system

Abstract

To provide a system.SOLUTION: The system includes: means of reading electronic documents including public information of other parties and material providing information in a dialogue form; means of predicting at least one of the information request and the proposal request from the read electronic document; means of proposing optimization of workflow based on at least one of the predicted information request and the proposal request; and means of recognizing the emotion of the user and adjusting the content of the optimization proposal depending on the emotion recognized.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Responding to RFIs (Request for Information) / RFPs (Request for Proposals) is one of the most important aspects of proposal activities, and it is necessary to predict in advance what the content will be. However, this prediction is difficult, and it is a heavy workload. [Means for solving the problem]

[0005] We provide a system that interactively reads the other party's public information, IR, trends in documents presented by the information systems department, etc. in PDF format and predicts the RFI / RFP to be presented based on the contents. Furthermore, by presenting the prediction results to the user interactively and making suggestions to reduce the workload based on the prediction results, we reduce the workload of responding to RFI / RFP. [Brief explanation of the drawings]

[0006] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 2 is a sequence diagram showing a flow of processing in the data processing system according to the first embodiment of the first form example. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Embodiment 1. [Figure 13] FIG. 10 is a sequence diagram showing a processing flow of a data processing system in a second embodiment of the second form example. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Embodiment Example 2. [Figure 15] FIG. 10 is a sequence diagram showing the flow of processing in a data processing system according to a third embodiment of the third embodiment. [Figure 16]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Embodiment 3. [Figure 17] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when an emotion engine is combined. [Figure 19] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the second embodiment of the second form example when an emotion engine is combined. [Figure 20] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Form Example 2 when an emotion engine is combined. [Figure 21] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the third embodiment of the third form example when an emotion engine is combined. [Figure 22] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Form Example 3 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0007] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0008] First, the terms used in the following description will be explained.

[0009] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices 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), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0011] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0012] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0013] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0014] [First embodiment]

[0015] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0016] 1, a 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.

[0017] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0018] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0019] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the 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.

[0020] 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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0021] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0022] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0023] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

[0024] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0025] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0026] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0027] "Example 1"

[0028] The system of the present invention has a means for interactively reading public information from the other party, IR, trends in materials presented by the information systems department, etc., in PDF format. Specifically, this information is stored in a database and analyzed by an AI engine. The analysis results are used to predict the content of RFI / RFP.

[0029] "Example 2"

[0030] Furthermore, the system of the present invention has a means for presenting the prediction results to the user in an interactive format. Specifically, the prediction results generated by the AI ​​engine are presented to the user through a user interface. This allows the user to understand the contents of the RFI / RFP in advance and plan an appropriate response.

[0031] "Example 3"

[0032] Furthermore, the system of the present invention has a means for proposing ways to reduce workloads based on the prediction results. Specifically, the AI ​​engine proposes workflow optimization based on the prediction results. For example, if the contents of the RFI / RFP match a specific pattern, it is possible to propose countermeasures based on past success stories.

[0033] The processing flow of each embodiment will be described below.

[0034] "Example 1"

[0035] Step 1: Obtain the other party's public information, IR, and information systems department presentation materials in PDF format.

[0036] Step 2: Convert the acquired PDF into text data and store it in a database.

[0037] Step 3: The AI ​​engine analyzes the information in the database and predicts the content of the RFI / RFP.

[0038] "Example 2"

[0039] Step 1: Obtain the prediction results generated by the AI ​​engine.

[0040] Step 2: Present the obtained prediction results to the user through the user interface.

[0041] "Example 3"

[0042] Step 1: The AI ​​engine proposes workflow optimization based on the prediction results.

[0043] Step 2: Present the proposed workflow to the user and make suggestions to reduce the workload.

[0044] Example 1

[0045] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0046] The traditional process of creating Requests for Information (RFI) and Requests for Proposals (RFP) required a lot of time and effort to manually collect and analyze information, resulting in inefficiency and a heavy workload. Furthermore, there was a lack of effective ways to utilize the vast amount of data, such as publicly available information from the other party, public reports, and materials presented by the information systems department. This resulted in issues such as a decline in prediction accuracy and difficulty in creating appropriate proposals.

[0047] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0048] In this invention, the server includes means for interactively reading in electronic document format information disclosed by the other party, public reports, trends in materials presented by the information systems department, etc., means for storing these electronic documents in a database, means for using an AI engine to analyze the stored data, and means for predicting the content of a request for information / request for proposal based on the analysis results. This makes it possible to efficiently analyze large amounts of data and create a request for information or request for proposal with high prediction accuracy.

[0049] "Other party public information" refers to all information that companies and organizations make public, including, for example, press releases and information on official websites.

[0050] "Public reports" refers to official documents such as financial reports and performance reports that are periodically published by companies or organizations.

[0051] "Information systems department presentation materials" refers to technical documents and presentation materials prepared by the information systems department of a company or organization.

[0052] "Electronic document format" refers to documents stored in a digital format such as PDF or Word.

[0053] "Interactive" refers to the way in which a user interacts with a system.

[0054] A "database" refers to a system for efficiently storing, retrieving, and managing information.

[0055] An "artificial intelligence engine" refers to software that analyzes data using techniques such as machine learning and natural language processing.

[0056] A "Request for Information (RFI)" is a formal document issued by a business or organization to gather specific information.

[0057] A "Request for Proposal (RFP)" refers to a formal document issued by a business or organization to solicit proposals for a specific project or service.

[0058] This invention is a system that interactively reads electronic documents such as public information, public reports, and documents submitted by the information systems department, stores this information in a database, and analyzes it using an artificial intelligence engine. The analysis results are used to predict the contents of requests for information (RFIs) and requests for proposals (RFPs).

[0059] Hardware and software used

[0060] server

[0061] The server uses the following hardware and software:

[0062] Database management system: MySQL (registered trademark), PostgreSQL

[0063] Artificial Intelligence Engine: Generative AI model (e.g., OpenAI® GPT-4®)

[0064] PDF parsing library: Python library

[0065] File Storage System: Cloud Storage Service

[0066] Terminal

[0067] The terminal provides an interface for the user to communicate with the server. The following software is used:

[0068] Client application: Web browser, dedicated client app

[0069] Program processing

[0070] server

[0071] The server receives electronic documents uploaded by users and stores them in a file storage system. The metadata of the stored electronic documents is recorded in a database. The server then converts the electronic documents into text using a PDF parsing library and inputs it into a generative AI model. The generative AI model analyzes the input text and generates analysis results. The analysis results are stored in a database and later provided to the user.

[0072] Terminal

[0073] The terminal provides an interface for users to upload electronic documents. When the user selects an electronic document and clicks the upload button, the terminal sends the electronic document to the server. The terminal also obtains the analysis results from the server and displays them to the user. The user can predict the contents of a request for information or a request for proposal based on the analysis results.

[0074] User

[0075] Users upload electronic documents, such as public information from the other party, public reports, and materials presented by the information systems department, to the server via their terminal. They receive the analysis results and use them to predict the contents of requests for information and requests for proposals. For example, when a user inputs a prompt statement such as "What are the technical requirements for the next RFP?" into the generative AI model, the AI ​​engine provides a prediction based on the analysis results.

[0076] Specific examples

[0077] Prompt Sentence Examples

[0078] "What are the technical requirements for the next RFP?"

[0079] By inputting this prompt into a generative AI model, the AI ​​engine will provide a prediction based on the analysis results. For example, the AI ​​engine may return a prediction such as, "The next RFP will likely require the introduction of cloud computing."

[0080] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0081] Step 1:

[0082] Subject: User

[0083] Users upload electronic documents such as public information from the other party, public reports, and materials presented by the Information Systems Department to the server via their terminals. Using a browser or a dedicated client application, users select the electronic document from the file selection dialog and click the upload button.

[0084] Input: Electronic document (PDF file)

[0085] Output: Upload request to server

[0086] Specific operation: When the user clicks the "Upload" button, the terminal sends the selected electronic document to the server as an HTTP POST request.

[0087] Step 2:

[0088] Subject: Server

[0089] The server stores the received electronic document in a file storage system and records the metadata of the stored electronic document (such as file name, upload date and time, and user ID) in a database.

[0090] Input: Uploaded electronic document

[0091] Output: Save to file storage system, metadata recording to database

[0092] Specific operation: The server stores the electronic document in the file storage system and records the URL of the storage location in the database.

[0093] Step 3:

[0094] Subject: Server

[0095] The server converts the stored electronic document into text using a PDF parsing library, and then inputs the converted text into a generative AI model.

[0096] Input: Stored electronic document

[0097] Output: Text data

[0098] Specific operation: The server converts the electronic document into text using a PDF parsing library (e.g., a Python library).

[0099] Step 4:

[0100] Subject: Server

[0101] The server inputs text data into the generative AI model and obtains analysis results, including predicted content for requests for information (RFIs) and requests for proposals (RFPs).

[0102] Input: Text data

[0103] Output: Analysis results

[0104] Specific operation: The server inputs text data into a generative AI model (e.g., OpenAI GPT-4) and obtains the analysis results.

[0105] Step 5:

[0106] Subject: Server

[0107] The server stores the analysis results obtained from the generative AI model in a database, recording the content of the analysis results, the date and time of generation, and the ID of the related electronic document.

[0108] Input: Analysis results

[0109] Output: Saving analysis results to a database

[0110] Specific operation: The server saves the analysis results in the database in JSON format.

[0111] Step 6:

[0112] Subject: Terminal

[0113] The device retrieves the analysis results from the server and displays them to the user, who then views them using a browser or a dedicated client application.

[0114] Input: Request for analysis results

[0115] Output: Display of analysis results

[0116] Specific operation: The device sends an HTTP GET request to the server to obtain the analysis results, which are then displayed in HTML or JSON format.

[0117] Step 7:

[0118] Subject: User

[0119] The user inputs a prompt to the generative AI model and obtains a prediction result. For example, the user inputs a prompt such as, "What are the technical requirements for the next RFP?"

[0120] Input: prompt statement

[0121] Output: Prediction results

[0122] Specific operation: When the user enters a prompt and clicks the "Send" button, the device sends the prompt to the server, which then passes the prompt to the generative AI model, obtains the prediction result, and returns it to the user.

[0123] (Application example 1)

[0124] Next, a description will be given of Application Example 1 of Embodiment Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0125] Today's companies and individuals are required to predict security risks from a vast amount of information and take appropriate measures. However, this information is diverse, and manual analysis takes a great deal of time and effort. Furthermore, finding appropriate measures requires advanced expertise, which is difficult for average users. For this reason, there is a need for a system that can efficiently and accurately predict security risks and propose countermeasures.

[0126] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0127] In this invention, the server includes means for interactively reading the other party's public information, public information, trends in materials presented by the information systems department, etc. in PDF format, means for predicting information requests / requests for proposals to be presented from the contents of the PDF, means for analyzing security risks based on the prediction results, and means for proposing security measures based on the analysis results. This allows users to efficiently and accurately predict security risks and take appropriate measures.

[0128] "Other party public information" refers to information that a company or organization has made public to the outside world.

[0129] "Public Information" means information that is publicly accessible.

[0130] "Materials presented by the Information Systems Department" refers to materials prepared and presented by the Information Systems Department.

[0131] "PDF" stands for Portable Document Format, a file format for electronically storing and displaying documents.

[0132] "Interaction style" refers to the way in which a user and a system interact with each other.

[0133] An "information request" is a request for specific information.

[0134] "Request for Proposal" means a request for a specific proposal.

[0135] "Prediction" refers to predicting future events or situations in advance.

[0136] A "security risk" is a potential threat or danger to information or systems.

[0137] "Analysis" refers to the detailed analysis of data or information.

[0138] A "solution" is a proposed solution to a particular problem or risk.

[0139] The following system configuration will be described as an embodiment of the present invention.

[0140] System Configuration

[0141] Hardware and Software

[0142] Hardware: Smartphone

[0143] Software: Python, PDF parsing library, SQLite, OpenAI API

[0144] Processing flow

[0145] 1. PDF Import:

[0146] The server uses a PDF analysis library to read PDF files and extract the text, thereby obtaining the contents of the other party's public information, public information, and materials presented by the Information Systems Department as digital data.

[0147] 2. Database connection:

[0148] The server connects to an SQLite database using the sqlite3 library, which allows for efficient storage and management of extracted text data.

[0149] 3. Data Retention:

[0150] The server stores the extracted text in a database, allowing for centralized management of data required for subsequent analysis.

[0151] 4. AI analysis:

[0152] The server uses the openai library to send the extracted text to OpenAI's API for security risk prediction, which can identify risks more quickly and accurately than a user could do manually.

[0153] 5. Results display:

[0154] The server presents the analysis results to the user in an interactive format, allowing the user to easily understand the results and take appropriate measures.

[0155] Specific examples

[0156] For example, if a company's IR information mentions the introduction of a new cloud service, the server analyzes this information and predicts the security risks of the cloud service. It also suggests countermeasures such as the introduction of multi-factor authentication and regular security audits.

[0157] Prompt Sentence Examples

[0158] Analyze the following information to predict security risks:

[0159] Corporate IR information

[0160] Information Systems Department presentation materials

[0161] Other party public information

[0162] Based on the analysis results, please propose specific security risks and countermeasures.

[0163] In this way, users can efficiently and accurately predict security risks and take appropriate measures.

[0164] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0165] Step 1:

[0166] The server reads the PDF file. Specifically, it uses a PDF parsing library to open the PDF file and extract the text from each page. The input is the PDF file, and the output is the extracted text data, which is used for subsequent parsing.

[0167] Step 2:

[0168] The server connects to the SQLite database by opening the database file using the sqlite3 library. The input is the path to the database file, and the output is a database connection object, which is used to store and retrieve data.

[0169] Step 3:

[0170] The server saves the extracted text data in a database. Specifically, it uses a database connection object to insert the text data into a specific table in the database. The input is the extracted text data, and the output is the data saved in the database. This saved data is used for subsequent analysis processing.

[0171] Step 4:

[0172] The server sends the stored text data to the AI ​​engine for analysis. Specifically, it uses the openai library to send the text data to OpenAI's API and predicts security risks. The input is text data retrieved from the database, and the output is the analysis result from the AI ​​engine. This analysis result is presented to the user.

[0173] Step 5:

[0174] The server presents the analysis results to the user in an interactive format. Specifically, it displays the analysis results through a user interface and provides information in a format that is easy for the user to understand. The input is the analysis results from the AI ​​engine, and the output is the information presented to the user. Based on this information, the user can take appropriate security measures.

[0175] Example 2

[0176] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0177] Conventional request for information (RFI) and request for proposal (RFP) processing systems have the problem that users have to manually analyze large amounts of information and plan appropriate responses, which requires a great deal of time and effort. Another issue is that the interface used to provide prediction results to users is not intuitive, which means users are unable to fully utilize the results. Furthermore, there is a lack of proposals for reducing workloads based on the prediction results, and specific support for improving users' work efficiency is insufficient.

[0178] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for interactively reading in document format information disclosed by the other party, information disclosure, trends in materials presented by the information systems department, etc., a means for predicting information requests / proposal requests to be presented based on the content of the information, a means for generating prediction results using a generative AI model, and a means for interactively presenting the prediction results to the user through a user interface. This allows the user to efficiently analyze large amounts of information, utilize the prediction results through an intuitive interface, and receive proposals for reducing their workload.

[0179] "Information publicly available from the other party" refers to information that a company or organization has made public, such as press releases and the contents of official websites.

[0180] "Disclosure" refers to information that a company or organization makes public based on legal or regulatory requirements, including, for example, financial reports and annual reports.

[0181] "Information systems department presentation materials" refers to materials created by the information systems department of a company or organization and presented internally or externally, including, for example, system specifications and operation manuals.

[0182] "Document format" refers to information recorded in a format such as text or PDF.

[0183] "Conversational" refers to the way in which a user and a system interact with each other, including, for example, chatbots and interactive web interfaces.

[0184] A "Request for Information (RFI)" is a formal request issued by a business or organization to obtain specific information.

[0185] "Request for Proposal (RFP)" refers to a formal request issued by a business or organization to solicit proposals for a specific project or service.

[0186] "Predictive forecasting" refers to the analysis of current data and information to predict future events and outcomes.

[0187] A "generative AI model" refers to an algorithm or system that uses artificial intelligence technology to analyze data and create predictions or products.

[0188] "User interface" refers to the screens and operating means through which a user interacts with a system, including, for example, web applications and mobile applications.

[0189] "Reducing workload" refers to reducing the workload on users through streamlining and automation of work.

[0190] This invention is a system that generates prediction results using a generative AI model and presents the results to a user in an interactive format. Specific embodiments of this system are described below.

[0191] Hardware and software used

[0192] Hardware: Servers, user devices (PCs, smartphones, etc.)

[0193] Software: Generative AI models (e.g., GPT-4), user interfaces (e.g., web applications)

[0194] Data processing and calculation

[0195] Data Entry

[0196] A user uses a terminal to enter information for an RFI (Request for Information) or RFP (Request for Proposal). For example, the user enters, "Please provide me with the information to create a proposal for a new marketing campaign."

[0197] Data transmission

[0198] The device sends the input information to the server, converting it into an appropriate format and sending it to the server using a secure communication protocol (e.g., HTTPS).

[0199] Generate prediction results

[0200] The server inputs the received information into a generative AI model (e.g., GPT-4). The server formats the information into an appropriate format and calls the generative AI model's API. The generative AI model generates a prediction based on the input information. For example, the model may generate a prediction such as, "This campaign requires the following resources: advertising budget, target audience, and duration."

[0201] Presentation of results

[0202] The server sends the generated prediction results to the user interface. The server converts the prediction results into an appropriate format and calls the user interface's API. The user interface presents the prediction results to the user in an interactive format. The user can confirm the message "This campaign requires the following resources. Would you like to know more?" and click Details to get more information.

[0203] Specific examples

[0204] Prompt Sentence Examples

[0205] "Please provide us with information to create a proposal for a new marketing campaign."

[0206] "What are your sales forecasts for the next quarter?"

[0207] In this way, users can understand the contents of RFI / RFP in advance and plan appropriate responses. They can also receive proposals for reducing workload based on the prediction results, which is expected to improve work efficiency.

[0208] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0209] Step 1:

[0210] The user enters the information.

[0211] A user uses a device (PC or smartphone) to input information for an RFI (Request for Information) or RFP (Request for Proposal). For example, the user might input, "Please provide me with the information to create a proposal for a new marketing campaign." The input information is saved in text format on the device.

[0212] Step 2:

[0213] The terminal sends the input information to the server.

[0214] The terminal converts the user's input information into JSON format and sends it to the server using the HTTPS protocol. If the transmission is successful, the terminal displays a confirmation message saying "Information sent." The input data is sent to the server and received by the server.

[0215] Step 3:

[0216] The server inputs information into the generative AI model.

[0217] The server parses the received JSON data and sends a POST request to the API endpoint of the generative AI model. The request includes the information entered by the user. The server formats the data appropriately and inputs it into the generative AI model.

[0218] Step 4:

[0219] The generative AI model generates the predicted results.

[0220] The generative AI model receives the request and processes the data internally. After a few seconds, the model generates a prediction and returns it to the server. For example, the model may generate a prediction such as, "This campaign requires the following resources: advertising budget, target audience, and duration." The generated prediction is then returned to the server.

[0221] Step 5:

[0222] The server sends the prediction results to the user interface.

[0223] The server analyzes the prediction results received from the generative AI model and sends a POST request to the user interface API. The request contains the prediction results. The server converts the prediction results into an appropriate format and sends them to the user interface.

[0224] Step 6:

[0225] The user checks the prediction results.

[0226] The user interface receives the prediction results and displays them in the browser. The user can see the message "This campaign requires the following resources. Would you like to know more?" and click Details to get more information. The user can then plan appropriate actions based on the prediction results.

[0227] (Application example 2)

[0228] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0229] In conventional logistics centers, it was difficult to understand the contents of requests for information (RFI) and requests for proposals (RFP) in advance and plan appropriate responses. Furthermore, there was a lack of a way to present prediction results to users in an interactive format, which did not sufficiently reduce the workload.

[0230] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for interactively reading the other party's public information, requests for information, trends in materials presented by the information systems department, etc. in electronic documents, means for predicting the requests for information / requests for proposals to be presented based on the contents of the electronic documents, and means for interactively presenting the prediction results to the user. This makes it possible to interactively present the prediction results to the user at the logistics center using an application installed on a smartphone.

[0231] "Other party public information" refers to information that a company or organization has made public to the outside world.

[0232] A "RFI" is a request for specific information.

[0233] "Materials presented by the Information Systems Department" refers to materials prepared and presented by the Information Systems Department.

[0234] "Electronic document" means a document stored in digital form.

[0235] "Interaction style" refers to the way in which a user and a system interact with each other.

[0236] "Request for Information / Request for Proposal" means a request for specific information and a request for specific proposals.

[0237] "Prediction" means predicting future events or outcomes in advance.

[0238] "Prediction result" refers to information obtained as a result of prediction.

[0239] "User" means a person who uses the system.

[0240] "Work load reduction" means reducing the burden of work.

[0241] A "logistics center" is a facility that stores, sorts, and delivers goods.

[0242] A "smartphone" is a mobile phone that can connect to the Internet and use applications.

[0243] An "application" is software that realizes a specific function.

[0244] As an embodiment of the present invention, a system using an application installed on a smartphone at a logistics center will be described.

[0245] First, the server has a means for interactively reading electronic documents such as publicly disclosed information from the other party, requests for information, and trends in documents presented by the information systems department, allowing the server to efficiently collect and analyze this information.

[0246] Next, the server has a means for predicting requests for information (RFIs) and requests for proposals (RFPs) from the collected information. This means uses a generative AI model to predict the content of future RFIs / RFPs. Specifically, the server uses the OpenAI API to generate prediction results based on text entered by the user.

[0247] Furthermore, the server has a means for presenting the prediction results to the user in an interactive format, allowing the user to check the prediction results in real time through a smartphone application. The user interface presents the prediction results in an interactive format and supports the user in efficiently carrying out their work.

[0248] As a specific example, if a user enters, "I'm looking for a new logistics partner. What kind of proposals can I expect?", the server will use the generative AI model to present a predicted result: "Possible proposals that can be expected from a new logistics partner include cost reduction, shorter delivery times, and the introduction of a tracking system."

[0249] An example of a prompt is as follows:

[0250] "Anticipate what the RFI / RFP will say and present it in a conversational format: We're looking for a new logistics partner. What proposals can we expect?"

[0251] In this way, a system can be realized that supports the managers and staff of the logistics center in carrying out their work efficiently.

[0252] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0253] Step 1:

[0254] The server interactively reads electronic documents such as the other party's public information, requests for information, and trends in documents presented by the information systems department. These electronic documents are provided to the server as input. The server analyzes these documents and extracts the necessary information. The analyzed information is obtained as output.

[0255] Step 2:

[0256] The server predicts future Requests for Information (RFI) and Requests for Proposal (RFP) based on the information obtained in step 1. As input, the parsed information is provided to the server. The server uses a generative AI model (e.g., OpenAI API) to predict the content of future RFIs / RFPs. As output, the prediction results are obtained.

[0257] Step 3:

[0258] The server interactively presents the prediction results obtained in step 2 to the user. As input, the prediction results are provided to the server. The server interactively presents the prediction results to the user through a user interface. As output, the user can check the prediction results.

[0259] Step 4:

[0260] The user checks the prediction results presented by the server through a smartphone application. The prediction results from the server are provided to the smartphone as input. The user plans and responds to work based on the prediction results. The user's work plan and response are obtained as output.

[0261] Step 5:

[0262] When a user enters the details of a new request for information or proposal, the information is sent to the server via a smartphone application. The smartphone receives the information entered by the user as input. The server receives this information and performs another prediction. The output is a new prediction result.

[0263] In this way, a system is realized that supports the managers and staff of the logistics center in carrying out their work efficiently.

[0264] Example 3

[0265] Next, a description will be given of a third embodiment of the third embodiment. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0266] In the conventional workflow, it was difficult to predict the content of requests for information (RFI) and requests for proposals (RFP) in advance and propose optimal responses. In addition, business data was often collected and analyzed manually, making it difficult to efficiently reduce workloads. This resulted in insufficient efficiency and optimization of business operations, and there was a risk that the company's competitiveness would decline.

[0267] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0268] In this invention, the server includes a means for interactively reading public information from the other party, trends in information materials, etc. in electronic document format, a means for predicting information requests / proposal requests to be presented based on the content of the information, a means for collecting business data, a means for analyzing the collected business data, a means for generating prediction results based on the analysis results, and a means for proposing optimization of business flows based on the prediction results. This enables efficient collection and analysis of business data, and realizes proposals for optimal business flows based on the prediction results. This reduces work load and improves work efficiency.

[0269] "Other party public information" refers to information that a company or organization has made public.

[0270] "Information materials" are materials provided internally or externally by a company or organization.

[0271] "Electronic document format" means a document stored in a digital format.

[0272] "Interaction style" refers to the way in which a user and a system interact with each other.

[0273] An "information request" is a request for specific information.

[0274] "Request for Proposal" means a request for a specific proposal.

[0275] "Prediction" means predicting future events or situations in advance.

[0276] "Business data" refers to data related to the business of a company or organization.

[0277] "Collection" means gathering the necessary data and information.

[0278] "Analysis" means analyzing data or information to find meaning.

[0279] "Prediction results" refer to future predictions obtained based on the analysis.

[0280] "Business flow" refers to the procedures and processes for business progress.

[0281] An "optimization proposal" is a proposal for optimizing business flow.

[0282] The present invention is a system for reducing workload, in which a server, a terminal, and a user work in cooperation with each other. A specific embodiment of this system will be described below.

[0283] First, the server interactively reads publicly available information and trends in information materials in electronic document format, including common electronic document formats such as PDF and Word. The server then analyzes these documents using natural language processing technology and predicts requests for information (RFIs) and requests for proposals (RFPs) based on their content.

[0284] Next, the server collects business data from each department within the company, including the contents of past RFIs / RFPs, examples of successful and unsuccessful projects, and details of business processes. A relational database such as MySQL or PostgreSQL is used as the database.

[0285] The collected business data is preprocessed by the server and input into the AI ​​engine. The AI ​​engine analyzes the data using machine learning frameworks such as TENSORFLOW (registered trademark) and PyTorch. The purpose of the analysis is to find patterns and trends within the data. The AI ​​engine analyzes the data and extracts important features.

[0286] The server generates predictions based on the results of the AI ​​engine's analysis. These predictions include bottlenecks and risks in future business processes, as well as the likelihood of success. These predictions are provided to users in the form of dashboards and reports.

[0287] Furthermore, the server generates workflow optimization proposals based on the prediction results. For example, if the content of a specific RFI / RFP matches a pattern based on past successes, it will propose specific countermeasures. This allows users to take specific actions to reduce their workload.

[0288] As a concrete example, consider the case where a user receives an RFP for a new project. The server analyzes the RFP and proposes the optimal solution based on the success of similar projects in the past.

[0289] Example prompt sentence:

[0290] "We've received an RFP for a new project. Please analyze the RFP and recommend the best solution based on past successes."

[0291] In this way, the system makes optimal proposals for reducing the workload through collaboration between the server, terminal, and user. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0292] Step 1:

[0293] The server interactively reads publicly available information from the other party and trends in information materials in electronic document format. Electronic documents such as PDF and Word documents are provided as input. The server analyzes these documents using natural language processing technology and extracts important information. The analyzed information is obtained as output. Specifically, the server reads the documents, performs text extraction, and identifies keywords and phrases.

[0294] Step 2:

[0295] The server predicts requests for information (RFIs) and requests for proposals (RFPs) in advance from the analyzed information. The analyzed information obtained in step 1 is given as input. The server uses a machine learning model to compare it with past data and predict future RFIs / RFPs. The output is the predicted RFIs / RFPs. Specifically, the server applies the prediction model to generate the predicted results.

[0296] Step 3:

[0297] The server collects business data from each department within the company. As input, it receives the business data provided by each department. The server saves the data in a database and extracts the necessary data. As output, it obtains the collected business data. Specifically, the server connects to the database and retrieves the data.

[0298] Step 4:

[0299] The server analyzes the collected business data. The business data obtained in step 3 is given as input. The server analyzes the data using an AI engine and extracts important features. The analysis results are obtained as output. Specifically, the server preprocesses the data and inputs it into the AI ​​engine.

[0300] Step 5:

[0301] The server generates a prediction result based on the analysis result. The analysis result obtained in step 4 is given as input. The server applies the prediction model to make a prediction about future business flows. The prediction result is obtained as output. Specifically, the server executes the prediction model and aggregates the results.

[0302] Step 6:

[0303] The server makes a proposal for optimizing the workflow based on the prediction results. The prediction results obtained in step 5 are given as input. The server refers to past examples of success and failure and proposes the optimal workflow. The output is an optimization proposal. Specifically, the server generates the proposal and notifies the user.

[0304] Step 7:

[0305] The user receives the optimization proposal provided by the server and adjusts the workflow. The optimization proposal from the server is given as input. The user checks the proposal and takes the necessary action. The output is the adjusted workflow. In concrete terms, the user reviews and executes the workflow based on the proposal.

[0306] (Application example 3)

[0307] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0308] The work flow at conventional logistics centers was often poorly predicted for workloads, and they were unable to respond appropriately when workloads increased. Furthermore, the work flow was not optimized, making it difficult to operate efficiently. This resulted in work delays, increased costs, and a decline in overall work efficiency.

[0309] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes means for interactively reading the other party's public information, trends in information materials, etc. in electronic documents, means for predicting the information request / proposal to be presented based on the contents of the electronic documents, means for analyzing business data and predicting the workload, and means for proposing optimization of the business flow based on the prediction results. This makes it possible to accurately predict the workload at the logistics center and propose optimal countermeasures to reduce the workload.

[0310] "Publicly disclosed information by the other party" refers to information and materials made public by companies and organizations, including press releases, official websites, reports, etc.

[0311] "Information materials" are materials provided internally or externally by a company or organization, including presentations, reports, data sheets, etc.

[0312] "Electronic document" refers to a document stored in a digital format, including PDFs, Word documents, Excel sheets, etc.

[0313] "Conversational" refers to the way in which users and systems interact with each other, including chatbots and interactive user interfaces.

[0314] "Request for Information" means a document requesting the provision of specific information, including a Request for Information (RFI).

[0315] "Request for Proposal" means a document requesting the submission of a specific proposal, including an RFP (Request for Proposal).

[0316] "Business data" refers to data related to the business of a company or organization, including work records, inventory data, shipping data, etc.

[0317] "Business volume" refers to the total volume of business within a specific period, including the number of transactions, working hours, and shipping volume.

[0318] "Business flow" refers to a series of steps or processes that show how work progresses, and includes work instructions and process maps.

[0319] "Optimization proposals" refer to proposals for streamlining business processes, including resource reallocation and improvements to work procedures.

[0320] The system for implementing this invention aims to optimize the workflow at a logistics center. The system has the function of interactively reading trends in publicly available information and provided information documents in electronic form and predicting requests for information (RFIs) and requests for proposals (RFPs) in advance based on the content. It also has the function of analyzing business data and predicting workload. Furthermore, it has the function of proposing workflow optimization based on the prediction results.

[0321] Hardware and software used

[0322] Hardware: Smartphones, servers

[0323] Software: Python, Pandas, Scikit-learn

[0324] System configuration

[0325] 1. Data Loading: The server loads the other party's public information and information materials in electronic document format, including PDF and Word documents.

[0326] 2. Prediction of Requests for Information / Requests for Proposal: The server analyzes the content of the loaded electronic documents and predicts Requests for Information (RFI) and Requests for Proposal (RFP) in advance.

[0327] 3. Analysis of business data: The server analyzes the business data of the logistics center and predicts the volume of work. Business data includes work records, inventory data, shipping data, etc.

[0328] 4. Workflow optimization proposals: Based on the prediction results, the server makes proposals for optimizing workflows, including resource reallocation and improvements to work procedures.

[0329] 5. User interface: Prediction results and optimization suggestions are presented to the user in an interactive format using a smartphone.

[0330] Processing flow

[0331] The server first reads and analyzes the other party's publicly available information and provided materials in electronic document format. Next, it uses a generative AI model to predict requests for information (RFIs) and requests for proposals (RFPs) in advance. It also analyzes the logistics center's operational data and predicts workloads. Based on the prediction results, it makes proposals for optimizing the workflow and presents them to the user in an interactive format.

[0332] Specific examples

[0333] For example, suppose the business data for a logistics center is in the following format:

[0334] csv

[0335] feature1,feature2,feature3,target

[0336] 10, 20, 30, 100

[0337] 15, 25, 35, 150

[0338] 20, 30, 40, 200

[0339] Example prompts to input to a generative AI model:

[0340] Create a program that analyzes operational data from a logistics center and proposes optimizations to reduce workload. The data is provided in CSV format, with feature1, feature2, and feature3 as features and target as target. Based on the prediction results, propose appropriate measures to prevent workload from increasing.

[0341] In this way, the system can streamline the workflow of the logistics center and provide optimal solutions to reduce the workload.

[0342] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0343] Step 1:

[0344] The server reads the other party's public information and information materials in electronic document format. PDF and Word documents are provided as input. The server analyzes these documents and converts them into text data. The analyzed text data is obtained as output.

[0345] Step 2:

[0346] The server predicts Request for Information (RFI) and Request for Proposal (RFP) in advance based on the analyzed text data. The text data obtained in step 1 is used as input. The server uses a generative AI model to detect specific patterns and generate prediction results. The output is the predicted content of the RFI or RFP.

[0347] Step 3:

[0348] The server reads the business data of the logistics center. The business data is provided in CSV format as input. The server reads the data using Pandas and sets features and targets. The features and targets are obtained as output.

[0349] Step 4:

[0350] The server predicts workload based on the workload data. The features and targets obtained in step 3 are used as input. The server trains a RandomForestRegressor model using Scikit-learn to make predictions. The predicted workload is obtained as output.

[0351] Step 5:

[0352] The server makes optimization proposals for the business flow based on the prediction results. The prediction results obtained in step 4 are used as input. The server refers to past successes and generates optimization proposals such as resource reallocation and improvements to work procedures. The optimization proposals are obtained as output.

[0353] Step 6:

[0354] The device (smartphone) presents the prediction results and optimization proposals to the user in an interactive format. The prediction results and optimization proposals obtained in steps 2 and 5 are used as input. The device uses an interactive user interface to present information to the user and prompt them to take necessary actions. The output is the information received by the user and the corresponding action.

[0355] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0356] "Example 1"

[0357] One embodiment of the present invention combines a system that includes a means for interactively reading public information, investor relations, and trends in documents presented by the information systems department in PDF format, a means for predicting RFIs / RFPs based on the content of such information, and an emotion engine that recognizes the user's emotions. This emotion engine recognizes emotions from the user's tone of voice, facial expressions, and choice of words, and feeds that information back to the system. For example, if the system determines that the user is feeling stressed, it takes that information into account and provides more appropriate RFI / RFP predictions.

[0358] "Example 2"

[0359] In another embodiment of the present invention, the system according to claim 2 is a system in which the means for interactively presenting prediction results to the user is combined with an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's reactions in real time and adjusts the presented prediction results according to the emotions. For example, if the user expresses surprise, the system takes this information into account and adjusts the level of detail in the prediction results.

[0360] "Example 3"

[0361] In a further embodiment of the present invention, the system according to claim 3 is a system in which the means for proposing workload reduction based on the prediction result is combined with an emotion engine that recognizes the user's emotions. This emotion engine recognizes the user's emotions and adjusts the workload reduction proposals according to those emotions. For example, if the user expresses anxiety, the system takes that information into account and makes more specific workload reduction proposals.

[0362] The processing flow of each embodiment will be described below.

[0363] "Example 1"

[0364] Step 1: The system interactively reads the other party's public information, IR, trends in materials presented by the Information Systems Department, etc. in PDF format.

[0365] Step 2: Based on the information read, the system predicts the contents of the RFI / RFP.

[0366] Step 3: At the same time, the emotion engine recognizes the user's emotions from their tone of voice, facial expressions, and language.

[0367] Step 4: The emotion engine feeds back the recognized emotion information to the system, which takes that information into account to provide more appropriate RFI / RFP prediction results.

[0368] "Example 2"

[0369] Step 1: The system presents the prediction results to the user in an interactive format.

[0370] Step 2: The emotion engine analyzes user reactions in real time.

[0371] Step 3: The emotion engine adjusts the predictions the system makes depending on the emotion it recognizes.

[0372] "Example 3"

[0373] Step 1: The system makes suggestions for reducing workload based on the prediction results.

[0374] Step 2: The emotion engine recognizes the user's emotion.

[0375] Step 3: The emotion engine adjusts the workload reduction suggestions made by the system according to the recognized emotion.

[0376] Example 1

[0377] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0378] Conventional request for information (RFI) and request for proposal (RFP) prediction systems do not fully utilize trends in publicly available information, financial information, or materials presented by the information systems department. Furthermore, the prediction results are not adjusted to take user emotions into account, which means that users' stress and anxiety cannot be alleviated. Furthermore, the lack of proposals for reducing workload based on the prediction results makes it difficult to improve users' work efficiency.

[0379] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0380] In this invention, the server includes means for interactively reading in electronic documents such as publicly disclosed information from the other party, financial information, and trends in materials presented by the information systems department, means for predicting requests for information / proposals to be presented based on the contents of the electronic documents, emotion recognition means for recognizing the user's emotions, and means for adjusting the prediction results based on the information obtained from the emotion recognition means. This enables more accurate RFI / RFP predictions that take the user's emotions into consideration, and makes it possible to make proposals to reduce the user's stress and anxiety while also reducing their workload.

[0381] "Other party public information" is information that a company or organization has made publicly available and that is publicly accessible through websites, reports, etc.

[0382] "Financial information" refers to information that shows the financial status of a company or organization, and is data contained in financial reports, settlement reports, etc.

[0383] "Information Systems Department Presentation Materials" are documents created and presented by the information systems department of a company or organization, and include information on the system's operational status, plans, and technical details.

[0384] An "electronic document" is a document stored in a digital format, including formats such as PDF and Word files.

[0385] "Interactive" refers to an interface in which the user and the system exchange information with each other, in the form of questions and answers.

[0386] A Request for Information (RFI) is a document issued by a company or organization to a supplier or partner, requesting the provision of specific information.

[0387] A "Request for Proposal (RFP)" is a document issued by a company or organization to suppliers or partners requesting proposals for a specific project or service.

[0388] "Prediction" is the prediction of future events or outcomes based on past data and trends.

[0389] "Emotion recognition means" refers to technology for analyzing and recognizing a user's emotions, and refers to a system that analyzes facial expressions, tone of voice, choice of words, etc.

[0390] "Means for adjusting predicted results" refers to technology that modifies or adjusts predicted results based on the user's emotional information.

[0391] The system of the present invention includes a means for interactively reading public information from the other party, financial information, and trends in materials presented by the information systems department in electronic documents, a means for predicting the requests for information (RFI) / requests for proposals (RFP) that will be presented based on the contents of the electronic documents, an emotion recognition means for recognizing the emotions of the user, and a means for adjusting the prediction results based on the information obtained from the emotion recognition means.

[0392] Hardware and software used

[0393] Hardware: Servers, user devices (PCs, tablets, smartphones, etc.)

[0394] Software: PDF readers, database management systems (e.g., MySQL, PostgreSQL), AI engines (e.g., TensorFlow, PyTorch), emotion recognition engines (e.g., Affectiva, Microsoft® Azure® Emotion API)

[0395] Specific operation of the system

[0396] 1. Data collection and storage

[0397] The server collects the other party's public information, financial information, and materials presented by the information systems department from the Internet.

[0398] What it does: The server automatically downloads PDF files from a company's official website or publicly available investor relations page and stores them in a MySQL database.

[0399] 2. Data Analysis

[0400] The server passes the accumulated PDF files to an AI engine, which analyzes their contents.

[0401] Specific operation: The server uses TensorFlow to extract text from PDF files and uses natural language processing techniques to extract keywords and topics.

[0402] 3. Predicting the contents of RFI / RFP

[0403] The server applies a generative AI model to predict the content of the RFI / RFP based on the analysis results.

[0404] Specific operation: The server uses a generative AI model (e.g., GPT-3 (registered trademark)) that has learned from past RFI / RFP data to generate items that are likely to be included in the next RFP.

[0405] 4. User Emotion Recognition

[0406] The device collects the user's tone of voice, facial expressions, and language choices through a camera and microphone.

[0407] How it works: When a user uses the system, the device captures their facial expressions with a camera and records their tone of voice with a microphone. These are then analyzed using Affectiva's API to recognize the user's emotions.

[0408] 5. Feedback and Adjustments

[0409] The server adjusts the prediction results based on the user's emotional information.

[0410] Specific behavior: If the user is feeling stressed, the server generates additional information to explain the prediction result in more detail.

[0411] Examples and prompts

[0412] Example: A system that predicts the content of the next RFP based on a company's financial information

[0413] The server downloads the company's latest financial reports and stores them in a database.

[0414] An AI engine analyzes the contents of the report and lists items that are likely to be included in the next RFP.

[0415] When a user uses the system, the emotion recognition engine analyzes the user's stress level and adjusts the prediction results.

[0416] Example prompt sentence:

[0417] Use the company's most recent financial report to predict what items are likely to be included in the next RFP. If users are feeling stressed, adjust your predictions to take that information into account.

[0418] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0419] Step 1:

[0420] Data collection

[0421] Input: URLs and file paths of the other party's public information, financial information, and documents presented by the Information Systems Department

[0422] Specific behavior: The server downloads the PDF file from the specified URL or file path.

[0423] Data processing: Temporarily save downloaded PDF files.

[0424] Output: Downloaded PDF file

[0425] Step 2:

[0426] Data accumulation

[0427] Input: Downloaded PDF file

[0428] Specific operation: The server saves the downloaded PDF file in a MySQL database, along with its metadata (collection date and time, file name, and source URL).

[0429] Data processing: Store PDF files and their metadata in a database.

[0430] Output: PDF files and metadata stored in a database

[0431] Step 3:

[0432] PDF analysis

[0433] Input: PDF files stored in the database

[0434] Specific operation: The server extracts text from PDF files using TensorFlow.

[0435] Data processing: The extracted text is analyzed using natural language processing techniques to extract important keywords and topics.

[0436] Output: Extracted keywords and topics

[0437] Step 4:

[0438] Saving analysis results

[0439] Input: Extracted keywords and topics

[0440] Specific operation: The server stores the extracted keywords and topics in a database.

[0441] Data processing: Store keywords and topics in a database.

[0442] Output: Keywords and topics stored in a database

[0443] Step 5:

[0444] RFI / RFP Content Prediction

[0445] Input: Keywords or topics stored in the database

[0446] Specific operation: The server uses a generative AI model (e.g., GPT-3) that has learned from past RFI / RFP data to generate items that are likely to be included in the next RFP.

[0447] Data processing: Generative AI models are used to generate predictions.

[0448] Output: Predicted RFP items

[0449] Step 6:

[0450] Saving prediction results

[0451] Input: Predicted RFP items

[0452] Specific behavior: The server saves the generated RFP items in a database.

[0453] Data processing: Store the prediction results in a database.

[0454] Output: Prediction results stored in a database

[0455] Step 7:

[0456] Collecting Emotional Data

[0457] Input: User's tone of voice, facial expressions, and language

[0458] Specific operation: When a user uses the system, the device captures facial expressions with a camera and records the tone of voice with a microphone.

[0459] Data processing: Collected audio and video data is temporarily stored.

[0460] Output: Collected audio and video data

[0461] Step 8:

[0462] Emotion analysis

[0463] Input: Collected audio and video data

[0464] Specific operation: The device uses Affectiva's API to analyze the user's emotions from their facial expressions and tone of voice.

[0465] Data processing: Analyze emotional data using an emotion recognition engine.

[0466] Output: Parsed emotion data

[0467] Step 9:

[0468] Feedback and Adjustments

[0469] Input: Parsed sentiment data, predicted RFP items

[0470] Specific operation: The server adjusts the prediction result based on the user's emotional information. If the user is feeling stressed, it generates additional information to explain the prediction result in more detail.

[0471] Data processing: Correct and adjust prediction results based on emotion data.

[0472] Output: Adjusted prediction results

[0473] Step 10:

[0474] Providing adjustment results

[0475] Input: Adjusted forecast results

[0476] Specific operation: The server displays the adjusted RFP prediction results on the user's terminal.

[0477] Data processing: Display the adjustment results in a user-friendly format.

[0478] Output: Adjustment results provided to the user

[0479] (Application example 1)

[0480] Next, a description will be given of Application Example 1 of Embodiment Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0481] With conventional systems, it was difficult to efficiently analyze publicly available information, disclosure documents, and documents submitted by the information systems department, and to predict the content of requests for information (RFI) and requests for proposals (RFP) in advance. Furthermore, because the system provided prediction results without taking into account the user's emotional state, it could cause stress for the user, and there was a problem in that the system was unable to provide appropriate information.

[0482] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes means for interactively reading in electronic document format information disclosed by the other party, information disclosure materials, trends in materials presented by the information systems department, etc., means for predicting in advance the information request / proposal request to be presented from the content of the electronic document, emotion recognition means for recognizing the user's emotion, and means for adjusting the prediction result according to the user's emotional state. This makes it possible to predict an appropriate information request / proposal request taking into account the user's emotional state.

[0483] "Other party public information" refers to all information that companies and organizations make public to the outside world.

[0484] A "disclosure document" is a document that compiles information that a company or organization must make public for legal or business reasons.

[0485] "Information Systems Department Presentation Materials" refers to technical or business materials prepared by the Information Systems Department and presented internally or externally.

[0486] "Electronic document format" refers to documents stored in a digital format such as PDF or Word.

[0487] "Interactional" refers to the manner in which a user and a system interact with each other.

[0488] "Request for Information (RFI)" refers to a document issued seeking specific information.

[0489] "Request for Proposal (RFP)" means a document issued to solicit proposals for a particular project or service.

[0490] "Prediction" refers to predicting future events or outcomes.

[0491] "Emotion recognition means" refers to technology that recognizes emotions from the user's tone of voice, facial expressions, and choice of words.

[0492] "Means for adjusting prediction results" refers to technology that changes or optimizes prediction results depending on the user's emotional state.

[0493] A system for implementing the present invention has the following configuration.

[0494] First, the server has a means for interactively reading public information from the other party, disclosure materials, and trends in materials presented by the information systems department in electronic document format. This means is realized, for example, using a PDF reading library such as a PDF analysis library. The server stores this information in a database and analyzes it using an AI engine. The AI ​​engine uses OpenAI's API and uses a generative AI model to predict the content of requests for information (RFIs) and requests for proposals (RFPs) in advance.

[0495] Next, the server has an emotion recognition unit that recognizes the user's emotions. This unit is implemented using a custom library (e.g., emotion_recognition library) for recognizing emotions from audio files. It recognizes emotions from the user's tone of voice, facial expressions, and phrasing, and feeds that information back to the system.

[0496] Furthermore, the server has a means to adjust the prediction results according to the user's emotional state. For example, if it determines that the user is feeling stressed, it will simplify the prediction results and provide them in an easy-to-understand format. This adjustment is made based on the analysis results of the AI ​​engine.

[0497] A concrete example is the "Smart Factory Assistant" application used by factory operation managers. This application interactively reads various data within the factory (production plans, machine operation status, maintenance history, etc.) in PDF format, and an AI engine analyzes it to predict future production plans and the need for maintenance. Furthermore, it uses an emotion engine to recognize the emotional state of managers and engineers, and if they are feeling stressed, it provides more concise and easy-to-understand information.

[0498] An example of a prompt is as follows:

[0499] Analyze the text below and predict the contents of the RFI / RFP:

[0500] Production plan

[0501] October 2023: Increase production of product A by 20%

[0502] November 2023: Maintenance schedule for Product B

[0503] December 2023: Start of prototyping of new product C

[0504] Analysis results:

[0505] By inputting this prompt into OpenAI's API, analysis results can be obtained.

[0506] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0507] Step 1:

[0508] The server interactively reads the other party's public information, information disclosure materials, trends in materials presented by the Information Systems Department, etc. in electronic document format. Specifically, it uses a PDF analysis library to read PDF files and extract text. The input is the PDF file, and the output is the extracted text.

[0509] Step 2:

[0510] The server stores the extracted text in a database, which also contains data from past requests for information (RFIs) and requests for proposals (RFPs). The input is the extracted text, and the output is the text data stored in the database.

[0511] Step 3:

[0512] The server uses an AI engine to analyze the text data stored in the database. Specifically, it uses OpenAI's API to perform analysis using a generative AI model. The input is the text data stored in the database, and the output is prediction information as the analysis result.

[0513] Step 4:

[0514] The server analyzes the audio file with an emotion recognition means to recognize the user's emotions. Specifically, it uses the emotion_recognition library to recognize emotions from the audio file. The input is the audio file, and the output is the recognized emotion information.

[0515] Step 5:

[0516] The server adjusts the prediction result based on the recognized emotional information. For example, if it determines that the user is feeling stressed, it will simplify the prediction result and provide it in an easy-to-understand format. The input is the analysis result and emotional information, and the output is the adjusted prediction result.

[0517] Step 6:

[0518] The server interactively presents the adjusted prediction results to the user. Specifically, it displays the prediction results through a user interface. The input is the adjusted prediction results, and the output is the information presented to the user.

[0519] Example 2

[0520] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0521] Conventional prediction systems for requests for information (RFI) and requests for proposals (RFP) provide uniform information without considering the user's feelings, making it difficult to provide appropriate information according to the user's level of understanding and reaction. In addition, there is no function to adjust the level of detail of the prediction results, so there are cases where the system is unable to provide the information the user needs appropriately.

[0522] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0523] In this invention, the server includes means for interactively reading in electronic document format information disclosed by the other party, information disclosure materials, trends in materials presented by the information systems department, etc., means for predicting information requests / proposal requests to be presented from the contents of the electronic document, means for generating prediction results using a generative AI model, means for analyzing user emotions using an emotion engine that recognizes user emotions, means for presenting the prediction results to the user through a user interface, and means for adjusting the level of detail of the prediction results according to the user emotions. This makes it possible to provide appropriate information according to the user's emotions.

[0524] "Other party public information" refers to information that a company or organization has made public to the outside world.

[0525] "Information disclosure documents" refer to reports and presentation materials officially released by companies and organizations.

[0526] "Information Systems Department Presentation Materials" refers to materials created by the information systems department of a company or organization and presented internally or externally.

[0527] "Electronic document format" refers to documents stored in a digital format such as PDF or Word.

[0528] "Interaction" refers to the manner in which a user and a system interact with each other.

[0529] A "Request for Information (RFI)" is a document issued by a business or organization requesting specific information.

[0530] A "Request for Proposal (RFP)" is a document issued by a business or organization to solicit proposals for a specific project or service.

[0531] A "generative AI model" is an artificial intelligence model that has been trained using machine learning or deep learning to perform a specific task.

[0532] An "emotion engine" is a system that recognizes and analyzes emotions from a user's facial expressions, voice, etc.

[0533] A "user interface" refers to the screens and operating means that allow a user to interact with a system.

[0534] "Prediction results" refer to information about future events or situations generated by a generative AI model based on input data.

[0535] "Level of detail" refers to the degree of specificity or fineness of the information.

[0536] To implement the present invention, it is necessary to generate a system program according to the following procedure.

[0537] First, the server is equipped with a means for interactively reading the other party's public information, public information materials, trends in materials presented by the information systems department, etc. in electronic document format. This means uses a software library (e.g., Apache (registered trademark) PDFBox or Python-docx) for reading digital documents such as PDF and Word.

[0538] The server then has a means for predicting requests for information (RFIs) or requests for proposals (RFPs) from the content of the documents it has read. This is achieved using a generative AI model, which is built using a machine learning framework such as TensorFlow or PyTorch.

[0539] Furthermore, the server includes a user interface for presenting the generated prediction results to a user, which is developed using a front-end framework such as React or Vue.js.

[0540] The server also has an emotion engine that recognizes the user's emotions. This emotion engine is built using tools such as OpenCV and Emotion API, and analyzes emotions from the user's facial expressions and voice in real time.

[0541] As a concrete example, consider the case where a user enters the following prompt sentence:

[0542] "Predict what's in your next RFP. If users express surprise, adjust the level of detail."

[0543] The server receives the prompt and uses a generative AI model to generate a prediction. The emotion engine then analyzes the user's real-time reaction and adjusts the level of detail in the prediction if the user expresses surprise. For example, if the user expresses surprise, the system will omit detailed explanations and present only the main points.

[0544] In this way, users can understand the contents of requests for information (RFIs) and requests for proposals (RFPs) in advance and plan appropriate responses.

[0545] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0546] Step 1:

[0547] The user enters a prompt statement

[0548] The user uses a terminal to input a prompt into the system's input form. For example, they might input, "Please predict the content of the next RFP. If the user expresses surprise, adjust the level of detail." The input prompt is sent to the server as an HTTP request.

[0549] Input: prompt statement

[0550] Output: HTTP request

[0551] Step 2:

[0552] The server receives the prompt.

[0553] The server receives the HTTP request sent by the user and extracts the prompt text, which is then passed to the next processing step.

[0554] Input: HTTP request

[0555] Output: prompt statement

[0556] Step 3:

[0557] The server generates prediction results using an AI engine

[0558] The server passes the prompt sentence to a generative AI model, which is built using TensorFlow or PyTorch, for example, and generates a prediction result based on the prompt sentence.

[0559] Input: prompt statement

[0560] Output: Prediction results

[0561] Step 4:

[0562] The server analyzes the user's emotions using an emotion engine.

[0563] The server passes the user's real-time reactions to the emotion engine, which analyzes the user's emotions by analyzing their facial expressions and voice using OpenCV and Emotion API.

[0564] Input: Real-time user responses (facial expressions and voice)

[0565] Output: User emotion data

[0566] Step 5:

[0567] The server presents the prediction results through a user interface.

[0568] The server adjusts the level of detail in the prediction results based on the analysis results of the emotion engine. For example, if the user expresses surprise, the server omits detailed explanations and presents only the main points. The adjusted prediction results are then presented to the user through a user interface.

[0569] Input: Prediction results, user emotion data

[0570] Output: Adjusted prediction results

[0571] Step 6:

[0572] The user can review the prediction results and provide feedback if necessary.

[0573] The user can review the presented prediction results and provide feedback if necessary, which is then sent to the server and used to improve the system.

[0574] Input: Adjusted forecast results

[0575] Output: User feedback

[0576] (Application example 2)

[0577] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0578] In conventional self-driving vehicles, when providing users with predicted traffic and driving conditions, the information presented does not take the user's emotions into consideration, making it difficult for users to properly understand the information and use the vehicle with confidence.In addition, because the level of detail in the prediction results is uniform, there is also the problem of being unable to respond flexibly to the user's situation and emotions.

[0579] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0580] In this invention, the server includes means for interactively reading in PDF the other party's public information, IR, trends in materials presented by the information systems department, etc., means for predicting the RFI / RFP to be presented from the contents of the PDF, means for interactively presenting the prediction results to the user, means for combining an emotion engine that recognizes the user's emotions, means for adjusting the level of detail of the prediction results according to the user's emotions, and means for generating prediction results of traffic conditions and operation conditions in an autonomous vehicle and presenting them to the user in an interactive format. This enables flexible information presentation according to the user's emotions, allowing users to use autonomous vehicles with peace of mind.

[0581] "Other party public information" refers to information that a company or organization has publicly disclosed, including financial reports, press releases, and information on its official website.

[0582] "IR" stands for investor relations and refers to the information provision activities that companies undertake for investors.

[0583] "Information systems department presentation materials" refers to various materials created and presented by the information systems department of a company or organization, including system specifications, operation manuals, reports, etc.

[0584] "PDF" stands for Portable Document Format and refers to a file format for storing and distributing documents electronically.

[0585] "Interactive style" refers to the way in which a user and a system interact with each other, including text chat and voice interaction.

[0586] "RFI" is an abbreviation for Request for Information and refers to a request for information.

[0587] "RFP" stands for Request for Proposal and refers to a request for proposal.

[0588] "Prediction" refers to predicting future events or situations in advance.

[0589] "Prediction results" refer to results obtained through prior prediction.

[0590] "User interface" refers to the means by which a user interacts with a system, including screen displays and audio outputs.

[0591] An "emotion engine" refers to a system for recognizing and analyzing user emotions.

[0592] "Traffic conditions" refers to the traffic flow and congestion on roads.

[0593] "Operation status" refers to the status of vehicle operation, including the route traveled and the estimated arrival time.

[0594] "Level of detail" refers to the degree of specificity or fineness of the information.

[0595] An "autonomous vehicle" refers to a vehicle that drives autonomously using artificial intelligence and sensor technology.

[0596] The system for implementing this invention has the following configuration: First, the server is equipped with a means for interactively reading the other party's public information, IR, trends in materials presented by the information systems department, etc. in PDF format, allowing the server to efficiently collect and analyze the necessary information.

[0597] The server then has a means to predict future RFIs / RFPs based on the content of the requests. This uses a generative AI model to predict future requirements and requests for proposals based on the collected information, allowing users to plan appropriate responses in advance.

[0598] Furthermore, the server has a means for presenting the prediction results to the user in an interactive format. This means uses a dialogue engine such as Dialogflow, and provides the prediction results to the user through a user interface. The user can ask questions or give instructions through this interface, and the system will respond appropriately.

[0599] The server also incorporates an emotion engine that recognizes the user's emotions. This emotion engine uses emotion recognition technology such as OpenCV to analyze the user's facial expressions and voice data in real time, allowing it to adjust the level of detail in the prediction results according to the user's emotions.

[0600] Furthermore, the autonomous vehicle is equipped with a means for generating predicted results of traffic and driving conditions and presenting them to the user in an interactive format. This means uses an AI engine such as TensorFlow to predict traffic and driving conditions and provide them to the user.

[0601] For example, if the user expresses surprise, the system will increase the detail of the prediction results and provide more specific information. Conversely, if the user is relaxed, the system will provide concise information. For example, if the user asks, "What is the current traffic situation?" the system will respond, "There is currently traffic congestion on major roads. Would you like to suggest an alternative route?"

[0602] In this way, it becomes possible to present information flexibly according to the user's emotions, allowing users to use self-driving vehicles with peace of mind.

[0603] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0604] Step 1:

[0605] The server interactively reads PDF files such as publicly disclosed information from the other party, investor relations information, and trends in documents presented by the information systems department. PDF files are provided as input, which the server analyzes and converts into text data. The analyzed text data is obtained as output. PDF analysis software (e.g., PyMuPDF) is used for this process.

[0606] Step 2:

[0607] The server uses a generative AI model to predict RFI / RFP in advance based on the analyzed text data. The text data obtained in step 1 is provided as input, and the server inputs this into the generative AI model. The predicted RFI / RFP is obtained as output. TensorFlow is used for this process.

[0608] Step 3:

[0609] The server presents the prediction results to the user in an interactive format. The prediction results obtained in step 2 are provided as input, and the server inputs them into a dialogue engine (e.g., Dialogflow). As output, a dialogue-style message to be presented to the user is generated. This message is displayed to the user through the user interface.

[0610] Step 4:

[0611] The device uses a camera and microphone to collect facial and voice data to recognize the user's emotions. The device receives real-time video and audio from the user as input, and inputs this data into an emotion recognition engine (e.g., OpenCV). The output is the user's emotion data.

[0612] Step 5:

[0613] The server adjusts the level of detail of the prediction results based on the user's emotional data. The emotional data obtained in step 4 and the prediction results obtained in step 2 are provided as input, and the server adjusts the level of detail of the information based on this. The adjusted prediction results are obtained as output.

[0614] Step 6:

[0615] The server generates predicted traffic and driving conditions for autonomous vehicles and presents them to the user in an interactive format. Real-time traffic data obtained from the vehicle's sensors is provided as input, and the server inputs this into a generative AI model. The output is predicted traffic and driving conditions. This is then input into a dialogue engine, which generates a message to be presented to the user.

[0616] Step 7:

[0617] The user issues questions or instructions to the system through a dialogue-style interface. The user's question or instruction is provided as input, which the server analyzes and generates an appropriate response. The output is a response message to the user. For example, if the user asks, "What is the current traffic situation?" the server responds, "There is currently traffic congestion on the main road. Would you like to suggest an alternative route?"

[0618] Example 3

[0619] Next, a description will be given of a third embodiment of the third embodiment. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0620] Conventional workflow optimization systems have low prediction accuracy and do not take user emotions into account when making suggestions, which means that their effectiveness in reducing workloads is limited. Furthermore, it is difficult to properly analyze the information entered by users and provide specific suggestions based on past success stories.

[0621] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0622] In this invention, the server includes a means for interactively reading the other party's public information, trends in information materials, etc. in electronic documents, a means for predicting information requests to be presented from the contents of the electronic documents, a means for proposing workflow optimization based on the prediction results, and a means for recognizing the user's emotions and adjusting the proposal contents according to the emotions. This improves the accuracy of the prediction results and makes it possible to propose specific ways to reduce the workload taking into account the user's emotions.

[0623] "Other party public information" refers to information and materials made public by companies and organizations.

[0624] "Information materials" refers to various materials and data provided by companies and organizations.

[0625] "Electronic Document" means a document stored in digital form.

[0626] "Interactional" refers to the manner in which a user and a system interact with each other.

[0627] "Information Request" means a request for specific information.

[0628] "Prediction" refers to predicting future outcomes or situations.

[0629] "Business flow" refers to the procedures and processes for business progress.

[0630] "Optimization" refers to making something the most efficient and effective.

[0631] "User emotion" refers to the emotional state of the user who uses the system.

[0632] "Emotion awareness" refers to detecting and understanding a user's emotional state.

[0633] "Adjusting the content of the suggestions" refers to changing the content of the suggestions depending on the user's emotions and situation.

[0634] MODE FOR CARRYING OUT THE INVENTION

[0635] This invention is a system aimed at optimizing business flow and reducing workload, and operates in cooperation with a server, a terminal, and a user.

[0636] Server Operation

[0637] The server first reads the other party's public information and information materials in an interactive format as electronic documents. At this time, the server analyzes the documents using natural language processing technology and predicts information requests in advance. Specifically, it uses a generative AI model built using machine learning frameworks such as TensorFlow and PyTorch.

[0638] The server then proposes workflow optimization based on the prediction results. For example, by referencing past success stories, it generates a proposal such as, "Detailed requirements definition was the key to success, so we recommend that you also define detailed requirements this time."

[0639] Furthermore, the server recognizes the user's emotions and adjusts its suggestions accordingly. For example, if the user expresses anxiety, the server can analyze the user's emotions using an emotion engine and provide more specific suggestions, such as, "In addition to detailed requirements definitions, using a project management tool will make progress management easier."

[0640] Device behavior

[0641] The terminal receives input from the user and sends that data to the server. For example, if the user types, "I want to create an RFP for a new project," that data is sent from the terminal to the server. The terminal converts the data into the appropriate format and sends it using a secure communication protocol (e.g., HTTPS).

[0642] When the server returns a proposal for optimizing the workflow, the terminal displays the proposal to the user, who then checks the proposal and decides on the next action to take.

[0643] User Actions

[0644] Users input the details of RFIs and RFPs through their terminals. Once input is complete, the user can receive workflow optimization proposals from the server. Furthermore, if the system recognizes the user's emotions, the emotion engine will adjust the proposals based on that information. For example, if the user expresses anxiety, the system will make more specific and detailed proposals for reducing workloads.

[0645] Specific examples

[0646] For example, a user might input "I want to create an RFP for a new project" into their device. The device then sends that information to the server, which uses its AI engine to refer to past successes and propose the optimal solution. Specifically, the server might return a suggestion such as, "Since detailed requirements definition was the key to success in past projects, we recommend that you also define detailed requirements this time."

[0647] For example, if a user inputs "I want to create an RFP for a new project, but I'm feeling anxious," and expresses this feeling of anxiety, the emotion engine will recognize the user's anxiety and send that information to the server. Based on that information, the server will make more specific and detailed proposals for reducing workloads. For example, it might return a proposal such as, "In addition to detailed requirements definition, using a project management tool will make progress management easier."

[0648] Prompt Sentence Examples

[0649] "We're creating an RFP for a new project. Please suggest the best solution based on past successes."

[0650] "I would like to create an RFP for a new project, but I am worried. Please give me some concrete suggestions on how to reduce the workload." The flow of the specific process in the third embodiment will be described with reference to FIG.

[0651] Step 1:

[0652] The user uses the terminal to input the contents of the RFI or RFP. For example, they might input "I would like to create an RFP for a new project." The input data is saved in text format on the terminal.

[0653] Step 2:

[0654] The terminal converts the data entered by the user into JSON format and sends it to the server using the HTTPS protocol. The input data is the text "I would like to create an RFP for a new project," and the output data is a request in JSON format.

[0655] Step 3:

[0656] The server receives the JSON data sent from the device and stores it in a database. The received data is a JSON-formatted request, and the stored data is a database entry.

[0657] Step 4:

[0658] The server uses a generative AI model to analyze the received data. Specifically, it uses a machine learning framework such as TensorFlow or PyTorch to generate predictions based on past successes. The input data are database entries, and the output data are predictions.

[0659] Step 5:

[0660] The server then proposes workflow optimization based on the generated prediction results. For example, it generates a proposal such as, "Detailed requirements definition was the key to success, so we recommend that you also define detailed requirements this time." The input data are the prediction results, and the output data are optimization proposals.

[0661] Step 6:

[0662] The server uses an emotion engine to recognize the user's emotion. If the user indicates an anxious emotion in the input data, the emotion engine analyzes the emotion and generates emotion information called "anxiety." The input data is text containing the user's emotion, and the output data is the emotion information.

[0663] Step 7:

[0664] The server adjusts the proposal content based on the emotional information received from the emotion engine. For example, if the user expresses anxiety, the server will make a more specific proposal such as, "In addition to detailed requirements definition, using a project management tool will make progress management easier." The input data is emotional information, and the output data is the adjusted proposal.

[0665] Step 8:

[0666] The server sends the final proposal to the terminal. The terminal displays the received proposal to the user. The input data is the adjusted proposal, and the output data is the proposal displayed to the user. The user checks the displayed proposal and decides on the next action.

[0667] (Application example 3)

[0668] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0669] Conventional workflow optimization systems have the problem that they do not take into account the user's emotional state when proposing ways to reduce work load, and therefore do not make appropriate suggestions when the user is in a stressful situation. In addition, there is a lack of means to monitor and optimize the workflow within the factory in real time, making it difficult to operate efficiently.

[0670] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes a means for interactively reading in document format information such as publicly disclosed information from the other party, publicly disclosed information, and trends in materials presented by the information systems department, a means for predicting information requests / proposals to be presented based on the content of the information, a means for proposing workload reduction based on the prediction results, a means for combining an emotion engine that recognizes the user's emotions, a means for adjusting the workload reduction proposals according to the emotions, and a means for monitoring the workflow within the factory in real time and proposing optimization. This makes it possible to propose appropriate workload reductions that take the user's emotional state into consideration, thereby enabling efficient optimization of the workflow within the factory.

[0671] "Other party public information" refers to information that a company or organization has made public to the outside world.

[0672] "Information disclosure" refers to the act of a company or organization disclosing internal information to the outside world.

[0673] "Materials presented by the Information Systems Department" refers to materials prepared and presented by the Information Systems Department.

[0674] A "document format" is a format in which information is expressed as a document.

[0675] "Interactive style" refers to the way in which a system and a user exchange information through dialogue.

[0676] An "information request" is a request for specific information.

[0677] "Request for Proposal" means a request for specific proposals.

[0678] "Prediction" is the act of predicting future events or situations in advance.

[0679] "Work load reduction" means reducing the workload involved in work.

[0680] An "emotion engine" is an engine that recognizes and analyzes the user's emotions.

[0681] "Business flow" refers to the flow and procedures of business.

[0682] "Real time" refers to processing or responding immediately in the current ongoing time.

[0683] "Optimization" means making something the most efficient for a particular purpose.

[0684] The system for implementing this invention is configured as follows: First, the server has a means for interactively reading in document format information disclosed by the other party, information disclosure, trends in materials presented by the information systems department, etc. This means allows the server to collect and analyze various information provided from outside.

[0685] Next, the server has a means for predicting future requests for information / proposals based on the content of the requests, allowing the server to predict future requests for information and proposals based on past data and trends and prepare countermeasures in advance.

[0686] Furthermore, the server has a means for proposing work load reduction based on the prediction results. With this means, the server can propose work flow optimization and present specific actions to reduce the work load.

[0687] The server also has a means for combining an emotion engine that recognizes the user's emotions. This emotion engine allows the server to recognize and analyze the user's emotional state in real time. For example, if the user is feeling stressed, the server can adjust the proposal for reducing the workload based on that information.

[0688] Furthermore, the server has a means for monitoring the workflow within the factory in real time and proposing optimization. This means allows the server to constantly monitor the workflow within the factory and make optimization proposals to achieve efficient business operations.

[0689] As a specific example, consider a case where a work flow in a factory consists of two steps: "assembly of parts" and "quality inspection." The server uses an emotion engine to monitor the emotional state of workers, and if a worker is feeling stressed, it suggests that a robot take over the "quality inspection." In this way, the burden on workers can be reduced and work efficiency can be improved.

[0690] Examples of prompts to input to a generative AI model include:

[0691] The workflow in the factory consists of two steps: "assembly of parts" and "quality inspection." If workers are feeling stressed, propose that a robot take over the "quality inspection" step.

[0692] By inputting this prompt into a generative AI model, specific suggestions for reducing workload can be obtained.

[0693] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0694] Step 1:

[0695] The server interactively reads document-based information such as public information from the other party, information disclosure, and trends in materials presented by the Information Systems Department. The input includes externally provided document data such as PDFs and text files. The server analyzes this document data and extracts important information. The output is the analyzed information.

[0696] Step 2:

[0697] The server predicts information requests / requests for proposals in advance based on the information obtained in step 1. The inputs are the analyzed information and past data. The server uses machine learning algorithms to predict future information requests and proposal requests. The output is the predicted results.

[0698] Step 3:

[0699] The server proposes workload reduction measures based on the prediction results. The input is the prediction results obtained in step 2. The server proposes workflow optimization and generates specific workload reduction measures. The output is a proposal for workload reduction.

[0700] Step 4:

[0701] The server monitors the user's emotional state in real time using an emotion engine that recognizes the user's emotions. The inputs are the user's facial expressions and voice data. The server analyzes the user's emotions using an emotion recognition algorithm. The output is the user's emotional state.

[0702] Step 5:

[0703] The server adjusts the workload reduction proposal based on the user's emotional state obtained in step 4. The inputs are the user's emotional state and the workload reduction proposal obtained in step 3. The server adjusts the proposal content according to the emotional state. The output is the adjusted workload reduction proposal.

[0704] Step 6:

[0705] The server monitors the workflow within the factory in real time and proposes optimization. The input is real-time data obtained from sensors and robots within the factory. The server analyzes this data and proposes optimization of the workflow. The output is a proposal for an optimized workflow.

[0706] Step 7:

[0707] The user receives proposals for reducing workloads and optimizing workflows provided by the server and reflects them in their actual work. The input is the proposals from the server. The user uses these to adjust work and operate robots. The output is more efficient business operations.

[0708] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0709] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0710] Another example of generative AI is Gemini (registered trademark) (Internet search engine). <url: https: gemini.google.com ?hl="ja">) are mentioned.

[0711] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0712] [Second embodiment]

[0713] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0714] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0715] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0716] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0717] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0718] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0719] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0720] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0721] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0722] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0723] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0724] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0725] "Example 1"

[0726] The system of the present invention has a means for interactively reading public information from the other party, IR, trends in materials presented by the information systems department, etc., in PDF format. Specifically, this information is stored in a database and analyzed by an AI engine. The analysis results are used to predict the content of RFI / RFP.

[0727] "Example 2"

[0728] Furthermore, the system of the present invention has a means for presenting the prediction results to the user in an interactive format. Specifically, the prediction results generated by the AI ​​engine are presented to the user through a user interface. This allows the user to understand the contents of the RFI / RFP in advance and plan an appropriate response.

[0729] "Example 3"

[0730] Furthermore, the system of the present invention has a means for proposing ways to reduce workloads based on the prediction results. Specifically, the AI ​​engine proposes workflow optimization based on the prediction results. For example, if the contents of the RFI / RFP match a specific pattern, it is possible to propose countermeasures based on past success stories.

[0731] The processing flow of each embodiment will be described below.

[0732] "Example 1"

[0733] Step 1: Obtain the other party's public information, IR, and information systems department presentation materials in PDF format.

[0734] Step 2: Convert the acquired PDF into text data and store it in a database.

[0735] Step 3: The AI ​​engine analyzes the information in the database and predicts the content of the RFI / RFP.

[0736] "Example 2"

[0737] Step 1: Obtain the prediction results generated by the AI ​​engine.

[0738] Step 2: Present the obtained prediction results to the user through the user interface.

[0739] "Example 3"

[0740] Step 1: The AI ​​engine proposes workflow optimization based on the prediction results.

[0741] Step 2: Present the proposed workflow to the user and make suggestions to reduce the workload.

[0742] Example 1

[0743] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0744] The traditional process of creating Requests for Information (RFI) and Requests for Proposals (RFP) required a lot of time and effort to manually collect and analyze information, resulting in inefficiency and a heavy workload. Furthermore, there was a lack of effective ways to utilize the vast amount of data, such as publicly available information from the other party, public reports, and materials presented by the information systems department. This resulted in issues such as a decline in prediction accuracy and difficulty in creating appropriate proposals.

[0745] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0746] In this invention, the server includes means for interactively reading in electronic document format information disclosed by the other party, public reports, trends in materials presented by the information systems department, etc., means for storing these electronic documents in a database, means for using an AI engine to analyze the stored data, and means for predicting the content of a request for information / request for proposal based on the analysis results. This makes it possible to efficiently analyze large amounts of data and create a request for information or request for proposal with high prediction accuracy.

[0747] "Other party public information" refers to all information that companies and organizations make public, including, for example, press releases and information on official websites.

[0748] "Public reports" refers to official documents such as financial reports and performance reports that are periodically published by companies or organizations.

[0749] "Information systems department presentation materials" refers to technical documents and presentation materials prepared by the information systems department of a company or organization.

[0750] "Electronic document format" refers to documents stored in a digital format such as PDF or Word.

[0751] "Interactive" refers to the way in which a user interacts with a system.

[0752] A "database" refers to a system for efficiently storing, retrieving, and managing information.

[0753] An "artificial intelligence engine" refers to software that analyzes data using techniques such as machine learning and natural language processing.

[0754] A "Request for Information (RFI)" is a formal document issued by a business or organization to gather specific information.

[0755] A "Request for Proposal (RFP)" refers to a formal document issued by a business or organization to solicit proposals for a specific project or service.

[0756] This invention is a system that interactively reads electronic documents such as public information, public reports, and documents submitted by the information systems department, stores this information in a database, and analyzes it using an artificial intelligence engine. The analysis results are used to predict the contents of requests for information (RFIs) and requests for proposals (RFPs).

[0757] Hardware and software used

[0758] server

[0759] The server uses the following hardware and software:

[0760] Database management systems: MySQL, PostgreSQL

[0761] Artificial Intelligence Engine: Generative AI models (e.g., OpenAI GPT-4)

[0762] PDF Parsing Library: Python Library

[0763] File Storage System: Cloud Storage Service

[0764] Terminal

[0765] The terminal provides an interface for the user to communicate with the server. The following software is used:

[0766] Client application: Web browser, dedicated client app

[0767] Program processing

[0768] server

[0769] The server receives electronic documents uploaded by users and stores them in a file storage system. The metadata of the stored electronic documents is recorded in a database. The server then converts the electronic documents into text using a PDF parsing library and inputs it into a generative AI model. The generative AI model analyzes the input text and generates analysis results. The analysis results are stored in a database and later provided to the user.

[0770] Terminal

[0771] The terminal provides an interface for users to upload electronic documents. When the user selects an electronic document and clicks the upload button, the terminal sends the electronic document to the server. The terminal also obtains the analysis results from the server and displays them to the user. The user can predict the contents of a request for information or a request for proposal based on the analysis results.

[0772] User

[0773] Users upload electronic documents, such as public information from the other party, public reports, and materials presented by the information systems department, to the server via their terminal. They receive the analysis results and use them to predict the contents of requests for information and requests for proposals. For example, when a user inputs a prompt statement such as "What are the technical requirements for the next RFP?" into the generative AI model, the AI ​​engine provides a prediction based on the analysis results.

[0774] Specific examples

[0775] Prompt Sentence Examples

[0776] "What are the technical requirements for the next RFP?"

[0777] By inputting this prompt into a generative AI model, the AI ​​engine will provide a prediction based on the analysis results. For example, the AI ​​engine may return a prediction such as, "The next RFP will likely require the introduction of cloud computing."

[0778] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0779] Step 1:

[0780] Subject: User

[0781] Users upload electronic documents such as public information from the other party, public reports, and materials presented by the Information Systems Department to the server via their terminals. Using a browser or a dedicated client application, users select the electronic document from the file selection dialog and click the upload button.

[0782] Input: Electronic document (PDF file)

[0783] Output: Upload request to server

[0784] Specific operation: When the user clicks the "Upload" button, the terminal sends the selected electronic document to the server as an HTTP POST request.

[0785] Step 2:

[0786] Subject: Server

[0787] The server stores the received electronic document in a file storage system and records the metadata of the stored electronic document (such as file name, upload date and time, and user ID) in a database.

[0788] Input: Uploaded electronic document

[0789] Output: Save to file storage system, metadata recording to database

[0790] Specific operation: The server stores the electronic document in the file storage system and records the URL of the storage location in the database.

[0791] Step 3:

[0792] Subject: Server

[0793] The server converts the stored electronic document into text using a PDF parsing library, and then inputs the converted text into a generative AI model.

[0794] Input: Stored electronic document

[0795] Output: Text data

[0796] Specific operation: The server converts the electronic document into text using a PDF parsing library (e.g., a Python library).

[0797] Step 4:

[0798] Subject: Server

[0799] The server inputs text data into the generative AI model and obtains analysis results, including predicted content for requests for information (RFIs) and requests for proposals (RFPs).

[0800] Input: Text data

[0801] Output: Analysis results

[0802] Specific operation: The server inputs text data into a generative AI model (e.g., OpenAI GPT-4) and obtains the analysis results.

[0803] Step 5:

[0804] Subject: Server

[0805] The server stores the analysis results obtained from the generative AI model in a database, recording the content of the analysis results, the date and time of generation, and the ID of the related electronic document.

[0806] Input: Analysis results

[0807] Output: Saving analysis results to a database

[0808] Specific operation: The server saves the analysis results in the database in JSON format.

[0809] Step 6:

[0810] Subject: Terminal

[0811] The device retrieves the analysis results from the server and displays them to the user, who then views them using a browser or a dedicated client application.

[0812] Input: Request for analysis results

[0813] Output: Display of analysis results

[0814] Specific operation: The device sends an HTTP GET request to the server to obtain the analysis results, which are then displayed in HTML or JSON format.

[0815] Step 7:

[0816] Subject: User

[0817] The user inputs a prompt to the generative AI model and obtains a prediction result. For example, the user inputs a prompt such as, "What are the technical requirements for the next RFP?"

[0818] Input: prompt statement

[0819] Output: Prediction results

[0820] Specific operation: When the user enters a prompt and clicks the "Send" button, the device sends the prompt to the server, which then passes the prompt to the generative AI model, obtains the prediction result, and returns it to the user.

[0821] (Application example 1)

[0822] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0823] Today's companies and individuals are required to predict security risks from a vast amount of information and take appropriate measures. However, this information is diverse, and manual analysis takes a great deal of time and effort. Furthermore, finding appropriate measures requires advanced expertise, which is difficult for average users. For this reason, there is a need for a system that can efficiently and accurately predict security risks and propose countermeasures.

[0824] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0825] In this invention, the server includes means for interactively reading the other party's public information, public information, trends in materials presented by the information systems department, etc. in PDF format, means for predicting information requests / requests for proposals to be presented from the contents of the PDF, means for analyzing security risks based on the prediction results, and means for proposing security measures based on the analysis results. This allows users to efficiently and accurately predict security risks and take appropriate measures.

[0826] "Other party public information" refers to information that a company or organization has made public to the outside world.

[0827] "Public Information" means information that is publicly accessible.

[0828] "Materials presented by the Information Systems Department" refers to materials prepared and presented by the Information Systems Department.

[0829] "PDF" stands for Portable Document Format, a file format for electronically storing and displaying documents.

[0830] "Interaction style" refers to the way in which a user and a system interact with each other.

[0831] An "information request" is a request for specific information.

[0832] "Request for Proposal" means a request for a specific proposal.

[0833] "Prediction" refers to predicting future events or situations in advance.

[0834] A "security risk" is a potential threat or danger to information or systems.

[0835] "Analysis" refers to the detailed analysis of data or information.

[0836] A "solution" is a proposed solution to a particular problem or risk.

[0837] The following system configuration will be described as an embodiment of the present invention.

[0838] System Configuration

[0839] Hardware and Software

[0840] Hardware: Smartphone

[0841] Software: Python, PDF parsing library, SQLite, OpenAI API

[0842] Processing flow

[0843] 1. PDF Import:

[0844] The server uses a PDF analysis library to read PDF files and extract the text, thereby obtaining the contents of the other party's public information, public information, and materials presented by the Information Systems Department as digital data.

[0845] 2. Database connection:

[0846] The server connects to an SQLite database using the sqlite3 library, which allows for efficient storage and management of extracted text data.

[0847] 3. Data Retention:

[0848] The server stores the extracted text in a database, allowing for centralized management of data required for subsequent analysis.

[0849] 4. AI analysis:

[0850] The server uses the openai library to send the extracted text to OpenAI's API for security risk prediction, which can identify risks more quickly and accurately than a user could do manually.

[0851] 5. Results display:

[0852] The server presents the analysis results to the user in an interactive format, allowing the user to easily understand the results and take appropriate measures.

[0853] Specific examples

[0854] For example, if a company's IR information mentions the introduction of a new cloud service, the server analyzes this information and predicts the security risks of the cloud service. It also suggests countermeasures such as the introduction of multi-factor authentication and regular security audits.

[0855] Prompt Sentence Examples

[0856] Analyze the following information to predict security risks:

[0857] Corporate IR information

[0858] Information Systems Department presentation materials

[0859] Other party public information

[0860] Based on the analysis results, please propose specific security risks and countermeasures.

[0861] In this way, users can efficiently and accurately predict security risks and take appropriate measures.

[0862] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0863] Step 1:

[0864] The server reads the PDF file. Specifically, it uses a PDF parsing library to open the PDF file and extract the text from each page. The input is the PDF file, and the output is the extracted text data, which is used for subsequent parsing.

[0865] Step 2:

[0866] The server connects to the SQLite database by opening the database file using the sqlite3 library. The input is the path to the database file, and the output is a database connection object, which is used to store and retrieve data.

[0867] Step 3:

[0868] The server saves the extracted text data in a database. Specifically, it uses a database connection object to insert the text data into a specific table in the database. The input is the extracted text data, and the output is the data saved in the database. This saved data is used for subsequent analysis processing.

[0869] Step 4:

[0870] The server sends the stored text data to the AI ​​engine for analysis. Specifically, it uses the openai library to send the text data to OpenAI's API and predicts security risks. The input is text data retrieved from the database, and the output is the analysis result from the AI ​​engine. This analysis result is presented to the user.

[0871] Step 5:

[0872] The server presents the analysis results to the user in an interactive format. Specifically, it displays the analysis results through a user interface and provides information in a format that is easy for the user to understand. The input is the analysis results from the AI ​​engine, and the output is the information presented to the user. Based on this information, the user can take appropriate security measures.

[0873] Example 2

[0874] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0875] Conventional request for information (RFI) and request for proposal (RFP) processing systems have the problem that users have to manually analyze large amounts of information and plan appropriate responses, which requires a great deal of time and effort. Another issue is that the interface used to provide prediction results to users is not intuitive, which means users are unable to fully utilize the results. Furthermore, there is a lack of proposals for reducing workloads based on the prediction results, and specific support for improving users' work efficiency is insufficient.

[0876] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for interactively reading in document format information disclosed by the other party, information disclosure, trends in materials presented by the information systems department, etc., a means for predicting information requests / proposal requests to be presented based on the content of the information, a means for generating prediction results using a generative AI model, and a means for interactively presenting the prediction results to the user through a user interface. This allows the user to efficiently analyze large amounts of information, utilize the prediction results through an intuitive interface, and receive proposals for reducing their workload.

[0877] "Information publicly available from the other party" refers to information that a company or organization has made public, such as press releases and the contents of official websites.

[0878] "Disclosure" refers to information that a company or organization makes public based on legal or regulatory requirements, including, for example, financial reports and annual reports.

[0879] "Information systems department presentation materials" refers to materials created by the information systems department of a company or organization and presented internally or externally, including, for example, system specifications and operation manuals.

[0880] "Document format" refers to information recorded in a format such as text or PDF.

[0881] "Conversational" refers to the way in which a user and a system interact with each other, including, for example, chatbots and interactive web interfaces.

[0882] A "Request for Information (RFI)" is a formal request issued by a business or organization to obtain specific information.

[0883] "Request for Proposal (RFP)" refers to a formal request issued by a business or organization to solicit proposals for a specific project or service.

[0884] "Predictive forecasting" refers to the analysis of current data and information to predict future events and outcomes.

[0885] A "generative AI model" refers to an algorithm or system that uses artificial intelligence technology to analyze data and create predictions or products.

[0886] "User interface" refers to the screens and operating means through which a user interacts with a system, including, for example, web applications and mobile applications.

[0887] "Reducing workload" refers to reducing the workload on users through streamlining and automation of work.

[0888] This invention is a system that generates prediction results using a generative AI model and presents the results to a user in an interactive format. Specific embodiments of this system are described below.

[0889] Hardware and software used

[0890] Hardware: Servers, user devices (PCs, smartphones, etc.)

[0891] Software: Generative AI models (e.g., GPT-4), user interfaces (e.g., web applications)

[0892] Data processing and calculation

[0893] Data Entry

[0894] A user uses a terminal to enter information for an RFI (Request for Information) or RFP (Request for Proposal). For example, the user enters, "Please provide me with the information to create a proposal for a new marketing campaign."

[0895] Data transmission

[0896] The device sends the input information to the server, converting it into an appropriate format and sending it to the server using a secure communication protocol (e.g., HTTPS).

[0897] Generate prediction results

[0898] The server inputs the received information into a generative AI model (e.g., GPT-4). The server formats the information into an appropriate format and calls the generative AI model's API. The generative AI model generates a prediction based on the input information. For example, the model may generate a prediction such as, "This campaign requires the following resources: advertising budget, target audience, and duration."

[0899] Presentation of results

[0900] The server sends the generated prediction results to the user interface. The server converts the prediction results into an appropriate format and calls the user interface's API. The user interface presents the prediction results to the user in an interactive format. The user can confirm the message "This campaign requires the following resources. Would you like to know more?" and click Details to get more information.

[0901] Specific examples

[0902] Prompt Sentence Examples

[0903] "Please provide us with information to create a proposal for a new marketing campaign."

[0904] "What are your sales forecasts for the next quarter?"

[0905] In this way, users can understand the contents of RFI / RFP in advance and plan appropriate responses. They can also receive proposals for reducing workload based on the prediction results, which is expected to improve work efficiency.

[0906] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0907] Step 1:

[0908] The user enters the information.

[0909] A user uses a device (PC or smartphone) to input information for an RFI (Request for Information) or RFP (Request for Proposal). For example, the user might input, "Please provide me with the information to create a proposal for a new marketing campaign." The input information is saved in text format on the device.

[0910] Step 2:

[0911] The terminal sends the input information to the server.

[0912] The terminal converts the user's input information into JSON format and sends it to the server using the HTTPS protocol. If the transmission is successful, the terminal displays a confirmation message saying "Information sent." The input data is sent to the server and received by the server.

[0913] Step 3:

[0914] The server inputs information into the generative AI model.

[0915] The server parses the received JSON data and sends a POST request to the API endpoint of the generative AI model. The request includes the information entered by the user. The server formats the data appropriately and inputs it into the generative AI model.

[0916] Step 4:

[0917] The generative AI model generates the predicted results.

[0918] The generative AI model receives the request and processes the data internally. After a few seconds, the model generates a prediction and returns it to the server. For example, the model may generate a prediction such as, "This campaign requires the following resources: advertising budget, target audience, and duration." The generated prediction is then returned to the server.

[0919] Step 5:

[0920] The server sends the prediction results to the user interface.

[0921] The server analyzes the prediction results received from the generative AI model and sends a POST request to the user interface API. The request contains the prediction results. The server converts the prediction results into an appropriate format and sends them to the user interface.

[0922] Step 6:

[0923] The user checks the prediction results.

[0924] The user interface receives the prediction results and displays them in the browser. The user can see the message "This campaign requires the following resources. Would you like to know more?" and click Details to get more information. The user can then plan appropriate actions based on the prediction results.

[0925] (Application example 2)

[0926] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0927] In conventional logistics centers, it was difficult to understand the contents of requests for information (RFI) and requests for proposals (RFP) in advance and plan appropriate responses. Furthermore, there was a lack of a way to present prediction results to users in an interactive format, which did not sufficiently reduce the workload.

[0928] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for interactively reading the other party's public information, requests for information, trends in materials presented by the information systems department, etc. in electronic documents, means for predicting the requests for information / requests for proposals to be presented based on the contents of the electronic documents, and means for interactively presenting the prediction results to the user. This makes it possible to interactively present the prediction results to the user at the logistics center using an application installed on a smartphone.

[0929] "Other party public information" refers to information that a company or organization has made public to the outside world.

[0930] A "RFI" is a request for specific information.

[0931] "Materials presented by the Information Systems Department" refers to materials prepared and presented by the Information Systems Department.

[0932] "Electronic document" means a document stored in digital form.

[0933] "Interaction style" refers to the way in which a user and a system interact with each other.

[0934] "Request for Information / Request for Proposal" means a request for specific information and a request for specific proposals.

[0935] "Prediction" means predicting future events or outcomes in advance.

[0936] "Prediction result" refers to information obtained as a result of prediction.

[0937] "User" means a person who uses the system.

[0938] "Work load reduction" means reducing the burden of work.

[0939] A "logistics center" is a facility that stores, sorts, and delivers goods.

[0940] A "smartphone" is a mobile phone that can connect to the Internet and use applications.

[0941] An "application" is software that realizes a specific function.

[0942] As an embodiment of the present invention, a system using an application installed on a smartphone at a logistics center will be described.

[0943] First, the server has a means for interactively reading electronic documents such as publicly disclosed information from the other party, requests for information, and trends in documents presented by the information systems department, allowing the server to efficiently collect and analyze this information.

[0944] Next, the server has a means for predicting requests for information (RFIs) and requests for proposals (RFPs) from the collected information. This means uses a generative AI model to predict the content of future RFIs / RFPs. Specifically, the server uses the OpenAI API to generate prediction results based on text entered by the user.

[0945] Furthermore, the server has a means for presenting the prediction results to the user in an interactive format, allowing the user to check the prediction results in real time through a smartphone application. The user interface presents the prediction results in an interactive format and supports the user in efficiently carrying out their work.

[0946] As a specific example, if a user enters, "I'm looking for a new logistics partner. What kind of proposals can I expect?", the server will use the generative AI model to present a predicted result: "Possible proposals that can be expected from a new logistics partner include cost reduction, shorter delivery times, and the introduction of a tracking system."

[0947] An example of a prompt is as follows:

[0948] "Anticipate what the RFI / RFP will say and present it in a conversational format: We're looking for a new logistics partner. What proposals can we expect?"

[0949] In this way, a system can be realized that supports the managers and staff of the logistics center in carrying out their work efficiently.

[0950] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0951] Step 1:

[0952] The server interactively reads electronic documents such as the other party's public information, requests for information, and trends in documents presented by the information systems department. These electronic documents are provided to the server as input. The server analyzes these documents and extracts the necessary information. The analyzed information is obtained as output.

[0953] Step 2:

[0954] The server predicts future Requests for Information (RFI) and Requests for Proposal (RFP) based on the information obtained in step 1. As input, the parsed information is provided to the server. The server uses a generative AI model (e.g., OpenAI API) to predict the content of future RFIs / RFPs. As output, the prediction results are obtained.

[0955] Step 3:

[0956] The server interactively presents the prediction results obtained in step 2 to the user. As input, the prediction results are provided to the server. The server interactively presents the prediction results to the user through a user interface. As output, the user can check the prediction results.

[0957] Step 4:

[0958] The user checks the prediction results presented by the server through a smartphone application. The prediction results from the server are provided to the smartphone as input. The user plans and responds to work based on the prediction results. The user's work plan and response are obtained as output.

[0959] Step 5:

[0960] When a user enters the details of a new request for information or proposal, the information is sent to the server via a smartphone application. The smartphone receives the information entered by the user as input. The server receives this information and performs another prediction. The output is a new prediction result.

[0961] In this way, a system is realized that supports the managers and staff of the logistics center in carrying out their work efficiently.

[0962] Example 3

[0963] Next, a description will be given of Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0964] In the conventional workflow, it was difficult to predict the content of requests for information (RFI) and requests for proposals (RFP) in advance and propose optimal responses. In addition, business data was often collected and analyzed manually, making it difficult to efficiently reduce workloads. This resulted in insufficient efficiency and optimization of business operations, and there was a risk that the company's competitiveness would decline.

[0965] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0966] In this invention, the server includes a means for interactively reading public information from the other party, trends in information materials, etc. in electronic document format, a means for predicting information requests / proposal requests to be presented based on the content of the information, a means for collecting business data, a means for analyzing the collected business data, a means for generating prediction results based on the analysis results, and a means for proposing optimization of business flows based on the prediction results. This enables efficient collection and analysis of business data, and realizes proposals for optimal business flows based on the prediction results. This reduces work load and improves work efficiency.

[0967] "Other party public information" refers to information that a company or organization has made public.

[0968] "Information materials" are materials provided internally or externally by a company or organization.

[0969] "Electronic document format" means a document stored in a digital format.

[0970] "Interaction style" refers to the way in which a user and a system interact with each other.

[0971] An "information request" is a request for specific information.

[0972] "Request for Proposal" means a request for a specific proposal.

[0973] "Prediction" means predicting future events or situations in advance.

[0974] "Business data" refers to data related to the business of a company or organization.

[0975] "Collection" means gathering the necessary data and information.

[0976] "Analysis" means analyzing data or information to find meaning.

[0977] "Prediction results" refer to future predictions obtained based on the analysis.

[0978] "Business flow" refers to the procedures and processes for business progress.

[0979] An "optimization proposal" is a proposal for optimizing business flow.

[0980] The present invention is a system for reducing workload, in which a server, a terminal, and a user work in cooperation with each other. A specific embodiment of this system will be described below.

[0981] First, the server interactively reads publicly available information and trends in information materials in electronic document format, including common electronic document formats such as PDF and Word. The server then analyzes these documents using natural language processing technology and predicts requests for information (RFIs) and requests for proposals (RFPs) based on their content.

[0982] Next, the server collects business data from each department within the company, including the contents of past RFIs / RFPs, examples of successful and unsuccessful projects, and details of business processes. A relational database such as MySQL or PostgreSQL is used as the database.

[0983] The collected business data is preprocessed by the server and input into the AI ​​engine. The AI ​​engine analyzes the data using machine learning frameworks such as TensorFlow and PyTorch. The purpose of the analysis is to find patterns and trends within the data. The AI ​​engine analyzes the data and extracts important features.

[0984] The server generates predictions based on the results of the AI ​​engine's analysis. These predictions include bottlenecks and risks in future business processes, as well as the likelihood of success. These predictions are provided to users in the form of dashboards and reports.

[0985] Furthermore, the server generates workflow optimization proposals based on the prediction results. For example, if the content of a specific RFI / RFP matches a pattern based on past successes, it will propose specific countermeasures. This allows users to take specific actions to reduce their workload.

[0986] As a concrete example, consider the case where a user receives an RFP for a new project. The server analyzes the RFP and proposes the optimal solution based on the success of similar projects in the past.

[0987] Example prompt sentence:

[0988] "We've received an RFP for a new project. Please analyze the RFP and recommend the best solution based on past successes."

[0989] In this way, the system makes optimal proposals for reducing the workload through collaboration between the server, terminal, and user. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0990] Step 1:

[0991] The server interactively reads publicly available information from the other party and trends in information materials in electronic document format. Electronic documents such as PDF and Word documents are provided as input. The server analyzes these documents using natural language processing technology and extracts important information. The analyzed information is obtained as output. Specifically, the server reads the documents, performs text extraction, and identifies keywords and phrases.

[0992] Step 2:

[0993] The server predicts requests for information (RFIs) and requests for proposals (RFPs) in advance from the analyzed information. The analyzed information obtained in step 1 is given as input. The server uses a machine learning model to compare it with past data and predict future RFIs / RFPs. The output is the predicted RFIs / RFPs. Specifically, the server applies the prediction model to generate the predicted results.

[0994] Step 3:

[0995] The server collects business data from each department within the company. As input, it receives the business data provided by each department. The server saves the data in a database and extracts the necessary data. As output, it obtains the collected business data. Specifically, the server connects to the database and retrieves the data.

[0996] Step 4:

[0997] The server analyzes the collected business data. The business data obtained in step 3 is given as input. The server analyzes the data using an AI engine and extracts important features. The analysis results are obtained as output. Specifically, the server preprocesses the data and inputs it into the AI ​​engine.

[0998] Step 5:

[0999] The server generates a prediction result based on the analysis result. The analysis result obtained in step 4 is given as input. The server applies the prediction model to make a prediction about future business flows. The prediction result is obtained as output. Specifically, the server executes the prediction model and aggregates the results.

[1000] Step 6:

[1001] The server makes a proposal for optimizing the workflow based on the prediction results. The prediction results obtained in step 5 are given as input. The server refers to past examples of success and failure and proposes the optimal workflow. The output is an optimization proposal. Specifically, the server generates the proposal and notifies the user.

[1002] Step 7:

[1003] The user receives the optimization proposal provided by the server and adjusts the workflow. The optimization proposal from the server is given as input. The user checks the proposal and takes the necessary action. The output is the adjusted workflow. In concrete terms, the user reviews and executes the workflow based on the proposal.

[1004] (Application example 3)

[1005] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1006] The work flow at conventional logistics centers was often poorly predicted for workloads, and they were unable to respond appropriately when workloads increased. Furthermore, the work flow was not optimized, making it difficult to operate efficiently. This resulted in work delays, increased costs, and a decline in overall work efficiency.

[1007] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes means for interactively reading the other party's public information, trends in information materials, etc. in electronic documents, means for predicting the information request / proposal to be presented based on the contents of the electronic documents, means for analyzing business data and predicting the workload, and means for proposing optimization of the business flow based on the prediction results. This makes it possible to accurately predict the workload at the logistics center and propose optimal countermeasures to reduce the workload.

[1008] "Publicly disclosed information by the other party" refers to information and materials made public by companies and organizations, including press releases, official websites, reports, etc.

[1009] "Information materials" are materials provided internally or externally by a company or organization, including presentations, reports, data sheets, etc.

[1010] "Electronic document" refers to a document stored in a digital format, including PDFs, Word documents, Excel sheets, etc.

[1011] "Conversational" refers to the way in which users and systems interact with each other, including chatbots and interactive user interfaces.

[1012] "Request for Information" means a document requesting the provision of specific information, including a Request for Information (RFI).

[1013] "Request for Proposal" means a document requesting the submission of a specific proposal, including an RFP (Request for Proposal).

[1014] "Business data" refers to data related to the business of a company or organization, including work records, inventory data, shipping data, etc.

[1015] "Business volume" refers to the total volume of business within a specific period, including the number of transactions, working hours, and shipping volume.

[1016] "Business flow" refers to a series of steps or processes that show how work progresses, and includes work instructions and process maps.

[1017] "Optimization proposals" refer to proposals for streamlining business processes, including resource reallocation and improvements to work procedures.

[1018] The system for implementing this invention aims to optimize the workflow at a logistics center. The system has the function of interactively reading trends in publicly available information and provided information documents in electronic form and predicting requests for information (RFIs) and requests for proposals (RFPs) in advance based on the content. It also has the function of analyzing business data and predicting workload. Furthermore, it has the function of proposing workflow optimization based on the prediction results.

[1019] Hardware and software used

[1020] Hardware: Smartphones, servers

[1021] Software: Python, Pandas, Scikit-learn

[1022] System configuration

[1023] 1. Data Loading: The server loads the other party's public information and information materials in electronic document format, including PDF and Word documents.

[1024] 2. Prediction of Requests for Information / Requests for Proposal: The server analyzes the content of the loaded electronic documents and predicts Requests for Information (RFI) and Requests for Proposal (RFP) in advance.

[1025] 3. Analysis of business data: The server analyzes the business data of the logistics center and predicts the volume of work. Business data includes work records, inventory data, shipping data, etc.

[1026] 4. Workflow optimization proposals: Based on the prediction results, the server makes proposals for optimizing workflows, including resource reallocation and improvements to work procedures.

[1027] 5. User interface: Prediction results and optimization suggestions are presented to the user in an interactive format using a smartphone.

[1028] Processing flow

[1029] The server first reads and analyzes the other party's publicly available information and provided materials in electronic document format. Next, it uses a generative AI model to predict requests for information (RFIs) and requests for proposals (RFPs) in advance. It also analyzes the logistics center's operational data and predicts workloads. Based on the prediction results, it makes proposals for optimizing the workflow and presents them to the user in an interactive format.

[1030] Specific examples

[1031] For example, suppose the business data for a logistics center is in the following format:

[1032] csv

[1033] feature1,feature2,feature3,target

[1034] 10, 20, 30, 100

[1035] 15, 25, 35, 150

[1036] 20, 30, 40, 200

[1037] Example prompts to input to a generative AI model:

[1038] Create a program that analyzes operational data from a logistics center and proposes optimizations to reduce workload. The data is provided in CSV format, with feature1, feature2, and feature3 as features and target as target. Based on the prediction results, propose appropriate measures to prevent workload from increasing.

[1039] In this way, the system can streamline the workflow of the logistics center and provide optimal solutions to reduce the workload.

[1040] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1041] Step 1:

[1042] The server reads the other party's public information and information materials in electronic document format. PDF and Word documents are provided as input. The server analyzes these documents and converts them into text data. The analyzed text data is obtained as output.

[1043] Step 2:

[1044] The server predicts Request for Information (RFI) and Request for Proposal (RFP) in advance based on the analyzed text data. The text data obtained in step 1 is used as input. The server uses a generative AI model to detect specific patterns and generate prediction results. The output is the predicted content of the RFI or RFP.

[1045] Step 3:

[1046] The server reads the business data of the logistics center. The business data is provided in CSV format as input. The server reads the data using Pandas and sets features and targets. The features and targets are obtained as output.

[1047] Step 4:

[1048] The server predicts workload based on the workload data. The features and targets obtained in step 3 are used as input. The server trains a RandomForestRegressor model using Scikit-learn to make predictions. The predicted workload is obtained as output.

[1049] Step 5:

[1050] The server makes optimization proposals for the business flow based on the prediction results. The prediction results obtained in step 4 are used as input. The server refers to past successes and generates optimization proposals such as resource reallocation and improvements to work procedures. The optimization proposals are obtained as output.

[1051] Step 6:

[1052] The device (smartphone) presents the prediction results and optimization proposals to the user in an interactive format. The prediction results and optimization proposals obtained in steps 2 and 5 are used as input. The device uses an interactive user interface to present information to the user and prompt them to take necessary actions. The output is the information received by the user and the corresponding action.

[1053] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1054] "Example 1"

[1055] One embodiment of the present invention combines a system that includes a means for interactively reading public information, investor relations, and trends in documents presented by the information systems department in PDF format, a means for predicting RFIs / RFPs based on the content of such information, and an emotion engine that recognizes the user's emotions. This emotion engine recognizes emotions from the user's tone of voice, facial expressions, and choice of words, and feeds that information back to the system. For example, if the system determines that the user is feeling stressed, it takes that information into account and provides more appropriate RFI / RFP predictions.

[1056] "Example 2"

[1057] In another embodiment of the present invention, the system according to claim 2 is a system in which the means for interactively presenting prediction results to the user is combined with an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's reactions in real time and adjusts the presented prediction results according to the emotions. For example, if the user expresses surprise, the system takes this information into account and adjusts the level of detail in the prediction results.

[1058] "Example 3"

[1059] In a further embodiment of the present invention, the system according to claim 3 is a system in which the means for proposing workload reduction based on the prediction result is combined with an emotion engine that recognizes the user's emotions. This emotion engine recognizes the user's emotions and adjusts the workload reduction proposals according to those emotions. For example, if the user expresses anxiety, the system takes that information into account and makes more specific workload reduction proposals.

[1060] The processing flow of each embodiment will be described below.

[1061] "Example 1"

[1062] Step 1: The system interactively reads the other party's public information, IR, trends in materials presented by the Information Systems Department, etc. in PDF format.

[1063] Step 2: Based on the information read, the system predicts the contents of the RFI / RFP.

[1064] Step 3: At the same time, the emotion engine recognizes the user's emotions from their tone of voice, facial expressions, and language.

[1065] Step 4: The emotion engine feeds back the recognized emotion information to the system, which takes that information into account to provide more appropriate RFI / RFP prediction results.

[1066] "Example 2"

[1067] Step 1: The system presents the prediction results to the user in an interactive format.

[1068] Step 2: The emotion engine analyzes user reactions in real time.

[1069] Step 3: The emotion engine adjusts the predictions the system makes depending on the emotion it recognizes.

[1070] "Example 3"

[1071] Step 1: The system makes suggestions for reducing workload based on the prediction results.

[1072] Step 2: The emotion engine recognizes the user's emotion.

[1073] Step 3: The emotion engine adjusts the workload reduction suggestions made by the system according to the recognized emotion.

[1074] Example 1

[1075] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1076] Conventional request for information (RFI) and request for proposal (RFP) prediction systems do not fully utilize trends in publicly available information, financial information, or materials presented by the information systems department. Furthermore, the prediction results are not adjusted to take user emotions into account, which means that users' stress and anxiety cannot be alleviated. Furthermore, the lack of proposals for reducing workload based on the prediction results makes it difficult to improve users' work efficiency.

[1077] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1078] In this invention, the server includes means for interactively reading in electronic documents such as publicly disclosed information from the other party, financial information, and trends in materials presented by the information systems department, means for predicting requests for information / proposals to be presented based on the contents of the electronic documents, emotion recognition means for recognizing the user's emotions, and means for adjusting the prediction results based on the information obtained from the emotion recognition means. This enables more accurate RFI / RFP predictions that take the user's emotions into consideration, and makes it possible to make proposals to reduce the user's stress and anxiety while also reducing their workload.

[1079] "Other party public information" is information that a company or organization has made publicly available and that is publicly accessible through websites, reports, etc.

[1080] "Financial information" refers to information that shows the financial status of a company or organization, and is data contained in financial reports, settlement reports, etc.

[1081] "Information Systems Department Presentation Materials" are documents created and presented by the information systems department of a company or organization, and include information on the system's operational status, plans, and technical details.

[1082] An "electronic document" is a document stored in a digital format, including formats such as PDF and Word files.

[1083] "Interactive" refers to an interface in which the user and the system exchange information with each other, in the form of questions and answers.

[1084] A Request for Information (RFI) is a document issued by a company or organization to a supplier or partner, requesting the provision of specific information.

[1085] A "Request for Proposal (RFP)" is a document issued by a company or organization to suppliers or partners requesting proposals for a specific project or service.

[1086] "Prediction" is the prediction of future events or outcomes based on past data and trends.

[1087] "Emotion recognition means" refers to technology for analyzing and recognizing a user's emotions, and refers to a system that analyzes facial expressions, tone of voice, choice of words, etc.

[1088] "Means for adjusting predicted results" refers to technology that modifies or adjusts predicted results based on the user's emotional information.

[1089] The system of the present invention includes a means for interactively reading public information from the other party, financial information, and trends in materials presented by the information systems department in electronic documents, a means for predicting the requests for information (RFI) / requests for proposals (RFP) that will be presented based on the contents of the electronic documents, an emotion recognition means for recognizing the emotions of the user, and a means for adjusting the prediction results based on the information obtained from the emotion recognition means.

[1090] Hardware and software used

[1091] Hardware: Servers, user devices (PCs, tablets, smartphones, etc.)

[1092] Software: PDF readers, database management systems (e.g., MySQL, PostgreSQL), AI engines (e.g., TensorFlow, PyTorch), emotion recognition engines (e.g., Affectiva, Microsoft Azure Emotion API)

[1093] Specific operation of the system

[1094] 1. Data collection and storage

[1095] The server collects the other party's public information, financial information, and materials presented by the information systems department from the Internet.

[1096] What it does: The server automatically downloads PDF files from a company's official website or publicly available investor relations page and stores them in a MySQL database.

[1097] 2. Data Analysis

[1098] The server passes the accumulated PDF files to an AI engine, which analyzes their contents.

[1099] Specific operation: The server uses TensorFlow to extract text from PDF files and uses natural language processing techniques to extract keywords and topics.

[1100] 3. Predicting the contents of RFI / RFP

[1101] The server applies a generative AI model to predict the content of the RFI / RFP based on the analysis results.

[1102] Specific operation: The server uses a generative AI model (e.g., GPT-3) that has learned from past RFI / RFP data to generate items that are likely to be included in the next RFP.

[1103] 4. User Emotion Recognition

[1104] The device collects the user's tone of voice, facial expressions, and language choices through a camera and microphone.

[1105] How it works: When a user uses the system, the device captures their facial expressions with a camera and records their tone of voice with a microphone. These are then analyzed using Affectiva's API to recognize the user's emotions.

[1106] 5. Feedback and Adjustments

[1107] The server adjusts the prediction results based on the user's emotional information.

[1108] Specific behavior: If the user is feeling stressed, the server generates additional information to explain the prediction result in more detail.

[1109] Examples and prompts

[1110] Example: A system that predicts the content of the next RFP based on a company's financial information

[1111] The server downloads the company's latest financial reports and stores them in a database.

[1112] An AI engine analyzes the contents of the report and lists items that are likely to be included in the next RFP.

[1113] When a user uses the system, the emotion recognition engine analyzes the user's stress level and adjusts the prediction results.

[1114] Example prompt sentence:

[1115] Use the company's most recent financial report to predict what items are likely to be included in the next RFP. If users are feeling stressed, adjust your predictions to take that information into account.

[1116] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1117] Step 1:

[1118] Data collection

[1119] Input: URLs and file paths of the other party's public information, financial information, and documents presented by the Information Systems Department

[1120] Specific behavior: The server downloads the PDF file from the specified URL or file path.

[1121] Data processing: Temporarily save downloaded PDF files.

[1122] Output: Downloaded PDF file

[1123] Step 2:

[1124] Data accumulation

[1125] Input: Downloaded PDF file

[1126] Specific operation: The server saves the downloaded PDF file in a MySQL database, along with its metadata (collection date and time, file name, and source URL).

[1127] Data processing: Store PDF files and their metadata in a database.

[1128] Output: PDF files and metadata stored in a database

[1129] Step 3:

[1130] PDF analysis

[1131] Input: PDF files stored in the database

[1132] Specific operation: The server extracts text from PDF files using TensorFlow.

[1133] Data processing: The extracted text is analyzed using natural language processing techniques to extract important keywords and topics.

[1134] Output: Extracted keywords and topics

[1135] Step 4:

[1136] Saving analysis results

[1137] Input: Extracted keywords and topics

[1138] Specific operation: The server stores the extracted keywords and topics in a database.

[1139] Data processing: Store keywords and topics in a database.

[1140] Output: Keywords and topics stored in a database

[1141] Step 5:

[1142] RFI / RFP Content Prediction

[1143] Input: Keywords or topics stored in the database

[1144] Specific operation: The server uses a generative AI model (e.g., GPT-3) that has learned from past RFI / RFP data to generate items that are likely to be included in the next RFP.

[1145] Data processing: Generative AI models are used to generate predictions.

[1146] Output: Predicted RFP items

[1147] Step 6:

[1148] Saving prediction results

[1149] Input: Predicted RFP items

[1150] Specific behavior: The server saves the generated RFP items in a database.

[1151] Data processing: Store the prediction results in a database.

[1152] Output: Prediction results stored in a database

[1153] Step 7:

[1154] Collecting Emotional Data

[1155] Input: User's tone of voice, facial expressions, and language

[1156] Specific operation: When a user uses the system, the device captures facial expressions with a camera and records the tone of voice with a microphone.

[1157] Data processing: Collected audio and video data is temporarily stored.

[1158] Output: Collected audio and video data

[1159] Step 8:

[1160] Emotion analysis

[1161] Input: Collected audio and video data

[1162] Specific operation: The device uses Affectiva's API to analyze the user's emotions from their facial expressions and tone of voice.

[1163] Data processing: Analyze emotional data using an emotion recognition engine.

[1164] Output: Parsed emotion data

[1165] Step 9:

[1166] Feedback and Adjustments

[1167] Input: Parsed sentiment data, predicted RFP items

[1168] Specific operation: The server adjusts the prediction result based on the user's emotional information. If the user is feeling stressed, it generates additional information to explain the prediction result in more detail.

[1169] Data processing: Correct and adjust prediction results based on emotion data.

[1170] Output: Adjusted prediction results

[1171] Step 10:

[1172] Providing adjustment results

[1173] Input: Adjusted forecast results

[1174] Specific operation: The server displays the adjusted RFP prediction results on the user's terminal.

[1175] Data processing: Display the adjustment results in a user-friendly format.

[1176] Output: Adjustment results provided to the user

[1177] (Application example 1)

[1178] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1179] With conventional systems, it was difficult to efficiently analyze publicly available information, disclosure documents, and documents submitted by the information systems department, and to predict the content of requests for information (RFI) and requests for proposals (RFP) in advance. Furthermore, because the system provided prediction results without taking into account the user's emotional state, it could cause stress for the user, and there was a problem in that the system was unable to provide appropriate information.

[1180] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes means for interactively reading in electronic document format information disclosed by the other party, information disclosure materials, trends in materials presented by the information systems department, etc., means for predicting in advance the information request / proposal request to be presented from the content of the electronic document, emotion recognition means for recognizing the user's emotion, and means for adjusting the prediction result according to the user's emotional state. This makes it possible to predict an appropriate information request / proposal request taking into account the user's emotional state.

[1181] "Other party public information" refers to all information that companies and organizations make public to the outside world.

[1182] A "disclosure document" is a document that compiles information that a company or organization must make public for legal or business reasons.

[1183] "Information Systems Department Presentation Materials" refers to technical or business materials prepared by the Information Systems Department and presented internally or externally.

[1184] "Electronic document format" refers to documents stored in a digital format such as PDF or Word.

[1185] "Interactional" refers to the manner in which a user and a system interact with each other.

[1186] "Request for Information (RFI)" refers to a document issued seeking specific information.

[1187] "Request for Proposal (RFP)" means a document issued to solicit proposals for a particular project or service.

[1188] "Prediction" refers to predicting future events or outcomes.

[1189] "Emotion recognition means" refers to technology that recognizes emotions from the user's tone of voice, facial expressions, and choice of words.

[1190] "Means for adjusting prediction results" refers to technology that changes or optimizes prediction results depending on the user's emotional state.

[1191] A system for implementing the present invention has the following configuration.

[1192] First, the server has a means for interactively reading public information from the other party, disclosure materials, and trends in materials presented by the information systems department in electronic document format. This means is realized, for example, using a PDF reading library such as a PDF analysis library. The server stores this information in a database and analyzes it using an AI engine. The AI ​​engine uses OpenAI's API and uses a generative AI model to predict the content of requests for information (RFIs) and requests for proposals (RFPs) in advance.

[1193] Next, the server has an emotion recognition unit that recognizes the user's emotions. This unit is implemented using a custom library (e.g., emotion_recognition library) for recognizing emotions from audio files. It recognizes emotions from the user's tone of voice, facial expressions, and phrasing, and feeds that information back to the system.

[1194] Furthermore, the server has a means to adjust the prediction results according to the user's emotional state. For example, if it determines that the user is feeling stressed, it will simplify the prediction results and provide them in an easy-to-understand format. This adjustment is made based on the analysis results of the AI ​​engine.

[1195] A concrete example is the "Smart Factory Assistant" application used by factory operation managers. This application interactively reads various data within the factory (production plans, machine operation status, maintenance history, etc.) in PDF format, and an AI engine analyzes it to predict future production plans and the need for maintenance. Furthermore, it uses an emotion engine to recognize the emotional state of managers and engineers, and if they are feeling stressed, it provides more concise and easy-to-understand information.

[1196] An example of a prompt is as follows:

[1197] Analyze the text below and predict the contents of the RFI / RFP:

[1198] Production plan

[1199] October 2023: Increase production of product A by 20%

[1200] November 2023: Maintenance schedule for Product B

[1201] December 2023: Start of prototyping of new product C

[1202] Analysis results:

[1203] By inputting this prompt into OpenAI's API, analysis results can be obtained.

[1204] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1205] Step 1:

[1206] The server interactively reads the other party's public information, information disclosure materials, trends in materials presented by the Information Systems Department, etc. in electronic document format. Specifically, it uses a PDF analysis library to read PDF files and extract text. The input is the PDF file, and the output is the extracted text.

[1207] Step 2:

[1208] The server stores the extracted text in a database, which also contains data from past requests for information (RFIs) and requests for proposals (RFPs). The input is the extracted text, and the output is the text data stored in the database.

[1209] Step 3:

[1210] The server uses an AI engine to analyze the text data stored in the database. Specifically, it uses OpenAI's API to perform analysis using a generative AI model. The input is the text data stored in the database, and the output is prediction information as the analysis result.

[1211] Step 4:

[1212] The server analyzes the audio file with an emotion recognition means to recognize the user's emotions. Specifically, it uses the emotion_recognition library to recognize emotions from the audio file. The input is the audio file, and the output is the recognized emotion information.

[1213] Step 5:

[1214] The server adjusts the prediction result based on the recognized emotional information. For example, if it determines that the user is feeling stressed, it will simplify the prediction result and provide it in an easy-to-understand format. The input is the analysis result and emotional information, and the output is the adjusted prediction result.

[1215] Step 6:

[1216] The server interactively presents the adjusted prediction results to the user. Specifically, it displays the prediction results through a user interface. The input is the adjusted prediction results, and the output is the information presented to the user.

[1217] Example 2

[1218] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1219] Conventional prediction systems for requests for information (RFI) and requests for proposals (RFP) provide uniform information without considering the user's feelings, making it difficult to provide appropriate information according to the user's level of understanding and reaction. In addition, there is no function to adjust the level of detail of the prediction results, so there are cases where the system is unable to provide the information the user needs appropriately.

[1220] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1221] In this invention, the server includes means for interactively reading in electronic document format information disclosed by the other party, information disclosure materials, trends in materials presented by the information systems department, etc., means for predicting information requests / proposal requests to be presented from the contents of the electronic document, means for generating prediction results using a generative AI model, means for analyzing user emotions using an emotion engine that recognizes user emotions, means for presenting the prediction results to the user through a user interface, and means for adjusting the level of detail of the prediction results according to the user emotions. This makes it possible to provide appropriate information according to the user's emotions.

[1222] "Other party public information" refers to information that a company or organization has made public to the outside world.

[1223] "Information disclosure documents" refer to reports and presentation materials officially released by companies and organizations.

[1224] "Information Systems Department Presentation Materials" refers to materials created by the information systems department of a company or organization and presented internally or externally.

[1225] "Electronic document format" refers to documents stored in a digital format such as PDF or Word.

[1226] "Interaction" refers to the manner in which a user and a system interact with each other.

[1227] A "Request for Information (RFI)" is a document issued by a business or organization requesting specific information.

[1228] A "Request for Proposal (RFP)" is a document issued by a business or organization to solicit proposals for a specific project or service.

[1229] A "generative AI model" is an artificial intelligence model that has been trained using machine learning or deep learning to perform a specific task.

[1230] An "emotion engine" is a system that recognizes and analyzes emotions from a user's facial expressions, voice, etc.

[1231] A "user interface" refers to the screens and operating means that allow a user to interact with a system.

[1232] "Prediction results" refer to information about future events or situations generated by a generative AI model based on input data.

[1233] "Level of detail" refers to the degree of specificity or fineness of the information.

[1234] To implement the present invention, it is necessary to generate a system program according to the following procedure.

[1235] First, the server is equipped with a means for interactively reading in electronic document format information disclosed by the other party, information disclosure materials, trends in materials presented by the Information Systems Department, etc. This means uses software libraries (e.g., Apache PDFBox or Python-docx) for reading digital documents such as PDF and Word.

[1236] The server then has a means for predicting requests for information (RFIs) or requests for proposals (RFPs) from the content of the documents it has read. This is achieved using a generative AI model, which is built using a machine learning framework such as TensorFlow or PyTorch.

[1237] Furthermore, the server includes a user interface for presenting the generated prediction results to a user, which is developed using a front-end framework such as React or Vue.js.

[1238] The server also has an emotion engine that recognizes the user's emotions. This emotion engine is built using tools such as OpenCV and Emotion API, and analyzes emotions from the user's facial expressions and voice in real time.

[1239] As a concrete example, consider the case where a user enters the following prompt sentence:

[1240] "Predict what's in your next RFP. If users express surprise, adjust the level of detail."

[1241] The server receives the prompt and uses a generative AI model to generate a prediction. The emotion engine then analyzes the user's real-time reaction and adjusts the level of detail in the prediction if the user expresses surprise. For example, if the user expresses surprise, the system will omit detailed explanations and present only the main points.

[1242] In this way, users can understand the contents of requests for information (RFIs) and requests for proposals (RFPs) in advance and plan appropriate responses.

[1243] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1244] Step 1:

[1245] The user enters a prompt statement

[1246] The user uses a terminal to input a prompt into the system's input form. For example, they might input, "Please predict the content of the next RFP. If the user expresses surprise, adjust the level of detail." The input prompt is sent to the server as an HTTP request.

[1247] Input: prompt statement

[1248] Output: HTTP request

[1249] Step 2:

[1250] The server receives the prompt.

[1251] The server receives the HTTP request sent by the user and extracts the prompt text, which is then passed to the next processing step.

[1252] Input: HTTP request

[1253] Output: prompt statement

[1254] Step 3:

[1255] The server generates prediction results using an AI engine

[1256] The server passes the prompt sentence to a generative AI model, which is built using TensorFlow or PyTorch, for example, and generates a prediction result based on the prompt sentence.

[1257] Input: prompt statement

[1258] Output: Prediction results

[1259] Step 4:

[1260] The server analyzes the user's emotions using an emotion engine.

[1261] The server passes the user's real-time reactions to the emotion engine, which analyzes the user's emotions by analyzing their facial expressions and voice using OpenCV and Emotion API.

[1262] Input: Real-time user responses (facial expressions and voice)

[1263] Output: User emotion data

[1264] Step 5:

[1265] The server presents the prediction results through a user interface.

[1266] The server adjusts the level of detail in the prediction results based on the analysis results of the emotion engine. For example, if the user expresses surprise, the server omits detailed explanations and presents only the main points. The adjusted prediction results are then presented to the user through a user interface.

[1267] Input: Prediction results, user emotion data

[1268] Output: Adjusted prediction results

[1269] Step 6:

[1270] The user can review the prediction results and provide feedback if necessary.

[1271] The user can review the presented prediction results and provide feedback if necessary, which is then sent to the server and used to improve the system.

[1272] Input: Adjusted forecast results

[1273] Output: User feedback

[1274] (Application example 2)

[1275] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1276] In conventional self-driving vehicles, when providing users with predicted traffic and driving conditions, the information presented does not take the user's emotions into consideration, making it difficult for users to properly understand the information and use the vehicle with confidence.In addition, because the level of detail in the prediction results is uniform, there is also the problem of being unable to respond flexibly to the user's situation and emotions.

[1277] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1278] In this invention, the server includes means for interactively reading in PDF the other party's public information, IR, trends in materials presented by the information systems department, etc., means for predicting the RFI / RFP to be presented from the contents of the PDF, means for interactively presenting the prediction results to the user, means for combining an emotion engine that recognizes the user's emotions, means for adjusting the level of detail of the prediction results according to the user's emotions, and means for generating prediction results of traffic conditions and operation conditions in an autonomous vehicle and presenting them to the user in an interactive format. This enables flexible information presentation according to the user's emotions, allowing users to use autonomous vehicles with peace of mind.

[1279] "Other party public information" refers to information that a company or organization has publicly disclosed, including financial reports, press releases, and information on its official website.

[1280] "IR" stands for investor relations and refers to the information provision activities that companies undertake for investors.

[1281] "Information systems department presentation materials" refers to various materials created and presented by the information systems department of a company or organization, including system specifications, operation manuals, reports, etc.

[1282] "PDF" stands for Portable Document Format and refers to a file format for storing and distributing documents electronically.

[1283] "Interactive style" refers to the way in which a user and a system interact with each other, including text chat and voice interaction.

[1284] "RFI" is an abbreviation for Request for Information and refers to a request for information.

[1285] "RFP" stands for Request for Proposal and refers to a request for proposal.

[1286] "Prediction" refers to predicting future events or situations in advance.

[1287] "Prediction results" refer to results obtained through prior prediction.

[1288] "User interface" refers to the means by which a user interacts with a system, including screen displays and audio outputs.

[1289] An "emotion engine" refers to a system for recognizing and analyzing user emotions.

[1290] "Traffic conditions" refers to the traffic flow and congestion on roads.

[1291] "Operation status" refers to the status of vehicle operation, including the route traveled and the estimated arrival time.

[1292] "Level of detail" refers to the degree of specificity or fineness of the information.

[1293] An "autonomous vehicle" refers to a vehicle that drives autonomously using artificial intelligence and sensor technology.

[1294] The system for implementing this invention has the following configuration: First, the server is equipped with a means for interactively reading the other party's public information, IR, trends in materials presented by the information systems department, etc. in PDF format, allowing the server to efficiently collect and analyze the necessary information.

[1295] The server then has a means to predict future RFIs / RFPs based on the content of the requests. This uses a generative AI model to predict future requirements and requests for proposals based on the collected information, allowing users to plan appropriate responses in advance.

[1296] Furthermore, the server has a means for presenting the prediction results to the user in an interactive format. This means uses a dialogue engine such as Dialogflow, and provides the prediction results to the user through a user interface. The user can ask questions or give instructions through this interface, and the system will respond appropriately.

[1297] The server also incorporates an emotion engine that recognizes the user's emotions. This emotion engine uses emotion recognition technology such as OpenCV to analyze the user's facial expressions and voice data in real time, allowing it to adjust the level of detail in the prediction results according to the user's emotions.

[1298] Furthermore, the autonomous vehicle is equipped with a means for generating predicted results of traffic and driving conditions and presenting them to the user in an interactive format. This means uses an AI engine such as TensorFlow to predict traffic and driving conditions and provide them to the user.

[1299] For example, if the user expresses surprise, the system will increase the detail of the prediction results and provide more specific information. Conversely, if the user is relaxed, the system will provide concise information. For example, if the user asks, "What is the current traffic situation?" the system will respond, "There is currently traffic congestion on major roads. Would you like to suggest an alternative route?"

[1300] In this way, it becomes possible to present information flexibly according to the user's emotions, allowing users to use self-driving vehicles with peace of mind.

[1301] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1302] Step 1:

[1303] The server interactively reads PDF files such as publicly disclosed information from the other party, investor relations information, and trends in documents presented by the information systems department. PDF files are provided as input, which the server analyzes and converts into text data. The analyzed text data is obtained as output. PDF analysis software (e.g., PyMuPDF) is used for this process.

[1304] Step 2:

[1305] The server uses a generative AI model to predict RFI / RFP in advance based on the analyzed text data. The text data obtained in step 1 is provided as input, and the server inputs this into the generative AI model. The predicted RFI / RFP is obtained as output. TensorFlow is used for this process.

[1306] Step 3:

[1307] The server presents the prediction results to the user in an interactive format. The prediction results obtained in step 2 are provided as input, and the server inputs them into a dialogue engine (e.g., Dialogflow). As output, a dialogue-style message to be presented to the user is generated. This message is displayed to the user through the user interface.

[1308] Step 4:

[1309] The device uses a camera and microphone to collect facial and voice data to recognize the user's emotions. The device receives real-time video and audio from the user as input, and inputs this data into an emotion recognition engine (e.g., OpenCV). The output is the user's emotion data.

[1310] Step 5:

[1311] The server adjusts the level of detail of the prediction results based on the user's emotional data. The emotional data obtained in step 4 and the prediction results obtained in step 2 are provided as input, and the server adjusts the level of detail of the information based on this. The adjusted prediction results are obtained as output.

[1312] Step 6:

[1313] The server generates predicted traffic and driving conditions for autonomous vehicles and presents them to the user in an interactive format. Real-time traffic data obtained from the vehicle's sensors is provided as input, and the server inputs this into a generative AI model. The output is predicted traffic and driving conditions. This is then input into a dialogue engine, which generates a message to be presented to the user.

[1314] Step 7:

[1315] The user issues questions or instructions to the system through a dialogue-style interface. The user's question or instruction is provided as input, which the server analyzes and generates an appropriate response. The output is a response message to the user. For example, if the user asks, "What is the current traffic situation?" the server responds, "There is currently traffic congestion on the main road. Would you like to suggest an alternative route?"

[1316] Example 3

[1317] Next, a description will be given of Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1318] Conventional workflow optimization systems have low prediction accuracy and do not take user emotions into account when making suggestions, which means that their effectiveness in reducing workloads is limited. Furthermore, it is difficult to properly analyze the information entered by users and provide specific suggestions based on past success stories.

[1319] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1320] In this invention, the server includes a means for interactively reading the other party's public information, trends in information materials, etc. in electronic documents, a means for predicting information requests to be presented from the contents of the electronic documents, a means for proposing workflow optimization based on the prediction results, and a means for recognizing the user's emotions and adjusting the proposal contents according to the emotions. This improves the accuracy of the prediction results and makes it possible to propose specific ways to reduce the workload taking into account the user's emotions.

[1321] "Other party public information" refers to information and materials made public by companies and organizations.

[1322] "Information materials" refers to various materials and data provided by companies and organizations.

[1323] "Electronic Document" means a document stored in digital form.

[1324] "Interactional" refers to the manner in which a user and a system interact with each other.

[1325] "Information Request" means a request for specific information.

[1326] "Prediction" refers to predicting future outcomes or situations.

[1327] "Business flow" refers to the procedures and processes for business progress.

[1328] "Optimization" refers to making something the most efficient and effective.

[1329] "User emotion" refers to the emotional state of the user who uses the system.

[1330] "Emotion awareness" refers to detecting and understanding a user's emotional state.

[1331] "Adjusting the content of the suggestions" refers to changing the content of the suggestions depending on the user's emotions and situation.

[1332] MODE FOR CARRYING OUT THE INVENTION

[1333] This invention is a system aimed at optimizing business flow and reducing workload, and operates in cooperation with a server, a terminal, and a user.

[1334] Server Operation

[1335] The server first reads the other party's public information and information materials in an interactive format as electronic documents. At this time, the server analyzes the documents using natural language processing technology and predicts information requests in advance. Specifically, it uses a generative AI model built using machine learning frameworks such as TensorFlow and PyTorch.

[1336] The server then proposes workflow optimization based on the prediction results. For example, by referencing past success stories, it generates a proposal such as, "Detailed requirements definition was the key to success, so we recommend that you also define detailed requirements this time."

[1337] Furthermore, the server recognizes the user's emotions and adjusts its suggestions accordingly. For example, if the user expresses anxiety, the server can analyze the user's emotions using an emotion engine and provide more specific suggestions, such as, "In addition to detailed requirements definitions, using a project management tool will make progress management easier."

[1338] Device behavior

[1339] The terminal receives input from the user and sends that data to the server. For example, if the user types, "I want to create an RFP for a new project," that data is sent from the terminal to the server. The terminal converts the data into the appropriate format and sends it using a secure communication protocol (e.g., HTTPS).

[1340] When the server returns a proposal for optimizing the workflow, the terminal displays the proposal to the user, who then checks the proposal and decides on the next action to take.

[1341] User Actions

[1342] Users input the details of RFIs and RFPs through their terminals. Once input is complete, the user can receive workflow optimization proposals from the server. Furthermore, if the system recognizes the user's emotions, the emotion engine will adjust the proposals based on that information. For example, if the user expresses anxiety, the system will make more specific and detailed proposals for reducing workloads.

[1343] Specific examples

[1344] For example, a user might input "I want to create an RFP for a new project" into their device. The device then sends that information to the server, which uses its AI engine to refer to past successes and propose the optimal solution. Specifically, the server might return a suggestion such as, "Since detailed requirements definition was the key to success in past projects, we recommend that you also define detailed requirements this time."

[1345] For example, if a user inputs "I want to create an RFP for a new project, but I'm feeling anxious," and expresses this feeling of anxiety, the emotion engine will recognize the user's anxiety and send that information to the server. Based on that information, the server will make more specific and detailed proposals for reducing workloads. For example, it might return a proposal such as, "In addition to detailed requirements definition, using a project management tool will make progress management easier."

[1346] Prompt Sentence Examples

[1347] "We're creating an RFP for a new project. Please suggest the best solution based on past successes."

[1348] "I would like to create an RFP for a new project, but I am worried. Please give me some concrete suggestions on how to reduce the workload." The flow of the specific process in the third embodiment will be described with reference to FIG.

[1349] Step 1:

[1350] The user uses the terminal to input the contents of the RFI or RFP. For example, they might input "I would like to create an RFP for a new project." The input data is saved in text format on the terminal.

[1351] Step 2:

[1352] The terminal converts the data entered by the user into JSON format and sends it to the server using the HTTPS protocol. The input data is the text "I would like to create an RFP for a new project," and the output data is a request in JSON format.

[1353] Step 3:

[1354] The server receives the JSON data sent from the device and stores it in a database. The received data is a JSON-formatted request, and the stored data is a database entry.

[1355] Step 4:

[1356] The server uses a generative AI model to analyze the received data. Specifically, it uses a machine learning framework such as TensorFlow or PyTorch to generate predictions based on past successes. The input data are database entries, and the output data are predictions.

[1357] Step 5:

[1358] The server then proposes workflow optimization based on the generated prediction results. For example, it generates a proposal such as, "Detailed requirements definition was the key to success, so we recommend that you also define detailed requirements this time." The input data are the prediction results, and the output data are optimization proposals.

[1359] Step 6:

[1360] The server uses an emotion engine to recognize the user's emotion. If the user indicates an anxious emotion in the input data, the emotion engine analyzes the emotion and generates emotion information called "anxiety." The input data is text containing the user's emotion, and the output data is the emotion information.

[1361] Step 7:

[1362] The server adjusts the proposal content based on the emotional information received from the emotion engine. For example, if the user expresses anxiety, the server will make a more specific proposal such as, "In addition to detailed requirements definition, using a project management tool will make progress management easier." The input data is emotional information, and the output data is the adjusted proposal.

[1363] Step 8:

[1364] The server sends the final proposal to the terminal. The terminal displays the received proposal to the user. The input data is the adjusted proposal, and the output data is the proposal displayed to the user. The user checks the displayed proposal and decides on the next action.

[1365] (Application example 3)

[1366] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1367] Conventional workflow optimization systems have the problem that they do not take into account the user's emotional state when proposing ways to reduce work load, and therefore do not make appropriate suggestions when the user is in a stressful situation. In addition, there is a lack of means to monitor and optimize the workflow within the factory in real time, making it difficult to operate efficiently.

[1368] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes a means for interactively reading in document format information such as publicly disclosed information from the other party, publicly disclosed information, and trends in materials presented by the information systems department, a means for predicting information requests / proposals to be presented based on the content of the information, a means for proposing workload reduction based on the prediction results, a means for combining an emotion engine that recognizes the user's emotions, a means for adjusting the workload reduction proposals according to the emotions, and a means for monitoring the workflow within the factory in real time and proposing optimization. This makes it possible to propose appropriate workload reductions that take the user's emotional state into consideration, thereby enabling efficient optimization of the workflow within the factory.

[1369] "Other party public information" refers to information that a company or organization has made public to the outside world.

[1370] "Information disclosure" refers to the act of a company or organization disclosing internal information to the outside world.

[1371] "Materials presented by the Information Systems Department" refers to materials prepared and presented by the Information Systems Department.

[1372] A "document format" is a format in which information is expressed as a document.

[1373] "Interactive style" refers to the way in which a system and a user exchange information through dialogue.

[1374] An "information request" is a request for specific information.

[1375] "Request for Proposal" means a request for specific proposals.

[1376] "Prediction" is the act of predicting future events or situations in advance.

[1377] "Work load reduction" means reducing the workload involved in work.

[1378] An "emotion engine" is an engine that recognizes and analyzes the user's emotions.

[1379] "Business flow" refers to the flow and procedures of business.

[1380] "Real time" refers to processing or responding immediately in the current ongoing time.

[1381] "Optimization" means making something the most efficient for a particular purpose.

[1382] The system for implementing this invention is configured as follows: First, the server has a means for interactively reading in document format information disclosed by the other party, information disclosure, trends in materials presented by the information systems department, etc. This means allows the server to collect and analyze various information provided from outside.

[1383] Next, the server has a means for predicting future requests for information / proposals based on the content of the requests, allowing the server to predict future requests for information and proposals based on past data and trends and prepare countermeasures in advance.

[1384] Furthermore, the server has a means for proposing work load reduction based on the prediction results. With this means, the server can propose work flow optimization and present specific actions to reduce the work load.

[1385] The server also has a means for combining an emotion engine that recognizes the user's emotions. This emotion engine allows the server to recognize and analyze the user's emotional state in real time. For example, if the user is feeling stressed, the server can adjust the proposal for reducing the workload based on that information.

[1386] Furthermore, the server has a means for monitoring the workflow within the factory in real time and proposing optimization. This means allows the server to constantly monitor the workflow within the factory and make optimization proposals to achieve efficient business operations.

[1387] As a specific example, consider a case where a work flow in a factory consists of two steps: "assembly of parts" and "quality inspection." The server uses an emotion engine to monitor the emotional state of workers, and if a worker is feeling stressed, it suggests that a robot take over the "quality inspection." In this way, the burden on workers can be reduced and work efficiency can be improved.

[1388] Examples of prompts to input to a generative AI model include:

[1389] The workflow in the factory consists of two steps: "assembly of parts" and "quality inspection." If workers are feeling stressed, propose that a robot take over the "quality inspection" step.

[1390] By inputting this prompt into a generative AI model, specific suggestions for reducing workload can be obtained.

[1391] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1392] Step 1:

[1393] The server interactively reads document-based information such as public information from the other party, information disclosure, and trends in materials presented by the Information Systems Department. The input includes externally provided document data such as PDFs and text files. The server analyzes this document data and extracts important information. The output is the analyzed information.

[1394] Step 2:

[1395] The server predicts information requests / requests for proposals in advance based on the information obtained in step 1. The inputs are the analyzed information and past data. The server uses machine learning algorithms to predict future information requests and proposal requests. The output is the predicted results.

[1396] Step 3:

[1397] The server proposes workload reduction measures based on the prediction results. The input is the prediction results obtained in step 2. The server proposes workflow optimization and generates specific workload reduction measures. The output is a proposal for workload reduction.

[1398] Step 4:

[1399] The server monitors the user's emotional state in real time using an emotion engine that recognizes the user's emotions. The inputs are the user's facial expressions and voice data. The server analyzes the user's emotions using an emotion recognition algorithm. The output is the user's emotional state.

[1400] Step 5:

[1401] The server adjusts the workload reduction proposal based on the user's emotional state obtained in step 4. The inputs are the user's emotional state and the workload reduction proposal obtained in step 3. The server adjusts the proposal content according to the emotional state. The output is the adjusted workload reduction proposal.

[1402] Step 6:

[1403] The server monitors the workflow within the factory in real time and proposes optimization. The input is real-time data obtained from sensors and robots within the factory. The server analyzes this data and proposes optimization of the workflow. The output is a proposal for an optimized workflow.

[1404] Step 7:

[1405] The user receives proposals for reducing workloads and optimizing workflows provided by the server and reflects them in their actual work. The input is the proposals from the server. The user uses these to adjust work and operate robots. The output is more efficient business operations.

[1406] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1407] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1408] Another example of generative AI is Gemini (internet search engine). <url: https: gemini.google.com ?hl="ja">) are mentioned.

[1409] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1410] [Third embodiment]

[1411] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1412] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1413] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1414] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1415] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1416] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1417] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1418] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1419] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1420] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1421] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1422] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1423] "Example 1"

[1424] The system of the present invention has a means for interactively reading public information from the other party, IR, trends in materials presented by the information systems department, etc., in PDF format. Specifically, this information is stored in a database and analyzed by an AI engine. The analysis results are used to predict the content of RFI / RFP.

[1425] "Example 2"

[1426] Furthermore, the system of the present invention has a means for presenting the prediction results to the user in an interactive format. Specifically, the prediction results generated by the AI ​​engine are presented to the user through a user interface. This allows the user to understand the contents of the RFI / RFP in advance and plan an appropriate response.

[1427] "Example 3"

[1428] Furthermore, the system of the present invention has a means for proposing ways to reduce workloads based on the prediction results. Specifically, the AI ​​engine proposes workflow optimization based on the prediction results. For example, if the contents of the RFI / RFP match a specific pattern, it is possible to propose countermeasures based on past success stories.

[1429] The processing flow of each embodiment will be described below.

[1430] "Example 1"

[1431] Step 1: Obtain the other party's public information, IR, and information systems department presentation materials in PDF format.

[1432] Step 2: Convert the acquired PDF into text data and store it in a database.

[1433] Step 3: The AI ​​engine analyzes the information in the database and predicts the content of the RFI / RFP.

[1434] "Example 2"

[1435] Step 1: Obtain the prediction results generated by the AI ​​engine.

[1436] Step 2: Present the obtained prediction results to the user through the user interface.

[1437] "Example 3"

[1438] Step 1: The AI ​​engine proposes workflow optimization based on the prediction results.

[1439] Step 2: Present the proposed workflow to the user and make suggestions to reduce the workload.

[1440] Example 1

[1441] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1442] The traditional process of creating Requests for Information (RFI) and Requests for Proposals (RFP) required a lot of time and effort to manually collect and analyze information, resulting in inefficiency and a heavy workload. Furthermore, there was a lack of effective ways to utilize the vast amount of data, such as publicly available information from the other party, public reports, and materials presented by the information systems department. This resulted in issues such as a decline in prediction accuracy and difficulty in creating appropriate proposals.

[1443] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1444] In this invention, the server includes means for interactively reading in electronic document format information disclosed by the other party, public reports, trends in materials presented by the information systems department, etc., means for storing these electronic documents in a database, means for using an AI engine to analyze the stored data, and means for predicting the content of a request for information / request for proposal based on the analysis results. This makes it possible to efficiently analyze large amounts of data and create a request for information or request for proposal with high prediction accuracy.

[1445] "Other party public information" refers to all information that companies and organizations make public, including, for example, press releases and information on official websites.

[1446] "Public reports" refers to official documents such as financial reports and performance reports that are periodically published by companies or organizations.

[1447] "Information systems department presentation materials" refers to technical documents and presentation materials prepared by the information systems department of a company or organization.

[1448] "Electronic document format" refers to documents stored in a digital format such as PDF or Word.

[1449] "Interactive" refers to the way in which a user interacts with a system.

[1450] A "database" refers to a system for efficiently storing, retrieving, and managing information.

[1451] An "artificial intelligence engine" refers to software that analyzes data using techniques such as machine learning and natural language processing.

[1452] A "Request for Information (RFI)" is a formal document issued by a business or organization to gather specific information.

[1453] A "Request for Proposal (RFP)" refers to a formal document issued by a business or organization to solicit proposals for a specific project or service.

[1454] This invention is a system that interactively reads electronic documents such as public information, public reports, and documents submitted by the information systems department, stores this information in a database, and analyzes it using an artificial intelligence engine. The analysis results are used to predict the contents of requests for information (RFIs) and requests for proposals (RFPs).

[1455] Hardware and software used

[1456] server

[1457] The server uses the following hardware and software:

[1458] Database management systems: MySQL, PostgreSQL

[1459] Artificial Intelligence Engine: Generative AI models (e.g., OpenAI GPT-4)

[1460] PDF Parsing Library: Python Library

[1461] File Storage System: Cloud Storage Service

[1462] Terminal

[1463] The terminal provides an interface for the user to communicate with the server. The following software is used:

[1464] Client application: Web browser, dedicated client app

[1465] Program processing

[1466] server

[1467] The server receives electronic documents uploaded by users and stores them in a file storage system. The metadata of the stored electronic documents is recorded in a database. The server then converts the electronic documents into text using a PDF parsing library and inputs it into a generative AI model. The generative AI model analyzes the input text and generates analysis results. The analysis results are stored in a database and later provided to the user.

[1468] Terminal

[1469] The terminal provides an interface for users to upload electronic documents. When the user selects an electronic document and clicks the upload button, the terminal sends the electronic document to the server. The terminal also obtains the analysis results from the server and displays them to the user. The user can predict the contents of a request for information or a request for proposal based on the analysis results.

[1470] User

[1471] Users upload electronic documents, such as public information from the other party, public reports, and materials presented by the information systems department, to the server via their terminal. They receive the analysis results and use them to predict the contents of requests for information and requests for proposals. For example, when a user inputs a prompt statement such as "What are the technical requirements for the next RFP?" into the generative AI model, the AI ​​engine provides a prediction based on the analysis results.

[1472] Specific examples

[1473] Prompt Sentence Examples

[1474] "What are the technical requirements for the next RFP?"

[1475] By inputting this prompt into a generative AI model, the AI ​​engine will provide a prediction based on the analysis results. For example, the AI ​​engine may return a prediction such as, "The next RFP will likely require the introduction of cloud computing."

[1476] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1477] Step 1:

[1478] Subject: User

[1479] Users upload electronic documents such as public information from the other party, public reports, and materials presented by the Information Systems Department to the server via their terminals. Using a browser or a dedicated client application, users select the electronic document from the file selection dialog and click the upload button.

[1480] Input: Electronic document (PDF file)

[1481] Output: Upload request to server

[1482] Specific operation: When the user clicks the "Upload" button, the terminal sends the selected electronic document to the server as an HTTP POST request.

[1483] Step 2:

[1484] Subject: Server

[1485] The server stores the received electronic document in a file storage system and records the metadata of the stored electronic document (such as file name, upload date and time, and user ID) in a database.

[1486] Input: Uploaded electronic document

[1487] Output: Save to file storage system, metadata recording to database

[1488] Specific operation: The server stores the electronic document in the file storage system and records the URL of the storage location in the database.

[1489] Step 3:

[1490] Subject: Server

[1491] The server converts the stored electronic document into text using a PDF parsing library, and then inputs the converted text into a generative AI model.

[1492] Input: Stored electronic document

[1493] Output: Text data

[1494] Specific operation: The server converts the electronic document into text using a PDF parsing library (e.g., a Python library).

[1495] Step 4:

[1496] Subject: Server

[1497] The server inputs text data into the generative AI model and obtains analysis results, including predicted content for requests for information (RFIs) and requests for proposals (RFPs).

[1498] Input: Text data

[1499] Output: Analysis results

[1500] Specific operation: The server inputs text data into a generative AI model (e.g., OpenAI GPT-4) and obtains the analysis results.

[1501] Step 5:

[1502] Subject: Server

[1503] The server stores the analysis results obtained from the generative AI model in a database, recording the content of the analysis results, the date and time of generation, and the ID of the related electronic document.

[1504] Input: Analysis results

[1505] Output: Saving analysis results to a database

[1506] Specific operation: The server saves the analysis results in the database in JSON format.

[1507] Step 6:

[1508] Subject: Terminal

[1509] The device retrieves the analysis results from the server and displays them to the user, who then views them using a browser or a dedicated client application.

[1510] Input: Request for analysis results

[1511] Output: Display of analysis results

[1512] Specific operation: The device sends an HTTP GET request to the server to obtain the analysis results, which are then displayed in HTML or JSON format.

[1513] Step 7:

[1514] Subject: User

[1515] The user inputs a prompt to the generative AI model and obtains a prediction result. For example, the user inputs a prompt such as, "What are the technical requirements for the next RFP?"

[1516] Input: prompt statement

[1517] Output: Prediction results

[1518] Specific operation: When the user enters a prompt and clicks the "Send" button, the device sends the prompt to the server, which then passes the prompt to the generative AI model, obtains the prediction result, and returns it to the user.

[1519] (Application example 1)

[1520] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1521] Today's companies and individuals are required to predict security risks from a vast amount of information and take appropriate measures. However, this information is diverse, and manual analysis takes a great deal of time and effort. Furthermore, finding appropriate measures requires advanced expertise, which is difficult for average users. For this reason, there is a need for a system that can efficiently and accurately predict security risks and propose countermeasures.

[1522] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1523] In this invention, the server includes means for interactively reading the other party's public information, public information, trends in materials presented by the information systems department, etc. in PDF format, means for predicting information requests / requests for proposals to be presented from the contents of the PDF, means for analyzing security risks based on the prediction results, and means for proposing security measures based on the analysis results. This allows users to efficiently and accurately predict security risks and take appropriate measures.

[1524] "Other party public information" refers to information that a company or organization has made public to the outside world.

[1525] "Public Information" means information that is publicly accessible.

[1526] "Materials presented by the Information Systems Department" refers to materials prepared and presented by the Information Systems Department.

[1527] "PDF" stands for Portable Document Format, a file format for electronically storing and displaying documents.

[1528] "Interaction style" refers to the way in which a user and a system interact with each other.

[1529] An "information request" is a request for specific information.

[1530] "Request for Proposal" means a request for a specific proposal.

[1531] "Prediction" refers to predicting future events or situations in advance.

[1532] A "security risk" is a potential threat or danger to information or systems.

[1533] "Analysis" refers to the detailed analysis of data or information.

[1534] A "solution" is a proposed solution to a particular problem or risk.

[1535] The following system configuration will be described as an embodiment of the present invention.

[1536] System Configuration

[1537] Hardware and Software

[1538] Hardware: Smartphone

[1539] Software: Python, PDF parsing library, SQLite, OpenAI API

[1540] Processing flow

[1541] 1. PDF Import:

[1542] The server uses a PDF analysis library to read PDF files and extract the text, thereby obtaining the contents of the other party's public information, public information, and materials presented by the Information Systems Department as digital data.

[1543] 2. Database connection:

[1544] The server connects to an SQLite database using the sqlite3 library, which allows for efficient storage and management of extracted text data.

[1545] 3. Data Retention:

[1546] The server stores the extracted text in a database, allowing for centralized management of data required for subsequent analysis.

[1547] 4. AI analysis:

[1548] The server uses the openai library to send the extracted text to OpenAI's API for security risk prediction, which can identify risks more quickly and accurately than a user could do manually.

[1549] 5. Results display:

[1550] The server presents the analysis results to the user in an interactive format, allowing the user to easily understand the results and take appropriate measures.

[1551] Specific examples

[1552] For example, if a company's IR information mentions the introduction of a new cloud service, the server analyzes this information and predicts the security risks of the cloud service. It also suggests countermeasures such as the introduction of multi-factor authentication and regular security audits.

[1553] Prompt Sentence Examples

[1554] Analyze the following information to predict security risks:

[1555] Corporate IR information

[1556] Information Systems Department presentation materials

[1557] Other party public information

[1558] Based on the analysis results, please propose specific security risks and countermeasures.

[1559] In this way, users can efficiently and accurately predict security risks and take appropriate measures.

[1560] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1561] Step 1:

[1562] The server reads the PDF file. Specifically, it uses a PDF parsing library to open the PDF file and extract the text from each page. The input is the PDF file, and the output is the extracted text data, which is used for subsequent parsing.

[1563] Step 2:

[1564] The server connects to the SQLite database by opening the database file using the sqlite3 library. The input is the path to the database file, and the output is a database connection object, which is used to store and retrieve data.

[1565] Step 3:

[1566] The server saves the extracted text data in a database. Specifically, it uses a database connection object to insert the text data into a specific table in the database. The input is the extracted text data, and the output is the data saved in the database. This saved data is used for subsequent analysis processing.

[1567] Step 4:

[1568] The server sends the stored text data to the AI ​​engine for analysis. Specifically, it uses the openai library to send the text data to OpenAI's API and predicts security risks. The input is text data retrieved from the database, and the output is the analysis result from the AI ​​engine. This analysis result is presented to the user.

[1569] Step 5:

[1570] The server presents the analysis results to the user in an interactive format. Specifically, it displays the analysis results through a user interface and provides information in a format that is easy for the user to understand. The input is the analysis results from the AI ​​engine, and the output is the information presented to the user. Based on this information, the user can take appropriate security measures.

[1571] Example 2

[1572] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1573] Conventional request for information (RFI) and request for proposal (RFP) processing systems have the problem that users have to manually analyze large amounts of information and plan appropriate responses, which requires a great deal of time and effort. Another issue is that the interface used to provide prediction results to users is not intuitive, which means users are unable to fully utilize the results. Furthermore, there is a lack of proposals for reducing workloads based on the prediction results, and specific support for improving users' work efficiency is insufficient.

[1574] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for interactively reading in document format information disclosed by the other party, information disclosure, trends in materials presented by the information systems department, etc., a means for predicting information requests / proposal requests to be presented based on the content of the information, a means for generating prediction results using a generative AI model, and a means for interactively presenting the prediction results to the user through a user interface. This allows the user to efficiently analyze large amounts of information, utilize the prediction results through an intuitive interface, and receive proposals for reducing their workload.

[1575] "Information publicly available from the other party" refers to information that a company or organization has made public, such as press releases and the contents of official websites.

[1576] "Disclosure" refers to information that a company or organization makes public based on legal or regulatory requirements, including, for example, financial reports and annual reports.

[1577] "Information systems department presentation materials" refers to materials created by the information systems department of a company or organization and presented internally or externally, including, for example, system specifications and operation manuals.

[1578] "Document format" refers to information recorded in a format such as text or PDF.

[1579] "Conversational" refers to the way in which a user and a system interact with each other, including, for example, chatbots and interactive web interfaces.

[1580] A "Request for Information (RFI)" is a formal request issued by a business or organization to obtain specific information.

[1581] "Request for Proposal (RFP)" refers to a formal request issued by a business or organization to solicit proposals for a specific project or service.

[1582] "Predictive forecasting" refers to the analysis of current data and information to predict future events and outcomes.

[1583] A "generative AI model" refers to an algorithm or system that uses artificial intelligence technology to analyze data and create predictions or products.

[1584] "User interface" refers to the screens and operating means through which a user interacts with a system, including, for example, web applications and mobile applications.

[1585] "Reducing workload" refers to reducing the workload on users through streamlining and automation of work.

[1586] This invention is a system that generates prediction results using a generative AI model and presents the results to a user in an interactive format. Specific embodiments of this system are described below.

[1587] Hardware and software used

[1588] Hardware: Servers, user devices (PCs, smartphones, etc.)

[1589] Software: Generative AI models (e.g., GPT-4), user interfaces (e.g., web applications)

[1590] Data processing and calculation

[1591] Data Entry

[1592] A user uses a terminal to enter information for an RFI (Request for Information) or RFP (Request for Proposal). For example, the user enters, "Please provide me with the information to create a proposal for a new marketing campaign."

[1593] Data transmission

[1594] The device sends the input information to the server, converting it into an appropriate format and sending it to the server using a secure communication protocol (e.g., HTTPS).

[1595] Generate prediction results

[1596] The server inputs the received information into a generative AI model (e.g., GPT-4). The server formats the information into an appropriate format and calls the generative AI model's API. The generative AI model generates a prediction based on the input information. For example, the model may generate a prediction such as, "This campaign requires the following resources: advertising budget, target audience, and duration."

[1597] Presentation of results

[1598] The server sends the generated prediction results to the user interface. The server converts the prediction results into an appropriate format and calls the user interface's API. The user interface presents the prediction results to the user in an interactive format. The user can confirm the message "This campaign requires the following resources. Would you like to know more?" and click Details to get more information.

[1599] Specific examples

[1600] Prompt Sentence Examples

[1601] "Please provide us with information to create a proposal for a new marketing campaign."

[1602] "What are your sales forecasts for the next quarter?"

[1603] In this way, users can understand the contents of RFI / RFP in advance and plan appropriate responses. They can also receive proposals for reducing workload based on the prediction results, which is expected to improve work efficiency.

[1604] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1605] Step 1:

[1606] The user enters the information.

[1607] A user uses a device (PC or smartphone) to input information for an RFI (Request for Information) or RFP (Request for Proposal). For example, the user might input, "Please provide me with the information to create a proposal for a new marketing campaign." The input information is saved in text format on the device.

[1608] Step 2:

[1609] The terminal sends the input information to the server.

[1610] The terminal converts the user's input information into JSON format and sends it to the server using the HTTPS protocol. If the transmission is successful, the terminal displays a confirmation message saying "Information sent." The input data is sent to the server and received by the server.

[1611] Step 3:

[1612] The server inputs information into the generative AI model.

[1613] The server parses the received JSON data and sends a POST request to the API endpoint of the generative AI model. The request includes the information entered by the user. The server formats the data appropriately and inputs it into the generative AI model.

[1614] Step 4:

[1615] The generative AI model generates the predicted results.

[1616] The generative AI model receives the request and processes the data internally. After a few seconds, the model generates a prediction and returns it to the server. For example, the model may generate a prediction such as, "This campaign requires the following resources: advertising budget, target audience, and duration." The generated prediction is then returned to the server.

[1617] Step 5:

[1618] The server sends the prediction results to the user interface.

[1619] The server analyzes the prediction results received from the generative AI model and sends a POST request to the user interface API. The request contains the prediction results. The server converts the prediction results into an appropriate format and sends them to the user interface.

[1620] Step 6:

[1621] The user checks the prediction results.

[1622] The user interface receives the prediction results and displays them in the browser. The user can see the message "This campaign requires the following resources. Would you like to know more?" and click Details to get more information. The user can then plan appropriate actions based on the prediction results.

[1623] (Application example 2)

[1624] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1625] In conventional logistics centers, it was difficult to understand the contents of requests for information (RFI) and requests for proposals (RFP) in advance and plan appropriate responses. Furthermore, there was a lack of a way to present prediction results to users in an interactive format, which did not sufficiently reduce the workload.

[1626] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for interactively reading the other party's public information, requests for information, trends in materials presented by the information systems department, etc. in electronic documents, means for predicting the requests for information / requests for proposals to be presented based on the contents of the electronic documents, and means for interactively presenting the prediction results to the user. This makes it possible to interactively present the prediction results to the user at the logistics center using an application installed on a smartphone.

[1627] "Other party public information" refers to information that a company or organization has made public to the outside world.

[1628] A "RFI" is a request for specific information.

[1629] "Materials presented by the Information Systems Department" refers to materials prepared and presented by the Information Systems Department.

[1630] "Electronic document" means a document stored in digital form.

[1631] "Interaction style" refers to the way in which a user and a system interact with each other.

[1632] "Request for Information / Request for Proposal" means a request for specific information and a request for specific proposals.

[1633] "Prediction" means predicting future events or outcomes in advance.

[1634] "Prediction result" refers to information obtained as a result of prediction.

[1635] "User" means a person who uses the system.

[1636] "Work load reduction" means reducing the burden of work.

[1637] A "logistics center" is a facility that stores, sorts, and delivers goods.

[1638] A "smartphone" is a mobile phone that can connect to the Internet and use applications.

[1639] An "application" is software that realizes a specific function.

[1640] As an embodiment of the present invention, a system using an application installed on a smartphone at a logistics center will be described.

[1641] First, the server has a means for interactively reading electronic documents such as publicly disclosed information from the other party, requests for information, and trends in documents presented by the information systems department, allowing the server to efficiently collect and analyze this information.

[1642] Next, the server has a means for predicting requests for information (RFIs) and requests for proposals (RFPs) from the collected information. This means uses a generative AI model to predict the content of future RFIs / RFPs. Specifically, the server uses the OpenAI API to generate prediction results based on text entered by the user.

[1643] Furthermore, the server has a means for presenting the prediction results to the user in an interactive format, allowing the user to check the prediction results in real time through a smartphone application. The user interface presents the prediction results in an interactive format and supports the user in efficiently carrying out their work.

[1644] As a specific example, if a user enters, "I'm looking for a new logistics partner. What kind of proposals can I expect?", the server will use the generative AI model to present a predicted result: "Possible proposals that can be expected from a new logistics partner include cost reduction, shorter delivery times, and the introduction of a tracking system."

[1645] An example of a prompt is as follows:

[1646] "Anticipate what the RFI / RFP will say and present it in a conversational format: We're looking for a new logistics partner. What proposals can we expect?"

[1647] In this way, a system can be realized that supports the managers and staff of the logistics center in carrying out their work efficiently.

[1648] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1649] Step 1:

[1650] The server interactively reads electronic documents such as the other party's public information, requests for information, and trends in documents presented by the information systems department. These electronic documents are provided to the server as input. The server analyzes these documents and extracts the necessary information. The analyzed information is obtained as output.

[1651] Step 2:

[1652] The server predicts future Requests for Information (RFI) and Requests for Proposal (RFP) based on the information obtained in step 1. As input, the parsed information is provided to the server. The server uses a generative AI model (e.g., OpenAI API) to predict the content of future RFIs / RFPs. As output, the prediction results are obtained.

[1653] Step 3:

[1654] The server interactively presents the prediction results obtained in step 2 to the user. As input, the prediction results are provided to the server. The server interactively presents the prediction results to the user through a user interface. As output, the user can check the prediction results.

[1655] Step 4:

[1656] The user checks the prediction results presented by the server through a smartphone application. The prediction results from the server are provided to the smartphone as input. The user plans and responds to work based on the prediction results. The user's work plan and response are obtained as output.

[1657] Step 5:

[1658] When a user enters the details of a new request for information or proposal, the information is sent to the server via a smartphone application. The smartphone receives the information entered by the user as input. The server receives this information and performs another prediction. The output is a new prediction result.

[1659] In this way, a system is realized that supports the managers and staff of the logistics center in carrying out their work efficiently.

[1660] Example 3

[1661] Next, a third embodiment of the third embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1662] In the conventional workflow, it was difficult to predict the content of requests for information (RFI) and requests for proposals (RFP) in advance and propose optimal responses. In addition, business data was often collected and analyzed manually, making it difficult to efficiently reduce workloads. This resulted in insufficient efficiency and optimization of business operations, and there was a risk that the company's competitiveness would decline.

[1663] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1664] In this invention, the server includes a means for interactively reading public information from the other party, trends in information materials, etc. in electronic document format, a means for predicting information requests / proposal requests to be presented based on the content of the information, a means for collecting business data, a means for analyzing the collected business data, a means for generating prediction results based on the analysis results, and a means for proposing optimization of business flows based on the prediction results. This enables efficient collection and analysis of business data, and realizes proposals for optimal business flows based on the prediction results. This reduces work load and improves work efficiency.

[1665] "Other party public information" refers to information that a company or organization has made public.

[1666] "Information materials" are materials provided internally or externally by a company or organization.

[1667] "Electronic document format" means a document stored in a digital format.

[1668] "Interaction style" refers to the way in which a user and a system interact with each other.

[1669] An "information request" is a request for specific information.

[1670] "Request for Proposal" means a request for a specific proposal.

[1671] "Prediction" means predicting future events or situations in advance.

[1672] "Business data" refers to data related to the business of a company or organization.

[1673] "Collection" means gathering the necessary data and information.

[1674] "Analysis" means analyzing data or information to find meaning.

[1675] "Prediction results" refer to future predictions obtained based on the analysis.

[1676] "Business flow" refers to the procedures and processes for business progress.

[1677] An "optimization proposal" is a proposal for optimizing business flow.

[1678] The present invention is a system for reducing workload, in which a server, a terminal, and a user work in cooperation with each other. A specific embodiment of this system will be described below.

[1679] First, the server interactively reads publicly available information and trends in information materials in electronic document format, including common electronic document formats such as PDF and Word. The server then analyzes these documents using natural language processing technology and predicts requests for information (RFIs) and requests for proposals (RFPs) based on their content.

[1680] Next, the server collects business data from each department within the company, including the contents of past RFIs / RFPs, examples of successful and unsuccessful projects, and details of business processes. A relational database such as MySQL or PostgreSQL is used as the database.

[1681] The collected business data is preprocessed by the server and input into the AI ​​engine. The AI ​​engine analyzes the data using machine learning frameworks such as TensorFlow and PyTorch. The purpose of the analysis is to find patterns and trends within the data. The AI ​​engine analyzes the data and extracts important features.

[1682] The server generates predictions based on the results of the AI ​​engine's analysis. These predictions include bottlenecks and risks in future business processes, as well as the likelihood of success. These predictions are provided to users in the form of dashboards and reports.

[1683] Furthermore, the server generates workflow optimization proposals based on the prediction results. For example, if the content of a specific RFI / RFP matches a pattern based on past successes, it will propose specific countermeasures. This allows users to take specific actions to reduce their workload.

[1684] As a concrete example, consider the case where a user receives an RFP for a new project. The server analyzes the RFP and proposes the optimal solution based on the success of similar projects in the past.

[1685] Example prompt sentence:

[1686] "We've received an RFP for a new project. Please analyze the RFP and recommend the best solution based on past successes."

[1687] In this way, the system makes optimal proposals for reducing the workload through collaboration between the server, terminal, and user. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1688] Step 1:

[1689] The server interactively reads publicly available information from the other party and trends in information materials in electronic document format. Electronic documents such as PDF and Word documents are provided as input. The server analyzes these documents using natural language processing technology and extracts important information. The analyzed information is obtained as output. Specifically, the server reads the documents, performs text extraction, and identifies keywords and phrases.

[1690] Step 2:

[1691] The server predicts requests for information (RFIs) and requests for proposals (RFPs) in advance from the analyzed information. The analyzed information obtained in step 1 is given as input. The server uses a machine learning model to compare it with past data and predict future RFIs / RFPs. The output is the predicted RFIs / RFPs. Specifically, the server applies the prediction model to generate the predicted results.

[1692] Step 3:

[1693] The server collects business data from each department within the company. As input, it receives the business data provided by each department. The server saves the data in a database and extracts the necessary data. As output, it obtains the collected business data. Specifically, the server connects to the database and retrieves the data.

[1694] Step 4:

[1695] The server analyzes the collected business data. The business data obtained in step 3 is given as input. The server analyzes the data using an AI engine and extracts important features. The analysis results are obtained as output. Specifically, the server preprocesses the data and inputs it into the AI ​​engine.

[1696] Step 5:

[1697] The server generates a prediction result based on the analysis result. The analysis result obtained in step 4 is given as input. The server applies the prediction model to make a prediction about future business flows. The prediction result is obtained as output. Specifically, the server executes the prediction model and aggregates the results.

[1698] Step 6:

[1699] The server makes a proposal for optimizing the workflow based on the prediction results. The prediction results obtained in step 5 are given as input. The server refers to past examples of success and failure and proposes the optimal workflow. The output is an optimization proposal. Specifically, the server generates the proposal and notifies the user.

[1700] Step 7:

[1701] The user receives the optimization proposal provided by the server and adjusts the workflow. The optimization proposal from the server is given as input. The user checks the proposal and takes the necessary action. The output is the adjusted workflow. In concrete terms, the user reviews and executes the workflow based on the proposal.

[1702] (Application example 3)

[1703] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1704] The work flow at conventional logistics centers was often poorly predicted for workloads, and they were unable to respond appropriately when workloads increased. Furthermore, the work flow was not optimized, making it difficult to operate efficiently. This resulted in work delays, increased costs, and a decline in overall work efficiency.

[1705] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes means for interactively reading the other party's public information, trends in information materials, etc. in electronic documents, means for predicting the information request / proposal to be presented based on the contents of the electronic documents, means for analyzing business data and predicting the workload, and means for proposing optimization of the business flow based on the prediction results. This makes it possible to accurately predict the workload at the logistics center and propose optimal countermeasures to reduce the workload.

[1706] "Publicly disclosed information by the other party" refers to information and materials made public by companies and organizations, including press releases, official websites, reports, etc.

[1707] "Information materials" are materials provided internally or externally by a company or organization, including presentations, reports, data sheets, etc.

[1708] "Electronic document" refers to a document stored in a digital format, including PDFs, Word documents, Excel sheets, etc.

[1709] "Conversational" refers to the way in which users and systems interact with each other, including chatbots and interactive user interfaces.

[1710] "Request for Information" means a document requesting the provision of specific information, including a Request for Information (RFI).

[1711] "Request for Proposal" means a document requesting the submission of a specific proposal, including an RFP (Request for Proposal).

[1712] "Business data" refers to data related to the business of a company or organization, including work records, inventory data, shipping data, etc.

[1713] "Business volume" refers to the total volume of business within a specific period, including the number of transactions, working hours, and shipping volume.

[1714] "Business flow" refers to a series of steps or processes that show how work progresses, and includes work instructions and process maps.

[1715] "Optimization proposals" refer to proposals for streamlining business processes, including resource reallocation and improvements to work procedures.

[1716] The system for implementing this invention aims to optimize the workflow at a logistics center. The system has the function of interactively reading trends in publicly available information and provided information documents in electronic form and predicting requests for information (RFIs) and requests for proposals (RFPs) in advance based on the content. It also has the function of analyzing business data and predicting workload. Furthermore, it has the function of proposing workflow optimization based on the prediction results.

[1717] Hardware and software used

[1718] Hardware: Smartphones, servers

[1719] Software: Python, Pandas, Scikit-learn

[1720] System configuration

[1721] 1. Data Loading: The server loads the other party's public information and information materials in electronic document format, including PDF and Word documents.

[1722] 2. Prediction of Requests for Information / Requests for Proposal: The server analyzes the content of the loaded electronic documents and predicts Requests for Information (RFI) and Requests for Proposal (RFP) in advance.

[1723] 3. Analysis of business data: The server analyzes the business data of the logistics center and predicts the volume of work. Business data includes work records, inventory data, shipping data, etc.

[1724] 4. Workflow optimization proposals: Based on the prediction results, the server makes proposals for optimizing workflows, including resource reallocation and improvements to work procedures.

[1725] 5. User interface: Prediction results and optimization suggestions are presented to the user in an interactive format using a smartphone.

[1726] Processing flow

[1727] The server first reads and analyzes the other party's publicly available information and provided materials in electronic document format. Next, it uses a generative AI model to predict requests for information (RFIs) and requests for proposals (RFPs) in advance. It also analyzes the logistics center's operational data and predicts workloads. Based on the prediction results, it makes proposals for optimizing the workflow and presents them to the user in an interactive format.

[1728] Specific examples

[1729] For example, suppose the business data for a logistics center is in the following format:

[1730] csv

[1731] feature1,feature2,feature3,target

[1732] 10, 20, 30, 100

[1733] 15, 25, 35, 150

[1734] 20, 30, 40, 200

[1735] Example prompts to input to a generative AI model:

[1736] Create a program that analyzes operational data from a logistics center and proposes optimizations to reduce workload. The data is provided in CSV format, with feature1, feature2, and feature3 as features and target as target. Based on the prediction results, propose appropriate measures to prevent workload from increasing.

[1737] In this way, the system can streamline the workflow of the logistics center and provide optimal solutions to reduce the workload.

[1738] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1739] Step 1:

[1740] The server reads the other party's public information and information materials in electronic document format. PDF and Word documents are provided as input. The server analyzes these documents and converts them into text data. The analyzed text data is obtained as output.

[1741] Step 2:

[1742] The server predicts Request for Information (RFI) and Request for Proposal (RFP) in advance based on the analyzed text data. The text data obtained in step 1 is used as input. The server uses a generative AI model to detect specific patterns and generate prediction results. The output is the predicted content of the RFI or RFP.

[1743] Step 3:

[1744] The server reads the business data of the logistics center. The business data is provided in CSV format as input. The server reads the data using Pandas and sets features and targets. The features and targets are obtained as output.

[1745] Step 4:

[1746] The server predicts workload based on the workload data. The features and targets obtained in step 3 are used as input. The server trains a RandomForestRegressor model using Scikit-learn to make predictions. The predicted workload is obtained as output.

[1747] Step 5:

[1748] The server makes optimization proposals for the business flow based on the prediction results. The prediction results obtained in step 4 are used as input. The server refers to past successes and generates optimization proposals such as resource reallocation and improvements to work procedures. The optimization proposals are obtained as output.

[1749] Step 6:

[1750] The device (smartphone) presents the prediction results and optimization proposals to the user in an interactive format. The prediction results and optimization proposals obtained in steps 2 and 5 are used as input. The device uses an interactive user interface to present information to the user and prompt them to take necessary actions. The output is the information received by the user and the corresponding action.

[1751] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1752] "Example 1"

[1753] One embodiment of the present invention combines a system that includes a means for interactively reading public information, investor relations, and trends in documents presented by the information systems department in PDF format, a means for predicting RFIs / RFPs based on the content of such information, and an emotion engine that recognizes the user's emotions. This emotion engine recognizes emotions from the user's tone of voice, facial expressions, and choice of words, and feeds that information back to the system. For example, if the system determines that the user is feeling stressed, it takes that information into account and provides more appropriate RFI / RFP predictions.

[1754] "Example 2"

[1755] In another embodiment of the present invention, the system according to claim 2 is a system in which the means for interactively presenting prediction results to the user is combined with an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's reactions in real time and adjusts the presented prediction results according to the emotions. For example, if the user expresses surprise, the system takes this information into account and adjusts the level of detail in the prediction results.

[1756] "Example 3"

[1757] In a further embodiment of the present invention, the system according to claim 3 is a system in which the means for proposing workload reduction based on the prediction result is combined with an emotion engine that recognizes the user's emotions. This emotion engine recognizes the user's emotions and adjusts the workload reduction proposals according to those emotions. For example, if the user expresses anxiety, the system takes that information into account and makes more specific workload reduction proposals.

[1758] The processing flow of each embodiment will be described below.

[1759] "Example 1"

[1760] Step 1: The system interactively reads the other party's public information, IR, trends in materials presented by the Information Systems Department, etc. in PDF format.

[1761] Step 2: Based on the information read, the system predicts the contents of the RFI / RFP.

[1762] Step 3: At the same time, the emotion engine recognizes the user's emotions from their tone of voice, facial expressions, and language.

[1763] Step 4: The emotion engine feeds back the recognized emotion information to the system, which takes that information into account to provide more appropriate RFI / RFP prediction results.

[1764] "Example 2"

[1765] Step 1: The system presents the prediction results to the user in an interactive format.

[1766] Step 2: The emotion engine analyzes user reactions in real time.

[1767] Step 3: The emotion engine adjusts the predictions the system makes depending on the emotion it recognizes.

[1768] "Example 3"

[1769] Step 1: The system makes suggestions for reducing workload based on the prediction results.

[1770] Step 2: The emotion engine recognizes the user's emotion.

[1771] Step 3: The emotion engine adjusts the workload reduction suggestions made by the system according to the recognized emotion.

[1772] Example 1

[1773] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1774] Conventional request for information (RFI) and request for proposal (RFP) prediction systems do not fully utilize trends in publicly available information, financial information, or materials presented by the information systems department. Furthermore, the prediction results are not adjusted to take user emotions into account, which means that users' stress and anxiety cannot be alleviated. Furthermore, the lack of proposals for reducing workload based on the prediction results makes it difficult to improve users' work efficiency.

[1775] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1776] In this invention, the server includes means for interactively reading in electronic documents such as publicly disclosed information from the other party, financial information, and trends in materials presented by the information systems department, means for predicting requests for information / proposals to be presented based on the contents of the electronic documents, emotion recognition means for recognizing the user's emotions, and means for adjusting the prediction results based on the information obtained from the emotion recognition means. This enables more accurate RFI / RFP predictions that take the user's emotions into consideration, and makes it possible to make proposals to reduce the user's stress and anxiety while also reducing their workload.

[1777] "Other party public information" is information that a company or organization has made publicly available and that is publicly accessible through websites, reports, etc.

[1778] "Financial information" refers to information that shows the financial status of a company or organization, and is data contained in financial reports, settlement reports, etc.

[1779] "Information Systems Department Presentation Materials" are documents created and presented by the information systems department of a company or organization, and include information on the system's operational status, plans, and technical details.

[1780] An "electronic document" is a document stored in a digital format, including formats such as PDF and Word files.

[1781] "Interactive" refers to an interface in which the user and the system exchange information with each other, in the form of questions and answers.

[1782] A Request for Information (RFI) is a document issued by a company or organization to a supplier or partner, requesting the provision of specific information.

[1783] A "Request for Proposal (RFP)" is a document issued by a company or organization to suppliers or partners requesting proposals for a specific project or service.

[1784] "Prediction" is the prediction of future events or outcomes based on past data and trends.

[1785] "Emotion recognition means" refers to technology for analyzing and recognizing a user's emotions, and refers to a system that analyzes facial expressions, tone of voice, choice of words, etc.

[1786] "Means for adjusting predicted results" refers to technology that modifies or adjusts predicted results based on the user's emotional information.

[1787] The system of the present invention includes a means for interactively reading public information from the other party, financial information, and trends in materials presented by the information systems department in electronic documents, a means for predicting the requests for information (RFI) / requests for proposals (RFP) that will be presented based on the contents of the electronic documents, an emotion recognition means for recognizing the emotions of the user, and a means for adjusting the prediction results based on the information obtained from the emotion recognition means.

[1788] Hardware and software used

[1789] Hardware: Servers, user devices (PCs, tablets, smartphones, etc.)

[1790] Software: PDF readers, database management systems (e.g., MySQL, PostgreSQL), AI engines (e.g., TensorFlow, PyTorch), emotion recognition engines (e.g., Affectiva, Microsoft Azure Emotion API)

[1791] Specific operation of the system

[1792] 1. Data collection and storage

[1793] The server collects the other party's public information, financial information, and materials presented by the information systems department from the Internet.

[1794] What it does: The server automatically downloads PDF files from a company's official website or publicly available investor relations page and stores them in a MySQL database.

[1795] 2. Data Analysis

[1796] The server passes the accumulated PDF files to an AI engine, which analyzes their contents.

[1797] Specific operation: The server uses TensorFlow to extract text from PDF files and uses natural language processing techniques to extract keywords and topics.

[1798] 3. Predicting the contents of RFI / RFP

[1799] The server applies a generative AI model to predict the content of the RFI / RFP based on the analysis results.

[1800] Specific operation: The server uses a generative AI model (e.g., GPT-3) that has learned from past RFI / RFP data to generate items that are likely to be included in the next RFP.

[1801] 4. User Emotion Recognition

[1802] The device collects the user's tone of voice, facial expressions, and language choices through a camera and microphone.

[1803] How it works: When a user uses the system, the device captures their facial expressions with a camera and records their tone of voice with a microphone. These are then analyzed using Affectiva's API to recognize the user's emotions.

[1804] 5. Feedback and Adjustments

[1805] The server adjusts the prediction results based on the user's emotional information.

[1806] Specific behavior: If the user is feeling stressed, the server generates additional information to explain the prediction result in more detail.

[1807] Examples and prompts

[1808] Example: A system that predicts the content of the next RFP based on a company's financial information

[1809] The server downloads the company's latest financial reports and stores them in a database.

[1810] An AI engine analyzes the contents of the report and lists items that are likely to be included in the next RFP.

[1811] When a user uses the system, the emotion recognition engine analyzes the user's stress level and adjusts the prediction results.

[1812] Example prompt sentence:

[1813] Use the company's most recent financial report to predict what items are likely to be included in the next RFP. If users are feeling stressed, adjust your predictions to take that information into account.

[1814] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1815] Step 1:

[1816] Data collection

[1817] Input: URLs and file paths of the other party's public information, financial information, and documents presented by the Information Systems Department

[1818] Specific behavior: The server downloads the PDF file from the specified URL or file path.

[1819] Data processing: Temporarily save downloaded PDF files.

[1820] Output: Downloaded PDF file

[1821] Step 2:

[1822] Data accumulation

[1823] Input: Downloaded PDF file

[1824] Specific operation: The server saves the downloaded PDF file in a MySQL database, along with its metadata (collection date and time, file name, and source URL).

[1825] Data processing: Store PDF files and their metadata in a database.

[1826] Output: PDF files and metadata stored in a database

[1827] Step 3:

[1828] PDF analysis

[1829] Input: PDF files stored in the database

[1830] Specific operation: The server extracts text from PDF files using TensorFlow.

[1831] Data processing: The extracted text is analyzed using natural language processing techniques to extract important keywords and topics.

[1832] Output: Extracted keywords and topics

[1833] Step 4:

[1834] Saving analysis results

[1835] Input: Extracted keywords and topics

[1836] Specific operation: The server stores the extracted keywords and topics in a database.

[1837] Data processing: Store keywords and topics in a database.

[1838] Output: Keywords and topics stored in a database

[1839] Step 5:

[1840] RFI / RFP Content Prediction

[1841] Input: Keywords or topics stored in the database

[1842] Specific ...

Claims

[Claim 1] means for interactively reading electronic documents including the other party's public information and information materials; a means for converting the read electronic document into text data, and inputting a prompt sentence input by a user that instructs prediction of what will be required in the next information request or proposal request and the text data into a generative AI model, thereby analyzing the text data and predicting the content of at least one of the information request and the proposal request according to the prompt sentence; a means for determining whether the content of at least one of the predicted information request and the proposal request corresponds to a predetermined pattern based on the content of the predicted information request and the proposal request, and when the determination result indicates that the content corresponds to the predetermined pattern, extracting past success cases or failure cases associated with the predetermined pattern from a database as the content of a proposal for the optimization of the optimal business flow, and making a proposal; a means for recognizing emotions from at least one of a user's facial expression, tone of voice, and language, and adjusting the content of the optimization proposal by changing the level of detail or the format of the proposal according to the recognized emotion; A system including:

Images