System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting case-of-failure data and case-of-success data; means for storing the collected case-of-failure data and case-of-success data in a database; means for analyzing the stored data to identify patterns and trends; means for generating rules of success and action plans based on the identified patterns and trends; means for displaying the generated rules of success and action plans on a user's terminal; and means for collecting feedback from the user to improve analysis results and algorithms.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] While it is important to find a path to success by learning from failure, it is difficult to effectively analyze failure cases and derive the principles of success. It is especially difficult to allocate sufficient time and resources to learning from failure in busy business and highly competitive market environments. Conventional technologies lack effective methods for solving these issues, and there is a need for objective and efficient methods for deriving the principles of success. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for collecting data on failure cases and success cases, a means for storing the collected data on failure cases and success cases in a database, a means for analyzing the stored data and identifying patterns and trends, a means for generating rules for success and action plans based on the identified patterns and trends, a means for displaying the generated rules for success and action plans on a user's device, and a means for collecting feedback from users and improving the analysis results and algorithms. This system makes it possible to efficiently collect and analyze data on failure cases and success cases, derive rules for success, and provide specific action plans.

[0006] "Failure case data" refers to information on cases in which activities carried out under specific conditions did not produce the desired results.

[0007] "Success story data" refers to information on cases in which activities carried out under specific conditions achieved desired results.

[0008] "Database" means a system for organizing data in digital form and efficiently managing, retrieving, updating and accessing it.

[0009] "Data preprocessing" refers to the process of converting raw data into an analyzable format, including tasks such as removing duplicate data, imputing incomplete data, and normalizing data.

[0010] A "pattern" refers to a particular trend or rule that is seen repeatedly in data.

[0011] "Trend" refers to the general direction or trend observed in the data.

[0012] "Laws of success" refer to basic principles and procedures for achieving success, derived from successful cases.

[0013] An "action plan" refers to a specific plan of action to achieve success.

[0014] "User terminal" refers to the electronic device (e.g., computer, smartphone, tablet) that a user uses to interact with the system through an interface.

[0015] "Feedback" refers to the results and opinions that users provide to the system.

[0016] An "algorithm" refers to a set of computational procedures or rules for solving a particular problem. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0021] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0022] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0038] The system of the present invention is composed of three main elements: a server, a terminal, and a user. The system collects data on failure cases and success cases, stores it in a database, analyzes it, generates rules for success and specific action plans, and provides them to users. It also collects feedback from users to continuously improve the accuracy of the system.

[0039] Data collection

[0040] The server collects data on success and failure cases from multiple sources, such as the Internet and internal databases. For example, it obtains success and failure cases in project management from public databases on the web, news articles, and specialized papers. The collected data is temporarily stored in the database in raw data form.

[0041] Data preprocessing and storage

[0042] The server preprocesses the collected data, which includes removing duplicates, completing incomplete data, and normalizing the data. The preprocessed data is then stored in a database again, ready for analysis.

[0043] Data analysis

[0044] The server then analyzes the preprocessed data using natural language processing (NLP) techniques and machine learning algorithms. The goal of this analysis is to identify patterns and trends in the data and uncover factors that lead to failures and successes. For example, in project management, it may be discovered that effective communication is the key to success.

[0045] Formulating success and action plans

[0046] The server derives the principles of success based on the results of the data analysis. Based on these principles, it generates a specific action plan. For example, it may formulate an action plan such as "hold regular meetings with stakeholders in the early stages of project planning."

[0047] Provision to users

[0048] The user accesses the system using a terminal. The server sends the generated success formula and action plan to the terminal and displays it to the user. The user can then proceed with their work according to the provided action plan.

[0049] Feedback and System Improvement

[0050] After the user implements the action plan, they provide the results as feedback to the system. For example, they input information such as, "As a result of regular meetings, the project progressed smoothly." The server then re-analyzes the data based on the collected feedback to improve the accuracy of the algorithm and action plan.

[0051] Specific examples

[0052] For example, if a company is trying to bring a new product to market, this system could work as follows:

[0053] Data collection

[0054] The server collects success stories and failure stories of new product launches from the Internet and past data within companies.

[0055] Data preprocessing and storage

[0056] The collected data is normalized through a data cleansing process and stored in a database.

[0057] Data analysis

[0058] Sarver uses natural language processing technology to analyze the data and identify factors that contribute to the success of new product launches. For example, he concludes that it is important to "clarify the target market and implement a well-thought-out marketing strategy."

[0059] Formulating success and action plans

[0060] Based on the results, the server generates a specific action plan, such as "conduct market research, clarify target segments, and then implement an advertising campaign."

[0061] Provision to users

[0062] When a user (a marketing person at a company) logs into the system using a terminal, an action plan proposed by the server is displayed.

[0063] Feedback and System Improvement

[0064] The user executes the action plan and provides feedback on the results to the system. Based on this information, the server updates the algorithm and reflects it in the next analysis, providing more accurate success rules and action plans.

[0065] This system gives companies a concrete way to efficiently and effectively learn from their mistakes and lead to success.

[0066] The processing flow will be explained below.

[0067] Step 1:

[0068] The server collects failure and success data from the internet and internal databases, for example, using web scraping or APIs to retrieve relevant data from blog posts, news articles, research papers, etc.

[0069] Step 2:

[0070] The server preprocesses the collected data, including data cleansing, removing duplicate data, completing incomplete data, and normalizing the data. Specifically, it removes noise from text data (e.g., HTML tags and unnecessary special characters) and standardizes the data format.

[0071] Step 3:

[0072] The server stores the preprocessed data in a case database. Each case contains detailed information such as case ID, date and time, background, and results, and this information is saved in the database.

[0073] Step 4:

[0074] The server analyzes the data in the case database using natural language processing (NLP) techniques and machine learning algorithms, specifically by performing text analysis to identify common patterns and trends among cases and by using clustering algorithms to group related cases.

[0075] Step 5:

[0076] Based on the analysis, the server derives success rules, such as identifying the importance of regular stakeholder feedback for successful project management.

[0077] Step 6:

[0078] The server generates a specific action plan based on the success formula, for example, an action plan that includes the instruction "obtain stakeholder feedback twice by the next milestone."

[0079] Step 7:

[0080] When a user accesses the system using a terminal, the server sends the generated success formula and action plan to the terminal and displays it. The user can check the proposed action plan on the terminal dashboard.

[0081] Step 8:

[0082] The user implements the proposed action plan and provides the results as feedback to the server via the terminal. For example, the user might input information such as, "As a result of obtaining feedback from stakeholders, the project progressed smoothly."

[0083] Step 9:

[0084] The server analyzes the feedback data provided by users to improve the accuracy of the algorithms and action plans, and uses the insights from the feedback to conduct the next data analysis and implement continuous system improvements.

[0085] Example 1

[0086] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0087] In today's business environment, it is important to learn from project successes and failures and develop concrete action plans based on them. However, many organizations do not do this efficiently and face challenges due to the lack of effective feedback loops, making it difficult to utilize this information.

[0088] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0089] In this invention, the server includes means for collecting failure case data and success case data, means for storing the collected failure case data and success case data in a database, means for preprocessing the stored data by deleting duplicate data, completing incomplete data, and normalizing the data, means for analyzing the preprocessed data and identifying patterns and trends using natural language processing technology and machine learning algorithms, means for generating a law of success and a specific action plan based on the identified patterns and trends, means for displaying the generated law of success and action plan on a user's terminal, and means for collecting feedback from users and analyzing the feedback to improve the analysis results and algorithms. This makes it possible to efficiently utilize information obtained from failure cases and success cases to formulate specific action plans and increase business success.

[0090] "Failure case data" refers to data on cases where goals were not achieved in past projects or tasks.

[0091] "Success case data" refers to data on cases where goals were achieved in past projects or tasks.

[0092] "Data collection methods" are methods for obtaining data from multiple sources, such as the Internet and internal company databases.

[0093] "Means for storing in a database" refers to means for storing collected data in a database for easy management and access.

[0094] The "preprocessing means" refers to a means for removing duplicate data from the collected data, completing incomplete data, and normalizing the data.

[0095] "Analysis means" refers to the means of applying natural language processing techniques and machine learning algorithms to pre-processed data to identify patterns and trends in the data.

[0096] The "means for generating rules of success" is a means for extracting rules that lead to success based on the patterns and trends identified by the analysis means.

[0097] A "means for generating an action plan" is a means for formulating specific guidelines and steps for action in accordance with the laws of success.

[0098] The "means for displaying on the user's terminal" refers to a means for visually displaying the generated success law and action plan to the user.

[0099] "Means for collecting feedback" refers to the means for incorporating results and opinions from users after the implementation of an action plan into the system.

[0100] "Means for improving the algorithm" refers to means for analyzing collected feedback and improving the accuracy of the analysis results and generation process.

[0101] The system of this invention is composed of three main elements: a server, a terminal, and a user. The system collects data on failure cases and success cases, stores this data in a database, and performs preprocessing and analysis to generate success rules and specific action plans, which are ultimately provided to the user. It also has a mechanism for collecting user feedback and continuously improving the accuracy of the system.

[0102] Data collection

[0103] The server collects failure and success case data from multiple appropriate data sources, such as the Internet and internal databases. Web scraping tools (e.g., BeautifulSoup or Scrapy) are used for this process. For example, project management success and failure cases are obtained from public databases on the Web, news articles, and specialized papers. The collected data is temporarily stored in a database (e.g., MySQL or PostgreSQL).

[0104] Data preprocessing and storage

[0105] The server preprocesses the collected raw data, using the Pandas library and regular expressions (Regex) to remove duplicates, impute incomplete data, and normalize the data into a standard format. Once preprocessed, the data is stored back in the database, ready for analysis.

[0106] Data analysis

[0107] The server analyzes the preprocessed data using natural language processing (NLP) techniques and machine learning algorithms. This analysis uses NLP libraries such as NLTK and Spacy, and machine learning libraries such as Scikit-learn and TensorFlow. The goal of the analysis is to identify patterns and trends in the data and identify factors behind success and failure. For example, a clustering algorithm can be used to classify similar successful and unsuccessful cases.

[0108] Formulating success and action plans

[0109] The server derives the principles of success based on the results of data analysis. Based on these principles, it generates specific action plans. For example, based on the principle that "regular meetings with stakeholders should be held in the early stages of project planning," it formulates a specific course of action that states "schedule weekly meetings and report on progress."

[0110] Provision to users

[0111] A user accesses the system using a terminal. When the user logs in to the system, the generated success formula and action plan are sent from the server to the terminal. The terminal visually displays this to the user, for example, in an easy-to-understand format through a dashboard.

[0112] Feedback and System Improvement

[0113] When users implement their action plans and provide feedback to the system, the server analyzes the feedback data again. The server analyzes the collected feedback and identifies new patterns and trends. Through this process, the server improves the accuracy of the algorithms and action plans.

[0114] Specific examples

[0115] For example, if a company is trying to bring a new product to market, this system would work as follows:

[0116] The server collects success stories and failure stories of new product launches from the Internet and past data within companies.

[0117] The collected data is normalized through a data cleansing process and stored in a database.

[0118] Sarver uses natural language processing technology to analyze the data and identify factors that contribute to the success of new product launches. For example, he concludes that it is important to "clarify the target market and implement a well-thought-out marketing strategy."

[0119] Based on the results, the server generates a specific action plan, such as "conduct market research, clarify target segments, and then implement an advertising campaign."

[0120] When a user (a marketing person at a company) logs into the system using a terminal, an action plan proposed by the server is displayed.

[0121] The user executes the action plan and provides feedback on the results to the system. Based on this information, the server updates the algorithm and reflects it in the next analysis.

[0122] Prompt Sentence Examples

[0123] Below are some example prompts to input to the generative AI model:

[0124] "Analyze a new product launch. Based on data from successful and unsuccessful cases, generate an action plan for making it a success."

[0125] This system allows companies to efficiently and effectively learn from their mistakes and provides a concrete path to success.

[0126] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0127] Step 1: Data collection

[0128] The server collects data on failures and successes from multiple sources, including the Internet and internal databases. Specifically, it uses web scraping tools (e.g., BeautifulSoup, Scrapy) to obtain data from public databases, news articles, and specialized papers. The collected raw data is temporarily stored in a database (e.g., MySQL, PostgreSQL).

[0129] Input: Information on the Internet, information from internal databases

[0130] Output: Raw data stored in a database

[0131] Step 2: Preprocessing the data

[0132] The server performs data cleansing on the collected raw data. Specifically, it uses the Pandas library to remove duplicate data, complete incomplete data, and normalize the data using regular expressions (Regex). Once preprocessed, the data is stored in the database again.

[0133] Input: Raw data stored in a database

[0134] Output: Data that has been cleansed and normalized

[0135] Step 3: Analyze the data

[0136] The server then analyzes the preprocessed data using natural language processing (NLP) techniques and machine learning algorithms. Using NLP libraries like NLTK and Spacy, and machine learning libraries like Scikit-learn and TensorFlow, the server identifies patterns and trends in the data. This analysis clarifies factors behind success and failure.

[0137] Input: Preprocessed data

[0138] Output: Analysis of factors behind success and failure

[0139] Step 4: Create a success formula and action plan

[0140] The server derives success rules based on the results of the data analysis and generates specific action plans. For example, a success rule may be "hold regular meetings with stakeholders in the early stages of project planning," and specific action guidelines (e.g., setting up weekly meetings) are then formulated based on that.

[0141] Input: Analysis results on factors behind success and failure

[0142] Output: Laws of success and concrete action plans

[0143] Step 5: Provide to users

[0144] The user accesses the system using a terminal and views the generated success formula and action plan. The server sends this information to the terminal, which then visually displays it on a dashboard or other device.

[0145] Input: Laws of success and concrete action plans

[0146] Output: Success formula and action plan displayed on the user's device

[0147] Step 6: Gather feedback and improve the system

[0148] Users input the results of their action plans as feedback into the system, which the server collects and analyzes again, identifying new patterns and trends to refine the algorithms and action plans.

[0149] Input: User feedback

[0150] Output: Updated algorithm and improved action plan

[0151] Through these steps, the system effectively utilizes data on both failure and success cases to provide specific improvement measures, thereby enabling users to increase the success rate of their work.

[0152] (Application example 1)

[0153] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0154] When operating autonomous vehicles, it is necessary to adapt to the environment after starting operation and continuously improve optimal driving patterns and operation methods. Collecting and analyzing data during operation, learning from successes and failures, and providing specific driving methods in real time are particularly challenging. Conventional methods do not efficiently generate executable action plans or improve the system through feedback, preventing improvements to the accuracy of autonomous driving.

[0155] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0156] In this invention, the server includes means for collecting failure case data and success case data, means for storing the collected failure case data and success case data in a database, means for analyzing the stored data and identifying patterns and trends, means for generating a success rule and an action plan based on the identified patterns and trends, means for displaying the generated success rule and action plan on a user's terminal, means for collecting user feedback and improving the analysis results and algorithm, means for collecting sensor data from the autonomous vehicle, means for preprocessing and normalizing the collected sensor data, means for analyzing trends in the data using natural language processing technology and machine learning algorithms, means for generating a success rule and specific operating methods for operating the autonomous vehicle based on the analysis results, means for displaying the generated operating methods on an autonomous vehicle operation management terminal, and means for collecting user feedback on operation results and improving the analysis results and algorithm. This makes it possible to continuously improve the operation accuracy of the autonomous vehicle and provide optimal operation patterns and operating methods in real time.

[0157] "Failure case data" is a record of when an autonomous vehicle did not perform as expected under certain circumstances or conditions.

[0158] "Success data" is a record of an autonomous vehicle performing as expected under specific circumstances or conditions.

[0159] A "database" is an information management system that systematically stores collected data and enables efficient searching and analysis.

[0160] "Pattern and trend identification methods" are techniques and methods used to analyze collected data and find common characteristics or recurring behaviors.

[0161] A "law of success" is a theory that specifies the factors and methodologies that will lead to the success of autonomous vehicles under certain conditions.

[0162] An "action plan" is a plan that outlines specific operational operations and countermeasures that should be implemented based on the principles of success.

[0163] "Means for collecting user feedback" refers to an interface or method by which a user can report the results of operating an autonomous vehicle to the system.

[0164] "Sensor data" refers to data about the surrounding environment and vehicle operation acquired by various sensors (e.g., LiDAR, cameras, radar) installed in autonomous vehicles.

[0165] "Data preprocessing" refers to a series of operations (e.g., missing value imputation, normalization, deduplication) performed on collected data to prepare it in an analyzable format.

[0166] "Natural language processing technology" is a technology that allows computers to understand, analyze, and generate natural language used by humans.

[0167] A "machine learning algorithm" is a mathematical model or method for learning patterns from data and using them to make predictions or classifications.

[0168] An "operation management terminal" is a device or system for managing and displaying the operating status, settings, and operation methods of an autonomous vehicle.

[0169] "Operation result feedback" refers to data that an autonomous vehicle provides back to the system regarding the results and situation it obtains during actual operation.

[0170] The system of this invention is designed to enhance the operation management of autonomous vehicles. This system consists of three main elements: a server, a terminal, and a user.

[0171] Data collection

[0172] The server collects real-time sensor data from the autonomous vehicle's LiDAR, camera, and radar sensors, providing detailed information about the vehicle's behavior and the surrounding environment during operation. This data also includes examples of successful and unsuccessful operations, and the system collects and stores this data in a database.

[0173] Data preprocessing and storage

[0174] The collected raw data is temporarily stored in a database. After that, a data preprocessing process is performed to remove duplicate data, complete incomplete data, and normalize the data. This preprocessed data is then stored in a database again, ready for analysis.

[0175] Data analysis

[0176] The server then analyzes the preprocessed data using natural language processing (NLP) and machine learning algorithms, including Python libraries such as pandas, scikit-learn, and joblib, to identify patterns and trends in the data and identify factors behind failures and successes.

[0177] Formulating success and action plans

[0178] Based on the results of the data analysis, the server derives rules of thumb, generating specific driving patterns and maneuvers, such as specific speed limits and emergency evasive actions. These action plans are further refined using generative AI models.

[0179] User Offerings and Feedback

[0180] The server displays the generated success formula and action plan on the management terminal or engineer's terminal. Users can use this information to manage the settings and operation of the autonomous vehicle. The operation results are fed back to the system by the user, and the server re-analyzes them based on this and improves the accuracy of the algorithm.

[0181] Specific examples

[0182] For example, when an autonomous vehicle is operating within a city, the server collects sensor data and analyzes examples of successful and unsuccessful driving. As a result, a specific action plan is generated, such as "setting the speed limit to 25 km / h in urban areas and automatically avoiding bicycle lanes when approaching them." This action plan is displayed on the terminal, and the operation manager applies it to operate the vehicle. The operation results are fed back to the system, and are reflected in future operations.

[0183] Prompt Sentence Examples

[0184] "This system uses sensor data from autonomous vehicles to identify factors that contribute to operational success and failure, and proposes specific action plans. Specifically, it suggests speed limits and how to avoid emergencies. Please explain the specific process for how this data is collected, analyzed, and used to derive the formula for success."

[0185] In this way, the invention continuously improves the driving accuracy of autonomous vehicles and provides optimal driving patterns and operating methods in real time.

[0186] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0187] Step 1:

[0188] The server collects sensor data in real time from sensor devices (LiDAR, camera, radar) installed in the autonomous vehicle. Raw data (vehicle behavior and surrounding environment during operation) is given as input and temporarily stored in a database. The output is a collection of collected raw data.

[0189] Step 2:

[0190] The server preprocesses the collected raw data. It receives the raw data as input, removes duplicates, completes incomplete data, and normalizes it. Specifically, it uses Python libraries (pandas, scikit-learn) for data cleansing and scaling. The output is a preprocessed, clean dataset.

[0191] Step 3:

[0192] The server analyzes the preprocessed data using natural language processing (NLP) and machine learning algorithms. It takes the preprocessed data as input and uses a Random Forest Classifier to identify patterns and trends in the data. The output is a list of success factors and failure factors as a result of the analysis.

[0193] Step 4:

[0194] The server generates a formula for success and a specific action plan based on the analysis results. It receives the analysis results as input and further refines the action plan using a generative AI model. The output is an action plan that includes specific driving patterns and operation methods. For example, specific instructions such as "set the speed limit to 25 km / h in urban areas" are generated.

[0195] Step 5:

[0196] The server sends the generated success rule and action plan to the terminal and displays it to the user. The server receives the action plan as input and displays it on the operation management terminal. The output is a specific action plan that is displayed on the user's terminal.

[0197] Step 6:

[0198] The user operates the autonomous vehicle based on the provided action plan. The action plan displayed on the terminal is received as input and executed. The output is the driving status and environmental data resulting from the execution.

[0199] Step 7:

[0200] The user inputs the results of the operation into the system as feedback. The system receives operational status and environmental data as input and feeds this back to the server. The output is a set of feedback data.

[0201] Step 8:

[0202] The server re-analyzes the collected feedback data to improve the accuracy of the algorithm. It receives the feedback data as input and re-analyzes it to refine the algorithm. The output is an updated algorithm and an improved action plan.

[0203] Through these steps, the operational accuracy and safety of autonomous vehicles will be continuously improved.

[0204] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0205] The system of the present invention is composed of three main elements: a server, a terminal, and a user. It also incorporates an emotion engine that recognizes the user's emotions. The system collects data on both failure and success cases, stores it in a database, analyzes it, generates rules for success and specific action plans, and provides them to the user. It also collects feedback from users to continuously improve the accuracy of the system. An embodiment of the system is described in detail below.

[0206] Data collection

[0207] The server collects failure and success data from the internet and internal databases, for example, using web scraping or APIs to retrieve relevant data from blog posts, news articles, research papers, etc.

[0208] Data preprocessing and storage

[0209] The server preprocesses the collected data. This includes data cleansing, removing duplicate data, completing incomplete data, and normalizing the data. Specifically, it removes noise from the text data (e.g., HTML tags and unnecessary special characters) and standardizes the data format. The preprocessed data is stored in a case database and is ready for analysis.

[0210] Data analysis

[0211] The server then analyzes the preprocessed data using natural language processing (NLP) techniques and machine learning algorithms. The goal of this analysis is to identify patterns and trends in the data and uncover factors that lead to failures and successes. For example, in project management, it may be discovered that effective communication is the key to success.

[0212] Analysis by emotion engine

[0213] The server includes an emotion engine that recognizes emotions based on user feedback. The emotion engine uses a text analysis algorithm to classify emotions from the user's feedback text. For example, if the user's feedback expresses emotions such as "very satisfied" or "anxious," the emotion information is reflected in the analysis.

[0214] Formulating success and action plans

[0215] The server derives the principles of success based on the results of data analysis and sentiment analysis by the emotion engine. Specific action plans are generated based on the principles of success. For example, an action plan could be formulated that includes holding regular meetings with stakeholders in the early stages of project planning.

[0216] Provision to users

[0217] The user accesses the system using a terminal. The server sends the generated success formula and action plan to the terminal and displays it. The user can check the proposed action plan on the terminal dashboard.

[0218] Feedback and System Improvement

[0219] After a user implements an action plan, they provide the results as feedback to the system. For example, they might enter information like, "As a result of obtaining stakeholder feedback, the project progressed more smoothly." The emotion engine simultaneously analyzes the emotions contained in the feedback. The server then re-analyzes the data based on this feedback, improving the accuracy of the algorithm and action plan.

[0220] Specific examples

[0221] For example, if a company is trying to bring a new product to market, this system could work as follows:

[0222] Data collection

[0223] The server collects success stories and failure stories of new product launches from the Internet and past data within companies.

[0224] Data preprocessing and storage

[0225] The collected data is normalized through a data cleansing process and stored in a case database.

[0226] Data analysis

[0227] Sarver uses natural language processing technology to analyze the data and identify factors that contribute to the success of new product launches. For example, he concludes that it is important to "clarify the target market and implement a well-thought-out marketing strategy."

[0228] Analysis by emotion engine

[0229] When receiving user feedback, the emotion engine classifies emotions such as "satisfaction" or "anxiety" and reflects that emotional data in new analysis.

[0230] Formulating success and action plans

[0231] Based on the results and sentiment data, the server generates a specific action plan: "Conduct market research, clarify target segments, and then implement an advertising campaign."

[0232] Provision to users

[0233] When a user (a marketing person at a company) logs into the system using a terminal, an action plan proposed by the server is displayed.

[0234] Feedback and System Improvement

[0235] The user executes the action plan and provides feedback on the results to the system. Based on this information and emotional data, the server updates the algorithm and reflects it in the next analysis, providing a more accurate formula for success and action plan.

[0236] This system allows companies to efficiently and effectively learn from failures and gain concrete methods to lead to success. It also takes into account user emotions, allowing for more accurate action plans to be formulated.

[0237] The processing flow will be explained below.

[0238] Step 1:

[0239] The server collects failure and success data from the internet and internal databases, for example, using web scraping or APIs to retrieve relevant data from blog posts, news articles, research papers, etc.

[0240] Step 2:

[0241] The server preprocesses the collected data, including data cleansing, removing duplicate data, completing incomplete data, and normalizing the data. Specifically, it removes noise from text data (e.g., HTML tags and unnecessary special characters) and standardizes the data format.

[0242] Step 3:

[0243] The server stores the preprocessed data in a case database, with each case containing detailed information such as case ID, date and time, background, and results.

[0244] Step 4:

[0245] The server analyzes the stored data using natural language processing (NLP) techniques and machine learning algorithms, specifically by performing text analysis to identify common patterns and trends among cases and by using clustering algorithms to group related cases.

[0246] Step 5:

[0247] Based on the analysis, the server derives the principles of success, for example, discovering that effective communication is the key to success in project management.

[0248] Step 6:

[0249] The server generates a specific action plan based on the success formula, for example, an action plan that includes the instruction "obtain stakeholder feedback twice by the next milestone."

[0250] Step 7:

[0251] When a user accesses the system using a terminal, the server sends the generated success formula and action plan to the terminal and displays it. The user can check the proposed action plan on the terminal dashboard.

[0252] Step 8:

[0253] The user executes the proposed action plan and provides the results and emotional feedback to the server via the terminal. For example, the user can input information such as "We were able to obtain stakeholder feedback successfully and the project progressed smoothly" and the emotion "I am satisfied."

[0254] Step 9:

[0255] The server analyzes the feedback and emotional data provided by users to improve the accuracy of algorithms and action plans. It uses insights from the feedback to conduct the next data analysis and implement continuous system improvements. By utilizing an emotional engine, the emotional information contained in user feedback is also reflected in the analysis.

[0256] As a concrete example, we will show how this system works in the marketing strategy of a new product.

[0257] Step 1:

[0258] The server collects success stories and failure stories of new product launches from the Internet and past data within companies.

[0259] Step 2:

[0260] The collected data is cleansed and duplicates are removed, and the text data is then formatted.

[0261] Step 3:

[0262] The server stores the pre-processed data in a database, recording detailed information about each case.

[0263] Step 4:

[0264] The server analyzes the cases in the database and identifies factors that contribute to success. For example, it finds that "clear target market definition and development of marketing strategies" are factors for success.

[0265] Step 5:

[0266] Based on the analysis results, we derive the formula for success: "Clearly define your target market and develop an appropriate advertising campaign."

[0267] Step 6:

[0268] The server generates a specific action plan based on the formula for success, such as "implementing an advertising campaign divided into three steps."

[0269] Step 7:

[0270] When a user (marketer) logs in to a terminal, the server transmits the generated action plan and displays it on the terminal.

[0271] Step 8:

[0272] After implementing the proposed action plan, the user provides the results and emotional feedback to the server via their device. For example, the user inputs "Sales increased as a result of the advertising campaign" and "I am satisfied."

[0273] Step 9:

[0274] The server analyzes the feedback data and emotion data and reflects it in the next data analysis, which improves the accuracy of the next action plan and allows the system to continuously improve.

[0275] Example 2

[0276] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0277] In conventional systems, the processes of collecting, analyzing, and providing users with data on failure and success cases were not efficiently coordinated, making it difficult to formulate specific action plans based on identified patterns and success rules.In addition, it was not possible to incorporate emotional analysis based on user feedback, making it difficult to generate more accurate action plans that reflected emotional information.

[0278] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for collecting failure case data and success case data; means for storing the collected failure case data and success case data in a database; means for preprocessing the stored data to perform data cleansing and for removing and normalizing duplicate data; means for analyzing the preprocessed data using natural language processing technology and machine learning algorithms to identify patterns and trends; means for performing sentiment analysis based on user feedback; means for generating rules for success and action plans based on the identified patterns, trends, and sentiment analysis; means for displaying the generated rules for success and action plans on the user's terminal; and means for collecting user feedback and improving the analysis results and algorithms. This links a series of processes from collection to analysis, provision, and feedback, enabling the generation of more accurate action plans that incorporate user sentiment information.

[0279] "Failure case data" is data that contains detailed information about failed attempts to achieve a particular goal or objective.

[0280] "Success story data" is data that contains detailed information about successful attempts to achieve a particular goal or objective.

[0281] "Means of collection" refers to the methods and techniques used to collect the required information from the Internet and internal databases.

[0282] A "database" is a system for efficiently managing and storing collected data.

[0283] "Preprocessing" refers to tasks such as data cleansing, removing duplicate data, and completing incomplete data to make data easier to analyze.

[0284] "Data cleansing" is the process of removing unnecessary information and errors from data.

[0285] "Deleting duplicate data" refers to the process of organizing and integrating duplicate data of the same content into one piece of data.

[0286] "Normalization" is the process of arranging data into a unified format.

[0287] "Natural language processing technology" is a technology that enables computers to understand and process the natural language used by humans.

[0288] A "machine learning algorithm" is an algorithm that learns patterns and rules based on data and makes predictions and classifications for new data.

[0289] "Means of identifying patterns and trends" refers to methods and techniques for finding common characteristics and trends through data analysis.

[0290] "Feedback" is information provided by a user as a result of an action plan they have implemented.

[0291] "Sentiment analysis" is a technology that identifies and classifies emotions from text data such as user feedback.

[0292] A "law of success" is a principle that indicates a set of effective actions or steps derived from past success stories.

[0293] An "action plan" is a plan that outlines specific actions to be taken based on the laws of success.

[0294] "Display means" refers to a method or technology for visually displaying the generated information and action plan on the user's terminal.

[0295] "Means for improving the algorithm" refers to the technology of adjusting the analysis algorithm based on the collected feedback and reflecting it in the next analysis.

[0296] The system of the present invention is composed of three main elements: a server, a terminal, and a user, and also incorporates an emotion engine that recognizes the user's emotions. The system collects data on both failure and success cases, stores it in a database, analyzes it, generates rules for success and specific action plans, and provides them to the user. It also collects feedback from users to continuously improve the accuracy of the system.

[0297] Hardware and Software Configuration

[0298] Server: The server plays a central role in collecting data, pre-processing, analyzing, generating action plans, providing them to users, and processing feedback.

[0299] Software used:

[0300] Web scraping tools (e.g., Python's BeautifulSoup)

[0301] Database (e.g. MySQL)

[0302] Natural language processing libraries (e.g., spaCy, NLTK)

[0303] Machine learning libraries (e.g., scikit-learn)

[0304] Sentiment analysis models (e.g., HuggingFace Transformers)

[0305] Device: The device that a user uses to access the system and view the action plan. A device can be a laptop, desktop computer, or mobile device.

[0306] User: A person who uses the system to learn from failures and successes and implements specific action plans. The user provides feedback to the system using a terminal.

[0307] Data collection

[0308] The server collects data on failures and successes from the internet and internal company databases, using web scraping tools and APIs with BeautifulSoup to extract the necessary data from related blog posts, news articles, research papers, and other sources.

[0309] Data preprocessing and storage

[0310] The collected data is cleansed on the server, removing duplicates and completing incomplete data. This involves using regular expressions to remove HTML tags and unnecessary special characters and standardize the data format. The preprocessed data is then stored in a database such as MySQL and prepared for analysis.

[0311] Data analysis

[0312] The server performs analysis using natural language processing techniques and machine learning algorithms. Specifically, it uses spaCy and NLTK to tokenize text data, tag parts of speech, and perform dependency analysis, and then uses scikit-learn algorithms to identify patterns and trends in the data. The goal of the analysis is to identify factors behind failures and successes.

[0313] Analysis by emotion engine

[0314] The server has a built-in emotion engine that recognizes emotions based on user feedback. Using HuggingFace's Transformers library, a text analysis algorithm classifies emotions from user feedback text and extracts emotions such as "satisfied" or "anxious."

[0315] Formulating success and action plans

[0316] The server derives success rules based on the results of data analysis and sentiment analysis, generating specific action plans such as "hold regular meetings with stakeholders in the early stages of project planning."

[0317] Provision to users

[0318] The user accesses the system using a terminal. The server sends the generated success formula and action plan to the terminal and displays it on the dashboard. The user can check the proposed action plan and implement it as necessary.

[0319] Feedback and System Improvement

[0320] After the user implements the action plan, they provide the results as feedback to the system. For example, they might enter information like, "After meeting with stakeholders, the project progressed smoothly." The server analyzes this feedback and updates the algorithm to improve the accuracy of the next analysis.

[0321] Examples of concrete examples and prompts

[0322] For example, consider the case of a new product launch. The server uses BeautifulSoup to collect successful and unsuccessful cases of new product launches from the Internet. The collected data is cleansed and normalized using pandas and stored in a MySQL database. The server analyzes the data using spaCy and identifies success factors using a classification algorithm in scikit-learn. An emotion engine extracts emotions from user feedback, and the server ultimately generates a specific action plan, such as "conduct market research, identify target segments, and then launch an advertising campaign." The user then checks this action plan on their device and provides feedback to the system after the plan is implemented.

[0323] Examples of prompts include:

[0324] "Collect and analyze success stories and failures in bringing new products to market, and create a concrete action plan to lead to success."

[0325] This system allows companies to efficiently and effectively learn from failure and gain concrete methods to lead to success. It also allows for the formulation of more accurate action plans by reflecting user emotions.

[0326] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0327] Step 1:

[0328] Data collection

[0329] The server collects data on failures and successes. Specifically, it uses Python's BeautifulSoup to scrape relevant web pages and obtain text data on failures and successes. It also uses APIs to extract data from blog posts, news articles, research papers, etc. The input is a URL or API endpoint, and the output is the raw data obtained.

[0330] Step 2:

[0331] Data preprocessing and storage

[0332] The server cleanses the collected data and normalizes it into a unified format. Specifically, it uses regular expressions to remove HTML tags and special characters, and converts it into a data frame using the pandas library. The input is raw data, and the output is cleansed, standardized data. The processed data is stored in a MySQL database.

[0333] Step 3:

[0334] Data analysis

[0335] The server analyzes the preprocessed data using natural language processing techniques and machine learning algorithms. Specifically, it uses spaCy to tokenize the text data and analyze basic linguistic structures (part-of-speech tagging, dependency analysis). It then applies classification models using scikit-learn algorithms to identify patterns and trends in the data. The input is the cleansed data, and the output is the analysis results (identified patterns and trends).

[0336] Step 4:

[0337] Analysis by emotion engine

[0338] The server uses an emotion engine to recognize emotions from user feedback. Specifically, it uses the Transformers library in HuggingFace to analyze the feedback text and classify emotions such as "satisfied," "anxious," and "excited." The input is the feedback text, and the output is the extracted emotion data.

[0339] Step 5:

[0340] Formulating success and action plans

[0341] The server derives success rules based on the results of data analysis and sentiment analysis. Specifically, it integrates the analysis results from the scikit-learn algorithm with sentiment data and formulates specific action plans based on successful examples of project management. For example, it generates a plan such as "hold regular meetings with stakeholders in the early stages of project planning." The input is the analysis results and sentiment data, and the output is a specific action plan.

[0342] Step 6:

[0343] Provision to users

[0344] Users access the system using their devices. The server sends the generated success formula and action plan to the user's device and displays it on a dashboard. Specifically, the user can view the action plan on a web page or mobile application. The input is the generated action plan, and the output is the action plan displayed on the user's device.

[0345] Step 7:

[0346] Feedback and System Improvement

[0347] Users provide feedback to the system on the results of their action plans. Specifically, they access a feedback form from their device and enter the results and their emotions. The server receives this feedback, analyzes it using an emotion engine, and then updates the algorithm using scikit-learn. The input is the user's feedback, and the output is the updated analysis algorithm.

[0348] This system allows companies to learn from both success and failure and develop specific action plans to lead to success. Furthermore, incorporating user emotional data makes it possible to generate more accurate action plans.

[0349] (Application example 2)

[0350] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0351] Conventional systems were able to collect and analyze data on both failure and success cases and generate action plans, but there was no concrete method for utilizing this data in in-factory robot control to improve work efficiency and reduce the occurrence of errors. Furthermore, there was a lack of a mechanism for evaluating user feedback based on sentiment analysis and improving analysis accuracy. Therefore, a means to further improve work efficiency in factories was needed.

[0352] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0353] In this invention, the server includes means for collecting failure case data and success case data, means for storing the collected failure case data and success case data in a database, means for analyzing the stored data and identifying patterns and trends, means for generating rules for success and action plans based on the identified patterns and trends, means for displaying the generated rules for success and action plans on a user's terminal, means for collecting user feedback and improving the analysis results and algorithms, means including a robot for collecting work data and sensor information, means for executing a machine learning algorithm based on the collected data, and means for classifying emotions from user feedback text, thereby enabling work efficiency in factories and reducing the occurrence of errors.

[0354] "Failure Data" is information relating to instances where a particular task or project did not achieve the expected results.

[0355] "Success Data" is information relating to instances where an expected result was achieved in a particular task or project.

[0356] A "database" is a structured collection of information for storing and managing collected data.

[0357] A "pattern or trend" is an element that indicates a consistent structure or variation in the data, or a set of regularities found in the data.

[0358] A "law of success" is a proven guideline or principle for achieving success under specific circumstances or conditions.

[0359] An "action plan" is a plan that details the specific actions or steps to be taken to achieve a goal.

[0360] "User terminal" refers to the device (e.g., smartphone, tablet, or PC) used by the user to access the system and view the displayed information.

[0361] "Feedback" is information provided by a user by inputting the results and impressions of the action plan they have implemented.

[0362] "Work data" is information about the performance of robots and workers in the factory.

[0363] "Sensor information" is data used to monitor the environment within the factory and the status of robots in real time.

[0364] A "machine learning algorithm" is a computational method for analyzing large amounts of data, discovering patterns within it, and making predictions and classifications.

[0365] "Feedback text" is a written expression of opinions and thoughts that a user inputs into the system.

[0366] A "sentiment classifier" is a technique for identifying and classifying emotions such as positive, negative, or neutral from feedback text.

[0367] The system of the present invention collects and analyzes data on both failure and success cases, generates rules for success and specific action plans, and provides them to users. Furthermore, it can use an emotion engine to analyze user feedback and improve the accuracy of the system.

[0368] This system is composed of three main elements: a server, a terminal, and a user, and uses the following hardware and software:

[0369] Hardware and software used

[0370] 1. Hardware:

[0371] Factory robots (e.g., industrial robots and smartphones)

[0372] 2. Software:

[0373] requests: An HTTP request library for collecting data.

[0374] textblob: A natural language processing library for sentiment analysis

[0375] numpy: A scientific computing library for data analysis

[0376] sklearn: A library that provides machine learning algorithms

[0377] Data collection

[0378] The server collects data on failures and successes from the internet and internal databases, specifically, by acquiring factory operation data and sensor information via API endpoints.

[0379] Data preprocessing and storage

[0380] The collected data is normalized through a data cleansing process and stored in a database. Specific processes of data cleansing include removing noise from text data and standardizing data formats.

[0381] Data analysis

[0382] The server analyzes the data using natural language processing (NLP) and machine learning algorithms, specifically by taking the collected work data and feedback text as input and identifying effective work steps.

[0383] Analysis by emotion engine

[0384] Analyze user feedback text and classify the sentiment. Use the textblob library to identify whether the feedback is positive or negative.

[0385] Formulating success and action plans

[0386] The server extracts the principles of success based on the results of data and sentiment analysis and generates specific action plans, such as "performing regular maintenance" or "optimal procedures for specific tasks," and provides the plan to the user.

[0387] Provision to users

[0388] The user accesses the system using a terminal. The server sends the generated success formula and action plan to the terminal and displays it. The user can check the proposed action plan on the terminal interface.

[0389] Feedback and System Improvement

[0390] After the user executes the action plan, the results are provided to the system as feedback. A specific example of feedback is inputting text such as "This task was very efficient. I would like to continue using this method next time." The emotion engine also analyzes the emotional information contained in this feedback.

[0391] Specific examples

[0392] When a factory robot performs a specific task, the system collects the robot's work data and sensor information, and uses this information to generate a success rule and action plan. When workers enter feedback, they can provide an example prompt such as, "This task was very efficient. I would like to continue using this method next time," which, along with sentiment analysis, can improve the system's accuracy.

[0393] In this way, the system of the present invention can provide a specific method for improving work efficiency and reducing the occurrence of errors within a factory.

[0394] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0395] Step 1:

[0396] Data collection

[0397] The server collects failure and success case data from the internet and internal databases. Specifically, it obtains data such as factory operation data and sensor information through API endpoints. The input is the API endpoint, and the output is the obtained raw data. The server collects data using an HTTP request library (requests).

[0398] Step 2:

[0399] Data preprocessing and storage

[0400] The server cleanses the collected data, removing duplicates and normalizing the data. Specifically, it removes noise from the text data and standardizes the format. The input is raw data, and the output is preprocessed clean data. The server stores this clean data in a database.

[0401] Step 3:

[0402] Data analysis

[0403] The server analyzes the preprocessed data using natural language processing (NLP) techniques and machine learning algorithms. Specifically, it uses the collected work data and feedback text as input to identify patterns and trends in the data. The input is clean data, and the output is the analysis results (patterns and trends). The server performs the analysis using NLP techniques and machine learning libraries (e.g., sklearn).

[0404] Step 4:

[0405] Analysis by emotion engine

[0406] The server collects feedback text from users and classifies its sentiment using an emotion engine. Specifically, it uses a natural language processing library (textblob) to identify whether the feedback is positive or negative. The input is the feedback text, and the output is the sentiment classification result.

[0407] Step 5:

[0408] Formulating success and action plans

[0409] The server extracts success rules based on the results of data analysis and sentiment analysis and generates specific action plans. For example, it suggests "performing regular maintenance" or "optimal procedures for specific tasks." The input is the analysis results and sentiment classification results, and the output is the generated success rules and action plans.

[0410] Step 6:

[0411] Provision to users

[0412] The server sends the generated success formula and action plan to the user's terminal and displays them. The user can check the proposed action plan on the terminal interface. The input is the success formula and action plan, and the output is the display on the user's terminal.

[0413] Step 7:

[0414] Feedback and System Improvement

[0415] After the user executes the action plan, they provide the results to the system as feedback. The server collects this feedback and analyzes it again to improve the accuracy of the system. For example, a user may input feedback such as "This task was very efficient. I would like to continue using this method next time." The input is feedback, and the output is new analysis results and algorithm improvements for the system.

[0416] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0417] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0418] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0419] [Second embodiment]

[0420] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0421] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0422] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0423] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0424] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0425] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0426] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0427] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0428] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0429] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0430] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0431] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0432] The system of the present invention is composed of three main elements: a server, a terminal, and a user. The system collects data on failure cases and success cases, stores it in a database, analyzes it, generates rules for success and specific action plans, and provides them to users. It also collects feedback from users to continuously improve the accuracy of the system.

[0433] Data collection

[0434] The server collects data on success and failure cases from multiple sources, such as the Internet and internal databases. For example, it obtains success and failure cases in project management from public databases on the web, news articles, and specialized papers. The collected data is temporarily stored in the database in raw data form.

[0435] Data preprocessing and storage

[0436] The server preprocesses the collected data, which includes removing duplicates, completing incomplete data, and normalizing the data. The preprocessed data is then stored in a database again, ready for analysis.

[0437] Data analysis

[0438] The server then analyzes the preprocessed data using natural language processing (NLP) techniques and machine learning algorithms. The goal of this analysis is to identify patterns and trends in the data and uncover factors that lead to failures and successes. For example, in project management, it may be discovered that effective communication is the key to success.

[0439] Formulating success and action plans

[0440] The server derives the principles of success based on the results of the data analysis. Based on these principles, it generates a specific action plan. For example, it may formulate an action plan such as "hold regular meetings with stakeholders in the early stages of project planning."

[0441] Provision to users

[0442] The user accesses the system using a terminal. The server sends the generated success formula and action plan to the terminal and displays it to the user. The user can then proceed with their work according to the provided action plan.

[0443] Feedback and System Improvement

[0444] After the user implements the action plan, they provide the results as feedback to the system. For example, they input information such as, "As a result of regular meetings, the project progressed smoothly." The server then re-analyzes the data based on the collected feedback to improve the accuracy of the algorithm and action plan.

[0445] Specific examples

[0446] For example, if a company is trying to bring a new product to market, this system could work as follows:

[0447] Data collection

[0448] The server collects success stories and failure stories of new product launches from the Internet and past data within companies.

[0449] Data preprocessing and storage

[0450] The collected data is normalized through a data cleansing process and stored in a database.

[0451] Data analysis

[0452] Sarver uses natural language processing technology to analyze the data and identify factors that contribute to the success of new product launches. For example, he concludes that it is important to "clarify the target market and implement a well-thought-out marketing strategy."

[0453] Formulating success and action plans

[0454] Based on the results, the server generates a specific action plan, such as "conduct market research, clarify target segments, and then implement an advertising campaign."

[0455] Provision to users

[0456] When a user (a marketing person at a company) logs into the system using a terminal, an action plan proposed by the server is displayed.

[0457] Feedback and System Improvement

[0458] The user executes the action plan and provides feedback on the results to the system. Based on this information, the server updates the algorithm and reflects it in the next analysis, providing more accurate success rules and action plans.

[0459] This system gives companies a concrete way to efficiently and effectively learn from their mistakes and lead to success.

[0460] The processing flow will be explained below.

[0461] Step 1:

[0462] The server collects failure and success data from the internet and internal databases, for example, using web scraping or APIs to retrieve relevant data from blog posts, news articles, research papers, etc.

[0463] Step 2:

[0464] The server preprocesses the collected data, including data cleansing, removing duplicate data, completing incomplete data, and normalizing the data. Specifically, it removes noise from text data (e.g., HTML tags and unnecessary special characters) and standardizes the data format.

[0465] Step 3:

[0466] The server stores the preprocessed data in a case database. Each case contains detailed information such as case ID, date and time, background, and results, and this information is saved in the database.

[0467] Step 4:

[0468] The server analyzes the data in the case database using natural language processing (NLP) techniques and machine learning algorithms, specifically by performing text analysis to identify common patterns and trends among cases and by using clustering algorithms to group related cases.

[0469] Step 5:

[0470] Based on the analysis, the server derives success rules, such as identifying the importance of regular stakeholder feedback for successful project management.

[0471] Step 6:

[0472] The server generates a specific action plan based on the success formula, for example, an action plan that includes the instruction "obtain stakeholder feedback twice by the next milestone."

[0473] Step 7:

[0474] When a user accesses the system using a terminal, the server sends the generated success formula and action plan to the terminal and displays it. The user can check the proposed action plan on the terminal dashboard.

[0475] Step 8:

[0476] The user implements the proposed action plan and provides the results as feedback to the server via the terminal. For example, the user might input information such as, "As a result of obtaining feedback from stakeholders, the project progressed smoothly."

[0477] Step 9:

[0478] The server analyzes the feedback data provided by users to improve the accuracy of the algorithms and action plans, and uses the insights from the feedback to conduct the next data analysis and implement continuous system improvements.

[0479] Example 1

[0480] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0481] In today's business environment, it is important to learn from project successes and failures and develop concrete action plans based on them. However, many organizations do not do this efficiently and face challenges due to the lack of effective feedback loops, making it difficult to utilize this information.

[0482] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0483] In this invention, the server includes means for collecting failure case data and success case data, means for storing the collected failure case data and success case data in a database, means for preprocessing the stored data by deleting duplicate data, completing incomplete data, and normalizing the data, means for analyzing the preprocessed data and identifying patterns and trends using natural language processing technology and machine learning algorithms, means for generating a law of success and a specific action plan based on the identified patterns and trends, means for displaying the generated law of success and action plan on a user's terminal, and means for collecting feedback from users and analyzing the feedback to improve the analysis results and algorithms. This makes it possible to efficiently utilize information obtained from failure cases and success cases to formulate specific action plans and increase business success.

[0484] "Failure case data" refers to data on cases where goals were not achieved in past projects or tasks.

[0485] "Success case data" refers to data on cases where goals were achieved in past projects or tasks.

[0486] "Data collection methods" are methods for obtaining data from multiple sources, such as the Internet and internal company databases.

[0487] "Means for storing in a database" refers to means for storing collected data in a database for easy management and access.

[0488] The "preprocessing means" refers to a means for removing duplicate data from the collected data, completing incomplete data, and normalizing the data.

[0489] "Analysis means" refers to the means of applying natural language processing techniques and machine learning algorithms to pre-processed data to identify patterns and trends in the data.

[0490] The "means for generating rules of success" is a means for extracting rules that lead to success based on the patterns and trends identified by the analysis means.

[0491] A "means for generating an action plan" is a means for formulating specific guidelines and steps for action in accordance with the laws of success.

[0492] The "means for displaying on the user's terminal" refers to a means for visually displaying the generated success law and action plan to the user.

[0493] "Means for collecting feedback" refers to the means for incorporating results and opinions from users after the implementation of an action plan into the system.

[0494] "Means for improving the algorithm" refers to means for analyzing collected feedback and improving the accuracy of the analysis results and generation process.

[0495] The system of this invention is composed of three main elements: a server, a terminal, and a user. The system collects data on failure cases and success cases, stores this data in a database, and performs preprocessing and analysis to generate success rules and specific action plans, which are ultimately provided to the user. It also has a mechanism for collecting user feedback and continuously improving the accuracy of the system.

[0496] Data collection

[0497] The server collects failure and success case data from multiple appropriate data sources, such as the Internet and internal databases. Web scraping tools (e.g., BeautifulSoup or Scrapy) are used for this process. For example, project management success and failure cases are obtained from public databases on the Web, news articles, and specialized papers. The collected data is temporarily stored in a database (e.g., MySQL or PostgreSQL).

[0498] Data preprocessing and storage

[0499] The server preprocesses the collected raw data, using the Pandas library and regular expressions (Regex) to remove duplicates, impute incomplete data, and normalize the data into a standard format. Once preprocessed, the data is stored back in the database, ready for analysis.

[0500] Data analysis

[0501] The server analyzes the preprocessed data using natural language processing (NLP) techniques and machine learning algorithms. This analysis uses NLP libraries such as NLTK and Spacy, and machine learning libraries such as Scikit-learn and TensorFlow. The goal of the analysis is to identify patterns and trends in the data and identify factors behind success and failure. For example, a clustering algorithm can be used to classify similar successful and unsuccessful cases.

[0502] Formulating success and action plans

[0503] The server derives the principles of success based on the results of data analysis. Based on these principles, it generates specific action plans. For example, based on the principle that "regular meetings with stakeholders should be held in the early stages of project planning," it formulates a specific course of action that states "schedule weekly meetings and report on progress."

[0504] Provision to users

[0505] A user accesses the system using a terminal. When the user logs in to the system, the generated success formula and action plan are sent from the server to the terminal. The terminal visually displays this to the user, for example, in an easy-to-understand format through a dashboard.

[0506] Feedback and System Improvement

[0507] When users implement their action plans and provide feedback to the system, the server analyzes the feedback data again. The server analyzes the collected feedback and identifies new patterns and trends. Through this process, the server improves the accuracy of the algorithms and action plans.

[0508] Specific examples

[0509] For example, if a company is trying to bring a new product to market, this system would work as follows:

[0510] The server collects success stories and failure stories of new product launches from the Internet and past data within companies.

[0511] The collected data is normalized through a data cleansing process and stored in a database.

[0512] Sarver uses natural language processing technology to analyze the data and identify factors that contribute to the success of new product launches. For example, he concludes that it is important to "clarify the target market and implement a well-thought-out marketing strategy."

[0513] Based on the results, the server generates a specific action plan, such as "conduct market research, clarify target segments, and then implement an advertising campaign."

[0514] When a user (a marketing person at a company) logs into the system using a terminal, an action plan proposed by the server is displayed.

[0515] The user executes the action plan and provides feedback on the results to the system. Based on this information, the server updates the algorithm and reflects it in the next analysis.

[0516] Prompt Sentence Examples

[0517] Below are some example prompts to input to the generative AI model:

[0518] "Analyze a new product launch. Based on data from successful and unsuccessful cases, generate an action plan for making it a success."

[0519] This system allows companies to efficiently and effectively learn from their mistakes and provides a concrete path to success.

[0520] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0521] Step 1: Data collection

[0522] The server collects data on failures and successes from multiple sources, including the Internet and internal databases. Specifically, it uses web scraping tools (e.g., BeautifulSoup, Scrapy) to obtain data from public databases, news articles, and specialized papers. The collected raw data is temporarily stored in a database (e.g., MySQL, PostgreSQL).

[0523] Input: Information on the Internet, information from internal databases

[0524] Output: Raw data stored in a database

[0525] Step 2: Preprocessing the data

[0526] The server performs data cleansing on the collected raw data. Specifically, it uses the Pandas library to remove duplicate data, complete incomplete data, and normalize the data using regular expressions (Regex). Once preprocessed, the data is stored in the database again.

[0527] Input: Raw data stored in a database

[0528] Output: Data that has been cleansed and normalized

[0529] Step 3: Analyze the data

[0530] The server then analyzes the preprocessed data using natural language processing (NLP) techniques and machine learning algorithms. Using NLP libraries like NLTK and Spacy, and machine learning libraries like Scikit-learn and TensorFlow, the server identifies patterns and trends in the data. This analysis clarifies factors behind success and failure.

[0531] Input: Preprocessed data

[0532] Output: Analysis of factors behind success and failure

[0533] Step 4: Create a success formula and action plan

[0534] The server derives success rules based on the results of the data analysis and generates specific action plans. For example, a success rule may be "hold regular meetings with stakeholders in the early stages of project planning," and specific action guidelines (e.g., setting up weekly meetings) are then formulated based on that.

[0535] Input: Analysis results on factors behind success and failure

[0536] Output: Laws of success and concrete action plans

[0537] Step 5: Provide to users

[0538] The user accesses the system using a terminal and views the generated success formula and action plan. The server sends this information to the terminal, which then visually displays it on a dashboard or other device.

[0539] Input: Laws of success and concrete action plans

[0540] Output: Success formula and action plan displayed on the user's device

[0541] Step 6: Gather feedback and improve the system

[0542] Users input the results of their action plans as feedback into the system, which the server collects and analyzes again, identifying new patterns and trends to refine the algorithms and action plans.

[0543] Input: User feedback

[0544] Output: Updated algorithm and improved action plan

[0545] Through these steps, the system effectively utilizes data on both failure and success cases to provide specific improvement measures, thereby enabling users to increase the success rate of their work.

[0546] (Application example 1)

[0547] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0548] When operating autonomous vehicles, it is necessary to adapt to the environment after starting operation and continuously improve optimal driving patterns and operation methods. Collecting and analyzing data during operation, learning from successes and failures, and providing specific driving methods in real time are particularly challenging. Conventional methods do not efficiently generate executable action plans or improve the system through feedback, preventing improvements to the accuracy of autonomous driving.

[0549] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0550] In this invention, the server includes means for collecting failure case data and success case data, means for storing the collected failure case data and success case data in a database, means for analyzing the stored data and identifying patterns and trends, means for generating a success rule and an action plan based on the identified patterns and trends, means for displaying the generated success rule and action plan on a user's terminal, means for collecting user feedback and improving the analysis results and algorithm, means for collecting sensor data from the autonomous vehicle, means for preprocessing and normalizing the collected sensor data, means for analyzing trends in the data using natural language processing technology and machine learning algorithms, means for generating a success rule and specific operating methods for operating the autonomous vehicle based on the analysis results, means for displaying the generated operating methods on an autonomous vehicle operation management terminal, and means for collecting user feedback on operation results and improving the analysis results and algorithm. This makes it possible to continuously improve the operation accuracy of the autonomous vehicle and provide optimal operation patterns and operating methods in real time.

[0551] "Failure case data" is a record of when an autonomous vehicle did not perform as expected under certain circumstances or conditions.

[0552] "Success data" is a record of an autonomous vehicle performing as expected under specific circumstances or conditions.

[0553] A "database" is an information management system that systematically stores collected data and enables efficient searching and analysis.

[0554] "Pattern and trend identification methods" are techniques and methods used to analyze collected data and find common characteristics or recurring behaviors.

[0555] A "law of success" is a theory that specifies the factors and methodologies that will lead to the success of autonomous vehicles under certain conditions.

[0556] An "action plan" is a plan that outlines specific operational operations and countermeasures that should be implemented based on the principles of success.

[0557] "Means for collecting user feedback" refers to an interface or method by which a user can report the results of operating an autonomous vehicle to the system.

[0558] "Sensor data" refers to data about the surrounding environment and vehicle operation acquired by various sensors (e.g., LiDAR, cameras, radar) installed in autonomous vehicles.

[0559] "Data preprocessing" refers to a series of operations (e.g., missing value imputation, normalization, deduplication) performed on collected data to prepare it in an analyzable format.

[0560] "Natural language processing technology" is a technology that allows computers to understand, analyze, and generate natural language used by humans.

[0561] A "machine learning algorithm" is a mathematical model or method for learning patterns from data and using them to make predictions or classifications.

[0562] An "operation management terminal" is a device or system for managing and displaying the operating status, settings, and operation methods of an autonomous vehicle.

[0563] "Operation result feedback" refers to data that an autonomous vehicle provides back to the system regarding the results and situation it obtains during actual operation.

[0564] The system of this invention is designed to enhance the operation management of autonomous vehicles. This system consists of three main elements: a server, a terminal, and a user.

[0565] Data collection

[0566] The server collects real-time sensor data from the autonomous vehicle's LiDAR, camera, and radar sensors, providing detailed information about the vehicle's behavior and the surrounding environment during operation. This data also includes examples of successful and unsuccessful operations, and the system collects and stores this data in a database.

[0567] Data preprocessing and storage

[0568] The collected raw data is temporarily stored in a database. After that, a data preprocessing process is performed to remove duplicate data, complete incomplete data, and normalize the data. This preprocessed data is then stored in a database again, ready for analysis.

[0569] Data analysis

[0570] The server then analyzes the preprocessed data using natural language processing (NLP) and machine learning algorithms, including Python libraries such as pandas, scikit-learn, and joblib, to identify patterns and trends in the data and identify factors behind failures and successes.

[0571] Formulating success and action plans

[0572] Based on the results of the data analysis, the server derives rules of thumb, generating specific driving patterns and maneuvers, such as specific speed limits and emergency evasive actions. These action plans are further refined using generative AI models.

[0573] User Offerings and Feedback

[0574] The server displays the generated success formula and action plan on the management terminal or engineer's terminal. Users can use this information to manage the settings and operation of the autonomous vehicle. The operation results are fed back to the system by the user, and the server re-analyzes them based on this and improves the accuracy of the algorithm.

[0575] Specific examples

[0576] For example, when an autonomous vehicle is operating within a city, the server collects sensor data and analyzes examples of successful and unsuccessful driving. As a result, a specific action plan is generated, such as "setting the speed limit to 25 km / h in urban areas and automatically avoiding bicycle lanes when approaching them." This action plan is displayed on the terminal, and the operation manager applies it to operate the vehicle. The operation results are fed back to the system, and are reflected in future operations.

[0577] Prompt Sentence Examples

[0578] "This system uses sensor data from autonomous vehicles to identify factors that contribute to operational success and failure, and proposes specific action plans. Specifically, it suggests speed limits and how to avoid emergencies. Please explain the specific process for how this data is collected, analyzed, and used to derive the formula for success."

[0579] In this way, the invention continuously improves the driving accuracy of autonomous vehicles and provides optimal driving patterns and operating methods in real time.

[0580] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0581] Step 1:

[0582] The server collects sensor data in real time from sensor devices (LiDAR, camera, radar) installed in the autonomous vehicle. Raw data (vehicle behavior and surrounding environment during operation) is given as input and temporarily stored in a database. The output is a collection of collected raw data.

[0583] Step 2:

[0584] The server preprocesses the collected raw data. It receives the raw data as input, removes duplicates, completes incomplete data, and normalizes it. Specifically, it uses Python libraries (pandas, scikit-learn) for data cleansing and scaling. The output is a preprocessed, clean dataset.

[0585] Step 3:

[0586] The server analyzes the preprocessed data using natural language processing (NLP) and machine learning algorithms. It takes the preprocessed data as input and uses a Random Forest Classifier to identify patterns and trends in the data. The output is a list of success factors and failure factors as a result of the analysis.

[0587] Step 4:

[0588] The server generates a formula for success and a specific action plan based on the analysis results. It receives the analysis results as input and further refines the action plan using a generative AI model. The output is an action plan that includes specific driving patterns and operation methods. For example, specific instructions such as "set the speed limit to 25 km / h in urban areas" are generated.

[0589] Step 5:

[0590] The server sends the generated success rule and action plan to the terminal and displays it to the user. The server receives the action plan as input and displays it on the operation management terminal. The output is a specific action plan that is displayed on the user's terminal.

[0591] Step 6:

[0592] The user operates the autonomous vehicle based on the provided action plan. The action plan displayed on the terminal is received as input and executed. The output is the driving status and environmental data resulting from the execution.

[0593] Step 7:

[0594] The user inputs the results of the operation into the system as feedback. The system receives operational status and environmental data as input and feeds this back to the server. The output is a set of feedback data.

[0595] Step 8:

[0596] The server re-analyzes the collected feedback data to improve the accuracy of the algorithm. It receives the feedback data as input and re-analyzes it to refine the algorithm. The output is an updated algorithm and an improved action plan.

[0597] Through these steps, the operational accuracy and safety of autonomous vehicles will be continuously improved.

[0598] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0599] The system of the present invention is composed of three main elements: a server, a terminal, and a user. It also incorporates an emotion engine that recognizes the user's emotions. The system collects data on both failure and success cases, stores it in a database, analyzes it, generates rules for success and specific action plans, and provides them to the user. It also collects feedback from users to continuously improve the accuracy of the system. An embodiment of the system is described in detail below.

[0600] Data collection

[0601] The server collects failure and success data from the internet and internal databases, for example, using web scraping or APIs to retrieve relevant data from blog posts, news articles, research papers, etc.

[0602] Data preprocessing and storage

[0603] The server preprocesses the collected data. This includes data cleansing, removing duplicate data, completing incomplete data, and normalizing the data. Specifically, it removes noise from the text data (e.g., HTML tags and unnecessary special characters) and standardizes the data format. The preprocessed data is stored in a case database and is ready for analysis.

[0604] Data analysis

[0605] The server then analyzes the preprocessed data using natural language processing (NLP) techniques and machine learning algorithms. The goal of this analysis is to identify patterns and trends in the data and uncover factors that lead to failures and successes. For example, in project management, it may be discovered that effective communication is the key to success.

[0606] Analysis by emotion engine

[0607] The server includes an emotion engine that recognizes emotions based on user feedback. The emotion engine uses a text analysis algorithm to classify emotions from the user's feedback text. For example, if the user's feedback expresses emotions such as "very satisfied" or "anxious," the emotion information is reflected in the analysis.

[0608] Formulating success and action plans

[0609] The server derives the principles of success based on the results of data analysis and sentiment analysis by the emotion engine. Specific action plans are generated based on the principles of success. For example, an action plan could be formulated that includes holding regular meetings with stakeholders in the early stages of project planning.

[0610] Provision to users

[0611] The user accesses the system using a terminal. The server sends the generated success formula and action plan to the terminal and displays it. The user can check the proposed action plan on the terminal dashboard.

[0612] Feedback and System Improvement

[0613] After a user implements an action plan, they provide the results as feedback to the system. For example, they might enter information like, "As a result of obtaining stakeholder feedback, the project progressed more smoothly." The emotion engine simultaneously analyzes the emotions contained in the feedback. The server then re-analyzes the data based on this feedback, improving the accuracy of the algorithm and action plan.

[0614] Specific examples

[0615] For example, if a company is trying to bring a new product to market, this system could work as follows:

[0616] Data collection

[0617] The server collects success stories and failure stories of new product launches from the Internet and past data within companies.

[0618] Data preprocessing and storage

[0619] The collected data is normalized through a data cleansing process and stored in a case database.

[0620] Data analysis

[0621] Sarver uses natural language processing technology to analyze the data and identify factors that contribute to the success of new product launches. For example, he concludes that it is important to "clarify the target market and implement a well-thought-out marketing strategy."

[0622] Analysis by emotion engine

[0623] When receiving user feedback, the emotion engine classifies emotions such as "satisfaction" or "anxiety" and reflects that emotional data in new analysis.

[0624] Formulating success and action plans

[0625] Based on the results and sentiment data, the server generates a specific action plan: "Conduct market research, clarify target segments, and then implement an advertising campaign."

[0626] Provision to users

[0627] When a user (a marketing person at a company) logs into the system using a terminal, an action plan proposed by the server is displayed.

[0628] Feedback and System Improvement

[0629] The user executes the action plan and provides feedback on the results to the system. Based on this information and emotional data, the server updates the algorithm and reflects it in the next analysis, providing a more accurate formula for success and action plan.

[0630] This system allows companies to efficiently and effectively learn from failures and gain concrete methods to lead to success. It also takes into account user emotions, allowing for more accurate action plans to be formulated.

[0631] The processing flow will be explained below.

[0632] Step 1:

[0633] The server collects failure and success data from the internet and internal databases, for example, using web scraping or APIs to retrieve relevant data from blog posts, news articles, research papers, etc.

[0634] Step 2:

[0635] The server preprocesses the collected data, including data cleansing, removing duplicate data, completing incomplete data, and normalizing the data. Specifically, it removes noise from text data (e.g., HTML tags and unnecessary special characters) and standardizes the data format.

[0636] Step 3:

[0637] The server stores the preprocessed data in a case database, with each case containing detailed information such as case ID, date and time, background, and results.

[0638] Step 4:

[0639] The server analyzes the stored data using natural language processing (NLP) techniques and machine learning algorithms, specifically by performing text analysis to identify common patterns and trends among cases and by using clustering algorithms to group related cases.

[0640] Step 5:

[0641] Based on the analysis, the server derives the principles of success, for example, discovering that effective communication is the key to success in project management.

[0642] Step 6:

[0643] The server generates a specific action plan based on the success formula, for example, an action plan that includes the instruction "obtain stakeholder feedback twice by the next milestone."

[0644] Step 7:

[0645] When a user accesses the system using a terminal, the server sends the generated success formula and action plan to the terminal and displays it. The user can check the proposed action plan on the terminal dashboard.

[0646] Step 8:

[0647] The user executes the proposed action plan and provides the results and emotional feedback to the server via the terminal. For example, the user can input information such as "We were able to obtain stakeholder feedback successfully and the project progressed smoothly" and the emotion "I am satisfied."

[0648] Step 9:

[0649] The server analyzes the feedback and emotional data provided by users to improve the accuracy of algorithms and action plans. It uses insights from the feedback to conduct the next data analysis and implement continuous system improvements. By utilizing an emotional engine, the emotional information contained in user feedback is also reflected in the analysis.

[0650] As a concrete example, we will show how this system works in the marketing strategy of a new product.

[0651] Step 1:

[0652] The server collects success stories and failure stories of new product launches from the Internet and past data within companies.

[0653] Step 2:

[0654] The collected data is cleansed and duplicates are removed, and the text data is then formatted.

[0655] Step 3:

[0656] The server stores the pre-processed data in a database, recording detailed information about each case.

[0657] Step 4:

[0658] The server analyzes the cases in the database and identifies factors that contribute to success. For example, it finds that "clear target market definition and development of marketing strategies" are factors for success.

[0659] Step 5:

[0660] Based on the analysis results, we derive the formula for success: "Clearly define your target market and develop an appropriate advertising campaign."

[0661] Step 6:

[0662] The server generates a specific action plan based on the formula for success, such as "implementing an advertising campaign divided into three steps."

[0663] Step 7:

[0664] When a user (marketer) logs in to a terminal, the server transmits the generated action plan and displays it on the terminal.

[0665] Step 8:

[0666] After implementing the proposed action plan, the user provides the results and emotional feedback to the server via their device. For example, the user inputs "Sales increased as a result of the advertising campaign" and "I am satisfied."

[0667] Step 9:

[0668] The server analyzes the feedback data and emotion data and reflects it in the next data analysis, which improves the accuracy of the next action plan and allows the system to continuously improve.

[0669] Example 2

[0670] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0671] In conventional systems, the processes of collecting, analyzing, and providing users with data on failure and success cases were not efficiently coordinated, making it difficult to formulate specific action plans based on identified patterns and success rules.In addition, it was not possible to incorporate emotional analysis based on user feedback, making it difficult to generate more accurate action plans that reflected emotional information.

[0672] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for collecting failure case data and success case data; means for storing the collected failure case data and success case data in a database; means for preprocessing the stored data to perform data cleansing and for removing and normalizing duplicate data; means for analyzing the preprocessed data using natural language processing technology and machine learning algorithms to identify patterns and trends; means for performing sentiment analysis based on user feedback; means for generating rules for success and action plans based on the identified patterns, trends, and sentiment analysis; means for displaying the generated rules for success and action plans on the user's terminal; and means for collecting user feedback and improving the analysis results and algorithms. This links a series of processes from collection to analysis, provision, and feedback, enabling the generation of more accurate action plans that incorporate user sentiment information.

[0673] "Failure case data" is data that contains detailed information about failed attempts to achieve a particular goal or objective.

[0674] "Success story data" is data that contains detailed information about successful attempts to achieve a particular goal or objective.

[0675] "Means of collection" refers to the methods and techniques used to collect the required information from the Internet and internal databases.

[0676] A "database" is a system for efficiently managing and storing collected data.

[0677] "Preprocessing" refers to tasks such as data cleansing, removing duplicate data, and completing incomplete data to make data easier to analyze.

[0678] "Data cleansing" is the process of removing unnecessary information and errors from data.

[0679] "Deleting duplicate data" refers to the process of organizing and integrating duplicate data of the same content into one piece of data.

[0680] "Normalization" is the process of arranging data into a unified format.

[0681] "Natural language processing technology" is a technology that enables computers to understand and process the natural language used by humans.

[0682] A "machine learning algorithm" is an algorithm that learns patterns and rules based on data and makes predictions and classifications for new data.

[0683] "Means of identifying patterns and trends" refers to methods and techniques for finding common characteristics and trends through data analysis.

[0684] "Feedback" is information provided by a user as a result of an action plan they have implemented.

[0685] "Sentiment analysis" is a technology that identifies and classifies emotions from text data such as user feedback.

[0686] A "law of success" is a principle that indicates a set of effective actions or steps derived from past success stories.

[0687] An "action plan" is a plan that outlines specific actions to be taken based on the laws of success.

[0688] "Display means" refers to a method or technology for visually displaying the generated information and action plan on the user's terminal.

[0689] "Means for improving the algorithm" refers to the technology of adjusting the analysis algorithm based on the collected feedback and reflecting it in the next analysis.

[0690] The system of the present invention is composed of three main elements: a server, a terminal, and a user, and also incorporates an emotion engine that recognizes the user's emotions. The system collects data on both failure and success cases, stores it in a database, analyzes it, generates rules for success and specific action plans, and provides them to the user. It also collects feedback from users to continuously improve the accuracy of the system.

[0691] Hardware and Software Configuration

[0692] Server: The server plays a central role in collecting data, pre-processing, analyzing, generating action plans, providing them to users, and processing feedback.

[0693] Software used:

[0694] Web scraping tools (e.g., Python's BeautifulSoup)

[0695] Database (e.g. MySQL)

[0696] Natural language processing libraries (e.g., spaCy, NLTK)

[0697] Machine learning libraries (e.g., scikit-learn)

[0698] Sentiment analysis models (e.g., HuggingFace Transformers)

[0699] Device: The device that a user uses to access the system and view the action plan. A device can be a laptop, desktop computer, or mobile device.

[0700] User: A person who uses the system to learn from failures and successes and implements specific action plans. The user provides feedback to the system using a terminal.

[0701] Data collection

[0702] The server collects data on failures and successes from the internet and internal company databases, using web scraping tools and APIs with BeautifulSoup to extract the necessary data from related blog posts, news articles, research papers, and other sources.

[0703] Data preprocessing and storage

[0704] The collected data is cleansed on the server, removing duplicates and completing incomplete data. This involves using regular expressions to remove HTML tags and unnecessary special characters and standardize the data format. The preprocessed data is then stored in a database such as MySQL and prepared for analysis.

[0705] Data analysis

[0706] The server performs analysis using natural language processing techniques and machine learning algorithms. Specifically, it uses spaCy and NLTK to tokenize text data, tag parts of speech, and perform dependency analysis, and then uses scikit-learn algorithms to identify patterns and trends in the data. The goal of the analysis is to identify factors behind failures and successes.

[0707] Analysis by emotion engine

[0708] The server has a built-in emotion engine that recognizes emotions based on user feedback. Using HuggingFace's Transformers library, a text analysis algorithm classifies emotions from user feedback text and extracts emotions such as "satisfied" or "anxious."

[0709] Formulating success and action plans

[0710] The server derives success rules based on the results of data analysis and sentiment analysis, generating specific action plans such as "hold regular meetings with stakeholders in the early stages of project planning."

[0711] Provision to users

[0712] The user accesses the system using a terminal. The server sends the generated success formula and action plan to the terminal and displays it on the dashboard. The user can check the proposed action plan and implement it as necessary.

[0713] Feedback and System Improvement

[0714] After the user implements the action plan, they provide the results as feedback to the system. For example, they might enter information like, "After meeting with stakeholders, the project progressed smoothly." The server analyzes this feedback and updates the algorithm to improve the accuracy of the next analysis.

[0715] Examples of concrete examples and prompts

[0716] For example, consider the case of a new product launch. The server uses BeautifulSoup to collect successful and unsuccessful cases of new product launches from the Internet. The collected data is cleansed and normalized using pandas and stored in a MySQL database. The server analyzes the data using spaCy and identifies success factors using a classification algorithm in scikit-learn. An emotion engine extracts emotions from user feedback, and the server ultimately generates a specific action plan, such as "conduct market research, identify target segments, and then launch an advertising campaign." The user then checks this action plan on their device and provides feedback to the system after the plan is implemented.

[0717] Examples of prompts include:

[0718] "Collect and analyze success stories and failures in bringing new products to market, and create a concrete action plan to lead to success."

[0719] This system allows companies to efficiently and effectively learn from failure and gain concrete methods to lead to success. It also allows for the formulation of more accurate action plans by reflecting user emotions.

[0720] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0721] Step 1:

[0722] Data collection

[0723] The server collects data on failures and successes. Specifically, it uses Python's BeautifulSoup to scrape relevant web pages and obtain text data on failures and successes. It also uses APIs to extract data from blog posts, news articles, research papers, etc. The input is a URL or API endpoint, and the output is the raw data obtained.

[0724] Step 2:

[0725] Data preprocessing and storage

[0726] The server cleanses the collected data and normalizes it into a unified format. Specifically, it uses regular expressions to remove HTML tags and special characters, and converts it into a data frame using the pandas library. The input is raw data, and the output is cleansed, standardized data. The processed data is stored in a MySQL database.

[0727] Step 3:

[0728] Data analysis

[0729] The server analyzes the preprocessed data using natural language processing techniques and machine learning algorithms. Specifically, it uses spaCy to tokenize the text data and analyze basic linguistic structures (part-of-speech tagging, dependency analysis). It then applies classification models using scikit-learn algorithms to identify patterns and trends in the data. The input is the cleansed data, and the output is the analysis results (identified patterns and trends).

[0730] Step 4:

[0731] Analysis by emotion engine

[0732] The server uses an emotion engine to recognize emotions from user feedback. Specifically, it uses the Transformers library in HuggingFace to analyze the feedback text and classify emotions such as "satisfied," "anxious," and "excited." The input is the feedback text, and the output is the extracted emotion data.

[0733] Step 5:

[0734] Formulating success and action plans

[0735] The server derives success rules based on the results of data analysis and sentiment analysis. Specifically, it integrates the analysis results from the scikit-learn algorithm with sentiment data and formulates specific action plans based on successful examples of project management. For example, it generates a plan such as "hold regular meetings with stakeholders in the early stages of project planning." The input is the analysis results and sentiment data, and the output is a specific action plan.

[0736] Step 6:

[0737] Provision to users

[0738] Users access the system using their devices. The server sends the generated success formula and action plan to the user's device and displays it on a dashboard. Specifically, the user can view the action plan on a web page or mobile application. The input is the generated action plan, and the output is the action plan displayed on the user's device.

[0739] Step 7:

[0740] Feedback and System Improvement

[0741] Users provide feedback to the system on the results of their action plans. Specifically, they access a feedback form from their device and enter the results and their emotions. The server receives this feedback, analyzes it using an emotion engine, and then updates the algorithm using scikit-learn. The input is the user's feedback, and the output is the updated analysis algorithm.

[0742] This system allows companies to learn from both success and failure and develop specific action plans to lead to success. Furthermore, incorporating user emotional data makes it possible to generate more accurate action plans.

[0743] (Application example 2)

[0744] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0745] Conventional systems were able to collect and analyze data on both failure and success cases and generate action plans, but there was no concrete method for utilizing this data in in-factory robot control to improve work efficiency and reduce the occurrence of errors. Furthermore, there was a lack of a mechanism for evaluating user feedback based on sentiment analysis and improving analysis accuracy. Therefore, a means to further improve work efficiency in factories was needed.

[0746] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0747] In this invention, the server includes means for collecting failure case data and success case data, means for storing the collected failure case data and success case data in a database, means for analyzing the stored data and identifying patterns and trends, means for generating rules for success and action plans based on the identified patterns and trends, means for displaying the generated rules for success and action plans on a user's terminal, means for collecting user feedback and improving the analysis results and algorithms, means including a robot for collecting work data and sensor information, means for executing a machine learning algorithm based on the collected data, and means for classifying emotions from user feedback text, thereby enabling work efficiency in factories and reducing the occurrence of errors.

[0748] "Failure Data" is information relating to instances where a particular task or project did not achieve the expected results.

[0749] "Success Data" is information relating to instances where an expected result was achieved in a particular task or project.

[0750] A "database" is a structured collection of information for storing and managing collected data.

[0751] A "pattern or trend" is an element that indicates a consistent structure or variation in the data, or a set of regularities found in the data.

[0752] A "law of success" is a proven guideline or principle for achieving success under specific circumstances or conditions.

[0753] An "action plan" is a plan that details the specific actions or steps to be taken to achieve a goal.

[0754] "User terminal" refers to the device (e.g., smartphone, tablet, or PC) used by the user to access the system and view the displayed information.

[0755] "Feedback" is information provided by a user by inputting the results and impressions of the action plan they have implemented.

[0756] "Work data" is information about the performance of robots and workers in the factory.

[0757] "Sensor information" is data used to monitor the environment within the factory and the status of robots in real time.

[0758] A "machine learning algorithm" is a computational method for analyzing large amounts of data, discovering patterns within it, and making predictions and classifications.

[0759] "Feedback text" is a written expression of opinions and thoughts that a user inputs into the system.

[0760] A "sentiment classifier" is a technique for identifying and classifying emotions such as positive, negative, or neutral from feedback text.

[0761] The system of the present invention collects and analyzes data on both failure and success cases, generates rules for success and specific action plans, and provides them to users. Furthermore, it can use an emotion engine to analyze user feedback and improve the accuracy of the system.

[0762] This system is composed of three main elements: a server, a terminal, and a user, and uses the following hardware and software:

[0763] Hardware and software used

[0764] 1. Hardware:

[0765] Factory robots (e.g., industrial robots and smartphones)

[0766] 2. Software:

[0767] requests: An HTTP request library for collecting data.

[0768] textblob: A natural language processing library for sentiment analysis

[0769] numpy: A scientific computing library for data analysis

[0770] sklearn: A library that provides machine learning algorithms

[0771] Data collection

[0772] The server collects data on failures and successes from the internet and internal databases, specifically, by acquiring factory operation data and sensor information via API endpoints.

[0773] Data preprocessing and storage

[0774] The collected data is normalized through a data cleansing process and stored in a database. Specific processes of data cleansing include removing noise from text data and standardizing data formats.

[0775] Data analysis

[0776] The server analyzes the data using natural language processing (NLP) and machine learning algorithms, specifically by taking the collected work data and feedback text as input and identifying effective work steps.

[0777] Analysis by emotion engine

[0778] Analyze user feedback text and classify the sentiment. Use the textblob library to identify whether the feedback is positive or negative.

[0779] Formulating success and action plans

[0780] The server extracts the principles of success based on the results of data and sentiment analysis and generates specific action plans, such as "performing regular maintenance" or "optimal procedures for specific tasks," and provides the plan to the user.

[0781] Provision to users

[0782] The user accesses the system using a terminal. The server sends the generated success formula and action plan to the terminal and displays it. The user can check the proposed action plan on the terminal interface.

[0783] Feedback and System Improvement

[0784] After the user executes the action plan, the results are provided to the system as feedback. A specific example of feedback is inputting text such as "This task was very efficient. I would like to continue using this method next time." The emotion engine also analyzes the emotional information contained in this feedback.

[0785] Specific examples

[0786] When a factory robot performs a specific task, the system collects the robot's work data and sensor information, and uses this information to generate a success rule and action plan. When workers enter feedback, they can provide an example prompt such as, "This task was very efficient. I would like to continue using this method next time," which, along with sentiment analysis, can improve the system's accuracy.

[0787] In this way, the system of the present invention can provide a specific method for improving work efficiency and reducing the occurrence of errors within a factory.

[0788] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0789] Step 1:

[0790] Data collection

[0791] The server collects failure and success case data from the internet and internal databases. Specifically, it obtains data such as factory operation data and sensor information through API endpoints. The input is the API endpoint, and the output is the obtained raw data. The server collects data using an HTTP request library (requests).

[0792] Step 2:

[0793] Data preprocessing and storage

[0794] The server cleanses the collected data, removing duplicates and normalizing the data. Specifically, it removes noise from the text data and standardizes the format. The input is raw data, and the output is preprocessed clean data. The server stores this clean data in a database.

[0795] Step 3:

[0796] Data analysis

[0797] The server analyzes the preprocessed data using natural language processing (NLP) techniques and machine learning algorithms. Specifically, it uses the collected work data and feedback text as input to identify patterns and trends in the data. The input is clean data, and the output is the analysis results (patterns and trends). The server performs the analysis using NLP techniques and machine learning libraries (e.g., sklearn).

[0798] Step 4:

[0799] Analysis by emotion engine

[0800] The server collects feedback text from users and classifies its sentiment using an emotion engine. Specifically, it uses a natural language processing library (textblob) to identify whether the feedback is positive or negative. The input is the feedback text, and the output is the sentiment classification result.

[0801] Step 5:

[0802] Formulating success and action plans

[0803] The server extracts success rules based on the results of data analysis and sentiment analysis and generates specific action plans. For example, it suggests "performing regular maintenance" or "optimal procedures for specific tasks." The input is the analysis results and sentiment classification results, and the output is the generated success rules and action plans.

[0804] Step 6:

[0805] Provision to users

[0806] The server sends the generated success formula and action plan to the user's terminal and displays them. The user can check the proposed action plan on the terminal interface. The input is the success formula and action plan, and the output is the display on the user's terminal.

[0807] Step 7:

[0808] Feedback and System Improvement

[0809] After the user executes the action plan, they provide the results to the system as feedback. The server collects this feedback and analyzes it again to improve the accuracy of the system. For example, a user may input feedback such as "This task was very efficient. I would like to continue using this method next time." The input is feedback, and the output is new analysis results and algorithm improvements for the system.

[0810] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0811] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0812] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0813] [Third embodiment]

[0814] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0815] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0816] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0817] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0818] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0819] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0820] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0821] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0822] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0823] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0824] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0825] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0826] The system of the present invention is composed of three main elements: a server, a terminal, and a user. The system collects data on failure cases and success cases, stores it in a database, analyzes it, generates rules for success and specific action plans, and provides them to users. It also collects feedback from users to continuously improve the accuracy of the system.

[0827] Data collection

[0828] The server collects data on success and failure cases from multiple sources, such as the Internet and internal databases. For example, it obtains success and failure cases in project management from public databases on the web, news articles, and specialized papers. The collected data is temporarily stored in the database in raw data form.

[0829] Data preprocessing and storage

[0830] The server preprocesses the collected data, which includes removing duplicates, completing incomplete data, and normalizing the data. The preprocessed data is then stored in a database again, ready for analysis.

[0831] Data analysis

[0832] The server then analyzes the preprocessed data using natural language processing (NLP) techniques and machine learning algorithms. The goal of this analysis is to identify patterns and trends in the data and uncover factors that lead to failures and successes. For example, in project management, it may be discovered that effective communication is the key to success.

[0833] Formulating success and action plans

[0834] The server derives the principles of success based on the results of the data analysis. Based on these principles, it generates a specific action plan. For example, it may formulate an action plan such as "hold regular meetings with stakeholders in the early stages of project planning."

[0835] Provision to users

[0836] The user accesses the system using a terminal. The server sends the generated success formula and action plan to the terminal and displays it to the user. The user can then proceed with their work according to the provided action plan.

[0837] Feedback and System Improvement

[0838] After the user implements the action plan, they provide the results as feedback to the system. For example, they input information such as, "As a result of regular meetings, the project progressed smoothly." The server then re-analyzes the data based on the collected feedback to improve the accuracy of the algorithm and action plan.

[0839] Specific examples

[0840] For example, if a company is trying to bring a new product to market, this system could work as follows:

[0841] Data collection

[0842] The server collects success stories and failure stories of new product launches from the Internet and past data within companies.

[0843] Data preprocessing and storage

[0844] The collected data is normalized through a data cleansing process and stored in a database.

[0845] Data analysis

[0846] Sarver uses natural language processing technology to analyze the data and identify factors that contribute to the success of new product launches. For example, he concludes that it is important to "clarify the target market and implement a well-thought-out marketing strategy."

[0847] Formulating success and action plans

[0848] Based on the results, the server generates a specific action plan, such as "conduct market research, clarify target segments, and then implement an advertising campaign."

[0849] Provision to users

[0850] When a user (a marketing person at a company) logs into the system using a terminal, an action plan proposed by the server is displayed.

[0851] Feedback and System Improvement

[0852] The user executes the action plan and provides feedback on the results to the system. Based on this information, the server updates the algorithm and reflects it in the next analysis, providing more accurate success rules and action plans.

[0853] This system gives companies a concrete way to efficiently and effectively learn from their mistakes and lead to success.

[0854] The processing flow will be explained below.

[0855] Step 1:

[0856] The server collects failure and success data from the internet and internal databases, for example, using web scraping or APIs to retrieve relevant data from blog posts, news articles, research papers, etc.

[0857] Step 2:

[0858] The server preprocesses the collected data, including data cleansing, removing duplicate data, completing incomplete data, and normalizing the data. Specifically, it removes noise from text data (e.g., HTML tags and unnecessary special characters) and standardizes the data format.

[0859] Step 3:

[0860] The server stores the preprocessed data in a case database. Each case contains detailed information such as case ID, date and time, background, and results, and this information is saved in the database.

[0861] Step 4:

[0862] The server analyzes the data in the case database using natural language processing (NLP) techniques and machine learning algorithms, specifically by performing text analysis to identify common patterns and trends among cases and by using clustering algorithms to group related cases.

[0863] Step 5:

[0864] Based on the analysis, the server derives success rules, such as identifying the importance of regular stakeholder feedback for successful project management.

[0865] Step 6:

[0866] The server generates a specific action plan based on the success formula, for example, an action plan that includes the instruction "obtain stakeholder feedback twice by the next milestone."

[0867] Step 7:

[0868] When a user accesses the system using a terminal, the server sends the generated success formula and action plan to the terminal and displays it. The user can check the proposed action plan on the terminal dashboard.

[0869] Step 8:

[0870] The user implements the proposed action plan and provides the results as feedback to the server via the terminal. For example, the user might input information such as, "As a result of obtaining feedback from stakeholders, the project progressed smoothly."

[0871] Step 9:

[0872] The server analyzes the feedback data provided by users to improve the accuracy of the algorithms and action plans, and uses the insights from the feedback to conduct the next data analysis and implement continuous system improvements.

[0873] Example 1

[0874] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0875] In today's business environment, it is important to learn from project successes and failures and develop concrete action plans based on them. However, many organizations do not do this efficiently and face challenges due to the lack of effective feedback loops, making it difficult to utilize this information.

[0876] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0877] In this invention, the server includes means for collecting failure case data and success case data, means for storing the collected failure case data and success case data in a database, means for preprocessing the stored data by deleting duplicate data, completing incomplete data, and normalizing the data, means for analyzing the preprocessed data and identifying patterns and trends using natural language processing technology and machine learning algorithms, means for generating a law of success and a specific action plan based on the identified patterns and trends, means for displaying the generated law of success and action plan on a user's terminal, and means for collecting feedback from users and analyzing the feedback to improve the analysis results and algorithms. This makes it possible to efficiently utilize information obtained from failure cases and success cases to formulate specific action plans and increase business success.

[0878] "Failure case data" refers to data on cases where goals were not achieved in past projects or tasks.

[0879] "Success case data" refers to data on cases where goals were achieved in past projects or tasks.

[0880] "Data collection methods" are methods for obtaining data from multiple sources, such as the Internet and internal company databases.

[0881] "Means for storing in a database" refers to means for storing collected data in a database for easy management and access.

[0882] The "preprocessing means" refers to a means for removing duplicate data from the collected data, completing incomplete data, and normalizing the data.

[0883] "Analysis means" refers to the means of applying natural language processing techniques and machine learning algorithms to pre-processed data to identify patterns and trends in the data.

[0884] The "means for generating rules of success" is a means for extracting rules that lead to success based on the patterns and trends identified by the analysis means.

[0885] A "means for generating an action plan" is a means for formulating specific guidelines and steps for action in accordance with the laws of success.

[0886] The "means for displaying on the user's terminal" refers to a means for visually displaying the generated success law and action plan to the user.

[0887] "Means for collecting feedback" refers to the means for incorporating results and opinions from users after the implementation of an action plan into the system.

[0888] "Means for improving the algorithm" refers to means for analyzing collected feedback and improving the accuracy of the analysis results and generation process.

[0889] The system of this invention is composed of three main elements: a server, a terminal, and a user. The system collects data on failure cases and success cases, stores this data in a database, and performs preprocessing and analysis to generate success rules and specific action plans, which are ultimately provided to the user. It also has a mechanism for collecting user feedback and continuously improving the accuracy of the system.

[0890] Data collection

[0891] The server collects failure and success case data from multiple appropriate data sources, such as the Internet and internal databases. Web scraping tools (e.g., BeautifulSoup or Scrapy) are used for this process. For example, project management success and failure cases are obtained from public databases on the Web, news articles, and specialized papers. The collected data is temporarily stored in a database (e.g., MySQL or PostgreSQL).

[0892] Data preprocessing and storage

[0893] The server preprocesses the collected raw data, using the Pandas library and regular expressions (Regex) to remove duplicates, impute incomplete data, and normalize the data into a standard format. Once preprocessed, the data is stored back in the database, ready for analysis.

[0894] Data analysis

[0895] The server analyzes the preprocessed data using natural language processing (NLP) techniques and machine learning algorithms. This analysis uses NLP libraries such as NLTK and Spacy, and machine learning libraries such as Scikit-learn and TensorFlow. The goal of the analysis is to identify patterns and trends in the data and identify factors behind success and failure. For example, a clustering algorithm can be used to classify similar successful and unsuccessful cases.

[0896] Formulating success and action plans

[0897] The server derives the principles of success based on the results of data analysis. Based on these principles, it generates specific action plans. For example, based on the principle that "regular meetings with stakeholders should be held in the early stages of project planning," it formulates a specific course of action that states "schedule weekly meetings and report on progress."

[0898] Provision to users

[0899] A user accesses the system using a terminal. When the user logs in to the system, the generated success formula and action plan are sent from the server to the terminal. The terminal visually displays this to the user, for example, in an easy-to-understand format through a dashboard.

[0900] Feedback and System Improvement

[0901] When users implement their action plans and provide feedback to the system, the server analyzes the feedback data again. The server analyzes the collected feedback and identifies new patterns and trends. Through this process, the server improves the accuracy of the algorithms and action plans.

[0902] Specific examples

[0903] For example, if a company is trying to bring a new product to market, this system would work as follows:

[0904] The server collects success stories and failure stories of new product launches from the Internet and past data within companies.

[0905] The collected data is normalized through a data cleansing process and stored in a database.

[0906] Sarver uses natural language processing technology to analyze the data and identify factors that contribute to the success of new product launches. For example, he concludes that it is important to "clarify the target market and implement a well-thought-out marketing strategy."

[0907] Based on the results, the server generates a specific action plan, such as "conduct market research, clarify target segments, and then implement an advertising campaign."

[0908] When a user (a marketing person at a company) logs into the system using a terminal, an action plan proposed by the server is displayed.

[0909] The user executes the action plan and provides feedback on the results to the system. Based on this information, the server updates the algorithm and reflects it in the next analysis.

[0910] Prompt Sentence Examples

[0911] Below are some example prompts to input to the generative AI model:

[0912] "Analyze a new product launch. Based on data from successful and unsuccessful cases, generate an action plan for making it a success."

[0913] This system allows companies to efficiently and effectively learn from their mistakes and provides a concrete path to success.

[0914] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0915] Step 1: Data collection

[0916] The server collects data on failures and successes from multiple sources, including the Internet and internal databases. Specifically, it uses web scraping tools (e.g., BeautifulSoup, Scrapy) to obtain data from public databases, news articles, and specialized papers. The collected raw data is temporarily stored in a database (e.g., MySQL, PostgreSQL).

[0917] Input: Information on the Internet, information from internal databases

[0918] Output: Raw data stored in a database

[0919] Step 2: Preprocessing the data

[0920] The server performs data cleansing on the collected raw data. Specifically, it uses the Pandas library to remove duplicate data, complete incomplete data, and normalize the data using regular expressions (Regex). Once preprocessed, the data is stored in the database again.

[0921] Input: Raw data stored in a database

[0922] Output: Data that has been cleansed and normalized

[0923] Step 3: Analyze the data

[0924] The server then analyzes the preprocessed data using natural language processing (NLP) techniques and machine learning algorithms. Using NLP libraries like NLTK and Spacy, and machine learning libraries like Scikit-learn and TensorFlow, the server identifies patterns and trends in the data. This analysis clarifies factors behind success and failure.

[0925] Input: Preprocessed data

[0926] Output: Analysis of factors behind success and failure

[0927] Step 4: Create a success formula and action plan

[0928] The server derives success rules based on the results of the data analysis and generates specific action plans. For example, a success rule may be "hold regular meetings with stakeholders in the early stages of project planning," and specific action guidelines (e.g., setting up weekly meetings) are then formulated based on that.

[0929] Input: Analysis results on factors behind success and failure

[0930] Output: Laws of success and concrete action plans

[0931] Step 5: Provide to users

[0932] The user accesses the system using a terminal and views the generated success formula and action plan. The server sends this information to the terminal, which then visually displays it on a dashboard or other device.

[0933] Input: Laws of success and concrete action plans

[0934] Output: Success formula and action plan displayed on the user's device

[0935] Step 6: Gather feedback and improve the system

[0936] Users input the results of their action plans as feedback into the system, which the server collects and analyzes again, identifying new patterns and trends to refine the algorithms and action plans.

[0937] Input: User feedback

[0938] Output: Updated algorithm and improved action plan

[0939] Through these steps, the system effectively utilizes data on both failure and success cases to provide specific improvement measures, thereby enabling users to increase the success rate of their work.

[0940] (Application example 1)

[0941] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0942] When operating autonomous vehicles, it is necessary to adapt to the environment after starting operation and continuously improve optimal driving patterns and operation methods. Collecting and analyzing data during operation, learning from successes and failures, and providing specific driving methods in real time are particularly challenging. Conventional methods do not efficiently generate executable action plans or improve the system through feedback, preventing improvements to the accuracy of autonomous driving.

[0943] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0944] In this invention, the server includes means for collecting failure case data and success case data, means for storing the collected failure case data and success case data in a database, means for analyzing the stored data and identifying patterns and trends, means for generating a success rule and an action plan based on the identified patterns and trends, means for displaying the generated success rule and action plan on a user's terminal, means for collecting user feedback and improving the analysis results and algorithm, means for collecting sensor data from the autonomous vehicle, means for preprocessing and normalizing the collected sensor data, means for analyzing trends in the data using natural language processing technology and machine learning algorithms, means for generating a success rule and specific operating methods for operating the autonomous vehicle based on the analysis results, means for displaying the generated operating methods on an autonomous vehicle operation management terminal, and means for collecting user feedback on operation results and improving the analysis results and algorithm. This makes it possible to continuously improve the operation accuracy of the autonomous vehicle and provide optimal operation patterns and operating methods in real time.

[0945] "Failure case data" is a record of when an autonomous vehicle did not perform as expected under certain circumstances or conditions.

[0946] "Success data" is a record of an autonomous vehicle performing as expected under specific circumstances or conditions.

[0947] A "database" is an information management system that systematically stores collected data and enables efficient searching and analysis.

[0948] "Pattern and trend identification methods" are techniques and methods used to analyze collected data and find common characteristics or recurring behaviors.

[0949] A "law of success" is a theory that specifies the factors and methodologies that will lead to the success of autonomous vehicles under certain conditions.

[0950] An "action plan" is a plan that outlines specific operational operations and countermeasures that should be implemented based on the principles of success.

[0951] "Means for collecting user feedback" refers to an interface or method by which a user can report the results of operating an autonomous vehicle to the system.

[0952] "Sensor data" refers to data about the surrounding environment and vehicle operation acquired by various sensors (e.g., LiDAR, cameras, radar) installed in autonomous vehicles.

[0953] "Data preprocessing" refers to a series of operations (e.g., missing value imputation, normalization, deduplication) performed on collected data to prepare it in an analyzable format.

[0954] "Natural language processing technology" is a technology that allows computers to understand, analyze, and generate natural language used by humans.

[0955] A "machine learning algorithm" is a mathematical model or method for learning patterns from data and using them to make predictions or classifications.

[0956] An "operation management terminal" is a device or system for managing and displaying the operating status, settings, and operation methods of an autonomous vehicle.

[0957] "Operation result feedback" refers to data that an autonomous vehicle provides back to the system regarding the results and situation it obtains during actual operation.

[0958] The system of this invention is designed to enhance the operation management of autonomous vehicles. This system consists of three main elements: a server, a terminal, and a user.

[0959] Data collection

[0960] The server collects real-time sensor data from the autonomous vehicle's LiDAR, camera, and radar sensors, providing detailed information about the vehicle's behavior and the surrounding environment during operation. This data also includes examples of successful and unsuccessful operations, and the system collects and stores this data in a database.

[0961] Data preprocessing and storage

[0962] The collected raw data is temporarily stored in a database. After that, a data preprocessing process is performed to remove duplicate data, complete incomplete data, and normalize the data. This preprocessed data is then stored in a database again, ready for analysis.

[0963] Data analysis

[0964] The server then analyzes the preprocessed data using natural language processing (NLP) and machine learning algorithms, including Python libraries such as pandas, scikit-learn, and joblib, to identify patterns and trends in the data and identify factors behind failures and successes.

[0965] Formulating success and action plans

[0966] Based on the results of the data analysis, the server derives rules of thumb, generating specific driving patterns and maneuvers, such as specific speed limits and emergency evasive actions. These action plans are further refined using generative AI models.

[0967] User Offerings and Feedback

[0968] The server displays the generated success formula and action plan on the management terminal or engineer's terminal. Users can use this information to manage the settings and operation of the autonomous vehicle. The operation results are fed back to the system by the user, and the server re-analyzes them based on this and improves the accuracy of the algorithm.

[0969] Specific examples

[0970] For example, when an autonomous vehicle is operating within a city, the server collects sensor data and analyzes examples of successful and unsuccessful driving. As a result, a specific action plan is generated, such as "setting the speed limit to 25 km / h in urban areas and automatically avoiding bicycle lanes when approaching them." This action plan is displayed on the terminal, and the operation manager applies it to operate the vehicle. The operation results are fed back to the system, and are reflected in future operations.

[0971] Prompt Sentence Examples

[0972] "This system uses sensor data from autonomous vehicles to identify factors that contribute to operational success and failure, and proposes specific action plans. Specifically, it suggests speed limits and how to avoid emergencies. Please explain the specific process for how this data is collected, analyzed, and used to derive the formula for success."

[0973] In this way, the invention continuously improves the driving accuracy of autonomous vehicles and provides optimal driving patterns and operating methods in real time.

[0974] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0975] Step 1:

[0976] The server collects sensor data in real time from sensor devices (LiDAR, camera, radar) installed in the autonomous vehicle. Raw data (vehicle behavior and surrounding environment during operation) is given as input and temporarily stored in a database. The output is a collection of collected raw data.

[0977] Step 2:

[0978] The server preprocesses the collected raw data. It receives the raw data as input, removes duplicates, completes incomplete data, and normalizes it. Specifically, it uses Python libraries (pandas, scikit-learn) for data cleansing and scaling. The output is a preprocessed, clean dataset.

[0979] Step 3:

[0980] The server analyzes the preprocessed data using natural language processing (NLP) and machine learning algorithms. It takes the preprocessed data as input and uses a Random Forest Classifier to identify patterns and trends in the data. The output is a list of success factors and failure factors as a result of the analysis.

[0981] Step 4:

[0982] The server generates a formula for success and a specific action plan based on the analysis results. It receives the analysis results as input and further refines the action plan using a generative AI model. The output is an action plan that includes specific driving patterns and operation methods. For example, specific instructions such as "set the speed limit to 25 km / h in urban areas" are generated.

[0983] Step 5:

[0984] The server sends the generated success rule and action plan to the terminal and displays it to the user. The server receives the action plan as input and displays it on the operation management terminal. The output is a specific action plan that is displayed on the user's terminal.

[0985] Step 6:

[0986] The user operates the autonomous vehicle based on the provided action plan. The action plan displayed on the terminal is received as input and executed. The output is the driving status and environmental data resulting from the execution.

[0987] Step 7:

[0988] The user inputs the results of the operation into the system as feedback. The system receives operational status and environmental data as input and feeds this back to the server. The output is a set of feedback data.

[0989] Step 8:

[0990] The server re-analyzes the collected feedback data to improve the accuracy of the algorithm. It receives the feedback data as input and re-analyzes it to refine the algorithm. The output is an updated algorithm and an improved action plan.

[0991] Through these steps, the operational accuracy and safety of autonomous vehicles will be continuously improved.

[0992] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0993] The system of the present invention is composed of three main elements: a server, a terminal, and a user. It also incorporates an emotion engine that recognizes the user's emotions. The system collects data on both failure and success cases, stores it in a database, analyzes it, generates rules for success and specific action plans, and provides them to the user. It also collects feedback from users to continuously improve the accuracy of the system. An embodiment of the system is described in detail below.

[0994] Data collection

[0995] The server collects failure and success data from the internet and internal databases, for example, using web scraping or APIs to retrieve relevant data from blog posts, news articles, research papers, etc.

[0996] Data preprocessing and storage

[0997] The server preprocesses the collected data. This includes data cleansing, removing duplicate data, completing incomplete data, and normalizing the data. Specifically, it removes noise from the text data (e.g., HTML tags and unnecessary special characters) and standardizes the data format. The preprocessed data is stored in a case database and is ready for analysis.

[0998] Data analysis

[0999] The server then analyzes the preprocessed data using natural language processing (NLP) techniques and machine learning algorithms. The goal of this analysis is to identify patterns and trends in the data and uncover factors that lead to failures and successes. For example, in project management, it may be discovered that effective communication is the key to success.

[1000] Analysis by emotion engine

[1001] The server includes an emotion engine that recognizes emotions based on user feedback. The emotion engine uses a text analysis algorithm to classify emotions from the user's feedback text. For example, if the user's feedback expresses emotions such as "very satisfied" or "anxious," the emotion information is reflected in the analysis.

[1002] Formulating success and action plans

[1003] The server derives the principles of success based on the results of data analysis and sentiment analysis by the emotion engine. Specific action plans are generated based on the principles of success. For example, an action plan could be formulated that includes holding regular meetings with stakeholders in the early stages of project planning.

[1004] Provision to users

[1005] The user accesses the system using a terminal. The server sends the generated success formula and action plan to the terminal and displays it. The user can check the proposed action plan on the terminal dashboard.

[1006] Feedback and System Improvement

[1007] After a user implements an action plan, they provide the results as feedback to the system. For example, they might enter information like, "As a result of obtaining stakeholder feedback, the project progressed more smoothly." The emotion engine simultaneously analyzes the emotions contained in the feedback. The server then re-analyzes the data based on this feedback, improving the accuracy of the algorithm and action plan.

[1008] Specific examples

[1009] For example, if a company is trying to bring a new product to market, this system could work as follows:

[1010] Data collection

[1011] The server collects success stories and failure stories of new product launches from the Internet and past data within companies.

[1012] Data preprocessing and storage

[1013] The collected data is normalized through a data cleansing process and stored in a case database.

[1014] Data analysis

[1015] Sarver uses natural language processing technology to analyze the data and identify factors that contribute to the success of new product launches. For example, he concludes that it is important to "clarify the target market and implement a well-thought-out marketing strategy."

[1016] Analysis by emotion engine

[1017] When receiving user feedback, the emotion engine classifies emotions such as "satisfaction" or "anxiety" and reflects that emotional data in new analysis.

[1018] Formulating success and action plans

[1019] Based on the results and sentiment data, the server generates a specific action plan: "Conduct market research, clarify target segments, and then implement an advertising campaign."

[1020] Provision to users

[1021] When a user (a marketing person at a company) logs into the system using a terminal, an action plan proposed by the server is displayed.

[1022] Feedback and System Improvement

[1023] The user executes the action plan and provides feedback on the results to the system. Based on this information and emotional data, the server updates the algorithm and reflects it in the next analysis, providing a more accurate formula for success and action plan.

[1024] This system allows companies to efficiently and effectively learn from failures and gain concrete methods to lead to success. It also takes into account user emotions, allowing for more accurate action plans to be formulated.

[1025] The processing flow will be explained below.

[1026] Step 1:

[1027] The server collects failure and success data from the internet and internal databases, for example, using web scraping or APIs to retrieve relevant data from blog posts, news articles, research papers, etc.

[1028] Step 2:

[1029] The server preprocesses the collected data, including data cleansing, removing duplicate data, completing incomplete data, and normalizing the data. Specifically, it removes noise from text data (e.g., HTML tags and unnecessary special characters) and standardizes the data format.

[1030] Step 3:

[1031] The server stores the preprocessed data in a case database, with each case containing detailed information such as case ID, date and time, background, and results.

[1032] Step 4:

[1033] The server analyzes the stored data using natural language processing (NLP) techniques and machine learning algorithms, specifically by performing text analysis to identify common patterns and trends among cases and by using clustering algorithms to group related cases.

[1034] Step 5:

[1035] Based on the analysis, the server derives the principles of success, for example, discovering that effective communication is the key to success in project management.

[1036] Step 6:

[1037] The server generates a specific action plan based on the success formula, for example, an action plan that includes the instruction "obtain stakeholder feedback twice by the next milestone."

[1038] Step 7:

[1039] When a user accesses the system using a terminal, the server sends the generated success formula and action plan to the terminal and displays it. The user can check the proposed action plan on the terminal dashboard.

[1040] Step 8:

[1041] The user executes the proposed action plan and provides the results and emotional feedback to the server via the terminal. For example, the user can input information such as "We were able to obtain stakeholder feedback successfully and the project progressed smoothly" and the emotion "I am satisfied."

[1042] Step 9:

[1043] The server analyzes the feedback and emotional data provided by users to improve the accuracy of algorithms and action plans. It uses insights from the feedback to conduct the next data analysis and implement continuous system improvements. By utilizing an emotional engine, the emotional information contained in user feedback is also reflected in the analysis.

[1044] As a concrete example, we will show how this system works in the marketing strategy of a new product.

[1045] Step 1:

[1046] The server collects success stories and failure stories of new product launches from the Internet and past data within companies.

[1047] Step 2:

[1048] The collected data is cleansed and duplicates are removed, and the text data is then formatted.

[1049] Step 3:

[1050] The server stores the pre-processed data in a database, recording detailed information about each case.

[1051] Step 4:

[1052] The server analyzes the cases in the database and identifies factors that contribute to success. For example, it finds that "clear target market definition and development of marketing strategies" are factors for success.

[1053] Step 5:

[1054] Based on the analysis results, we derive the formula for success: "Clearly define your target market and develop an appropriate advertising campaign."

[1055] Step 6:

[1056] The server generates a specific action plan based on the formula for success, such as "implementing an advertising campaign divided into three steps."

[1057] Step 7:

[1058] When a user (marketer) logs in to a terminal, the server transmits the generated action plan and displays it on the terminal.

[1059] Step 8:

[1060] After implementing the proposed action plan, the user provides the results and emotional feedback to the server via their device. For example, the user inputs "Sales increased as a result of the advertising campaign" and "I am satisfied."

[1061] Step 9:

[1062] The server analyzes the feedback data and emotion data and reflects it in the next data analysis, which improves the accuracy of the next action plan and allows the system to continuously improve.

[1063] Example 2

[1064] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1065] In conventional systems, the processes of collecting, analyzing, and providing users with data on failure and success cases were not efficiently coordinated, making it difficult to formulate specific action plans based on identified patterns and success rules.In addition, it was not possible to incorporate emotional analysis based on user feedback, making it difficult to generate more accurate action plans that reflected emotional information.

[1066] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for collecting failure case data and success case data; means for storing the collected failure case data and success case data in a database; means for preprocessing the stored data to perform data cleansing and for removing and normalizing duplicate data; means for analyzing the preprocessed data using natural language processing technology and machine learning algorithms to identify patterns and trends; means for performing sentiment analysis based on user feedback; means for generating rules for success and action plans based on the identified patterns, trends, and sentiment analysis; means for displaying the generated rules for success and action plans on the user's terminal; and means for collecting user feedback and improving the analysis results and algorithms. This links a series of processes from collection to analysis, provision, and feedback, enabling the generation of more accurate action plans that incorporate user sentiment information.

[1067] "Failure case data" is data that contains detailed information about failed attempts to achieve a particular goal or objective.

[1068] "Success story data" is data that contains detailed information about successful attempts to achieve a particular goal or objective.

[1069] "Means of collection" refers to the methods and techniques used to collect the required information from the Internet and internal databases.

[1070] A "database" is a system for efficiently managing and storing collected data.

[1071] "Preprocessing" refers to tasks such as data cleansing, removing duplicate data, and completing incomplete data to make data easier to analyze.

[1072] "Data cleansing" is the process of removing unnecessary information and errors from data.

[1073] "Deleting duplicate data" refers to the process of organizing and integrating duplicate data of the same content into one piece of data.

[1074] "Normalization" is the process of arranging data into a unified format.

[1075] "Natural language processing technology" is a technology that enables computers to understand and process the natural language used by humans.

[1076] A "machine learning algorithm" is an algorithm that learns patterns and rules based on data and makes predictions and classifications for new data.

[1077] "Means of identifying patterns and trends" refers to methods and techniques for finding common characteristics and trends through data analysis.

[1078] "Feedback" is information provided by a user as a result of an action plan they have implemented.

[1079] "Sentiment analysis" is a technology that identifies and classifies emotions from text data such as user feedback.

[1080] A "law of success" is a principle that indicates a set of effective actions or steps derived from past success stories.

[1081] An "action plan" is a plan that outlines specific actions to be taken based on the laws of success.

[1082] "Display means" refers to a method or technology for visually displaying the generated information and action plan on the user's terminal.

[1083] "Means for improving the algorithm" refers to the technology of adjusting the analysis algorithm based on the collected feedback and reflecting it in the next analysis.

[1084] The system of the present invention is composed of three main elements: a server, a terminal, and a user, and also incorporates an emotion engine that recognizes the user's emotions. The system collects data on both failure and success cases, stores it in a database, analyzes it, generates rules for success and specific action plans, and provides them to the user. It also collects feedback from users to continuously improve the accuracy of the system.

[1085] Hardware and Software Configuration

[1086] Server: The server plays a central role in collecting data, pre-processing, analyzing, generating action plans, providing them to users, and processing feedback.

[1087] Software used:

[1088] Web scraping tools (e.g., Python's BeautifulSoup)

[1089] Database (e.g. MySQL)

[1090] Natural language processing libraries (e.g., spaCy, NLTK)

[1091] Machine learning libraries (e.g., scikit-learn)

[1092] Sentiment analysis models (e.g., HuggingFace Transformers)

[1093] Device: The device that a user uses to access the system and view the action plan. A device can be a laptop, desktop computer, or mobile device.

[1094] User: A person who uses the system to learn from failures and successes and implements specific action plans. The user provides feedback to the system using a terminal.

[1095] Data collection

[1096] The server collects data on failures and successes from the internet and internal company databases, using web scraping tools and APIs with BeautifulSoup to extract the necessary data from related blog posts, news articles, research papers, and other sources.

[1097] Data preprocessing and storage

[1098] The collected data is cleansed on the server, removing duplicates and completing incomplete data. This involves using regular expressions to remove HTML tags and unnecessary special characters and standardize the data format. The preprocessed data is then stored in a database such as MySQL and prepared for analysis.

[1099] Data analysis

[1100] The server performs analysis using natural language processing techniques and machine learning algorithms. Specifically, it uses spaCy and NLTK to tokenize text data, tag parts of speech, and perform dependency analysis, and then uses scikit-learn algorithms to identify patterns and trends in the data. The goal of the analysis is to identify factors behind failures and successes.

[1101] Analysis by emotion engine

[1102] The server has a built-in emotion engine that recognizes emotions based on user feedback. Using HuggingFace's Transformers library, a text analysis algorithm classifies emotions from user feedback text and extracts emotions such as "satisfied" or "anxious."

[1103] Formulating success and action plans

[1104] The server derives success rules based on the results of data analysis and sentiment analysis, generating specific action plans such as "hold regular meetings with stakeholders in the early stages of project planning."

[1105] Provision to users

[1106] The user accesses the system using a terminal. The server sends the generated success formula and action plan to the terminal and displays it on the dashboard. The user can check the proposed action plan and implement it as necessary.

[1107] Feedback and System Improvement

[1108] After the user implements the action plan, they provide the results as feedback to the system. For example, they might enter information like, "After meeting with stakeholders, the project progressed smoothly." The server analyzes this feedback and updates the algorithm to improve the accuracy of the next analysis.

[1109] Examples of concrete examples and prompts

[1110] For example, consider the case of a new product launch. The server uses BeautifulSoup to collect successful and unsuccessful cases of new product launches from the Internet. The collected data is cleansed and normalized using pandas and stored in a MySQL database. The server analyzes the data using spaCy and identifies success factors using a classification algorithm in scikit-learn. An emotion engine extracts emotions from user feedback, and the server ultimately generates a specific action plan, such as "conduct market research, identify target segments, and then launch an advertising campaign." The user then checks this action plan on their device and provides feedback to the system after the plan is implemented.

[1111] Examples of prompts include:

[1112] "Collect and analyze success stories and failures in bringing new products to market, and create a concrete action plan to lead to success."

[1113] This system allows companies to efficiently and effectively learn from failure and gain concrete methods to lead to success. It also allows for the formulation of more accurate action plans by reflecting user emotions.

[1114] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1115] Step 1:

[1116] Data collection

[1117] The server collects data on failures and successes. Specifically, it uses Python's BeautifulSoup to scrape relevant web pages and obtain text data on failures and successes. It also uses APIs to extract data from blog posts, news articles, research papers, etc. The input is a URL or API endpoint, and the output is the raw data obtained.

[1118] Step 2:

[1119] Data preprocessing and storage

[1120] The server cleanses the collected data and normalizes it into a unified format. Specifically, it uses regular expressions to remove HTML tags and special characters, and converts it into a data frame using the pandas library. The input is raw data, and the output is cleansed, standardized data. The processed data is stored in a MySQL database.

[1121] Step 3:

[1122] Data analysis

[1123] The server analyzes the preprocessed data using natural language processing techniques and machine learning algorithms. Specifically, it uses spaCy to tokenize the text data and analyze basic linguistic structures (part-of-speech tagging, dependency analysis). It then applies classification models using scikit-learn algorithms to identify patterns and trends in the data. The input is the cleansed data, and the output is the analysis results (identified patterns and trends).

[1124] Step 4:

[1125] Analysis by emotion engine

[1126] The server uses an emotion engine to recognize emotions from user feedback. Specifically, it uses the Transformers library in HuggingFace to analyze the feedback text and classify emotions such as "satisfied," "anxious," and "excited." The input is the feedback text, and the output is the extracted emotion data.

[1127] Step 5:

[1128] Formulating success and action plans

[1129] The server derives success rules based on the results of data analysis and sentiment analysis. Specifically, it integrates the analysis results from the scikit-learn algorithm with sentiment data and formulates specific action plans based on successful examples of project management. For example, it generates a plan such as "hold regular meetings with stakeholders in the early stages of project planning." The input is the analysis results and sentiment data, and the output is a specific action plan.

[1130] Step 6:

[1131] Provision to users

[1132] Users access the system using their devices. The server sends the generated success formula and action plan to the user's device and displays it on a dashboard. Specifically, the user can view the action plan on a web page or mobile application. The input is the generated action plan, and the output is the action plan displayed on the user's device.

[1133] Step 7:

[1134] Feedback and System Improvement

[1135] Users provide feedback to the system on the results of their action plans. Specifically, they access a feedback form from their device and enter the results and their emotions. The server receives this feedback, analyzes it using an emotion engine, and then updates the algorithm using scikit-learn. The input is the user's feedback, and the output is the updated analysis algorithm.

[1136] This system allows companies to learn from both success and failure and develop specific action plans to lead to success. Furthermore, incorporating user emotional data makes it possible to generate more accurate action plans.

[1137] (Application example 2)

[1138] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1139] Conventional systems were able to collect and analyze data on both failure and success cases and generate action plans, but there was no concrete method for utilizing this data in in-factory robot control to improve work efficiency and reduce the occurrence of errors. Furthermore, there was a lack of a mechanism for evaluating user feedback based on sentiment analysis and improving analysis accuracy. Therefore, a means to further improve work efficiency in factories was needed.

[1140] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1141] In this invention, the server includes means for collecting failure case data and success case data, means for storing the collected failure case data and success case data in a database, means for analyzing the stored data and identifying patterns and trends, means for generating rules for success and action plans based on the identified patterns and trends, means for displaying the generated rules for success and action plans on a user's terminal, means for collecting user feedback and improving the analysis results and algorithms, means including a robot for collecting work data and sensor information, means for executing a machine learning algorithm based on the collected data, and means for classifying emotions from user feedback text, thereby enabling work efficiency in factories and reducing the occurrence of errors.

[1142] "Failure Data" is information relating to instances where a particular task or project did not achieve the expected results.

[1143] "Success Data" is information relating to instances where an expected result was achieved in a particular task or project.

[1144] A "database" is a structured collection of information for storing and managing collected data.

[1145] A "pattern or trend" is an element that indicates a consistent structure or variation in the data, or a set of regularities found in the data.

[1146] A "law of success" is a proven guideline or principle for achieving success under specific circumstances or conditions.

[1147] An "action plan" is a plan that details the specific actions or steps to be taken to achieve a goal.

[1148] "User terminal" refers to the device (e.g., smartphone, tablet, or PC) used by the user to access the system and view the displayed information.

[1149] "Feedback" is information provided by a user by inputting the results and impressions of the action plan they have implemented.

[1150] "Work data" is information about the performance of robots and workers in the factory.

[1151] "Sensor information" is data used to monitor the environment within the factory and the status of robots in real time.

[1152] A "machine learning algorithm" is a computational method for analyzing large amounts of data, discovering patterns within it, and making predictions and classifications.

[1153] "Feedback text" is a written expression of opinions and thoughts that a user inputs into the system.

[1154] A "sentiment classifier" is a technique for identifying and classifying emotions such as positive, negative, or neutral from feedback text.

[1155] The system of the present invention collects and analyzes data on both failure and success cases, generates rules for success and specific action plans, and provides them to users. Furthermore, it can use an emotion engine to analyze user feedback and improve the accuracy of the system.

[1156] This system is composed of three main elements: a server, a terminal, and a user, and uses the following hardware and software:

[1157] Hardware and software used

[1158] 1. Hardware:

[1159] Factory robots (e.g., industrial robots and smartphones)

[1160] 2. Software:

[1161] requests: An HTTP request library for collecting data.

[1162] textblob: A natural language processing library for sentiment analysis

[1163] numpy: A scientific computing library for data analysis

[1164] sklearn: A library that provides machine learning algorithms

[1165] Data collection

[1166] The server collects data on failures and successes from the internet and internal databases, specifically, by acquiring factory operation data and sensor information via API endpoints.

[1167] Data preprocessing and storage

[1168] The collected data is normalized through a data cleansing process and stored in a database. Specific processes of data cleansing include removing noise from text data and standardizing data formats.

[1169] Data analysis

[1170] The server analyzes the data using natural language processing (NLP) and machine learning algorithms, specifically by taking the collected work data and feedback text as input and identifying effective work steps.

[1171] Analysis by emotion engine

[1172] Analyze user feedback text and classify the sentiment. Use the textblob library to identify whether the feedback is positive or negative.

[1173] Formulating success and action plans

[1174] The server extracts the principles of success based on the results of data and sentiment analysis and generates specific action plans, such as "performing regular maintenance" or "optimal procedures for specific tasks," and provides the plan to the user.

[1175] Provision to users

[1176] The user accesses the system using a terminal. The server sends the generated success formula and action plan to the terminal and displays it. The user can check the proposed action plan on the terminal interface.

[1177] Feedback and System Improvement

[1178] After the user executes the action plan, the results are provided to the system as feedback. A specific example of feedback is inputting text such as "This task was very efficient. I would like to continue using this method next time." The emotion engine also analyzes the emotional information contained in this feedback.

[1179] Specific examples

[1180] When a factory robot performs a specific task, the system collects the robot's work data and sensor information, and uses this information to generate a success rule and action plan. When workers enter feedback, they can provide an example prompt such as, "This task was very efficient. I would like to continue using this method next time," which, along with sentiment analysis, can improve the system's accuracy.

[1181] In this way, the system of the present invention can provide a specific method for improving work efficiency and reducing the occurrence of errors within a factory.

[1182] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1183] Step 1:

[1184] Data collection

[1185] The server collects failure and success case data from the internet and internal databases. Specifically, it obtains data such as factory operation data and sensor information through API endpoints. The input is the API endpoint, and the output is the obtained raw data. The server collects data using an HTTP request library (requests).

[1186] Step 2:

[1187] Data preprocessing and storage

[1188] The server cleanses the collected data, removing duplicates and normalizing the data. Specifically, it removes noise from the text data and standardizes the format. The input is raw data, and the output is preprocessed clean data. The server stores this clean data in a database.

[1189] Step 3:

[1190] Data analysis

[1191] The server analyzes the preprocessed data using natural language processing (NLP) techniques and machine learning algorithms. Specifically, it uses the collected work data and feedback text as input to identify patterns and trends in the data. The input is clean data, and the output is the analysis results (patterns and trends). The server performs the analysis using NLP techniques and machine learning libraries (e.g., sklearn).

[1192] Step 4:

[1193] Analysis by emotion engine

[1194] The server collects feedback text from users and classifies its sentiment using an emotion engine. Specifically, it uses a natural language processing library (textblob) to identify whether the feedback is positive or negative. The input is the feedback text, and the output is the sentiment classification result.

[1195] Step 5:

[1196] Formulating success and action plans

[1197] The server extracts success rules based on the results of data analysis and sentiment analysis and generates specific action plans. For example, it suggests "performing regular maintenance" or "optimal procedures for specific tasks." The input is the analysis results and sentiment classification results, and the output is the generated success rules and action plans.

[1198] Step 6:

[1199] Provision to users

[1200] The server sends the generated success formula and action plan to the user's terminal and displays them. The user can check the proposed action plan on the terminal interface. The input is the success formula and action plan, and the output is the display on the user's terminal.

[1201] Step 7:

[1202] Feedback and System Improvement

[1203] After the user executes the action plan, they provide the results to the system as feedback. The server collects this feedback and analyzes it again to improve the accuracy of the system. For example, a user may input feedback such as "This task was very efficient. I would like to continue using this method next time." The input is feedback, and the output is new analysis results and algorithm improvements for the system.

[1204] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1205] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1206] 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 the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1207] [Fourth embodiment]

[1208] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1209] 7, a 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.

[1210] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1211] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1212] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1213] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1214] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1215] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1216] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1217] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1218] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1219] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1220] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1221] The system of the present invention is composed of three main elements: a server, a terminal, and a user. The system collects data on failure cases and success cases, stores it in a database, analyzes it, generates rules for success and specific action plans, and provides them to users. It also collects feedback from users to continuously improve the accuracy of the system.

[1222] Data collection

[1223] The server collects data on success and failure cases from multiple sources, such as the Internet and internal databases. For example, it obtains success and failure cases in project management from public databases on the web, news articles, and specialized papers. The collected data is temporarily stored in the database in raw data form.

[1224] Data preprocessing and storage

[1225] The server preprocesses the collected data, which includes removing duplicates, completing incomplete data, and normalizing the data. The preprocessed data is then stored in a database again, ready for analysis.

[1226] Data analysis

[1227] The server then analyzes the preprocessed data using natural language processing (NLP) techniques and machine learning algorithms. The goal of this analysis is to identify patterns and trends in the data and uncover factors that lead to failures and successes. For example, in project management, it may be discovered that effective communication is the key to success.

[1228] Formulating success and action plans

[1229] The server derives the principles of success based on the results of the data analysis. Based on these principles, it generates a specific action plan. For example, it may formulate an action plan such as "hold regular meetings with stakeholders in the early stages of project planning."

[1230] Provision to users

[1231] The user accesses the system using a terminal. The server sends the generated success formula and action plan to the terminal and displays it to the user. The user can then proceed with their work according to the provided action plan.

[1232] Feedback and System Improvement

[1233] After the user implements the action plan, they provide the results as feedback to the system. For example, they input information such as, "As a result of regular meetings, the project progressed smoothly." The server then re-analyzes the data based on the collected feedback to improve the accuracy of the algorithm and action plan.

[1234] Specific examples

[1235] For example, if a company is trying to bring a new product to market, this system could work as follows:

[1236] Data collection

[1237] The server collects success stories and failure stories of new product launches from the Internet and past data within companies.

[1238] Data preprocessing and storage

[1239] The collected data is normalized through a data cleansing process and stored in a database.

[1240] Data analysis

[1241] Sarver uses natural language processing technology to analyze the data and identify factors that contribute to the success of new product launches. For example, he concludes that it is important to "clarify the target market and implement a well-thought-out marketing strategy."

[1242] Formulating success and action plans

[1243] Based on the results, the server generates a specific action plan, such as "conduct market research, clarify target segments, and then implement an advertising campaign."

[1244] Provision to users

[1245] When a user (a marketing person at a company) logs into the system using a terminal, an action plan proposed by the server is displayed.

[1246] Feedback and System Improvement

[1247] The user executes the action plan and provides feedback on the results to the system. Based on this information, the server updates the algorithm and reflects it in the next analysis, providing more accurate success rules and action plans.

[1248] This system gives companies a concrete way to efficiently and effectively learn from their mistakes and lead to success.

[1249] The processing flow will be explained below.

[1250] Step 1:

[1251] The server collects failure and success data from the internet and internal databases, for example, using web scraping or APIs to retrieve relevant data from blog posts, news articles, research papers, etc.

[1252] Step 2:

[1253] The server preprocesses the collected data, including data cleansing, removing duplicate data, completing incomplete data, and normalizing the data. Specifically, it removes noise from text data (e.g., HTML tags and unnecessary special characters) and standardizes the data format.

[1254] Step 3:

[1255] The server stores the preprocessed data in a case database. Each case contains detailed information such as case ID, date and time, background, and results, and this information is saved in the database.

[1256] Step 4:

[1257] The server analyzes the data in the case database using natural language processing (NLP) techniques and machine learning algorithms, specifically by performing text analysis to identify common patterns and trends among cases and by using clustering algorithms to group related cases.

[1258] Step 5:

[1259] Based on the analysis, the server derives success rules, such as identifying the importance of regular stakeholder feedback for successful project management.

[1260] Step 6:

[1261] The server generates a specific action plan based on the success formula, for example, an action plan that includes the instruction "obtain stakeholder feedback twice by the next milestone."

[1262] Step 7:

[1263] When a user accesses the system using a terminal, the server sends the generated success formula and action plan to the terminal and displays it. The user can check the proposed action plan on the terminal dashboard.

[1264] Step 8:

[1265] The user implements the proposed action plan and provides the results as feedback to the server via the terminal. For example, the user might input information such as, "As a result of obtaining feedback from stakeholders, the project progressed smoothly."

[1266] Step 9:

[1267] The server analyzes the feedback data provided by users to improve the accuracy of the algorithms and action plans, and uses the insights from the feedback to conduct the next data analysis and implement continuous system improvements.

[1268] Example 1

[1269] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1270] In today's business environment, it is important to learn from project successes and failures and develop concrete action plans based on them. However, many organizations do not do this efficiently and face challenges due to the lack of effective feedback loops, making it difficult to utilize this information.

[1271] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1272] In this invention, the server includes means for collecting failure case data and success case data, means for storing the collected failure case data and success case data in a database, means for preprocessing the stored data by deleting duplicate data, completing incomplete data, and normalizing the data, means for analyzing the preprocessed data and identifying patterns and trends using natural language processing technology and machine learning algorithms, means for generating a law of success and a specific action plan based on the identified patterns and trends, means for displaying the generated law of success and action plan on a user's terminal, and means for collecting feedback from users and analyzing the feedback to improve the analysis results and algorithms. This makes it possible to efficiently utilize information obtained from failure cases and success cases to formulate specific action plans and increase business success.

[1273] "Failure case data" refers to data on cases where goals were not achieved in past projects or tasks.

[1274] "Success case data" refers to data on cases where goals were achieved in past projects or tasks.

[1275] "Data collection methods" are methods for obtaining data from multiple sources, such as the Internet and internal company databases.

[1276] "Means for storing in a database" refers to means for storing collected data in a database for easy management and access.

[1277] The "preprocessing means" refers to a means for removing duplicate data from the collected data, completing incomplete data, and normalizing the data.

[1278] "Analysis means" refers to the means of applying natural language processing techniques and machine learning algorithms to pre-processed data to identify patterns and trends in the data.

[1279] The "means for generating rules of success" is a means for extracting rules that lead to success based on the patterns and trends identified by the analysis means.

[1280] A "means for generating an action plan" is a means for formulating specific guidelines and steps for action in accordance with the laws of success.

[1281] The "means for displaying on the user's terminal" refers to a means for visually displaying the generated success law and action plan to the user.

[1282] "Means for collecting feedback" refers to the means for incorporating results and opinions from users after the implementation of an action plan into the system.

[1283] "Means for improving the algorithm" refers to means for analyzing collected feedback and improving the accuracy of the analysis results and generation process.

[1284] The system of this invention is composed of three main elements: a server, a terminal, and a user. The system collects data on failure cases and success cases, stores this data in a database, and performs preprocessing and analysis to generate success rules and specific action plans, which are ultimately provided to the user. It also has a mechanism for collecting user feedback and continuously improving the accuracy of the system.

[1285] Data collection

[1286] The server collects failure and success case data from multiple appropriate data sources, such as the Internet and internal databases. Web scraping tools (e.g., BeautifulSoup or Scrapy) are used for this process. For example, project management success and failure cases are obtained from public databases on the Web, news articles, and specialized papers. The collected data is temporarily stored in a database (e.g., MySQL or PostgreSQL).

[1287] Data preprocessing and storage

[1288] The server preprocesses the collected raw data, using the Pandas library and regular expressions (Regex) to remove duplicates, impute incomplete data, and normalize the data into a standard format. Once preprocessed, the data is stored back in the database, ready for analysis.

[1289] Data analysis

[1290] The server analyzes the preprocessed data using natural language processing (NLP) techniques and machine learning algorithms. This analysis uses NLP libraries such as NLTK and Spacy, and machine learning libraries such as Scikit-learn and TensorFlow. The goal of the analysis is to identify patterns and trends in the data and identify factors behind success and failure. For example, a clustering algorithm can be used to classify similar successful and unsuccessful cases.

[1291] Formulating success and action plans

[1292] The server derives the principles of success based on the results of data analysis. Based on these principles, it generates specific action plans. For example, based on the principle that "regular meetings with stakeholders should be held in the early stages of project planning," it formulates a specific course of action that states "schedule weekly meetings and report on progress."

[1293] Provision to users

[1294] A user accesses the system using a terminal. When the user logs in to the system, the generated success formula and action plan are sent from the server to the terminal. The terminal visually displays this to the user, for example, in an easy-to-understand format through a dashboard.

[1295] Feedback and System Improvement

[1296] When users implement their action plans and provide feedback to the system, the server analyzes the feedback data again. The server analyzes the collected feedback and identifies new patterns and trends. Through this process, the server improves the accuracy of the algorithms and action plans.

[1297] Specific examples

[1298] For example, if a company is trying to bring a new product to market, this system would work as follows:

[1299] The server collects success stories and failure stories of new product launches from the Internet and past data within companies.

[1300] The collected data is normalized through a data cleansing process and stored in a database.

[1301] Sarver uses natural language processing technology to analyze the data and identify factors that contribute to the success of new product launches. For example, he concludes that it is important to "clarify the target market and implement a well-thought-out marketing strategy."

[1302] Based on the results, the server generates a specific action plan, such as "conduct market research, clarify target segments, and then implement an advertising campaign."

[1303] When a user (a marketing person at a company) logs into the system using a terminal, an action plan proposed by the server is displayed.

[1304] The user executes the action plan and provides feedback on the results to the system. Based on this information, the server updates the algorithm and reflects it in the next analysis.

[1305] Prompt Sentence Examples

[1306] Below are some example prompts to input to the generative AI model:

[1307] "Analyze a new product launch. Based on data from successful and unsuccessful cases, generate an action plan for making it a success."

[1308] This system allows companies to efficiently and effectively learn from their mistakes and provides a concrete path to success.

[1309] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1310] Step 1: Data collection

[1311] The server collects data on failures and successes from multiple sources, including the Internet and internal databases. Specifically, it uses web scraping tools (e.g., BeautifulSoup, Scrapy) to obtain data from public databases, news articles, and specialized papers. The collected raw data is temporarily stored in a database (e.g., MySQL, PostgreSQL).

[1312] Input: Information on the Internet, information from internal databases

[1313] Output: Raw data stored in a database

[1314] Step 2: Preprocessing the data

[1315] The server performs data cleansing on the collected raw data. Specifically, it uses the Pandas library to remove duplicate data, complete incomplete data, and normalize the data using regular expressions (Regex). Once preprocessed, the data is stored in the database again.

[1316] Input: Raw data stored in a database

[1317] Output: Data that has been cleansed and normalized

[1318] Step 3: Analyze the data

[1319] The server then analyzes the preprocessed data using natural language processing (NLP) techniques and machine learning algorithms. Using NLP libraries like NLTK and Spacy, and machine learning libraries like Scikit-learn and TensorFlow, the server identifies patterns and trends in the data. This analysis clarifies factors behind success and failure.

[1320] Input: Preprocessed data

[1321] Output: Analysis of factors behind success and failure

[1322] Step 4: Create a success formula and action plan

[1323] The server derives success rules based on the results of the data analysis and generates specific action plans. For example, a success rule may be "hold regular meetings with stakeholders in the early stages of project planning," and specific action guidelines (e.g., setting up weekly meetings) are then formulated based on that.

[1324] Input: Analysis results on factors behind success and failure

[1325] Output: Laws of success and concrete action plans

[1326] Step 5: Provide to users

[1327] The user accesses the system using a terminal and views the generated success formula and action plan. The server sends this information to the terminal, which then visually displays it on a dashboard or other device.

[1328] Input: Laws of success and concrete action plans

[1329] Output: Success formula and action plan displayed on the user's device

[1330] Step 6: Gather feedback and improve the system

[1331] Users input the results of their action plans as feedback into the system, which the server collects and analyzes again, identifying new patterns and trends to refine the algorithms and action plans.

[1332] Input: User feedback

[1333] Output: Updated algorithm and improved action plan

[1334] Through these steps, the system effectively utilizes data on both failure and success cases to provide specific improvement measures, thereby enabling users to increase the success rate of their work.

[1335] (Application example 1)

[1336] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1337] When operating autonomous vehicles, it is necessary to adapt to the environment after starting operation and continuously improve optimal driving patterns and operation methods. Collecting and analyzing data during operation, learning from successes and failures, and providing specific driving methods in real time are particularly challenging. Conventional methods do not efficiently generate executable action plans or improve the system through feedback, preventing improvements to the accuracy of autonomous driving.

[1338] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1339] In this invention, the server includes means for collecting failure case data and success case data, means for storing the collected failure case data and success case data in a database, means for analyzing the stored data and identifying patterns and trends, means for generating a success rule and an action plan based on the identified patterns and trends, means for displaying the generated success rule and action plan on a user's terminal, means for collecting user feedback and improving the analysis results and algorithm, means for collecting sensor data from the autonomous vehicle, means for preprocessing and normalizing the collected sensor data, means for analyzing trends in the data using natural language processing technology and machine learning algorithms, means for generating a success rule and specific operating methods for operating the autonomous vehicle based on the analysis results, means for displaying the generated operating methods on an autonomous vehicle operation management terminal, and means for collecting user feedback on operation results and improving the analysis results and algorithm. This makes it possible to continuously improve the operation accuracy of the autonomous vehicle and provide optimal operation patterns and operating methods in real time.

[1340] "Failure case data" is a record of when an autonomous vehicle did not perform as expected under certain circumstances or conditions.

[1341] "Success data" is a record of an autonomous vehicle performing as expected under specific circumstances or conditions.

[1342] A "database" is an information management system that systematically stores collected data and enables efficient searching and analysis.

[1343] "Pattern and trend identification methods" are techniques and methods used to analyze collected data and find common characteristics or recurring behaviors.

[1344] A "law of success" is a theory that specifies the factors and methodologies that will lead to the success of autonomous vehicles under certain conditions.

[1345] An "action plan" is a plan that outlines specific operational operations and countermeasures that should be implemented based on the principles of success.

[1346] "Means for collecting user feedback" refers to an interface or method by which a user can report the results of operating an autonomous vehicle to the system.

[1347] "Sensor data" refers to data about the surrounding environment and vehicle operation acquired by various sensors (e.g., LiDAR, cameras, radar) installed in autonomous vehicles.

[1348] "Data preprocessing" refers to a series of operations (e.g., missing value imputation, normalization, deduplication) performed on collected data to prepare it in an analyzable format.

[1349] "Natural language processing technology" is a technology that allows computers to understand, analyze, and generate natural language used by humans.

[1350] A "machine learning algorithm" is a mathematical model or method for learning patterns from data and using them to make predictions or classifications.

[1351] An "operation management terminal" is a device or system for managing and displaying the operating status, settings, and operation methods of an autonomous vehicle.

[1352] "Operation result feedback" refers to data that an autonomous vehicle provides back to the system regarding the results and situation it obtains during actual operation.

[1353] The system of this invention is designed to enhance the operation management of autonomous vehicles. This system consists of three main elements: a server, a terminal, and a user.

[1354] Data collection

[1355] The server collects real-time sensor data from the autonomous vehicle's LiDAR, camera, and radar sensors, providing detailed information about the vehicle's behavior and the surrounding environment during operation. This data also includes examples of successful and unsuccessful operations, and the system collects and stores this data in a database.

[1356] Data preprocessing and storage

[1357] The collected raw data is temporarily stored in a database. After that, a data preprocessing process is performed to remove duplicate data, complete incomplete data, and normalize the data. This preprocessed data is then stored in a database again, ready for analysis.

[1358] Data analysis

[1359] The server then analyzes the preprocessed data using natural language processing (NLP) and machine learning algorithms, including Python libraries such as pandas, scikit-learn, and joblib, to identify patterns and trends in the data and identify factors behind failures and successes.

[1360] Formulating success and action plans

[1361] Based on the results of the data analysis, the server derives rules of thumb, generating specific driving patterns and maneuvers, such as specific speed limits and emergency evasive actions. These action plans are further refined using generative AI models.

[1362] User Offerings and Feedback

[1363] The server displays the generated success formula and action plan on the management terminal or engineer's terminal. Users can use this information to manage the settings and operation of the autonomous vehicle. The operation results are fed back to the system by the user, and the server re-analyzes them based on this and improves the accuracy of the algorithm.

[1364] Specific examples

[1365] For example, when an autonomous vehicle is operating within a city, the server collects sensor data and analyzes examples of successful and unsuccessful driving. As a result, a specific action plan is generated, such as "setting the speed limit to 25 km / h in urban areas and automatically avoiding bicycle lanes when approaching them." This action plan is displayed on the terminal, and the operation manager applies it to operate the vehicle. The operation results are fed back to the system, and are reflected in future operations.

[1366] Prompt Sentence Examples

[1367] "This system uses sensor data from autonomous vehicles to identify factors that contribute to operational success and failure, and proposes specific action plans. Specifically, it suggests speed limits and how to avoid emergencies. Please explain the specific process for how this data is collected, analyzed, and used to derive the formula for success."

[1368] In this way, the invention continuously improves the driving accuracy of autonomous vehicles and provides optimal driving patterns and operating methods in real time.

[1369] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1370] Step 1:

[1371] The server collects sensor data in real time from sensor devices (LiDAR, camera, radar) installed in the autonomous vehicle. Raw data (vehicle behavior and surrounding environment during operation) is given as input and temporarily stored in a database. The output is a collection of collected raw data.

[1372] Step 2:

[1373] The server preprocesses the collected raw data. It receives the raw data as input, removes duplicates, completes incomplete data, and normalizes it. Specifically, it uses Python libraries (pandas, scikit-learn) for data cleansing and scaling. The output is a preprocessed, clean dataset.

[1374] Step 3:

[1375] The server analyzes the preprocessed data using natural language processing (NLP) and machine learning algorithms. It takes the preprocessed data as input and uses a Random Forest Classifier to identify patterns and trends in the data. The output is a list of success factors and failure factors as a result of the analysis.

[1376] Step 4:

[1377] The server generates a formula for success and a specific action plan based on the analysis results. It receives the analysis results as input and further refines the action plan using a generative AI model. The output is an action plan that includes specific driving patterns and operation methods. For example, specific instructions such as "set the speed limit to 25 km / h in urban areas" are generated.

[1378] Step 5:

[1379] The server sends the generated success rule and action plan to the terminal and displays it to the user. The server receives the action plan as input and displays it on the operation management terminal. The output is a specific action plan that is displayed on the user's terminal.

[1380] Step 6:

[1381] The user operates the autonomous vehicle based on the provided action plan. The action plan displayed on the terminal is received as input and executed. The output is the driving status and environmental data resulting from the execution.

[1382] Step 7:

[1383] The user inputs the results of the operation into the system as feedback. The system receives operational status and environmental data as input and feeds this back to the server. The output is a set of feedback data.

[1384] Step 8:

[1385] The server re-analyzes the collected feedback data to improve the accuracy of the algorithm. It receives the feedback data as input and re-analyzes it to refine the algorithm. The output is an updated algorithm and an improved action plan.

[1386] Through these steps, the operational accuracy and safety of autonomous vehicles will be continuously improved.

[1387] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1388] The system of the present invention is composed of three main elements: a server, a terminal, and a user. It also incorporates an emotion engine that recognizes the user's emotions. The system collects data on both failure and success cases, stores it in a database, analyzes it, generates rules for success and specific action plans, and provides them to the user. It also collects feedback from users to continuously improve the accuracy of the system. An embodiment of the system is described in detail below.

[1389] Data collection

[1390] The server collects failure and success data from the internet and internal databases, for example, using web scraping or APIs to retrieve relevant data from blog posts, news articles, research papers, etc.

[1391] Data preprocessing and storage

[1392] The server preprocesses the collected data. This includes data cleansing, removing duplicate data, completing incomplete data, and normalizing the data. Specifically, it removes noise from the text data (e.g., HTML tags and unnecessary special characters) and standardizes the data format. The preprocessed data is stored in a case database and is ready for analysis.

[1393] Data analysis

[1394] The server then analyzes the preprocessed data using natural language processing (NLP) techniques and machine learning algorithms. The goal of this analysis is to identify patterns and trends in the data and uncover factors that lead to failures and successes. For example, in project management, it may be discovered that effective communication is the key to success.

[1395] Analysis by emotion engine

[1396] The server includes an emotion engine that recognizes emotions based on user feedback. The emotion engine uses a text analysis algorithm to classify emotions from the user's feedback text. For example, if the user's feedback expresses emotions such as "very satisfied" or "anxious," the emotion information is reflected in the analysis.

[1397] Formulating success and action plans

[1398] The server derives the principles of success based on the results of data analysis and sentiment analysis by the emotion engine. Specific action plans are generated based on the principles of success. For example, an action plan could be formulated that includes holding regular meetings with stakeholders in the early stages of project planning.

[1399] Provision to users

[1400] The user accesses the system using a terminal. The server sends the generated success formula and action plan to the terminal and displays it. The user can check the proposed action plan on the terminal dashboard.

[1401] Feedback and System Improvement

[1402] After a user implements an action plan, they provide the results as feedback to the system. For example, they might enter information like, "As a result of obtaining stakeholder feedback, the project progressed more smoothly." The emotion engine simultaneously analyzes the emotions contained in the feedback. The server then re-analyzes the data based on this feedback, improving the accuracy of the algorithm and action plan.

[1403] Specific examples

[1404] For example, if a company is trying to bring a new product to market, this system could work as follows:

[1405] Data collection

[1406] The server collects success stories and failure stories of new product launches from the Internet and past data within companies.

[1407] Data preprocessing and storage

[1408] The collected data is normalized through a data cleansing process and stored in a case database.

[1409] Data analysis

[1410] Sarver uses natural language processing technology to analyze the data and identify factors that contribute to the success of new product launches. For example, he concludes that it is important to "clarify the target market and implement a well-thought-out marketing strategy."

[1411] Analysis by emotion engine

[1412] When receiving user feedback, the emotion engine classifies emotions such as "satisfaction" or "anxiety" and reflects that emotional data in new analysis.

[1413] Formulating success and action plans

[1414] Based on the results and sentiment data, the server generates a specific action plan: "Conduct market research, clarify target segments, and then implement an advertising campaign."

[1415] Provision to users

[1416] When a user (a marketing person at a company) logs into the system using a terminal, an action plan proposed by the server is displayed.

[1417] Feedback and System Improvement

[1418] The user executes the action plan and provides feedback on the results to the system. Based on this information and emotional data, the server updates the algorithm and reflects it in the next analysis, providing a more accurate formula for success and action plan.

[1419] This system allows companies to efficiently and effectively learn from failures and gain concrete methods to lead to success. It also takes into account user emotions, allowing for more accurate action plans to be formulated.

[1420] The processing flow will be explained below.

[1421] Step 1:

[1422] The server collects failure and success data from the internet and internal databases, for example, using web scraping or APIs to retrieve relevant data from blog posts, news articles, research papers, etc.

[1423] Step 2:

[1424] The server preprocesses the collected data, including data cleansing, removing duplicate data, completing incomplete data, and normalizing the data. Specifically, it removes noise from text data (e.g., HTML tags and unnecessary special characters) and standardizes the data format.

[1425] Step 3:

[1426] The server stores the preprocessed data in a case database, with each case containing detailed information such as case ID, date and time, background, and results.

[1427] Step 4:

[1428] The server analyzes the stored data using natural language processing (NLP) techniques and machine learning algorithms, specifically by performing text analysis to identify common patterns and trends among cases and by using clustering algorithms to group related cases.

[1429] Step 5:

[1430] Based on the analysis, the server derives the principles of success, for example, discovering that effective communication is the key to success in project management.

[1431] Step 6:

[1432] The server generates a specific action plan based on the success formula, for example, an action plan that includes the instruction "obtain stakeholder feedback twice by the next milestone."

[1433] Step 7:

[1434] When a user accesses the system using a terminal, the server sends the generated success formula and action plan to the terminal and displays it. The user can check the proposed action plan on the terminal dashboard.

[1435] Step 8:

[1436] The user executes the proposed action plan and provides the results and emotional feedback to the server via the terminal. For example, the user can input information such as "We were able to obtain stakeholder feedback successfully and the project progressed smoothly" and the emotion "I am satisfied."

[1437] Step 9:

[1438] The server analyzes the feedback and emotional data provided by users to improve the accuracy of algorithms and action plans. It uses insights from the feedback to conduct the next data analysis and implement continuous system improvements. By utilizing an emotional engine, the emotional information contained in user feedback is also reflected in the analysis.

[1439] As a concrete example, we will show how this system works in the marketing strategy of a new product.

[1440] Step 1:

[1441] The server collects success stories and failure stories of new product launches from the Internet and past data within companies.

[1442] Step 2:

[1443] The collected data is cleansed and duplicates are removed, and the text data is then formatted.

[1444] Step 3:

[1445] The server stores the pre-processed data in a database, recording detailed information about each case.

[1446] Step 4:

[1447] The server analyzes the cases in the database and identifies factors that contribute to success. For example, it finds that "clear target market definition and development of marketing strategies" are factors for success.

[1448] Step 5:

[1449] Based on the analysis results, we derive the formula for success: "Clearly define your target market and develop an appropriate advertising campaign."

[1450] Step 6:

[1451] The server generates a specific action plan based on the formula for success, such as "implementing an advertising campaign divided into three steps."

[1452] Step 7:

[1453] When a user (marketer) logs in to a terminal, the server transmits the generated action plan and displays it on the terminal.

[1454] Step 8:

[1455] After implementing the proposed action plan, the user provides the results and emotional feedback to the server via their device. For example, the user inputs "Sales increased as a result of the advertising campaign" and "I am satisfied."

[1456] Step 9:

[1457] The server analyzes the feedback data and emotion data and reflects it in the next data analysis, which improves the accuracy of the next action plan and allows the system to continuously improve.

[1458] Example 2

[1459] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1460] In conventional systems, the processes of collecting, analyzing, and providing users with data on failure and success cases were not efficiently coordinated, making it difficult to formulate specific action plans based on identified patterns and success rules.In addition, it was not possible to incorporate emotional analysis based on user feedback, making it difficult to generate more accurate action plans that reflected emotional information.

[1461] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for collecting failure case data and success case data; means for storing the collected failure case data and success case data in a database; means for preprocessing the stored data to perform data cleansing and for removing and normalizing duplicate data; means for analyzing the preprocessed data using natural language processing technology and machine learning algorithms to identify patterns and trends; means for performing sentiment analysis based on user feedback; means for generating rules for success and action plans based on the identified patterns, trends, and sentiment analysis; means for displaying the generated rules for success and action plans on the user's terminal; and means for collecting user feedback and improving the analysis results and algorithms. This links a series of processes from collection to analysis, provision, and feedback, enabling the generation of more accurate action plans that incorporate user sentiment information.

[1462] "Failure case data" is data that contains detailed information about failed attempts to achieve a particular goal or objective.

[1463] "Success story data" is data that contains detailed information about successful attempts to achieve a particular goal or objective.

[1464] "Means of collection" refers to the methods and techniques used to collect the required information from the Internet and internal databases.

[1465] A "database" is a system for efficiently managing and storing collected data.

[1466] "Preprocessing" refers to tasks such as data cleansing, removing duplicate data, and completing incomplete data to make data easier to analyze.

[1467] "Data cleansing" is the process of removing unnecessary information and errors from data.

[1468] "Deleting duplicate data" refers to the process of organizing and integrating duplicate data of the same content into one piece of data.

[1469] "Normalization" is the process of arranging data into a unified format.

[1470] "Natural language processing technology" is a technology that enables computers to understand and process the natural language used by humans.

[1471] A "machine learning algorithm" is an algorithm that learns patterns and rules based on data and makes predictions and classifications for new data.

[1472] "Means of identifying patterns and trends" refers to methods and techniques for finding common characteristics and trends through data analysis.

[1473] "Feedback" is information provided by a user as a result of an action plan they have implemented.

[1474] "Sentiment analysis" is a technology that identifies and classifies emotions from text data such as user feedback.

[1475] A "law of success" is a principle that indicates a set of effective actions or steps derived from past success stories.

[1476] An "action plan" is a plan that outlines specific actions to be taken based on the laws of success.

[1477] "Display means" refers to a method or technology for visually displaying the generated information and action plan on the user's terminal.

[1478] "Means for improving the algorithm" refers to the technology of adjusting the analysis algorithm based on the collected feedback and reflecting it in the next analysis.

[1479] The system of the present invention is composed of three main elements: a server, a terminal, and a user, and also incorporates an emotion engine that recognizes the user's emotions. The system collects data on both failure and success cases, stores it in a database, analyzes it, generates rules for success and specific action plans, and provides them to the user. It also collects feedback from users to continuously improve the accuracy of the system.

[1480] Hardware and Software Configuration

[1481] Server: The server plays a central role in collecting data, pre-processing, analyzing, generating action plans, providing them to users, and processing feedback.

[1482] Software used:

[1483] Web scraping tools (e.g., Python's BeautifulSoup)

[1484] Database (e.g. MySQL)

[1485] Natural language processing libraries (e.g., spaCy, NLTK)

[1486] Machine learning libraries (e.g., scikit-learn)

[1487] Sentiment analysis models (e.g., HuggingFace Transformers)

[1488] Device: The device that a user uses to access the system and view the action plan. A device can be a laptop, desktop computer, or mobile device.

[1489] User: A person who uses the system to learn from failures and successes and implements specific action plans. The user provides feedback to the system using a terminal.

[1490] Data collection

[1491] The server collects data on failures and successes from the internet and internal company databases, using web scraping tools and APIs with BeautifulSoup to extract the necessary data from related blog posts, news articles, research papers, and other sources.

[1492] Data preprocessing and storage

[1493] The collected data is cleansed on the server, removing duplicates and completing incomplete data. This involves using regular expressions to remove HTML tags and unnecessary special characters and standardize the data format. The preprocessed data is then stored in a database such as MySQL and prepared for analysis.

[1494] Data analysis

[1495] The server performs analysis using natural language processing techniques and machine learning algorithms. Specifically, it uses spaCy and NLTK to tokenize text data, tag parts of speech, and perform dependency analysis, and then uses scikit-learn algorithms to identify patterns and trends in the data. The goal of the analysis is to identify factors behind failures and successes.

[1496] Analysis by emotion engine

[1497] The server has a built-in emotion engine that recognizes emotions based on user feedback. Using HuggingFace's Transformers library, a text analysis algorithm classifies emotions from user feedback text and extracts emotions such as "satisfied" or "anxious."

[1498] Formulating success and action plans

[1499] The server derives success rules based on the results of data analysis and sentiment analysis, generating specific action plans such as "hold regular meetings with stakeholders in the early stages of project planning."

[1500] Provision to users

[1501] The user accesses the system using a terminal. The server sends the generated success formula and action plan to the terminal and displays it on the dashboard. The user can check the proposed action plan and implement it as necessary.

[1502] Feedback and System Improvement

[1503] After the user implements the action plan, they provide the results as feedback to the system. For example, they might enter information like, "After meeting with stakeholders, the project progressed smoothly." The server analyzes this feedback and updates the algorithm to improve the accuracy of the next analysis.

[1504] Examples of concrete examples and prompts

[1505] For example, consider the case of a new product launch. The server uses BeautifulSoup to collect successful and unsuccessful cases of new product launches from the Internet. The collected data is cleansed and normalized using pandas and stored in a MySQL database. The server analyzes the data using spaCy and identifies success factors using a classification algorithm in scikit-learn. An emotion engine extracts emotions from user feedback, and the server ultimately generates a specific action plan, such as "conduct market research, identify target segments, and then launch an advertising campaign." The user then checks this action plan on their device and provides feedback to the system after the plan is implemented.

[1506] Examples of prompts include:

[1507] "Collect and analyze success stories and failures in bringing new products to market, and create a concrete action plan to lead to success."

[1508] This system allows companies to efficiently and effectively learn from failure and gain concrete methods to lead to success. It also allows for the formulation of more accurate action plans by reflecting user emotions.

[1509] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1510] Step 1:

[1511] Data collection

[1512] The server collects data on failures and successes. Specifically, it uses Python's BeautifulSoup to scrape relevant web pages and obtain text data on failures and successes. It also uses APIs to extract data from blog posts, news articles, research papers, etc. The input is a URL or API endpoint, and the output is the raw data obtained.

[1513] Step 2:

[1514] Data preprocessing and storage

[1515] The server cleanses the collected data and normalizes it into a unified format. Specifically, it uses regular expressions to remove HTML tags and special characters, and converts it into a data frame using the pandas library. The input is raw data, and the output is cleansed, standardized data. The processed data is stored in a MySQL database.

[1516] Step 3:

[1517] Data analysis

[1518] The server analyzes the preprocessed data using natural language processing techniques and machine learning algorithms. Specifically, it uses spaCy to tokenize the text data and analyze basic linguistic structures (part-of-speech tagging, dependency analysis). It then applies classification models using scikit-learn algorithms to identify patterns and trends in the data. The input is the cleansed data, and the output is the analysis results (identified patterns and trends).

[1519] Step 4:

[1520] Analysis by emotion engine

[1521] The server uses an emotion engine to recognize emotions from user feedback. Specifically, it uses the Transformers library in HuggingFace to analyze the feedback text and classify emotions such as "satisfied," "anxious," and "excited." The input is the feedback text, and the output is the extracted emotion data.

[1522] Step 5:

[1523] Formulating success and action plans

[1524] The server derives success rules based on the results of data analysis and sentiment analysis. Specifically, it integrates the analysis results from the scikit-learn algorithm with sentiment data and formulates specific action plans based on successful examples of project management. For example, it generates a plan such as "hold regular meetings with stakeholders in the early stages of project planning." The input is the analysis results and sentiment data, and the output is a specific action plan.

[1525] Step 6:

[1526] Provision to users

[1527] Users access the system using their devices. The server sends the generated success formula and action plan to the user's device and displays it on a dashboard. Specifically, the user can view the action plan on a web page or mobile application. The input is the generated action plan, and the output is the action plan displayed on the user's device.

[1528] Step 7:

[1529] Feedback and System Improvement

[1530] Users provide feedback to the system on the results of their action plans. Specifically, they access a feedback form from their device and enter the results and their emotions. The server receives this feedback, analyzes it using an emotion engine, and then updates the algorithm using scikit-learn. The input is the user's feedback, and the output is the updated analysis algorithm.

[1531] This system allows companies to learn from both success and failure and develop specific action plans to lead to success. Furthermore, incorporating user emotional data makes it possible to generate more accurate action plans.

[1532] (Application example 2)

[1533] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1534] Conventional systems were able to collect and analyze data on both failure and success cases and generate action plans, but there was no concrete method for utilizing this data in in-factory robot control to improve work efficiency and reduce the occurrence of errors. Furthermore, there was a lack of a mechanism for evaluating user feedback based on sentiment analysis and improving analysis accuracy. Therefore, a means to further improve work efficiency in factories was needed.

[1535] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1536] In this invention, the server includes means for collecting failure case data and success case data, means for storing the collected failure case data and success case data in a database, means for analyzing the stored data and identifying patterns and trends, means for generating rules for success and action plans based on the identified patterns and trends, means for displaying the generated rules for success and action plans on a user's terminal, means for collecting user feedback and improving the analysis results and algorithms, means including a robot for collecting work data and sensor information, means for executing a machine learning algorithm based on the collected data, and means for classifying emotions from user feedback text, thereby enabling work efficiency in factories and reducing the occurrence of errors.

[1537] "Failure Data" is information relating to instances where a particular task or project did not achieve the expected results.

[1538] "Success Data" is information relating to instances where an expected result was achieved in a particular task or project.

[1539] A "database" is a structured collection of information for storing and managing collected data.

[1540] A "pattern or trend" is an element that indicates a consistent structure or variation in the data, or a set of regularities found in the data.

[1541] A "law of success" is a proven guideline or principle for achieving success under specific circumstances or conditions.

[1542] An "action plan" is a plan that details the specific actions or steps to be taken to achieve a goal.

[1543] "User terminal" refers to the device (e.g., smartphone, tablet, or PC) used by the user to access the system and view the displayed information.

[1544] "Feedback" is information provided by a user by inputting the results and impressions of the action plan they have implemented.

[1545] "Work data" is information about the performance of robots and workers in the factory.

[1546] "Sensor information" is data used to monitor the environment within the factory and the status of robots in real time.

[1547] A "machine learning algorithm" is a computational method for analyzing large amounts of data, discovering patterns within it, and making predictions and classifications.

[1548] "Feedback text" is a written expression of opinions and thoughts that a user inputs into the system.

[1549] A "sentiment classifier" is a technique for identifying and classifying emotions such as positive, negative, or neutral from feedback text.

[1550] The system of the present invention collects and analyzes data on both failure and success cases, generates rules for success and specific action plans, and provides them to users. Furthermore, it can use an emotion engine to analyze user feedback and improve the accuracy of the system.

[1551] This system is composed of three main elements: a server, a terminal, and a user, and uses the following hardware and software:

[1552] Hardware and software used

[1553] 1. Hardware:

[1554] Factory robots (e.g., industrial robots and smartphones)

[1555] 2. Software:

[1556] requests: An HTTP request library for collecting data.

[1557] textblob: A natural language processing library for sentiment analysis

[1558] numpy: A scientific computing library for data analysis

[1559] sklearn: A library that provides machine learning algorithms

[1560] Data collection

[1561] The server collects data on failures and successes from the internet and internal databases, specifically, by acquiring factory operation data and sensor information via API endpoints.

[1562] Data preprocessing and storage

[1563] The collected data is normalized through a data cleansing process and stored in a database. Specific processes of data cleansing include removing noise from text data and standardizing data formats.

[1564] Data analysis

[1565] The server analyzes the data using natural language processing (NLP) and machine learning algorithms, specifically by taking the collected work data and feedback text as input and identifying effective work steps.

[1566] Analysis by emotion engine

[1567] Analyze user feedback text and classify the sentiment. Use the textblob library to identify whether the feedback is positive or negative.

[1568] Formulating success and action plans

[1569] The server extracts the principles of success based on the results of data and sentiment analysis and generates specific action plans, such as "performing regular maintenance" or "optimal procedures for specific tasks," and provides the plan to the user.

[1570] Provision to users

[1571] The user accesses the system using a terminal. The server sends the generated success formula and action plan to the terminal and displays it. The user can check the proposed action plan on the terminal interface.

[1572] Feedback and System Improvement

[1573] After the user executes the action plan, the results are provided to the system as feedback. A specific example of feedback is inputting text such as "This task was very efficient. I would like to continue using this method next time." The emotion engine also analyzes the emotional information contained in this feedback.

[1574] Specific examples

[1575] When a factory robot performs a specific task, the system collects the robot's work data and sensor information, and uses this information to generate a success rule and action plan. When workers enter feedback, they can provide an example prompt such as, "This task was very efficient. I would like to continue using this method next time," which, along with sentiment analysis, can improve the system's accuracy.

[1576] In this way, the system of the present invention can provide a specific method for improving work efficiency and reducing the occurrence of errors within a factory.

[1577] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1578] Step 1:

[1579] Data collection

[1580] The server collects failure and success case data from the internet and internal databases. Specifically, it obtains data such as factory operation data and sensor information through API endpoints. The input is the API endpoint, and the output is the obtained raw data. The server collects data using an HTTP request library (requests).

[1581] Step 2:

[1582] Data preprocessing and storage

[1583] The server cleanses the collected data, removing duplicates and normalizing the data. Specifically, it removes noise from the text data and standardizes the format. The input is raw data, and the output is preprocessed clean data. The server stores this clean data in a database.

[1584] Step 3:

[1585] Data analysis

[1586] The server analyzes the preprocessed data using natural language processing (NLP) techniques and machine learning algorithms. Specifically, it uses the collected work data and feedback text as input to identify patterns and trends in the data. The input is clean data, and the output is the analysis results (patterns and trends). The server performs the analysis using NLP techniques and machine learning libraries (e.g., sklearn).

[1587] Step 4:

[1588] Analysis by emotion engine

[1589] The server collects feedback text from users and classifies its sentiment using an emotion engine. Specifically, it uses a natural language processing library (textblob) to identify whether the feedback is positive or negative. The input is the feedback text, and the output is the sentiment classification result.

[1590] Step 5:

[1591] Formulating success and action plans

[1592] The server extracts success rules based on the results of data analysis and sentiment analysis and generates specific action plans. For example, it suggests "performing regular maintenance" or "optimal procedures for specific tasks." The input is the analysis results and sentiment classification results, and the output is the generated success rules and action plans.

[1593] Step 6:

[1594] Provision to users

[1595] The server sends the generated success formula and action plan to the user's terminal and displays them. The user can check the proposed action plan on the terminal interface. The input is the success formula and action plan, and the output is the display on the user's terminal.

[1596] Step 7:

[1597] Feedback and System Improvement

[1598] After the user executes the action plan, they provide the results to the system as feedback. The server collects this feedback and analyzes it again to improve the accuracy of the system. For example, a user may input feedback such as "This task was very efficient. I would like to continue using this method next time." The input is feedback, and the output is new analysis results and algorithm improvements for the system.

[1599] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1600] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1601] 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 the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1602] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1603] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1604] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1605] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1606] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1607] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1608] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1609] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1610] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1611] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1612] 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.

[1613] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1614] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1615] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific processing may be a single processor.

[1616] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1617] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1618] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1619] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1620] The following is further disclosed regarding the above embodiment.

[1621] (Claim 1)

[1622] A means of collecting failure and success case data;

[1623] A means for storing the collected failure case data and success case data in a database;

[1624] A means for analyzing the stored data and identifying patterns and trends;

[1625] A means of generating success rules and action plans based on identified patterns and trends;

[1626] A means for displaying the generated success law and action plan on the user's terminal;

[1627] a means of collecting user feedback and improving the analysis results and algorithms;

[1628] A system including:

[1629] (Claim 2)

[1630] The system of claim 1, further comprising: preprocessing the collected data to remove duplicate data and normalize the data.

[1631] (Claim 3)

[1632] 2. The system according to claim 1, wherein the data stored in the database is analyzed using natural language processing techniques.

[1633] "Example 1"

[1634] (Claim 1)

[1635] A means of collecting failure and success case data;

[1636] A means for storing the collected failure case data and success case data in a database;

[1637] means for preprocessing the stored data by removing duplicate data, imputing incomplete data, and normalizing the data;

[1638] A means of analyzing pre-processed data and identifying patterns and trends using natural language processing techniques and machine learning algorithms;

[1639] A means of generating success formulas and specific action plans based on identified patterns and trends;

[1640] A means for displaying the generated success law and action plan on the user's terminal;

[1641] means for collecting feedback from users and analyzing the feedback to improve the analysis results and algorithms;

[1642] A system including:

[1643] (Claim 2)

[1644] The system of claim 1, further comprising: preprocessing the collected data to remove duplicate data, impute incomplete data, and normalize the data.

[1645] (Claim 3)

[1646] The system according to claim 1, wherein the data stored in the database is analyzed using natural language processing techniques and machine learning algorithms.

[1647] "Application Example 1"

[1648] (Claim 1)

[1649] A means of collecting failure and success case data;

[1650] A means for storing the collected failure case data and success case data in a database;

[1651] A means for analyzing the stored data and identifying patterns and trends;

[1652] A means of generating success rules and action plans based on identified patterns and trends;

[1653] A means for displaying the generated success law and action plan on the user's terminal;

[1654] a means of collecting user feedback and improving the analysis results and algorithms;

[1655] a means for collecting sensor data from the autonomous vehicle;

[1656] a means for preprocessing and normalizing the collected sensor data;

[1657] A means of analyzing trends in data using natural language processing techniques and machine learning algorithms;

[1658] A means for generating a success rule and a specific operation method for the operation of the autonomous driving vehicle based on the analysis results;

[1659] a means for displaying the generated operation method on an operation management terminal of the autonomous driving vehicle;

[1660] A means of collecting feedback from users on the results of their operations and improving the analysis results and algorithms;

[1661] A system including:

[1662] (Claim 2)

[1663] The system of claim 1, further comprising: preprocessing the collected data to remove duplicate data and normalize the data.

[1664] (Claim 3)

[1665] The system according to claim 1, wherein the data stored in the database is analyzed using natural language processing techniques and machine learning algorithms.

[1666] "Example 2: Combining Emotion Engines"

[1667] (Claim 1)

[1668] A means of collecting failure and success case data;

[1669] A means for storing the collected failure case data and success case data in a database;

[1670] means for preprocessing the stored data to cleanse the data, remove duplicates, and normalize the data;

[1671] A means of analyzing the pre-processed data using natural language processing techniques and machine learning algorithms to identify patterns and trends; and

[1672] means for performing sentiment analysis based on user feedback;

[1673] a means for generating success formulas and action plans based on identified patterns, trends and sentiment analysis;

[1674] A means for displaying the generated success law and action plan on the user's terminal;

[1675] a means of collecting user feedback and improving the analysis results and algorithms;

[1676] A system including:

[1677] (Claim 2)

[1678] The system of claim 1, further comprising: preprocessing the collected data to remove duplicate data and normalize the data.

[1679] (Claim 3)

[1680] 2. The system according to claim 1, wherein the data stored in the database is analyzed using natural language processing technology.

[1681] "Application example 2 when combining emotion engines"

[1682] (Claim 1)

[1683] A means of collecting failure and success case data;

[1684] A means for storing the collected failure case data and success case data in a database;

[1685] A means for analyzing the stored data and identifying patterns and trends;

[1686] A means of generating success rules and action plans based on identified patterns and trends;

[1687] A means for displaying the generated success law and action plan on the user's terminal;

[1688] a means of collecting user feedback and improving the analysis results and algorithms;

[1689] a means including a robot for collecting operation data and sensor information;

[1690] means for executing machine learning algorithms based on the collected data;

[1691] means for classifying emotions from the user's feedback text;

[1692] A system including:

[1693] (Claim 2)

[1694] The system of claim 1, further comprising: preprocessing the collected data to remove duplicate data and normalize the data.

[1695] (Claim 3)

[1696] 2. The system according to claim 1, wherein the data stored in the database is analyzed using natural language processing techniques. [Explanation of symbols]

[1697] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting failure and success case data; A means for storing the collected failure case data and success case data in a database; A means for analyzing the stored data and identifying patterns and trends; A means of generating success rules and action plans based on identified patterns and trends; A means for displaying the generated success law and action plan on the user's terminal; a means of collecting user feedback and improving the analysis results and algorithms; A system including:

2. The system of claim 1 , further comprising: preprocessing the collected data to remove duplicate data and normalize the data.

3. The system according to claim 1, wherein the data stored in the database is analyzed using natural language processing techniques.

Images