system

Abstract

We provide the system. [Solution] Means of obtaining data from information sources, A means of analyzing and classifying the acquired data, A method for automatically generating proposals based on classified data, A means of reviewing and correcting the generated proposal on a mobile device and outputting it in digital format, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In corporate sales, it takes a lot of time to collect information, analyze it, and create a proposal before visiting a customer, and many sales employees have to do these tasks outside of working hours, which hinders efficient sales activities and overtime has become the norm. Also, there is a problem that it is difficult to accurately collect a wide range of information including the trends of competing companies and the industry in a short time and reflect it in the proposal.

Means for Solving the Problems

[0005] The present invention provides a system that includes means for acquiring data from an information source, means for analyzing and classifying the acquired data, means for automatically generating a proposal based on the classified data, and means for outputting the generated proposal. This enables sales staff to collect necessary information in a short time and create proposals efficiently, thereby improving the efficiency of sales activities and reducing overtime hours.

[0006] "Information sources" refer to public or private documents, web pages, news articles, etc., that serve as the starting point for obtaining data.

[0007] "Means of acquiring data" refers to the software or hardware functions used to search for and retrieve necessary information from a source.

[0008] "Means for analyzing acquired data" refers to functions that process collected data and extract meaningful information or patterns.

[0009] "Means of classification" refers to the function of dividing information obtained through analysis into specific categories or groups.

[0010] "Methods for automatically generating proposals" refers to functions that automatically create documents to be presented to customers using pre-configured templates or algorithms.

[0011] "Means of outputting the generated proposal" refers to functions for displaying, printing, or saving the completed proposal in digital format. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3]It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0013] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0018] In the following embodiments, the numbered communication I / F (Interface) is an interface that includes a communication processor, an antenna, and the like. 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), or Bluetooth (registered trademark).

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] This invention provides a system for streamlining information gathering, analysis, and proposal creation in sales activities. This system consists of a server, terminals, and users who operate them.

[0034] First, the server automatically collects data from registered sources. This includes using web crawling technology to retrieve corporate investor relations information, industry news, press releases, and more.

[0035] Next, the server analyzes the collected data using natural language processing and machine learning algorithms, classifying the information into customer information, competitor information, and industry information. The analyzed data is stored in an internal database, forming the basis for proposal creation.

[0036] Next, the server automatically generates a proposal based on pre-configured templates and analytical data. Here, the information is structured to include content tailored to customer needs, competitive analysis results, and industry trends.

[0037] The generated proposal is presented to the user via a terminal. The user can review the proposal and make modifications or add additional information to suit their specific client. This step further personalizes the proposal.

[0038] The terminal allows users to export finalized proposals in formats such as PDF, supporting presentation to clients and email sending. Operations are seamlessly performed through a user-friendly interface.

[0039] As a concrete example, consider the process by which a sales representative preparing a proposal for a major manufacturer uses this system. The user simply enters the name of the target company, and the server automatically collects and analyzes the relevant data. The proposal is generated based on a template and includes competitive analysis graphs and predictive data. Finally, the user can make any necessary adjustments and submit the completed proposal to the client.

[0040] In this way, this system reduces the burden on sales staff in information gathering, analysis, and proposal creation, thereby improving the overall efficiency of operations.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The server crawls data from specified sources based on pre-registered company names and related keywords. This process includes accessing official company IR information, news sites, and press release sites. The server parses the HTML of web pages and extracts text data.

[0044] Step 2:

[0045] The server analyzes the collected text data using natural language processing (NLP) techniques. Specifically, it extracts keywords and important phrases and analyzes the semantic relationships within the document. This allows the data to be classified into customer information, competitor information, and industry trends.

[0046] Step 3:

[0047] The server stores the analyzed information in a database and organizes the elements necessary for creating a proposal. The server uses machine learning algorithms to predict industry trends and generate insights into competitors' strategies.

[0048] Step 4:

[0049] The server automatically generates a proposal based on classified and analyzed information using a pre-configured proposal template. During this process, it generates graphs and tables to provide logical support for the proposal.

[0050] Step 5:

[0051] The terminal displays the completed proposal to the user. The user can preview the proposal, review its contents, and make adjustments. If necessary, they can enter additional information or customize it to meet the specific needs of a particular customer.

[0052] Step 6:

[0053] The terminal exports the user-reviewed and finalized proposal in PDF or PPTX format. The user then prepares the completed proposal for emailing or printing and submitting to the client.

[0054] (Example 1)

[0055] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0056] In modern business activities, efficient information gathering and analysis, as well as the creation of appropriate proposals, are essential. However, these processes are time-consuming and labor-intensive. Furthermore, manual research and proposal creation can limit the comprehensiveness of information and the quality of proposals, potentially reducing the effectiveness of sales activities. Therefore, there is a need for methods to automate the process from information gathering to proposal creation and improve efficiency.

[0057] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0058] In this invention, the server includes means for collecting information from information sources, means for analyzing and categorizing the collected information, and means for automatically generating documents based on the categorized information. This enables efficient information collection and analysis, as well as the automatic generation of high-quality proposals.

[0059] A "source of information" refers to an external or internal database or online resource that provides information.

[0060] "Means of information gathering" refers to the process of obtaining necessary information from information sources using specific algorithms or technologies.

[0061] "Means of analysis and classification" refers to the techniques and processes used to analyze acquired information and classify it into specific categories.

[0062] "Means of automatically generating documents" refers to the process of automatically creating documents such as proposals using a computer based on templates and collected and analyzed information.

[0063] "Means of distribution" refers to the technology used to transfer or send generated documents to the target terminal or destination.

[0064] A "scheduling function" refers to a function that automatically executes tasks such as information gathering and analysis at pre-set times and conditions.

[0065] An "editable format" refers to a file or document format that allows users to change or modify its content as needed.

[0066] "Means of converting to output format" refers to the technologies and processes used to convert edited documents into specific formats such as PDF.

[0067] "Means of storage or transmission" refers to means of storing generated or edited documents on digital media or delivering them to the required recipients.

[0068] This system consists of servers, terminals, and users, and automates everything from information gathering to proposal creation to streamline sales activities.

[0069] The server plays a crucial role in efficiently collecting and analyzing information. Specifically, it uses web crawling technologies such as Apache® Nutch and Scrapy to retrieve data from internet sources. The retrieved data is then processed using natural language processing with Python libraries like NLTK and spaCy, and analyzed using Scikit-learn's machine learning algorithms. This analysis classifies the data into customer information, competitor information, and industry information. The analyzed data is stored in a MySQL® database and forms the basis for proposal creation.

[0070] In generating proposals, the server automatically creates proposals using the Google Docs API based on a pre-configured template. This template includes customer names, industry analysis results, and competitor information. The generated proposals are saved in an editable format for distribution.

[0071] The terminal presents the generated proposal to the user and supports editing. Users can preview the proposal through the terminal and make adjustments and customizations to meet specific customer needs. The edited proposal can be converted to PDF format and is designed for easy export or email sending. In this way, the terminal provides a user-friendly interface and supports the finalization of the proposal.

[0072] A concrete example of this system's use is when a sales representative visits a manufacturer. The user enters the manufacturer's name, and the server automatically collects relevant information, analyzes it, and then creates a proposal using a template. This proposal includes competitive analysis graphs and industry trends, which the user can review, make adjustments, and then submit the final version to the customer in PDF format.

[0073] An example of a prompt message might be, "Collect the necessary data to generate a sales proposal for a major manufacturer, and compile the analysis results into a report."

[0074] This invention enables the streamlining of the sales process and reduces the burden of proposal creation through the collaboration of servers, terminals, and users.

[0075] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0076] Step 1:

[0077] The server collects information from various sources. The input is a list of URLs for specified sources, specifically using crawler software to retrieve the data. The server uses Apache Nutch and employs web crawling techniques to collect data from a variety of sources on the internet. This process outputs data such as corporate investor relations information, industry news, and press releases.

[0078] Step 2:

[0079] The server analyzes and categorizes the collected information. The input is the raw data collected in Step 1. The data is analyzed using natural language processing with Python libraries such as NLTK and spaCy. Furthermore, machine learning algorithms utilizing Scikit-learn are used to classify the data into customer information, competitor information, and industry information. The output here is structured, analyzed data.

[0080] Step 3:

[0081] The server automatically generates documents based on the categorized information. The input is the data categorized in step 2. The server uses the Google Docs API to automatically generate proposals by inserting the data into a pre-configured template. The proposals include customer names, industry analysis results, and competitor information, and an editable document is created as output.

[0082] Step 4:

[0083] The terminal presents the generated document to the user and supports the editing process. The input is the proposal from Step 3. The user reviews the proposal through the terminal and makes revisions as needed to meet the customer's specific needs. This process utilizes a user-friendly interface, allowing for easy previewing and editing. The output is the final, revised version of the document.

[0084] Step 5:

[0085] The terminal converts the edited document into an output format and stores or transmits it. The input is the document completed in step 4. It has the function to convert and save it in PDF format, and can be transmitted to the customer via email or other means as needed. This ensures that the proposal is submitted to the customer in a formal format.

[0086] (Application Example 1)

[0087] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0088] In modern sales activities, there is a demand for the rapid and effective generation of proposals for customers. However, traditional methods require a great deal of time and effort from information gathering to proposal creation, making it difficult to improve sales efficiency. Furthermore, in today's increasingly paperless world, the digital management and transmission systems for proposals are inadequate.

[0089] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0090] In this invention, the server includes means for acquiring data from an information source, means for analyzing and classifying the acquired data, and means for automatically generating a proposal based on the classified data. This allows sales representatives to immediately review and revise the generated proposal on a mobile information terminal such as a smartphone and send it to the customer in digital format. This significantly improves the efficiency of sales activities and reduces the workload.

[0091] "Information sources" refer to the locations or media from which data is collected, such as industry news and publicly available company information.

[0092] "Means of acquiring data" refers to methods and devices for collecting necessary data from information sources, such as using web crawling technology.

[0093] "Means for analyzing and classifying data" refers to methods or mechanisms for analyzing acquired data and assigning it to specific categories based on its content.

[0094] "Means for automatically generating proposals" refers to methods or devices for creating proposals using templates based on classified data.

[0095] A "portable information terminal" is a portable electronic device, including smartphones and tablets.

[0096] "Means of outputting in digital format" refers to methods or devices for saving a created document in an electronic file format and making it available for transmission to other digital devices.

[0097] To realize this application, the server automatically retrieves data from information sources. Specifically, it uses web crawling technology to collect necessary information from publicly available company information and industry news. Next, the server analyzes the collected data using natural language processing technology and machine learning algorithms, classifying it into customer information, competitor information, and industry information. This analyzed data is stored in an internal database. Furthermore, based on the classified data, a proposal is automatically generated using templates and data analysis results.

[0098] The terminal uses a smartphone or tablet as a personal information terminal to display the generated proposal. Through this terminal, users can review and revise the proposal, and, if necessary, export and send it in digital format.

[0099] As a concrete example, when a user enters the name of a client company, the server automatically collects and analyzes relevant data from the payment industry. At this time, a proposal including competitive analysis and industry trends is generated, allowing sales representatives to efficiently present proposals to clients.

[0100] An example of a prompt for a generative AI model might be: "How can I create an application that allows a sales representative at an online payment service company to generate proposals optimized for their client companies?"

[0101] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0102] Step 1:

[0103] The server uses web crawling technology to retrieve data from external sources. The input is search keywords, such as the client company name specified by the user, and the output is the collected raw data. This data is diverse, including publicly available company information, industry news, and press releases.

[0104] Step 2:

[0105] The server analyzes the collected raw data using natural language processing techniques and classifies it into customer information, competitor information, and industry information. The input is the raw data obtained in step 1, and the output is the analyzed and classified data. This step involves data processing such as keyword extraction, sentiment analysis, and name recognition.

[0106] Step 3:

[0107] The server stores the analyzed and classified data in an internal database. The input is the analyzed data generated in step 2, and the output is the information stored in the database. This procedure allows for efficient access to the data needed in subsequent steps.

[0108] Step 4:

[0109] The server automatically generates proposals using analytical data stored in the database and pre-built templates. The input is the analytical data and templates in the database, and the output is the completed proposal. This step specifically focuses on structuring the information to reflect customer needs and industry trends.

[0110] Step 5:

[0111] The terminal displays the generated proposal to the user on their mobile device. The input is the proposal generated in step 4, and the output is what is displayed on the user's screen. The user can review and modify this display, allowing for customization of the proposal.

[0112] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0113] This invention provides a system that, in addition to information gathering, analysis, and automatic proposal generation, also has the function of recognizing user emotions and customizing the content of the proposal. This system is realized through a configuration that combines a server, terminals, users, and an emotion engine.

[0114] First, the server crawls target information sources based on registered company names and keywords, and collects the necessary data. The collected data is analyzed using natural language processing (NLP) technology and classified into customer information, competitor information, and industry trends. This data is stored in a database and serves as the basis for creating proposals.

[0115] Next, the proposal is automatically generated using analytical data and pre-configured templates. Here, the emotion engine plays a crucial role. The terminal senses user input, such as facial expressions, voice, and text input, and the emotion engine analyzes this data. The emotion engine determines the user's emotional state and customizes the tone and content of the proposal based on that.

[0116] This system tailors proposals based on the user's desired emotions and nuances, providing a more personalized experience. For example, if a user is highly motivated, the proposal will use positive and forward-looking language. Conversely, if a more cautious approach is required, a more neutral and subdued tone will be applied.

[0117] Users can preview the proposal output via their device and make final adjustments. Furthermore, the emotion engine learns from past feedback, resulting in more refined proposals in the future.

[0118] Thus, the present invention is a system that takes user emotions into consideration, enabling more effective and personalized sales support. By introducing an emotion engine, user-centered proposal creation is achieved in a way that cannot be obtained through mere data analysis.

[0119] The following describes the processing flow.

[0120] Step 1:

[0121] The server crawls information sources based on pre-specified companies and related keywords, collecting data from web pages and news feeds. The server is programmed to extract meaningful information even from obfuscated data during this process.

[0122] Step 2:

[0123] The server analyzes the collected data using natural language processing (NLP) techniques. The analyzed data is categorized into customer information, competitor information, industry trends, and so on. This categorized information is then stored in a database as foundational information for generating proposals later.

[0124] Step 3:

[0125] The server uses stored classification information to automatically generate proposals based on pre-configured templates. These templates organize content according to a typical proposal structure and include features for inserting graphs and tables as visualizations.

[0126] Step 4:

[0127] The device receives input from the user and uses an emotion engine to analyze the user's emotions from their facial expressions, voice, and text. The emotion engine determines the user's current emotional state and dynamically adjusts the content and tone of the proposal based on that.

[0128] Step 5:

[0129] The device presents the user with a customized proposal based on the output of the emotion engine. The user can review the displayed proposal and make final adjustments to suit a specific client. The user can also edit parts of the proposal or add additional information as needed.

[0130] Step 6:

[0131] The device exports the finalized proposal in PDF or PPTX format. Users can then prepare this proposal for submission to the client or send it via email. After the proposal is used, feedback is incorporated into the sentiment engine to improve the accuracy and personalization of future proposal generation.

[0132] (Example 2)

[0133] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0134] Conventional information gathering and automated document generation systems have the challenge of difficulty in personalizing based on user emotions, and if the generated documents do not align with the user's emotions, they cannot provide effective suggestions or information.

[0135] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0136] In this invention, the server includes means for collecting information from information sources, means for analyzing and classifying the collected information, means for automatically generating documents based on the classified information, and means for analyzing the user's emotions and customizing the documents. This makes it possible to generate personalized documents that are appropriate to the user's emotions.

[0137] "Information sources" refer to websites and databases on the internet from which data and information are obtained.

[0138] "Means of collecting information" refers to the software or system mechanisms used to obtain necessary information from information sources.

[0139] "Means of analysis and classification" refers to technical methods for organizing acquired information according to specific criteria and making it identifiable.

[0140] "Methods for automatically generating documents" refers to the process of constructing documents using templates and generative AI models based on analyzed and classified information.

[0141] "Means of analyzing user emotions and customizing documents" refers to methods for analyzing a user's emotional state and modifying the content and tone of the generated document based on the results of that analysis.

[0142] "Means of output" refers to digital or analog methods used to present the generated document to the user.

[0143] This invention is an embodiment of a system that includes information gathering, automatic document generation, and document customization through user sentiment analysis. This system is composed of a server, terminals, users, and a sentiment engine.

[0144] The server collects necessary information from multiple sources. Specifically, the server uses crawling software to crawl websites and databases. Technologies used include Python's BeautifulSoup and Scrapy. The collected information is analyzed using natural language processing (NLP) techniques. The Python spaCy library is used for analysis, and the information is classified as customer information, competitor information, or industry trends.

[0145] Subsequently, the server automatically generates documents based on the analyzed information. This generation process utilizes templates and a generation AI model. This ensures that the information is structured into an appropriate document format. The generated documents can then be used as business proposals or reports.

[0146] The device's role is to capture and analyze the user's emotions. Using its built-in camera and microphone, the device acquires the user's facial expressions and voice, and sends this data to the emotion engine. The emotion engine analyzes the acquired data and uses emotion recognition software to identify the user's emotional state. This may involve using services such as Microsoft® Azure®'s Emotion API.

[0147] Users can preview documents generated through their devices before receiving them. By using emotional data, the tone of the document is adjusted, resulting in more personalized proposals. For example, if a user requests event planning, the emotional engine will detect high motivation, adding an energetic tone to the generated document. Conversely, if caution is required, a neutral and calm tone will be reflected.

[0148] As a concrete example, here is an example of a prompt sentence to give to a generative AI model:

[0149] "I'm planning a weekend event for businesses. Please create a proposal that will motivate participants and deliver maximum results within the budget."

[0150] In this way, the system enables flexible document generation that meets the user's needs.

[0151] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0152] Step 1:

[0153] The server collects necessary information from information sources. Inputs are registered company names and keywords, and output is the collected raw data. Specifically, the server uses crawling software to traverse websites and databases based on specified keywords. The crawled data is stored on the server in HTML or Raw Text format.

[0154] Step 2:

[0155] The server analyzes and classifies the collected information. The input is the raw data obtained in step 1, and the output is the classified information. The server uses natural language processing libraries such as Python's spaCy to analyze the text data and classify it into customer information, competitor information, and industry trends. Morphological analysis and contextual analysis are performed to achieve data categorization.

[0156] Step 3:

[0157] The server automatically generates documents based on the classified information. The input is the classified information obtained in step 2, and the output is the generated document. The server combines a template engine and a generative AI model to incorporate the information into the appropriate document format. For example, the template engine uses Jinja2 to insert information into a pre-designed template to complete the document.

[0158] Step 4:

[0159] The device captures and analyzes the user's emotions. Input is the user's facial expressions and voice, and output is emotion data. The device uses its built-in camera and microphone to record and photograph the user's interactions. This data is sent to an emotion engine, where the emotional state is identified. Specifically, emotion recognition software analyzes the user's facial muscle movements and voice tone.

[0160] Step 5:

[0161] The server customizes the document based on sentiment data. The input is the sentiment data obtained in step 4, and the output is the customized document. The server fine-tunes the tone and content of the document according to the results of the sentiment engine. For example, if the user is highly motivated, the server changes the wording of the document to be more positive.

[0162] Step 6:

[0163] The user receives and previews the customized document through their device. The input is the document generated in step 5, and the output is the final, adjusted document. The user reviews the appropriateness of the proposals and wording, and makes corrections and revisions to the document as needed. This completes the personalized business document.

[0164] (Application Example 2)

[0165] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0166] In modern society, with the sheer volume of information available, information gathering and analysis are essential for making accurate recommendations. However, general recommendation systems struggle to provide nuanced responses that take into account the emotions of users. Furthermore, even in providing information related to safety, there is a problem in being unable to respond to situations where appropriate recommendations are required based on the emotional state of the user.

[0167] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0168] In this invention, the server includes means for acquiring data from information sources, means for analyzing and classifying the acquired data, means for automatically generating proposals based on the classified data, means for outputting the generated proposals, means for detecting the user's emotions and adjusting the proposals based on those emotions, and means for collecting information on safety and proposing safety improvement measures that correspond to the user's emotions. This enables personalized responses that take into account the user's emotions, making it possible to provide more accurate and reassuring information and proposals.

[0169] "Information sources" refer to documents, databases, and other materials that serve as the starting point for acquiring data.

[0170] "Means of acquiring data" refers to technical means for automatically collecting necessary data from information sources.

[0171] "Means for analyzing and classifying data" refers to technical means for analyzing acquired data and classifying it according to specific criteria.

[0172] "Methods for automatically generating proposals" refers to methods for automatically creating proposals using templates based on analyzed and classified data.

[0173] "Means for outputting the generated proposal" refers to the technical means for providing the created proposal to the user.

[0174] "Means for detecting user emotions and adjusting proposals based on those emotions" refers to methods for analyzing user emotions from facial expressions, voice, etc., and changing the content and tone of proposals accordingly.

[0175] "Means of collecting safety-related information and proposing safety improvement measures that respond to users' emotions" refers to means of collecting safety-related information and providing optimal safety measures that are tailored to the emotional state of users.

[0176] In this embodiment of the invention, the server first retrieves relevant data from an information source. The retrieved data is analyzed and classified using natural language processing technology. This organizes the information of interest to the user and forms the basis for automatic proposal generation. Based on the analyzed and classified data, the server automatically generates a proposal using a pre-configured template.

[0177] Next, the device provides an interface for detecting the user's emotions. Using the camera and microphone built into the device, it collects the user's facial expressions and voice, and analyzes the emotions using open-source emotion recognition libraries (e.g., OpenCV or TENSORFLOW®). Upon receiving the emotion information, the device sends the analysis results to the server, which then adjusts the content and tone of the proposal. This enables personalized proposals tailored to the user's emotions.

[0178] Furthermore, the server collects security-related information and proposes security enhancement measures tailored to the user's feelings. This allows users to act with confidence and take appropriate actions depending on the situation.

[0179] For example, if a user traveling uses their device and the system detects that they are experiencing emotional instability, the server can quickly provide the latest safety information for the area and offer specific action plans to enhance safety. This proposal, outlining the safety measures, is then output to the user via their device.

[0180] Another example of a prompt for a generative AI model is, "If the user is feeling anxious, how should you create suggestions for safe travel?" This allows the AI ​​to provide appropriate information to alleviate the user's anxiety.

[0181] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0182] Step 1:

[0183] The server crawls information sources based on registered keywords and company names to retrieve data. The input consists of keywords and company names pre-set by the user, and the output is a collection of relevant data. Web scraping and API access are used for data retrieval.

[0184] Step 2:

[0185] The server analyzes the acquired data using natural language processing (NLP) techniques and classifies it into customer information, competitor information, and industry trends. The input is the data set obtained in step 1, and the output is the analyzed and classified data. NLP techniques include morphological analysis and text mining.

[0186] Step 3:

[0187] The server automatically generates proposals using pre-configured templates based on classified data. The input is classified data, and the output is a basic proposal document. This generation process utilizes a template engine, embedding the necessary information into the template.

[0188] Step 4:

[0189] The device uses a camera and microphone to collect the user's facial expressions and voice, and detects emotions using an emotion recognition library. The input is the user's voice and video data, and the output is the analyzed emotional state. This process involves facial recognition and voice analysis.

[0190] Step 5:

[0191] The server receives emotional information and adjusts the content and tone of the proposal according to the user's emotions. The input is the user's emotional information and the existing proposal; the output is the adjusted proposal. This enables personalized service that takes the user's emotions into consideration.

[0192] Step 6:

[0193] The server collects security-related information and proposes security enhancements tailored to the user's emotional state. Inputs are available security information and the user's emotional state, while outputs are user-specific reassurance measures. This includes real-time data feeding and analysis.

[0194] Step 7:

[0195] The user reviews the final proposal output via the terminal. The input here is the proposal generated through steps 5 and 6, while the output is the user's feedback and subsequent fine-tuning. Additional manual editing is also possible in this final step.

[0196] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0197] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0198] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0199] [Second Embodiment]

[0200] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0201] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0202] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0203] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0204] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0205] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0206] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0207] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0208] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0209] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0210] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0211] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0212] This invention provides a system for streamlining information gathering, analysis, and proposal creation in sales activities. This system consists of a server, terminals, and users who operate them.

[0213] First, the server automatically collects data from registered sources. This includes using web crawling technology to retrieve corporate investor relations information, industry news, press releases, and more.

[0214] Next, the server analyzes the collected data using natural language processing and machine learning algorithms, classifying the information into customer information, competitor information, and industry information. The analyzed data is stored in an internal database, forming the basis for proposal creation.

[0215] Next, the server automatically generates a proposal based on pre-configured templates and analytical data. Here, the information is structured to include content tailored to customer needs, competitive analysis results, and industry trends.

[0216] The generated proposal is presented to the user via a terminal. The user can review the proposal and make modifications or add additional information to suit their specific client. This step further personalizes the proposal.

[0217] The terminal allows users to export finalized proposals in formats such as PDF, supporting presentation to clients and email sending. Operations are seamlessly performed through a user-friendly interface.

[0218] As a concrete example, consider the process by which a sales representative preparing a proposal for a major manufacturer uses this system. The user simply enters the name of the target company, and the server automatically collects and analyzes the relevant data. The proposal is generated based on a template and includes competitive analysis graphs and predictive data. Finally, the user can make any necessary adjustments and submit the completed proposal to the client.

[0219] In this way, this system reduces the burden on sales staff in information gathering, analysis, and proposal creation, thereby improving the overall efficiency of operations.

[0220] The following describes the processing flow.

[0221] Step 1:

[0222] The server crawls data from specified sources based on pre-registered company names and related keywords. This process includes accessing official company IR information, news sites, and press release sites. The server parses the HTML of web pages and extracts text data.

[0223] Step 2:

[0224] The server analyzes the collected text data using natural language processing (NLP) techniques. Specifically, it extracts keywords and important phrases and analyzes the semantic relationships within the document. This allows the data to be classified into customer information, competitor information, and industry trends.

[0225] Step 3:

[0226] The server stores the analyzed information in a database and organizes the elements necessary for creating a proposal. The server uses machine learning algorithms to predict industry trends and generate insights into competitors' strategies.

[0227] Step 4:

[0228] The server automatically generates a proposal based on classified and analyzed information using a pre-configured proposal template. During this process, it generates graphs and tables to provide logical support for the proposal.

[0229] Step 5:

[0230] The terminal displays the completed proposal to the user. The user can preview the proposal, review its contents, and make adjustments. If necessary, they can enter additional information or customize it to meet the specific needs of a particular customer.

[0231] Step 6:

[0232] The terminal exports the user-reviewed and finalized proposal in PDF or PPTX format. The user then prepares the completed proposal for emailing or printing and submitting to the client.

[0233] (Example 1)

[0234] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0235] In modern business activities, efficient information gathering and analysis, as well as the creation of appropriate proposals, are essential. However, these processes are time-consuming and labor-intensive. Furthermore, manual research and proposal creation can limit the comprehensiveness of information and the quality of proposals, potentially reducing the effectiveness of sales activities. Therefore, there is a need for methods to automate the process from information gathering to proposal creation and improve efficiency.

[0236] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0237] In this invention, the server includes means for collecting information from information sources, means for analyzing and categorizing the collected information, and means for automatically generating documents based on the categorized information. This enables efficient information collection and analysis, as well as the automatic generation of high-quality proposals.

[0238] A "source of information" refers to an external or internal database or online resource that provides information.

[0239] "Means of information gathering" refers to the process of obtaining necessary information from information sources using specific algorithms or technologies.

[0240] "Means of analysis and classification" refers to the techniques and processes used to analyze acquired information and classify it into specific categories.

[0241] "Means of automatically generating documents" refers to the process of automatically creating documents such as proposals using a computer based on templates and collected and analyzed information.

[0242] "Means of distribution" refers to the technology used to transfer or send generated documents to the target terminal or destination.

[0243] A "scheduling function" refers to a function that automatically executes tasks such as information gathering and analysis at pre-set times and conditions.

[0244] An "editable format" refers to a file or document format that allows users to change or modify its content as needed.

[0245] "Means of converting to output format" refers to the technologies and processes used to convert edited documents into specific formats such as PDF.

[0246] "Means of storage or transmission" refers to means of storing generated or edited documents on digital media or delivering them to the required recipients.

[0247] This system consists of servers, terminals, and users, and automates everything from information gathering to proposal creation to streamline sales activities.

[0248] The server plays a crucial role in efficiently collecting and analyzing information. Specifically, it uses web crawling technologies such as Apache Nutch and Scrapy to retrieve data from internet sources. The retrieved data is then processed using natural language processing with Python libraries like NLTK and spaCy, and analyzed using Scikit-learn's machine learning algorithms. This analysis classifies the data into customer information, competitor information, and industry information. The analyzed data is stored in a MySQL database and forms the basis for proposal creation.

[0249] In generating proposals, the server automatically creates proposals using the Google Docs API based on a pre-configured template. This template includes customer names, industry analysis results, and competitor information. The generated proposals are saved in an editable format for distribution.

[0250] The terminal presents the generated proposal to the user and supports editing. Users can preview the proposal through the terminal and make adjustments and customizations to meet specific customer needs. The edited proposal can be converted to PDF format and is designed for easy export or email sending. In this way, the terminal provides a user-friendly interface and supports the finalization of the proposal.

[0251] A concrete example of this system's use is when a sales representative visits a manufacturer. The user enters the manufacturer's name, and the server automatically collects relevant information, analyzes it, and then creates a proposal using a template. This proposal includes competitive analysis graphs and industry trends, which the user can review, make adjustments, and then submit the final version to the customer in PDF format.

[0252] An example of a prompt message might be, "Collect the necessary data to generate a sales proposal for a major manufacturer, and compile the analysis results into a report."

[0253] This invention enables the streamlining of the sales process and reduces the burden of proposal creation through the collaboration of servers, terminals, and users.

[0254] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0255] Step 1:

[0256] The server collects information from various sources. The input is a list of URLs for specified sources, specifically using crawler software to retrieve the data. The server uses Apache Nutch and employs web crawling techniques to collect data from a variety of sources on the internet. This process outputs data such as corporate investor relations information, industry news, and press releases.

[0257] Step 2:

[0258] The server analyzes and categorizes the collected information. The input is the raw data collected in Step 1. The data is analyzed using natural language processing with Python libraries such as NLTK and spaCy. Furthermore, machine learning algorithms utilizing Scikit-learn are used to classify the data into customer information, competitor information, and industry information. The output here is structured, analyzed data.

[0259] Step 3:

[0260] The server automatically generates documents based on the categorized information. The input is the data categorized in step 2. The server uses the Google Docs API to automatically generate proposals by inserting the data into a pre-configured template. The proposals include customer names, industry analysis results, and competitor information, and an editable document is created as output.

[0261] Step 4:

[0262] The terminal presents the generated document to the user and supports the editing process. The input is the proposal from Step 3. The user reviews the proposal through the terminal and makes revisions as needed to meet the customer's specific needs. This process utilizes a user-friendly interface, allowing for easy previewing and editing. The output is the final, revised version of the document.

[0263] Step 5:

[0264] The terminal converts the edited document into an output format and stores or transmits it. The input is the document completed in step 4. It has the function to convert and save it in PDF format, and can be transmitted to the customer via email or other means as needed. This ensures that the proposal is submitted to the customer in a formal format.

[0265] (Application Example 1)

[0266] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0267] In modern sales activities, there is a demand for the rapid and effective generation of proposals for customers. However, traditional methods require a great deal of time and effort from information gathering to proposal creation, making it difficult to improve sales efficiency. Furthermore, in today's increasingly paperless world, the digital management and transmission systems for proposals are inadequate.

[0268] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0269] In this invention, the server includes means for acquiring data from an information source, means for analyzing and classifying the acquired data, and means for automatically generating a proposal based on the classified data. This allows sales representatives to immediately review and revise the generated proposal on a mobile information terminal such as a smartphone and send it to the customer in digital format. This significantly improves the efficiency of sales activities and reduces the workload.

[0270] "Information sources" refer to the locations or media from which data is collected, such as industry news and publicly available company information.

[0271] "Means of acquiring data" refers to methods and devices for collecting necessary data from information sources, such as using web crawling technology.

[0272] "Means for analyzing and classifying data" refers to methods or mechanisms for analyzing acquired data and assigning it to specific categories based on its content.

[0273] "Means for automatically generating proposals" refers to methods or devices for creating proposals using templates based on classified data.

[0274] A "portable information terminal" is a portable electronic device, including smartphones and tablets.

[0275] "Means of outputting in digital format" refers to methods or devices for saving a created document in an electronic file format and making it available for transmission to other digital devices.

[0276] To realize this application, the server automatically retrieves data from information sources. Specifically, it uses web crawling technology to collect necessary information from publicly available company information and industry news. Next, the server analyzes the collected data using natural language processing technology and machine learning algorithms, classifying it into customer information, competitor information, and industry information. This analyzed data is stored in an internal database. Furthermore, based on the classified data, a proposal is automatically generated using templates and data analysis results.

[0277] The terminal uses a smartphone or tablet as a personal information terminal to display the generated proposal. Through this terminal, users can review and revise the proposal, and, if necessary, export and send it in digital format.

[0278] As a concrete example, when a user enters the name of a client company, the server automatically collects and analyzes relevant data from the payment industry. At this time, a proposal including competitive analysis and industry trends is generated, allowing sales representatives to efficiently present proposals to clients.

[0279] As an example of a prompt sentence for a generative AI model, "How can an application be created for a salesperson of a company providing an online payment service to generate an optimized proposal for a client company?" can be considered.

[0280] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0281] Step 1:

[0282] The server acquires data from an external information source using web crawling technology. The input is a search keyword such as the client company name specified by the user, and the output is the raw data collected. This data covers a wide range, including publicly available company information, industry news, press releases, etc.

[0283] Step 2:

[0284] The server analyzes the collected raw data using natural language processing technology and classifies it into customer information, competitive information, and industry information. The input is the raw data obtained in Step 1, and the output is the analyzed and classified data. In this step, data processing such as keyword extraction, sentiment analysis, and name identification is performed.

[0285] Step 3:

[0286] The server stores the analyzed and classified data in an internal database. The input is the analyzed data generated in Step 2, and the output is the information stored in the database. By this procedure, the data required in subsequent steps can be efficiently accessed.

[0287] Step 4:

[0288] The server automatically generates proposals using analytical data stored in the database and pre-built templates. The input is the analytical data and templates in the database, and the output is the completed proposal. This step specifically focuses on structuring the information to reflect customer needs and industry trends.

[0289] Step 5:

[0290] The terminal displays the generated proposal to the user on their mobile device. The input is the proposal generated in step 4, and the output is what is displayed on the user's screen. The user can review and modify this display, allowing for customization of the proposal.

[0291] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0292] This invention provides a system that, in addition to information gathering, analysis, and automatic proposal generation, also has the function of recognizing user emotions and customizing the content of the proposal. This system is realized through a configuration that combines a server, terminals, users, and an emotion engine.

[0293] First, the server crawls target information sources based on registered company names and keywords, and collects the necessary data. The collected data is analyzed using natural language processing (NLP) technology and classified into customer information, competitor information, and industry trends. This data is stored in a database and serves as the basis for creating proposals.

[0294] Next, the proposal is automatically generated using analytical data and pre-configured templates. Here, the emotion engine plays a crucial role. The terminal senses user input, such as facial expressions, voice, and text input, and the emotion engine analyzes this data. The emotion engine determines the user's emotional state and customizes the tone and content of the proposal based on that.

[0295] This system tailors proposals based on the user's desired emotions and nuances, providing a more personalized experience. For example, if a user is highly motivated, the proposal will use positive and forward-looking language. Conversely, if a more cautious approach is required, a more neutral and subdued tone will be applied.

[0296] Users can preview the proposal output via their device and make final adjustments. Furthermore, the emotion engine learns from past feedback, resulting in more refined proposals in the future.

[0297] Thus, the present invention is a system that takes user emotions into consideration, enabling more effective and personalized sales support. By introducing an emotion engine, user-centered proposal creation is achieved in a way that cannot be obtained through mere data analysis.

[0298] The following describes the processing flow.

[0299] Step 1:

[0300] The server crawls information sources based on pre-specified companies and related keywords, collecting data from web pages and news feeds. The server is programmed to extract meaningful information even from obfuscated data during this process.

[0301] Step 2:

[0302] The server analyzes the collected data using natural language processing (NLP) technology. The analyzed data is classified into categories such as customer information, competitive information, and industry trends. These classified information are stored in a database as the base information for generating proposals later.

[0303] Step 3:

[0304] The server uses the stored classified information to automatically generate a proposal based on a pre-set template. This template summarizes the content according to the general structure of a proposal and has the function of inserting graphs and tables as visualizations.

[0305] Step 4:

[0306] The terminal receives input from the user and analyzes the emotion from the user's expression, voice, and text using an emotion engine. The emotion engine determines the user's current emotional state and dynamically adjusts the content and tone of the proposal based on it.

[0307] Step 5:

[0308] The terminal presents the customized proposal to the user based on the output of the emotion engine. The user can check the displayed proposal and make final adjustments according to a specific customer. Also, the user can edit a part of the proposal or add additional information as needed.

[0309] Step 6:

[0310] The terminal exports the finalized proposal in PDF or PPTX format. The user can prepare to submit this proposal to the customer or send it by email. After using the proposal, the feedback is incorporated into the emotion engine, improving the accuracy and personalization of proposal generation for subsequent times.

[0311] (Example 2)

[0312] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0313] Conventional information gathering and automated document generation systems have the challenge of difficulty in personalizing based on user emotions, and if the generated documents do not align with the user's emotions, they cannot provide effective suggestions or information.

[0314] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0315] In this invention, the server includes means for collecting information from information sources, means for analyzing and classifying the collected information, means for automatically generating documents based on the classified information, and means for analyzing the user's emotions and customizing the documents. This makes it possible to generate personalized documents that are appropriate to the user's emotions.

[0316] "Information sources" refer to websites and databases on the internet from which data and information are obtained.

[0317] "Means of collecting information" refers to the software or system mechanisms used to obtain necessary information from information sources.

[0318] "Means of analysis and classification" refers to technical methods for organizing acquired information according to specific criteria and making it identifiable.

[0319] "Methods for automatically generating documents" refers to the process of constructing documents using templates and generative AI models based on analyzed and classified information.

[0320] "Means of analyzing user emotions and customizing documents" refers to methods for analyzing a user's emotional state and modifying the content and tone of the generated document based on the results of that analysis.

[0321] "Means of output" refers to digital or analog methods used to present the generated document to the user.

[0322] This invention is an embodiment of a system that includes information gathering, automatic document generation, and document customization through user sentiment analysis. This system is composed of a server, terminals, users, and a sentiment engine.

[0323] The server collects necessary information from multiple sources. Specifically, the server uses crawling software to crawl websites and databases. Technologies used include Python's BeautifulSoup and Scrapy. The collected information is analyzed using natural language processing (NLP) techniques. The Python spaCy library is used for analysis, and the information is classified as customer information, competitor information, or industry trends.

[0324] Subsequently, the server automatically generates documents based on the analyzed information. This generation process utilizes templates and a generation AI model. This ensures that the information is structured into an appropriate document format. The generated documents can then be used as business proposals or reports.

[0325] The device's role is to capture and analyze the user's emotions. It uses its built-in camera and microphone to capture the user's facial expressions and voice, and sends this data to the emotion engine. The emotion engine analyzes the acquired data and uses emotion recognition software to identify the user's emotional state. Microsoft Azure's Emotion API, for example, is often used.

[0326] Users can preview documents generated through their devices before receiving them. By using emotional data, the tone of the document is adjusted, resulting in more personalized proposals. For example, if a user requests event planning, the emotional engine will detect high motivation, adding an energetic tone to the generated document. Conversely, if caution is required, a neutral and calm tone will be reflected.

[0327] As a concrete example, here is an example of a prompt sentence to give to a generative AI model:

[0328] "I'm planning a weekend event for businesses. Please create a proposal that will motivate participants and deliver maximum results within the budget."

[0329] In this way, the system enables flexible document generation that meets the user's needs.

[0330] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0331] Step 1:

[0332] The server collects necessary information from information sources. Inputs are registered company names and keywords, and output is the collected raw data. Specifically, the server uses crawling software to traverse websites and databases based on specified keywords. The crawled data is stored on the server in HTML or Raw Text format.

[0333] Step 2:

[0334] The server analyzes and classifies the collected information. The input is the raw data obtained in step 1, and the output is the classified information. The server uses natural language processing libraries such as Python's spaCy to analyze the text data and classify it into customer information, competitor information, and industry trends. Morphological analysis and contextual analysis are performed to achieve data categorization.

[0335] Step 3:

[0336] The server automatically generates documents based on the classified information. The input is the classified information obtained in step 2, and the output is the generated document. The server combines a template engine and a generative AI model to incorporate the information into the appropriate document format. For example, the template engine uses Jinja2 to insert information into a pre-designed template to complete the document.

[0337] Step 4:

[0338] The device captures and analyzes the user's emotions. Input is the user's facial expressions and voice, and output is emotion data. The device uses its built-in camera and microphone to record and photograph the user's interactions. This data is sent to an emotion engine, where the emotional state is identified. Specifically, emotion recognition software analyzes the user's facial muscle movements and voice tone.

[0339] Step 5:

[0340] The server customizes the document based on sentiment data. The input is the sentiment data obtained in step 4, and the output is the customized document. The server fine-tunes the tone and content of the document according to the results of the sentiment engine. For example, if the user is highly motivated, the server changes the wording of the document to be more positive.

[0341] Step 6:

[0342] The user receives and previews the customized document through their device. The input is the document generated in step 5, and the output is the final, adjusted document. The user reviews the appropriateness of the proposals and wording, and makes corrections and revisions to the document as needed. This completes the personalized business document.

[0343] (Application Example 2)

[0344] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0345] In modern society, with the sheer volume of information available, information gathering and analysis are essential for making accurate recommendations. However, general recommendation systems struggle to provide nuanced responses that take into account the emotions of users. Furthermore, even in providing information related to safety, there is a problem in being unable to respond to situations where appropriate recommendations are required based on the emotional state of the user.

[0346] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0347] In this invention, the server includes means for acquiring data from information sources, means for analyzing and classifying the acquired data, means for automatically generating proposals based on the classified data, means for outputting the generated proposals, means for detecting the user's emotions and adjusting the proposals based on those emotions, and means for collecting information on safety and proposing safety improvement measures that correspond to the user's emotions. This enables personalized responses that take into account the user's emotions, making it possible to provide more accurate and reassuring information and proposals.

[0348] "Information sources" refer to documents, databases, and other materials that serve as the starting point for acquiring data.

[0349] "Means of acquiring data" refers to technical means for automatically collecting necessary data from information sources.

[0350] "Means for analyzing and classifying data" refers to technical means for analyzing acquired data and classifying it according to specific criteria.

[0351] "Methods for automatically generating proposals" refers to methods for automatically creating proposals using templates based on analyzed and classified data.

[0352] "Means for outputting the generated proposal" refers to the technical means for providing the created proposal to the user.

[0353] "Means for detecting user emotions and adjusting proposals based on those emotions" refers to methods for analyzing user emotions from facial expressions, voice, etc., and changing the content and tone of proposals accordingly.

[0354] "Means of collecting safety-related information and proposing safety improvement measures that respond to users' emotions" refers to means of collecting safety-related information and providing optimal safety measures that are tailored to the emotional state of users.

[0355] In this embodiment of the invention, the server first retrieves relevant data from an information source. The retrieved data is analyzed and classified using natural language processing technology. This organizes the information of interest to the user and forms the basis for automatic proposal generation. Based on the analyzed and classified data, the server automatically generates a proposal using a pre-configured template.

[0356] Next, the device provides an interface for detecting the user's emotions. Using the camera and microphone built into the device, it collects the user's facial expressions and voice, and analyzes the emotions using open-source emotion recognition libraries (e.g., OpenCV or TensorFlow). Upon receiving the emotion information, the device sends the analysis results to the server, which then adjusts the content and tone of the proposal. This enables personalized proposals tailored to the user's emotions.

[0357] Furthermore, the server collects security-related information and proposes security enhancement measures tailored to the user's feelings. This allows users to act with confidence and take appropriate actions depending on the situation.

[0358] For example, if a user traveling uses their device and the system detects that they are experiencing emotional instability, the server can quickly provide the latest safety information for the area and offer specific action plans to enhance safety. This proposal, outlining the safety measures, is then output to the user via their device.

[0359] Another example of a prompt for a generative AI model is, "If the user is feeling anxious, how should you create suggestions for safe travel?" This allows the AI ​​to provide appropriate information to alleviate the user's anxiety.

[0360] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0361] Step 1:

[0362] The server crawls information sources based on registered keywords and company names to retrieve data. The input consists of keywords and company names pre-set by the user, and the output is a collection of relevant data. Web scraping and API access are used for data retrieval.

[0363] Step 2:

[0364] The server analyzes the acquired data using natural language processing (NLP) techniques and classifies it into customer information, competitor information, and industry trends. The input is the data set obtained in step 1, and the output is the analyzed and classified data. NLP techniques include morphological analysis and text mining.

[0365] Step 3:

[0366] The server automatically generates proposals using pre-configured templates based on classified data. The input is classified data, and the output is a basic proposal document. This generation process utilizes a template engine, embedding the necessary information into the template.

[0367] Step 4:

[0368] The device uses a camera and microphone to collect the user's facial expressions and voice, and detects emotions using an emotion recognition library. The input is the user's voice and video data, and the output is the analyzed emotional state. This process involves facial recognition and voice analysis.

[0369] Step 5:

[0370] The server receives emotional information and adjusts the content and tone of the proposal according to the user's emotions. The input is the user's emotional information and the existing proposal; the output is the adjusted proposal. This enables personalized service that takes the user's emotions into consideration.

[0371] Step 6:

[0372] The server collects security-related information and proposes security enhancements tailored to the user's emotional state. Inputs are available security information and the user's emotional state, while outputs are user-specific reassurance measures. This includes real-time data feeding and analysis.

[0373] Step 7:

[0374] The user reviews the final proposal output via the terminal. The input here is the proposal generated through steps 5 and 6, while the output is the user's feedback and subsequent fine-tuning. Additional manual editing is also possible in this final step.

[0375] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0376] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0377] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0378] [Third Embodiment]

[0379] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0380] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0381] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0382] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0383] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0384] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0385] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0386] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0387] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0388] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0389] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0390] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0391] This invention provides a system for streamlining information gathering, analysis, and proposal creation in sales activities. This system consists of a server, terminals, and users who operate them.

[0392] First, the server automatically collects data from registered sources. This includes using web crawling technology to retrieve corporate investor relations information, industry news, press releases, and more.

[0393] Next, the server analyzes the collected data using natural language processing and machine learning algorithms, classifying the information into customer information, competitor information, and industry information. The analyzed data is stored in an internal database, forming the basis for proposal creation.

[0394] Next, the server automatically generates a proposal based on pre-configured templates and analytical data. Here, the information is structured to include content tailored to customer needs, competitive analysis results, and industry trends.

[0395] The generated proposal is presented to the user via a terminal. The user can review the proposal and make modifications or add additional information to suit their specific client. This step further personalizes the proposal.

[0396] The terminal allows users to export finalized proposals in formats such as PDF, supporting presentation to clients and email sending. Operations are seamlessly performed through a user-friendly interface.

[0397] As a concrete example, consider the process by which a sales representative preparing a proposal for a major manufacturer uses this system. The user simply enters the name of the target company, and the server automatically collects and analyzes the relevant data. The proposal is generated based on a template and includes competitive analysis graphs and predictive data. Finally, the user can make any necessary adjustments and submit the completed proposal to the client.

[0398] In this way, this system reduces the burden on sales staff in information gathering, analysis, and proposal creation, thereby improving the overall efficiency of operations.

[0399] The following describes the processing flow.

[0400] Step 1:

[0401] The server crawls data from specified sources based on pre-registered company names and related keywords. This process includes accessing official company IR information, news sites, and press release sites. The server parses the HTML of web pages and extracts text data.

[0402] Step 2:

[0403] The server analyzes the collected text data using natural language processing (NLP) techniques. Specifically, it extracts keywords and important phrases and analyzes the semantic relationships within the document. This allows the data to be classified into customer information, competitor information, and industry trends.

[0404] Step 3:

[0405] The server stores the analyzed information in a database and organizes the elements necessary for creating a proposal. The server uses machine learning algorithms to predict industry trends and generate insights into competitors' strategies.

[0406] Step 4:

[0407] The server automatically generates a proposal based on classified and analyzed information using a pre-configured proposal template. During this process, it generates graphs and tables to provide logical support for the proposal.

[0408] Step 5:

[0409] The terminal displays the completed proposal to the user. The user can preview the proposal, review its contents, and make adjustments. If necessary, they can enter additional information or customize it to meet the specific needs of a particular customer.

[0410] Step 6:

[0411] The terminal exports the user-reviewed and finalized proposal in PDF or PPTX format. The user then prepares the completed proposal for emailing or printing and submitting to the client.

[0412] (Example 1)

[0413] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0414] In modern business activities, efficient information gathering and analysis, as well as the creation of appropriate proposals, are essential. However, these processes are time-consuming and labor-intensive. Furthermore, manual research and proposal creation can limit the comprehensiveness of information and the quality of proposals, potentially reducing the effectiveness of sales activities. Therefore, there is a need for methods to automate the process from information gathering to proposal creation and improve efficiency.

[0415] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0416] In this invention, the server includes means for collecting information from information sources, means for analyzing and categorizing the collected information, and means for automatically generating documents based on the categorized information. This enables efficient information collection and analysis, as well as the automatic generation of high-quality proposals.

[0417] A "source of information" refers to an external or internal database or online resource that provides information.

[0418] "Means of information gathering" refers to the process of obtaining necessary information from information sources using specific algorithms or technologies.

[0419] "Means of analysis and classification" refers to the techniques and processes used to analyze acquired information and classify it into specific categories.

[0420] "Means of automatically generating documents" refers to the process of automatically creating documents such as proposals using a computer based on templates and collected and analyzed information.

[0421] "Means of distribution" refers to the technology used to transfer or send generated documents to the target terminal or destination.

[0422] A "scheduling function" refers to a function that automatically executes tasks such as information gathering and analysis at pre-set times and conditions.

[0423] An "editable format" refers to a file or document format that allows users to change or modify its content as needed.

[0424] "Means of converting to output format" refers to the technologies and processes used to convert edited documents into specific formats such as PDF.

[0425] "Means of storage or transmission" refers to means of storing generated or edited documents on digital media or delivering them to the required recipients.

[0426] This system consists of servers, terminals, and users, and automates everything from information gathering to proposal creation to streamline sales activities.

[0427] The server plays a crucial role in efficiently collecting and analyzing information. Specifically, it uses web crawling technologies such as Apache Nutch and Scrapy to retrieve data from internet sources. The retrieved data is then processed using natural language processing with Python libraries like NLTK and spaCy, and analyzed using Scikit-learn's machine learning algorithms. This analysis classifies the data into customer information, competitor information, and industry information. The analyzed data is stored in a MySQL database and forms the basis for proposal creation.

[0428] In generating proposals, the server automatically creates proposals using the Google Docs API based on a pre-configured template. This template includes customer names, industry analysis results, and competitor information. The generated proposals are saved in an editable format for distribution.

[0429] The terminal presents the generated proposal to the user and supports editing. Users can preview the proposal through the terminal and make adjustments and customizations to meet specific customer needs. The edited proposal can be converted to PDF format and is designed for easy export or email sending. In this way, the terminal provides a user-friendly interface and supports the finalization of the proposal.

[0430] A concrete example of this system's use is when a sales representative visits a manufacturer. The user enters the manufacturer's name, and the server automatically collects relevant information, analyzes it, and then creates a proposal using a template. This proposal includes competitive analysis graphs and industry trends, which the user can review, make adjustments, and then submit the final version to the customer in PDF format.

[0431] An example of a prompt message might be, "Collect the necessary data to generate a sales proposal for a major manufacturer, and compile the analysis results into a report."

[0432] This invention enables the streamlining of the sales process and reduces the burden of proposal creation through the collaboration of servers, terminals, and users.

[0433] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0434] Step 1:

[0435] The server collects information from various sources. The input is a list of URLs for specified sources, specifically using crawler software to retrieve the data. The server uses Apache Nutch and employs web crawling techniques to collect data from a variety of sources on the internet. This process outputs data such as corporate investor relations information, industry news, and press releases.

[0436] Step 2:

[0437] The server analyzes and categorizes the collected information. The input is the raw data collected in Step 1. The data is analyzed using natural language processing with Python libraries such as NLTK and spaCy. Furthermore, machine learning algorithms utilizing Scikit-learn are used to classify the data into customer information, competitor information, and industry information. The output here is structured, analyzed data.

[0438] Step 3:

[0439] The server automatically generates documents based on the categorized information. The input is the data categorized in step 2. The server uses the Google Docs API to automatically generate proposals by inserting the data into a pre-configured template. The proposals include customer names, industry analysis results, and competitor information, and an editable document is created as output.

[0440] Step 4:

[0441] The terminal presents the generated document to the user and supports the editing process. The input is the proposal from Step 3. The user reviews the proposal through the terminal and makes revisions as needed to meet the customer's specific needs. This process utilizes a user-friendly interface, allowing for easy previewing and editing. The output is the final, revised version of the document.

[0442] Step 5:

[0443] The terminal converts the edited document into an output format and stores or transmits it. The input is the document completed in step 4. It has the function to convert and save it in PDF format, and can be transmitted to the customer via email or other means as needed. This ensures that the proposal is submitted to the customer in a formal format.

[0444] (Application Example 1)

[0445] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0446] In modern sales activities, there is a demand for the rapid and effective generation of proposals for customers. However, traditional methods require a great deal of time and effort from information gathering to proposal creation, making it difficult to improve sales efficiency. Furthermore, in today's increasingly paperless world, the digital management and transmission systems for proposals are inadequate.

[0447] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0448] In this invention, the server includes means for acquiring data from an information source, means for analyzing and classifying the acquired data, and means for automatically generating a proposal based on the classified data. This allows sales representatives to immediately review and revise the generated proposal on a mobile information terminal such as a smartphone and send it to the customer in digital format. This significantly improves the efficiency of sales activities and reduces the workload.

[0449] "Information sources" refer to the locations or media from which data is collected, such as industry news and publicly available company information.

[0450] "Means of acquiring data" refers to methods and devices for collecting necessary data from information sources, such as using web crawling technology.

[0451] "Means for analyzing and classifying data" refers to methods or mechanisms for analyzing acquired data and assigning it to specific categories based on its content.

[0452] "Means for automatically generating proposals" refers to methods or devices for creating proposals using templates based on classified data.

[0453] A "portable information terminal" is a portable electronic device, including smartphones and tablets.

[0454] "Means of outputting in digital format" refers to methods or devices for saving a created document in an electronic file format and making it available for transmission to other digital devices.

[0455] To realize this application, the server automatically retrieves data from information sources. Specifically, it uses web crawling technology to collect necessary information from publicly available company information and industry news. Next, the server analyzes the collected data using natural language processing technology and machine learning algorithms, classifying it into customer information, competitor information, and industry information. This analyzed data is stored in an internal database. Furthermore, based on the classified data, a proposal is automatically generated using templates and data analysis results.

[0456] The terminal uses a smartphone or tablet as a personal information terminal to display the generated proposal. Through this terminal, users can review and revise the proposal, and, if necessary, export and send it in digital format.

[0457] As a concrete example, when a user enters the name of a client company, the server automatically collects and analyzes relevant data from the payment industry. At this time, a proposal including competitive analysis and industry trends is generated, allowing sales representatives to efficiently present proposals to clients.

[0458] An example of a prompt for a generative AI model might be: "How can I create an application that allows a sales representative at an online payment service company to generate proposals optimized for their client companies?"

[0459] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0460] Step 1:

[0461] The server uses web crawling technology to retrieve data from external sources. The input is search keywords, such as the client company name specified by the user, and the output is the collected raw data. This data is diverse, including publicly available company information, industry news, and press releases.

[0462] Step 2:

[0463] The server analyzes the collected raw data using natural language processing techniques and classifies it into customer information, competitor information, and industry information. The input is the raw data obtained in step 1, and the output is the analyzed and classified data. This step involves data processing such as keyword extraction, sentiment analysis, and name recognition.

[0464] Step 3:

[0465] The server stores the analyzed and classified data in an internal database. The input is the analyzed data generated in step 2, and the output is the information stored in the database. This procedure allows for efficient access to the data needed in subsequent steps.

[0466] Step 4:

[0467] The server automatically generates proposals using analytical data stored in the database and pre-built templates. The input is the analytical data and templates in the database, and the output is the completed proposal. This step specifically focuses on structuring the information to reflect customer needs and industry trends.

[0468] Step 5:

[0469] The terminal displays the generated proposal to the user on their mobile device. The input is the proposal generated in step 4, and the output is what is displayed on the user's screen. The user can review and modify this display, allowing for customization of the proposal.

[0470] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0471] This invention provides a system that, in addition to information gathering, analysis, and automatic proposal generation, also has the function of recognizing user emotions and customizing the content of the proposal. This system is realized through a configuration that combines a server, terminals, users, and an emotion engine.

[0472] First, the server crawls target information sources based on registered company names and keywords, and collects the necessary data. The collected data is analyzed using natural language processing (NLP) technology and classified into customer information, competitor information, and industry trends. This data is stored in a database and serves as the basis for creating proposals.

[0473] Next, the proposal is automatically generated using analytical data and pre-configured templates. Here, the emotion engine plays a crucial role. The terminal senses user input, such as facial expressions, voice, and text input, and the emotion engine analyzes this data. The emotion engine determines the user's emotional state and customizes the tone and content of the proposal based on that.

[0474] This system tailors proposals based on the user's desired emotions and nuances, providing a more personalized experience. For example, if a user is highly motivated, the proposal will use positive and forward-looking language. Conversely, if a more cautious approach is required, a more neutral and subdued tone will be applied.

[0475] Users can preview the proposal output via their device and make final adjustments. Furthermore, the emotion engine learns from past feedback, resulting in more refined proposals in the future.

[0476] Thus, the present invention is a system that takes user emotions into consideration, enabling more effective and personalized sales support. By introducing an emotion engine, user-centered proposal creation is achieved in a way that cannot be obtained through mere data analysis.

[0477] The following describes the processing flow.

[0478] Step 1:

[0479] The server crawls information sources based on pre-specified companies and related keywords, collecting data from web pages and news feeds. The server is programmed to extract meaningful information even from obfuscated data during this process.

[0480] Step 2:

[0481] The server analyzes the collected data using natural language processing (NLP) techniques. The analyzed data is categorized into customer information, competitor information, industry trends, and so on. This categorized information is then stored in a database as foundational information for generating proposals later.

[0482] Step 3:

[0483] The server uses stored classification information to automatically generate proposals based on pre-configured templates. These templates organize content according to a typical proposal structure and include features for inserting graphs and tables as visualizations.

[0484] Step 4:

[0485] The device receives input from the user and uses an emotion engine to analyze the user's emotions from their facial expressions, voice, and text. The emotion engine determines the user's current emotional state and dynamically adjusts the content and tone of the proposal based on that.

[0486] Step 5:

[0487] The device presents the user with a customized proposal based on the output of the emotion engine. The user can review the displayed proposal and make final adjustments to suit a specific client. The user can also edit parts of the proposal or add additional information as needed.

[0488] Step 6:

[0489] The device exports the finalized proposal in PDF or PPTX format. Users can then prepare this proposal for submission to the client or send it via email. After the proposal is used, feedback is incorporated into the sentiment engine to improve the accuracy and personalization of future proposal generation.

[0490] (Example 2)

[0491] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0492] Conventional information gathering and automated document generation systems have the challenge of difficulty in personalizing based on user emotions, and if the generated documents do not align with the user's emotions, they cannot provide effective suggestions or information.

[0493] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0494] In this invention, the server includes means for collecting information from information sources, means for analyzing and classifying the collected information, means for automatically generating documents based on the classified information, and means for analyzing the user's emotions and customizing the documents. This makes it possible to generate personalized documents that are appropriate to the user's emotions.

[0495] "Information sources" refer to websites and databases on the internet from which data and information are obtained.

[0496] "Means of collecting information" refers to the software or system mechanisms used to obtain necessary information from information sources.

[0497] "Means of analysis and classification" refers to technical methods for organizing acquired information according to specific criteria and making it identifiable.

[0498] "Methods for automatically generating documents" refers to the process of constructing documents using templates and generative AI models based on analyzed and classified information.

[0499] "Means of analyzing user emotions and customizing documents" refers to methods for analyzing a user's emotional state and modifying the content and tone of the generated document based on the results of that analysis.

[0500] "Means of output" refers to digital or analog methods used to present the generated document to the user.

[0501] This invention is an embodiment of a system that includes information gathering, automatic document generation, and document customization through user sentiment analysis. This system is composed of a server, terminals, users, and a sentiment engine.

[0502] The server collects necessary information from multiple sources. Specifically, the server uses crawling software to crawl websites and databases. Technologies used include Python's BeautifulSoup and Scrapy. The collected information is analyzed using natural language processing (NLP) techniques. The Python spaCy library is used for analysis, and the information is classified as customer information, competitor information, or industry trends.

[0503] Subsequently, the server automatically generates documents based on the analyzed information. This generation process utilizes templates and a generation AI model. This ensures that the information is structured into an appropriate document format. The generated documents can then be used as business proposals or reports.

[0504] The device's role is to capture and analyze the user's emotions. It uses its built-in camera and microphone to capture the user's facial expressions and voice, and sends this data to the emotion engine. The emotion engine analyzes the acquired data and uses emotion recognition software to identify the user's emotional state. Microsoft Azure's Emotion API, for example, is often used.

[0505] Users can preview documents generated through their devices before receiving them. By using emotional data, the tone of the document is adjusted, resulting in more personalized proposals. For example, if a user requests event planning, the emotional engine will detect high motivation, adding an energetic tone to the generated document. Conversely, if caution is required, a neutral and calm tone will be reflected.

[0506] As a concrete example, here is an example of a prompt sentence to give to a generative AI model:

[0507] "I'm planning a weekend event for businesses. Please create a proposal that will motivate participants and deliver maximum results within the budget."

[0508] In this way, the system enables flexible document generation that meets the user's needs.

[0509] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0510] Step 1:

[0511] The server collects necessary information from information sources. Inputs are registered company names and keywords, and output is the collected raw data. Specifically, the server uses crawling software to traverse websites and databases based on specified keywords. The crawled data is stored on the server in HTML or Raw Text format.

[0512] Step 2:

[0513] The server analyzes and classifies the collected information. The input is the raw data obtained in step 1, and the output is the classified information. The server uses natural language processing libraries such as Python's spaCy to analyze the text data and classify it into customer information, competitor information, and industry trends. Morphological analysis and contextual analysis are performed to achieve data categorization.

[0514] Step 3:

[0515] The server automatically generates documents based on the classified information. The input is the classified information obtained in step 2, and the output is the generated document. The server combines a template engine and a generative AI model to incorporate the information into the appropriate document format. For example, the template engine uses Jinja2 to insert information into a pre-designed template to complete the document.

[0516] Step 4:

[0517] The device captures and analyzes the user's emotions. Input is the user's facial expressions and voice, and output is emotion data. The device uses its built-in camera and microphone to record and photograph the user's interactions. This data is sent to an emotion engine, where the emotional state is identified. Specifically, emotion recognition software analyzes the user's facial muscle movements and voice tone.

[0518] Step 5:

[0519] The server customizes the document based on sentiment data. The input is the sentiment data obtained in step 4, and the output is the customized document. The server fine-tunes the tone and content of the document according to the results of the sentiment engine. For example, if the user is highly motivated, the server changes the wording of the document to be more positive.

[0520] Step 6:

[0521] The user receives and previews the customized document through their device. The input is the document generated in step 5, and the output is the final, adjusted document. The user reviews the appropriateness of the proposals and wording, and makes corrections and revisions to the document as needed. This completes the personalized business document.

[0522] (Application Example 2)

[0523] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0524] In modern society, with the sheer volume of information available, information gathering and analysis are essential for making accurate recommendations. However, general recommendation systems struggle to provide nuanced responses that take into account the emotions of users. Furthermore, even in providing information related to safety, there is a problem in being unable to respond to situations where appropriate recommendations are required based on the emotional state of the user.

[0525] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0526] In this invention, the server includes means for acquiring data from information sources, means for analyzing and classifying the acquired data, means for automatically generating proposals based on the classified data, means for outputting the generated proposals, means for detecting the user's emotions and adjusting the proposals based on those emotions, and means for collecting information on safety and proposing safety improvement measures that correspond to the user's emotions. This enables personalized responses that take into account the user's emotions, making it possible to provide more accurate and reassuring information and proposals.

[0527] "Information sources" refer to documents, databases, and other materials that serve as the starting point for acquiring data.

[0528] "Means of acquiring data" refers to technical means for automatically collecting necessary data from information sources.

[0529] "Means for analyzing and classifying data" refers to technical means for analyzing acquired data and classifying it according to specific criteria.

[0530] "Methods for automatically generating proposals" refers to methods for automatically creating proposals using templates based on analyzed and classified data.

[0531] "Means for outputting the generated proposal" refers to the technical means for providing the created proposal to the user.

[0532] "Means for detecting user emotions and adjusting proposals based on those emotions" refers to methods for analyzing user emotions from facial expressions, voice, etc., and changing the content and tone of proposals accordingly.

[0533] "Means of collecting safety-related information and proposing safety improvement measures that respond to users' emotions" refers to means of collecting safety-related information and providing optimal safety measures that are tailored to the emotional state of users.

[0534] In this embodiment of the invention, the server first retrieves relevant data from an information source. The retrieved data is analyzed and classified using natural language processing technology. This organizes the information of interest to the user and forms the basis for automatic proposal generation. Based on the analyzed and classified data, the server automatically generates a proposal using a pre-configured template.

[0535] Next, the device provides an interface for detecting the user's emotions. Using the camera and microphone built into the device, it collects the user's facial expressions and voice, and analyzes the emotions using open-source emotion recognition libraries (e.g., OpenCV or TensorFlow). Upon receiving the emotion information, the device sends the analysis results to the server, which then adjusts the content and tone of the proposal. This enables personalized proposals tailored to the user's emotions.

[0536] Furthermore, the server collects security-related information and proposes security enhancement measures tailored to the user's feelings. This allows users to act with confidence and take appropriate actions depending on the situation.

[0537] For example, if a user traveling uses their device and the system detects that they are experiencing emotional instability, the server can quickly provide the latest safety information for the area and offer specific action plans to enhance safety. This proposal, outlining the safety measures, is then output to the user via their device.

[0538] Another example of a prompt for a generative AI model is, "If the user is feeling anxious, how should you create suggestions for safe travel?" This allows the AI ​​to provide appropriate information to alleviate the user's anxiety.

[0539] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0540] Step 1:

[0541] The server crawls information sources based on registered keywords and company names to retrieve data. The input consists of keywords and company names pre-set by the user, and the output is a collection of relevant data. Web scraping and API access are used for data retrieval.

[0542] Step 2:

[0543] The server analyzes the acquired data using natural language processing (NLP) techniques and classifies it into customer information, competitor information, and industry trends. The input is the data set obtained in step 1, and the output is the analyzed and classified data. NLP techniques include morphological analysis and text mining.

[0544] Step 3:

[0545] The server automatically generates proposals using pre-configured templates based on classified data. The input is classified data, and the output is a basic proposal document. This generation process utilizes a template engine, embedding the necessary information into the template.

[0546] Step 4:

[0547] The device uses a camera and microphone to collect the user's facial expressions and voice, and detects emotions using an emotion recognition library. The input is the user's voice and video data, and the output is the analyzed emotional state. This process involves facial recognition and voice analysis.

[0548] Step 5:

[0549] The server receives emotional information and adjusts the content and tone of the proposal according to the user's emotions. The input is the user's emotional information and the existing proposal; the output is the adjusted proposal. This enables personalized service that takes the user's emotions into consideration.

[0550] Step 6:

[0551] The server collects security-related information and proposes security enhancements tailored to the user's emotional state. Inputs are available security information and the user's emotional state, while outputs are user-specific reassurance measures. This includes real-time data feeding and analysis.

[0552] Step 7:

[0553] The user reviews the final proposal output via the terminal. The input here is the proposal generated through steps 5 and 6, while the output is the user's feedback and subsequent fine-tuning. Additional manual editing is also possible in this final step.

[0554] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0555] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0556] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0557] [Fourth Embodiment]

[0558] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0559] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0560] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0561] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0562] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0563] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0564] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0565] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0566] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0567] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0568] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0569] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0570] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0571] This invention provides a system for streamlining information gathering, analysis, and proposal creation in sales activities. This system consists of a server, terminals, and users who operate them.

[0572] First, the server automatically collects data from registered sources. This includes using web crawling technology to retrieve corporate investor relations information, industry news, press releases, and more.

[0573] Next, the server analyzes the collected data using natural language processing and machine learning algorithms, classifying the information into customer information, competitor information, and industry information. The analyzed data is stored in an internal database, forming the basis for proposal creation.

[0574] Next, the server automatically generates a proposal based on pre-configured templates and analytical data. Here, the information is structured to include content tailored to customer needs, competitive analysis results, and industry trends.

[0575] The generated proposal is presented to the user via a terminal. The user can review the proposal and make modifications or add additional information to suit their specific client. This step further personalizes the proposal.

[0576] The terminal allows users to export finalized proposals in formats such as PDF, supporting presentation to clients and email sending. Operations are seamlessly performed through a user-friendly interface.

[0577] As a concrete example, consider the process by which a sales representative preparing a proposal for a major manufacturer uses this system. The user simply enters the name of the target company, and the server automatically collects and analyzes the relevant data. The proposal is generated based on a template and includes competitive analysis graphs and predictive data. Finally, the user can make any necessary adjustments and submit the completed proposal to the client.

[0578] In this way, this system reduces the burden on sales staff in information gathering, analysis, and proposal creation, thereby improving the overall efficiency of operations.

[0579] The following describes the processing flow.

[0580] Step 1:

[0581] The server crawls data from specified sources based on pre-registered company names and related keywords. This process includes accessing official company IR information, news sites, and press release sites. The server parses the HTML of web pages and extracts text data.

[0582] Step 2:

[0583] The server analyzes the collected text data using natural language processing (NLP) techniques. Specifically, it extracts keywords and important phrases and analyzes the semantic relationships within the document. This allows the data to be classified into customer information, competitor information, and industry trends.

[0584] Step 3:

[0585] The server stores the analyzed information in a database and organizes the elements necessary for creating a proposal. The server uses machine learning algorithms to predict industry trends and generate insights into competitors' strategies.

[0586] Step 4:

[0587] The server automatically generates a proposal based on classified and analyzed information using a pre-configured proposal template. During this process, it generates graphs and tables to provide logical support for the proposal.

[0588] Step 5:

[0589] The terminal displays the completed proposal to the user. The user can preview the proposal, review its contents, and make adjustments. If necessary, they can enter additional information or customize it to meet the specific needs of a particular customer.

[0590] Step 6:

[0591] The terminal exports the user-reviewed and finalized proposal in PDF or PPTX format. The user then prepares the completed proposal for emailing or printing and submitting to the client.

[0592] (Example 1)

[0593] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0594] In modern business activities, efficient information gathering and analysis, as well as the creation of appropriate proposals, are essential. However, these processes are time-consuming and labor-intensive. Furthermore, manual research and proposal creation can limit the comprehensiveness of information and the quality of proposals, potentially reducing the effectiveness of sales activities. Therefore, there is a need for methods to automate the process from information gathering to proposal creation and improve efficiency.

[0595] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0596] In this invention, the server includes means for collecting information from information sources, means for analyzing and categorizing the collected information, and means for automatically generating documents based on the categorized information. This enables efficient information collection and analysis, as well as the automatic generation of high-quality proposals.

[0597] A "source of information" refers to an external or internal database or online resource that provides information.

[0598] "Means of information gathering" refers to the process of obtaining necessary information from information sources using specific algorithms or technologies.

[0599] "Means of analysis and classification" refers to the techniques and processes used to analyze acquired information and classify it into specific categories.

[0600] "Means of automatically generating documents" refers to the process of automatically creating documents such as proposals using a computer based on templates and collected and analyzed information.

[0601] "Means of distribution" refers to the technology used to transfer or send generated documents to the target terminal or destination.

[0602] A "scheduling function" refers to a function that automatically executes tasks such as information gathering and analysis at pre-set times and conditions.

[0603] An "editable format" refers to a file or document format that allows users to change or modify its content as needed.

[0604] "Means of converting to output format" refers to the technologies and processes used to convert edited documents into specific formats such as PDF.

[0605] "Means of storage or transmission" refers to means of storing generated or edited documents on digital media or delivering them to the required recipients.

[0606] This system consists of servers, terminals, and users, and automates everything from information gathering to proposal creation to streamline sales activities.

[0607] The server plays a crucial role in efficiently collecting and analyzing information. Specifically, it uses web crawling technologies such as Apache Nutch and Scrapy to retrieve data from internet sources. The retrieved data is then processed using natural language processing with Python libraries like NLTK and spaCy, and analyzed using Scikit-learn's machine learning algorithms. This analysis classifies the data into customer information, competitor information, and industry information. The analyzed data is stored in a MySQL database and forms the basis for proposal creation.

[0608] In generating proposals, the server automatically creates proposals using the Google Docs API based on a pre-configured template. This template includes customer names, industry analysis results, and competitor information. The generated proposals are saved in an editable format for distribution.

[0609] The terminal presents the generated proposal to the user and supports editing. Users can preview the proposal through the terminal and make adjustments and customizations to meet specific customer needs. The edited proposal can be converted to PDF format and is designed for easy export or email sending. In this way, the terminal provides a user-friendly interface and supports the finalization of the proposal.

[0610] A concrete example of this system's use is when a sales representative visits a manufacturer. The user enters the manufacturer's name, and the server automatically collects relevant information, analyzes it, and then creates a proposal using a template. This proposal includes competitive analysis graphs and industry trends, which the user can review, make adjustments, and then submit the final version to the customer in PDF format.

[0611] An example of a prompt message might be: "Collect the necessary data to generate a sales proposal for a major manufacturer, and compile the analysis results into a report."

[0612] This invention enables the streamlining of the sales process and reduces the burden of proposal creation through the collaboration of servers, terminals, and users.

[0613] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0614] Step 1:

[0615] The server collects information from various sources. The input is a list of URLs for specified sources, specifically using crawler software to retrieve the data. The server uses Apache Nutch and employs web crawling techniques to collect data from a variety of sources on the internet. This process outputs data such as corporate investor relations information, industry news, and press releases.

[0616] Step 2:

[0617] The server analyzes and categorizes the collected information. The input is the raw data collected in Step 1. The data is analyzed using natural language processing with Python libraries such as NLTK and spaCy. Furthermore, machine learning algorithms utilizing Scikit-learn are used to classify the data into customer information, competitor information, and industry information. The output here is structured, analyzed data.

[0618] Step 3:

[0619] The server automatically generates documents based on the categorized information. The input is the data categorized in step 2. The server uses the Google Docs API to automatically generate proposals by inserting the data into a pre-configured template. The proposals include customer names, industry analysis results, and competitor information, and an editable document is created as output.

[0620] Step 4:

[0621] The terminal presents the generated document to the user and supports the editing process. The input is the proposal from Step 3. The user reviews the proposal through the terminal and makes revisions as needed to meet the customer's specific needs. This process utilizes a user-friendly interface, allowing for easy previewing and editing. The output is the final, revised version of the document.

[0622] Step 5:

[0623] The terminal converts the edited document into an output format and stores or transmits it. The input is the document completed in step 4. It has the function to convert and save it in PDF format, and can be transmitted to the customer via email or other means as needed. This ensures that the proposal is submitted to the customer in a formal format.

[0624] (Application Example 1)

[0625] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0626] In modern sales activities, there is a demand for the rapid and effective generation of proposals for customers. However, traditional methods require a great deal of time and effort from information gathering to proposal creation, making it difficult to improve sales efficiency. Furthermore, in today's increasingly paperless world, the digital management and transmission systems for proposals are inadequate.

[0627] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0628] In this invention, the server includes means for acquiring data from an information source, means for analyzing and classifying the acquired data, and means for automatically generating a proposal based on the classified data. This allows sales representatives to immediately review and revise the generated proposal on a mobile information terminal such as a smartphone and send it to the customer in digital format. This significantly improves the efficiency of sales activities and reduces the workload.

[0629] "Information sources" refer to the locations or media from which data is collected, such as industry news and publicly available company information.

[0630] "Means of acquiring data" refers to methods and devices for collecting necessary data from information sources, such as using web crawling technology.

[0631] "Means for analyzing and classifying data" refers to methods or mechanisms for analyzing acquired data and assigning it to specific categories based on its content.

[0632] "Means for automatically generating proposals" refers to methods or devices for creating proposals using templates based on classified data.

[0633] A "portable information terminal" is a portable electronic device, including smartphones and tablets.

[0634] "Means of outputting in digital format" refers to methods or devices for saving a created document in an electronic file format and making it available for transmission to other digital devices.

[0635] To realize this application, the server automatically retrieves data from information sources. Specifically, it uses web crawling technology to collect necessary information from publicly available company information and industry news. Next, the server analyzes the collected data using natural language processing technology and machine learning algorithms, classifying it into customer information, competitor information, and industry information. This analyzed data is stored in an internal database. Furthermore, based on the classified data, a proposal is automatically generated using templates and data analysis results.

[0636] The terminal uses a smartphone or tablet as a personal information terminal to display the generated proposal. Through this terminal, users can review and revise the proposal, and, if necessary, export and send it in digital format.

[0637] As a concrete example, when a user enters the name of a client company, the server automatically collects and analyzes relevant data from the payment industry. At this time, a proposal including competitive analysis and industry trends is generated, allowing sales representatives to efficiently present proposals to clients.

[0638] An example of a prompt for a generative AI model might be: "How can I create an application that allows a sales representative at an online payment service company to generate proposals optimized for their client companies?"

[0639] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0640] Step 1:

[0641] The server uses web crawling technology to retrieve data from external sources. The input is search keywords, such as the client company name specified by the user, and the output is the collected raw data. This data is diverse, including publicly available company information, industry news, and press releases.

[0642] Step 2:

[0643] The server analyzes the collected raw data using natural language processing techniques and classifies it into customer information, competitor information, and industry information. The input is the raw data obtained in step 1, and the output is the analyzed and classified data. This step involves data processing such as keyword extraction, sentiment analysis, and name recognition.

[0644] Step 3:

[0645] The server stores the analyzed and classified data in an internal database. The input is the analyzed data generated in step 2, and the output is the information stored in the database. This procedure allows for efficient access to the data needed in subsequent steps.

[0646] Step 4:

[0647] The server automatically generates proposals using analytical data stored in the database and pre-built templates. The input is the analytical data and templates in the database, and the output is the completed proposal. This step specifically focuses on structuring the information to reflect customer needs and industry trends.

[0648] Step 5:

[0649] The terminal displays the generated proposal to the user on their mobile device. The input is the proposal generated in step 4, and the output is what is displayed on the user's screen. The user can review and modify this display, allowing for customization of the proposal.

[0650] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0651] This invention provides a system that, in addition to information gathering, analysis, and automatic proposal generation, also has the function of recognizing user emotions and customizing the content of the proposal. This system is realized through a configuration that combines a server, terminals, users, and an emotion engine.

[0652] First, the server crawls target information sources based on registered company names and keywords, and collects the necessary data. The collected data is analyzed using natural language processing (NLP) technology and classified into customer information, competitor information, and industry trends. This data is stored in a database and serves as the basis for creating proposals.

[0653] Next, the proposal is automatically generated using analytical data and pre-configured templates. Here, the emotion engine plays a crucial role. The terminal senses user input, such as facial expressions, voice, and text input, and the emotion engine analyzes this data. The emotion engine determines the user's emotional state and customizes the tone and content of the proposal based on that.

[0654] This system tailors proposals based on the user's desired emotions and nuances, providing a more personalized experience. For example, if a user is highly motivated, the proposal will use positive and forward-looking language. Conversely, if a more cautious approach is required, a more neutral and subdued tone will be applied.

[0655] Users can preview the proposal output via their device and make final adjustments. Furthermore, the emotion engine learns from past feedback, resulting in more refined proposals in the future.

[0656] Thus, the present invention is a system that takes user emotions into consideration, enabling more effective and personalized sales support. By introducing an emotion engine, user-centered proposal creation is achieved in a way that cannot be obtained through mere data analysis.

[0657] The following describes the processing flow.

[0658] Step 1:

[0659] The server crawls information sources based on pre-specified companies and related keywords, collecting data from web pages and news feeds. The server is programmed to extract meaningful information even from obfuscated data during this process.

[0660] Step 2:

[0661] The server analyzes the collected data using natural language processing (NLP) techniques. The analyzed data is categorized into customer information, competitor information, industry trends, and so on. This categorized information is then stored in a database as foundational information for generating proposals later.

[0662] Step 3:

[0663] The server uses stored classification information to automatically generate proposals based on pre-configured templates. These templates organize content according to a typical proposal structure and include features for inserting graphs and tables as visualizations.

[0664] Step 4:

[0665] The device receives input from the user and uses an emotion engine to analyze the user's emotions from their facial expressions, voice, and text. The emotion engine determines the user's current emotional state and dynamically adjusts the content and tone of the proposal based on that.

[0666] Step 5:

[0667] The device presents the user with a customized proposal based on the output of the emotion engine. The user can review the displayed proposal and make final adjustments to suit a specific client. The user can also edit parts of the proposal or add additional information as needed.

[0668] Step 6:

[0669] The device exports the finalized proposal in PDF or PPTX format. Users can then prepare this proposal for submission to the client or send it via email. After the proposal is used, feedback is incorporated into the sentiment engine to improve the accuracy and personalization of future proposal generation.

[0670] (Example 2)

[0671] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0672] Conventional information gathering and automated document generation systems have the challenge of difficulty in personalizing based on user emotions, and if the generated documents do not align with the user's emotions, they cannot provide effective suggestions or information.

[0673] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0674] In this invention, the server includes means for collecting information from information sources, means for analyzing and classifying the collected information, means for automatically generating documents based on the classified information, and means for analyzing the user's emotions and customizing the documents. This makes it possible to generate personalized documents that are appropriate to the user's emotions.

[0675] "Information sources" refer to websites and databases on the internet from which data and information are obtained.

[0676] "Means of collecting information" refers to the software or system mechanisms used to obtain necessary information from information sources.

[0677] "Means of analysis and classification" refers to technical methods for organizing acquired information according to specific criteria and making it identifiable.

[0678] "Methods for automatically generating documents" refers to the process of constructing documents using templates and generative AI models based on analyzed and classified information.

[0679] "Means of analyzing user emotions and customizing documents" refers to methods for analyzing a user's emotional state and modifying the content and tone of the generated document based on the results of that analysis.

[0680] "Means of output" refers to digital or analog methods used to present the generated document to the user.

[0681] This invention is an embodiment of a system that includes information gathering, automatic document generation, and document customization through user sentiment analysis. This system is composed of a server, terminals, users, and a sentiment engine.

[0682] The server collects necessary information from multiple sources. Specifically, the server uses crawling software to crawl websites and databases. Technologies used include Python's BeautifulSoup and Scrapy. The collected information is analyzed using natural language processing (NLP) techniques. The Python spaCy library is used for analysis, and the information is classified as customer information, competitor information, or industry trends.

[0683] Subsequently, the server automatically generates documents based on the analyzed information. This generation process utilizes templates and a generation AI model. This ensures that the information is structured into an appropriate document format. The generated documents can then be used as business proposals or reports.

[0684] The device's role is to capture and analyze the user's emotions. It uses its built-in camera and microphone to capture the user's facial expressions and voice, and sends this data to the emotion engine. The emotion engine analyzes the acquired data and uses emotion recognition software to identify the user's emotional state. Microsoft Azure's Emotion API, for example, is often used.

[0685] Users can preview documents generated through their devices before receiving them. By using emotional data, the tone of the document is adjusted, resulting in more personalized proposals. For example, if a user requests event planning, the emotional engine will detect high motivation, adding an energetic tone to the generated document. Conversely, if caution is required, a neutral and calm tone will be reflected.

[0686] As a concrete example, here is an example of a prompt sentence to give to a generative AI model:

[0687] "I'm planning a weekend event for businesses. Please create a proposal that will motivate participants and deliver maximum results within the budget."

[0688] In this way, the system enables flexible document generation that meets the user's needs.

[0689] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0690] Step 1:

[0691] The server collects necessary information from information sources. Inputs are registered company names and keywords, and output is the collected raw data. Specifically, the server uses crawling software to traverse websites and databases based on specified keywords. The crawled data is stored on the server in HTML or Raw Text format.

[0692] Step 2:

[0693] The server analyzes and classifies the collected information. The input is the raw data obtained in step 1, and the output is the classified information. The server uses natural language processing libraries such as Python's spaCy to analyze the text data and classify it into customer information, competitor information, and industry trends. Morphological analysis and contextual analysis are performed to achieve data categorization.

[0694] Step 3:

[0695] The server automatically generates documents based on the classified information. The input is the classified information obtained in step 2, and the output is the generated document. The server combines a template engine and a generative AI model to incorporate the information into the appropriate document format. For example, the template engine uses Jinja2 to insert information into a pre-designed template to complete the document.

[0696] Step 4:

[0697] The device captures and analyzes the user's emotions. Input is the user's facial expressions and voice, and output is emotion data. The device uses its built-in camera and microphone to record and photograph the user's interactions. This data is sent to an emotion engine, where the emotional state is identified. Specifically, emotion recognition software analyzes the user's facial muscle movements and voice tone.

[0698] Step 5:

[0699] The server customizes the document based on sentiment data. The input is the sentiment data obtained in step 4, and the output is the customized document. The server fine-tunes the tone and content of the document according to the results of the sentiment engine. For example, if the user is highly motivated, the server changes the wording of the document to be more positive.

[0700] Step 6:

[0701] The user receives and previews the customized document through their device. The input is the document generated in step 5, and the output is the final, adjusted document. The user reviews the appropriateness of the proposals and wording, and makes corrections and revisions to the document as needed. This completes the personalized business document.

[0702] (Application Example 2)

[0703] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0704] In modern society, with the sheer volume of information available, information gathering and analysis are essential for making accurate recommendations. However, general recommendation systems struggle to provide nuanced responses that take into account the emotions of users. Furthermore, even in providing information related to safety, there is a problem in being unable to respond to situations where appropriate recommendations are required based on the emotional state of the user.

[0705] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0706] In this invention, the server includes means for acquiring data from information sources, means for analyzing and classifying the acquired data, means for automatically generating proposals based on the classified data, means for outputting the generated proposals, means for detecting the user's emotions and adjusting the proposals based on those emotions, and means for collecting information on safety and proposing safety improvement measures that correspond to the user's emotions. This enables personalized responses that take into account the user's emotions, making it possible to provide more accurate and reassuring information and proposals.

[0707] "Information sources" refer to documents, databases, and other materials that serve as the starting point for acquiring data.

[0708] "Means of acquiring data" refers to technical means for automatically collecting necessary data from information sources.

[0709] "Means for analyzing and classifying data" refers to technical means for analyzing acquired data and classifying it according to specific criteria.

[0710] "Methods for automatically generating proposals" refers to methods for automatically creating proposals using templates based on analyzed and classified data.

[0711] "Means for outputting the generated proposal" refers to the technical means for providing the created proposal to the user.

[0712] "Means for detecting user emotions and adjusting proposals based on those emotions" refers to methods for analyzing user emotions from facial expressions, voice, etc., and changing the content and tone of proposals accordingly.

[0713] "Means of collecting safety-related information and proposing safety improvement measures that respond to users' emotions" refers to means of collecting safety-related information and providing optimal safety measures that are tailored to the emotional state of users.

[0714] In this embodiment of the invention, the server first retrieves relevant data from an information source. The retrieved data is analyzed and classified using natural language processing technology. This organizes the information of interest to the user and forms the basis for automatic proposal generation. Based on the analyzed and classified data, the server automatically generates a proposal using a pre-configured template.

[0715] Next, the device provides an interface for detecting the user's emotions. Using the camera and microphone built into the device, it collects the user's facial expressions and voice, and analyzes the emotions using open-source emotion recognition libraries (e.g., OpenCV or TensorFlow). Upon receiving the emotion information, the device sends the analysis results to the server, which then adjusts the content and tone of the proposal. This enables personalized proposals tailored to the user's emotions.

[0716] Furthermore, the server collects security-related information and proposes security enhancement measures tailored to the user's feelings. This allows users to act with confidence and take appropriate actions depending on the situation.

[0717] For example, if a user traveling uses their device and the system detects that they are experiencing emotional instability, the server can quickly provide the latest safety information for the area and offer specific action plans to enhance safety. This proposal, outlining the safety measures, is then output to the user via their device.

[0718] Another example of a prompt for a generative AI model is, "If the user is feeling anxious, how should you create suggestions for safe travel?" This allows the AI ​​to provide appropriate information to alleviate the user's anxiety.

[0719] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0720] Step 1:

[0721] The server crawls information sources based on registered keywords and company names to retrieve data. The input consists of keywords and company names pre-set by the user, and the output is a collection of relevant data. Web scraping and API access are used for data retrieval.

[0722] Step 2:

[0723] The server analyzes the acquired data using natural language processing (NLP) techniques and classifies it into customer information, competitor information, and industry trends. The input is the data set obtained in step 1, and the output is the analyzed and classified data. NLP techniques include morphological analysis and text mining.

[0724] Step 3:

[0725] The server automatically generates proposals using pre-configured templates based on classified data. The input is classified data, and the output is a basic proposal document. This generation process utilizes a template engine, embedding the necessary information into the template.

[0726] Step 4:

[0727] The device uses a camera and microphone to collect the user's facial expressions and voice, and detects emotions using an emotion recognition library. The input is the user's voice and video data, and the output is the analyzed emotional state. This process involves facial recognition and voice analysis.

[0728] Step 5:

[0729] The server receives emotional information and adjusts the content and tone of the proposal according to the user's emotions. The input is the user's emotional information and the existing proposal, and the output is the adjusted proposal. This enables personalized service that takes the user's emotions into consideration.

[0730] Step 6:

[0731] The server collects security-related information and proposes security enhancements tailored to the user's emotional state. Inputs are available security information and the user's emotional state, while outputs are user-specific reassurance measures. This includes real-time data feeding and analysis.

[0732] Step 7:

[0733] The user reviews the final proposal output via the terminal. The input here is the proposal generated through steps 5 and 6, while the output is the user's feedback and subsequent fine-tuning. Additional manual editing is also possible in this final step.

[0734] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0735] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0736] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0737] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0738] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0739] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0740] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0741] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0742] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0743] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0744] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0745] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0746] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0747] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0748] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0749] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0750] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0751] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0752] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0753] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0754] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0755] The following is further disclosed regarding the embodiments described above.

[0756] (Claim 1)

[0757] Means of obtaining data from information sources,

[0758] A means of analyzing and classifying the acquired data,

[0759] A method for automatically generating proposals based on classified data,

[0760] A means of outputting the generated proposal,

[0761] A system that includes this.

[0762] (Claim 2)

[0763] The system according to claim 1, wherein the analysis means analyzes the data using natural language processing technology.

[0764] (Claim 3)

[0765] The system according to claim 1, wherein the proposal generation means automatically generates a proposal using a template.

[0766] "Example 1"

[0767] (Claim 1)

[0768] Means of gathering information from sources,

[0769] A means of analyzing and classifying the collected information,

[0770] A means of automatically generating documents based on segmented information,

[0771] Means for distributing the generated documents,

[0772] A means of providing a scheduling function for regularly collecting information,

[0773] A means of presenting a document to users in an editable format and enabling editing,

[0774] A means for converting the edited document into an output format and storing or transmitting it,

[0775] A system that includes this.

[0776] (Claim 2)

[0777] The system according to claim 1, wherein the analysis means analyzes information using a natural language processing method.

[0778] (Claim 3)

[0779] The system according to claim 1, wherein the document generation means automatically generates a document using a template.

[0780] "Application Example 1"

[0781] (Claim 1)

[0782] Means of obtaining data from information sources,

[0783] A means of analyzing and classifying the acquired data,

[0784] A method for automatically generating proposals based on classified data,

[0785] A means of reviewing and correcting the generated proposal on a mobile device and outputting it in digital format,

[0786] A system that includes this.

[0787] (Claim 2)

[0788] The system according to claim 1, wherein the analysis means analyzes the data using natural language processing technology and machine learning algorithms.

[0789] (Claim 3)

[0790] The system according to claim 1, wherein the proposal generation means automatically generates a proposal using a template and data analysis results.

[0791] "Example 2 of combining an emotion engine"

[0792] (Claim 1)

[0793] Means of gathering information from sources,

[0794] A means of analyzing and classifying the collected information,

[0795] A means of automatically generating documents based on classified information,

[0796] A means of analyzing user emotions and customizing documents,

[0797] A means for outputting the generated document,

[0798] A system that includes this.

[0799] (Claim 2)

[0800] The system according to claim 1, wherein the analysis means analyzes information using natural language processing technology.

[0801] (Claim 3)

[0802] The system according to claim 1, wherein the document generation means automatically generates a document using a template.

[0803] "Application example 2 when combining with an emotional engine"

[0804] (Claim 1)

[0805] Means of obtaining data from information sources,

[0806] A means of analyzing and classifying the acquired data,

[0807] A method for automatically generating proposals based on classified data,

[0808] A means of outputting the generated proposal,

[0809] A means of detecting the user's emotions and adjusting the proposal based on those emotions,

[0810] A means of collecting safety-related information and proposing safety improvement measures that respond to user sentiment,

[0811] A system that includes this.

[0812] (Claim 2)

[0813] The system according to claim 1, wherein the analysis means analyzes the data using natural language processing technology.

[0814] (Claim 3)

[0815] The system according to claim 1, wherein the proposal generation means automatically generates a proposal using a template. [Explanation of Symbols]

[0816] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means of obtaining data from information sources, A means of analyzing and classifying the acquired data, A method for automatically generating proposals based on classified data, A means of reviewing and correcting the generated proposal on a mobile device and outputting it in digital format, A system that includes this.

2. The system according to claim 1, wherein the analysis means analyzes the data using natural language processing technology and machine learning algorithms.

3. The system according to claim 1, wherein the proposal generation means automatically generates a proposal using a template and data analysis results.

Images