is data on the emotional state.

[0250] Step 5:

[0251] The server receives the sentiment data acquired in step 4 and adjusts the work schedule using TaskOptimizer. In this process, the sentiment data and the current work schedule are used as input to optimize the work content and speed. The adjusted work schedule is obtained as output.

[0252] Step 6:

[0253] The revised work plan is sent back to the user's terminal for review. This allows the user to visually understand the newly proposed work and update their feedback as needed. The input is the new work plan.

[0254] 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.

[0255] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), 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.

[0256] 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.

[0257] [Second Embodiment]

[0258] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0259] 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.

[0260] 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).

[0261] 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.

[0262] 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.

[0263] 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).

[0264] 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.

[0265] 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.

[0266] 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.

[0267] 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.

[0268] 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.

[0269] 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".

[0270] Embodiments of the present invention will now be described. This system operates primarily through a server and a user's terminal.

[0271] First, the user submits the bid specification from their terminal to the server. Upon receiving the specification, the server immediately begins analysis using natural language processing technology. Specifically, the server extracts important keywords and requirements from the specification and stores them in a database as structured data. This converts the information within the document into a format that is easy for the system to handle.

[0272] Next, the server references similar past bidding data to generate a proposal best suited to the specifications. This process examines specific countermeasures and resource allocations for each requirement based on past successful proposals. The generated proposal is then sent to the user's terminal for review.

[0273] Users send feedback on the proposal to the server via their device, and the proposal is automatically revised based on that feedback. This process is repeated until the user is completely satisfied with the proposal.

[0274] In project management after receiving an order, the server automatically generates a Work Breakdown Structure (WBS) based on the proposal. This divides the project into easily understandable work units, allowing for appropriate allocation of resources and time. Subsequently, the server monitors the project's progress in real time, and if deviations from the plan occur, it sends reminders and warnings to the user's terminal. This allows the user to detect problems early and take appropriate measures.

[0275] For example, in a large-scale IT system implementation project, utilizing a WBS (Work Breakdown Structure) generated by the server and progress monitoring functions allows for timely understanding of the progress of each phase, enabling smooth project execution. In this way, the present invention streamlines the entire process from bidding to project management, contributing to improved competitiveness for users.

[0276] The following describes the processing flow.

[0277] Step 1:

[0278] The server receives the bid specifications submitted by the user. The specifications are sent in digital format and stored securely on the server's storage.

[0279] Step 2:

[0280] The server analyzes the received specification document using natural language processing technology. Specifically, it extracts keywords and requirements from the document and converts them into structured data.

[0281] Step 3:

[0282] Based on the analysis result of the specification document, the server searches for similar cases from the past bidding database. It analyzes the data of successful past proposals and picks up important elements.

[0283] Step 4:

[0284] While referring to past data, the server automatically generates an optimal proposal that meets the requirements of the specification document. Make sure the proposal includes specific countermeasures and estimates.

[0285] Step 5:

[0286] The server sends the generated proposal to the user's terminal. The user checks the details of the proposal via the terminal and provides feedback if necessary.

[0287] Step 6:

[0288] The server automatically adjusts the proposal according to the user's feedback. This process is repeated until the user is satisfied.

[0289] Step 7:

[0290] After receiving the order, the server automatically generates a WBS (Work Breakdown Structure) based on the proposal. Each work item of the project is specified, and the necessary resources and time allocation are made.

[0291] Step 8:

[0292] The server monitors project progress in real time. Progress data is updated periodically and kept as a buffer to notify users in case of unexpected events.

[0293] Step 9:

[0294] When a deviation from the project schedule is detected, the server sends reminders or warnings to the user's device. This allows the user to take the necessary action immediately.

[0295] (Example 1)

[0296] 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."

[0297] Current project management and bid proposal generation systems rely on manual or partially automated processes for extracting key elements from specifications, generating proposals based on historical data, refining proposals, and real-time monitoring of project progress. This leads to inefficiencies and a high likelihood of human error. A system is needed to perform these processes more efficiently and accurately.

[0298] 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.

[0299] This invention includes a server that receives specifications submitted from a user's terminal, analyzes the specifications using natural language processing technology, and extracts important elements; a generative AI model that automatically generates optimal proposals by referencing relevant historical data based on the analyzed information; a system that automatically creates a project work breakdown structure based on the generated proposals and formulates a plan; and a system that monitors progress in real time if it deviates from predictions and notifies the user of reminders or warnings as needed. This improves efficiency and accuracy throughout project management and enhances the user's competitiveness.

[0300] "User terminal" refers to the computing resources used by the user to submit specifications, review proposals, and input feedback.

[0301] "Natural language processing technology" refers to the technology of using computers to analyze natural language and extract useful information from language data.

[0302] "Key elements" refer to keywords and conditions within the specifications that are essential for project proposal and management.

[0303] A "generative AI model" refers to an artificial intelligence model that automatically generates optimal suggestions based on past data.

[0304] "Related past data" refers to information compiled from past bidding processes and project execution data.

[0305] "Optimal proposal content" refers to a plan generated to meet the requirements of the specifications and increase the chances of project success.

[0306] A "work breakdown structure" refers to a structure that clearly defines the specific work units of a project and shows the workflow and resource allocation.

[0307] "Monitoring progress in real time" means immediately grasping the current situation of the project and continuously checking the progress as planned.

[0308] "Reminder or warning" refers to information that notifies the user to reconfirm important matters and abnormal situations during the progress of the project.

[0309] As an embodiment of this invention, two major computing resources, namely a server and a user's terminal, are used. The server starts processing by receiving the specification submitted from the user's terminal. The server utilizes natural language processing technology to analyze the specification and extract important elements. The natural language processing technology used here applies a generative AI model. This model includes, for example, natural language processing libraries such as SpaCy and NLTK, as well as more advanced models such as BERT and GPT series.

[0310] The extracted important elements are stored in the database as structured data. Next, the server refers to the past related database based on this analysis result and utilizes the generative AI model to automatically generate the optimal proposed content. The generated proposed content is sent to the user's terminal for the user to review.

[0311] The terminal provides an interface for the user to view the proposed content and input feedback. This feedback is sent to the server and used to adjust the proposed content. This process is repeated until the user is satisfied.

[0312] After the proposal is finalized, the server automatically creates a work breakdown structure (WBS) of the project based on the generated proposed content. This WBS defines specific work units and helps in the appropriate allocation of resources. The server monitors the progress of the project in real time and supports early problem-solving by immediately sending a reminder or warning to the user's terminal if there is a deviation from the plan.

[0313] As a concrete example, in a large-scale IT system implementation project, a possible prompt used by the server might be, "Based on the requirements described in the specifications, refer to past success stories and generate the optimal proposal." This prompt allows the server to connect relevant historical data with different situations and provide the user with appropriate suggestions.

[0314] In this way, the present invention can streamline the process from bidding to project management, contributing to improved competitiveness for users.

[0315] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0316] Step 1:

[0317] The user's device uploads the bid specifications and submits them to the server. The input here is the specifications prepared by the user, in formats such as text files or PDFs. The output is a notification indicating that the file has been successfully sent to the server. Specifically, the device provides an interface that allows the user to select the desired file using a file selection function.

[0318] Step 2:

[0319] The server analyzes the received specification using natural language processing technology and extracts important elements. The input is the specification file received in step 1. The server uses a generative AI model (e.g., BERT, GPT) to extract keywords and requirements from the specification and organize them as structured data. The output is a database entry containing the extracted important elements.

[0320] Step 3:

[0321] The server references relevant historical data and automatically generates optimal proposals using a generative AI model. The input consists of the structured data generated in step 2 and historical project data. Here, the AI ​​model performs the analysis according to the prompt "Based on the requirements described in the specification, refer to past success stories and generate optimal proposals." The output is a document containing the generated proposals.

[0322] Step 4:

[0323] The server sends the generated proposal to the user's device and requests the user's review. The input is the proposal created in step 3. The output is the proposal displayed on the user's device. The device provides an interface that makes it easy for the user to review the content and includes a form for providing feedback.

[0324] Step 5:

[0325] Users send feedback on the proposed content to the server via their device. Input is user feedback, including comments and change requests. Output is the feedback data received by the server. The device provides a feedback submission button, allowing users to easily record their revisions.

[0326] Step 6:

[0327] The server adjusts the suggestions based on the feedback and updates them automatically. The input is the feedback received in step 5. The generating AI model analyzes the feedback and appropriately modifies the suggestions. The output is the new suggestions that reflect the feedback. This process is repeated until the user is satisfied with the suggestions.

[0328] Step 7:

[0329] The server automatically generates a Work Breakdown Structure (WBS) for the project based on the final proposal and constructs the project plan. The input is the proposal finalized in step 6. The server clarifies the hierarchical structure of tasks and efficiently allocates resources and schedules. The output is the completed WBS and project plan.

[0330] Step 8:

[0331] The server monitors project progress in real time and sends reminders or alerts to the user's terminal if there are deviations from the plan. The input is the current project progress information. The server analyzes the progress data using monitoring tools and detects anomalies. The output is support for quick action by sending necessary notifications to the user's terminal.

[0332] (Application Example 1)

[0333] 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."

[0334] The entire process of construction projects, from the bidding process to project management, presents challenges due to the significant time and effort required for manual document analysis, proposal creation, and progress monitoring. This can lead to project delays and wasted resources, thus creating a need for efficient and automated systems.

[0335] 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.

[0336] This invention includes a server that analyzes received documents using natural language processing technology and extracts key elements, a server that automatically generates optimal proposals by referencing relevant past data based on the analyzed information, and a server that provides an interface for uploading bidding specifications from a mobile device. This streamlines the process from bidding to management of construction projects, enabling optimal resource allocation and real-time monitoring of progress.

[0337] "Natural language processing technology" refers to technologies that enable computers to understand, analyze, and generate human language.

[0338] "Documents" refers to text data related to a project, such as bidding specifications.

[0339] "Key elements" are essential information and requirements for a project that are extracted through document analysis.

[0340] "Related past data" refers to information about records and results of similar projects that have been carried out in the past.

[0341] "Optimal proposal content" refers to information that presents the most effective solutions or plans for the project's requirements.

[0342] A "plan" is a schedule that outlines the specific steps and resource allocation required to carry out a project.

[0343] "Progress" is a measure that indicates whether project activities are proceeding according to plan.

[0344] A "notification or warning" is information issued when the project's progress deviates from the schedule.

[0345] "Mobile devices" refer to portable information processing devices such as smartphones and tablets.

[0346] An "interface" is the means or environment through which a user interacts with a system.

[0347] "Resources" refer to all available elements necessary for a project, including personnel, materials, and time.

[0348] The system for realizing this invention primarily operates using a server and a mobile terminal. The server uses natural language processing technology to analyze bid specifications uploaded by users and extract key elements. The software library spaCy is used to analyze the text data, and the extracted keywords are stored in a database as structured data.

[0349] The server also uses Pandas to manage historical bidding data and generates optimal proposals using a machine learning model with Scikit-learn. The generated proposals are sent to mobile devices, where users review them and provide feedback. This feedback is analyzed by TensorFlow and used to refine the proposals.

[0350] Furthermore, the server uses NetworkX to create project management plans and has the capability to monitor progress in real time. If project progress deviates from the plan, it uses Twilio to send notifications or warnings to the user's mobile device. This notification feature allows the user to immediately understand the situation and take appropriate action.

[0351] As a concrete example, in the construction industry, when bidding takes place for a new bridge construction project, this system analyzes the bidding specifications and makes optimal proposals based on past successes. Furthermore, if delays occur in the foundation work as the project progresses, it immediately sends notifications to mobile devices to support early detection and countermeasures for the problem.

[0352] An example of a prompt is, "Analyze the bidding specifications for the new bridge construction project and generate the optimal proposal based on past success stories." This prompt provides the foundation for the server to perform appropriate analysis and make proposals.

[0353] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0354] Step 1:

[0355] Users upload bid specifications from their mobile devices. On the device, they select the bid specifications, and the data is transferred via a form submitted to the server. Input is text data, and output is confirmation of the successful upload to the server.

[0356] Step 2:

[0357] The server analyzes the received bid specifications using natural language processing techniques. It uses the spaCy library to analyze the text data and extract key elements. The input is the uploaded text data, and the output consists of extracted keywords and structured data.

[0358] Step 3:

[0359] The server automatically generates optimal suggestions using an AI model based on the extracted information and references relevant historical data. Relevant data is retrieved from a database managed with Pandas, and a machine learning model using Scikit-learn generates the suggestions. The input consists of structured data and historical data, and the output is the newly generated suggestions.

[0360] Step 4:

[0361] The server sends the generated proposal to the user's mobile device. The user reviews the proposal via their device. The input is the generated proposal, and the output is what is presented to the user.

[0362] Step 5:

[0363] Users provide feedback on the proposed content. This feedback is sent to the server via an interface on the device. The input is the user's feedback, and the output is the feedback data sent to the server.

[0364] Step 6:

[0365] The server adjusts the proposal based on the feedback received. It analyzes the feedback data using TensorFlow and reconstructs the proposal by applying a generative AI model. The input is the feedback data, and the output is the adjusted proposal.

[0366] Step 7:

[0367] The server creates a project management plan based on the adjusted proposal. NetworkX automatically generates a work breakdown diagram based on the hierarchical structure, preparing for project progress management. The input is the adjusted proposal, and the output is the project management plan.

[0368] Step 8:

[0369] The server monitors project progress in real time and, as needed, sends notifications or alerts to the user's mobile device using Twilio. The input is project progress data, and the output is notifications or alerts to the user.

[0370] 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.

[0371] Specific embodiments of the present invention will now be described. This system consists of a server, a terminal, and a user interface using an emotion engine.

[0372] First, the user sends the bid specifications to the server using their device. The server analyzes the contents of the received specifications using natural language processing technology and extracts important elements from them. Based on this analysis information, the server then proceeds to a process of referencing a database of past bids and generating the optimal proposal.

[0373] The generated suggestions are sent to the user's device for review. This is where the emotion engine comes into play. When the user provides emotion-based feedback, the device analyzes emotion data from the user's input data and the content of the conversation. The server retrieves this emotion information and further adjusts the suggestions, taking the user's emotional state into consideration. For example, if the user feels uneasy about the suggestions, the server may add more detailed information or specify risk mitigation measures.

[0374] The emotion engine is also utilized in the project management phase. The server collects user feedback during the project, analyzes the emotion data, and incorporates it into the project management plan. For example, if a user's stress level is high, the project schedule is re-evaluated and optimized to reduce the burden.

[0375] As a concrete example, suppose an initial proposal for a project is presented to a user, and the user expresses dissatisfaction through the system. In this case, the server automatically adds more specific proposal details and supplementary materials to the proposal based on information from the emotion engine, and then re-presents it to the user's terminal. In this way, integrating an emotion engine makes it possible to increase user satisfaction and improve the quality of proposals.

[0376] This invention utilizes emotional data throughout the entire process, from bidding to project management, to enhance user decision-making support. This system enables flexible and effective process management that takes user emotions into account.

[0377] The following describes the processing flow.

[0378] Step 1:

[0379] The user sends the bid specifications from their terminal to the server. The terminal prepares the specifications in digital format and transfers the data to the server via secure communication.

[0380] Step 2:

[0381] The server analyzes the received specifications using a natural language processing engine and extracts key elements. These key elements include technical requirements, budget constraints, and deadlines. This information is recorded in the database as structured data.

[0382] Step 3:

[0383] Based on the analysis results, the server references a database of past bids and automatically generates the optimal proposal content corresponding to the specifications. The proposal content learns patterns from past successful cases and is provided to the user as a rational plan.

[0384] Step 4:

[0385] The server generates a proposal and sends it to the user's terminal. The user reviews it and evaluates the proposal to suit their needs.

[0386] Step 5:

[0387] The emotion engine receives user feedback and analyzes the emotions contained within it. The device generates emotion data from the ratings and comments entered by the user and sends it to the server.

[0388] Step 6:

[0389] The server utilizes the emotion engine's analysis results to revise or adjust the proposal's content. Additional information or changes are added to the proposal based on the issues indicated by the user's emotions.

[0390] Step 7:

[0391] After receiving an order, the server creates a Work Breakdown Structure (WBS) based on the proposal and monitors its progress in real time. The emotion engine analyzes user feedback and emotions throughout the project to help adjust the plan.

[0392] Step 8:

[0393] The server monitors project progress and sends reminders and alerts to users. In particular, it takes into account user sentiment analysis results to provide appropriate notifications at the right time.

[0394] The above describes the processing flow of this system incorporating an emotion engine.

[0395] (Example 2)

[0396] 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".

[0397] Traditional systems fail to consider user emotions in generating proposals and managing projects, resulting in decreased user satisfaction and project efficiency. In particular, the inability to adequately incorporate user feedback leads to rigid proposals and a lack of flexibility in project progress.

[0398] 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.

[0399] In this invention, the server includes means for analyzing received documents and extracting important elements using natural language processing technology, means for automatically generating optimal suggestions by referring to relevant past data based on the analyzed information, and means for adjusting the suggestions based on the generated suggestions by analyzing emotional data and providing information that takes into account the user's emotional state. This enables dynamic adjustment of suggestions according to the user's emotional state and optimization of project management.

[0400] "Natural language processing technology" is a technique that enables computers to understand and analyze human language, and is a means of structuring information within documents and extracting important elements.

[0401] "Key elements" are valuable pieces of information or keywords that should be extracted from the data within a document as a result of analysis, and are useful for generating proposals.

[0402] "Proposed content" refers to information including recommendations and plans generated by the server based on the analyzed information and relevant historical data.

[0403] "Emotional data" refers to data that indicates the emotional state and reactions extracted from user feedback, and is used by the system to make adjustments that take the user's emotions into account.

[0404] Project management is a set of tasks that involve planning, executing, monitoring, and controlling activities to achieve specific goals, including managing and coordinating progress.

[0405] This invention relates to a system comprising a server, a terminal, and a user interface that utilizes sentiment data. The user sends a bid specification from the terminal to the server. The server analyzes the received specification using natural language processing technology and extracts key elements. This process typically employs a "natural language processing tool." Based on the analysis results, the server references relevant historical data and automatically generates the optimal proposal. "Data management software" is likely to be used for database management.

[0406] The proposal is sent to the user's device, where the user reviews it. When the user provides feedback on the proposal, the emotion engine is utilized. The device analyzes the user's feedback and generates emotion data. An "emotion analysis tool" is used to analyze this emotion data and understand the user's emotional state.

[0407] The server acquires sentiment data and further adjusts the suggestions based on the user's emotions. For example, if the user feels anxious, the server may add more detailed information to the suggestion or suggest risk mitigation measures. A possible example of a specific prompt might be, "If the user has expressed dissatisfaction with the suggestion, please advise on how to improve the suggestion considering their emotions."

[0408] Through this system, users can provide emotion-based, interactive feedback, which contributes to the refinement of proposals. This is expected to improve user satisfaction and increase the efficiency of project management.

[0409] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0410] Step 1:

[0411] User: Use the terminal to create the bid specifications and send them to the server.

[0412] Input: Bidding specifications (text data) created by the user on their device.

[0413] Output: Specification data sent to the server.

[0414] Specific operation: When the user enters the specifications on their device and clicks the "Submit" button, the specifications are uploaded to the server.

[0415] Step 2:

[0416] Server: Analyzes the received specifications using natural language processing technology.

[0417] Input: Specification data received by the server.

[0418] Data processing: Use natural language processing tools to perform syntactic analysis and extract key phrases from documents.

[0419] Output: A list of the extracted key elements.

[0420] Specific operation: The analysis engine on the server starts up, analyzes the text of the specification document, and identifies important keywords and phrases.

[0421] Step 3:

[0422] Server: Based on the extracted elements, it references relevant past data to generate the most suitable suggestions.

[0423] Input: A list of the key elements extracted.

[0424] Data Calculation: Refer to historical bidding data through database queries and select recommendations from similar cases.

[0425] Output: The generated suggestions.

[0426] Specific operation: The server retrieves relevant information from the database and combines it to generate the optimal suggestions.

[0427] Step 4:

[0428] Server: Sends the generated suggestions to the user's terminal.

[0429] Input: The generated suggestions.

[0430] Output: The proposed content delivered to the user's device.

[0431] Specific operation: The server sends the suggestion to the user via the network, and a notification is displayed on the user's device screen.

[0432] Step 5:

[0433] User: Review the proposal and provide feedback.

[0434] Input: The submitted proposal.

[0435] Output: User sentiment feedback (text or selection format).

[0436] Specific actions: The user reads the proposal, selects buttons to express anxiety or reassurance, or enters comments.

[0437] Step 6:

[0438] Terminal: Analyzes feedback using an emotion engine.

[0439] Input: User emotional feedback.

[0440] Data processing: Using emotion analysis tools, quantify or classify the user's emotional state from feedback.

[0441] Output: Sentiment data.

[0442] Specific operation: The sentiment analysis engine analyzes the text or selection data of the feedback and generates a sentiment score.

[0443] Step 7:

[0444] Server: Adjusts suggestions based on sentiment data.

[0445] Input: Sentiment data and initial proposal content.

[0446] Data processing: Data processing is performed to add additional information and detailed explanations to the proposal, taking into account emotional states.

[0447] Output: Revised proposal.

[0448] Specific actions: Referencing sentiment data to supplement unclear points in the proposal and add information that will reassure the user.

[0449] Step 8:

[0450] Server: Analyzes emotional feedback during project progress and optimizes the plan.

[0451] Input: Project progress information and sentiment data.

[0452] Data processing: Compare progress and sentiment scores to re-evaluate schedules and tasks.

[0453] Output: Adjusted project plan.

[0454] Specific action: A schedule optimization algorithm is activated, adjusting the project in response to increasing stress levels.

[0455] (Application Example 2)

[0456] 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."

[0457] In the past, on-site work management of machinery has often relied on experience and intuition, leading to challenges in improving worker satisfaction, safety, and work efficiency. Furthermore, insufficient adjustments to work processes that take into account workers' emotional states have resulted in a tendency for stress and fatigue to accumulate.

[0458] 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.

[0459] In this invention, the server includes means for analyzing received documents and extracting important elements using natural language processing technology, means for automatically generating optimal suggestions by referring to relevant past data based on the analyzed information, and means for obtaining emotion-based feedback from workers and adjusting work plans according to the emotion information. This makes it possible to improve the efficiency of work planning and enhance worker satisfaction and safety on site.

[0460] "Natural language processing technology" is a technology that enables computers to understand and analyze human language.

[0461] "Document analysis" means deciphering the content of a received document and understanding its meaning and structure.

[0462] "Extracting key elements" means extracting information that is considered particularly important from an analyzed document.

[0463] "Referring to related data" means searching past databases to find similar information.

[0464] "Automatically generating proposals" means that a computer creates the optimal actions and plans based on the analysis results.

[0465] "Obtaining emotion-based feedback from workers" means collecting information about the emotional state of the workers.

[0466] "Adjusting work plans based on emotional information" means re-evaluating work schedules and workloads by considering workers' emotional data.

[0467] "Efficiency improvement" means reviewing work processes, reducing waste, and increasing effectiveness.

[0468] "Enhancing safety" means reducing accidents and risks, and ensuring that work is carried out safely.

[0469] "Satisfaction level" refers to the degree of satisfaction that users feel with a service or product.

[0470] In realizing this invention, the server handles the main processing. First, the server analyzes the document sent from the user's terminal using natural language processing technology and extracts important elements. The analyzed information is compared with past data stored on the server, and optimal suggestions are automatically generated based on the content. The user receives the generated suggestions using a terminal such as a smartphone or smart glasses and provides feedback based on their own feelings.

[0471] For obtaining emotional feedback, an emotion analysis engine called EmotionAnalyzer is used to analyze the user's emotional state from their feedback. The emotional data is sent to a server, and a task optimization engine known as TaskOptimizer dynamically adjusts the work schedules of workers and machines based on the emotional information. This process leads to improved work efficiency and safety, and ultimately, increased user satisfaction.

[0472] As a concrete example, suppose one task in a factory's manufacturing process places a greater burden on the team than others. When a leader wearing smart glasses perceives this burden, the server generates new suggestions for distributing the workload based on their feedback and notifies the team on-site.

[0473] By utilizing a generative AI model, prompts can be presented to the user as follows: "Based on the feedback received through the smart glasses, please tell me how to safely adjust the work speed of the factory robot."

[0474] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0475] Step 1:

[0476] The server analyzes documents received from the user's terminal using natural language processing techniques. The input documents contain user requests and specifications. Based on this input, the server extracts important elements. The output is a list of the elements extracted from the document.

[0477] Step 2:

[0478] The server uses the elements obtained in Step 1 to refer to the historical database and search for relevant data. This process uses a similarity matching algorithm to search for data. The input is a list of extracted elements, and the output generates relevant suggestions.

[0479] Step 3:

[0480] The generated suggestions are sent to the user's device. On the device, the user reviews the suggestions provided via their smartphone or smart glasses. Based on the suggestions, the user provides feedback that reflects their own feelings.

[0481] Step 4:

[0482] The device uses EmotionAnalyzer to analyze user feedback based on emotions. The analyzed emotional data is extracted from the user's feedback. The input is emotional feedback, and the output is data on the emotional state.

[0483] Step 5:

[0484] The server receives the sentiment data acquired in step 4 and adjusts the work schedule using TaskOptimizer. In this process, the sentiment data and the current work schedule are used as input to optimize the work content and speed. The adjusted work schedule is obtained as output.

[0485] Step 6:

[0486] The revised work plan is sent back to the user's terminal for review. This allows the user to visually understand the newly proposed work and update their feedback as needed. The input is the new work plan.

[0487] 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.

[0488] 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.

[0489] 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.

[0490] [Third Embodiment]

[0491] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0492] 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.

[0493] 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).

[0494] 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.

[0495] 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.

[0496] 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).

[0497] 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.

[0498] 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.

[0499] 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.

[0500] 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.

[0501] 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.

[0502] 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".

[0503] Embodiments of the present invention will now be described. This system operates primarily through a server and a user's terminal.

[0504] First, the user submits the bid specification from their terminal to the server. Upon receiving the specification, the server immediately begins analysis using natural language processing technology. Specifically, the server extracts important keywords and requirements from the specification and stores them in a database as structured data. This converts the information within the document into a format that is easy for the system to handle.

[0505] Next, the server references similar past bidding data to generate a proposal best suited to the specifications. This process examines specific countermeasures and resource allocations for each requirement based on past successful proposals. The generated proposal is then sent to the user's terminal for review.

[0506] Users send feedback on the proposal to the server via their device, and the proposal is automatically revised based on that feedback. This process is repeated until the user is completely satisfied with the proposal.

[0507] In project management after receiving an order, the server automatically generates a Work Breakdown Structure (WBS) based on the proposal. This divides the project into easily understandable work units, allowing for appropriate allocation of resources and time. Subsequently, the server monitors the project's progress in real time, and if deviations from the plan occur, it sends reminders and warnings to the user's terminal. This allows the user to detect problems early and take appropriate measures.

[0508] For example, in a large-scale IT system implementation project, utilizing a WBS (Work Breakdown Structure) generated by the server and progress monitoring functions allows for timely understanding of the progress of each phase, enabling smooth project execution. In this way, the present invention streamlines the entire process from bidding to project management, contributing to improved competitiveness for users.

[0509] The following describes the processing flow.

[0510] Step 1:

[0511] The server receives the bid specifications submitted by the user. The specifications are sent in digital format and stored securely on the server's storage.

[0512] Step 2:

[0513] The server analyzes the received specifications using natural language processing technology. Specifically, it extracts keywords and requirements from the document and converts them into structured data.

[0514] Step 3:

[0515] The server searches for similar projects in the past bidding database based on the analysis results of the specifications. It analyzes data from successful past proposals and picks out important elements.

[0516] Step 4:

[0517] The server automatically generates the optimal proposal that meets the requirements of the specification document, referencing historical data. The proposal will include specific countermeasures and cost estimates.

[0518] Step 5:

[0519] The server generates a proposal and sends it to the user's terminal. The user reviews the proposal details via their terminal and provides feedback as needed.

[0520] Step 6:

[0521] Based on user feedback, the server automatically adjusts the proposal. This process is repeated until the user is satisfied.

[0522] Step 7:

[0523] After receiving an order, the server automatically generates a Work Breakdown Structure (WBS) based on the proposal. Each work item of the project is clearly defined, and the necessary resources and time are allocated to them.

[0524] Step 8:

[0525] The server monitors project progress in real time. Progress data is updated periodically and kept as a buffer to notify users in case of unexpected events.

[0526] Step 9:

[0527] When a deviation from the project schedule is detected, the server sends reminders or warnings to the user's device. This allows the user to take the necessary action immediately.

[0528] (Example 1)

[0529] 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."

[0530] Current project management and bid proposal generation systems rely on manual or partially automated processes for extracting key elements from specifications, generating proposals based on historical data, refining proposals, and real-time monitoring of project progress. This leads to inefficiencies and a high likelihood of human error. A system is needed to perform these processes more efficiently and accurately.

[0531] 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.

[0532] This invention includes a server that receives specifications submitted from a user's terminal, analyzes the specifications using natural language processing technology, and extracts important elements; a generative AI model that automatically generates optimal proposals by referencing relevant historical data based on the analyzed information; a system that automatically creates a project work breakdown structure based on the generated proposals and formulates a plan; and a system that monitors progress in real time if it deviates from predictions and notifies the user of reminders or warnings as needed. This improves efficiency and accuracy throughout project management and enhances the user's competitiveness.

[0533] "User terminal" refers to the computing resources used by the user to submit specifications, review proposals, and input feedback.

[0534] "Natural language processing technology" refers to the technology of using computers to analyze natural language and extract useful information from language data.

[0535] "Key elements" refer to keywords and conditions within the specifications that are essential for project proposal and management.

[0536] A "generative AI model" refers to an artificial intelligence model that automatically generates optimal suggestions based on past data.

[0537] "Related past data" refers to information compiled from past bidding processes and project execution data.

[0538] "Optimal proposal content" refers to a plan generated to meet the requirements of the specifications and increase the chances of project success.

[0539] A "work breakdown structure" refers to a structure that clearly defines the specific work units of a project and shows the workflow and resource allocation.

[0540] "Monitoring progress in real time" means immediately understanding the current status of a project and continuously confirming that it is progressing according to plan.

[0541] "Reminders or warnings" refer to information that informs users of important matters in the progress of a project or to notify them of abnormal situations.

[0542] In implementing this invention, two main computing resources are used: a server and a user's terminal. The server begins processing upon receiving a specification document submitted from the user's terminal. The server utilizes natural language processing technology to analyze the specification document and extract important elements. The natural language processing technology used here is a generative AI model. This model includes, for example, natural language processing libraries such as SpaCy and NLTK, as well as more advanced models such as BERT and GPT-based models.

[0543] The extracted key elements are stored in a database as structured data. Next, the server uses this analysis result to refer to relevant past databases and utilizes a generative AI model to automatically generate optimal suggestions. The generated suggestions are sent to the user's terminal for review.

[0544] The terminal provides an interface where the user can review the proposal and enter feedback. This feedback is sent to the server and used to refine the proposal. This process is repeated until the user is satisfied.

[0545] Once the proposal is finalized, the server automatically creates a Work Breakdown Structure (WBS) for the project based on the generated proposal. This WBS defines specific work units and helps in the appropriate allocation of resources. The server monitors project progress in real time and supports early problem resolution by immediately sending reminders or warnings to the user's terminal if there are any deviations from the plan.

[0546] As a concrete example, in a large-scale IT system implementation project, a possible prompt used by the server might be, "Based on the requirements described in the specifications, refer to past success stories and generate the optimal proposal." This prompt allows the server to connect relevant historical data with different situations and provide the user with appropriate suggestions.

[0547] In this way, the present invention can streamline the process from bidding to project management, contributing to improved competitiveness for users.

[0548] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0549] Step 1:

[0550] The user's device uploads the bid specifications and submits them to the server. The input here is the specifications prepared by the user, in formats such as text files or PDFs. The output is a notification indicating that the file has been successfully sent to the server. Specifically, the device provides an interface that allows the user to select the desired file using a file selection function.

[0551] Step 2:

[0552] The server analyzes the received specification using natural language processing technology and extracts important elements. The input is the specification file received in step 1. The server uses a generative AI model (e.g., BERT, GPT) to extract keywords and requirements from the specification and organize them as structured data. The output is a database entry containing the extracted important elements.

[0553] Step 3:

[0554] The server references relevant historical data and automatically generates optimal proposals using a generative AI model. The input consists of the structured data generated in step 2 and historical project data. Here, the AI ​​model performs the analysis according to the prompt "Based on the requirements described in the specification, refer to past success stories and generate optimal proposals." The output is a document containing the generated proposals.

[0555] Step 4:

[0556] The server sends the generated proposal to the user's device and requests the user's review. The input is the proposal created in step 3. The output is the proposal displayed on the user's device. The device provides an interface that makes it easy for the user to review the content and includes a form for providing feedback.

[0557] Step 5:

[0558] Users send feedback on the proposed content to the server via their device. Input is user feedback, including comments and change requests. Output is the feedback data received by the server. The device provides a feedback submission button, allowing users to easily record their revisions.

[0559] Step 6:

[0560] The server adjusts the suggestions based on the feedback and updates them automatically. The input is the feedback received in step 5. The generating AI model analyzes the feedback and appropriately modifies the suggestions. The output is the new suggestions that reflect the feedback. This process is repeated until the user is satisfied with the suggestions.

[0561] Step 7:

[0562] The server automatically generates a Work Breakdown Structure (WBS) for the project based on the final proposal and constructs the project plan. The input is the proposal finalized in step 6. The server clarifies the hierarchical structure of tasks and efficiently allocates resources and schedules. The output is the completed WBS and project plan.

[0563] Step 8:

[0564] The server monitors project progress in real time and sends reminders or alerts to the user's terminal if there are deviations from the plan. The input is the current project progress information. The server analyzes the progress data using monitoring tools and detects anomalies. The output is support for quick action by sending necessary notifications to the user's terminal.

[0565] (Application Example 1)

[0566] 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."

[0567] The entire process of construction projects, from the bidding process to project management, presents challenges due to the significant time and effort required for manual document analysis, proposal creation, and progress monitoring. This can lead to project delays and wasted resources, thus creating a need for efficient and automated systems.

[0568] 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.

[0569] This invention includes a server that analyzes received documents using natural language processing technology and extracts key elements, a server that automatically generates optimal proposals by referencing relevant past data based on the analyzed information, and a server that provides an interface for uploading bidding specifications from a mobile device. This streamlines the process from bidding to management of construction projects, enabling optimal resource allocation and real-time monitoring of progress.

[0570] "Natural language processing technology" refers to technologies that enable computers to understand, analyze, and generate human language.

[0571] "Documents" refers to text data related to a project, such as bidding specifications.

[0572] "Key elements" are essential information and requirements for a project that are extracted through document analysis.

[0573] "Related past data" refers to information about records and results of similar projects that have been carried out in the past.

[0574] "Optimal proposal content" refers to information that presents the most effective solutions or plans for the project's requirements.

[0575] A "plan" is a schedule that outlines the specific steps and resource allocation required to carry out a project.

[0576] "Progress" is a measure that indicates whether project activities are proceeding according to plan.

[0577] A "notification or warning" is information issued when the project's progress deviates from the schedule.

[0578] "Mobile devices" refer to portable information processing devices such as smartphones and tablets.

[0579] An "interface" is the means or environment through which a user interacts with a system.

[0580] "Resources" refer to all available elements necessary for a project, including personnel, materials, and time.

[0581] The system for realizing this invention primarily operates using a server and a mobile terminal. The server uses natural language processing technology to analyze bid specifications uploaded by users and extract key elements. The software library spaCy is used to analyze the text data, and the extracted keywords are stored in a database as structured data.

[0582] The server also uses Pandas to manage historical bidding data and generates optimal proposals using a machine learning model with Scikit-learn. The generated proposals are sent to mobile devices, where users review them and provide feedback. This feedback is analyzed by TensorFlow and used to refine the proposals.

[0583] Furthermore, the server uses NetworkX to create project management plans and has the capability to monitor progress in real time. If project progress deviates from the plan, it uses Twilio to send notifications or warnings to the user's mobile device. This notification feature allows the user to immediately understand the situation and take appropriate action.

[0584] As a concrete example, in the construction industry, when bidding takes place for a new bridge construction project, this system analyzes the bidding specifications and makes optimal proposals based on past successes. Furthermore, if delays occur in the foundation work as the project progresses, it immediately sends notifications to mobile devices to support early detection and countermeasures for the problem.

[0585] An example of a prompt is, "Analyze the bidding specifications for the new bridge construction project and generate the optimal proposal based on past success stories." This prompt provides the foundation for the server to perform appropriate analysis and make proposals.

[0586] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0587] Step 1:

[0588] Users upload bid specifications from their mobile devices. On the device, they select the bid specifications, and the data is transferred via a form submitted to the server. Input is text data, and output is confirmation of the successful upload to the server.

[0589] Step 2:

[0590] The server analyzes the received bid specifications using natural language processing techniques. It uses the spaCy library to analyze the text data and extract key elements. The input is the uploaded text data, and the output consists of extracted keywords and structured data.

[0591] Step 3:

[0592] The server automatically generates optimal suggestions using an AI model based on the extracted information and references relevant historical data. Relevant data is retrieved from a database managed with Pandas, and a machine learning model using Scikit-learn generates the suggestions. The input consists of structured data and historical data, and the output is the newly generated suggestions.

[0593] Step 4:

[0594] The server sends the generated proposal to the user's mobile device. The user reviews the proposal via their device. The input is the generated proposal, and the output is what is presented to the user.

[0595] Step 5:

[0596] Users provide feedback on the proposed content. This feedback is sent to the server via an interface on the device. The input is the user's feedback, and the output is the feedback data sent to the server.

[0597] Step 6:

[0598] The server adjusts the proposal based on the feedback received. It analyzes the feedback data using TensorFlow and reconstructs the proposal by applying a generative AI model. The input is the feedback data, and the output is the adjusted proposal.

[0599] Step 7:

[0600] The server creates a project management plan based on the adjusted proposal. NetworkX automatically generates a work breakdown diagram based on the hierarchical structure, preparing for project progress management. The input is the adjusted proposal, and the output is the project management plan.

[0601] Step 8:

[0602] The server monitors project progress in real time and, as needed, sends notifications or alerts to the user's mobile device using Twilio. The input is project progress data, and the output is notifications or alerts to the user.

[0603] 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.

[0604] Specific embodiments of the present invention will now be described. This system consists of a server, a terminal, and a user interface using an emotion engine.

[0605] First, the user sends the bid specifications to the server using their device. The server analyzes the contents of the received specifications using natural language processing technology and extracts important elements from them. Based on this analysis information, the server then proceeds to a process of referencing a database of past bids and generating the optimal proposal.

[0606] The generated suggestions are sent to the user's device for review. This is where the emotion engine comes into play. When the user provides emotion-based feedback, the device analyzes emotion data from the user's input data and the content of the conversation. The server retrieves this emotion information and further adjusts the suggestions, taking the user's emotional state into consideration. For example, if the user feels uneasy about the suggestions, the server may add more detailed information or specify risk mitigation measures.

[0607] The emotion engine is also utilized in the project management phase. The server collects user feedback during the project, analyzes the emotion data, and incorporates it into the project management plan. For example, if a user's stress level is high, the project schedule is re-evaluated and optimized to reduce the burden.

[0608] As a concrete example, suppose an initial proposal for a project is presented to a user, and the user expresses dissatisfaction through the system. In this case, the server automatically adds more specific proposal details and supplementary materials to the proposal based on information from the emotion engine, and then re-presents it to the user's terminal. In this way, integrating an emotion engine makes it possible to increase user satisfaction and improve the quality of proposals.

[0609] This invention utilizes emotional data throughout the entire process, from bidding to project management, to enhance user decision-making support. This system enables flexible and effective process management that takes user emotions into account.

[0610] The following describes the processing flow.

[0611] Step 1:

[0612] The user sends the bid specifications from their terminal to the server. The terminal prepares the specifications in digital format and transfers the data to the server via secure communication.

[0613] Step 2:

[0614] The server analyzes the received specifications using a natural language processing engine and extracts key elements. These key elements include technical requirements, budget constraints, and deadlines. This information is recorded in the database as structured data.

[0615] Step 3:

[0616] Based on the analysis results, the server references a database of past bids and automatically generates the optimal proposal content corresponding to the specifications. The proposal content learns patterns from past successful cases and is provided to the user as a rational plan.

[0617] Step 4:

[0618] The server generates a proposal and sends it to the user's terminal. The user reviews it and evaluates the proposal to suit their needs.

[0619] Step 5:

[0620] The emotion engine receives user feedback and analyzes the emotions contained within it. The device generates emotion data from the ratings and comments entered by the user and sends it to the server.

[0621] Step 6:

[0622] The server utilizes the emotion engine's analysis results to revise or adjust the proposal's content. Additional information or changes are added to the proposal based on the issues indicated by the user's emotions.

[0623] Step 7:

[0624] After receiving an order, the server creates a Work Breakdown Structure (WBS) based on the proposal and monitors its progress in real time. The emotion engine analyzes user feedback and emotions throughout the project to help adjust the plan.

[0625] Step 8:

[0626] The server monitors project progress and sends reminders and alerts to users. In particular, it takes into account user sentiment analysis results to provide appropriate notifications at the right time.

[0627] The above describes the processing flow of this system incorporating an emotion engine.

[0628] (Example 2)

[0629] 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."

[0630] Traditional systems fail to consider user emotions in generating proposals and managing projects, resulting in decreased user satisfaction and project efficiency. In particular, the inability to adequately incorporate user feedback leads to rigid proposals and a lack of flexibility in project progress.

[0631] 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.

[0632] In this invention, the server includes means for analyzing received documents and extracting important elements using natural language processing technology, means for automatically generating optimal suggestions by referring to relevant past data based on the analyzed information, and means for adjusting the suggestions based on the generated suggestions by analyzing emotional data and providing information that takes into account the user's emotional state. This enables dynamic adjustment of suggestions according to the user's emotional state and optimization of project management.

[0633] "Natural language processing technology" is a technique that enables computers to understand and analyze human language, and is a means of structuring information within documents and extracting important elements.

[0634] "Key elements" are valuable pieces of information or keywords that should be extracted from the data within a document as a result of analysis, and are useful for generating proposals.

[0635] "Proposed content" refers to information including recommendations and plans generated by the server based on the analyzed information and relevant historical data.

[0636] "Emotional data" refers to data that indicates the emotional state and reactions extracted from user feedback, and is used by the system to make adjustments that take the user's emotions into account.

[0637] Project management is a set of tasks that involve planning, executing, monitoring, and controlling activities to achieve specific goals, including managing and coordinating progress.

[0638] This invention relates to a system comprising a server, a terminal, and a user interface that utilizes sentiment data. The user sends a bid specification from the terminal to the server. The server analyzes the received specification using natural language processing technology and extracts key elements. This process typically employs a "natural language processing tool." Based on the analysis results, the server references relevant historical data and automatically generates the optimal proposal. "Data management software" is likely to be used for database management.

[0639] The proposal is sent to the user's device, where the user reviews it. When the user provides feedback on the proposal, the emotion engine is utilized. The device analyzes the user's feedback and generates emotion data. An "emotion analysis tool" is used to analyze this emotion data and understand the user's emotional state.

[0640] The server acquires sentiment data and further adjusts the suggestions based on the user's emotions. For example, if the user feels anxious, the server may add more detailed information to the suggestion or suggest risk mitigation measures. A possible example of a specific prompt might be, "If the user has expressed dissatisfaction with the suggestion, please advise on how to improve the suggestion considering their emotions."

[0641] Through this system, users can provide emotion-based, interactive feedback, which contributes to the refinement of proposals. This is expected to improve user satisfaction and increase the efficiency of project management.

[0642] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0643] Step 1:

[0644] User: Use the terminal to create the bid specifications and send them to the server.

[0645] Input: Bidding specifications (text data) created by the user on their device.

[0646] Output: Specification data sent to the server.

[0647] Specific operation: When the user enters the specifications on their device and clicks the "Submit" button, the specifications are uploaded to the server.

[0648] Step 2:

[0649] Server: Analyzes the received specifications using natural language processing technology.

[0650] Input: Specification data received by the server.

[0651] Data processing: Use natural language processing tools to perform syntactic analysis and extract key phrases from documents.

[0652] Output: A list of the extracted key elements.

[0653] Specific operation: The analysis engine on the server starts up, analyzes the text of the specification document, and identifies important keywords and phrases.

[0654] Step 3:

[0655] Server: Based on the extracted elements, it references relevant past data to generate the most suitable suggestions.

[0656] Input: A list of the key elements extracted.

[0657] Data Calculation: Refer to historical bidding data through database queries and select recommendations from similar cases.

[0658] Output: The generated suggestions.

[0659] Specific operation: The server retrieves relevant information from the database and combines it to generate the optimal suggestions.

[0660] Step 4:

[0661] Server: Sends the generated suggestions to the user's terminal.

[0662] Input: The generated suggestions.

[0663] Output: The proposed content delivered to the user's device.

[0664] Specific operation: The server sends the suggestion to the user via the network, and a notification is displayed on the user's device screen.

[0665] Step 5:

[0666] User: Review the proposal and provide feedback.

[0667] Input: The submitted proposal.

[0668] Output: User sentiment feedback (text or selection format).

[0669] Specific actions: The user reads the proposal, selects buttons to express anxiety or reassurance, or enters comments.

[0670] Step 6:

[0671] Terminal: Analyzes feedback using an emotion engine.

[0672] Input: User emotional feedback.

[0673] Data processing: Using emotion analysis tools, quantify or classify the user's emotional state from feedback.

[0674] Output: Sentiment data.

[0675] Specific operation: The sentiment analysis engine analyzes the text or selection data of the feedback and generates a sentiment score.

[0676] Step 7:

[0677] Server: Adjusts suggestions based on sentiment data.

[0678] Input: Sentiment data and initial proposal content.

[0679] Data processing: Data processing is performed to add additional information and detailed explanations to the proposal, taking into account emotional states.

[0680] Output: Revised proposal.

[0681] Specific actions: Referencing sentiment data to supplement unclear points in the proposal and add information that will reassure the user.

[0682] Step 8:

[0683] Server: Analyzes emotional feedback during project progress and optimizes the plan.

[0684] Input: Project progress information and sentiment data.

[0685] Data processing: Compare progress and sentiment scores to re-evaluate schedules and tasks.

[0686] Output: Adjusted project plan.

[0687] Specific action: A schedule optimization algorithm is activated, adjusting the project in response to increasing stress levels.

[0688] (Application Example 2)

[0689] 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."

[0690] In the past, on-site work management of machinery has often relied on experience and intuition, leading to challenges in improving worker satisfaction, safety, and work efficiency. Furthermore, insufficient adjustments to work processes that take into account workers' emotional states have resulted in a tendency for stress and fatigue to accumulate.

[0691] 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.

[0692] In this invention, the server includes means for analyzing received documents and extracting important elements using natural language processing technology, means for automatically generating optimal suggestions by referring to relevant past data based on the analyzed information, and means for obtaining emotion-based feedback from workers and adjusting work plans according to the emotion information. This makes it possible to improve the efficiency of work planning and enhance worker satisfaction and safety on site.

[0693] "Natural language processing technology" is a technology that enables computers to understand and analyze human language.

[0694] "Document analysis" means deciphering the content of a received document and understanding its meaning and structure.

[0695] "Extracting key elements" means extracting information that is considered particularly important from an analyzed document.

[0696] "Referring to related data" means searching past databases to find similar information.

[0697] "Automatically generating proposals" means that a computer creates the optimal actions and plans based on the analysis results.

[0698] "Obtaining emotion-based feedback from workers" means collecting information about the emotional state of the workers.

[0699] "Adjusting work plans based on emotional information" means re-evaluating work schedules and workloads by considering workers' emotional data.

[0700] "Efficiency improvement" means reviewing work processes, reducing waste, and increasing effectiveness.

[0701] "Enhancing safety" means reducing accidents and risks, and ensuring that work is carried out safely.

[0702] "Satisfaction level" refers to the degree of satisfaction that users feel with a service or product.

[0703] In realizing this invention, the server handles the main processing. First, the server analyzes the document sent from the user's terminal using natural language processing technology and extracts important elements. The analyzed information is compared with past data stored on the server, and optimal suggestions are automatically generated based on the content. The user receives the generated suggestions using a terminal such as a smartphone or smart glasses and provides feedback based on their own feelings.

[0704] For obtaining emotional feedback, an emotion analysis engine called EmotionAnalyzer is used to analyze the user's emotional state from their feedback. The emotional data is sent to a server, and a task optimization engine known as TaskOptimizer dynamically adjusts the work schedules of workers and machines based on the emotional information. This process leads to improved work efficiency and safety, and ultimately, increased user satisfaction.

[0705] As a concrete example, suppose one task in a factory's manufacturing process places a greater burden on the team than others. When a leader wearing smart glasses perceives this burden, the server generates new suggestions for distributing the workload based on their feedback and notifies the team on-site.

[0706] By utilizing a generative AI model, prompts can be presented to the user as follows: "Based on the feedback received through the smart glasses, please tell me how to safely adjust the work speed of the factory robot."

[0707] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0708] Step 1:

[0709] The server analyzes documents received from the user's terminal using natural language processing techniques. The input documents contain user requests and specifications. Based on this input, the server extracts important elements. The output is a list of the elements extracted from the document.

[0710] Step 2:

[0711] The server uses the elements obtained in Step 1 to refer to the historical database and search for relevant data. This process uses a similarity matching algorithm to search for data. The input is a list of extracted elements, and the output generates relevant suggestions.

[0712] Step 3:

[0713] The generated suggestions are sent to the user's device. On the device, the user reviews the suggestions provided via their smartphone or smart glasses. Based on the suggestions, the user provides feedback that reflects their own feelings.

[0714] Step 4:

[0715] The device uses EmotionAnalyzer to analyze user feedback based on emotions. The analyzed emotional data is extracted from the user's feedback. The input is emotional feedback, and the output is data on the emotional state.

[0716] Step 5:

[0717] The server receives the sentiment data acquired in step 4 and adjusts the work schedule using TaskOptimizer. In this process, the sentiment data and the current work schedule are used as input to optimize the work content and speed. The adjusted work schedule is obtained as output.

[0718] Step 6:

[0719] The revised work plan is sent back to the user's terminal for review. This allows the user to visually understand the newly proposed work and update their feedback as needed. The input is the new work plan.

[0720] 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.

[0721] 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.

[0722] 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.

[0723] [Fourth Embodiment]

[0724] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0725] 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.

[0726] 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).

[0727] 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.

[0728] 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.

[0729] 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).

[0730] 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.

[0731] 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.

[0732] 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.

[0733] 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.

[0734] 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.

[0735] 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.

[0736] 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".

[0737] Embodiments of the present invention will now be described. This system operates primarily through a server and a user's terminal.

[0738] First, the user submits the bid specification from their terminal to the server. Upon receiving the specification, the server immediately begins analysis using natural language processing technology. Specifically, the server extracts important keywords and requirements from the specification and stores them in a database as structured data. This converts the information within the document into a format that is easy for the system to handle.

[0739] Next, the server references similar past bidding data to generate a proposal best suited to the specifications. This process examines specific countermeasures and resource allocations for each requirement based on past successful proposals. The generated proposal is then sent to the user's terminal for review.

[0740] Users send feedback on the proposal to the server via their device, and the proposal is automatically revised based on that feedback. This process is repeated until the user is completely satisfied with the proposal.

[0741] In project management after receiving an order, the server automatically generates a Work Breakdown Structure (WBS) based on the proposal. This divides the project into easily understandable work units, allowing for appropriate allocation of resources and time. Subsequently, the server monitors the project's progress in real time, and if deviations from the plan occur, it sends reminders and warnings to the user's terminal. This allows the user to detect problems early and take appropriate measures.

[0742] For example, in a large-scale IT system implementation project, utilizing a WBS (Work Breakdown Structure) generated by the server and progress monitoring functions allows for timely understanding of the progress of each phase, enabling smooth project execution. In this way, the present invention streamlines the entire process from bidding to project management, contributing to improved competitiveness for users.

[0743] The following describes the processing flow.

[0744] Step 1:

[0745] The server receives the bid specifications submitted by the user. The specifications are sent in digital format and stored securely on the server's storage.

[0746] Step 2:

[0747] The server analyzes the received specifications using natural language processing technology. Specifically, it extracts keywords and requirements from the document and converts them into structured data.

[0748] Step 3:

[0749] The server searches for similar projects in the past bidding database based on the analysis results of the specifications. It analyzes data from successful past proposals and picks out important elements.

[0750] Step 4:

[0751] The server automatically generates the optimal proposal that meets the requirements of the specification document, referencing historical data. The proposal will include specific countermeasures and cost estimates.

[0752] Step 5:

[0753] The server generates a proposal and sends it to the user's terminal. The user reviews the proposal details via their terminal and provides feedback as needed.

[0754] Step 6:

[0755] Based on user feedback, the server automatically adjusts the proposal. This process is repeated until the user is satisfied.

[0756] Step 7:

[0757] After receiving an order, the server automatically generates a Work Breakdown Structure (WBS) based on the proposal. Each work item of the project is clearly defined, and the necessary resources and time are allocated to them.

[0758] Step 8:

[0759] The server monitors project progress in real time. Progress data is updated periodically and kept as a buffer to notify users in case of unexpected events.

[0760] Step 9:

[0761] When a deviation from the project schedule is detected, the server sends reminders or warnings to the user's device. This allows the user to take the necessary action immediately.

[0762] (Example 1)

[0763] 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".

[0764] Current project management and bid proposal generation systems rely on manual or partially automated processes for extracting key elements from specifications, generating proposals based on historical data, refining proposals, and real-time monitoring of project progress. This leads to inefficiencies and a high likelihood of human error. A system is needed to perform these processes more efficiently and accurately.

[0765] 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.

[0766] This invention includes a server that receives specifications submitted from a user's terminal, analyzes the specifications using natural language processing technology, and extracts important elements; a generative AI model that automatically generates optimal proposals by referencing relevant historical data based on the analyzed information; a system that automatically creates a project work breakdown structure based on the generated proposals and formulates a plan; and a system that monitors progress in real time if it deviates from predictions and notifies the user of reminders or warnings as needed. This improves efficiency and accuracy throughout project management and enhances the user's competitiveness.

[0767] "User terminal" refers to the computing resources used by the user to submit specifications, review proposals, and input feedback.

[0768] "Natural language processing technology" refers to the technology of using computers to analyze natural language and extract useful information from language data.

[0769] "Key elements" refer to keywords and conditions within the specifications that are essential for project proposal and management.

[0770] A "generative AI model" refers to an artificial intelligence model that automatically generates optimal suggestions based on past data.

[0771] "Related past data" refers to information compiled from past bidding processes and project execution data.

[0772] "Optimal proposal content" refers to a plan generated to meet the requirements of the specifications and increase the chances of project success.

[0773] A "work breakdown structure" refers to a structure that clearly defines the specific work units of a project and shows the workflow and resource allocation.

[0774] "Monitoring progress in real time" means immediately understanding the current status of a project and continuously confirming that it is progressing according to plan.

[0775] "Reminders or warnings" refer to information that informs users of important matters in the progress of a project or to notify them of abnormal situations.

[0776] In implementing this invention, two main computing resources are used: a server and a user's terminal. The server begins processing upon receiving a specification document submitted from the user's terminal. The server utilizes natural language processing technology to analyze the specification document and extract important elements. The natural language processing technology used here is a generative AI model. This model includes, for example, natural language processing libraries such as SpaCy and NLTK, as well as more advanced models such as BERT and GPT-based models.

[0777] The extracted key elements are stored in a database as structured data. Next, the server uses this analysis result to refer to relevant past databases and utilizes a generative AI model to automatically generate optimal suggestions. The generated suggestions are sent to the user's terminal for review.

[0778] The terminal provides an interface where the user can review the proposal and enter feedback. This feedback is sent to the server and used to refine the proposal. This process is repeated until the user is satisfied.

[0779] Once the proposal is finalized, the server automatically creates a Work Breakdown Structure (WBS) for the project based on the generated proposal. This WBS defines specific work units and helps in the appropriate allocation of resources. The server monitors project progress in real time and supports early problem resolution by immediately sending reminders or warnings to the user's terminal if there are any deviations from the plan.

[0780] As a concrete example, in a large-scale IT system implementation project, a possible prompt used by the server might be, "Based on the requirements described in the specifications, refer to past success stories and generate the optimal proposal." This prompt allows the server to connect relevant historical data with different situations and provide the user with appropriate suggestions.

[0781] In this way, the present invention can streamline the process from bidding to project management, contributing to improved competitiveness for users.

[0782] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0783] Step 1:

[0784] The user's device uploads the bid specifications and submits them to the server. The input here is the specifications prepared by the user, in formats such as text files or PDFs. The output is a notification indicating that the file has been successfully sent to the server. Specifically, the device provides an interface that allows the user to select the desired file using a file selection function.

[0785] Step 2:

[0786] The server analyzes the received specification using natural language processing technology and extracts important elements. The input is the specification file received in step 1. The server uses a generative AI model (e.g., BERT, GPT) to extract keywords and requirements from the specification and organize them as structured data. The output is a database entry containing the extracted important elements.

[0787] Step 3:

[0788] The server references relevant historical data and automatically generates optimal proposals using a generative AI model. The input consists of the structured data generated in step 2 and historical project data. Here, the AI ​​model performs the analysis according to the prompt "Based on the requirements described in the specification, refer to past success stories and generate optimal proposals." The output is a document containing the generated proposals.

[0789] Step 4:

[0790] The server sends the generated proposal to the user's device and requests the user's review. The input is the proposal created in step 3. The output is the proposal displayed on the user's device. The device provides an interface that makes it easy for the user to review the content and includes a form for providing feedback.

[0791] Step 5:

[0792] Users send feedback on the proposed content to the server via their device. Input is user feedback, including comments and change requests. Output is the feedback data received by the server. The device provides a feedback submission button, allowing users to easily record their revisions.

[0793] Step 6:

[0794] The server adjusts the suggestions based on the feedback and updates them automatically. The input is the feedback received in step 5. The generating AI model analyzes the feedback and appropriately modifies the suggestions. The output is the new suggestions that reflect the feedback. This process is repeated until the user is satisfied with the suggestions.

[0795] Step 7:

[0796] The server automatically generates a Work Breakdown Structure (WBS) for the project based on the final proposal and constructs the project plan. The input is the proposal finalized in step 6. The server clarifies the hierarchical structure of tasks and efficiently allocates resources and schedules. The output is the completed WBS and project plan.

[0797] Step 8:

[0798] The server monitors project progress in real time and sends reminders or alerts to the user's terminal if there are deviations from the plan. The input is the current project progress information. The server analyzes the progress data using monitoring tools and detects anomalies. The output is support for quick action by sending necessary notifications to the user's terminal.

[0799] (Application Example 1)

[0800] 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".

[0801] The entire process of construction projects, from the bidding process to project management, presents challenges due to the significant time and effort required for manual document analysis, proposal creation, and progress monitoring. This can lead to project delays and wasted resources, thus creating a need for efficient and automated systems.

[0802] 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.

[0803] This invention includes a server that analyzes received documents using natural language processing technology and extracts key elements, a server that automatically generates optimal proposals by referencing relevant past data based on the analyzed information, and a server that provides an interface for uploading bidding specifications from a mobile device. This streamlines the process from bidding to management of construction projects, enabling optimal resource allocation and real-time monitoring of progress.

[0804] "Natural language processing technology" refers to technologies that enable computers to understand, analyze, and generate human language.

[0805] "Documents" refers to text data related to a project, such as bidding specifications.

[0806] "Key elements" are essential information and requirements for a project that are extracted through document analysis.

[0807] "Related past data" refers to information about records and results of similar projects that have been carried out in the past.

[0808] "Optimal proposal content" refers to information that presents the most effective solutions or plans for the project's requirements.

[0809] A "plan" is a schedule that outlines the specific steps and resource allocation required to carry out a project.

[0810] "Progress" is a measure that indicates whether project activities are proceeding according to plan.

[0811] A "notification or warning" is information issued when the project's progress deviates from the schedule.

[0812] "Mobile devices" refer to portable information processing devices such as smartphones and tablets.

[0813] An "interface" is the means or environment through which a user interacts with a system.

[0814] "Resources" refer to all available elements necessary for a project, including personnel, materials, and time.

[0815] The system for realizing this invention primarily operates using a server and a mobile terminal. The server uses natural language processing technology to analyze bid specifications uploaded by users and extract key elements. The software library spaCy is used to analyze the text data, and the extracted keywords are stored in a database as structured data.

[0816] The server also uses Pandas to manage historical bidding data and generates optimal proposals using a machine learning model with Scikit-learn. The generated proposals are sent to mobile devices, where users review them and provide feedback. This feedback is analyzed by TensorFlow and used to refine the proposals.

[0817] Furthermore, the server uses NetworkX to create project management plans and has the capability to monitor progress in real time. If project progress deviates from the plan, it uses Twilio to send notifications or warnings to the user's mobile device. This notification feature allows the user to immediately understand the situation and take appropriate action.

[0818] As a concrete example, in the construction industry, when bidding takes place for a new bridge construction project, this system analyzes the bidding specifications and makes optimal proposals based on past successes. Furthermore, if delays occur in the foundation work as the project progresses, it immediately sends notifications to mobile devices to support early detection and countermeasures for the problem.

[0819] An example of a prompt is, "Analyze the bidding specifications for the new bridge construction project and generate the optimal proposal based on past success stories." This prompt provides the foundation for the server to perform appropriate analysis and make proposals.

[0820] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0821] Step 1:

[0822] Users upload bid specifications from their mobile devices. On the device, they select the bid specifications, and the data is transferred via a form submitted to the server. Input is text data, and output is confirmation of the successful upload to the server.

[0823] Step 2:

[0824] The server analyzes the received bid specifications using natural language processing techniques. It uses the spaCy library to analyze the text data and extract key elements. The input is the uploaded text data, and the output consists of extracted keywords and structured data.

[0825] Step 3:

[0826] The server automatically generates optimal suggestions using an AI model based on the extracted information and references relevant historical data. Relevant data is retrieved from a database managed with Pandas, and a machine learning model using Scikit-learn generates the suggestions. The input consists of structured data and historical data, and the output is the newly generated suggestions.

[0827] Step 4:

[0828] The server sends the generated proposal to the user's mobile device. The user reviews the proposal via their device. The input is the generated proposal, and the output is what is presented to the user.

[0829] Step 5:

[0830] Users provide feedback on the proposed content. This feedback is sent to the server via an interface on the device. The input is the user's feedback, and the output is the feedback data sent to the server.

[0831] Step 6:

[0832] The server adjusts the proposal based on the feedback received. It analyzes the feedback data using TensorFlow and reconstructs the proposal by applying a generative AI model. The input is the feedback data, and the output is the adjusted proposal.

[0833] Step 7:

[0834] The server creates a project management plan based on the adjusted proposal. NetworkX automatically generates a work breakdown diagram based on the hierarchical structure, preparing for project progress management. The input is the adjusted proposal, and the output is the project management plan.

[0835] Step 8:

[0836] The server monitors project progress in real time and, as needed, sends notifications or alerts to the user's mobile device using Twilio. The input is project progress data, and the output is notifications or alerts to the user.

[0837] 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.

[0838] Specific embodiments of the present invention will now be described. This system consists of a server, a terminal, and a user interface using an emotion engine.

[0839] First, the user sends the bid specifications to the server using their device. The server analyzes the contents of the received specifications using natural language processing technology and extracts important elements from them. Based on this analysis information, the server then proceeds to a process of referencing a database of past bids and generating the optimal proposal.

[0840] The generated suggestions are sent to the user's device for review. This is where the emotion engine comes into play. When the user provides emotion-based feedback, the device analyzes emotion data from the user's input data and the content of the conversation. The server retrieves this emotion information and further adjusts the suggestions, taking the user's emotional state into consideration. For example, if the user feels uneasy about the suggestions, the server may add more detailed information or specify risk mitigation measures.

[0841] The emotion engine is also utilized in the project management phase. The server collects user feedback during the project, analyzes the emotion data, and incorporates it into the project management plan. For example, if a user's stress level is high, the project schedule is re-evaluated and optimized to reduce the burden.

[0842] As a concrete example, suppose an initial proposal for a project is presented to a user, and the user expresses dissatisfaction through the system. In this case, the server automatically adds more specific proposal details and supplementary materials to the proposal based on information from the emotion engine, and then re-presents it to the user's terminal. In this way, integrating an emotion engine makes it possible to increase user satisfaction and improve the quality of proposals.

[0843] This invention utilizes emotional data throughout the entire process, from bidding to project management, to enhance user decision-making support. This system enables flexible and effective process management that takes user emotions into account.

[0844] The following describes the processing flow.

[0845] Step 1:

[0846] The user sends the bid specifications from their terminal to the server. The terminal prepares the specifications in digital format and transfers the data to the server via secure communication.

[0847] Step 2:

[0848] The server analyzes the received specifications using a natural language processing engine and extracts key elements. These key elements include technical requirements, budget constraints, and deadlines. This information is recorded in the database as structured data.

[0849] Step 3:

[0850] Based on the analysis results, the server references a database of past bids and automatically generates the optimal proposal content corresponding to the specifications. The proposal content learns patterns from past successful cases and is provided to the user as a rational plan.

[0851] Step 4:

[0852] The server generates a proposal and sends it to the user's terminal. The user reviews it and evaluates the proposal to suit their needs.

[0853] Step 5:

[0854] The emotion engine receives user feedback and analyzes the emotions contained within it. The device generates emotion data from the ratings and comments entered by the user and sends it to the server.

[0855] Step 6:

[0856] The server utilizes the emotion engine's analysis results to revise or adjust the proposal's content. Additional information or changes are added to the proposal based on the issues indicated by the user's emotions.

[0857] Step 7:

[0858] After receiving an order, the server creates a Work Breakdown Structure (WBS) based on the proposal and monitors its progress in real time. The emotion engine analyzes user feedback and emotions throughout the project to help adjust the plan.

[0859] Step 8:

[0860] The server monitors project progress and sends reminders and alerts to users. In particular, it takes into account user sentiment analysis results to provide appropriate notifications at the right time.

[0861] The above describes the processing flow of this system incorporating an emotion engine.

[0862] (Example 2)

[0863] 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".

[0864] Traditional systems fail to consider user emotions in generating proposals and managing projects, resulting in decreased user satisfaction and project efficiency. In particular, the inability to adequately incorporate user feedback leads to rigid proposals and a lack of flexibility in project progress.

[0865] 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.

[0866] In this invention, the server includes means for analyzing received documents and extracting important elements using natural language processing technology, means for automatically generating optimal suggestions by referring to relevant past data based on the analyzed information, and means for adjusting the suggestions based on the generated suggestions by analyzing emotional data and providing information that takes into account the user's emotional state. This enables dynamic adjustment of suggestions according to the user's emotional state and optimization of project management.

[0867] "Natural language processing technology" is a technique that enables computers to understand and analyze human language, and is a means of structuring information within documents and extracting important elements.

[0868] "Key elements" are valuable pieces of information or keywords that should be extracted from the data within a document as a result of analysis, and are useful for generating proposals.

[0869] "Proposed content" refers to information including recommendations and plans generated by the server based on the analyzed information and relevant historical data.

[0870] "Emotional data" refers to data that indicates the emotional state and reactions extracted from user feedback, and is used by the system to make adjustments that take the user's emotions into account.

[0871] Project management is a set of tasks that involve planning, executing, monitoring, and controlling activities to achieve specific goals, including managing and coordinating progress.

[0872] This invention relates to a system comprising a server, a terminal, and a user interface that utilizes sentiment data. The user sends a bid specification from the terminal to the server. The server analyzes the received specification using natural language processing technology and extracts key elements. This process typically employs a "natural language processing tool." Based on the analysis results, the server references relevant historical data and automatically generates the optimal proposal. "Data management software" is likely to be used for database management.

[0873] The proposal is sent to the user's device, where the user reviews it. When the user provides feedback on the proposal, the emotion engine is utilized. The device analyzes the user's feedback and generates emotion data. An "emotion analysis tool" is used to analyze this emotion data and understand the user's emotional state.

[0874] The server acquires sentiment data and further adjusts the suggestions based on the user's emotions. For example, if the user feels anxious, the server may add more detailed information to the suggestion or suggest risk mitigation measures. A possible example of a specific prompt might be, "If the user has expressed dissatisfaction with the suggestion, please advise on how to improve the suggestion considering their emotions."

[0875] Through this system, users can provide emotion-based, interactive feedback, which contributes to the refinement of proposals. This is expected to improve user satisfaction and increase the efficiency of project management.

[0876] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0877] Step 1:

[0878] User: Use the terminal to create the bid specifications and send them to the server.

[0879] Input: Bidding specifications (text data) created by the user on their device.

[0880] Output: Specification data sent to the server.

[0881] Specific operation: When the user enters the specifications on their device and clicks the "Submit" button, the specifications are uploaded to the server.

[0882] Step 2:

[0883] Server: Analyzes the received specifications using natural language processing technology.

[0884] Input: Specification data received by the server.

[0885] Data processing: Use natural language processing tools to perform syntactic analysis and extract key phrases from documents.

[0886] Output: A list of the extracted key elements.

[0887] Specific operation: The analysis engine on the server starts up, analyzes the text of the specification document, and identifies important keywords and phrases.

[0888] Step 3:

[0889] Server: Based on the extracted elements, it references relevant past data to generate the most suitable suggestions.

[0890] Input: A list of the key elements extracted.

[0891] Data Calculation: Refer to historical bidding data through database queries and select recommendations from similar cases.

[0892] Output: The generated suggestions.

[0893] Specific operation: The server retrieves relevant information from the database and combines it to generate the optimal suggestions.

[0894] Step 4:

[0895] Server: Sends the generated suggestions to the user's terminal.

[0896] Input: The generated suggestions.

[0897] Output: The proposed content delivered to the user's device.

[0898] Specific operation: The server sends the suggestion to the user via the network, and a notification is displayed on the user's device screen.

[0899] Step 5:

[0900] User: Review the proposal and provide feedback.

[0901] Input: The submitted proposal.

[0902] Output: User sentiment feedback (text or selection format).

[0903] Specific actions: The user reads the proposal, selects buttons to express anxiety or reassurance, or enters comments.

[0904] Step 6:

[0905] Terminal: Analyzes feedback using an emotion engine.

[0906] Input: User emotional feedback.

[0907] Data processing: Using emotion analysis tools, quantify or classify the user's emotional state from feedback.

[0908] Output: Sentiment data.

[0909] Specific operation: The sentiment analysis engine analyzes the text or selection data of the feedback and generates a sentiment score.

[0910] Step 7:

[0911] Server: Adjusts suggestions based on sentiment data.

[0912] Input: Sentiment data and initial proposal content.

[0913] Data processing: Data processing is performed to add additional information and detailed explanations to the proposal, taking into account emotional states.

[0914] Output: Revised proposal.

[0915] Specific actions: Referencing sentiment data to supplement unclear points in the proposal and add information that will reassure the user.

[0916] Step 8:

[0917] Server: Analyzes emotional feedback during project progress and optimizes the plan.

[0918] Input: Project progress information and sentiment data.

[0919] Data processing: Compare progress and sentiment scores to re-evaluate schedules and tasks.

[0920] Output: Adjusted project plan.

[0921] Specific action: A schedule optimization algorithm is activated, adjusting the project in response to increasing stress levels.

[0922] (Application Example 2)

[0923] 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".

[0924] In the past, on-site work management of machinery has often relied on experience and intuition, leading to challenges in improving worker satisfaction, safety, and work efficiency. Furthermore, insufficient adjustments to work processes that take into account workers' emotional states have resulted in a tendency for stress and fatigue to accumulate.

[0925] 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.

[0926] In this invention, the server includes means for analyzing received documents and extracting important elements using natural language processing technology, means for automatically generating optimal suggestions by referring to relevant past data based on the analyzed information, and means for obtaining emotion-based feedback from workers and adjusting work plans according to the emotion information. This makes it possible to improve the efficiency of work planning and enhance worker satisfaction and safety on site.

[0927] "Natural language processing technology" is a technology that enables computers to understand and analyze human language.

[0928] "Document analysis" means deciphering the content of a received document and understanding its meaning and structure.

[0929] "Extracting key elements" means extracting information that is considered particularly important from an analyzed document.

[0930] "Referring to related data" means searching past databases to find similar information.

[0931] "Automatically generating proposals" means that a computer creates the optimal actions and plans based on the analysis results.

[0932] "Obtaining emotion-based feedback from workers" means collecting information about the emotional state of the workers.

[0933] "Adjusting work plans based on emotional information" means re-evaluating work schedules and workloads by considering workers' emotional data.

[0934] "Efficiency improvement" means reviewing work processes, reducing waste, and increasing effectiveness.

[0935] "Enhancing safety" means reducing accidents and risks, and ensuring that work is carried out safely.

[0936] "Satisfaction level" refers to the degree of satisfaction that users feel with a service or product.

[0937] In realizing this invention, the server handles the main processing. First, the server analyzes the document sent from the user's terminal using natural language processing technology and extracts important elements. The analyzed information is compared with past data stored on the server, and optimal suggestions are automatically generated based on the content. The user receives the generated suggestions using a terminal such as a smartphone or smart glasses and provides feedback based on their own feelings.

[0938] For obtaining emotional feedback, an emotion analysis engine called EmotionAnalyzer is used to analyze the user's emotional state from their feedback. The emotional data is sent to a server, and a task optimization engine known as TaskOptimizer dynamically adjusts the work schedules of workers and machines based on the emotional information. This process leads to improved work efficiency and safety, and ultimately, increased user satisfaction.

[0939] As a concrete example, suppose one task in a factory's manufacturing process places a greater burden on the team than others. When a leader wearing smart glasses perceives this burden, the server generates new suggestions for distributing the workload based on their feedback and notifies the team on-site.

[0940] By utilizing a generative AI model, prompts can be presented to the user as follows: "Based on the feedback received through the smart glasses, please tell me how to safely adjust the work speed of the factory robot."

[0941] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0942] Step 1:

[0943] The server analyzes documents received from the user's terminal using natural language processing techniques. The input documents contain user requests and specifications. Based on this input, the server extracts important elements. The output is a list of the elements extracted from the document.

[0944] Step 2:

[0945] The server uses the elements obtained in Step 1 to refer to the historical database and search for relevant data. This process uses a similarity matching algorithm to search for data. The input is a list of extracted elements, and the output generates relevant suggestions.

[0946] Step 3:

[0947] The generated suggestions are sent to the user's device. On the device, the user reviews the suggestions provided via their smartphone or smart glasses. Based on the suggestions, the user provides feedback that reflects their own feelings.

[0948] Step 4:

[0949] The device uses EmotionAnalyzer to analyze user feedback based on emotions. The analyzed emotional data is extracted from the user's feedback. The input is emotional feedback, and the output is data on the emotional state.

[0950] Step 5:

[0951] The server receives the sentiment data acquired in step 4 and adjusts the work schedule using TaskOptimizer. In this process, the sentiment data and the current work schedule are used as input to optimize the work content and speed. The adjusted work schedule is obtained as output.

[0952] Step 6:

[0953] The revised work plan is sent back to the user's terminal for review. This allows the user to visually understand the newly proposed work and update their feedback as needed. The input is the new work plan.

[0954] 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.

[0955] 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.

[0956] 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 robot 414.

[0957] 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.

[0958] 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.

[0959] 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.

[0960] 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.

[0961] 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.

[0962] 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."

[0963] 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.

[0964] 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.

[0965] 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.

[0966] 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.

[0967] 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.

[0968] 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.

[0969] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0970] 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.

[0971] 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.

[0972] 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.

[0973] 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.

[0974] 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.

[0975] The following is further disclosed regarding the embodiments described above.

[0976] (Claim 1)

[0977] A means of analyzing a received document using natural language processing technology and extracting important elements,

[0978] A means to automatically generate optimal suggestions by referencing past relevant data based on the analyzed information,

[0979] A means to create a project management plan based on the generated proposals and to monitor progress in real time,

[0980] A means of issuing reminders or warnings as needed,

[0981] A system that includes this.

[0982] (Claim 2)

[0983] The system according to claim 1, which manages the progress of each task in project management using a work breakdown diagram based on the created hierarchical structure.

[0984] (Claim 3)

[0985] The system according to claim 1, including an interface that adjusts the proposed content based on feedback provided by the user.

[0986] "Example 1"

[0987] (Claim 1)

[0988] A means of receiving specifications submitted from the user's terminal, analyzing the specifications using natural language processing technology, and extracting important elements,

[0989] A means of automatically generating optimal suggestions using a generative AI model, based on the analyzed information and referencing relevant past data.

[0990] A method for automatically creating a project work breakdown structure based on the generated proposals and formulating a plan,

[0991] A means to monitor progress in real time if it deviates from the prediction and to notify the user of reminders or warnings as needed,

[0992] A system that includes this.

[0993] (Claim 2)

[0994] The system according to claim 1, which manages the progress of each task in a project based on the created work breakdown structure.

[0995] (Claim 3)

[0996] The system according to claim 1, comprising an interface for receiving feedback from users and adjusting the proposed content based on that feedback.

[0997] "Application Example 1"

[0998] (Claim 1)

[0999] A means of analyzing a received document using natural language processing technology and extracting important elements,

[1000] A means to automatically generate optimal suggestions by referencing past relevant data based on the analyzed information,

[1001] A means to create a plan based on the generated proposals and monitor progress in real time,

[1002] Means of issuing notifications or warnings as needed,

[1003] A means of providing an interface for uploading bidding specifications from a mobile device,

[1004] A means of providing optimized proposals that show appropriate resource and time allocation based on specification analysis and past examples,

[1005] A system that includes this.

[1006] (Claim 2)

[1007] The system according to claim 1, which manages the progress of each activity in project management using a work breakdown diagram based on the created hierarchical structure.

[1008] (Claim 3)

[1009] The system according to claim 1, including an interface that adjusts the proposed content based on feedback provided by the user.

[1010] "Example 2 of combining an emotion engine"

[1011] (Claim 1)

[1012] A means of analyzing a received document using natural language processing technology and extracting important elements,

[1013] A means to automatically generate optimal suggestions by referencing past relevant data based on the analyzed information,

[1014] Based on the generated suggestions, a means of analyzing emotional data to adjust the suggestions and providing information that takes into account the user's emotional state,

[1015] Analyzing emotional data feedback during project management to dynamically optimize project plans,

[1016] A system that includes this.

[1017] (Claim 2)

[1018] The system according to claim 1, which manages the progress of each task using a work breakdown diagram based on the created hierarchical structure and adjusts the workload of tasks based on emotional feedback.

[1019] (Claim 3)

[1020] The system according to claim 1, including an interface that adjusts the suggested content based on emotional feedback provided by the user.

[1021] "Application example 2 when combining with an emotional engine"

[1022] (Claim 1)

[1023] A means of analyzing a received document using natural language processing technology and extracting important elements,

[1024] A means to automatically generate optimal suggestions by referencing past relevant data based on the analyzed information,

[1025] Based on the generated proposals, a work plan for the machinery to be used on-site is created, and a means of monitoring progress in real time is provided.

[1026] A means of obtaining emotion-based feedback from workers and adjusting work plans according to emotional information,

[1027] A system that includes this.

[1028] (Claim 2)

[1029] The system according to claim 1, which obtains feedback based on the worker's emotions through a device that assists the work, and adjusts the working speed of the machine.

[1030] (Claim 3)

[1031] The system according to claim 1, which includes an interface for improving the evaluation of work proposals based on the worker's emotional information. [Explanation of Symbols]

[1032] 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 analyzing a received document using natural language processing technology and extracting important elements, A means to automatically generate optimal suggestions by referencing past relevant data based on the analyzed information, A means to create a plan based on the generated proposals and monitor progress in real time, Means of issuing notifications or warnings as needed, A means of providing an interface for uploading bidding specifications from a mobile device, A means of providing optimized proposals that show appropriate resource and time allocation based on specification analysis and past examples, A system that includes this.

2. The system according to claim 1, which manages the progress of each activity in project management using a work breakdown diagram based on the created hierarchical structure.

3. The system according to claim 1, including an interface that adjusts the proposed content based on feedback provided by the user.

Images