system

Abstract

We provide the system. [Solution] Means of collecting market information, A means of understanding the activities of competitors by analyzing the collected market information, A means of learning from past success stories, A method for automatically generating proposals, Means for monitoring the progress of the project, A means of issuing an alert when a problem occurs, 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 in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Proposal activities in the sales department require a variety of tasks such as information collection, competitive analysis, proposal writing, and project progress management. If not carried out efficiently, there is a problem of consuming a large amount of time and labor. In particular, while improving the quality of proposals and making prompt responses are required, the limitations of human resources often become inhibiting factors for the business expansion of enterprises.

Means for Solving the Problems

[0005] To solve the above problems, the present invention provides a system equipped with means for collecting market information and analyzing the collected information to understand the activities of competitors. It also includes means for learning from past success stories and automatically generating proposals based on them. Furthermore, it enables rapid response by monitoring the progress of projects in real time and issuing immediate alerts when problems occur. This improves efficiency at each stage of the proposal activity and supports the expansion of corporate performance.

[0006] "Market information" refers to information necessary for proposal activities, including data on market trends, competitive landscape, and customer needs.

[0007] "Collection" is the process of obtaining necessary data from information sources such as the internet and databases.

[0008] "Analysis" is a method of evaluating collected data and deriving relevant insights.

[0009] "Competitors" are other companies operating in the same market or segment, and are rivals competing for customers and market share.

[0010] "Activities" refer to a series of actions and strategies that a company takes to establish its position in the market.

[0011] A "success story" refers to a track record of proposals or projects that have received high praise from customers in the past.

[0012] "Learning" is the process of acquiring new knowledge and skills by using algorithms to extract patterns and regularities based on data.

[0013] A "proposal" is a document created to present proposed ideas or the value of products and services to a customer.

[0014] "Automatic generation" refers to a system creating documents or data without human intervention.

[0015] A "project" is a set of activities planned to achieve a specific goal.

[0016] The "progress" is a situation indicating whether the tasks or processes of the project are proceeding as planned.

[0017] "Monitoring" is an activity in which the system checks data in real time to prepare for unexpected situations.

[0018] "Real time" is a term indicating that information is processed or provided in real time.

[0019] "When a problem occurs" refers to the moment when an event or obstacle beyond the plan or expectation occurs.

[0020] An "alert" is a notice or warning to arouse attention.

[0021] "Quick response" refers to an action that quickly and effectively addresses the occurred problem.

Brief Description of Drawings

[0022] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7]It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when 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.

Modes for Carrying Out the Invention

[0023] 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.

[0024] First, the language used in the following description will be explained.

[0025] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0026] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0027] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0028] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0029] 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."

[0030] [First Embodiment]

[0031] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0032] 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.

[0033] 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).

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0039] 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.

[0040] 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.

[0041] 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.

[0042] 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".

[0043] One embodiment of the present invention is a system that autonomously supports sales proposal activities. This system operates primarily with a server, a terminal, and a user.

[0044] The server first automatically collects market information from the internet and internal databases. During this process, it utilizes text mining technology to extract data on industry trends, target company needs, and the latest developments of competitors. The collected data is then analyzed by a data analysis module built within the server. The analysis results provide the foundational information for formulating optimal proposals for target companies.

[0045] The server then runs an algorithm to learn from a database of past proposal activities and success stories. This database contains detailed information about past projects. The server uses machine learning techniques to identify common factors in successful proposals and forms a template for new proposals.

[0046] During the proposal generation phase, the server automatically creates a document based on the information it has collected, analyzed, and learned. This document, as a proposal, includes information on competitors and content aligned with the target company's needs. The proposal is provided to the user via their terminal. The user can review the generated proposal and make specific customizations or modifications as needed.

[0047] Throughout the project, the server monitors the schedule and task progress, collecting updates in real time. If any problems arise during project execution, the server immediately sends an alert to the user's terminal and proposes solutions based on past cases. This implementation allows companies to streamline their sales proposal activities and implement rapid and effective sales strategies.

[0048] The above describes a specific method for implementing the present invention. This system enables the entire sales process to proceed seamlessly, providing consistent support from proposal to order placement and follow-up.

[0049] The following describes the processing flow.

[0050] Step 1:

[0051] The server collects market information. Using web scraping techniques and API connections, it retrieves the latest information from industry reports and news sites and stores it in a database.

[0052] Step 2:

[0053] The server analyzes collected market information. Using natural language processing, it extracts competitor trends and target company needs from text data and generates reports.

[0054] Step 3:

[0055] The server learns from past proposal data. Successful proposals and project examples are fed into a machine learning algorithm to extract success factors and form templates for new proposals.

[0056] Step 4:

[0057] The server automatically generates proposals. Using analysis results and training data, it creates and saves customized proposals tailored to the target company's needs.

[0058] Step 5:

[0059] Users review proposals through their devices. They can provide feedback on automatically generated proposals and edit or add information as needed.

[0060] Step 6:

[0061] The server collects user feedback after the proposal is submitted. It analyzes the client's responses and uses them to improve the proposal if revisions are needed.

[0062] Step 7:

[0063] The server monitors the project's progress. It checks the schedule and task progress in real time and manages the project's progress.

[0064] Step 8:

[0065] The server will respond when problems occur. If a problem arises during project progress, an alert will be quickly delivered to the user's terminal, and specific suggestions for resolution will be provided.

[0066] (Example 1)

[0067] 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."

[0068] Traditional sales proposal activities relied heavily on manual processes for gathering market information, analyzing competitors, and learning from success stories, requiring significant time and effort. Furthermore, identifying and resolving issues requiring immediate attention during project execution proved difficult. This limited the effectiveness of sales strategies and hindered efficient work processes.

[0069] 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.

[0070] In this invention, the server includes means for collecting information from a database, means for analyzing the collected information to recognize competitor activities, and means for learning from past cases to identify contributing factors. This automates information gathering and analysis in sales activities, enabling efficient proposal creation and real-time project management.

[0071] A "database" is a collection of data that is systematically structured for the purpose of collecting, managing, and retrieving information.

[0072] "Analyzing information" is the process of processing collected data to derive useful insights and conclusions.

[0073] "Recognizing competitor activities" is the process of understanding, comparing, and evaluating the actions and plans of other business entities.

[0074] "Learning from past examples" means analyzing successful past operations and proposals and extracting useful patterns and factors from them.

[0075] A "generative model" is an algorithm or technique for generating new information based on a large amount of data.

[0076] "Generating a document" refers to the process of automatically creating documents or proposals based on pre-defined rules and algorithms.

[0077] "Monitoring the situation" means continuously checking the progress of a project or task and taking action as needed.

[0078] "Issuing a warning" refers to an alert function that immediately notifies users when a problem occurs and prompts them to take appropriate action.

[0079] "Display on a device" means providing information visually through a user interface and creating an environment where users can view and edit that information.

[0080] "Generating a framework" refers to the process of creating templates for proposals and documents, which serve as a foundation for creating new documents.

[0081] "Analyzing responses to a document" refers to the act of collecting and analyzing feedback on a created document to measure areas for improvement and its effectiveness.

[0082] This invention is a system that autonomously supports sales proposal activities, specifically involving a server, terminals, and users. The system utilizes Python-based web scraping and text mining techniques to collect information from databases and the web. Libraries such as BeautifulSoup and Scrapy are useful for this purpose. The server analyzes the collected information using Pandas and NumPy to understand industry trends and competitor activities.

[0083] Furthermore, the server uses Scikit-learn to learn from past successes. This identifies common patterns in successful proposals and forms a framework for new proposals. Generative AI models using the OpenAI® API are utilized to generate these proposals. Specifically, advanced language generation is achieved using AI models from the GPT series.

[0084] The proposal is created by the server and then visually displayed to the user via their terminal. The user reviews the proposal on their terminal and edits the content as needed using Google Docs or Word. Throughout the project, the server monitors progress in real time and immediately sends notifications to the terminal if any problems arise. In this process, it integrates with project management tools to support rapid response.

[0085] As an example, when a user creates a proposal for a new product, this system allows them to quickly obtain a proposal that reflects market trends. For example, a prompt sentence to be entered into the generating AI model might be, "Create a proposal for a new cloud service product and include a sentence that emphasizes differentiation from competitors."

[0086] This invention enables the efficient and consistent collection, analysis, proposal writing, and project management of information related to sales activities, which is expected to lead to smoother sales operations for companies.

[0087] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0088] Step 1:

[0089] The server collects market information from the internet and internal databases. The input specifies the URL of the information source and the required data type. Specifically, it uses a web crawler to retrieve the information and organizes it using libraries such as BeautifulSoup and Scrapy. The output is market information formatted as text and numerical data.

[0090] Step 2:

[0091] The server processes the collected information using a data analysis module. The input is market information obtained in step 1, and the data is organized and aggregated using Pandas and NumPy. Then, Matplotlib is used to visualize the data and derive the needs of target companies and industry trends. The output is the analyzed data and trend graphs.

[0092] Step 3:

[0093] The server learns from a database of past success stories and generates proposal templates. The input is data from past proposals and success stories. A machine learning algorithm using Scikit-learn identifies common patterns in successful proposals. The output is a new proposal template.

[0094] Step 4:

[0095] The server creates a proposal based on the generated template. The inputs are the analysis data and template obtained in steps 2 and 3. The generating AI model is used to construct the document using this data. The output is a proposal tailored to the target company's needs.

[0096] Step 5:

[0097] The terminal displays the proposal sent from the server to the user. The input is the proposal data from the server. The user reviews this proposal in Google Docs or Word and edits it as needed. The output is the final version of the proposal customized by the user.

[0098] Step 6:

[0099] The server monitors project progress and issues alerts when problems occur. Inputs include the project schedule and task progress information for ongoing projects. It integrates with project management tools and displays warnings on the user's terminal if an anomaly is detected. Outputs are suggestions for immediate action to address the problem.

[0100] (Application Example 1)

[0101] 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."

[0102] In modern sales activities, while rapid and effective proposals are required, the market is becoming increasingly complex and customer needs are diversifying. Therefore, there is a need for a system that can efficiently and consistently execute everything from information gathering and analysis to proposal creation and project management. Furthermore, a lack of support tools to help sales representatives maintain up-to-date information and smooth project progress is also a challenge.

[0103] 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.

[0104] In this invention, the server includes means for collecting market data, means for analyzing the collected market data to identify the activities of competing organizations, means for learning from past success stories, and means for providing information on mobile terminals for sales activities. This enables sales representatives to quickly generate proposal documents, formulate effective sales strategies based on the latest information, monitor project progress in real time, and immediately take action to resolve problems.

[0105] "Means of collecting market data" refers to the function of obtaining information about the market environment from the internet or internal databases. This information is used as background data necessary for sales activities.

[0106] "Means of analyzing collected market data to identify the activities of competing organizations" refers to the function of analyzing acquired market data to clarify the activities and market positions of other competing organizations.

[0107] "Methods for learning from past success stories" refer to the function of studying the results and proposals of previous sales activities and extracting the factors for success. This allows for improvement in the quality of new proposals.

[0108] "Methods for automatically generating proposal documents" refer to a function that automatically creates high-quality sales proposals based on analyzed and learned information. This will improve the efficiency of proposal creation.

[0109] "Means of providing information on mobile devices for sales activities" refers to a function that provides necessary information to the devices carried by sales representatives and allows them to view the latest data in real time.

[0110] "Means for monitoring project progress" refers to functions that allow you to understand the status of sales projects and track their progress. This is useful for schedule management and checking task progress.

[0111] "A means of issuing an alert when a problem occurs" refers to a function that allows for the rapid notification of the person in charge when a problem arises during the progress of a project. This enables rapid problem resolution.

[0112] To implement this invention, it is first necessary to prepare an infrastructure for the server to collect and analyze market data. This infrastructure will utilize a database equipped with text mining technology and machine learning algorithms. Specifically, the Python language will be used to scrape data with BeautifulSoup, organize it with Pandas, and analyze it with scikit-learn. This data will include the trends of competing organizations and past success stories, making it fundamental information for sales proposals.

[0113] Next, the server utilizes a generative AI model to automatically generate proposal documents based on the collected and analyzed data. These documents are sent in real time to the mobile devices used by sales representatives. Users can view, edit, and utilize the generated proposal documents on a dashboard developed using React. Furthermore, the generative AI model can be used to provide prompts such as the following:

[0114] As a specific example, a sales representative can use the following prompt before visiting a customer.

[0115] "Please create a proposal for the target company. Their main need is for the latest payment technology. Please include information on the activities of their competitors."

[0116] Furthermore, the server monitors project progress, issues alerts when problems arise, and generates and provides solutions based on past cases to the user. This optimizes the sales process in real time, enabling rapid response. Implementing this system streamlines the entire sales process, providing consistent support from proposal to order placement and follow-up.

[0117] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0118] Step 1:

[0119] The server collects market data from the internet and internal databases. Inputs are URLs and query information obtained through various APIs and scraping techniques. The data is extracted and structured using BeautifulSoup. The output is a collection of market data in text format, which is used in the next analysis step.

[0120] Step 2:

[0121] The server analyzes the collected market data using text mining techniques. The input is the market data set obtained in Step 1. This data is organized using Pandas, and then analyzed using scikit-learn to identify industry trends and the activities of competing organizations. The output is trend data and competitive activity information as a result of the analysis.

[0122] Step 3:

[0123] The server learns from a database of past success stories. The input consists of past proposals and project success stories. Using machine learning algorithms, it extracts success factors from this data and learns patterns. The output is a model of success patterns that helps generate new proposals.

[0124] Step 4:

[0125] The server automatically generates proposal documents using a generative AI model. The input consists of the analysis results from Step 2 and the success pattern model from Step 3. Using document generation technology, it creates proposals optimized for sales. The output is the proposal document provided to the sales representative.

[0126] Step 5:

[0127] The terminal receives proposal documents sent from the server and displays them for the sales representative to review and edit. The input is the proposal document sent from the server. A React-based interface is used, allowing the user to edit and save the proposal document. The output is the edited proposal document.

[0128] Step 6:

[0129] The server monitors project progress and collects progress data. Input is progress information obtained from project management tools (e.g., Jira API). Progress is monitored in real time, and important changes are notified. Output is a project progress report.

[0130] Step 7:

[0131] The server issues an alert and provides a solution when a problem occurs. The input is the problem information detected in step 6. It selects a solution based on a database of past cases and provides it to the user along with the alert. The output is an alert for the problem and guidance on the solution.

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

[0133] One possible embodiment of the present invention is a system that recognizes user emotions and more effectively supports sales proposal activities. In addition to conventional functions such as market information gathering, competitor analysis, and automatic proposal generation, this system integrates an emotion engine to enable more personalized proposals.

[0134] The server first performs basic functions such as market information and competitive analysis. It analyzes the collected data to understand the needs of target companies and the activities of competitors. Subsequently, it uses machine learning to analyze a database of past success stories and generates new proposal templates.

[0135] The role of the emotion engine is to acquire user emotion data through the device's camera or voice input as the user reviews or revises the proposal. This data is sent to the server and analyzed in real time. For example, if a user shows emotions of stress or dissatisfaction while viewing a particular part of the proposal, the server will re-evaluate that part and suggest revising the proposal.

[0136] User emotion-based feedback is used at every phase of the proposal process. For example, before submitting a proposal, the content is optimized to prioritize the structure and expression that elicited the most favorable responses from users. After the proposal is submitted, the emotion engine is also applied to client feedback, allowing for an emotional analysis of areas for improvement in future proposals.

[0137] During project execution, the server monitors user emotional data and issues alerts if stress levels rise. For example, as a project deadline approaches, the server suggests appropriate breaks to the user and provides support to maintain work efficiency.

[0138] This allows for flexible adjustment of proposals and project management in response to user emotions, enabling more effective and satisfying sales proposal activities. The above describes the specific implementation method of the present invention. This system allows companies to optimize the entire sales process based on the emotional responses of consumers and clients, and to improve consistency from proposal to order placement and follow-up.

[0139] The following describes the processing flow.

[0140] Step 1:

[0141] The server collects market information via the internet and internal databases. This includes the latest industry trends, competitor activities, and the business needs of target companies.

[0142] Step 2:

[0143] The server analyzes the market information it collects. Using natural language processing, it extracts key insights from text data and generates competitive analysis reports.

[0144] Step 3:

[0145] The server learns from past success stories using machine learning. It extracts success factors from past proposal records in the database and creates a new proposal template.

[0146] Step 4:

[0147] The server automatically generates proposals. Based on the acquired analysis results and success story templates, it creates proposals optimized for the target company.

[0148] Step 5:

[0149] The user reviews the proposal generated through their device. While viewing the proposal, the device uses its built-in camera and microphone to collect user emotion data.

[0150] Step 6:

[0151] The server receives user sentiment data and analyzes it in real time. It identifies areas where the user has expressed stress or dissatisfaction and generates advice for improving the proposal.

[0152] Step 7:

[0153] Users revise the proposal based on their emotional feedback. By implementing specific improvements, the proposal's quality is enhanced.

[0154] Step 8:

[0155] After submitting the proposal to the client, feedback is received from the client based on user sentiment analysis. The server analyzes this data and extracts areas for improvement for the next proposal.

[0156] Step 9:

[0157] During the project, the server monitors the user's emotional state. If negative emotions such as stress increase, it sends the user suggestions for rest or coping strategies.

[0158] Step 10:

[0159] The server centrally manages all acquired data and uses it to build strategies for future sales activities. This data will be utilized in future sales efforts.

[0160] (Example 2)

[0161] 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".

[0162] In today's market, there is a demand for more effective and personalized sales proposals. However, traditional proposal methods fail to adequately improve client satisfaction because proposals are created without considering the user's emotional state. Furthermore, it is difficult to manage stress during project progress and to grasp the activities of competitors in real time.

[0163] 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.

[0164] In this invention, the server includes means for collecting market information, means for analyzing the collected market information to understand the activities of competing organizations, and means for collecting sentiment data. This makes it possible to optimize proposal documents based on the user's sentiment and to manage stress during project progress.

[0165] "Market information" refers to data about the market for a product or service, including customer trends and the actions of competitors.

[0166] "Means of collection" refers to the methods and techniques used to gather necessary data and information, usually involving the use of digital tools and systems.

[0167] "Means of analysis" refer to the techniques and methods used to process collected data and derive meaningful insights and conclusions.

[0168] "Competing organizations" refer to other companies or organizations that offer similar products or services in the same market or industry.

[0169] "Past success stories" are records of successful activities and projects carried out to date, which can serve as a reference for new strategies and plans.

[0170] A "proposal document" is a document that describes the sales pitch or proposal for a specific product or service, and forms part of the proposal activities conducted with customers.

[0171] "Methods of automatic generation" refer to technologies that use specific algorithms or programs to automatically create documents and data.

[0172] "Emotional data" refers to data that indicates an individual's emotional state, and is often obtained from facial expressions and tone of voice.

[0173] "Means of analysis" refers to the techniques and methods used to analyze input data and understand its structure and meaning.

[0174] "Means of monitoring" refers to methods and techniques for carefully observing a specific object and detecting anomalies or changes.

[0175] "Warning mechanisms" refer to methods and techniques for providing necessary attention or notice based on specific conditions or circumstances.

[0176] A "template" refers to a basic format or template that can be used for a specific purpose.

[0177] This invention is a system that recognizes user emotions and effectively supports sales proposal activities. By acquiring user emotion data and optimizing proposals based on that data, it is possible to improve client satisfaction.

[0178] The server first collects market information. Specifically, it uses data scraping tools to gather necessary data from publicly available databases and social media on the internet. It also interacts with databases and APIs to periodically obtain the latest information.

[0179] The server analyzes data collected through the analysis engine. Using Python and R languages, it applies machine learning algorithms to understand the activities of competing organizations and market trends, and generates proposal document templates based on past success stories.

[0180] The device uses its built-in camera and microphone to monitor the user's emotional data in real time. Emotion recognition software analyzes the user's facial expressions and tone of voice to detect their emotional state. This allows the system to identify the user's stress levels and satisfaction while reviewing proposed documents.

[0181] The collected sentiment data is sent to a server. The server uses a sentiment analysis algorithm to analyze the data and generate real-time feedback. Based on this feedback, the user can revise and optimize the proposed document.

[0182] For example, if a user expresses dissatisfaction while reviewing a specific section of a proposal document, the server sends a prompt to the AI ​​model saying, "Re-evaluate the relevant part of the proposal document and suggest more appropriate options." In this way, more effective proposals are created.

[0183] As an example of a prompt, you can send a message like, "The user expressed concern in the pricing section. Please suggest a more convincing pricing strategy," to the generative AI model to obtain appropriate improvements.

[0184] This system allows companies to optimize the entire sales process based on user emotions, enabling them to build a consistent strategy from proposal to order and even follow-up.

[0185] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0186] Step 1:

[0187] The server collects market and competitor data. It takes user-specified keywords as input and uses data scraping tools to retrieve information from publicly available databases and social media on the internet. This allows it to output up-to-date datasets on target markets and competing organizations. Specifically, the server periodically calls APIs to update the database.

[0188] Step 2:

[0189] The server analyzes the collected data. Using the dataset as input, it analyzes market trends and competitive landscapes using machine learning algorithms in Python or R. This results in the output of segmented market information and an understanding of competitive activities. Specifically, the server applies random forests and neural networks to extract data patterns.

[0190] Step 3:

[0191] The server generates proposal document templates based on past success stories. Using past case data as input, it employs a generation AI model to output new document templates. Specifically, during this process, the server selects a document structure with a high probability of success.

[0192] Step 4:

[0193] The device collects user emotion data. It uses emotion recognition software, taking the user's facial expressions and voice as input, to output real-time emotional state data. Specifically, the device continuously monitors the user's reactions through its built-in camera and microphone.

[0194] Step 5:

[0195] The server analyzes emotional data and generates feedback. It takes emotional state data as input and outputs feedback using an emotional analysis algorithm. Through its specific actions, the server periodically evaluates changes in the user's emotions and suggests necessary improvements.

[0196] Step 6:

[0197] The user revises the proposal document based on the generated feedback. The server receives feedback as input and outputs an optimized proposal document with the revisions made. Specifically, the user adjusts sections of the proposal document according to the feedback.

[0198] Step 7:

[0199] During project progress, the server monitors changes in the situation and issues warnings as needed. It takes progress data and stress level status as input and outputs warnings at the appropriate time. Specifically, its function is to send timely alerts regarding the user's work status.

[0200] (Application Example 2)

[0201] 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".

[0202] In modern sales activities, personalization tailored to the individual emotions of each customer is essential. However, conventional systems tend to focus on collecting market information and competitor analysis, failing to adequately grasp the real-time emotions of customers and users and optimize proposals based on that understanding. This makes it difficult to improve customer satisfaction and increase sales.

[0203] 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.

[0204] In this invention, the server includes means for collecting market information, means for analyzing the collected market information to understand the activities of competitors, means for learning from past success stories, means for automatically generating proposals, means for monitoring the progress of projects, means for issuing alerts when problems occur, means for acquiring user emotion data, means for analyzing the emotion data to optimize proposal content, and means for analyzing customer facial expressions and tone of voice to support sales proposals. This enables real-time optimization of proposals based on customer emotions.

[0205] "Means of collecting market information" refers to methods and devices for collecting data related to the market.

[0206] "Means of analyzing collected market information to understand the activities of competitors" refers to methods of analyzing collected data to understand the actions and strategies of competitors.

[0207] "Means of learning from past successes" refers to methods and systems for studying and learning from previously successful examples.

[0208] "Methods for automatically generating proposals" refers to a system for automatically creating sales proposals.

[0209] "Means of monitoring project progress" refers to methods and tools for tracking project progress and checking its status.

[0210] "Means of issuing alerts when a problem occurs" refers to methods or devices that issue warnings and draw attention when a problem arises.

[0211] "Means for acquiring user emotional data" refers to methods or devices for collecting information about users' emotions.

[0212] "Methods for analyzing emotional data to optimize proposals" refers to methods for analyzing acquired emotional information and optimizing proposals based on the results.

[0213] "Means of analyzing customer facial expressions and tone of voice to support sales proposals" refers to methods or devices that analyze a customer's facial expressions and tone of voice and use that information to support sales proposals.

[0214] This system is designed to optimize sales proposals based on user emotions by combining multiple methods. The server first collects market information and analyzes that data to understand competitor activities. This analysis utilizes databases and data analysis software. Furthermore, the server learns from past successes using machine learning models and automatically generates proposals based on that learning. This makes it possible to quickly create more effective sales materials.

[0215] Next, the user's device collects input data using its camera and microphone. This data includes the user's facial expressions and tone of voice. This data is analyzed using tools such as OpenCV and the Google Cloud Speech-to-Text API, and the user's emotions are sent to the server in real time. The server analyzes this emotion data and optimizes the suggestions using a generative AI model. The optimized suggestions are then sent back to the user's device.

[0216] As a concrete example, when a sales staff member is interacting with a customer, the system analyzes the customer's facial expressions and changes in voice, generating a prompt such as, "Based on the emotions this customer is showing, please suggest what to propose next." This prompt is then used to inform sales proposals. In this way, each proposal is optimized according to the individual customer's needs and emotions, leading to improved customer satisfaction and sales performance.

[0217] The hardware components include smartphones and smart glasses, while the software requires technologies such as Python, OpenCV, and Google Cloud Speech-to-Text. This system allows users to optimize sales pitches in real time based on emotions, enabling them to respond more appropriately to customers.

[0218] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0219] Step 1:

[0220] The server collects market information. Inputs include publicly available data from the internet, news feeds, and company activity reports. The server uses a crawler to collect this data and stores it in a database. The output is an organized list of market information.

[0221] Step 2:

[0222] The server analyzes the collected market information to understand the activities of competitors. The input is the market information collected in Step 1. Data mining techniques are used to identify competitor strategies and market trends. The output obtained from this process is a competitive activity analysis report.

[0223] Step 3:

[0224] The server learns from past success stories. The input is a database of past success stories within the company. The server applies machine learning algorithms to extract the factors contributing to success. The output is a model for generating new proposals.

[0225] Step 4:

[0226] The server automatically generates proposals. The inputs are proposal models derived from successful case studies and competitive analysis reports. Using the generation AI model, customized proposals are created for each customer. The output is the automatically generated proposal.

[0227] Step 5:

[0228] The device acquires user emotion data. Input consists of the user's facial image and voice data. This data is collected using the device's camera and microphone, and emotions are analyzed in real time. The output is the analyzed emotion data.

[0229] Step 6:

[0230] The server analyzes emotional data to optimize the proposal. The input is the emotional data and proposal obtained from step 5. Using a generative AI model, the proposal is adjusted based on the emotions. The output is an emotionally optimized proposal.

[0231] Step 7:

[0232] The terminal presents the optimized proposal to the user. The input is an optimized proposal sent from the server. The proposal is displayed on the terminal's screen and communicated to the user. The output is obtained as visual information for the user.

[0233] Step 8:

[0234] The user responds to the proposal. The input is an optimization proposal, and the user provides feedback and makes selections regarding it. The terminal further analyzes this response and acquires data to help improve the proposal in the future. The output is the user's feedback data.

[0235] 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.

[0236] 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.

[0237] 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.

[0238] [Second Embodiment]

[0239] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0240] 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.

[0241] 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).

[0242] 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.

[0243] 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.

[0244] 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).

[0245] 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.

[0246] 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.

[0247] 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.

[0248] 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.

[0249] 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.

[0250] 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".

[0251] One embodiment of the present invention is a system that autonomously supports sales proposal activities. This system operates primarily with a server, a terminal, and a user.

[0252] The server first automatically collects market information from the internet and internal databases. During this process, it utilizes text mining technology to extract data on industry trends, target company needs, and the latest developments of competitors. The collected data is then analyzed by a data analysis module built within the server. The analysis results provide the foundational information for formulating optimal proposals for target companies.

[0253] The server then runs an algorithm to learn from a database of past proposal activities and success stories. This database contains detailed information about past projects. The server uses machine learning techniques to identify common factors in successful proposals and forms a template for new proposals.

[0254] During the proposal generation phase, the server automatically creates a document based on the information it has collected, analyzed, and learned. This document, as a proposal, includes information on competitors and content aligned with the target company's needs. The proposal is provided to the user via their terminal. The user can review the generated proposal and make specific customizations or modifications as needed.

[0255] Throughout the project, the server monitors the schedule and task progress, collecting updates in real time. If any problems arise during project execution, the server immediately sends an alert to the user's terminal and proposes solutions based on past cases. This implementation allows companies to streamline their sales proposal activities and implement rapid and effective sales strategies.

[0256] The above describes a specific method for implementing the present invention. This system enables the entire sales process to proceed seamlessly, providing consistent support from proposal to order placement and follow-up.

[0257] The following describes the processing flow.

[0258] Step 1:

[0259] The server collects market information. Using web scraping techniques and API connections, it retrieves the latest information from industry reports and news sites and stores it in a database.

[0260] Step 2:

[0261] The server analyzes collected market information. Using natural language processing, it extracts competitor trends and target company needs from text data and generates reports.

[0262] Step 3:

[0263] The server learns from past proposal data. Successful proposals and project examples are fed into a machine learning algorithm to extract success factors and form templates for new proposals.

[0264] Step 4:

[0265] The server automatically generates proposals. Using analysis results and training data, it creates and saves customized proposals tailored to the target company's needs.

[0266] Step 5:

[0267] Users review proposals through their devices. They can provide feedback on automatically generated proposals and edit or add information as needed.

[0268] Step 6:

[0269] The server collects user feedback after the proposal is submitted. It analyzes the client's responses and uses them to improve the proposal if revisions are needed.

[0270] Step 7:

[0271] The server monitors the project's progress. It checks the schedule and task progress in real time and manages the project's progress.

[0272] Step 8:

[0273] The server will respond when problems occur. If a problem arises during project progress, an alert will be quickly delivered to the user's terminal, and specific suggestions for resolution will be provided.

[0274] (Example 1)

[0275] 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".

[0276] Traditional sales proposal activities relied heavily on manual processes for gathering market information, analyzing competitors, and learning from success stories, requiring significant time and effort. Furthermore, identifying and resolving issues requiring immediate attention during project execution proved difficult. This limited the effectiveness of sales strategies and hindered efficient work processes.

[0277] 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.

[0278] In this invention, the server includes means for collecting information from a database, means for analyzing the collected information to recognize competitor activities, and means for learning from past cases to identify contributing factors. This automates information gathering and analysis in sales activities, enabling efficient proposal creation and real-time project management.

[0279] A "database" is a collection of data that is systematically structured for the purpose of collecting, managing, and retrieving information.

[0280] "Analyzing information" is the process of processing collected data to derive useful insights and conclusions.

[0281] "Recognizing competitor activities" is the process of understanding, comparing, and evaluating the actions and plans of other business entities.

[0282] "Learning from past examples" means analyzing successful past operations and proposals and extracting useful patterns and factors from them.

[0283] A "generative model" is an algorithm or technology for generating new information based on a large amount of data.

[0284] "Generating a document" is the process of automatically creating documents or proposals based on pre-set rules or algorithms.

[0285] "Monitoring the situation" is the act of continuously checking the progress of a project or business and taking appropriate actions as needed.

[0286] "Issuing a warning" is an alert function that immediately notifies when a problem occurs and prompts appropriate actions.

[0287] "Display on the terminal" is to provide information visually through the user interface and create an environment where users can view and edit information.

[0288] "Generating a framework" is the process of creating templates for proposals or documents to serve as a basis for creating new documents.

[0289] "Analyzing the reaction to a document" is the act of collecting and analyzing feedback on the created document and measuring areas for improvement and effectiveness.

[0290] The present invention is a system for autonomously supporting business proposal activities, and specifically, it is mainly carried out by a server, a terminal, and a user. For the implementation of the system, web scraping technology and text mining technology using Python are utilized to collect information from databases and the web. Libraries such as BeautifulSoup and Scrapy are useful for this. The server analyzes the collected information using Pandas and NumPy to understand industry trends and the movements of competing companies.

[0291] Furthermore, the server uses Scikit-learn to learn from past successes. This identifies common patterns in successful proposals and forms a framework for new proposals. Generative AI models using the OpenAI API are utilized to generate these proposals. Specifically, advanced language generation is achieved using AI models from the GPT series.

[0292] The proposal is created by the server and then visually displayed to the user via their terminal. The user reviews the proposal on their terminal and edits the content as needed using Google Docs or Word. Throughout the project, the server monitors progress in real time and immediately sends notifications to the terminal if any problems arise. In this process, it integrates with project management tools to support rapid response.

[0293] As an example, when a user creates a proposal for a new product, this system allows them to quickly obtain a proposal that reflects market trends. For example, a prompt sentence to be entered into the generating AI model might be, "Create a proposal for a new cloud service product and include a sentence that emphasizes differentiation from competitors."

[0294] This invention enables the efficient and consistent collection, analysis, proposal writing, and project management of information related to sales activities, which is expected to lead to smoother sales operations for companies.

[0295] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0296] Step 1:

[0297] The server collects market information from the internet and internal databases. The input specifies the URL of the information source and the required data type. Specifically, it uses a web crawler to retrieve the information and organizes it using libraries such as BeautifulSoup and Scrapy. The output is market information formatted as text and numerical data.

[0298] Step 2:

[0299] The server processes the collected information using a data analysis module. The input is market information obtained in step 1, and the data is organized and aggregated using Pandas and NumPy. Then, Matplotlib is used to visualize the data and derive the needs of target companies and industry trends. The output is the analyzed data and trend graphs.

[0300] Step 3:

[0301] The server learns from a database of past success stories and generates proposal templates. The input is data from past proposals and success stories. A machine learning algorithm using Scikit-learn identifies common patterns in successful proposals. The output is a new proposal template.

[0302] Step 4:

[0303] The server creates a proposal based on the generated template. The inputs are the analysis data and template obtained in steps 2 and 3. The generating AI model is used to construct the document using this data. The output is a proposal tailored to the target company's needs.

[0304] Step 5:

[0305] The terminal displays the proposal sent from the server to the user. The input is the proposal data from the server. The user reviews this proposal in Google Docs or Word and edits it as needed. The output is the final version of the proposal customized by the user.

[0306] Step 6:

[0307] The server monitors the progress of the project and issues alerts when problems occur. The input is the schedule of the ongoing project and the task progress information. It cooperates with the project management tool and displays a warning on the user's terminal when an abnormality is detected. The output is a proposal for an immediate response to the problem.

[0308] (Application Example 1)

[0309] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0310] In modern sales activities, while quick and effective proposals are required, the complexity of the market and the diversification of customer needs are advancing. Therefore, a means that can consistently and efficiently execute from information collection and analysis to proposal document creation and project management is necessary. Also, the lack of support tools for sales staff to always maintain up-to-date information and smooth project progress is an issue.

[0311] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0312] In this invention, the server includes means for collecting market data, means for analyzing the collected market data to identify the trends of competing organizations, means for learning past successful cases, and means for providing information on a mobile terminal for sales activities. As a result, sales staff can quickly generate proposal documents, formulate effective sales strategies based on up-to-date information, monitor the progress of the project in real time, and immediately take measures to solve problems.

[0313] The "means for collecting market data" refers to the function of obtaining information on the market environment from the Internet or the in-house database. This information is utilized as background data necessary for sales activities.

[0314] "Means of analyzing collected market data to identify the activities of competing organizations" refers to the function of analyzing acquired market data to clarify the activities and market positions of other competing organizations.

[0315] "Methods for learning from past success stories" refer to the function of studying the results and proposals of previous sales activities and extracting the factors for success. This allows for improvement in the quality of new proposals.

[0316] "Methods for automatically generating proposal documents" refer to a function that automatically creates high-quality sales proposals based on analyzed and learned information. This will improve the efficiency of proposal creation.

[0317] "Means of providing information on mobile devices for sales activities" refers to a function that provides necessary information to the devices carried by sales representatives and allows them to view the latest data in real time.

[0318] "Means for monitoring project progress" refers to functions that allow you to understand the status of sales projects and track their progress. This is useful for schedule management and checking task progress.

[0319] "A means of issuing an alert when a problem occurs" refers to a function that allows for the rapid notification of the person in charge when a problem arises during the progress of a project. This enables rapid problem resolution.

[0320] To implement this invention, it is first necessary to prepare an infrastructure for the server to collect and analyze market data. This infrastructure will utilize a database equipped with text mining technology and machine learning algorithms. Specifically, the Python language will be used to scrape data with BeautifulSoup, organize it with Pandas, and analyze it with scikit-learn. This data will include the trends of competing organizations and past success stories, making it fundamental information for sales proposals.

[0321] Next, the server utilizes a generative AI model to automatically generate proposal documents based on the collected and analyzed data. These documents are sent in real time to the mobile devices used by sales representatives. Users can view, edit, and utilize the generated proposal documents on a dashboard developed using React. Furthermore, the generative AI model can be used to provide prompts such as the following:

[0322] As a specific example, a sales representative can use the following prompt before visiting a customer.

[0323] "Please create a proposal for the target company. Their main need is for the latest payment technology. Please include information on the activities of their competitors."

[0324] Furthermore, the server monitors project progress, issues alerts when problems arise, and generates and provides solutions based on past cases to the user. This optimizes the sales process in real time, enabling rapid response. Implementing this system streamlines the entire sales process, providing consistent support from proposal to order placement and follow-up.

[0325] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0326] Step 1:

[0327] The server collects market data from the internet and internal databases. Inputs are URLs and query information obtained through various APIs and scraping techniques. The data is extracted and structured using BeautifulSoup. The output is a collection of market data in text format, which is used in the next analysis step.

[0328] Step 2:

[0329] The server analyzes the collected market data using text mining techniques. The input is the market data set obtained in Step 1. This data is organized using Pandas, and then analyzed using scikit-learn to identify industry trends and the activities of competing organizations. The output is trend data and competitive activity information as a result of the analysis.

[0330] Step 3:

[0331] The server learns from a database of past success stories. The input consists of past proposals and project success stories. Using machine learning algorithms, it extracts success factors from this data and learns patterns. The output is a model of success patterns that helps generate new proposals.

[0332] Step 4:

[0333] The server automatically generates proposal documents using a generative AI model. The input consists of the analysis results from Step 2 and the success pattern model from Step 3. Using document generation technology, it creates proposals optimized for sales. The output is the proposal document provided to the sales representative.

[0334] Step 5:

[0335] The terminal receives proposal documents sent from the server and displays them for the sales representative to review and edit. The input is the proposal document sent from the server. A React-based interface is used, allowing the user to edit and save the proposal document. The output is the edited proposal document.

[0336] Step 6:

[0337] The server monitors project progress and collects progress data. Input is progress information obtained from project management tools (e.g., Jira API). Progress is monitored in real time, and important changes are notified. Output is a project progress report.

[0338] Step 7:

[0339] The server issues an alert and provides a solution when a problem occurs. The input is the problem information detected in step 6. It selects a solution based on a database of past cases and provides it to the user along with the alert. The output is an alert for the problem and guidance on the solution.

[0340] 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.

[0341] One possible embodiment of the present invention is a system that recognizes user emotions and more effectively supports sales proposal activities. In addition to conventional functions such as market information gathering, competitor analysis, and automatic proposal generation, this system integrates an emotion engine to enable more personalized proposals.

[0342] The server first performs basic functions such as market information and competitive analysis. It analyzes the collected data to understand the needs of target companies and the activities of competitors. Subsequently, it uses machine learning to analyze a database of past success stories and generates new proposal templates.

[0343] The role of the emotion engine is to acquire user emotion data through the device's camera or voice input as the user reviews or revises the proposal. This data is sent to the server and analyzed in real time. For example, if a user shows emotions of stress or dissatisfaction while viewing a particular part of the proposal, the server will re-evaluate that part and suggest revising the proposal.

[0344] User emotion-based feedback is used at every phase of the proposal process. For example, before submitting a proposal, the content is optimized to prioritize the structure and expression that elicited the most favorable responses from users. After the proposal is submitted, the emotion engine is also applied to client feedback, allowing for an emotional analysis of areas for improvement in future proposals.

[0345] During project execution, the server monitors user emotional data and issues alerts if stress levels rise. For example, as a project deadline approaches, the server suggests appropriate breaks to the user and provides support to maintain work efficiency.

[0346] This allows for flexible adjustment of proposals and project management in response to user emotions, enabling more effective and satisfying sales proposal activities. The above describes the specific implementation method of the present invention. This system allows companies to optimize the entire sales process based on the emotional responses of consumers and clients, and to improve consistency from proposal to order placement and follow-up.

[0347] The following describes the processing flow.

[0348] Step 1:

[0349] The server collects market information via the internet and internal databases. This includes the latest industry trends, competitor activities, and the business needs of target companies.

[0350] Step 2:

[0351] The server analyzes the market information it collects. Using natural language processing, it extracts key insights from text data and generates competitive analysis reports.

[0352] Step 3:

[0353] The server learns from past success stories using machine learning. It extracts success factors from past proposal records in the database and creates a new proposal template.

[0354] Step 4:

[0355] The server automatically generates proposals. Based on the acquired analysis results and success story templates, it creates proposals optimized for the target company.

[0356] Step 5:

[0357] The user reviews the proposal generated through their device. While viewing the proposal, the device uses its built-in camera and microphone to collect user emotion data.

[0358] Step 6:

[0359] The server receives user sentiment data and analyzes it in real time. It identifies areas where the user has expressed stress or dissatisfaction and generates advice for improving the proposal.

[0360] Step 7:

[0361] Users revise the proposal based on their emotional feedback. By implementing specific improvements, the proposal's quality is enhanced.

[0362] Step 8:

[0363] After submitting the proposal to the client, feedback is received from the client based on user sentiment analysis. The server analyzes this data and extracts areas for improvement for the next proposal.

[0364] Step 9:

[0365] During the project, the server monitors the user's emotional state. If negative emotions such as stress increase, it sends the user suggestions for rest or coping strategies.

[0366] Step 10:

[0367] The server centrally manages all acquired data and uses it to build strategies for future sales activities. This data will be utilized in future sales efforts.

[0368] (Example 2)

[0369] 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".

[0370] In today's market, there is a demand for more effective and personalized sales proposals. However, traditional proposal methods fail to adequately improve client satisfaction because proposals are created without considering the user's emotional state. Furthermore, it is difficult to manage stress during project progress and to grasp the activities of competitors in real time.

[0371] 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.

[0372] In this invention, the server includes means for collecting market information, means for analyzing the collected market information to understand the activities of competing organizations, and means for collecting sentiment data. This makes it possible to optimize proposal documents based on the user's sentiment and to manage stress during project progress.

[0373] "Market information" refers to data about the market for a product or service, including customer trends and the actions of competitors.

[0374] "Means of collection" refers to the methods and techniques used to gather necessary data and information, usually involving the use of digital tools and systems.

[0375] "Means of analysis" refer to the techniques and methods used to process collected data and derive meaningful insights and conclusions.

[0376] "Competing organizations" refer to other companies or organizations that offer similar products or services in the same market or industry.

[0377] "Past success stories" are records of successful activities and projects carried out to date, which can serve as a reference for new strategies and plans.

[0378] A "proposal document" is a document that describes the sales pitch or proposal for a specific product or service, and forms part of the proposal activities conducted with customers.

[0379] "Methods of automatic generation" refer to technologies that use specific algorithms or programs to automatically create documents and data.

[0380] "Emotional data" refers to data that indicates an individual's emotional state, and is often obtained from facial expressions and tone of voice.

[0381] "Means of analysis" refers to the techniques and methods used to analyze input data and understand its structure and meaning.

[0382] "Means of monitoring" refers to methods and techniques for carefully observing a specific object and detecting anomalies or changes.

[0383] "Warning mechanisms" refer to methods and techniques for providing necessary attention or notice based on specific conditions or circumstances.

[0384] A "template" refers to a basic format or template that can be used for a specific purpose.

[0385] This invention is a system that recognizes user emotions and effectively supports sales proposal activities. By acquiring user emotion data and optimizing proposals based on that data, it is possible to improve client satisfaction.

[0386] The server first collects market information. Specifically, it uses data scraping tools to gather necessary data from publicly available databases and social media on the internet. It also interacts with databases and APIs to periodically obtain the latest information.

[0387] The server analyzes data collected through the analysis engine. Using Python and R languages, it applies machine learning algorithms to understand the activities of competing organizations and market trends, and generates proposal document templates based on past success stories.

[0388] The device uses its built-in camera and microphone to monitor the user's emotional data in real time. Emotion recognition software analyzes the user's facial expressions and tone of voice to detect their emotional state. This allows the system to identify the user's stress levels and satisfaction while reviewing proposed documents.

[0389] The collected sentiment data is sent to a server. The server uses a sentiment analysis algorithm to analyze the data and generate real-time feedback. Based on this feedback, the user can revise and optimize the proposed document.

[0390] For example, if a user expresses dissatisfaction while reviewing a specific section of a proposal document, the server sends a prompt to the AI ​​model saying, "Re-evaluate the relevant part of the proposal document and suggest more appropriate options." In this way, more effective proposals are created.

[0391] As an example of a prompt, you can send a message like, "The user expressed concern in the pricing section. Please suggest a more convincing pricing strategy," to the generative AI model to obtain appropriate improvements.

[0392] This system allows companies to optimize the entire sales process based on user emotions, enabling them to build a consistent strategy from proposal to order and even follow-up.

[0393] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0394] Step 1:

[0395] The server collects market and competitor data. It takes user-specified keywords as input and uses data scraping tools to retrieve information from publicly available databases and social media on the internet. This allows it to output up-to-date datasets on target markets and competing organizations. Specifically, the server periodically calls APIs to update the database.

[0396] Step 2:

[0397] The server analyzes the collected data. Using the dataset as input, it analyzes market trends and competitive landscapes using machine learning algorithms in Python or R. This results in the output of segmented market information and an understanding of competitive activities. Specifically, the server applies random forests and neural networks to extract data patterns.

[0398] Step 3:

[0399] The server generates proposal document templates based on past success stories. Using past case data as input, it employs a generation AI model to output new document templates. Specifically, during this process, the server selects a document structure with a high probability of success.

[0400] Step 4:

[0401] The device collects user emotion data. It uses emotion recognition software, taking the user's facial expressions and voice as input, to output real-time emotional state data. Specifically, the device continuously monitors the user's reactions through its built-in camera and microphone.

[0402] Step 5:

[0403] The server analyzes emotional data and generates feedback. It takes emotional state data as input and outputs feedback using an emotional analysis algorithm. Through its specific actions, the server periodically evaluates changes in the user's emotions and suggests necessary improvements.

[0404] Step 6:

[0405] The user revises the proposal document based on the generated feedback. The server receives feedback as input and outputs an optimized proposal document with the revisions made. Specifically, the user adjusts sections of the proposal document according to the feedback.

[0406] Step 7:

[0407] During project progress, the server monitors changes in the situation and issues warnings as needed. It takes progress data and stress level status as input and outputs warnings at the appropriate time. Specifically, its function is to send timely alerts regarding the user's work status.

[0408] (Application Example 2)

[0409] 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."

[0410] In modern sales activities, personalization tailored to the individual emotions of each customer is essential. However, conventional systems tend to focus on collecting market information and competitor analysis, failing to adequately grasp the real-time emotions of customers and users and optimize proposals based on that understanding. This makes it difficult to improve customer satisfaction and increase sales.

[0411] 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.

[0412] In this invention, the server includes means for collecting market information, means for analyzing the collected market information to understand the activities of competitors, means for learning from past success stories, means for automatically generating proposals, means for monitoring the progress of projects, means for issuing alerts when problems occur, means for acquiring user emotion data, means for analyzing the emotion data to optimize proposal content, and means for analyzing customer facial expressions and tone of voice to support sales proposals. This enables real-time optimization of proposals based on customer emotions.

[0413] "Means of collecting market information" refers to methods and devices for collecting data related to the market.

[0414] "Means of analyzing collected market information to understand the activities of competitors" refers to methods of analyzing collected data to understand the actions and strategies of competitors.

[0415] "Means of learning from past successes" refers to methods and systems for studying and learning from previously successful examples.

[0416] "Methods for automatically generating proposals" refers to a system for automatically creating sales proposals.

[0417] "Means of monitoring project progress" refers to methods and tools for tracking project progress and checking its status.

[0418] "Means of issuing alerts when a problem occurs" refers to methods or devices that issue warnings and draw attention when a problem arises.

[0419] "Means for acquiring user emotional data" refers to methods or devices for collecting information about users' emotions.

[0420] "Methods for analyzing emotional data to optimize proposals" refers to methods for analyzing acquired emotional information and optimizing proposals based on the results.

[0421] "Means of analyzing customer facial expressions and tone of voice to support sales proposals" refers to methods or devices that analyze a customer's facial expressions and tone of voice and use that information to support sales proposals.

[0422] This system is designed to optimize sales proposals based on user emotions by combining multiple methods. The server first collects market information and analyzes that data to understand competitor activities. This analysis utilizes databases and data analysis software. Furthermore, the server learns from past successes using machine learning models and automatically generates proposals based on that learning. This makes it possible to quickly create more effective sales materials.

[0423] Next, the user's device collects input data using its camera and microphone. This data includes the user's facial expressions and tone of voice. This data is analyzed using tools such as OpenCV and the Google Cloud Speech-to-Text API, and the user's emotions are sent to the server in real time. The server analyzes this emotion data and optimizes the suggestions using a generative AI model. The optimized suggestions are then sent back to the user's device.

[0424] As a concrete example, when a sales staff member is interacting with a customer, the system analyzes the customer's facial expressions and changes in voice, generating a prompt such as, "Based on the emotions this customer is showing, please suggest what to propose next." This prompt is then used to inform sales proposals. In this way, each proposal is optimized according to the individual customer's needs and emotions, leading to improved customer satisfaction and sales performance.

[0425] The hardware components include smartphones and smart glasses, while the software requires technologies such as Python, OpenCV, and Google Cloud Speech-to-Text. This system allows users to optimize sales pitches in real time based on emotions, enabling them to respond more appropriately to customers.

[0426] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0427] Step 1:

[0428] The server collects market information. Inputs include publicly available data from the internet, news feeds, and company activity reports. The server uses a crawler to collect this data and stores it in a database. The output is an organized list of market information.

[0429] Step 2:

[0430] The server analyzes the collected market information to understand the activities of competitors. The input is the market information collected in Step 1. Data mining techniques are used to identify competitor strategies and market trends. The output obtained from this process is a competitive activity analysis report.

[0431] Step 3:

[0432] The server learns from past success stories. The input is a database of past success stories within the company. The server applies machine learning algorithms to extract the factors contributing to success. The output is a model for generating new proposals.

[0433] Step 4:

[0434] The server automatically generates proposals. The inputs are proposal models derived from successful case studies and competitive analysis reports. Using the generation AI model, customized proposals are created for each customer. The output is the automatically generated proposal.

[0435] Step 5:

[0436] The device acquires user emotion data. Input consists of the user's facial image and voice data. This data is collected using the device's camera and microphone, and emotions are analyzed in real time. The output is the analyzed emotion data.

[0437] Step 6:

[0438] The server analyzes emotional data to optimize the proposal. The input is the emotional data and proposal obtained from step 5. Using a generative AI model, the proposal is adjusted based on the emotions. The output is an emotionally optimized proposal.

[0439] Step 7:

[0440] The terminal presents the optimized proposal to the user. The input is an optimized proposal sent from the server. The proposal is displayed on the terminal's screen and communicated to the user. The output is obtained as visual information for the user.

[0441] Step 8:

[0442] The user responds to the proposal. The input is an optimization proposal, and the user provides feedback and makes selections regarding it. The terminal further analyzes this response and acquires data to help improve the proposal in the future. The output is the user's feedback data.

[0443] 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.

[0444] 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.

[0445] 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.

[0446] [Third Embodiment]

[0447] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0448] 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.

[0449] 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).

[0450] 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.

[0451] 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.

[0452] 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).

[0453] 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.

[0454] 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.

[0455] 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.

[0456] 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.

[0457] 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.

[0458] 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".

[0459] One embodiment of the present invention is a system that autonomously supports sales proposal activities. This system operates primarily with a server, a terminal, and a user.

[0460] The server first automatically collects market information from the internet and internal databases. During this process, it utilizes text mining technology to extract data on industry trends, target company needs, and the latest developments of competitors. The collected data is then analyzed by a data analysis module built within the server. The analysis results provide the foundational information for formulating optimal proposals for target companies.

[0461] The server then runs an algorithm to learn from a database of past proposal activities and success stories. This database contains detailed information about past projects. The server uses machine learning techniques to identify common factors in successful proposals and forms a template for new proposals.

[0462] During the proposal generation phase, the server automatically creates a document based on the information it has collected, analyzed, and learned. This document, as a proposal, includes information on competitors and content aligned with the target company's needs. The proposal is provided to the user via their terminal. The user can review the generated proposal and make specific customizations or modifications as needed.

[0463] Throughout the project, the server monitors the schedule and task progress, collecting updates in real time. If any problems arise during project execution, the server immediately sends an alert to the user's terminal and proposes solutions based on past cases. This implementation allows companies to streamline their sales proposal activities and implement rapid and effective sales strategies.

[0464] The above describes a specific method for implementing the present invention. This system enables the entire sales process to proceed seamlessly, providing consistent support from proposal to order placement and follow-up.

[0465] The following describes the processing flow.

[0466] Step 1:

[0467] The server collects market information. Using web scraping techniques and API connections, it retrieves the latest information from industry reports and news sites and stores it in a database.

[0468] Step 2:

[0469] The server analyzes collected market information. Using natural language processing, it extracts competitor trends and target company needs from text data and generates reports.

[0470] Step 3:

[0471] The server learns from past proposal data. Successful proposals and project examples are fed into a machine learning algorithm to extract success factors and form templates for new proposals.

[0472] Step 4:

[0473] The server automatically generates proposals. Using analysis results and training data, it creates and saves customized proposals tailored to the target company's needs.

[0474] Step 5:

[0475] Users review proposals through their devices. They can provide feedback on automatically generated proposals and edit or add information as needed.

[0476] Step 6:

[0477] The server collects user feedback after the proposal is submitted. It analyzes the client's responses and uses them to improve the proposal if revisions are needed.

[0478] Step 7:

[0479] The server monitors the project's progress. It checks the schedule and task progress in real time and manages the project's progress.

[0480] Step 8:

[0481] The server will respond when problems occur. If a problem arises during project progress, an alert will be quickly delivered to the user's terminal, and specific suggestions for resolution will be provided.

[0482] (Example 1)

[0483] 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."

[0484] Traditional sales proposal activities relied heavily on manual processes for gathering market information, analyzing competitors, and learning from success stories, requiring significant time and effort. Furthermore, identifying and resolving issues requiring immediate attention during project execution proved difficult. This limited the effectiveness of sales strategies and hindered efficient work processes.

[0485] 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.

[0486] In this invention, the server includes means for collecting information from a database, means for analyzing the collected information to recognize competitor activities, and means for learning from past cases to identify contributing factors. This automates information gathering and analysis in sales activities, enabling efficient proposal creation and real-time project management.

[0487] A "database" is a collection of data that is systematically structured for the purpose of collecting, managing, and retrieving information.

[0488] "Analyzing information" is the process of processing collected data to derive useful insights and conclusions.

[0489] "Recognizing competitor activities" is the process of understanding, comparing, and evaluating the actions and plans of other business entities.

[0490] "Learning from past examples" means analyzing successful past operations and proposals and extracting useful patterns and factors from them.

[0491] A "generative model" is an algorithm or technique for generating new information based on a large amount of data.

[0492] "Generating a document" refers to the process of automatically creating documents or proposals based on pre-defined rules and algorithms.

[0493] "Monitoring the situation" means continuously checking the progress of a project or task and taking action as needed.

[0494] "Issuing a warning" refers to an alert function that immediately notifies users when a problem occurs and prompts them to take appropriate action.

[0495] "Display on a device" means providing information visually through a user interface and creating an environment where users can view and edit that information.

[0496] "Generating a framework" refers to the process of creating templates for proposals and documents, which serve as a foundation for creating new documents.

[0497] "Analyzing responses to a document" refers to the act of collecting and analyzing feedback on a created document to measure areas for improvement and its effectiveness.

[0498] This invention is a system that autonomously supports sales proposal activities, specifically involving a server, terminals, and users. The system utilizes Python-based web scraping and text mining techniques to collect information from databases and the web. Libraries such as BeautifulSoup and Scrapy are useful for this purpose. The server analyzes the collected information using Pandas and NumPy to understand industry trends and competitor activities.

[0499] Furthermore, the server uses Scikit-learn to learn from past successes. This identifies common patterns in successful proposals and forms a framework for new proposals. Generative AI models using the OpenAI API are utilized to generate these proposals. Specifically, advanced language generation is achieved using AI models from the GPT series.

[0500] The proposal is created by the server and then visually displayed to the user via their terminal. The user reviews the proposal on their terminal and edits the content as needed using Google Docs or Word. Throughout the project, the server monitors progress in real time and immediately sends notifications to the terminal if any problems arise. In this process, it integrates with project management tools to support rapid response.

[0501] As an example, when a user creates a proposal for a new product, this system allows them to quickly obtain a proposal that reflects market trends. For example, a prompt sentence to be entered into the generating AI model might be, "Create a proposal for a new cloud service product and include a sentence that emphasizes differentiation from competitors."

[0502] This invention enables the efficient and consistent collection, analysis, proposal writing, and project management of information related to sales activities, which is expected to lead to smoother sales operations for companies.

[0503] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0504] Step 1:

[0505] The server collects market information from the internet and internal databases. The input specifies the URL of the information source and the required data type. Specifically, it uses a web crawler to retrieve the information and organizes it using libraries such as BeautifulSoup and Scrapy. The output is market information formatted as text and numerical data.

[0506] Step 2:

[0507] The server processes the collected information using a data analysis module. The input is market information obtained in step 1, and the data is organized and aggregated using Pandas and NumPy. Then, Matplotlib is used to visualize the data and derive the needs of target companies and industry trends. The output is the analyzed data and trend graphs.

[0508] Step 3:

[0509] The server learns from a database of past success stories and generates proposal templates. The input is data from past proposals and success stories. A machine learning algorithm using Scikit-learn identifies common patterns in successful proposals. The output is a new proposal template.

[0510] Step 4:

[0511] The server creates a proposal based on the generated template. The inputs are the analysis data and template obtained in steps 2 and 3. The generating AI model is used to construct the document using this data. The output is a proposal tailored to the target company's needs.

[0512] Step 5:

[0513] The terminal displays the proposal sent from the server to the user. The input is the proposal data from the server. The user reviews this proposal in Google Docs or Word and edits it as needed. The output is the final version of the proposal customized by the user.

[0514] Step 6:

[0515] The server monitors project progress and issues alerts when problems occur. Inputs include the project schedule and task progress information for ongoing projects. It integrates with project management tools and displays warnings on the user's terminal if an anomaly is detected. Outputs are suggestions for immediate action to address the problem.

[0516] (Application Example 1)

[0517] 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."

[0518] In modern sales activities, while rapid and effective proposals are required, the market is becoming increasingly complex and customer needs are diversifying. Therefore, there is a need for a system that can efficiently and consistently execute everything from information gathering and analysis to proposal creation and project management. Furthermore, a lack of support tools to help sales representatives maintain up-to-date information and smooth project progress is also a challenge.

[0519] 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.

[0520] In this invention, the server includes means for collecting market data, means for analyzing the collected market data to identify the activities of competing organizations, means for learning from past success stories, and means for providing information on mobile terminals for sales activities. This enables sales representatives to quickly generate proposal documents, formulate effective sales strategies based on the latest information, monitor project progress in real time, and immediately take action to resolve problems.

[0521] "Means of collecting market data" refers to the function of obtaining information about the market environment from the internet or internal databases. This information is used as background data necessary for sales activities.

[0522] "Means of analyzing collected market data to identify the activities of competing organizations" refers to the function of analyzing acquired market data to clarify the activities and market positions of other competing organizations.

[0523] "Methods for learning from past success stories" refer to the function of studying the results and proposals of previous sales activities and extracting the factors for success. This allows for improvement in the quality of new proposals.

[0524] "Methods for automatically generating proposal documents" refer to a function that automatically creates high-quality sales proposals based on analyzed and learned information. This will improve the efficiency of proposal creation.

[0525] "Means of providing information on mobile devices for sales activities" refers to a function that provides necessary information to the devices carried by sales representatives and allows them to view the latest data in real time.

[0526] "Means for monitoring project progress" refers to functions that allow you to understand the status of sales projects and track their progress. This is useful for schedule management and checking task progress.

[0527] "A means of issuing an alert when a problem occurs" refers to a function that allows for the rapid notification of the person in charge when a problem arises during the progress of a project. This enables rapid problem resolution.

[0528] To implement this invention, it is first necessary to prepare an infrastructure for the server to collect and analyze market data. This infrastructure will utilize a database equipped with text mining technology and machine learning algorithms. Specifically, the Python language will be used to scrape data with BeautifulSoup, organize it with Pandas, and analyze it with scikit-learn. This data will include the trends of competing organizations and past success stories, making it fundamental information for sales proposals.

[0529] Next, the server utilizes a generative AI model to automatically generate proposal documents based on the collected and analyzed data. These documents are sent in real time to the mobile devices used by sales representatives. Users can view, edit, and utilize the generated proposal documents on a dashboard developed using React. Furthermore, the generative AI model can be used to provide prompts such as the following:

[0530] As a specific example, a sales representative can use the following prompt before visiting a customer.

[0531] "Please create a proposal for the target company. Their main need is for the latest payment technology. Please include information on the activities of their competitors."

[0532] Furthermore, the server monitors project progress, issues alerts when problems arise, and generates and provides solutions based on past cases to the user. This optimizes the sales process in real time, enabling rapid response. Implementing this system streamlines the entire sales process, providing consistent support from proposal to order placement and follow-up.

[0533] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0534] Step 1:

[0535] The server collects market data from the internet and internal databases. Inputs are URLs and query information obtained through various APIs and scraping techniques. The data is extracted and structured using BeautifulSoup. The output is a collection of market data in text format, which is used in the next analysis step.

[0536] Step 2:

[0537] The server analyzes the collected market data using text mining techniques. The input is the market data set obtained in Step 1. This data is organized using Pandas, and then analyzed using scikit-learn to identify industry trends and the activities of competing organizations. The output is trend data and competitive activity information as a result of the analysis.

[0538] Step 3:

[0539] The server learns from a database of past success stories. The input consists of past proposals and project success stories. Using machine learning algorithms, it extracts success factors from this data and learns patterns. The output is a model of success patterns that helps generate new proposals.

[0540] Step 4:

[0541] The server automatically generates proposal documents using a generative AI model. The input consists of the analysis results from Step 2 and the success pattern model from Step 3. Using document generation technology, it creates proposals optimized for sales. The output is the proposal document provided to the sales representative.

[0542] Step 5:

[0543] The terminal receives proposal documents sent from the server and displays them for the sales representative to review and edit. The input is the proposal document sent from the server. A React-based interface is used, allowing the user to edit and save the proposal document. The output is the edited proposal document.

[0544] Step 6:

[0545] The server monitors project progress and collects progress data. Input is progress information obtained from project management tools (e.g., Jira API). Progress is monitored in real time, and important changes are notified. Output is a project progress report.

[0546] Step 7:

[0547] The server issues an alert and provides a solution when a problem occurs. The input is the problem information detected in step 6. It selects a solution based on a database of past cases and provides it to the user along with the alert. The output is an alert for the problem and guidance on the solution.

[0548] 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.

[0549] One possible embodiment of the present invention is a system that recognizes user emotions and more effectively supports sales proposal activities. In addition to conventional functions such as market information gathering, competitor analysis, and automatic proposal generation, this system integrates an emotion engine to enable more personalized proposals.

[0550] The server first performs basic functions such as market information and competitive analysis. It analyzes the collected data to understand the needs of target companies and the activities of competitors. Subsequently, it uses machine learning to analyze a database of past success stories and generates new proposal templates.

[0551] The role of the emotion engine is to acquire user emotion data through the device's camera or voice input as the user reviews or revises the proposal. This data is sent to the server and analyzed in real time. For example, if a user shows emotions of stress or dissatisfaction while viewing a particular part of the proposal, the server will re-evaluate that part and suggest revising the proposal.

[0552] User emotion-based feedback is used at every phase of the proposal process. For example, before submitting a proposal, the content is optimized to prioritize the structure and expression that elicited the most favorable responses from users. After the proposal is submitted, the emotion engine is also applied to client feedback, allowing for an emotional analysis of areas for improvement in future proposals.

[0553] During project execution, the server monitors user emotional data and issues alerts if stress levels rise. For example, as a project deadline approaches, the server suggests appropriate breaks to the user and provides support to maintain work efficiency.

[0554] This allows for flexible adjustment of proposals and project management in response to user emotions, enabling more effective and satisfying sales proposal activities. The above describes the specific implementation method of the present invention. This system allows companies to optimize the entire sales process based on the emotional responses of consumers and clients, and to improve consistency from proposal to order placement and follow-up.

[0555] The following describes the processing flow.

[0556] Step 1:

[0557] The server collects market information via the internet and internal databases. This includes the latest industry trends, competitor activities, and the business needs of target companies.

[0558] Step 2:

[0559] The server analyzes the market information it collects. Using natural language processing, it extracts key insights from text data and generates competitive analysis reports.

[0560] Step 3:

[0561] The server learns from past success stories using machine learning. It extracts success factors from past proposal records in the database and creates a new proposal template.

[0562] Step 4:

[0563] The server automatically generates proposals. Based on the acquired analysis results and success story templates, it creates proposals optimized for the target company.

[0564] Step 5:

[0565] The user reviews the proposal generated through their device. While viewing the proposal, the device uses its built-in camera and microphone to collect user emotion data.

[0566] Step 6:

[0567] The server receives user sentiment data and analyzes it in real time. It identifies areas where the user has expressed stress or dissatisfaction and generates advice for improving the proposal.

[0568] Step 7:

[0569] Users revise the proposal based on their emotional feedback. By implementing specific improvements, the proposal's quality is enhanced.

[0570] Step 8:

[0571] After submitting the proposal to the client, feedback is received from the client based on user sentiment analysis. The server analyzes this data and extracts areas for improvement for the next proposal.

[0572] Step 9:

[0573] During the project, the server monitors the user's emotional state. If negative emotions such as stress increase, it sends the user suggestions for rest or coping strategies.

[0574] Step 10:

[0575] The server centrally manages all acquired data and uses it to build strategies for future sales activities. This data will be utilized in future sales efforts.

[0576] (Example 2)

[0577] 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."

[0578] In today's market, there is a demand for more effective and personalized sales proposals. However, traditional proposal methods fail to adequately improve client satisfaction because proposals are created without considering the user's emotional state. Furthermore, it is difficult to manage stress during project progress and to grasp the activities of competitors in real time.

[0579] 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.

[0580] In this invention, the server includes means for collecting market information, means for analyzing the collected market information to understand the activities of competing organizations, and means for collecting sentiment data. This makes it possible to optimize proposal documents based on the user's sentiment and to manage stress during project progress.

[0581] "Market information" refers to data about the market for a product or service, including customer trends and the actions of competitors.

[0582] "Means of collection" refers to the methods and techniques used to gather necessary data and information, usually involving the use of digital tools and systems.

[0583] "Means of analysis" refer to the techniques and methods used to process collected data and derive meaningful insights and conclusions.

[0584] "Competing organizations" refer to other companies or organizations that offer similar products or services in the same market or industry.

[0585] "Past success stories" are records of successful activities and projects carried out to date, which can serve as a reference for new strategies and plans.

[0586] A "proposal document" is a document that describes the sales pitch or proposal for a specific product or service, and forms part of the proposal activities conducted with customers.

[0587] "Methods of automatic generation" refer to technologies that use specific algorithms or programs to automatically create documents and data.

[0588] "Emotional data" refers to data that indicates an individual's emotional state, and is often obtained from facial expressions and tone of voice.

[0589] "Means of analysis" refers to the techniques and methods used to analyze input data and understand its structure and meaning.

[0590] "Means of monitoring" refers to methods and techniques for carefully observing a specific object and detecting anomalies or changes.

[0591] "Warning mechanisms" refer to methods and techniques for providing necessary attention or notice based on specific conditions or circumstances.

[0592] A "template" refers to a basic format or template that can be used for a specific purpose.

[0593] This invention is a system that recognizes user emotions and effectively supports sales proposal activities. By acquiring user emotion data and optimizing proposals based on that data, it is possible to improve client satisfaction.

[0594] The server first collects market information. Specifically, it uses data scraping tools to gather necessary data from publicly available databases and social media on the internet. It also interacts with databases and APIs to periodically obtain the latest information.

[0595] The server analyzes data collected through the analysis engine. Using Python and R languages, it applies machine learning algorithms to understand the activities of competing organizations and market trends, and generates proposal document templates based on past success stories.

[0596] The device uses its built-in camera and microphone to monitor the user's emotional data in real time. Emotion recognition software analyzes the user's facial expressions and tone of voice to detect their emotional state. This allows the system to identify the user's stress levels and satisfaction while reviewing proposed documents.

[0597] The collected sentiment data is sent to a server. The server uses a sentiment analysis algorithm to analyze the data and generate real-time feedback. Based on this feedback, the user can revise and optimize the proposed document.

[0598] For example, if a user expresses dissatisfaction while reviewing a specific section of a proposal document, the server sends a prompt to the AI ​​model saying, "Re-evaluate the relevant part of the proposal document and suggest more appropriate options." In this way, more effective proposals are created.

[0599] As an example of a prompt, you can send a message like, "The user expressed concern in the pricing section. Please suggest a more convincing pricing strategy," to the generative AI model to obtain appropriate improvements.

[0600] This system allows companies to optimize the entire sales process based on user emotions, enabling them to build a consistent strategy from proposal to order and even follow-up.

[0601] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0602] Step 1:

[0603] The server collects market and competitor data. It takes user-specified keywords as input and uses data scraping tools to retrieve information from publicly available databases and social media on the internet. This allows it to output up-to-date datasets on target markets and competing organizations. Specifically, the server periodically calls APIs to update the database.

[0604] Step 2:

[0605] The server analyzes the collected data. Using the dataset as input, it analyzes market trends and competitive landscapes using machine learning algorithms in Python or R. This results in the output of segmented market information and an understanding of competitive activities. Specifically, the server applies random forests and neural networks to extract data patterns.

[0606] Step 3:

[0607] The server generates proposal document templates based on past success stories. Using past case data as input, it employs a generation AI model to output new document templates. Specifically, during this process, the server selects a document structure with a high probability of success.

[0608] Step 4:

[0609] The device collects user emotion data. It uses emotion recognition software, taking the user's facial expressions and voice as input, to output real-time emotional state data. Specifically, the device continuously monitors the user's reactions through its built-in camera and microphone.

[0610] Step 5:

[0611] The server analyzes emotional data and generates feedback. It takes emotional state data as input and outputs feedback using an emotional analysis algorithm. Through its specific actions, the server periodically evaluates changes in the user's emotions and suggests necessary improvements.

[0612] Step 6:

[0613] The user revises the proposal document based on the generated feedback. The server receives feedback as input and outputs an optimized proposal document with the revisions made. Specifically, the user adjusts sections of the proposal document according to the feedback.

[0614] Step 7:

[0615] During project progress, the server monitors changes in the situation and issues warnings as needed. It takes progress data and stress level status as input and outputs warnings at the appropriate time. Specifically, its function is to send timely alerts regarding the user's work status.

[0616] (Application Example 2)

[0617] 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."

[0618] In modern sales activities, personalization tailored to the individual emotions of each customer is essential. However, conventional systems tend to focus on collecting market information and competitor analysis, failing to adequately grasp the real-time emotions of customers and users and optimize proposals based on that understanding. This makes it difficult to improve customer satisfaction and increase sales.

[0619] 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.

[0620] In this invention, the server includes means for collecting market information, means for analyzing the collected market information to understand the activities of competitors, means for learning from past success stories, means for automatically generating proposals, means for monitoring the progress of projects, means for issuing alerts when problems occur, means for acquiring user emotion data, means for analyzing the emotion data to optimize proposal content, and means for analyzing customer facial expressions and tone of voice to support sales proposals. This enables real-time optimization of proposals based on customer emotions.

[0621] "Means of collecting market information" refers to methods and devices for collecting data related to the market.

[0622] "Means of analyzing collected market information to understand the activities of competitors" refers to methods of analyzing collected data to understand the actions and strategies of competitors.

[0623] "Means of learning from past successes" refers to methods and systems for studying and learning from previously successful examples.

[0624] "Methods for automatically generating proposals" refers to a system for automatically creating sales proposals.

[0625] "Means of monitoring project progress" refers to methods and tools for tracking project progress and checking its status.

[0626] "Means of issuing alerts when a problem occurs" refers to methods or devices that issue warnings and draw attention when a problem arises.

[0627] "Means for acquiring user emotional data" refers to methods or devices for collecting information about users' emotions.

[0628] "Methods for analyzing emotional data to optimize proposals" refers to methods for analyzing acquired emotional information and optimizing proposals based on the results.

[0629] "Means of analyzing customer facial expressions and tone of voice to support sales proposals" refers to methods or devices that analyze a customer's facial expressions and tone of voice and use that information to support sales proposals.

[0630] This system is designed to optimize sales proposals based on user emotions by combining multiple methods. The server first collects market information and analyzes that data to understand competitor activities. This analysis utilizes databases and data analysis software. Furthermore, the server learns from past successes using machine learning models and automatically generates proposals based on that learning. This makes it possible to quickly create more effective sales materials.

[0631] Next, the user's device collects input data using its camera and microphone. This data includes the user's facial expressions and tone of voice. This data is analyzed using tools such as OpenCV and the Google Cloud Speech-to-Text API, and the user's emotions are sent to the server in real time. The server analyzes this emotion data and optimizes the suggestions using a generative AI model. The optimized suggestions are then sent back to the user's device.

[0632] As a concrete example, when a sales staff member is interacting with a customer, the system analyzes the customer's facial expressions and changes in voice, generating a prompt such as, "Based on the emotions this customer is showing, please suggest what to propose next." This prompt is then used to inform sales proposals. In this way, each proposal is optimized according to the individual customer's needs and emotions, leading to improved customer satisfaction and sales performance.

[0633] The hardware components include smartphones and smart glasses, while the software requires technologies such as Python, OpenCV, and Google Cloud Speech-to-Text. This system allows users to optimize sales pitches in real time based on emotions, enabling them to respond more appropriately to customers.

[0634] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0635] Step 1:

[0636] The server collects market information. Inputs include publicly available data from the internet, news feeds, and company activity reports. The server uses a crawler to collect this data and stores it in a database. The output is an organized list of market information.

[0637] Step 2:

[0638] The server analyzes the collected market information to understand the activities of competitors. The input is the market information collected in Step 1. Data mining techniques are used to identify competitor strategies and market trends. The output obtained from this process is a competitive activity analysis report.

[0639] Step 3:

[0640] The server learns from past success stories. The input is a database of past success stories within the company. The server applies machine learning algorithms to extract the factors contributing to success. The output is a model for generating new proposals.

[0641] Step 4:

[0642] The server automatically generates proposals. The inputs are proposal models derived from successful case studies and competitive analysis reports. Using the generation AI model, customized proposals are created for each customer. The output is the automatically generated proposal.

[0643] Step 5:

[0644] The device acquires user emotion data. Input consists of the user's facial image and voice data. This data is collected using the device's camera and microphone, and emotions are analyzed in real time. The output is the analyzed emotion data.

[0645] Step 6:

[0646] The server analyzes emotional data to optimize the proposal. The input is the emotional data and proposal obtained from step 5. Using a generative AI model, the proposal is adjusted based on the emotions. The output is an emotionally optimized proposal.

[0647] Step 7:

[0648] The terminal presents the optimized proposal to the user. The input is an optimized proposal sent from the server. The proposal is displayed on the terminal's screen and communicated to the user. The output is obtained as visual information for the user.

[0649] Step 8:

[0650] The user responds to the proposal. The input is an optimization proposal, and the user provides feedback and makes selections regarding it. The terminal further analyzes this response and acquires data to help improve the proposal in the future. The output is the user's feedback data.

[0651] 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.

[0652] 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.

[0653] 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.

[0654] [Fourth Embodiment]

[0655] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0656] 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.

[0657] 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).

[0658] 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.

[0659] 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.

[0660] 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).

[0661] 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.

[0662] 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.

[0663] 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.

[0664] 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.

[0665] 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.

[0666] 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.

[0667] 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".

[0668] One embodiment of the present invention is a system that autonomously supports sales proposal activities. This system operates primarily with a server, a terminal, and a user.

[0669] The server first automatically collects market information from the internet and internal databases. During this process, it utilizes text mining technology to extract data on industry trends, target company needs, and the latest developments of competitors. The collected data is then analyzed by a data analysis module built within the server. The analysis results provide the foundational information for formulating optimal proposals for target companies.

[0670] The server then runs an algorithm to learn from a database of past proposal activities and success stories. This database contains detailed information about past projects. The server uses machine learning techniques to identify common factors in successful proposals and forms a template for new proposals.

[0671] During the proposal generation phase, the server automatically creates a document based on the information it has collected, analyzed, and learned. This document, as a proposal, includes information on competitors and content aligned with the target company's needs. The proposal is provided to the user via their terminal. The user can review the generated proposal and make specific customizations or modifications as needed.

[0672] Throughout the project, the server monitors the schedule and task progress, collecting updates in real time. If any problems arise during project execution, the server immediately sends an alert to the user's terminal and proposes solutions based on past cases. This implementation allows companies to streamline their sales proposal activities and implement rapid and effective sales strategies.

[0673] The above describes a specific method for implementing the present invention. This system enables the entire sales process to proceed seamlessly, providing consistent support from proposal to order placement and follow-up.

[0674] The following describes the processing flow.

[0675] Step 1:

[0676] The server collects market information. Using web scraping techniques and API connections, it retrieves the latest information from industry reports and news sites and stores it in a database.

[0677] Step 2:

[0678] The server analyzes collected market information. Using natural language processing, it extracts competitor trends and target company needs from text data and generates reports.

[0679] Step 3:

[0680] The server learns from past proposal data. Successful proposals and project examples are fed into a machine learning algorithm to extract success factors and form templates for new proposals.

[0681] Step 4:

[0682] The server automatically generates proposals. Using analysis results and training data, it creates and saves customized proposals tailored to the target company's needs.

[0683] Step 5:

[0684] Users review proposals through their devices. They can provide feedback on automatically generated proposals and edit or add information as needed.

[0685] Step 6:

[0686] The server collects user feedback after the proposal is submitted. It analyzes the client's responses and uses them to improve the proposal if revisions are needed.

[0687] Step 7:

[0688] The server monitors the project's progress. It checks the schedule and task progress in real time and manages the project's progress.

[0689] Step 8:

[0690] The server will respond when problems occur. If a problem arises during project progress, an alert will be quickly delivered to the user's terminal, and specific suggestions for resolution will be provided.

[0691] (Example 1)

[0692] 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".

[0693] Traditional sales proposal activities relied heavily on manual processes for gathering market information, analyzing competitors, and learning from success stories, requiring significant time and effort. Furthermore, identifying and resolving issues requiring immediate attention during project execution proved difficult. This limited the effectiveness of sales strategies and hindered efficient work processes.

[0694] 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.

[0695] In this invention, the server includes means for collecting information from a database, means for analyzing the collected information to recognize competitor activities, and means for learning from past cases to identify contributing factors. This automates information gathering and analysis in sales activities, enabling efficient proposal creation and real-time project management.

[0696] A "database" is a collection of data that is systematically structured for the purpose of collecting, managing, and retrieving information.

[0697] "Analyzing information" is the process of processing collected data to derive useful insights and conclusions.

[0698] "Recognizing competitor activities" is the process of understanding, comparing, and evaluating the actions and plans of other business entities.

[0699] "Learning from past examples" means analyzing successful past operations and proposals and extracting useful patterns and factors from them.

[0700] A "generative model" is an algorithm or technique for generating new information based on a large amount of data.

[0701] "Generating a document" refers to the process of automatically creating documents or proposals based on pre-defined rules and algorithms.

[0702] "Monitoring the situation" means continuously checking the progress of a project or task and taking action as needed.

[0703] "Issuing a warning" refers to an alert function that immediately notifies users when a problem occurs and prompts them to take appropriate action.

[0704] "Display on a device" means providing information visually through a user interface and creating an environment where users can view and edit that information.

[0705] "Generating a framework" refers to the process of creating templates for proposals and documents, which serve as a foundation for creating new documents.

[0706] "Analyzing responses to a document" refers to the act of collecting and analyzing feedback on a created document to measure areas for improvement and its effectiveness.

[0707] This invention is a system that autonomously supports sales proposal activities, specifically involving a server, terminals, and users. The system utilizes Python-based web scraping and text mining techniques to collect information from databases and the web. Libraries such as BeautifulSoup and Scrapy are useful for this purpose. The server analyzes the collected information using Pandas and NumPy to understand industry trends and competitor activities.

[0708] Furthermore, the server uses Scikit-learn to learn from past successes. This identifies common patterns in successful proposals and forms a framework for new proposals. Generative AI models using the OpenAI API are utilized to generate these proposals. Specifically, advanced language generation is achieved using AI models from the GPT series.

[0709] The proposal is created by the server and then visually displayed to the user via their terminal. The user reviews the proposal on their terminal and edits the content as needed using Google Docs or Word. Throughout the project, the server monitors progress in real time and immediately sends notifications to the terminal if any problems arise. In this process, it integrates with project management tools to support rapid response.

[0710] As an example, when a user creates a proposal for a new product, this system allows them to quickly obtain a proposal that reflects market trends. For example, a prompt sentence to be entered into the generating AI model might be, "Create a proposal for a new cloud service product and include a sentence that emphasizes differentiation from competitors."

[0711] This invention enables the efficient and consistent collection, analysis, proposal writing, and project management of information related to sales activities, which is expected to lead to smoother sales operations for companies.

[0712] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0713] Step 1:

[0714] The server collects market information from the internet and internal databases. The input specifies the URL of the information source and the required data type. Specifically, it uses a web crawler to retrieve the information and organizes it using libraries such as BeautifulSoup and Scrapy. The output is market information formatted as text and numerical data.

[0715] Step 2:

[0716] The server processes the collected information using a data analysis module. The input is market information obtained in step 1, and the data is organized and aggregated using Pandas and NumPy. Then, Matplotlib is used to visualize the data and derive the needs of target companies and industry trends. The output is the analyzed data and trend graphs.

[0717] Step 3:

[0718] The server learns from a database of past success stories and generates proposal templates. The input is data from past proposals and success stories. A machine learning algorithm using Scikit-learn identifies common patterns in successful proposals. The output is a new proposal template.

[0719] Step 4:

[0720] The server creates a proposal based on the generated template. The inputs are the analysis data and template obtained in steps 2 and 3. The generating AI model is used to construct the document using this data. The output is a proposal tailored to the target company's needs.

[0721] Step 5:

[0722] The terminal displays the proposal sent from the server to the user. The input is the proposal data from the server. The user reviews this proposal in Google Docs or Word and edits it as needed. The output is the final version of the proposal customized by the user.

[0723] Step 6:

[0724] The server monitors project progress and issues alerts when problems occur. Inputs include the project schedule and task progress information for ongoing projects. It integrates with project management tools and displays warnings on the user's terminal if an anomaly is detected. Outputs are suggestions for immediate action to address the problem.

[0725] (Application Example 1)

[0726] 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".

[0727] In modern sales activities, while rapid and effective proposals are required, the market is becoming increasingly complex and customer needs are diversifying. Therefore, there is a need for a system that can efficiently and consistently execute everything from information gathering and analysis to proposal creation and project management. Furthermore, a lack of support tools to help sales representatives maintain up-to-date information and smooth project progress is also a challenge.

[0728] 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.

[0729] In this invention, the server includes means for collecting market data, means for analyzing the collected market data to identify the activities of competing organizations, means for learning from past success stories, and means for providing information on mobile terminals for sales activities. This enables sales representatives to quickly generate proposal documents, formulate effective sales strategies based on the latest information, monitor project progress in real time, and immediately take action to resolve problems.

[0730] "Means of collecting market data" refers to the function of obtaining information about the market environment from the internet or internal databases. This information is used as background data necessary for sales activities.

[0731] "Means of analyzing collected market data to identify the activities of competing organizations" refers to the function of analyzing acquired market data to clarify the activities and market positions of other competing organizations.

[0732] "Methods for learning from past success stories" refer to the function of studying the results and proposals of previous sales activities and extracting the factors for success. This allows for improvement in the quality of new proposals.

[0733] "Methods for automatically generating proposal documents" refer to a function that automatically creates high-quality sales proposals based on analyzed and learned information. This will improve the efficiency of proposal creation.

[0734] "Means of providing information on mobile devices for sales activities" refers to a function that provides necessary information to the devices carried by sales representatives and allows them to view the latest data in real time.

[0735] "Means for monitoring project progress" refers to functions that allow you to understand the status of sales projects and track their progress. This is useful for schedule management and checking task progress.

[0736] "A means of issuing an alert when a problem occurs" refers to a function that allows for the rapid notification of the person in charge when a problem arises during the progress of a project. This enables rapid problem resolution.

[0737] To implement this invention, it is first necessary to prepare an infrastructure for the server to collect and analyze market data. This infrastructure will utilize a database equipped with text mining technology and machine learning algorithms. Specifically, the Python language will be used to scrape data with BeautifulSoup, organize it with Pandas, and analyze it with scikit-learn. This data will include the trends of competing organizations and past success stories, making it fundamental information for sales proposals.

[0738] Next, the server utilizes a generative AI model to automatically generate proposal documents based on the collected and analyzed data. These documents are sent in real time to the mobile devices used by sales representatives. Users can view, edit, and utilize the generated proposal documents on a dashboard developed using React. Furthermore, the generative AI model can be used to provide prompts such as the following:

[0739] As a specific example, a sales representative can use the following prompt before visiting a customer.

[0740] "Please create a proposal for the target company. Their main need is for the latest payment technology. Please include information on the activities of their competitors."

[0741] Furthermore, the server monitors project progress, issues alerts when problems arise, and generates and provides solutions based on past cases to the user. This optimizes the sales process in real time, enabling rapid response. Implementing this system streamlines the entire sales process, providing consistent support from proposal to order placement and follow-up.

[0742] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0743] Step 1:

[0744] The server collects market data from the internet and internal databases. Inputs are URLs and query information obtained through various APIs and scraping techniques. The data is extracted and structured using BeautifulSoup. The output is a collection of market data in text format, which is used in the next analysis step.

[0745] Step 2:

[0746] The server analyzes the collected market data using text mining techniques. The input is the market data set obtained in Step 1. This data is organized using Pandas, and then analyzed using scikit-learn to identify industry trends and the activities of competing organizations. The output is trend data and competitive activity information as a result of the analysis.

[0747] Step 3:

[0748] The server learns from a database of past success stories. The input consists of past proposals and project success stories. Using machine learning algorithms, it extracts success factors from this data and learns patterns. The output is a model of success patterns that helps generate new proposals.

[0749] Step 4:

[0750] The server automatically generates proposal documents using a generative AI model. The input consists of the analysis results from Step 2 and the success pattern model from Step 3. Using document generation technology, it creates proposals optimized for sales. The output is the proposal document provided to the sales representative.

[0751] Step 5:

[0752] The terminal receives proposal documents sent from the server and displays them for the sales representative to review and edit. The input is the proposal document sent from the server. A React-based interface is used, allowing the user to edit and save the proposal document. The output is the edited proposal document.

[0753] Step 6:

[0754] The server monitors project progress and collects progress data. Input is progress information obtained from project management tools (e.g., Jira API). Progress is monitored in real time, and important changes are notified. Output is a project progress report.

[0755] Step 7:

[0756] The server issues an alert and provides a solution when a problem occurs. The input is the problem information detected in step 6. It selects a solution based on a database of past cases and provides it to the user along with the alert. The output is an alert for the problem and guidance on the solution.

[0757] 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.

[0758] One possible embodiment of the present invention is a system that recognizes user emotions and more effectively supports sales proposal activities. In addition to conventional functions such as market information gathering, competitor analysis, and automatic proposal generation, this system integrates an emotion engine to enable more personalized proposals.

[0759] The server first performs basic functions such as market information and competitive analysis. It analyzes the collected data to understand the needs of target companies and the activities of competitors. Subsequently, it uses machine learning to analyze a database of past success stories and generates new proposal templates.

[0760] The role of the emotion engine is to acquire user emotion data through the device's camera or voice input as the user reviews or revises the proposal. This data is sent to the server and analyzed in real time. For example, if a user shows emotions of stress or dissatisfaction while viewing a particular part of the proposal, the server will re-evaluate that part and suggest revising the proposal.

[0761] User emotion-based feedback is used at every phase of the proposal process. For example, before submitting a proposal, the content is optimized to prioritize the structure and expression that elicited the most favorable responses from users. After the proposal is submitted, the emotion engine is also applied to client feedback, allowing for an emotional analysis of areas for improvement in future proposals.

[0762] During project execution, the server monitors user emotional data and issues alerts if stress levels rise. For example, as a project deadline approaches, the server suggests appropriate breaks to the user and provides support to maintain work efficiency.

[0763] This allows for flexible adjustment of proposals and project management in response to user emotions, enabling more effective and satisfying sales proposal activities. The above describes the specific implementation method of the present invention. This system allows companies to optimize the entire sales process based on the emotional responses of consumers and clients, and to improve consistency from proposal to order placement and follow-up.

[0764] The following describes the processing flow.

[0765] Step 1:

[0766] The server collects market information via the internet and internal databases. This includes the latest industry trends, competitor activities, and the business needs of target companies.

[0767] Step 2:

[0768] The server analyzes the market information it collects. Using natural language processing, it extracts key insights from text data and generates competitive analysis reports.

[0769] Step 3:

[0770] The server learns from past success stories using machine learning. It extracts success factors from past proposal records in the database and creates a new proposal template.

[0771] Step 4:

[0772] The server automatically generates proposals. Based on the acquired analysis results and success story templates, it creates proposals optimized for the target company.

[0773] Step 5:

[0774] The user reviews the proposal generated through their device. While viewing the proposal, the device uses its built-in camera and microphone to collect user emotion data.

[0775] Step 6:

[0776] The server receives user sentiment data and analyzes it in real time. It identifies areas where the user has expressed stress or dissatisfaction and generates advice for improving the proposal.

[0777] Step 7:

[0778] Users revise the proposal based on their emotional feedback. By implementing specific improvements, the proposal's quality is enhanced.

[0779] Step 8:

[0780] After submitting the proposal to the client, feedback is received from the client based on user sentiment analysis. The server analyzes this data and extracts areas for improvement for the next proposal.

[0781] Step 9:

[0782] During the project, the server monitors the user's emotional state. If negative emotions such as stress increase, it sends the user suggestions for rest or coping strategies.

[0783] Step 10:

[0784] The server centrally manages all acquired data and uses it to build strategies for future sales activities. This data will be utilized in future sales efforts.

[0785] (Example 2)

[0786] 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".

[0787] In today's market, there is a demand for more effective and personalized sales proposals. However, traditional proposal methods fail to adequately improve client satisfaction because proposals are created without considering the user's emotional state. Furthermore, it is difficult to manage stress during project progress and to grasp the activities of competitors in real time.

[0788] 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.

[0789] In this invention, the server includes means for collecting market information, means for analyzing the collected market information to understand the activities of competing organizations, and means for collecting sentiment data. This makes it possible to optimize proposal documents based on the user's sentiment and to manage stress during project progress.

[0790] "Market information" refers to data about the market for a product or service, including customer trends and the actions of competitors.

[0791] "Means of collection" refers to the methods and techniques used to gather necessary data and information, usually involving the use of digital tools and systems.

[0792] "Means of analysis" refer to the techniques and methods used to process collected data and derive meaningful insights and conclusions.

[0793] "Competing organizations" refer to other companies or organizations that offer similar products or services in the same market or industry.

[0794] "Past success stories" are records of successful activities and projects carried out to date, which can serve as a reference for new strategies and plans.

[0795] A "proposal document" is a document that describes the sales pitch or proposal for a specific product or service, and forms part of the proposal activities conducted with customers.

[0796] "Methods of automatic generation" refer to technologies that use specific algorithms or programs to automatically create documents and data.

[0797] "Emotional data" refers to data that indicates an individual's emotional state, and is often obtained from facial expressions and tone of voice.

[0798] "Means of analysis" refers to the techniques and methods used to analyze input data and understand its structure and meaning.

[0799] "Means of monitoring" refers to methods and techniques for carefully observing a specific object and detecting anomalies or changes.

[0800] "Warning mechanisms" refer to methods and techniques for providing necessary attention or notice based on specific conditions or circumstances.

[0801] A "template" refers to a basic format or template that can be used for a specific purpose.

[0802] This invention is a system that recognizes user emotions and effectively supports sales proposal activities. By acquiring user emotion data and optimizing proposals based on that data, it is possible to improve client satisfaction.

[0803] The server first collects market information. Specifically, it uses data scraping tools to gather necessary data from publicly available databases and social media on the internet. It also interacts with databases and APIs to periodically obtain the latest information.

[0804] The server analyzes data collected through the analysis engine. Using Python and R languages, it applies machine learning algorithms to understand the activities of competing organizations and market trends, and generates proposal document templates based on past success stories.

[0805] The device uses its built-in camera and microphone to monitor the user's emotional data in real time. Emotion recognition software analyzes the user's facial expressions and tone of voice to detect their emotional state. This allows the system to identify the user's stress levels and satisfaction while reviewing proposed documents.

[0806] The collected sentiment data is sent to a server. The server uses a sentiment analysis algorithm to analyze the data and generate real-time feedback. Based on this feedback, the user can revise and optimize the proposed document.

[0807] For example, if a user expresses dissatisfaction while reviewing a specific section of a proposal document, the server sends a prompt to the AI ​​model saying, "Re-evaluate the relevant part of the proposal document and suggest more appropriate options." In this way, more effective proposals are created.

[0808] As an example of a prompt, you can send a message like, "The user expressed concern in the pricing section. Please suggest a more convincing pricing strategy," to the generative AI model to obtain appropriate improvements.

[0809] This system allows companies to optimize the entire sales process based on user emotions, enabling them to build a consistent strategy from proposal to order and even follow-up.

[0810] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0811] Step 1:

[0812] The server collects market and competitor data. It takes user-specified keywords as input and uses data scraping tools to retrieve information from publicly available databases and social media on the internet. This allows it to output up-to-date datasets on target markets and competing organizations. Specifically, the server periodically calls APIs to update the database.

[0813] Step 2:

[0814] The server analyzes the collected data. Using the dataset as input, it analyzes market trends and competitive landscapes using machine learning algorithms in Python or R. This results in the output of segmented market information and an understanding of competitive activities. Specifically, the server applies random forests and neural networks to extract data patterns.

[0815] Step 3:

[0816] The server generates proposal document templates based on past success stories. Using past case data as input, it employs a generation AI model to output new document templates. Specifically, during this process, the server selects a document structure with a high probability of success.

[0817] Step 4:

[0818] The device collects user emotion data. It uses emotion recognition software, taking the user's facial expressions and voice as input, to output real-time emotional state data. Specifically, the device continuously monitors the user's reactions through its built-in camera and microphone.

[0819] Step 5:

[0820] The server analyzes emotional data and generates feedback. It takes emotional state data as input and outputs feedback using an emotional analysis algorithm. Through its specific actions, the server periodically evaluates changes in the user's emotions and suggests necessary improvements.

[0821] Step 6:

[0822] The user revises the proposal document based on the generated feedback. The server receives feedback as input and outputs an optimized proposal document with the revisions made. Specifically, the user adjusts sections of the proposal document according to the feedback.

[0823] Step 7:

[0824] During project progress, the server monitors changes in the situation and issues warnings as needed. It takes progress data and stress level status as input and outputs warnings at the appropriate time. Specifically, its function is to send timely alerts regarding the user's work status.

[0825] (Application Example 2)

[0826] 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".

[0827] In modern sales activities, personalization tailored to the individual emotions of each customer is essential. However, conventional systems tend to focus on collecting market information and competitor analysis, failing to adequately grasp the real-time emotions of customers and users and optimize proposals based on that understanding. This makes it difficult to improve customer satisfaction and increase sales.

[0828] 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.

[0829] In this invention, the server includes means for collecting market information, means for analyzing the collected market information to understand the activities of competitors, means for learning from past success stories, means for automatically generating proposals, means for monitoring the progress of projects, means for issuing alerts when problems occur, means for acquiring user emotion data, means for analyzing the emotion data to optimize proposal content, and means for analyzing customer facial expressions and tone of voice to support sales proposals. This enables real-time optimization of proposals based on customer emotions.

[0830] "Means of collecting market information" refers to methods and devices for collecting data related to the market.

[0831] "Means of analyzing collected market information to understand the activities of competitors" refers to methods of analyzing collected data to understand the actions and strategies of competitors.

[0832] "Means of learning from past successes" refers to methods and systems for studying and learning from previously successful examples.

[0833] "Methods for automatically generating proposals" refers to a system for automatically creating sales proposals.

[0834] "Means of monitoring project progress" refers to methods and tools for tracking project progress and checking its status.

[0835] "Means of issuing alerts when a problem occurs" refers to methods or devices that issue warnings and draw attention when a problem arises.

[0836] "Means for acquiring user emotional data" refers to methods or devices for collecting information about users' emotions.

[0837] "Methods for analyzing emotional data to optimize proposals" refers to methods for analyzing acquired emotional information and optimizing proposals based on the results.

[0838] "Means of analyzing customer facial expressions and tone of voice to support sales proposals" refers to methods or devices that analyze a customer's facial expressions and tone of voice and use that information to support sales proposals.

[0839] This system is designed to optimize sales proposals based on user emotions by combining multiple methods. The server first collects market information and analyzes that data to understand competitor activities. This analysis utilizes databases and data analysis software. Furthermore, the server learns from past successes using machine learning models and automatically generates proposals based on that learning. This makes it possible to quickly create more effective sales materials.

[0840] Next, the user's device collects input data using its camera and microphone. This data includes the user's facial expressions and tone of voice. This data is analyzed using tools such as OpenCV and the Google Cloud Speech-to-Text API, and the user's emotions are sent to the server in real time. The server analyzes this emotion data and optimizes the suggestions using a generative AI model. The optimized suggestions are then sent back to the user's device.

[0841] As a concrete example, when a sales staff member is interacting with a customer, the system analyzes the customer's facial expressions and changes in voice, generating a prompt such as, "Based on the emotions this customer is showing, please suggest what to propose next." This prompt is then used to inform sales proposals. In this way, each proposal is optimized according to the individual customer's needs and emotions, leading to improved customer satisfaction and sales performance.

[0842] The hardware components include smartphones and smart glasses, while the software requires technologies such as Python, OpenCV, and Google Cloud Speech-to-Text. This system allows users to optimize sales pitches in real time based on emotions, enabling them to respond more appropriately to customers.

[0843] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0844] Step 1:

[0845] The server collects market information. Inputs include publicly available data from the internet, news feeds, and company activity reports. The server uses a crawler to collect this data and stores it in a database. The output is an organized list of market information.

[0846] Step 2:

[0847] The server analyzes the collected market information to understand the activities of competitors. The input is the market information collected in Step 1. Data mining techniques are used to identify competitor strategies and market trends. The output obtained from this process is a competitive activity analysis report.

[0848] Step 3:

[0849] The server learns from past success stories. The input is a database of past success stories within the company. The server applies machine learning algorithms to extract the factors contributing to success. The output is a model for generating new proposals.

[0850] Step 4:

[0851] The server automatically generates proposals. The inputs are proposal models derived from successful case studies and competitive analysis reports. Using the generation AI model, customized proposals are created for each customer. The output is the automatically generated proposal.

[0852] Step 5:

[0853] The device acquires user emotion data. Input consists of the user's facial image and voice data. This data is collected using the device's camera and microphone, and emotions are analyzed in real time. The output is the analyzed emotion data.

[0854] Step 6:

[0855] The server analyzes emotional data to optimize the proposal. The input is the emotional data and proposal obtained from step 5. Using a generative AI model, the proposal is adjusted based on the emotions. The output is an emotionally optimized proposal.

[0856] Step 7:

[0857] The terminal presents the optimized proposal to the user. The input is an optimized proposal sent from the server. The proposal is displayed on the terminal's screen and communicated to the user. The output is obtained as visual information for the user.

[0858] Step 8:

[0859] The user responds to the proposal. The input is an optimization proposal, and the user provides feedback and makes selections regarding it. The terminal further analyzes this response and acquires data to help improve the proposal in the future. The output is the user's feedback data.

[0860] 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.

[0861] 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.

[0862] 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.

[0863] 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.

[0864] 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.

[0865] 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.

[0866] 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.

[0867] 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.

[0868] 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."

[0869] 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.

[0870] 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.

[0871] 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.

[0872] 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.

[0873] 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.

[0874] 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.

[0875] 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.

[0876] 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.

[0877] 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.

[0878] 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.

[0879] 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.

[0880] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0881] The following is further disclosed regarding the embodiments described above.

[0882] (Claim 1)

[0883] Means of collecting market information,

[0884] A means of understanding the activities of competitors by analyzing the collected market information,

[0885] A means of learning from past success stories,

[0886] A method for automatically generating proposals,

[0887] Means for monitoring the progress of the project,

[0888] A means of issuing an alert when a problem occurs,

[0889] A system that includes this.

[0890] (Claim 2)

[0891] The system according to claim 1, further comprising means for analyzing successful cases and generating templates for new proposals.

[0892] (Claim 3)

[0893] The system according to claim 1, further comprising means for analyzing feedback on a proposal and extracting areas for improvement.

[0894] "Example 1"

[0895] (Claim 1)

[0896] Means of collecting information from a database,

[0897] A means of analyzing collected information to recognize the activities of competitors,

[0898] A means of identifying factors by learning from past cases,

[0899] A means of generating documents using a generative model,

[0900] Means for monitoring the status of ongoing work,

[0901] A means of issuing a warning when a problem occurs,

[0902] A terminal display method for incorporating customer requests into a document,

[0903] A system that includes this.

[0904] (Claim 2)

[0905] The system according to claim 1, further comprising means for analyzing common patterns from successful cases and generating a framework for new documents.

[0906] (Claim 3)

[0907] The system according to claim 1, further comprising means for analyzing responses to a document and identifying areas for improvement.

[0908] "Application Example 1"

[0909] (Claim 1)

[0910] Means of collecting market data,

[0911] A means of analyzing collected market data to identify the trends of competing organizations,

[0912] A means of learning from past success stories,

[0913] A means of automatically generating proposal documents,

[0914] Means for monitoring the progress of the project,

[0915] A means of issuing an alarm when a problem occurs,

[0916] Means of providing information on mobile devices for sales activities,

[0917] A system that includes this.

[0918] (Claim 2)

[0919] The system according to claim 1, further comprising means for analyzing successful cases and generating templates for new proposals.

[0920] (Claim 3)

[0921] The system according to claim 1, further comprising means for analyzing evaluations of the proposal document and extracting areas for improvement.

[0922] "Example 2 of combining an emotion engine"

[0923] (Claim 1)

[0924] Means of collecting market information,

[0925] A means of understanding the activities of competing organizations by analyzing collected market information,

[0926] A means of learning from past success stories,

[0927] A means of automatically generating proposal documents,

[0928] Means of collecting emotional data,

[0929] A means of analyzing collected emotional data and providing feedback,

[0930] Means for monitoring the progress of the project,

[0931] A means of issuing a warning when a problem occurs,

[0932] A system that includes this.

[0933] (Claim 2)

[0934] The system according to claim 1, further comprising means for analyzing successful cases and generating templates for new proposals.

[0935] (Claim 3)

[0936] The system according to claim 1, further comprising means for analyzing feedback on a proposal document and extracting areas for improvement.

[0937] "Application example 2 of combining emotional engines"

[0938] (Claim 1)

[0939] Means of collecting market information,

[0940] A means of understanding the activities of competitors by analyzing the collected market information,

[0941] A means of learning from past success stories,

[0942] A method for automatically generating proposals,

[0943] Means for monitoring the progress of the project,

[0944] A means of issuing an alert when a problem occurs,

[0945] Means for obtaining user sentiment data,

[0946] A method for analyzing emotional data to optimize the proposed content,

[0947] A means of supporting sales proposals by analyzing the customer's facial expressions and tone of voice,

[0948] A system that includes this.

[0949] (Claim 2)

[0950] The system according to claim 1, further comprising means for analyzing successful cases and generating templates for new proposals.

[0951] (Claim 3)

[0952] The system according to claim 1, further comprising means for analyzing feedback on a proposal and extracting areas for improvement. [Explanation of Symbols]

[0953] 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 collecting market information, A means of understanding the activities of competitors by analyzing the collected market information, A means of learning from past success stories, A method for automatically generating proposals, Means for monitoring the progress of the project, A means of issuing an alert when a problem occurs, A system that includes this.

2. The system according to claim 1, further comprising means for analyzing successful cases and generating templates for new proposals.

3. The system according to claim 1, further comprising means for analyzing feedback on a proposal and extracting areas for improvement.

Images