System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting required data; means for pre-processing the collected data; means for training a machine learning model using the pre-processed data; means for simulating a plurality of decision scenarios; and means for presenting an optimal decision result to a user.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] There is a demand to reduce the time corporate managers spend on decision-making so that they can focus on their primary focus: problem discovery, problem formulation, and problem solving. However, in conventional data-driven decision-making systems, the series of processes - data collection, preprocessing, model creation and training, decision-making simulation, and result presentation - are not integrated, and each process is carried out separately, resulting in reduced efficiency and a long time required for decision-making. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides a data-driven decision-making system that integrates data collection, preprocessing, model creation and training, decision-making simulation, and result presentation. Specifically, the system includes a means for collecting necessary data, a means for preprocessing the collected data, a means for training a machine learning model using the preprocessed data, a means for simulating multiple decision-making scenarios, and a means for presenting the optimal decision-making results to the user. This system significantly reduces the time managers spend on decision-making and maximizes labor productivity.

[0006] "Means of collecting data" refers to a system for automatically collecting necessary data from inside and outside the company.

[0007] "Data preprocessing means" refers to a mechanism for removing incomplete data and noise from collected data and converting it into a format suitable for analysis.

[0008] A "means for training machine learning models" is a mechanism for using preprocessed data to create and optimize machine learning models to predict future trends and patterns.

[0009] A "means for simulating multiple decision-making scenarios" is a mechanism for assuming different decision-making conditions and strategies, simulating those scenarios, and obtaining predicted results.

[0010] The "means for presenting optimal decision-making results to the user" is a mechanism for presenting the most advantageous decision-making results to the user in an easy-to-understand manner based on the results of the simulation.

[0011] "Noise detection and filtering means" are mechanisms for identifying and removing outliers and errors in data.

[0012] A "market trend data scraping method" is a system for automatically extracting data on market conditions and market trends from websites on the Internet. [Brief explanation of the drawings]

[0013] [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

[0014] 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.

[0015] First, the terms used in the following description will be explained.

[0016] 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).

[0017] 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.

[0018] 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.

[0019] 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.

[0020] 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."

[0021] [First embodiment]

[0022] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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."

[0034] This invention relates to a data-driven decision-making system that enables corporate managers to make efficient decisions. This system integrates data collection, preprocessing, machine learning model training, decision-making simulation, and result presentation, with the aim of reducing the time managers spend on decision-making and maximizing labor productivity.

[0035] Overall system overview

[0036] The system includes the following major components:

[0037] 1. Data collection methods:

[0038] The server collects the necessary data from various sources, both inside and outside the company, including sales databases, customer relationship management systems (CRM), market trend data from the Internet, industry reports, and news APIs.

[0039] 2. Data preprocessing methods:

[0040] The server preprocesses the collected data and converts it into a format suitable for analysis: removing incomplete data and noise, integrating data from different sources, and normalizing the data if necessary.

[0041] 3. Model creation and training methods:

[0042] The server uses the preprocessed data to train a machine learning model, splitting the dataset into training data and test data, creating and optimizing the model using a machine learning algorithm, and evaluating its performance.

[0043] 4. Decision-making simulation tools:

[0044] The server uses the trained model to simulate various decision-making scenarios, compares the results of each scenario, and selects the optimal decision based on business goals.

[0045] 5. Presentation of results:

[0046] The server presents the optimal decision-making results to the user, generates reports through a dashboard, and presents the user with a clear and specific action plan.

[0047] Specific Examples

[0048] For example, if a company is considering launching a new product, the process using this system would proceed as follows:

[0049] 1. Data Collection:

[0050] The server automatically collects sales data, customer purchase history, current market trends, competitor activity, and more.

[0051] 2. Data Preprocessing:

[0052] The server cleanses the collected data, imputes missing values, filters outliers, and also consolidates and converts the data into a unified format.

[0053] 3. Model creation and training:

[0054] The server uses the data split into training and test data to train a machine learning model, for example, to create a model that predicts the success rate of a new product based on past market launch data.

[0055] 4. Decision-making simulation:

[0056] The server simulates multiple scenarios that change the timing of new product launches, pricing, and marketing strategies, and calculates the probability of success and return on investment (ROI) for each scenario.

[0057] 5. Presentation of results:

[0058] The server will suggest the most effective strategy to the user (for example, "launch at full price in April and conduct a large-scale marketing campaign"). The server will then provide the user with detailed reasons for the suggestion and expected results via a dashboard. The user can then create a specific action plan based on this information.

[0059] Through the above process, the system of the present invention supports data-driven decision-making and enables corporate managers to efficiently tackle problem-solving.

[0060] The processing flow will be explained below.

[0061] Program processing flow

[0062] Step 1: Data collection

[0063] The server collects the necessary data from inside and outside the company.

[0064] 1. The server connects to the sales database and extracts the sales data.

[0065] 2. The server retrieves customer feedback and purchase history from the customer relationship management system (CRM).

[0066] 3. The server scrapes market trend data using public APIs on the Internet.

[0067] 4. The server collects competitor trend data from news APIs and industry reports.

[0068] Step 2: Data Preprocessing

[0069] The server pre-processes the collected data and converts it into a format suitable for analysis.

[0070] 1. The server identifies incomplete data and missing values ​​in the generated database and imputes or removes them appropriately.

[0071] 2. The server detects and filters outliers and errors.

[0072] 3. The server consolidates data from different sources and normalizes it for consistency.

[0073] 4. The server normalizes and unifies inconsistent data formats.

[0074] Step 3: Model creation and training

[0075] The server uses the preprocessed data to create and train a machine learning model.

[0076] 1. The server splits the dataset into training data and test data.

[0077] 2. The server trains the model using the machine learning algorithm of your choice (e.g., decision tree, random forest, neural network).

[0078] 3. The server uses historical data to optimize the model parameters.

[0079] 4. The server uses the test data to calculate evaluation metrics such as precision, recall, and F1 score of the trained model and evaluate the model's performance.

[0080] Step 4: Decision-making simulation

[0081] The server uses the trained model to simulate multiple decision-making scenarios.

[0082] 1. The server generates different scenarios for new product launch timing, pricing, marketing strategies, etc.

[0083] 2. The server applies the model to each scenario and predicts future sales, customer acquisition, ROI (return on investment), etc.

[0084] 3. The server compares the results of each scenario and evaluates them based on business goals.

[0085] 4. The server selects the most advantageous scenario and proposes a strategy.

[0086] Step 5: Presenting the results

[0087] The server generates the optimal decision-making results as a report and presents it to the user.

[0088] 1. The server creates a report based on the data from the optimal decision-making scenario.

[0089] 2. The server will provide a report with the reasons for the recommendation and the specific results expected (e.g., projected sales, number of customers, risk assessment).

[0090] 3. The server displays the report on the user's device via a dashboard.

[0091] 4. Users review the presented reports and use them to make data-driven decisions.

[0092] Through these steps, the system effectively supports data-driven decision making.

[0093] Example 1

[0094] 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."

[0095] When corporate managers make decisions, the time and effort required to efficiently collect, preprocess, and analyze massive amounts of data to make optimal decisions is a major challenge. Traditional methods pose the risk of incorrect decision-making due to data inconsistencies, missing data, or noise. Furthermore, the process of simulating various scenarios and identifying optimal strategies is complex and requires advanced expertise. There is a need for a system that can solve these challenges and improve the accuracy and efficiency of decision-making.

[0096] 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.

[0097] In this invention, the server includes means for collecting necessary data, means for preprocessing the collected data, means for training a machine learning model using the preprocessed data, means for simulating multiple decision-making scenarios, and means for presenting the optimal decision-making results to users. This allows corporate managers to efficiently use massive amounts of data and make quick and accurate decisions. Furthermore, by dividing the data and applying machine learning algorithms, the performance of the model can be optimized, and comparative analysis between different scenarios can be performed to derive the optimal strategy. Furthermore, by visualizing the simulation results and presenting them through a dashboard, users can intuitively understand the results and formulate executable action plans.

[0098] "Means for collecting data" refers to methods and devices for efficiently obtaining necessary data from multiple data sources inside and outside the company.

[0099] "Data preprocessing means" refers to a method or device for imputing missing values, removing noise, integrating, and normalizing collected data, and converting it into a form suitable for analysis.

[0100] A "means for training a machine learning model" is a method or apparatus that uses preprocessed data, splits it into training data and test data, and creates and optimizes a model using a machine learning algorithm.

[0101] A "means for simulating decision-making scenarios" is a method or device that uses a trained machine learning model to construct various decision-making scenarios and calculate the probability of success and return on investment (ROI).

[0102] "Means for presenting optimal decision-making results to users" refers to a method or device for presenting optimal strategies and results obtained from a simulation to users in an easy-to-understand manner through an interface such as a dashboard.

[0103] "Means for detecting and filtering noise in data" refers to methods and devices for detecting inconsistencies and outliers in data and removing data that is unsuitable for analysis.

[0104] A "means for splitting a dataset" is a method for splitting data into training data and test data for training and evaluating a machine learning model.

[0105] The "means for calculating the probability of success and return on investment for each scenario" refers to a method or device for statistically evaluating the results of each decision-making scenario and calculating the probability of success and return on investment.

[0106] A "means for visualizing simulation results" is a method or device for displaying the results of a simulation in a visual format such as a graph or chart, allowing users to intuitively understand the results.

[0107] A "dashboard" is a user interface that allows users to centrally view and operate information obtained from the system.

[0108] This invention relates to a data-driven decision-making system that enables corporate managers to make efficient decisions. This system integrates data collection, preprocessing, machine learning model training, decision-making simulation, and result presentation, with the aim of reducing the time managers spend on decision-making and maximizing labor productivity.

[0109] Overall system overview

[0110] The system includes the following major components:

[0111] Data collection methods

[0112] Data preprocessing measures

[0113] How to train machine learning models

[0114] Decision-making simulation tools

[0115] Presentation of results

[0116] Data collection methods

[0117] The server automatically collects the required data from multiple data sources, both internal and external to the company. It uses Python's requests and pandas libraries to execute API requests and database queries. For example, it retrieves sales data from a sales database and customer information from a CRM system. It also uses external APIs (e.g., Google Trends API) to collect market trend data and news APIs (e.g., NewsAPI) to retrieve the latest industry reports and news.

[0118] Data preprocessing measures

[0119] The server preprocesses the collected data and converts it into a format suitable for analysis. This process includes data cleansing, missing value completion, noise removal, data integration from different sources, and normalization. Specifically, data processing is performed using the Python pandas and numpy libraries.

[0120] How to train machine learning models

[0121] The server trains a machine learning model using the preprocessed data. It splits the dataset into training data and test data, and creates and optimizes the model using a machine learning algorithm (e.g., random forest, linear regression). The model is trained using libraries such as scikit-learn, TensorFlow, and Keras.

[0122] Decision-making simulation tools

[0123] The server uses the trained model to simulate various decision-making scenarios, such as the timing of new product launches, pricing, and marketing strategies, and calculates the probability of success and return on investment (ROI) for each scenario.

[0124] Presentation of results

[0125] The server presents the optimal decision-making results to the user. Here, the simulation results are visualized and displayed on a dashboard. Tools such as matplotlib and dash are used to build a user-friendly interface. Through the dashboard, the user can formulate a specific action plan.

[0126] Specific Examples

[0127] For example, if a company is considering launching a new product into the market, the system would implement the following process:

[0128] 1. Data collection: The server automatically collects data such as sales data, customer purchase history, current market trends, and competitor activity.

[0129] 2. Data Preprocessing: The server cleanses the collected data, imputes missing values, filters outliers, and integrates data from different sources into a unified format.

[0130] 3. Model creation and training: The server splits the preprocessed dataset into training data and test data, and trains a machine learning model, for example, to predict the success rate of a new product based on historical market launch data.

[0131] 4. Decision-making simulation: The server simulates multiple scenarios that change the timing of new product launches, pricing, and marketing strategies, and calculates the probability of success and return on investment (ROI) for each scenario.

[0132] 5. Presentation of results: The server proposes the most effective strategy to the user. For example, if it determines that launching at full price in April and running a large-scale marketing campaign is the optimal strategy, the server will present the reasons for this proposal and the expected results in detail via a dashboard. The user can then formulate a specific action plan based on this information.

[0133] Prompt Sentence Examples

[0134] "Imagine a company is introducing a new product in April. Collect and preprocess data such as sales data, customer purchase history, market trends, and competitor behavior, and train a machine learning model to predict the success rate of the new product launch. Then, create multiple simulation scenarios to suggest optimal launch timing, pricing, and marketing strategies, compare them, and select the optimal strategy to present in a dashboard."

[0135] In this way, the system of the present invention supports data-driven decision making and enables corporate managers to efficiently tackle problems.

[0136] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0137] Step 1: Data collection

[0138] The server collects the required data from multiple data sources, both internal and external to the company. Inputs include a sales database, CRM system, market trend API, and news API. Based on this input, the server makes API requests using Python's requests library and executes database queries using the pandas library. Specific operations include retrieving data from the sales database, retrieving customer purchase history, and scraping and collecting the latest market trends and competitor activity. The output is the raw data retrieved from the various data sources.

[0139] Step 2: Data Preprocessing

[0140] The server preprocesses the collected raw data and converts it into a format suitable for analysis. The input includes the collected raw data. Based on this input, the server cleanses the data, imputes missing values, removes noise, integrates data from different sources, and normalizes it. Specifically, it uses Python's pandas and numpy libraries to process the data and generate clean data suitable for analysis. The output is a preprocessed, integrated dataset.

[0141] Step 3: Model creation and training

[0142] The server trains a machine learning model using a preprocessed dataset. The input includes the preprocessed dataset. Based on this input, the server splits the dataset into training data and test data, and creates and optimizes a model using a machine learning algorithm (e.g., random forest, linear regression). Specifically, it uses libraries such as scikit-learn, TensorFlow, and Keras to build the model and evaluate its performance. The output is a trained machine learning model.

[0143] Step 4: Decision-making simulation

[0144] The server uses the trained model to simulate various decision-making scenarios. The inputs include the trained machine learning model and the scenarios to be simulated (e.g., launch timing, pricing, marketing strategy). Based on these inputs, the server inputs each scenario into the model and calculates the probability of success and return on investment (ROI). Specifically, it constructs simulation scenarios in Python and applies them to the model. The output is the resulting data, including the probability of success and ROI for each scenario.

[0145] Step 5: Presenting the results

[0146] The server presents the simulation results to the user. The input includes the simulation result data. Based on this input, the server visualizes the results and displays them to the user through a dashboard. Specifically, it uses matplotlib and dash to create graphs and charts and displays the results on a web dashboard. The output is a dashboard that the user can view.

[0147] Through the above steps, this system can perform consistent processing from data collection to result presentation, supporting efficient decision-making.

[0148] (Application example 1)

[0149] 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."

[0150] In real-time traffic volume analysis and route optimization for autonomous vehicles, conventional methods require a lot of time and resources for data collection and preprocessing, making it difficult to make quick decisions.Furthermore, there was no system for comparing multiple traffic scenarios, making it difficult to present optimal routes in real time.

[0151] 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.

[0152] In this invention, the server includes means for collecting necessary data, means for preprocessing the collected data, means for training a machine learning model using the preprocessed data, means for acquiring current traffic condition data and simulating multiple route optimization scenarios, and means for presenting an optimal route to a user, thereby enabling real-time traffic condition analysis and prompt presentation of an optimal route based on multiple scenarios.

[0153] "Necessary data" refers to information necessary to understand traffic conditions, such as traffic volume, traffic speed, accident information, and weather conditions.

[0154] "Preprocessing" is the process of cleansing data after collection, filling in missing values, filtering outliers, integrating and normalizing the data.

[0155] A "machine learning model" is an algorithm that is trained using preprocessed data to predict current and future conditions based on past data.

[0156] "Traffic condition data" is data that indicates the current state of road traffic, and includes, for example, traffic volume, traffic speed, accident information, weather conditions, and the like.

[0157] A "route optimization scenario" is a scenario that simulates multiple routes based on traffic condition data to identify the most efficient or safe route.

[0158] The "optimal route" is the route that is deemed most desirable in terms of shortest time, least energy consumption, safety, etc., after comparing multiple route optimization scenarios.

[0159] "Noise" refers to factors that impair the accuracy of data, such as outliers, errors, and missing values ​​in a dataset.

[0160] "Real-time traffic data" refers to data that shows the state of road traffic at the current time and that is collected and analyzed quickly.

[0161] The system that realizes this application example performs real-time traffic analysis and route optimization for autonomous vehicles. The system consists of a server, a terminal, and a user.

[0162] System Configuration

[0163] server

[0164] The server implements the following methods:

[0165] 1. Data collection method: The server collects real-time traffic condition data such as traffic volume, traffic speed, accident information, weather conditions, etc. This is done by retrieving data from external APIs (e.g., Google Maps API, Here API).

[0166] 2. Data preprocessing means: The server cleanses the collected data, imputes missing values, filters outliers, and performs data integration and normalization.

[0167] 3. Machine learning model training method: The server uses the preprocessed data to train the machine learning model. For training, it uses a machine learning library such as scikit-learn.

[0168] 4. Simulation method: The server obtains current traffic condition data and simulates multiple route optimization scenarios, thereby predicting travel times for multiple scenarios.

[0169] 5. Result presentation: The server presents the optimal route to the user based on the simulation results. The presentation is done via a smartphone or the display of the in-vehicle computer.

[0170] Terminal

[0171] The terminal (smartphone or in-vehicle computer) receives the optimal route information sent from the server and visually displays it to the user.

[0172] User

[0173] The user navigates the autonomous vehicle based on the displayed optimal route information, allowing the user to reach the destination via an optimized route, avoiding traffic congestion and obstacles.

[0174] Program processing

[0175] The program in this system performs the following operations:

[0176] Data collection method: Use data collection API to obtain real-time traffic information. For example, the server obtains the latest traffic information from Google Maps API and Here API every minute.

[0177] Data preprocessing methods: Data will be cleansed, integrated, and normalized using Python's pandas library, etc. Appropriate statistical methods will be used to impute missing values.

[0178] Machine learning model training method: Using scikit-learn, a random forest regression model is trained on the preprocessed data. The trained model predicts current and future traffic conditions based on past data.

[0179] Simulation method: Using the trained model, create new traffic scenarios and predict travel times for each scenario, thereby identifying the most efficient routes.

[0180] Result presentation method: The optimal route and the reasons for it are displayed on the device's user interface. For example, the optimal route is displayed on a map in a smartphone application, and is communicated to the user along with voice guidance.

[0181] Specific examples

[0182] For example, here is a prompt to input to a generative AI model:

[0183] "Get traffic information based on the current date, time, and location to train a machine learning model for route optimization. Input data includes traffic speed, traffic volume, and weather conditions. Propose new strategies and predict travel times for each scenario."

[0184] By using such prompt sentences, it becomes possible to suggest optimal routes that take real-time traffic conditions into consideration.

[0185] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0186] Step 1:

[0187] The server collects traffic data. Specifically, it uses Google Maps API and Here API to obtain real-time data such as traffic volume, traffic speed, accident information, and weather conditions. The input of this process is raw data from the API, and the output is the collected traffic data.

[0188] Step 2:

[0189] The server preprocesses the collected data. Specifically, it uses the Python pandas library to cleanse the data, impute missing values, and filter outliers. It also integrates the data and normalizes it into a unified format. The input of this process is the collected traffic situation data, and the output is the cleansed and normalized data.

[0190] Step 3:

[0191] The server uses the preprocessed data to train a machine learning model. Specifically, it uses a random forest regression model from scikit-learn and trains it on historical traffic data. It splits the data into training data and test data, and evaluates the model's performance. The input of this process is the cleansed and normalized data, and the output is a trained machine learning model.

[0192] Step 4:

[0193] The server retrieves current traffic data and simulates multiple route optimization scenarios. For example, it generates scenarios that vary specific time periods or weather conditions, and predicts travel times for each scenario. The inputs to this process are current traffic data and a trained machine learning model, and the output is predicted travel times for each scenario.

[0194] Step 5:

[0195] The server presents the optimal route to the user based on the simulation results. Specifically, it compares the travel time of each route, selects the most efficient route, and displays it on the user interface. The terminal (smartphone or in-vehicle computer) receives this information and provides visual and audio guidance to the user. The input to this process is the predicted travel time for each scenario, and the output is optimal route information presented to the user.

[0196] Step 6:

[0197] The user navigates based on the presented optimal route information. The autonomous vehicle's navigation system drives according to the optimal route, avoiding traffic congestion and obstacles to reach the destination. The input of this process is the optimal route information, and the output is the user's arrival at the destination.

[0198] 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.

[0199] This invention relates to a data-driven decision-making system for corporate managers to make efficient decisions, and in particular, to a system that further improves the decision-making process by incorporating an emotion engine that recognizes user emotions. This system integrates data collection, preprocessing, machine learning model training, decision-making simulation, and result presentation, aiming to reduce the time managers spend on decision-making and maximize labor productivity.

[0200] Overall system overview

[0201] The system includes the following major components:

[0202] 1. Data collection methods:

[0203] The server collects the necessary data from various sources, both inside and outside the company, including sales databases, customer relationship management systems (CRM), market trend data from the Internet, industry reports, and news APIs.

[0204] 2. Data preprocessing methods:

[0205] The server preprocesses the collected data and converts it into a format suitable for analysis: removing incomplete data and noise, integrating data from different sources, and normalizing the data if necessary.

[0206] 3. Model creation and training methods:

[0207] The server uses the preprocessed data to train a machine learning model, splitting the dataset into training data and test data, creating and optimizing the model using a machine learning algorithm, and evaluating its performance.

[0208] 4. Decision-making simulation tools:

[0209] The server uses the trained model to simulate various decision-making scenarios, compares the results of each scenario, and selects the optimal decision based on business goals.

[0210] 5. Presentation of results:

[0211] The server presents the optimal decision-making results to the user, generates reports through a dashboard, and presents the user with a clear and specific action plan.

[0212] 6. Emotion recognition means:

[0213] The server uses an emotion engine to collect and analyze the user's emotional data, allowing it to adjust the evaluation and optimization of decision-making scenarios based on the user's emotional state.

[0214] Specific Examples

[0215] For example, if a company is considering launching a new product, the process using this system would proceed as follows:

[0216] 1. Data Collection:

[0217] The server automatically collects sales data, customer purchase history, current market trends, competitor activity, and more.

[0218] 2. Data Preprocessing:

[0219] The server cleanses the collected data, imputes missing values, filters outliers, and also consolidates and converts the data into a unified format.

[0220] 3. Model creation and training:

[0221] The server uses the data split into training and test data to train a machine learning model, for example, to create a model that predicts the success rate of a new product based on past market launch data.

[0222] 4. Decision-making simulation:

[0223] The server simulates multiple scenarios that change the timing of new product launches, pricing, and marketing strategies, and calculates the probability of success and return on investment (ROI) for each scenario.

[0224] 5. Emotion recognition:

[0225] The server uses an emotion engine to analyze the user's facial expressions and tone of voice to recognize their emotional state in real time. For example, if the user is feeling anxious, the server will adjust the explanation of the decision-making scenario to take that emotion into account.

[0226] 6. Presentation of results:

[0227] The server recommends the most effective strategy to the user (e.g., "launch at full price in April and conduct a large-scale marketing campaign"). The server provides the user with detailed reasons for the recommendation and expected results via a dashboard. The user can then create a specific action plan based on this information.

[0228] By combining this system with an emotion engine, the system can make better decisions by taking the user's emotions into account. For example, if the user is feeling stressed, the system can suggest a more cautious approach. This makes the decision-making process more comfortable and trustworthy for the user.

[0229] The processing flow will be explained below.

[0230] Program processing flow

[0231] Step 1: Data collection

[0232] The server collects the necessary data from inside and outside the company.

[0233] 1. The server connects to the sales database and extracts the sales data.

[0234] 2. The server retrieves customer feedback and purchase history from the customer relationship management system (CRM).

[0235] 3. The server scrapes market trend data using public APIs on the Internet.

[0236] 4. The server collects competitor trend data from news APIs and industry reports.

[0237] Step 2: Data Preprocessing

[0238] The server pre-processes the collected data and converts it into a format suitable for analysis.

[0239] 1. The server identifies incomplete data and missing values ​​and imputes or removes them appropriately.

[0240] 2. The server detects and filters outliers and errors.

[0241] 3. The server consolidates data from different sources and normalizes it for consistency.

[0242] 4. The server normalizes and unifies inconsistent data formats.

[0243] Step 3: Model creation and training

[0244] The server uses the preprocessed data to create and train a machine learning model.

[0245] 1. The server splits the dataset into training data and test data.

[0246] 2. The server trains the model using the machine learning algorithm of your choice (e.g., decision tree, random forest, neural network).

[0247] 3. The server uses the training data to optimize the model parameters.

[0248] 4. The server uses the test data to calculate evaluation metrics such as precision, recall, and F1 score of the trained model and evaluate the model's performance.

[0249] Step 4: Decision-making simulation

[0250] The server uses the trained model to simulate multiple decision-making scenarios.

[0251] 1. The server generates different scenarios for new product launch timing, pricing, marketing strategies, etc.

[0252] 2. The server applies the model to each scenario and predicts future sales, customer acquisition, ROI (return on investment), etc.

[0253] 3. The server compares the results of each scenario and evaluates the best scenario based on business goals.

[0254] 4. The server selects the most favorable scenario and recommends that strategy.

[0255] Step 5: Emotion Recognition

[0256] The server uses an emotion engine to collect and analyze the user's emotion data.

[0257] 1. The server analyzes the user's facial expressions and tone of voice to recognize their emotional state in real time.

[0258] 2. The server accumulates the user's emotional data and tracks its changes.

[0259] 3. The server adjusts the evaluation of the decision scenario based on the user's emotional state.

[0260] 4. The server suggests a cautious approach if the user is experiencing stress or anxiety.

[0261] Step 6: Presenting the results

[0262] The server generates the optimal decision-making results as a report and presents it to the user.

[0263] 1. The server creates a report based on the data from the optimal decision-making scenario.

[0264] 2. The server will provide a report with the reasons for the recommendation and the specific results expected (e.g., projected sales, number of customers, risk assessment).

[0265] 3. The server displays the report on the user's device via a dashboard.

[0266] 4. Users review the presented reports and use them to make data-driven decisions.

[0267] Through these steps, the system, which combines an emotion engine, efficiently supports data-driven decision-making and promotes better decision-making that takes users' emotions into account.

[0268] Example 2

[0269] 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."

[0270] In order for corporate managers to make efficient decisions, they need to effectively collect and analyze large amounts of data and use the results to make optimal decisions. However, this takes time and effort, which can distract managers from their core work. In addition, users' emotions can sometimes influence decision-making, and systems that do not take this into account may not produce optimal results.

[0271] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0272] In this invention, the server includes means for collecting necessary data, means for preprocessing the collected data, means for training a machine learning model using the preprocessed data, means for simulating multiple decision-making scenarios, means for presenting optimal decision-making results to the user, means for collecting and analyzing user emotion data, and means for adjusting the decision-making scenarios based on the emotion data. This allows managers to make quick and optimal decisions using a data-driven system, thereby maximizing work efficiency and labor productivity. Furthermore, taking user emotions into consideration enables more appropriate and reliable decision-making.

[0273] "Means for collecting data" refers to the technical means for automatically obtaining the necessary data from various data sources inside and outside the company.

[0274] "Data preprocessing means" refers to technical means for completing missing values ​​in collected data, removing noise, and converting the data into a unified format.

[0275] A "means for training a machine learning model" is a technical means for applying a machine learning algorithm to preprocessed data to create a model that makes predictions or classifications for a particular problem.

[0276] "Means for simulating decision-making scenarios" refers to technical means that use a trained machine learning model to try out multiple decision-making scenarios and select the optimal scenario based on the results.

[0277] "Means for presenting decision-making results to users" refers to technical means such as dashboards and report generation for presenting optimal decision-making results obtained through simulation to users.

[0278] "Means for collecting and analyzing emotional data" refers to technical means for collecting emotional data such as a user's facial expressions and tone of voice in real time and analyzing this data to understand the user's emotional state.

[0279] "Means for adjusting decision-making scenarios based on emotional data" refers to technical means for adjusting the explanation method and content of decision-making scenarios based on collected emotional data of users, to adapt them to the emotional state of the users.

[0280] This invention relates to a data-driven decision-making system that helps corporate managers make efficient decisions, and in particular, to a system that further improves the decision-making process by incorporating an emotion engine that recognizes user emotions. This system integrates data collection, preprocessing, machine learning model training, decision-making simulation, and result presentation, aiming to reduce the time managers spend on decision-making and maximize labor productivity.

[0281] The system includes the following major components:

[0282] Data collection methods

[0283] The server collects the necessary data from inside and outside the company. Specific data sources include sales databases, customer relationship management systems (CRM), market trend data from the Internet, industry reports, news APIs, etc. For example, the server uses SQL queries to extract sales data from the sales database for the past five years, or collects market trend data through APIs.

[0284] Data preprocessing measures

[0285] The server completes the collected data by filling in missing values, removing noise, and converting data from different formats into a unified format using Python's Pandas and Scikit-learn libraries. For example, the server scales and normalizes the data to prepare it for analysis.

[0286] Model creation and training methods

[0287] The server trains a machine learning model using the preprocessed data. Specifically, it splits the data into training data and test data, creates a random forest or deep learning model using the Scikit-learn library, and performs cross-validation to evaluate the model's performance. For example, a model can be trained using past market launch data to predict the success rate of a new product.

[0288] Decision-making simulation tools

[0289] The server sets up multiple decision-making scenarios based on the trained model and runs simulations. It calculates the probability of success and return on investment (ROI) for each scenario and selects the optimal decision. For example, it simulates scenarios that change the timing of new product launches, pricing, marketing strategies, etc.

[0290] Presentation of results

[0291] The server generates a dashboard to present the optimal decision-making results to the user. The dashboard displays visual reports and concrete action plans. For example, the server uses the Matplotlib library to draw graphs and present information in an easy-to-understand format to the user.

[0292] emotion recognition means

[0293] The server uses an emotion engine to collect and analyze the user's facial expression data and tone of voice in real time. This allows it to understand the user's emotional state and adjust the explanation and presentation of the decision-making scenario accordingly. For example, if the user is feeling anxious, the server will take that emotion into account and provide a more thorough explanation.

[0294] Specific examples

[0295] For example, if a company is considering launching a new product, the process using this system would proceed as follows:

[0296] 1. The server automatically collects sales data, customer purchase history, current market trends, competitor activity, etc.

[0297] 2. The server cleanses the collected data, imputes missing values, filters outliers, and consolidates the data into a unified format.

[0298] 3. The server uses the split data to train a machine learning model, for example, to predict the success rate of a new product based on past market launch data.

[0299] 4. The server simulates multiple scenarios that change the timing of new product launches, pricing, and marketing strategies, and calculates the probability of success and return on investment (ROI) for each scenario.

[0300] 5. The server uses an emotion engine to analyze the user's facial expressions and tone of voice to recognize their emotional state in real time. For example, if the user is feeling anxious, the server will adjust the explanation of the decision-making scenario to take that emotion into account.

[0301] 6. The server recommends the most effective strategy to the user (e.g., "Launch at full price in April and conduct a large-scale marketing campaign") and provides the reasons for the recommendation and the expected results in detail via a dashboard.

[0302] Prompt Sentence Examples

[0303] You are considering launching a new product. Based on sales data, customer purchase history, and current market trend data, please predict the following:

[0304] 1. Optimal time to market

[0305] 2. Optimal pricing level

[0306] 3. Optimal marketing strategies

[0307] Furthermore, based on these scenarios, we would like you to analyze the user's reactions using an emotion engine and suggest optimal decisions.

[0308] In this way, the system provides an effective means for making data-driven decisions, and by taking user emotions into account, it supports more reliable decision-making.

[0309] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0310] Step 1:

[0311] The server collects the necessary data from a sales database, a customer relationship management system (CRM), a market trend data API, an industry report API, etc. For example, the server runs an SQL query against the sales database to retrieve sales data for the past five years. It also sends an API request to retrieve the latest market trend data. This gives the server an input dataset to integrate data from each data source.

[0312] Step 2:

[0313] The server preprocesses the collected data by completing missing values, removing noise, and unifying different data formats. Specifically, it uses Python's Pandas library to convert data from different sources into DataFrame format, and then uses Scikit-learn's Imputer class to complete missing values. It also performs outlier filtering, scaling, and normalizing the data. The server then outputs a preprocessed dataset in a format suitable for analysis.

[0314] Step 3:

[0315] The server splits the preprocessed dataset into training data and test data. Specifically, it uses Scikit-learn's train_test_split function to set 80% of the data as training data and 20% as test data. The server then trains a model using a machine learning algorithm. For example, it uses a random forest algorithm to create a model that predicts the success rate of a new product based on historical market data. Through this training process, the server outputs a predictive model.

[0316] Step 4:

[0317] The server uses the trained predictive model to simulate multiple decision-making scenarios. Specifically, it tests various patterns of pricing, launch timing, and marketing strategies for new products, and calculates the success probability and return on investment (ROI) for each. For example, it uses the Markov Chain Monte Carlo (MCMC) method to simulate the success probability for various scenarios. The server then outputs the simulation results for each scenario.

[0318] Step 5:

[0319] The server uses an emotion engine to collect and analyze the user's emotional data (facial expressions and tone of voice) in real time. Specifically, it uses an emotion analysis API to process data acquired from the camera and microphone to understand the user's emotional state. For example, if the user is feeling anxious, that emotional data is taken as input and works with other modules in the system to take appropriate action. The server then outputs the user's emotional data.

[0320] Step 6:

[0321] The server presents the optimal decision-making result to the user based on the simulation results and the user's emotional state. Specifically, it generates a dashboard and displays visual reports and specific action plans. For example, it uses the Matplotlib library to draw graphs of success probability and ROI, providing information in an intuitive format for the user. This allows the server to output the optimal decision-making result and present it to the user.

[0322] Through the above process, this system supports data-driven decision-making while also supporting more accurate decision-making that takes into account the user's emotions.

[0323] (Application example 2)

[0324] 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."

[0325] While conventional data-driven decision-making systems use data analysis and machine learning to make efficient decisions, they do not take into account the emotional state of the user, which means they ignore the impact that the mental and physical state of managers and workers, in particular, has on the results. Furthermore, in factory production management, there is a lack of a way to present optimal production schedules that reflect the stress and fatigue levels of workers, which risks reducing labor productivity and work efficiency. To solve this problem, a system is needed that recognizes the user's emotional state in real time and adjusts decision-making based on that.

[0326] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting necessary data, means for preprocessing the collected data, means for training a machine learning model using the preprocessed data, means for simulating multiple decision-making scenarios, means for presenting optimal decision-making results to the user, means for recognizing the user's emotional state, and means for adjusting decision-making based on the recognized emotional state. This enables more appropriate decision-making that takes the user's physical and mental state into consideration, and can also improve labor productivity in factory production management while reducing worker stress and fatigue.

[0327] "Means of collecting data" refers to devices and systems for collecting a variety of information, such as production data within the factory, equipment operation data, and worker work history and emotional data.

[0328] "Means for preprocessing data" refers to devices or systems that cleanse collected data, fill in missing values, remove noise, and format the data in a way that is suitable for analysis.

[0329] A "means for training a machine learning model" is a device or system that uses preprocessed data to learn various patterns and create and optimize models that can be used for subsequent decision-making.

[0330] A "means for simulating decision-making scenarios" is a device or system that assumes multiple possible scenarios and performs calculations to predict the outcomes.

[0331] The "means for presenting optimal decision-making results to the user" refers to a device or system equipped with a dashboard or interface for analyzing the simulation results and presenting them to the user in an easy-to-understand format.

[0332] The "means for recognizing the user's emotional state" refers to a device or system equipped with an emotion engine or sensor that analyzes the facial expressions and tone of voice of workers and managers to recognize their emotional state in real time.

[0333] A "means for adjusting decision-making based on emotional state" is a device or system that adjusts the explanation or proposal content of a decision-making scenario according to the recognized emotional state, thereby supporting more appropriate decision-making.

[0334] This invention relates to a system for managing production within a factory. This system collects and preprocesses necessary data, such as production data, equipment operation data, and worker work history, and then trains a machine learning model to simulate multiple decision-making scenarios and present the optimal results to the user. The system can also recognize the user's emotional state and adjust decision-making based on that.

[0335] System Configuration

[0336] Hardware

[0337] The server is equipped with a database for collecting and storing data, a high-performance CPU and GPU for training and running machine learning models, and sensors such as cameras and microphones for detecting the emotional state of workers.

[0338] software

[0339] The software used includes Pandas for data preprocessing, scikit-learn and TensorFlow for creating machine learning models, and EmotionEngine for emotion recognition.

[0340] Data collection and preprocessing

[0341] The server collects production data, equipment operation data, and worker work history in real time from sensors installed on each piece of equipment and work station in the factory. The collected data is preprocessed using Pandas to cleanse the data, fill in missing values, and remove noise. This generates clean data suitable for analysis.

[0342] Training the model

[0343] The preprocessed data is used to train a machine learning model using scikit-learn and TensorFlow. Data used to train the model is used to optimize production schedules and provide predictive maintenance functions for equipment. This makes it possible to predict optimal production plans and maintenance timing.

[0344] Decision-making simulation

[0345] Using the trained model, multiple decision-making scenarios are simulated on the server, including scenarios for changes to production schedules and marketing strategies. The results of each scenario are compared, and the most effective decision is presented to the user.

[0346] Emotion recognition and decision-making regulation

[0347] The server uses the EmotionEngine, an emotion recognition engine, to analyze the worker's facial expressions and tone of voice to recognize their emotional state in real time. Based on the recognized emotional state, the server adjusts the decision-making scenario and presents the optimal action plan that takes into account the user's mental health.

[0348] Presentation of results

[0349] The server presents the optimal decision-making results to the user via a dashboard, where the user can view the details of the proposed strategy and the expected results. A concrete action plan is also provided, allowing the user to take immediate action.

[0350] Examples of concrete examples and prompts

[0351] For example, consider a situation where a problem occurs on a factory production line and an urgent readjustment of the production schedule is required. In this case, the emotion recognition engine detects the stress of the workers, and the system proposes an optimal production schedule and break plan.

[0352] Example prompts to input to a generative AI model:

[0353] "Please suggest optimal production schedules and break plans based on current production line data, equipment status, and worker emotional states."

[0354] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0355] Step 1:

[0356] The server collects production data, equipment operation data, and worker work history in real time from sensors installed on each piece of equipment and work station in the factory. This includes the specific operation of sending the data acquired from each sensor to the collection server via a network. The input is sensor data, and the output is collected and accumulated data.

[0357] Step 2:

[0358] The server performs data preprocessing. It cleanses the collected production data, equipment operation data, and worker work history data, filling in missing values ​​and removing noise. At this stage, Pandas is used to unify the data format and format it into a form that is easy to analyze. The input is the collected data, and the output is preprocessed, clean data.

[0359] Step 3:

[0360] The server uses the preprocessed data to train a machine learning model. Specifically, it splits the dataset into training data and test data using scikit-learn or TensorFlow, and then uses a machine learning algorithm to create and train the optimal model. The input is the preprocessed data, and the output is a trained machine learning model.

[0361] Step 4:

[0362] The server uses the trained model to simulate multiple decision-making scenarios. For example, it predicts and compares the outcomes of each scenario when changes are made to production schedules or equipment maintenance schedules. The inputs are the trained machine learning model and scenario data, and the output is the simulation results for each scenario.

[0363] Step 5:

[0364] The server uses an emotion recognition engine to recognize the emotional state of workers in real time. Specifically, it uses the Emotion Engine to analyze facial expressions and tone of voice obtained from cameras and microphones to identify the worker's stress level and fatigue state. The input is sensor data from the cameras and microphones, and the output is the worker's emotional state.

[0365] Step 6:

[0366] The server adjusts the decision-making scenario based on the recognized emotional state. For example, if a worker is experiencing high stress or fatigue, the server reevaluates and adjusts the production schedule or rest plan. The inputs are emotional state data and simulation results, and the output is the adjusted decision-making scenario.

[0367] Step 7:

[0368] The server presents the optimal decision-making results to the user. Specifically, it uses a dashboard to visually present the user with optimal production schedules, equipment maintenance schedules, worker care plans, etc. The input is the adjusted decision-making scenario, and the output is a specific action plan presented to the user.

[0369] 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.

[0370] 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.

[0371] 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.

[0372] [Second embodiment]

[0373] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0374] 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.

[0375] 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).

[0376] 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.

[0377] 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.

[0378] 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).

[0379] 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.

[0380] 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.

[0381] 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.

[0382] 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.

[0383] 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.

[0384] 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."

[0385] This invention relates to a data-driven decision-making system that enables corporate managers to make efficient decisions. This system integrates data collection, preprocessing, machine learning model training, decision-making simulation, and result presentation, with the aim of reducing the time managers spend on decision-making and maximizing labor productivity.

[0386] Overall system overview

[0387] The system includes the following major components:

[0388] 1. Data collection methods:

[0389] The server collects the necessary data from various sources, both inside and outside the company, including sales databases, customer relationship management systems (CRM), market trend data from the Internet, industry reports, and news APIs.

[0390] 2. Data preprocessing methods:

[0391] The server preprocesses the collected data and converts it into a format suitable for analysis: removing incomplete data and noise, integrating data from different sources, and normalizing the data if necessary.

[0392] 3. Model creation and training methods:

[0393] The server uses the preprocessed data to train a machine learning model, splitting the dataset into training data and test data, creating and optimizing the model using a machine learning algorithm, and evaluating its performance.

[0394] 4. Decision-making simulation tools:

[0395] The server uses the trained model to simulate various decision-making scenarios, compares the results of each scenario, and selects the optimal decision based on business goals.

[0396] 5. Presentation of results:

[0397] The server presents the optimal decision-making results to the user, generates reports through a dashboard, and presents the user with a clear and specific action plan.

[0398] Specific Examples

[0399] For example, if a company is considering launching a new product, the process using this system would proceed as follows:

[0400] 1. Data Collection:

[0401] The server automatically collects sales data, customer purchase history, current market trends, competitor activity, and more.

[0402] 2. Data Preprocessing:

[0403] The server cleanses the collected data, imputes missing values, filters outliers, and also consolidates and converts the data into a unified format.

[0404] 3. Model creation and training:

[0405] The server uses the data split into training and test data to train a machine learning model, for example, to create a model that predicts the success rate of a new product based on past market launch data.

[0406] 4. Decision-making simulation:

[0407] The server simulates multiple scenarios that change the timing of new product launches, pricing, and marketing strategies, and calculates the probability of success and return on investment (ROI) for each scenario.

[0408] 5. Presentation of results:

[0409] The server will suggest the most effective strategy to the user (for example, "launch at full price in April and conduct a large-scale marketing campaign"). The server will then provide the user with detailed reasons for the suggestion and expected results via a dashboard. The user can then create a specific action plan based on this information.

[0410] Through the above process, the system of the present invention supports data-driven decision-making and enables corporate managers to efficiently tackle problem-solving.

[0411] The processing flow will be explained below.

[0412] Program processing flow

[0413] Step 1: Data collection

[0414] The server collects the necessary data from inside and outside the company.

[0415] 1. The server connects to the sales database and extracts the sales data.

[0416] 2. The server retrieves customer feedback and purchase history from the customer relationship management system (CRM).

[0417] 3. The server scrapes market trend data using public APIs on the Internet.

[0418] 4. The server collects competitor trend data from news APIs and industry reports.

[0419] Step 2: Data Preprocessing

[0420] The server pre-processes the collected data and converts it into a format suitable for analysis.

[0421] 1. The server identifies incomplete data and missing values ​​in the generated database and imputes or removes them appropriately.

[0422] 2. The server detects and filters outliers and errors.

[0423] 3. The server consolidates data from different sources and normalizes it for consistency.

[0424] 4. The server normalizes and unifies inconsistent data formats.

[0425] Step 3: Model creation and training

[0426] The server uses the preprocessed data to create and train a machine learning model.

[0427] 1. The server splits the dataset into training data and test data.

[0428] 2. The server trains the model using the machine learning algorithm of your choice (e.g., decision tree, random forest, neural network).

[0429] 3. The server uses historical data to optimize the model parameters.

[0430] 4. The server uses the test data to calculate evaluation metrics such as precision, recall, and F1 score of the trained model and evaluate the model's performance.

[0431] Step 4: Decision-making simulation

[0432] The server uses the trained model to simulate multiple decision-making scenarios.

[0433] 1. The server generates different scenarios for new product launch timing, pricing, marketing strategies, etc.

[0434] 2. The server applies the model to each scenario and predicts future sales, customer acquisition, ROI (return on investment), etc.

[0435] 3. The server compares the results of each scenario and evaluates them based on business goals.

[0436] 4. The server selects the most advantageous scenario and proposes a strategy.

[0437] Step 5: Presenting the results

[0438] The server generates the optimal decision-making results as a report and presents it to the user.

[0439] 1. The server creates a report based on the data from the optimal decision-making scenario.

[0440] 2. The server will provide a report with the reasons for the recommendation and the specific results expected (e.g., projected sales, number of customers, risk assessment).

[0441] 3. The server displays the report on the user's device via a dashboard.

[0442] 4. Users review the presented reports and use them to make data-driven decisions.

[0443] Through these steps, the system effectively supports data-driven decision making.

[0444] Example 1

[0445] 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."

[0446] When corporate managers make decisions, the time and effort required to efficiently collect, preprocess, and analyze massive amounts of data to make optimal decisions is a major challenge. Traditional methods pose the risk of incorrect decision-making due to data inconsistencies, missing data, or noise. Furthermore, the process of simulating various scenarios and identifying optimal strategies is complex and requires advanced expertise. There is a need for a system that can solve these challenges and improve the accuracy and efficiency of decision-making.

[0447] 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.

[0448] In this invention, the server includes means for collecting necessary data, means for preprocessing the collected data, means for training a machine learning model using the preprocessed data, means for simulating multiple decision-making scenarios, and means for presenting the optimal decision-making results to users. This allows corporate managers to efficiently use massive amounts of data and make quick and accurate decisions. Furthermore, by dividing the data and applying machine learning algorithms, the performance of the model can be optimized, and comparative analysis between different scenarios can be performed to derive the optimal strategy. Furthermore, by visualizing the simulation results and presenting them through a dashboard, users can intuitively understand the results and formulate executable action plans.

[0449] "Means for collecting data" refers to methods and devices for efficiently obtaining necessary data from multiple data sources inside and outside the company.

[0450] "Data preprocessing means" refers to a method or device for imputing missing values, removing noise, integrating, and normalizing collected data, and converting it into a form suitable for analysis.

[0451] A "means for training a machine learning model" is a method or apparatus that uses preprocessed data, splits it into training data and test data, and creates and optimizes a model using a machine learning algorithm.

[0452] A "means for simulating decision-making scenarios" is a method or device that uses a trained machine learning model to construct various decision-making scenarios and calculate the probability of success and return on investment (ROI).

[0453] "Means for presenting optimal decision-making results to users" refers to a method or device for presenting optimal strategies and results obtained from a simulation to users in an easy-to-understand manner through an interface such as a dashboard.

[0454] "Means for detecting and filtering noise in data" refers to methods and devices for detecting inconsistencies and outliers in data and removing data that is unsuitable for analysis.

[0455] A "means for splitting a dataset" is a method for splitting data into training data and test data for training and evaluating a machine learning model.

[0456] The "means for calculating the probability of success and return on investment for each scenario" refers to a method or device for statistically evaluating the results of each decision-making scenario and calculating the probability of success and return on investment.

[0457] A "means for visualizing simulation results" is a method or device for displaying the results of a simulation in a visual format such as a graph or chart, allowing users to intuitively understand the results.

[0458] A "dashboard" is a user interface that allows users to centrally view and operate information obtained from the system.

[0459] This invention relates to a data-driven decision-making system that enables corporate managers to make efficient decisions. This system integrates data collection, preprocessing, machine learning model training, decision-making simulation, and result presentation, with the aim of reducing the time managers spend on decision-making and maximizing labor productivity.

[0460] Overall system overview

[0461] The system includes the following major components:

[0462] Data collection methods

[0463] Data preprocessing measures

[0464] How to train machine learning models

[0465] Decision-making simulation tools

[0466] Presentation of results

[0467] Data collection methods

[0468] The server automatically collects the required data from multiple data sources, both internal and external to the company. It uses Python's requests and pandas libraries to execute API requests and database queries. For example, it retrieves sales data from a sales database and customer information from a CRM system. It also uses external APIs (e.g., Google Trends API) to collect market trend data and news APIs (e.g., NewsAPI) to retrieve the latest industry reports and news.

[0469] Data preprocessing measures

[0470] The server preprocesses the collected data and converts it into a format suitable for analysis. This process includes data cleansing, missing value completion, noise removal, data integration from different sources, and normalization. Specifically, data processing is performed using the Python pandas and numpy libraries.

[0471] How to train machine learning models

[0472] The server trains a machine learning model using the preprocessed data. It splits the dataset into training data and test data, and creates and optimizes the model using a machine learning algorithm (e.g., random forest, linear regression). The model is trained using libraries such as scikit-learn, TensorFlow, and Keras.

[0473] Decision-making simulation tools

[0474] The server uses the trained model to simulate various decision-making scenarios, such as the timing of new product launches, pricing, and marketing strategies, and calculates the probability of success and return on investment (ROI) for each scenario.

[0475] Presentation of results

[0476] The server presents the optimal decision-making results to the user. Here, the simulation results are visualized and displayed on a dashboard. Tools such as matplotlib and dash are used to build a user-friendly interface. Through the dashboard, the user can formulate a specific action plan.

[0477] Specific Examples

[0478] For example, if a company is considering launching a new product into the market, the system would implement the following process:

[0479] 1. Data collection: The server automatically collects data such as sales data, customer purchase history, current market trends, and competitor activity.

[0480] 2. Data Preprocessing: The server cleanses the collected data, imputes missing values, filters outliers, and integrates data from different sources into a unified format.

[0481] 3. Model creation and training: The server splits the preprocessed dataset into training data and test data, and trains a machine learning model, for example, to predict the success rate of a new product based on historical market launch data.

[0482] 4. Decision-making simulation: The server simulates multiple scenarios that change the timing of new product launches, pricing, and marketing strategies, and calculates the probability of success and return on investment (ROI) for each scenario.

[0483] 5. Presentation of results: The server proposes the most effective strategy to the user. For example, if it determines that launching at full price in April and running a large-scale marketing campaign is the optimal strategy, the server will present the reasons for this proposal and the expected results in detail via a dashboard. The user can then formulate a specific action plan based on this information.

[0484] Prompt Sentence Examples

[0485] "Imagine a company is introducing a new product in April. Collect and preprocess data such as sales data, customer purchase history, market trends, and competitor behavior, and train a machine learning model to predict the success rate of the new product launch. Then, create multiple simulation scenarios to suggest optimal launch timing, pricing, and marketing strategies, compare them, and select the optimal strategy to present in a dashboard."

[0486] In this way, the system of the present invention supports data-driven decision making and enables corporate managers to efficiently tackle problems.

[0487] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0488] Step 1: Data collection

[0489] The server collects the required data from multiple data sources, both internal and external to the company. Inputs include a sales database, CRM system, market trend API, and news API. Based on this input, the server makes API requests using Python's requests library and executes database queries using the pandas library. Specific operations include retrieving data from the sales database, retrieving customer purchase history, and scraping and collecting the latest market trends and competitor activity. The output is the raw data retrieved from the various data sources.

[0490] Step 2: Data Preprocessing

[0491] The server preprocesses the collected raw data and converts it into a format suitable for analysis. The input includes the collected raw data. Based on this input, the server cleanses the data, imputes missing values, removes noise, integrates data from different sources, and normalizes it. Specifically, it uses Python's pandas and numpy libraries to process the data and generate clean data suitable for analysis. The output is a preprocessed, integrated dataset.

[0492] Step 3: Model creation and training

[0493] The server trains a machine learning model using a preprocessed dataset. The input includes the preprocessed dataset. Based on this input, the server splits the dataset into training data and test data, and creates and optimizes a model using a machine learning algorithm (e.g., random forest, linear regression). Specifically, it uses libraries such as scikit-learn, TensorFlow, and Keras to build the model and evaluate its performance. The output is a trained machine learning model.

[0494] Step 4: Decision-making simulation

[0495] The server uses the trained model to simulate various decision-making scenarios. The inputs include the trained machine learning model and the scenarios to be simulated (e.g., launch timing, pricing, marketing strategy). Based on these inputs, the server inputs each scenario into the model and calculates the probability of success and return on investment (ROI). Specifically, it constructs simulation scenarios in Python and applies them to the model. The output is the resulting data, including the probability of success and ROI for each scenario.

[0496] Step 5: Presenting the results

[0497] The server presents the simulation results to the user. The input includes the simulation result data. Based on this input, the server visualizes the results and displays them to the user through a dashboard. Specifically, it uses matplotlib and dash to create graphs and charts and displays the results on a web dashboard. The output is a dashboard that the user can view.

[0498] Through the above steps, this system can perform consistent processing from data collection to result presentation, supporting efficient decision-making.

[0499] (Application example 1)

[0500] 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."

[0501] In real-time traffic volume analysis and route optimization for autonomous vehicles, conventional methods require a lot of time and resources for data collection and preprocessing, making it difficult to make quick decisions.Furthermore, there was no system for comparing multiple traffic scenarios, making it difficult to present optimal routes in real time.

[0502] 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.

[0503] In this invention, the server includes means for collecting necessary data, means for preprocessing the collected data, means for training a machine learning model using the preprocessed data, means for acquiring current traffic condition data and simulating multiple route optimization scenarios, and means for presenting an optimal route to a user, thereby enabling real-time traffic condition analysis and prompt presentation of an optimal route based on multiple scenarios.

[0504] "Necessary data" refers to information necessary to understand traffic conditions, such as traffic volume, traffic speed, accident information, and weather conditions.

[0505] "Preprocessing" is the process of cleansing data after collection, filling in missing values, filtering outliers, integrating and normalizing the data.

[0506] A "machine learning model" is an algorithm that is trained using preprocessed data to predict current and future conditions based on past data.

[0507] "Traffic condition data" is data that indicates the current state of road traffic, and includes, for example, traffic volume, traffic speed, accident information, weather conditions, and the like.

[0508] A "route optimization scenario" is a scenario that simulates multiple routes based on traffic condition data to identify the most efficient or safe route.

[0509] The "optimal route" is the route that is deemed most desirable in terms of shortest time, least energy consumption, safety, etc., after comparing multiple route optimization scenarios.

[0510] "Noise" refers to factors that impair the accuracy of data, such as outliers, errors, and missing values ​​in a dataset.

[0511] "Real-time traffic data" refers to data that shows the state of road traffic at the current time and that is collected and analyzed quickly.

[0512] The system that realizes this application example performs real-time traffic analysis and route optimization for autonomous vehicles. The system consists of a server, a terminal, and a user.

[0513] System Configuration

[0514] server

[0515] The server implements the following methods:

[0516] 1. Data collection method: The server collects real-time traffic condition data such as traffic volume, traffic speed, accident information, weather conditions, etc. This is done by retrieving data from external APIs (e.g., Google Maps API, Here API).

[0517] 2. Data preprocessing means: The server cleanses the collected data, imputes missing values, filters outliers, and performs data integration and normalization.

[0518] 3. Machine learning model training method: The server uses the preprocessed data to train the machine learning model. For training, it uses a machine learning library such as scikit-learn.

[0519] 4. Simulation method: The server obtains current traffic condition data and simulates multiple route optimization scenarios, thereby predicting travel times for multiple scenarios.

[0520] 5. Result presentation: The server presents the optimal route to the user based on the simulation results. The presentation is done via a smartphone or the display of the in-vehicle computer.

[0521] Terminal

[0522] The terminal (smartphone or in-vehicle computer) receives the optimal route information sent from the server and visually displays it to the user.

[0523] User

[0524] The user navigates the autonomous vehicle based on the displayed optimal route information, allowing the user to reach the destination via an optimized route, avoiding traffic congestion and obstacles.

[0525] Program processing

[0526] The program in this system performs the following operations:

[0527] Data collection method: Use data collection API to obtain real-time traffic information. For example, the server obtains the latest traffic information from Google Maps API and Here API every minute.

[0528] Data preprocessing methods: Data will be cleansed, integrated, and normalized using Python's pandas library, etc. Appropriate statistical methods will be used to impute missing values.

[0529] Machine learning model training method: Using scikit-learn, a random forest regression model is trained on the preprocessed data. The trained model predicts current and future traffic conditions based on past data.

[0530] Simulation method: Using the trained model, create new traffic scenarios and predict travel times for each scenario, thereby identifying the most efficient routes.

[0531] Result presentation method: The optimal route and the reasons for it are displayed on the device's user interface. For example, the optimal route is displayed on a map in a smartphone application, and is communicated to the user along with voice guidance.

[0532] Specific examples

[0533] For example, here is a prompt to input to a generative AI model:

[0534] "Get traffic information based on the current date, time, and location to train a machine learning model for route optimization. Input data includes traffic speed, traffic volume, and weather conditions. Propose new strategies and predict travel times for each scenario."

[0535] By using such prompt sentences, it becomes possible to suggest optimal routes that take real-time traffic conditions into consideration.

[0536] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0537] Step 1:

[0538] The server collects traffic data. Specifically, it uses Google Maps API and Here API to obtain real-time data such as traffic volume, traffic speed, accident information, and weather conditions. The input of this process is raw data from the API, and the output is the collected traffic data.

[0539] Step 2:

[0540] The server preprocesses the collected data. Specifically, it uses the Python pandas library to cleanse the data, impute missing values, and filter outliers. It also integrates the data and normalizes it into a unified format. The input of this process is the collected traffic situation data, and the output is the cleansed and normalized data.

[0541] Step 3:

[0542] The server uses the preprocessed data to train a machine learning model. Specifically, it uses a random forest regression model from scikit-learn and trains it on historical traffic data. It splits the data into training data and test data, and evaluates the model's performance. The input of this process is the cleansed and normalized data, and the output is a trained machine learning model.

[0543] Step 4:

[0544] The server retrieves current traffic data and simulates multiple route optimization scenarios. For example, it generates scenarios that vary specific time periods or weather conditions, and predicts travel times for each scenario. The inputs to this process are current traffic data and a trained machine learning model, and the output is predicted travel times for each scenario.

[0545] Step 5:

[0546] The server presents the optimal route to the user based on the simulation results. Specifically, it compares the travel time of each route, selects the most efficient route, and displays it on the user interface. The terminal (smartphone or in-vehicle computer) receives this information and provides visual and audio guidance to the user. The input to this process is the predicted travel time for each scenario, and the output is optimal route information presented to the user.

[0547] Step 6:

[0548] The user navigates based on the presented optimal route information. The autonomous vehicle's navigation system drives according to the optimal route, avoiding traffic congestion and obstacles to reach the destination. The input of this process is the optimal route information, and the output is the user's arrival at the destination.

[0549] 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.

[0550] This invention relates to a data-driven decision-making system for corporate managers to make efficient decisions, and in particular, to a system that further improves the decision-making process by incorporating an emotion engine that recognizes user emotions. This system integrates data collection, preprocessing, machine learning model training, decision-making simulation, and result presentation, aiming to reduce the time managers spend on decision-making and maximize labor productivity.

[0551] Overall system overview

[0552] The system includes the following major components:

[0553] 1. Data collection methods:

[0554] The server collects the necessary data from various sources, both inside and outside the company, including sales databases, customer relationship management systems (CRM), market trend data from the Internet, industry reports, and news APIs.

[0555] 2. Data preprocessing methods:

[0556] The server preprocesses the collected data and converts it into a format suitable for analysis: removing incomplete data and noise, integrating data from different sources, and normalizing the data if necessary.

[0557] 3. Model creation and training methods:

[0558] The server uses the preprocessed data to train a machine learning model, splitting the dataset into training data and test data, creating and optimizing the model using a machine learning algorithm, and evaluating its performance.

[0559] 4. Decision-making simulation tools:

[0560] The server uses the trained model to simulate various decision-making scenarios, compares the results of each scenario, and selects the optimal decision based on business goals.

[0561] 5. Presentation of results:

[0562] The server presents the optimal decision-making results to the user, generates reports through a dashboard, and presents the user with a clear and specific action plan.

[0563] 6. Emotion recognition means:

[0564] The server uses an emotion engine to collect and analyze the user's emotional data, allowing it to adjust the evaluation and optimization of decision-making scenarios based on the user's emotional state.

[0565] Specific Examples

[0566] For example, if a company is considering launching a new product, the process using this system would proceed as follows:

[0567] 1. Data Collection:

[0568] The server automatically collects sales data, customer purchase history, current market trends, competitor activity, and more.

[0569] 2. Data Preprocessing:

[0570] The server cleanses the collected data, imputes missing values, filters outliers, and also consolidates and converts the data into a unified format.

[0571] 3. Model creation and training:

[0572] The server uses the data split into training and test data to train a machine learning model, for example, to create a model that predicts the success rate of a new product based on past market launch data.

[0573] 4. Decision-making simulation:

[0574] The server simulates multiple scenarios that change the timing of new product launches, pricing, and marketing strategies, and calculates the probability of success and return on investment (ROI) for each scenario.

[0575] 5. Emotion recognition:

[0576] The server uses an emotion engine to analyze the user's facial expressions and tone of voice to recognize their emotional state in real time. For example, if the user is feeling anxious, the server will adjust the explanation of the decision-making scenario to take that emotion into account.

[0577] 6. Presentation of results:

[0578] The server recommends the most effective strategy to the user (e.g., "launch at full price in April and conduct a large-scale marketing campaign"). The server provides the user with detailed reasons for the recommendation and expected results via a dashboard. The user can then create a specific action plan based on this information.

[0579] By combining this system with an emotion engine, the system can make better decisions by taking the user's emotions into account. For example, if the user is feeling stressed, the system can suggest a more cautious approach. This makes the decision-making process more comfortable and trustworthy for the user.

[0580] The processing flow will be explained below.

[0581] Program processing flow

[0582] Step 1: Data collection

[0583] The server collects the necessary data from inside and outside the company.

[0584] 1. The server connects to the sales database and extracts the sales data.

[0585] 2. The server retrieves customer feedback and purchase history from the customer relationship management system (CRM).

[0586] 3. The server scrapes market trend data using public APIs on the Internet.

[0587] 4. The server collects competitor trend data from news APIs and industry reports.

[0588] Step 2: Data Preprocessing

[0589] The server pre-processes the collected data and converts it into a format suitable for analysis.

[0590] 1. The server identifies incomplete data and missing values ​​and imputes or removes them appropriately.

[0591] 2. The server detects and filters outliers and errors.

[0592] 3. The server consolidates data from different sources and normalizes it for consistency.

[0593] 4. The server normalizes and unifies inconsistent data formats.

[0594] Step 3: Model creation and training

[0595] The server uses the preprocessed data to create and train a machine learning model.

[0596] 1. The server splits the dataset into training data and test data.

[0597] 2. The server trains the model using the machine learning algorithm of your choice (e.g., decision tree, random forest, neural network).

[0598] 3. The server uses the training data to optimize the model parameters.

[0599] 4. The server uses the test data to calculate evaluation metrics such as precision, recall, and F1 score of the trained model and evaluate the model's performance.

[0600] Step 4: Decision-making simulation

[0601] The server uses the trained model to simulate multiple decision-making scenarios.

[0602] 1. The server generates different scenarios for new product launch timing, pricing, marketing strategies, etc.

[0603] 2. The server applies the model to each scenario and predicts future sales, customer acquisition, ROI (return on investment), etc.

[0604] 3. The server compares the results of each scenario and evaluates the best scenario based on business goals.

[0605] 4. The server selects the most favorable scenario and recommends that strategy.

[0606] Step 5: Emotion Recognition

[0607] The server uses an emotion engine to collect and analyze the user's emotion data.

[0608] 1. The server analyzes the user's facial expressions and tone of voice to recognize their emotional state in real time.

[0609] 2. The server accumulates the user's emotional data and tracks its changes.

[0610] 3. The server adjusts the evaluation of the decision scenario based on the user's emotional state.

[0611] 4. The server suggests a cautious approach if the user is experiencing stress or anxiety.

[0612] Step 6: Presenting the results

[0613] The server generates the optimal decision-making results as a report and presents it to the user.

[0614] 1. The server creates a report based on the data from the optimal decision-making scenario.

[0615] 2. The server will provide a report with the reasons for the recommendation and the specific results expected (e.g., projected sales, number of customers, risk assessment).

[0616] 3. The server displays the report on the user's device via a dashboard.

[0617] 4. Users review the presented reports and use them to make data-driven decisions.

[0618] Through these steps, the system, which combines an emotion engine, efficiently supports data-driven decision-making and promotes better decision-making that takes users' emotions into account.

[0619] Example 2

[0620] 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."

[0621] In order for corporate managers to make efficient decisions, they need to effectively collect and analyze large amounts of data and use the results to make optimal decisions. However, this takes time and effort, which can distract managers from their core work. In addition, users' emotions can sometimes influence decision-making, and systems that do not take this into account may not produce optimal results.

[0622] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0623] In this invention, the server includes means for collecting necessary data, means for preprocessing the collected data, means for training a machine learning model using the preprocessed data, means for simulating multiple decision-making scenarios, means for presenting optimal decision-making results to the user, means for collecting and analyzing user emotion data, and means for adjusting the decision-making scenarios based on the emotion data. This allows managers to make quick and optimal decisions using a data-driven system, thereby maximizing work efficiency and labor productivity. Furthermore, taking user emotions into consideration enables more appropriate and reliable decision-making.

[0624] "Means for collecting data" refers to the technical means for automatically obtaining the necessary data from various data sources inside and outside the company.

[0625] "Data preprocessing means" refers to technical means for completing missing values ​​in collected data, removing noise, and converting the data into a unified format.

[0626] A "means for training a machine learning model" is a technical means for applying a machine learning algorithm to preprocessed data to create a model that makes predictions or classifications for a particular problem.

[0627] "Means for simulating decision-making scenarios" refers to technical means that use a trained machine learning model to try out multiple decision-making scenarios and select the optimal scenario based on the results.

[0628] "Means for presenting decision-making results to users" refers to technical means such as dashboards and report generation for presenting optimal decision-making results obtained through simulation to users.

[0629] "Means for collecting and analyzing emotional data" refers to technical means for collecting emotional data such as a user's facial expressions and tone of voice in real time and analyzing this data to understand the user's emotional state.

[0630] "Means for adjusting decision-making scenarios based on emotional data" refers to technical means for adjusting the explanation method and content of decision-making scenarios based on collected emotional data of users, to adapt them to the emotional state of the users.

[0631] This invention relates to a data-driven decision-making system that helps corporate managers make efficient decisions, and in particular, to a system that further improves the decision-making process by incorporating an emotion engine that recognizes user emotions. This system integrates data collection, preprocessing, machine learning model training, decision-making simulation, and result presentation, aiming to reduce the time managers spend on decision-making and maximize labor productivity.

[0632] The system includes the following major components:

[0633] Data collection methods

[0634] The server collects the necessary data from inside and outside the company. Specific data sources include sales databases, customer relationship management systems (CRM), market trend data from the Internet, industry reports, news APIs, etc. For example, the server uses SQL queries to extract sales data from the sales database for the past five years, or collects market trend data through APIs.

[0635] Data preprocessing measures

[0636] The server completes the collected data by filling in missing values, removing noise, and converting data from different formats into a unified format using Python's Pandas and Scikit-learn libraries. For example, the server scales and normalizes the data to prepare it for analysis.

[0637] Model creation and training methods

[0638] The server trains a machine learning model using the preprocessed data. Specifically, it splits the data into training data and test data, creates a random forest or deep learning model using the Scikit-learn library, and performs cross-validation to evaluate the model's performance. For example, a model can be trained using past market launch data to predict the success rate of a new product.

[0639] Decision-making simulation tools

[0640] The server sets up multiple decision-making scenarios based on the trained model and runs simulations. It calculates the probability of success and return on investment (ROI) for each scenario and selects the optimal decision. For example, it simulates scenarios that change the timing of new product launches, pricing, marketing strategies, etc.

[0641] Presentation of results

[0642] The server generates a dashboard to present the optimal decision-making results to the user. The dashboard displays visual reports and concrete action plans. For example, the server uses the Matplotlib library to draw graphs and present information in an easy-to-understand format to the user.

[0643] emotion recognition means

[0644] The server uses an emotion engine to collect and analyze the user's facial expression data and tone of voice in real time. This allows it to understand the user's emotional state and adjust the explanation and presentation of the decision-making scenario accordingly. For example, if the user is feeling anxious, the server will take that emotion into account and provide a more thorough explanation.

[0645] Specific examples

[0646] For example, if a company is considering launching a new product, the process using this system would proceed as follows:

[0647] 1. The server automatically collects sales data, customer purchase history, current market trends, competitor activity, etc.

[0648] 2. The server cleanses the collected data, imputes missing values, filters outliers, and consolidates the data into a unified format.

[0649] 3. The server uses the split data to train a machine learning model, for example, to predict the success rate of a new product based on past market launch data.

[0650] 4. The server simulates multiple scenarios that change the timing of new product launches, pricing, and marketing strategies, and calculates the probability of success and return on investment (ROI) for each scenario.

[0651] 5. The server uses an emotion engine to analyze the user's facial expressions and tone of voice to recognize their emotional state in real time. For example, if the user is feeling anxious, the server will adjust the explanation of the decision-making scenario to take that emotion into account.

[0652] 6. The server recommends the most effective strategy to the user (e.g., "Launch at full price in April and conduct a large-scale marketing campaign") and provides the reasons for the recommendation and the expected results in detail via a dashboard.

[0653] Prompt Sentence Examples

[0654] You are considering launching a new product. Based on sales data, customer purchase history, and current market trend data, please predict the following:

[0655] 1. Optimal time to market

[0656] 2. Optimal pricing level

[0657] 3. Optimal marketing strategies

[0658] Furthermore, based on these scenarios, we would like you to analyze the user's reactions using an emotion engine and suggest optimal decisions.

[0659] In this way, the system provides an effective means for making data-driven decisions, and by taking user emotions into account, it supports more reliable decision-making.

[0660] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0661] Step 1:

[0662] The server collects the necessary data from a sales database, a customer relationship management system (CRM), a market trend data API, an industry report API, etc. For example, the server runs an SQL query against the sales database to retrieve sales data for the past five years. It also sends an API request to retrieve the latest market trend data. This gives the server an input dataset to integrate data from each data source.

[0663] Step 2:

[0664] The server preprocesses the collected data by completing missing values, removing noise, and unifying different data formats. Specifically, it uses Python's Pandas library to convert data from different sources into DataFrame format, and then uses Scikit-learn's Imputer class to complete missing values. It also performs outlier filtering, scaling, and normalizing the data. The server then outputs a preprocessed dataset in a format suitable for analysis.

[0665] Step 3:

[0666] The server splits the preprocessed dataset into training data and test data. Specifically, it uses Scikit-learn's train_test_split function to set 80% of the data as training data and 20% as test data. The server then trains a model using a machine learning algorithm. For example, it uses a random forest algorithm to create a model that predicts the success rate of a new product based on historical market data. Through this training process, the server outputs a predictive model.

[0667] Step 4:

[0668] The server uses the trained predictive model to simulate multiple decision-making scenarios. Specifically, it tests various patterns of pricing, launch timing, and marketing strategies for new products, and calculates the success probability and return on investment (ROI) for each. For example, it uses the Markov Chain Monte Carlo (MCMC) method to simulate the success probability for various scenarios. The server then outputs the simulation results for each scenario.

[0669] Step 5:

[0670] The server uses an emotion engine to collect and analyze the user's emotional data (facial expressions and tone of voice) in real time. Specifically, it uses an emotion analysis API to process data acquired from the camera and microphone to understand the user's emotional state. For example, if the user is feeling anxious, that emotional data is taken as input and works with other modules in the system to take appropriate action. The server then outputs the user's emotional data.

[0671] Step 6:

[0672] The server presents the optimal decision-making result to the user based on the simulation results and the user's emotional state. Specifically, it generates a dashboard and displays visual reports and specific action plans. For example, it uses the Matplotlib library to draw graphs of success probability and ROI, providing information in an intuitive format for the user. This allows the server to output the optimal decision-making result and present it to the user.

[0673] Through the above process, this system supports data-driven decision-making while also supporting more accurate decision-making that takes into account the user's emotions.

[0674] (Application example 2)

[0675] 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."

[0676] While conventional data-driven decision-making systems use data analysis and machine learning to make efficient decisions, they do not take into account the emotional state of the user, which means they ignore the impact that the mental and physical state of managers and workers, in particular, has on the results. Furthermore, in factory production management, there is a lack of a way to present optimal production schedules that reflect the stress and fatigue levels of workers, which risks reducing labor productivity and work efficiency. To solve this problem, a system is needed that recognizes the user's emotional state in real time and adjusts decision-making based on that.

[0677] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting necessary data, means for preprocessing the collected data, means for training a machine learning model using the preprocessed data, means for simulating multiple decision-making scenarios, means for presenting optimal decision-making results to the user, means for recognizing the user's emotional state, and means for adjusting decision-making based on the recognized emotional state. This enables more appropriate decision-making that takes the user's physical and mental state into consideration, and can also improve labor productivity in factory production management while reducing worker stress and fatigue.

[0678] "Means of collecting data" refers to devices and systems for collecting a variety of information, such as production data within the factory, equipment operation data, and worker work history and emotional data.

[0679] "Means for preprocessing data" refers to devices or systems that cleanse collected data, fill in missing values, remove noise, and format the data in a way that is suitable for analysis.

[0680] A "means for training a machine learning model" is a device or system that uses preprocessed data to learn various patterns and create and optimize models that can be used for subsequent decision-making.

[0681] A "means for simulating decision-making scenarios" is a device or system that assumes multiple possible scenarios and performs calculations to predict the outcomes.

[0682] The "means for presenting optimal decision-making results to the user" refers to a device or system equipped with a dashboard or interface for analyzing the simulation results and presenting them to the user in an easy-to-understand format.

[0683] The "means for recognizing the user's emotional state" refers to a device or system equipped with an emotion engine or sensor that analyzes the facial expressions and tone of voice of workers and managers to recognize their emotional state in real time.

[0684] A "means for adjusting decision-making based on emotional state" is a device or system that adjusts the explanation or proposal content of a decision-making scenario according to the recognized emotional state, thereby supporting more appropriate decision-making.

[0685] This invention relates to a system for managing production within a factory. This system collects and preprocesses necessary data, such as production data, equipment operation data, and worker work history, and then trains a machine learning model to simulate multiple decision-making scenarios and present the optimal results to the user. The system can also recognize the user's emotional state and adjust decision-making based on that.

[0686] System Configuration

[0687] Hardware

[0688] The server is equipped with a database for collecting and storing data, a high-performance CPU and GPU for training and running machine learning models, and sensors such as cameras and microphones for detecting the emotional state of workers.

[0689] software

[0690] The software used includes Pandas for data preprocessing, scikit-learn and TensorFlow for creating machine learning models, and EmotionEngine for emotion recognition.

[0691] Data collection and preprocessing

[0692] The server collects production data, equipment operation data, and worker work history in real time from sensors installed on each piece of equipment and work station in the factory. The collected data is preprocessed using Pandas to cleanse the data, fill in missing values, and remove noise. This generates clean data suitable for analysis.

[0693] Training the model

[0694] The preprocessed data is used to train a machine learning model using scikit-learn and TensorFlow. Data used to train the model is used to optimize production schedules and provide predictive maintenance functions for equipment. This makes it possible to predict optimal production plans and maintenance timing.

[0695] Decision-making simulation

[0696] Using the trained model, multiple decision-making scenarios are simulated on the server, including scenarios for changes to production schedules and marketing strategies. The results of each scenario are compared, and the most effective decision is presented to the user.

[0697] Emotion recognition and decision-making regulation

[0698] The server uses the EmotionEngine, an emotion recognition engine, to analyze the worker's facial expressions and tone of voice to recognize their emotional state in real time. Based on the recognized emotional state, the server adjusts the decision-making scenario and presents the optimal action plan that takes into account the user's mental health.

[0699] Presentation of results

[0700] The server presents the optimal decision-making results to the user via a dashboard, where the user can view the details of the proposed strategy and the expected results. A concrete action plan is also provided, allowing the user to take immediate action.

[0701] Examples of concrete examples and prompts

[0702] For example, consider a situation where a problem occurs on a factory production line and an urgent readjustment of the production schedule is required. In this case, the emotion recognition engine detects the stress of the workers, and the system proposes an optimal production schedule and break plan.

[0703] Example prompts to input to a generative AI model:

[0704] "Please suggest optimal production schedules and break plans based on current production line data, equipment status, and worker emotional states."

[0705] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0706] Step 1:

[0707] The server collects production data, equipment operation data, and worker work history in real time from sensors installed on each piece of equipment and work station in the factory. This includes the specific operation of sending the data acquired from each sensor to the collection server via a network. The input is sensor data, and the output is collected and accumulated data.

[0708] Step 2:

[0709] The server performs data preprocessing. It cleanses the collected production data, equipment operation data, and worker work history data, filling in missing values ​​and removing noise. At this stage, Pandas is used to unify the data format and format it into a form that is easy to analyze. The input is the collected data, and the output is preprocessed, clean data.

[0710] Step 3:

[0711] The server uses the preprocessed data to train a machine learning model. Specifically, it splits the dataset into training data and test data using scikit-learn or TensorFlow, and then uses a machine learning algorithm to create and train the optimal model. The input is the preprocessed data, and the output is a trained machine learning model.

[0712] Step 4:

[0713] The server uses the trained model to simulate multiple decision-making scenarios. For example, it predicts and compares the outcomes of each scenario when changes are made to production schedules or equipment maintenance schedules. The inputs are the trained machine learning model and scenario data, and the output is the simulation results for each scenario.

[0714] Step 5:

[0715] The server uses an emotion recognition engine to recognize the emotional state of workers in real time. Specifically, it uses the Emotion Engine to analyze facial expressions and tone of voice obtained from cameras and microphones to identify the worker's stress level and fatigue state. The input is sensor data from the cameras and microphones, and the output is the worker's emotional state.

[0716] Step 6:

[0717] The server adjusts the decision-making scenario based on the recognized emotional state. For example, if a worker is experiencing high stress or fatigue, the server reevaluates and adjusts the production schedule or rest plan. The inputs are emotional state data and simulation results, and the output is the adjusted decision-making scenario.

[0718] Step 7:

[0719] The server presents the optimal decision-making results to the user. Specifically, it uses a dashboard to visually present the user with optimal production schedules, equipment maintenance schedules, worker care plans, etc. The input is the adjusted decision-making scenario, and the output is a specific action plan presented to the user.

[0720] 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.

[0721] 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.

[0722] 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.

[0723] [Third embodiment]

[0724] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0725] 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.

[0726] 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).

[0727] 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.

[0728] 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.

[0729] 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).

[0730] 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.

[0731] 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.

[0732] 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.

[0733] 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.

[0734] 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.

[0735] 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."

[0736] This invention relates to a data-driven decision-making system that enables corporate managers to make efficient decisions. This system integrates data collection, preprocessing, machine learning model training, decision-making simulation, and result presentation, with the aim of reducing the time managers spend on decision-making and maximizing labor productivity.

[0737] Overall system overview

[0738] The system includes the following major components:

[0739] 1. Data collection methods:

[0740] The server collects the necessary data from various sources, both inside and outside the company, including sales databases, customer relationship management systems (CRM), market trend data from the Internet, industry reports, and news APIs.

[0741] 2. Data preprocessing methods:

[0742] The server preprocesses the collected data and converts it into a format suitable for analysis: removing incomplete data and noise, integrating data from different sources, and normalizing the data if necessary.

[0743] 3. Model creation and training methods:

[0744] The server uses the preprocessed data to train a machine learning model, splitting the dataset into training data and test data, creating and optimizing the model using a machine learning algorithm, and evaluating its performance.

[0745] 4. Decision-making simulation tools:

[0746] The server uses the trained model to simulate various decision-making scenarios, compares the results of each scenario, and selects the optimal decision based on business goals.

[0747] 5. Presentation of results:

[0748] The server presents the optimal decision-making results to the user, generates reports through a dashboard, and presents the user with a clear and specific action plan.

[0749] Specific Examples

[0750] For example, if a company is considering launching a new product, the process using this system would proceed as follows:

[0751] 1. Data Collection:

[0752] The server automatically collects sales data, customer purchase history, current market trends, competitor activity, and more.

[0753] 2. Data Preprocessing:

[0754] The server cleanses the collected data, imputes missing values, filters outliers, and also consolidates and converts the data into a unified format.

[0755] 3. Model creation and training:

[0756] The server uses the data split into training and test data to train a machine learning model, for example, to create a model that predicts the success rate of a new product based on past market launch data.

[0757] 4. Decision-making simulation:

[0758] The server simulates multiple scenarios that change the timing of new product launches, pricing, and marketing strategies, and calculates the probability of success and return on investment (ROI) for each scenario.

[0759] 5. Presentation of results:

[0760] The server will suggest the most effective strategy to the user (for example, "launch at full price in April and conduct a large-scale marketing campaign"). The server will then provide the user with detailed reasons for the suggestion and expected results via a dashboard. The user can then create a specific action plan based on this information.

[0761] Through the above process, the system of the present invention supports data-driven decision-making and enables corporate managers to efficiently tackle problem-solving.

[0762] The processing flow will be explained below.

[0763] Program processing flow

[0764] Step 1: Data collection

[0765] The server collects the necessary data from inside and outside the company.

[0766] 1. The server connects to the sales database and extracts the sales data.

[0767] 2. The server retrieves customer feedback and purchase history from the customer relationship management system (CRM).

[0768] 3. The server scrapes market trend data using public APIs on the Internet.

[0769] 4. The server collects competitor trend data from news APIs and industry reports.

[0770] Step 2: Data Preprocessing

[0771] The server pre-processes the collected data and converts it into a format suitable for analysis.

[0772] 1. The server identifies incomplete data and missing values ​​in the generated database and imputes or removes them appropriately.

[0773] 2. The server detects and filters outliers and errors.

[0774] 3. The server consolidates data from different sources and normalizes it for consistency.

[0775] 4. The server normalizes and unifies inconsistent data formats.

[0776] Step 3: Model creation and training

[0777] The server uses the preprocessed data to create and train a machine learning model.

[0778] 1. The server splits the dataset into training data and test data.

[0779] 2. The server trains the model using the machine learning algorithm of your choice (e.g., decision tree, random forest, neural network).

[0780] 3. The server uses historical data to optimize the model parameters.

[0781] 4. The server uses the test data to calculate evaluation metrics such as precision, recall, and F1 score of the trained model and evaluate the model's performance.

[0782] Step 4: Decision-making simulation

[0783] The server uses the trained model to simulate multiple decision-making scenarios.

[0784] 1. The server generates different scenarios for new product launch timing, pricing, marketing strategies, etc.

[0785] 2. The server applies the model to each scenario and predicts future sales, customer acquisition, ROI (return on investment), etc.

[0786] 3. The server compares the results of each scenario and evaluates them based on business goals.

[0787] 4. The server selects the most advantageous scenario and proposes a strategy.

[0788] Step 5: Presenting the results

[0789] The server generates the optimal decision-making results as a report and presents it to the user.

[0790] 1. The server creates a report based on the data from the optimal decision-making scenario.

[0791] 2. The server will provide a report with the reasons for the recommendation and the specific results expected (e.g., projected sales, number of customers, risk assessment).

[0792] 3. The server displays the report on the user's device via a dashboard.

[0793] 4. Users review the presented reports and use them to make data-driven decisions.

[0794] Through these steps, the system effectively supports data-driven decision making.

[0795] Example 1

[0796] 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."

[0797] When corporate managers make decisions, the time and effort required to efficiently collect, preprocess, and analyze massive amounts of data to make optimal decisions is a major challenge. Traditional methods pose the risk of incorrect decision-making due to data inconsistencies, missing data, or noise. Furthermore, the process of simulating various scenarios and identifying optimal strategies is complex and requires advanced expertise. There is a need for a system that can solve these challenges and improve the accuracy and efficiency of decision-making.

[0798] 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.

[0799] In this invention, the server includes means for collecting necessary data, means for preprocessing the collected data, means for training a machine learning model using the preprocessed data, means for simulating multiple decision-making scenarios, and means for presenting the optimal decision-making results to users. This allows corporate managers to efficiently use massive amounts of data and make quick and accurate decisions. Furthermore, by dividing the data and applying machine learning algorithms, the performance of the model can be optimized, and comparative analysis between different scenarios can be performed to derive the optimal strategy. Furthermore, by visualizing the simulation results and presenting them through a dashboard, users can intuitively understand the results and formulate executable action plans.

[0800] "Means for collecting data" refers to methods and devices for efficiently obtaining necessary data from multiple data sources inside and outside the company.

[0801] "Data preprocessing means" refers to a method or device for imputing missing values, removing noise, integrating, and normalizing collected data, and converting it into a form suitable for analysis.

[0802] A "means for training a machine learning model" is a method or apparatus that uses preprocessed data, splits it into training data and test data, and creates and optimizes a model using a machine learning algorithm.

[0803] A "means for simulating decision-making scenarios" is a method or device that uses a trained machine learning model to construct various decision-making scenarios and calculate the probability of success and return on investment (ROI).

[0804] "Means for presenting optimal decision-making results to users" refers to a method or device for presenting optimal strategies and results obtained from a simulation to users in an easy-to-understand manner through an interface such as a dashboard.

[0805] "Means for detecting and filtering noise in data" refers to methods and devices for detecting inconsistencies and outliers in data and removing data that is unsuitable for analysis.

[0806] A "means for splitting a dataset" is a method for splitting data into training data and test data for training and evaluating a machine learning model.

[0807] The "means for calculating the probability of success and return on investment for each scenario" refers to a method or device for statistically evaluating the results of each decision-making scenario and calculating the probability of success and return on investment.

[0808] A "means for visualizing simulation results" is a method or device for displaying the results of a simulation in a visual format such as a graph or chart, allowing users to intuitively understand the results.

[0809] A "dashboard" is a user interface that allows users to centrally view and operate information obtained from the system.

[0810] This invention relates to a data-driven decision-making system that enables corporate managers to make efficient decisions. This system integrates data collection, preprocessing, machine learning model training, decision-making simulation, and result presentation, with the aim of reducing the time managers spend on decision-making and maximizing labor productivity.

[0811] Overall system overview

[0812] The system includes the following major components:

[0813] Data collection methods

[0814] Data preprocessing measures

[0815] How to train machine learning models

[0816] Decision-making simulation tools

[0817] Presentation of results

[0818] Data collection methods

[0819] The server automatically collects the required data from multiple data sources, both internal and external to the company. It uses Python's requests and pandas libraries to execute API requests and database queries. For example, it retrieves sales data from a sales database and customer information from a CRM system. It also uses external APIs (e.g., Google Trends API) to collect market trend data and news APIs (e.g., NewsAPI) to retrieve the latest industry reports and news.

[0820] Data preprocessing measures

[0821] The server preprocesses the collected data and converts it into a format suitable for analysis. This process includes data cleansing, missing value completion, noise removal, data integration from different sources, and normalization. Specifically, data processing is performed using the Python pandas and numpy libraries.

[0822] How to train machine learning models

[0823] The server trains a machine learning model using the preprocessed data. It splits the dataset into training data and test data, and creates and optimizes the model using a machine learning algorithm (e.g., random forest, linear regression). The model is trained using libraries such as scikit-learn, TensorFlow, and Keras.

[0824] Decision-making simulation tools

[0825] The server uses the trained model to simulate various decision-making scenarios, such as the timing of new product launches, pricing, and marketing strategies, and calculates the probability of success and return on investment (ROI) for each scenario.

[0826] Presentation of results

[0827] The server presents the optimal decision-making results to the user. Here, the simulation results are visualized and displayed on a dashboard. Tools such as matplotlib and dash are used to build a user-friendly interface. Through the dashboard, the user can formulate a specific action plan.

[0828] Specific Examples

[0829] For example, if a company is considering launching a new product into the market, the system would implement the following process:

[0830] 1. Data collection: The server automatically collects data such as sales data, customer purchase history, current market trends, and competitor activity.

[0831] 2. Data Preprocessing: The server cleanses the collected data, imputes missing values, filters outliers, and integrates data from different sources into a unified format.

[0832] 3. Model creation and training: The server splits the preprocessed dataset into training data and test data, and trains a machine learning model, for example, to predict the success rate of a new product based on historical market launch data.

[0833] 4. Decision-making simulation: The server simulates multiple scenarios that change the timing of new product launches, pricing, and marketing strategies, and calculates the probability of success and return on investment (ROI) for each scenario.

[0834] 5. Presentation of results: The server proposes the most effective strategy to the user. For example, if it determines that launching at full price in April and running a large-scale marketing campaign is the optimal strategy, the server will present the reasons for this proposal and the expected results in detail via a dashboard. The user can then formulate a specific action plan based on this information.

[0835] Prompt Sentence Examples

[0836] "Imagine a company is introducing a new product in April. Collect and preprocess data such as sales data, customer purchase history, market trends, and competitor behavior, and train a machine learning model to predict the success rate of the new product launch. Then, create multiple simulation scenarios to suggest optimal launch timing, pricing, and marketing strategies, compare them, and select the optimal strategy to present in a dashboard."

[0837] In this way, the system of the present invention supports data-driven decision making and enables corporate managers to efficiently tackle problems.

[0838] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0839] Step 1: Data collection

[0840] The server collects the required data from multiple data sources, both internal and external to the company. Inputs include a sales database, CRM system, market trend API, and news API. Based on this input, the server makes API requests using Python's requests library and executes database queries using the pandas library. Specific operations include retrieving data from the sales database, retrieving customer purchase history, and scraping and collecting the latest market trends and competitor activity. The output is the raw data retrieved from the various data sources.

[0841] Step 2: Data Preprocessing

[0842] The server preprocesses the collected raw data and converts it into a format suitable for analysis. The input includes the collected raw data. Based on this input, the server cleanses the data, imputes missing values, removes noise, integrates data from different sources, and normalizes it. Specifically, it uses Python's pandas and numpy libraries to process the data and generate clean data suitable for analysis. The output is a preprocessed, integrated dataset.

[0843] Step 3: Model creation and training

[0844] The server trains a machine learning model using a preprocessed dataset. The input includes the preprocessed dataset. Based on this input, the server splits the dataset into training data and test data, and creates and optimizes a model using a machine learning algorithm (e.g., random forest, linear regression). Specifically, it uses libraries such as scikit-learn, TensorFlow, and Keras to build the model and evaluate its performance. The output is a trained machine learning model.

[0845] Step 4: Decision-making simulation

[0846] The server uses the trained model to simulate various decision-making scenarios. The inputs include the trained machine learning model and the scenarios to be simulated (e.g., launch timing, pricing, marketing strategy). Based on these inputs, the server inputs each scenario into the model and calculates the probability of success and return on investment (ROI). Specifically, it constructs simulation scenarios in Python and applies them to the model. The output is the resulting data, including the probability of success and ROI for each scenario.

[0847] Step 5: Presenting the results

[0848] The server presents the simulation results to the user. The input includes the simulation result data. Based on this input, the server visualizes the results and displays them to the user through a dashboard. Specifically, it uses matplotlib and dash to create graphs and charts and displays the results on a web dashboard. The output is a dashboard that the user can view.

[0849] Through the above steps, this system can perform consistent processing from data collection to result presentation, supporting efficient decision-making.

[0850] (Application example 1)

[0851] 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."

[0852] In real-time traffic volume analysis and route optimization for autonomous vehicles, conventional methods require a lot of time and resources for data collection and preprocessing, making it difficult to make quick decisions.Furthermore, there was no system for comparing multiple traffic scenarios, making it difficult to present optimal routes in real time.

[0853] 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.

[0854] In this invention, the server includes means for collecting necessary data, means for preprocessing the collected data, means for training a machine learning model using the preprocessed data, means for acquiring current traffic condition data and simulating multiple route optimization scenarios, and means for presenting an optimal route to a user, thereby enabling real-time traffic condition analysis and prompt presentation of an optimal route based on multiple scenarios.

[0855] "Necessary data" refers to information necessary to understand traffic conditions, such as traffic volume, traffic speed, accident information, and weather conditions.

[0856] "Preprocessing" is the process of cleansing data after collection, filling in missing values, filtering outliers, integrating and normalizing the data.

[0857] A "machine learning model" is an algorithm that is trained using preprocessed data to predict current and future conditions based on past data.

[0858] "Traffic condition data" is data that indicates the current state of road traffic, and includes, for example, traffic volume, traffic speed, accident information, weather conditions, and the like.

[0859] A "route optimization scenario" is a scenario that simulates multiple routes based on traffic condition data to identify the most efficient or safe route.

[0860] The "optimal route" is the route that is deemed most desirable in terms of shortest time, least energy consumption, safety, etc., after comparing multiple route optimization scenarios.

[0861] "Noise" refers to factors that impair the accuracy of data, such as outliers, errors, and missing values ​​in a dataset.

[0862] "Real-time traffic data" refers to data that shows the state of road traffic at the current time and that is collected and analyzed quickly.

[0863] The system that realizes this application example performs real-time traffic analysis and route optimization for autonomous vehicles. The system consists of a server, a terminal, and a user.

[0864] System Configuration

[0865] server

[0866] The server implements the following methods:

[0867] 1. Data collection method: The server collects real-time traffic condition data such as traffic volume, traffic speed, accident information, weather conditions, etc. This is done by retrieving data from external APIs (e.g., Google Maps API, Here API).

[0868] 2. Data preprocessing means: The server cleanses the collected data, imputes missing values, filters outliers, and performs data integration and normalization.

[0869] 3. Machine learning model training method: The server uses the preprocessed data to train the machine learning model. For training, it uses a machine learning library such as scikit-learn.

[0870] 4. Simulation method: The server obtains current traffic condition data and simulates multiple route optimization scenarios, thereby predicting travel times for multiple scenarios.

[0871] 5. Result presentation: The server presents the optimal route to the user based on the simulation results. The presentation is done via a smartphone or the display of the in-vehicle computer.

[0872] Terminal

[0873] The terminal (smartphone or in-vehicle computer) receives the optimal route information sent from the server and visually displays it to the user.

[0874] User

[0875] The user navigates the autonomous vehicle based on the displayed optimal route information, allowing the user to reach the destination via an optimized route, avoiding traffic congestion and obstacles.

[0876] Program processing

[0877] The program in this system performs the following operations:

[0878] Data collection method: Use data collection API to obtain real-time traffic information. For example, the server obtains the latest traffic information from Google Maps API and Here API every minute.

[0879] Data preprocessing methods: Data will be cleansed, integrated, and normalized using Python's pandas library, etc. Appropriate statistical methods will be used to impute missing values.

[0880] Machine learning model training method: Using scikit-learn, a random forest regression model is trained on the preprocessed data. The trained model predicts current and future traffic conditions based on past data.

[0881] Simulation method: Using the trained model, create new traffic scenarios and predict travel times for each scenario, thereby identifying the most efficient routes.

[0882] Result presentation method: The optimal route and the reasons for it are displayed on the device's user interface. For example, the optimal route is displayed on a map in a smartphone application, and is communicated to the user along with voice guidance.

[0883] Specific examples

[0884] For example, here is a prompt to input to a generative AI model:

[0885] "Get traffic information based on the current date, time, and location to train a machine learning model for route optimization. Input data includes traffic speed, traffic volume, and weather conditions. Propose new strategies and predict travel times for each scenario."

[0886] By using such prompt sentences, it becomes possible to suggest optimal routes that take real-time traffic conditions into consideration.

[0887] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0888] Step 1:

[0889] The server collects traffic data. Specifically, it uses Google Maps API and Here API to obtain real-time data such as traffic volume, traffic speed, accident information, and weather conditions. The input of this process is raw data from the API, and the output is the collected traffic data.

[0890] Step 2:

[0891] The server preprocesses the collected data. Specifically, it uses the Python pandas library to cleanse the data, impute missing values, and filter outliers. It also integrates the data and normalizes it into a unified format. The input of this process is the collected traffic situation data, and the output is the cleansed and normalized data.

[0892] Step 3:

[0893] The server uses the preprocessed data to train a machine learning model. Specifically, it uses a random forest regression model from scikit-learn and trains it on historical traffic data. It splits the data into training data and test data, and evaluates the model's performance. The input of this process is the cleansed and normalized data, and the output is a trained machine learning model.

[0894] Step 4:

[0895] The server retrieves current traffic data and simulates multiple route optimization scenarios. For example, it generates scenarios that vary specific time periods or weather conditions, and predicts travel times for each scenario. The inputs to this process are current traffic data and a trained machine learning model, and the output is predicted travel times for each scenario.

[0896] Step 5:

[0897] The server presents the optimal route to the user based on the simulation results. Specifically, it compares the travel time of each route, selects the most efficient route, and displays it on the user interface. The terminal (smartphone or in-vehicle computer) receives this information and provides visual and audio guidance to the user. The input to this process is the predicted travel time for each scenario, and the output is optimal route information presented to the user.

[0898] Step 6:

[0899] The user navigates based on the presented optimal route information. The autonomous vehicle's navigation system drives according to the optimal route, avoiding traffic congestion and obstacles to reach the destination. The input of this process is the optimal route information, and the output is the user's arrival at the destination.

[0900] 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.

[0901] This invention relates to a data-driven decision-making system for corporate managers to make efficient decisions, and in particular, to a system that further improves the decision-making process by incorporating an emotion engine that recognizes user emotions. This system integrates data collection, preprocessing, machine learning model training, decision-making simulation, and result presentation, aiming to reduce the time managers spend on decision-making and maximize labor productivity.

[0902] Overall system overview

[0903] The system includes the following major components:

[0904] 1. Data collection methods:

[0905] The server collects the necessary data from various sources, both inside and outside the company, including sales databases, customer relationship management systems (CRM), market trend data from the Internet, industry reports, and news APIs.

[0906] 2. Data preprocessing methods:

[0907] The server preprocesses the collected data and converts it into a format suitable for analysis: removing incomplete data and noise, integrating data from different sources, and normalizing the data if necessary.

[0908] 3. Model creation and training methods:

[0909] The server uses the preprocessed data to train a machine learning model, splitting the dataset into training data and test data, creating and optimizing the model using a machine learning algorithm, and evaluating its performance.

[0910] 4. Decision-making simulation tools:

[0911] The server uses the trained model to simulate various decision-making scenarios, compares the results of each scenario, and selects the optimal decision based on business goals.

[0912] 5. Presentation of results:

[0913] The server presents the optimal decision-making results to the user, generates reports through a dashboard, and presents the user with a clear and specific action plan.

[0914] 6. Emotion recognition means:

[0915] The server uses an emotion engine to collect and analyze the user's emotional data, allowing it to adjust the evaluation and optimization of decision-making scenarios based on the user's emotional state.

[0916] Specific Examples

[0917] For example, if a company is considering launching a new product, the process using this system would proceed as follows:

[0918] 1. Data Collection:

[0919] The server automatically collects sales data, customer purchase history, current market trends, competitor activity, and more.

[0920] 2. Data Preprocessing:

[0921] The server cleanses the collected data, imputes missing values, filters outliers, and also consolidates and converts the data into a unified format.

[0922] 3. Model creation and training:

[0923] The server uses the data split into training and test data to train a machine learning model, for example, to create a model that predicts the success rate of a new product based on past market launch data.

[0924] 4. Decision-making simulation:

[0925] The server simulates multiple scenarios that change the timing of new product launches, pricing, and marketing strategies, and calculates the probability of success and return on investment (ROI) for each scenario.

[0926] 5. Emotion recognition:

[0927] The server uses an emotion engine to analyze the user's facial expressions and tone of voice to recognize their emotional state in real time. For example, if the user is feeling anxious, the server will adjust the explanation of the decision-making scenario to take that emotion into account.

[0928] 6. Presentation of results:

[0929] The server recommends the most effective strategy to the user (e.g., "launch at full price in April and conduct a large-scale marketing campaign"). The server provides the user with detailed reasons for the recommendation and expected results via a dashboard. The user can then create a specific action plan based on this information.

[0930] By combining this system with an emotion engine, the system can make better decisions by taking the user's emotions into account. For example, if the user is feeling stressed, the system can suggest a more cautious approach. This makes the decision-making process more comfortable and trustworthy for the user.

[0931] The processing flow will be explained below.

[0932] Program processing flow

[0933] Step 1: Data collection

[0934] The server collects the necessary data from inside and outside the company.

[0935] 1. The server connects to the sales database and extracts the sales data.

[0936] 2. The server retrieves customer feedback and purchase history from the customer relationship management system (CRM).

[0937] 3. The server scrapes market trend data using public APIs on the Internet.

[0938] 4. The server collects competitor trend data from news APIs and industry reports.

[0939] Step 2: Data Preprocessing

[0940] The server pre-processes the collected data and converts it into a format suitable for analysis.

[0941] 1. The server identifies incomplete data and missing values ​​and imputes or removes them appropriately.

[0942] 2. The server detects and filters outliers and errors.

[0943] 3. The server consolidates data from different sources and normalizes it for consistency.

[0944] 4. The server normalizes and unifies inconsistent data formats.

[0945] Step 3: Model creation and training

[0946] The server uses the preprocessed data to create and train a machine learning model.

[0947] 1. The server splits the dataset into training data and test data.

[0948] 2. The server trains the model using the machine learning algorithm of your choice (e.g., decision tree, random forest, neural network).

[0949] 3. The server uses the training data to optimize the model parameters.

[0950] 4. The server uses the test data to calculate evaluation metrics such as precision, recall, and F1 score of the trained model and evaluate the model's performance.

[0951] Step 4: Decision-making simulation

[0952] The server uses the trained model to simulate multiple decision-making scenarios.

[0953] 1. The server generates different scenarios for new product launch timing, pricing, marketing strategies, etc.

[0954] 2. The server applies the model to each scenario and predicts future sales, customer acquisition, ROI (return on investment), etc.

[0955] 3. The server compares the results of each scenario and evaluates the best scenario based on business goals.

[0956] 4. The server selects the most favorable scenario and recommends that strategy.

[0957] Step 5: Emotion Recognition

[0958] The server uses an emotion engine to collect and analyze the user's emotion data.

[0959] 1. The server analyzes the user's facial expressions and tone of voice to recognize their emotional state in real time.

[0960] 2. The server accumulates the user's emotional data and tracks its changes.

[0961] 3. The server adjusts the evaluation of the decision scenario based on the user's emotional state.

[0962] 4. The server suggests a cautious approach if the user is experiencing stress or anxiety.

[0963] Step 6: Presenting the results

[0964] The server generates the optimal decision-making results as a report and presents it to the user.

[0965] 1. The server creates a report based on the data from the optimal decision-making scenario.

[0966] 2. The server will provide a report with the reasons for the recommendation and the specific results expected (e.g., projected sales, number of customers, risk assessment).

[0967] 3. The server displays the report on the user's device via a dashboard.

[0968] 4. Users review the presented reports and use them to make data-driven decisions.

[0969] Through these steps, the system, which combines an emotion engine, efficiently supports data-driven decision-making and promotes better decision-making that takes users' emotions into account.

[0970] Example 2

[0971] 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."

[0972] In order for corporate managers to make efficient decisions, they need to effectively collect and analyze large amounts of data and use the results to make optimal decisions. However, this takes time and effort, which can distract managers from their core work. In addition, users' emotions can sometimes influence decision-making, and systems that do not take this into account may not produce optimal results.

[0973] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0974] In this invention, the server includes means for collecting necessary data, means for preprocessing the collected data, means for training a machine learning model using the preprocessed data, means for simulating multiple decision-making scenarios, means for presenting optimal decision-making results to the user, means for collecting and analyzing user emotion data, and means for adjusting the decision-making scenarios based on the emotion data. This allows managers to make quick and optimal decisions using a data-driven system, thereby maximizing work efficiency and labor productivity. Furthermore, taking user emotions into consideration enables more appropriate and reliable decision-making.

[0975] "Means for collecting data" refers to the technical means for automatically obtaining the necessary data from various data sources inside and outside the company.

[0976] "Data preprocessing means" refers to technical means for completing missing values ​​in collected data, removing noise, and converting the data into a unified format.

[0977] A "means for training a machine learning model" is a technical means for applying a machine learning algorithm to preprocessed data to create a model that makes predictions or classifications for a particular problem.

[0978] "Means for simulating decision-making scenarios" refers to technical means that use a trained machine learning model to try out multiple decision-making scenarios and select the optimal scenario based on the results.

[0979] "Means for presenting decision-making results to users" refers to technical means such as dashboards and report generation for presenting optimal decision-making results obtained through simulation to users.

[0980] "Means for collecting and analyzing emotional data" refers to technical means for collecting emotional data such as a user's facial expressions and tone of voice in real time and analyzing this data to understand the user's emotional state.

[0981] "Means for adjusting decision-making scenarios based on emotional data" refers to technical means for adjusting the explanation method and content of decision-making scenarios based on collected emotional data of users, to adapt them to the emotional state of the users.

[0982] This invention relates to a data-driven decision-making system that helps corporate managers make efficient decisions, and in particular, to a system that further improves the decision-making process by incorporating an emotion engine that recognizes user emotions. This system integrates data collection, preprocessing, machine learning model training, decision-making simulation, and result presentation, aiming to reduce the time managers spend on decision-making and maximize labor productivity.

[0983] The system includes the following major components:

[0984] Data collection methods

[0985] The server collects the necessary data from inside and outside the company. Specific data sources include sales databases, customer relationship management systems (CRM), market trend data from the Internet, industry reports, news APIs, etc. For example, the server uses SQL queries to extract sales data from the sales database for the past five years, or collects market trend data through APIs.

[0986] Data preprocessing measures

[0987] The server completes the collected data by filling in missing values, removing noise, and converting data from different formats into a unified format using Python's Pandas and Scikit-learn libraries. For example, the server scales and normalizes the data to prepare it for analysis.

[0988] Model creation and training methods

[0989] The server trains a machine learning model using the preprocessed data. Specifically, it splits the data into training data and test data, creates a random forest or deep learning model using the Scikit-learn library, and performs cross-validation to evaluate the model's performance. For example, a model can be trained using past market launch data to predict the success rate of a new product.

[0990] Decision-making simulation tools

[0991] The server sets up multiple decision-making scenarios based on the trained model and runs simulations. It calculates the probability of success and return on investment (ROI) for each scenario and selects the optimal decision. For example, it simulates scenarios that change the timing of new product launches, pricing, marketing strategies, etc.

[0992] Presentation of results

[0993] The server generates a dashboard to present the optimal decision-making results to the user. The dashboard displays visual reports and concrete action plans. For example, the server uses the Matplotlib library to draw graphs and present information in an easy-to-understand format to the user.

[0994] emotion recognition means

[0995] The server uses an emotion engine to collect and analyze the user's facial expression data and tone of voice in real time. This allows it to understand the user's emotional state and adjust the explanation and presentation of the decision-making scenario accordingly. For example, if the user is feeling anxious, the server will take that emotion into account and provide a more thorough explanation.

[0996] Specific examples

[0997] For example, if a company is considering launching a new product, the process using this system would proceed as follows:

[0998] 1. The server automatically collects sales data, customer purchase history, current market trends, competitor activity, etc.

[0999] 2. The server cleanses the collected data, imputes missing values, filters outliers, and consolidates the data into a unified format.

[1000] 3. The server uses the split data to train a machine learning model, for example, to predict the success rate of a new product based on past market launch data.

[1001] 4. The server simulates multiple scenarios that change the timing of new product launches, pricing, and marketing strategies, and calculates the probability of success and return on investment (ROI) for each scenario.

[1002] 5. The server uses an emotion engine to analyze the user's facial expressions and tone of voice to recognize their emotional state in real time. For example, if the user is feeling anxious, the server will adjust the explanation of the decision-making scenario to take that emotion into account.

[1003] 6. The server recommends the most effective strategy to the user (e.g., "Launch at full price in April and conduct a large-scale marketing campaign") and provides the reasons for the recommendation and the expected results in detail via a dashboard.

[1004] Prompt Sentence Examples

[1005] You are considering launching a new product. Based on sales data, customer purchase history, and current market trend data, please predict the following:

[1006] 1. Optimal time to market

[1007] 2. Optimal pricing level

[1008] 3. Optimal marketing strategies

[1009] Furthermore, based on these scenarios, we would like you to analyze the user's reactions using an emotion engine and suggest optimal decisions.

[1010] In this way, the system provides an effective means for making data-driven decisions, and by taking user emotions into account, it supports more reliable decision-making.

[1011] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1012] Step 1:

[1013] The server collects the necessary data from a sales database, a customer relationship management system (CRM), a market trend data API, an industry report API, etc. For example, the server runs an SQL query against the sales database to retrieve sales data for the past five years. It also sends an API request to retrieve the latest market trend data. This gives the server an input dataset to integrate data from each data source.

[1014] Step 2:

[1015] The server preprocesses the collected data by completing missing values, removing noise, and unifying different data formats. Specifically, it uses Python's Pandas library to convert data from different sources into DataFrame format, and then uses Scikit-learn's Imputer class to complete missing values. It also performs outlier filtering, scaling, and normalizing the data. The server then outputs a preprocessed dataset in a format suitable for analysis.

[1016] Step 3:

[1017] The server splits the preprocessed dataset into training data and test data. Specifically, it uses Scikit-learn's train_test_split function to set 80% of the data as training data and 20% as test data. The server then trains a model using a machine learning algorithm. For example, it uses a random forest algorithm to create a model that predicts the success rate of a new product based on historical market data. Through this training process, the server outputs a predictive model.

[1018] Step 4:

[1019] The server uses the trained predictive model to simulate multiple decision-making scenarios. Specifically, it tests various patterns of pricing, launch timing, and marketing strategies for new products, and calculates the success probability and return on investment (ROI) for each. For example, it uses the Markov Chain Monte Carlo (MCMC) method to simulate the success probability for various scenarios. The server then outputs the simulation results for each scenario.

[1020] Step 5:

[1021] The server uses an emotion engine to collect and analyze the user's emotional data (facial expressions and tone of voice) in real time. Specifically, it uses an emotion analysis API to process data acquired from the camera and microphone to understand the user's emotional state. For example, if the user is feeling anxious, that emotional data is taken as input and works with other modules in the system to take appropriate action. The server then outputs the user's emotional data.

[1022] Step 6:

[1023] The server presents the optimal decision-making result to the user based on the simulation results and the user's emotional state. Specifically, it generates a dashboard and displays visual reports and specific action plans. For example, it uses the Matplotlib library to draw graphs of success probability and ROI, providing information in an intuitive format for the user. This allows the server to output the optimal decision-making result and present it to the user.

[1024] Through the above process, this system supports data-driven decision-making while also supporting more accurate decision-making that takes into account the user's emotions.

[1025] (Application example 2)

[1026] 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."

[1027] While conventional data-driven decision-making systems use data analysis and machine learning to make efficient decisions, they do not take into account the emotional state of the user, which means they ignore the impact that the mental and physical state of managers and workers, in particular, has on the results. Furthermore, in factory production management, there is a lack of a way to present optimal production schedules that reflect the stress and fatigue levels of workers, which risks reducing labor productivity and work efficiency. To solve this problem, a system is needed that recognizes the user's emotional state in real time and adjusts decision-making based on that.

[1028] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting necessary data, means for preprocessing the collected data, means for training a machine learning model using the preprocessed data, means for simulating multiple decision-making scenarios, means for presenting optimal decision-making results to the user, means for recognizing the user's emotional state, and means for adjusting decision-making based on the recognized emotional state. This enables more appropriate decision-making that takes the user's physical and mental state into consideration, and can also improve labor productivity in factory production management while reducing worker stress and fatigue.

[1029] "Means of collecting data" refers to devices and systems for collecting a variety of information, such as production data within the factory, equipment operation data, and worker work history and emotional data.

[1030] "Means for preprocessing data" refers to devices or systems that cleanse collected data, fill in missing values, remove noise, and format the data in a way that is suitable for analysis.

[1031] A "means for training a machine learning model" is a device or system that uses preprocessed data to learn various patterns and create and optimize models that can be used for subsequent decision-making.

[1032] A "means for simulating decision-making scenarios" is a device or system that assumes multiple possible scenarios and performs calculations to predict the outcomes.

[1033] The "means for presenting optimal decision-making results to the user" refers to a device or system equipped with a dashboard or interface for analyzing the simulation results and presenting them to the user in an easy-to-understand format.

[1034] The "means for recognizing the user's emotional state" refers to a device or system equipped with an emotion engine or sensor that analyzes the facial expressions and tone of voice of workers and managers to recognize their emotional state in real time.

[1035] A "means for adjusting decision-making based on emotional state" is a device or system that adjusts the explanation or proposal content of a decision-making scenario according to the recognized emotional state, thereby supporting more appropriate decision-making.

[1036] This invention relates to a system for managing production within a factory. This system collects and preprocesses necessary data, such as production data, equipment operation data, and worker work history, and then trains a machine learning model to simulate multiple decision-making scenarios and present the optimal results to the user. The system can also recognize the user's emotional state and adjust decision-making based on that.

[1037] System Configuration

[1038] Hardware

[1039] The server is equipped with a database for collecting and storing data, a high-performance CPU and GPU for training and running machine learning models, and sensors such as cameras and microphones for detecting the emotional state of workers.

[1040] software

[1041] The software used includes Pandas for data preprocessing, scikit-learn and TensorFlow for creating machine learning models, and EmotionEngine for emotion recognition.

[1042] Data collection and preprocessing

[1043] The server collects production data, equipment operation data, and worker work history in real time from sensors installed on each piece of equipment and work station in the factory. The collected data is preprocessed using Pandas to cleanse the data, fill in missing values, and remove noise. This generates clean data suitable for analysis.

[1044] Training the model

[1045] The preprocessed data is used to train a machine learning model using scikit-learn and TensorFlow. Data used to train the model is used to optimize production schedules and provide predictive maintenance functions for equipment. This makes it possible to predict optimal production plans and maintenance timing.

[1046] Decision-making simulation

[1047] Using the trained model, multiple decision-making scenarios are simulated on the server, including scenarios for changes to production schedules and marketing strategies. The results of each scenario are compared, and the most effective decision is presented to the user.

[1048] Emotion recognition and decision-making regulation

[1049] The server uses the EmotionEngine, an emotion recognition engine, to analyze the worker's facial expressions and tone of voice to recognize their emotional state in real time. Based on the recognized emotional state, the server adjusts the decision-making scenario and presents the optimal action plan that takes into account the user's mental health.

[1050] Presentation of results

[1051] The server presents the optimal decision-making results to the user via a dashboard, where the user can view the details of the proposed strategy and the expected results. A concrete action plan is also provided, allowing the user to take immediate action.

[1052] Examples of concrete examples and prompts

[1053] For example, consider a situation where a problem occurs on a factory production line and an urgent readjustment of the production schedule is required. In this case, the emotion recognition engine detects the stress of the workers, and the system proposes an optimal production schedule and break plan.

[1054] Example prompts to input to a generative AI model:

[1055] "Please suggest optimal production schedules and break plans based on current production line data, equipment status, and worker emotional states."

[1056] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1057] Step 1:

[1058] The server collects production data, equipment operation data, and worker work history in real time from sensors installed on each piece of equipment and work station in the factory. This includes the specific operation of sending the data acquired from each sensor to the collection server via a network. The input is sensor data, and the output is collected and accumulated data.

[1059] Step 2:

[1060] The server performs data preprocessing. It cleanses the collected production data, equipment operation data, and worker work history data, filling in missing values ​​and removing noise. At this stage, Pandas is used to unify the data format and format it into a form that is easy to analyze. The input is the collected data, and the output is preprocessed, clean data.

[1061] Step 3:

[1062] The server uses the preprocessed data to train a machine learning model. Specifically, it splits the dataset into training data and test data using scikit-learn or TensorFlow, and then uses a machine learning algorithm to create and train the optimal model. The input is the preprocessed data, and the output is a trained machine learning model.

[1063] Step 4:

[1064] The server uses the trained model to simulate multiple decision-making scenarios. For example, it predicts and compares the outcomes of each scenario when changes are made to production schedules or equipment maintenance schedules. The inputs are the trained machine learning model and scenario data, and the output is the simulation results for each scenario.

[1065] Step 5:

[1066] The server uses an emotion recognition engine to recognize the emotional state of workers in real time. Specifically, it uses the Emotion Engine to analyze facial expressions and tone of voice obtained from cameras and microphones to identify the worker's stress level and fatigue state. The input is sensor data from the cameras and microphones, and the output is the worker's emotional state.

[1067] Step 6:

[1068] The server adjusts the decision-making scenario based on the recognized emotional state. For example, if a worker is experiencing high stress or fatigue, the server reevaluates and adjusts the production schedule or rest plan. The inputs are emotional state data and simulation results, and the output is the adjusted decision-making scenario.

[1069] Step 7:

[1070] The server presents the optimal decision-making results to the user. Specifically, it uses a dashboard to visually present the user with optimal production schedules, equipment maintenance schedules, worker care plans, etc. The input is the adjusted decision-making scenario, and the output is a specific action plan presented to the user.

[1071] 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.

[1072] 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.

[1073] 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.

[1074] [Fourth embodiment]

[1075] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1076] 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.

[1077] 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).

[1078] 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.

[1079] 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.

[1080] 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).

[1081] 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.

[1082] 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.

[1083] 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.

[1084] 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.

[1085] 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.

[1086] 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.

[1087] 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."

[1088] This invention relates to a data-driven decision-making system that enables corporate managers to make efficient decisions. This system integrates data collection, preprocessing, machine learning model training, decision-making simulation, and result presentation, with the aim of reducing the time managers spend on decision-making and maximizing labor productivity.

[1089] Overall system overview

[1090] The system includes the following major components:

[1091] 1. Data collection methods:

[1092] The server collects the necessary data from various sources, both inside and outside the company, including sales databases, customer relationship management systems (CRM), market trend data from the Internet, industry reports, and news APIs.

[1093] 2. Data preprocessing methods:

[1094] The server preprocesses the collected data and converts it into a format suitable for analysis: removing incomplete data and noise, integrating data from different sources, and normalizing the data if necessary.

[1095] 3. Model creation and training methods:

[1096] The server uses the preprocessed data to train a machine learning model, splitting the dataset into training data and test data, creating and optimizing the model using a machine learning algorithm, and evaluating its performance.

[1097] 4. Decision-making simulation tools:

[1098] The server uses the trained model to simulate various decision-making scenarios, compares the results of each scenario, and selects the optimal decision based on business goals.

[1099] 5. Presentation of results:

[1100] The server presents the optimal decision-making results to the user, generates reports through a dashboard, and presents the user with a clear and specific action plan.

[1101] Specific Examples

[1102] For example, if a company is considering launching a new product, the process using this system would proceed as follows:

[1103] 1. Data Collection:

[1104] The server automatically collects sales data, customer purchase history, current market trends, competitor activity, and more.

[1105] 2. Data Preprocessing:

[1106] The server cleanses the collected data, imputes missing values, filters outliers, and also consolidates and converts the data into a unified format.

[1107] 3. Model creation and training:

[1108] The server uses the data split into training and test data to train a machine learning model, for example, to create a model that predicts the success rate of a new product based on past market launch data.

[1109] 4. Decision-making simulation:

[1110] The server simulates multiple scenarios that change the timing of new product launches, pricing, and marketing strategies, and calculates the probability of success and return on investment (ROI) for each scenario.

[1111] 5. Presentation of results:

[1112] The server will suggest the most effective strategy to the user (for example, "launch at full price in April and conduct a large-scale marketing campaign"). The server will then provide the user with detailed reasons for the suggestion and expected results via a dashboard. The user can then create a specific action plan based on this information.

[1113] Through the above process, the system of the present invention supports data-driven decision-making and enables corporate managers to efficiently tackle problem-solving.

[1114] The processing flow will be explained below.

[1115] Program processing flow

[1116] Step 1: Data collection

[1117] The server collects the necessary data from inside and outside the company.

[1118] 1. The server connects to the sales database and extracts the sales data.

[1119] 2. The server retrieves customer feedback and purchase history from the customer relationship management system (CRM).

[1120] 3. The server scrapes market trend data using public APIs on the Internet.

[1121] 4. The server collects competitor trend data from news APIs and industry reports.

[1122] Step 2: Data Preprocessing

[1123] The server pre-processes the collected data and converts it into a format suitable for analysis.

[1124] 1. The server identifies incomplete data and missing values ​​in the generated database and imputes or removes them appropriately.

[1125] 2. The server detects and filters outliers and errors.

[1126] 3. The server consolidates data from different sources and normalizes it for consistency.

[1127] 4. The server normalizes and unifies inconsistent data formats.

[1128] Step 3: Model creation and training

[1129] The server uses the preprocessed data to create and train a machine learning model.

[1130] 1. The server splits the dataset into training data and test data.

[1131] 2. The server trains the model using the machine learning algorithm of your choice (e.g., decision tree, random forest, neural network).

[1132] 3. The server uses historical data to optimize the model parameters.

[1133] 4. The server uses the test data to calculate evaluation metrics such as precision, recall, and F1 score of the trained model and evaluate the model's performance.

[1134] Step 4: Decision-making simulation

[1135] The server uses the trained model to simulate multiple decision-making scenarios.

[1136] 1. The server generates different scenarios for new product launch timing, pricing, marketing strategies, etc.

[1137] 2. The server applies the model to each scenario and predicts future sales, customer acquisition, ROI (return on investment), etc.

[1138] 3. The server compares the results of each scenario and evaluates them based on business goals.

[1139] 4. The server selects the most advantageous scenario and proposes a strategy.

[1140] Step 5: Presenting the results

[1141] The server generates the optimal decision-making results as a report and presents it to the user.

[1142] 1. The server creates a report based on the data from the optimal decision-making scenario.

[1143] 2. The server will provide a report with the reasons for the recommendation and the specific results expected (e.g., projected sales, number of customers, risk assessment).

[1144] 3. The server displays the report on the user's device via a dashboard.

[1145] 4. Users review the presented reports and use them to make data-driven decisions.

[1146] Through these steps, the system effectively supports data-driven decision making.

[1147] Example 1

[1148] 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."

[1149] When corporate managers make decisions, the time and effort required to efficiently collect, preprocess, and analyze massive amounts of data to make optimal decisions is a major challenge. Traditional methods pose the risk of incorrect decision-making due to data inconsistencies, missing data, or noise. Furthermore, the process of simulating various scenarios and identifying optimal strategies is complex and requires advanced expertise. There is a need for a system that can solve these challenges and improve the accuracy and efficiency of decision-making.

[1150] 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.

[1151] In this invention, the server includes means for collecting necessary data, means for preprocessing the collected data, means for training a machine learning model using the preprocessed data, means for simulating multiple decision-making scenarios, and means for presenting the optimal decision-making results to users. This allows corporate managers to efficiently use massive amounts of data and make quick and accurate decisions. Furthermore, by dividing the data and applying machine learning algorithms, the performance of the model can be optimized, and comparative analysis between different scenarios can be performed to derive the optimal strategy. Furthermore, by visualizing the simulation results and presenting them through a dashboard, users can intuitively understand the results and formulate executable action plans.

[1152] "Means for collecting data" refers to methods and devices for efficiently obtaining necessary data from multiple data sources inside and outside the company.

[1153] "Data preprocessing means" refers to a method or device for imputing missing values, removing noise, integrating, and normalizing collected data, and converting it into a form suitable for analysis.

[1154] A "means for training a machine learning model" is a method or apparatus that uses preprocessed data, splits it into training data and test data, and creates and optimizes a model using a machine learning algorithm.

[1155] A "means for simulating decision-making scenarios" is a method or device that uses a trained machine learning model to construct various decision-making scenarios and calculate the probability of success and return on investment (ROI).

[1156] "Means for presenting optimal decision-making results to users" refers to a method or device for presenting optimal strategies and results obtained from a simulation to users in an easy-to-understand manner through an interface such as a dashboard.

[1157] "Means for detecting and filtering noise in data" refers to methods and devices for detecting inconsistencies and outliers in data and removing data that is unsuitable for analysis.

[1158] A "means for splitting a dataset" is a method for splitting data into training data and test data for training and evaluating a machine learning model.

[1159] The "means for calculating the probability of success and return on investment for each scenario" refers to a method or device for statistically evaluating the results of each decision-making scenario and calculating the probability of success and return on investment.

[1160] A "means for visualizing simulation results" is a method or device for displaying the results of a simulation in a visual format such as a graph or chart, allowing users to intuitively understand the results.

[1161] A "dashboard" is a user interface that allows users to centrally view and operate information obtained from the system.

[1162] This invention relates to a data-driven decision-making system that enables corporate managers to make efficient decisions. This system integrates data collection, preprocessing, machine learning model training, decision-making simulation, and result presentation, with the aim of reducing the time managers spend on decision-making and maximizing labor productivity.

[1163] Overall system overview

[1164] The system includes the following major components:

[1165] Data collection methods

[1166] Data preprocessing measures

[1167] How to train machine learning models

[1168] Decision-making simulation tools

[1169] Presentation of results

[1170] Data collection methods

[1171] The server automatically collects the required data from multiple data sources, both internal and external to the company. It uses Python's requests and pandas libraries to execute API requests and database queries. For example, it retrieves sales data from a sales database and customer information from a CRM system. It also uses external APIs (e.g., Google Trends API) to collect market trend data and news APIs (e.g., NewsAPI) to retrieve the latest industry reports and news.

[1172] Data preprocessing measures

[1173] The server preprocesses the collected data and converts it into a format suitable for analysis. This process includes data cleansing, missing value completion, noise removal, data integration from different sources, and normalization. Specifically, data processing is performed using the Python pandas and numpy libraries.

[1174] How to train machine learning models

[1175] The server trains a machine learning model using the preprocessed data. It splits the dataset into training data and test data, and creates and optimizes the model using a machine learning algorithm (e.g., random forest, linear regression). The model is trained using libraries such as scikit-learn, TensorFlow, and Keras.

[1176] Decision-making simulation tools

[1177] The server uses the trained model to simulate various decision-making scenarios, such as the timing of new product launches, pricing, and marketing strategies, and calculates the probability of success and return on investment (ROI) for each scenario.

[1178] Presentation of results

[1179] The server presents the optimal decision-making results to the user. Here, the simulation results are visualized and displayed on a dashboard. Tools such as matplotlib and dash are used to build a user-friendly interface. Through the dashboard, the user can formulate a specific action plan.

[1180] Specific Examples

[1181] For example, if a company is considering launching a new product into the market, the system would implement the following process:

[1182] 1. Data collection: The server automatically collects data such as sales data, customer purchase history, current market trends, and competitor activity.

[1183] 2. Data Preprocessing: The server cleanses the collected data, imputes missing values, filters outliers, and integrates data from different sources into a unified format.

[1184] 3. Model creation and training: The server splits the preprocessed dataset into training data and test data, and trains a machine learning model, for example, to predict the success rate of a new product based on historical market launch data.

[1185] 4. Decision-making simulation: The server simulates multiple scenarios that change the timing of new product launches, pricing, and marketing strategies, and calculates the probability of success and return on investment (ROI) for each scenario.

[1186] 5. Presentation of results: The server proposes the most effective strategy to the user. For example, if it determines that launching at full price in April and running a large-scale marketing campaign is the optimal strategy, the server will present the reasons for this proposal and the expected results in detail via a dashboard. The user can then formulate a specific action plan based on this information.

[1187] Prompt Sentence Examples

[1188] "Imagine a company is introducing a new product in April. Collect and preprocess data such as sales data, customer purchase history, market trends, and competitor behavior, and train a machine learning model to predict the success rate of the new product launch. Then, create multiple simulation scenarios to suggest optimal launch timing, pricing, and marketing strategies, compare them, and select the optimal strategy to present in a dashboard."

[1189] In this way, the system of the present invention supports data-driven decision making and enables corporate managers to efficiently tackle problems.

[1190] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1191] Step 1: Data collection

[1192] The server collects the required data from multiple data sources, both internal and external to the company. Inputs include a sales database, CRM system, market trend API, and news API. Based on this input, the server makes API requests using Python's requests library and executes database queries using the pandas library. Specific operations include retrieving data from the sales database, retrieving customer purchase history, and scraping and collecting the latest market trends and competitor activity. The output is the raw data retrieved from the various data sources.

[1193] Step 2: Data Preprocessing

[1194] The server preprocesses the collected raw data and converts it into a format suitable for analysis. The input includes the collected raw data. Based on this input, the server cleanses the data, imputes missing values, removes noise, integrates data from different sources, and normalizes it. Specifically, it uses Python's pandas and numpy libraries to process the data and generate clean data suitable for analysis. The output is a preprocessed, integrated dataset.

[1195] Step 3: Model creation and training

[1196] The server trains a machine learning model using a preprocessed dataset. The input includes the preprocessed dataset. Based on this input, the server splits the dataset into training data and test data, and creates and optimizes a model using a machine learning algorithm (e.g., random forest, linear regression). Specifically, it uses libraries such as scikit-learn, TensorFlow, and Keras to build the model and evaluate its performance. The output is a trained machine learning model.

[1197] Step 4: Decision-making simulation

[1198] The server uses the trained model to simulate various decision-making scenarios. The inputs include the trained machine learning model and the scenarios to be simulated (e.g., launch timing, pricing, marketing strategy). Based on these inputs, the server inputs each scenario into the model and calculates the probability of success and return on investment (ROI). Specifically, it constructs simulation scenarios in Python and applies them to the model. The output is the resulting data, including the probability of success and ROI for each scenario.

[1199] Step 5: Presenting the results

[1200] The server presents the simulation results to the user. The input includes the simulation result data. Based on this input, the server visualizes the results and displays them to the user through a dashboard. Specifically, it uses matplotlib and dash to create graphs and charts and displays the results on a web dashboard. The output is a dashboard that the user can view.

[1201] Through the above steps, this system can perform consistent processing from data collection to result presentation, supporting efficient decision-making.

[1202] (Application example 1)

[1203] 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."

[1204] In real-time traffic volume analysis and route optimization for autonomous vehicles, conventional methods require a lot of time and resources for data collection and preprocessing, making it difficult to make quick decisions.Furthermore, there was no system for comparing multiple traffic scenarios, making it difficult to present optimal routes in real time.

[1205] 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.

[1206] In this invention, the server includes means for collecting necessary data, means for preprocessing the collected data, means for training a machine learning model using the preprocessed data, means for acquiring current traffic condition data and simulating multiple route optimization scenarios, and means for presenting an optimal route to a user, thereby enabling real-time traffic condition analysis and prompt presentation of an optimal route based on multiple scenarios.

[1207] "Necessary data" refers to information necessary to understand traffic conditions, such as traffic volume, traffic speed, accident information, and weather conditions.

[1208] "Preprocessing" is the process of cleansing data after collection, filling in missing values, filtering outliers, integrating and normalizing the data.

[1209] A "machine learning model" is an algorithm that is trained using preprocessed data to predict current and future conditions based on past data.

[1210] "Traffic condition data" is data that indicates the current state of road traffic, and includes, for example, traffic volume, traffic speed, accident information, weather conditions, and the like.

[1211] A "route optimization scenario" is a scenario that simulates multiple routes based on traffic condition data to identify the most efficient or safe route.

[1212] The "optimal route" is the route that is deemed most desirable in terms of shortest time, least energy consumption, safety, etc., after comparing multiple route optimization scenarios.

[1213] "Noise" refers to factors that impair the accuracy of data, such as outliers, errors, and missing values ​​in a dataset.

[1214] "Real-time traffic data" refers to data that shows the state of road traffic at the current time and that is collected and analyzed quickly.

[1215] The system that realizes this application example performs real-time traffic analysis and route optimization for autonomous vehicles. The system consists of a server, a terminal, and a user.

[1216] System Configuration

[1217] server

[1218] The server implements the following methods:

[1219] 1. Data collection method: The server collects real-time traffic condition data such as traffic volume, traffic speed, accident information, weather conditions, etc. This is done by retrieving data from external APIs (e.g., Google Maps API, Here API).

[1220] 2. Data preprocessing means: The server cleanses the collected data, imputes missing values, filters outliers, and performs data integration and normalization.

[1221] 3. Machine learning model training method: The server uses the preprocessed data to train the machine learning model. For training, it uses a machine learning library such as scikit-learn.

[1222] 4. Simulation method: The server obtains current traffic condition data and simulates multiple route optimization scenarios, thereby predicting travel times for multiple scenarios.

[1223] 5. Result presentation: The server presents the optimal route to the user based on the simulation results. The presentation is done via a smartphone or the display of the in-vehicle computer.

[1224] Terminal

[1225] The terminal (smartphone or in-vehicle computer) receives the optimal route information sent from the server and visually displays it to the user.

[1226] User

[1227] The user navigates the autonomous vehicle based on the displayed optimal route information, allowing the user to reach the destination via an optimized route, avoiding traffic congestion and obstacles.

[1228] Program processing

[1229] The program in this system performs the following operations:

[1230] Data collection method: Use data collection API to obtain real-time traffic information. For example, the server obtains the latest traffic information from Google Maps API and Here API every minute.

[1231] Data preprocessing methods: Data will be cleansed, integrated, and normalized using Python's pandas library, etc. Appropriate statistical methods will be used to impute missing values.

[1232] Machine learning model training method: Using scikit-learn, a random forest regression model is trained on the preprocessed data. The trained model predicts current and future traffic conditions based on past data.

[1233] Simulation method: Using the trained model, create new traffic scenarios and predict travel times for each scenario, thereby identifying the most efficient routes.

[1234] Result presentation method: The optimal route and the reasons for it are displayed on the device's user interface. For example, the optimal route is displayed on a map in a smartphone application, and is communicated to the user along with voice guidance.

[1235] Specific examples

[1236] For example, here is a prompt to input to a generative AI model:

[1237] "Get traffic information based on the current date, time, and location to train a machine learning model for route optimization. Input data includes traffic speed, traffic volume, and weather conditions. Propose new strategies and predict travel times for each scenario."

[1238] By using such prompt sentences, it becomes possible to suggest optimal routes that take real-time traffic conditions into consideration.

[1239] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1240] Step 1:

[1241] The server collects traffic data. Specifically, it uses Google Maps API and Here API to obtain real-time data such as traffic volume, traffic speed, accident information, and weather conditions. The input of this process is raw data from the API, and the output is the collected traffic data.

[1242] Step 2:

[1243] The server preprocesses the collected data. Specifically, it uses the Python pandas library to cleanse the data, impute missing values, and filter outliers. It also integrates the data and normalizes it into a unified format. The input of this process is the collected traffic situation data, and the output is the cleansed and normalized data.

[1244] Step 3:

[1245] The server uses the preprocessed data to train a machine learning model. Specifically, it uses a random forest regression model from scikit-learn and trains it on historical traffic data. It splits the data into training data and test data, and evaluates the model's performance. The input of this process is the cleansed and normalized data, and the output is a trained machine learning model.

[1246] Step 4:

[1247] The server retrieves current traffic data and simulates multiple route optimization scenarios. For example, it generates scenarios that vary specific time periods or weather conditions, and predicts travel times for each scenario. The inputs to this process are current traffic data and a trained machine learning model, and the output is predicted travel times for each scenario.

[1248] Step 5:

[1249] The server presents the optimal route to the user based on the simulation results. Specifically, it compares the travel time of each route, selects the most efficient route, and displays it on the user interface. The terminal (smartphone or in-vehicle computer) receives this information and provides visual and audio guidance to the user. The input to this process is the predicted travel time for each scenario, and the output is optimal route information presented to the user.

[1250] Step 6:

[1251] The user navigates based on the presented optimal route information. The autonomous vehicle's navigation system drives according to the optimal route, avoiding traffic congestion and obstacles to reach the destination. The input of this process is the optimal route information, and the output is the user's arrival at the destination.

[1252] 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.

[1253] This invention relates to a data-driven decision-making system for corporate managers to make efficient decisions, and in particular, to a system that further improves the decision-making process by incorporating an emotion engine that recognizes user emotions. This system integrates data collection, preprocessing, machine learning model training, decision-making simulation, and result presentation, aiming to reduce the time managers spend on decision-making and maximize labor productivity.

[1254] Overall system overview

[1255] The system includes the following major components:

[1256] 1. Data collection methods:

[1257] The server collects the necessary data from various sources, both inside and outside the company, including sales databases, customer relationship management systems (CRM), market trend data from the Internet, industry reports, and news APIs.

[1258] 2. Data preprocessing methods:

[1259] The server preprocesses the collected data and converts it into a format suitable for analysis: removing incomplete data and noise, integrating data from different sources, and normalizing the data if necessary.

[1260] 3. Model creation and training methods:

[1261] The server uses the preprocessed data to train a machine learning model, splitting the dataset into training data and test data, creating and optimizing the model using a machine learning algorithm, and evaluating its performance.

[1262] 4. Decision-making simulation tools:

[1263] The server uses the trained model to simulate various decision-making scenarios, compares the results of each scenario, and selects the optimal decision based on business goals.

[1264] 5. Presentation of results:

[1265] The server presents the optimal decision-making results to the user, generates reports through a dashboard, and presents the user with a clear and specific action plan.

[1266] 6. Emotion recognition means:

[1267] The server uses an emotion engine to collect and analyze the user's emotional data, allowing it to adjust the evaluation and optimization of decision-making scenarios based on the user's emotional state.

[1268] Specific Examples

[1269] For example, if a company is considering launching a new product, the process using this system would proceed as follows:

[1270] 1. Data Collection:

[1271] The server automatically collects sales data, customer purchase history, current market trends, competitor activity, and more.

[1272] 2. Data Preprocessing:

[1273] The server cleanses the collected data, imputes missing values, filters outliers, and also consolidates and converts the data into a unified format.

[1274] 3. Model creation and training:

[1275] The server uses the data split into training and test data to train a machine learning model, for example, to create a model that predicts the success rate of a new product based on past market launch data.

[1276] 4. Decision-making simulation:

[1277] The server simulates multiple scenarios that change the timing of new product launches, pricing, and marketing strategies, and calculates the probability of success and return on investment (ROI) for each scenario.

[1278] 5. Emotion recognition:

[1279] The server uses an emotion engine to analyze the user's facial expressions and tone of voice to recognize their emotional state in real time. For example, if the user is feeling anxious, the server will adjust the explanation of the decision-making scenario to take that emotion into account.

[1280] 6. Presentation of results:

[1281] The server recommends the most effective strategy to the user (e.g., "launch at full price in April and conduct a large-scale marketing campaign"). The server provides the user with detailed reasons for the recommendation and expected results via a dashboard. The user can then create a specific action plan based on this information.

[1282] By combining this system with an emotion engine, the system can make better decisions by taking the user's emotions into account. For example, if the user is feeling stressed, the system can suggest a more cautious approach. This makes the decision-making process more comfortable and trustworthy for the user.

[1283] The processing flow will be explained below.

[1284] Program processing flow

[1285] Step 1: Data collection

[1286] The server collects the necessary data from inside and outside the company.

[1287] 1. The server connects to the sales database and extracts the sales data.

[1288] 2. The server retrieves customer feedback and purchase history from the customer relationship management system (CRM).

[1289] 3. The server scrapes market trend data using public APIs on the Internet.

[1290] 4. The server collects competitor trend data from news APIs and industry reports.

[1291] Step 2: Data Preprocessing

[1292] The server pre-processes the collected data and converts it into a format suitable for analysis.

[1293] 1. The server identifies incomplete data and missing values ​​and imputes or removes them appropriately.

[1294] 2. The server detects and filters outliers and errors.

[1295] 3. The server consolidates data from different sources and normalizes it for consistency.

[1296] 4. The server normalizes and unifies inconsistent data formats.

[1297] Step 3: Model creation and training

[1298] The server uses the preprocessed data to create and train a machine learning model.

[1299] 1. The server splits the dataset into training data and test data.

[1300] 2. The server trains the model using the machine learning algorithm of your choice (e.g., decision tree, random forest, neural network).

[1301] 3. The server uses the training data to optimize the model parameters.

[1302] 4. The server uses the test data to calculate evaluation metrics such as precision, recall, and F1 score of the trained model and evaluate the model's performance.

[1303] Step 4: Decision-making simulation

[1304] The server uses the trained model to simulate multiple decision-making scenarios.

[1305] 1. The server generates different scenarios for new product launch timing, pricing, marketing strategies, etc.

[1306] 2. The server applies the model to each scenario and predicts future sales, customer acquisition, ROI (return on investment), etc.

[1307] 3. The server compares the results of each scenario and evaluates the best scenario based on business goals.

[1308] 4. The server selects the most favorable scenario and recommends that strategy.

[1309] Step 5: Emotion Recognition

[1310] The server uses an emotion engine to collect and analyze the user's emotion data.

[1311] 1. The server analyzes the user's facial expressions and tone of voice to recognize their emotional state in real time.

[1312] 2. The server accumulates the user's emotional data and tracks its changes.

[1313] 3. The server adjusts the evaluation of the decision scenario based on the user's emotional state.

[1314] 4. The server suggests a cautious approach if the user is experiencing stress or anxiety.

[1315] Step 6: Presenting the results

[1316] The server generates the optimal decision-making results as a report and presents it to the user.

[1317] 1. The server creates a report based on the data from the optimal decision-making scenario.

[1318] 2. The server will provide a report with the reasons for the recommendation and the specific results expected (e.g., projected sales, number of customers, risk assessment).

[1319] 3. The server displays the report on the user's device via a dashboard.

[1320] 4. Users review the presented reports and use them to make data-driven decisions.

[1321] Through these steps, the system, which combines an emotion engine, efficiently supports data-driven decision-making and promotes better decision-making that takes users' emotions into account.

[1322] Example 2

[1323] 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."

[1324] In order for corporate managers to make efficient decisions, they need to effectively collect and analyze large amounts of data and use the results to make optimal decisions. However, this takes time and effort, which can distract managers from their core work. In addition, users' emotions can sometimes influence decision-making, and systems that do not take this into account may not produce optimal results.

[1325] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1326] In this invention, the server includes means for collecting necessary data, means for preprocessing the collected data, means for training a machine learning model using the preprocessed data, means for simulating multiple decision-making scenarios, means for presenting optimal decision-making results to the user, means for collecting and analyzing user emotion data, and means for adjusting the decision-making scenarios based on the emotion data. This allows managers to make quick and optimal decisions using a data-driven system, thereby maximizing work efficiency and labor productivity. Furthermore, taking user emotions into consideration enables more appropriate and reliable decision-making.

[1327] "Means for collecting data" refers to the technical means for automatically obtaining the necessary data from various data sources inside and outside the company.

[1328] "Data preprocessing means" refers to technical means for completing missing values ​​in collected data, removing noise, and converting the data into a unified format.

[1329] A "means for training a machine learning model" is a technical means for applying a machine learning algorithm to preprocessed data to create a model that makes predictions or classifications for a particular problem.

[1330] "Means for simulating decision-making scenarios" refers to technical means that use a trained machine learning model to try out multiple decision-making scenarios and select the optimal scenario based on the results.

[1331] "Means for presenting decision-making results to users" refers to technical means such as dashboards and report generation for presenting optimal decision-making results obtained through simulation to users.

[1332] "Means for collecting and analyzing emotional data" refers to technical means for collecting emotional data such as a user's facial expressions and tone of voice in real time and analyzing this data to understand the user's emotional state.

[1333] "Means for adjusting decision-making scenarios based on emotional data" refers to technical means for adjusting the explanation method and content of decision-making scenarios based on collected emotional data of users, to adapt them to the emotional state of the users.

[1334] This invention relates to a data-driven decision-making system that helps corporate managers make efficient decisions, and in particular, to a system that further improves the decision-making process by incorporating an emotion engine that recognizes user emotions. This system integrates data collection, preprocessing, machine learning model training, decision-making simulation, and result presentation, aiming to reduce the time managers spend on decision-making and maximize labor productivity.

[1335] The system includes the following major components:

[1336] Data collection methods

[1337] The server collects the necessary data from inside and outside the company. Specific data sources include sales databases, customer relationship management systems (CRM), market trend data from the Internet, industry reports, news APIs, etc. For example, the server uses SQL queries to extract sales data from the sales database for the past five years, or collects market trend data through APIs.

[1338] Data preprocessing measures

[1339] The server completes the collected data by filling in missing values, removing noise, and converting data from different formats into a unified format using Python's Pandas and Scikit-learn libraries. For example, the server scales and normalizes the data to prepare it for analysis.

[1340] Model creation and training methods

[1341] The server trains a machine learning model using the preprocessed data. Specifically, it splits the data into training data and test data, creates a random forest or deep learning model using the Scikit-learn library, and performs cross-validation to evaluate the model's performance. For example, a model can be trained using past market launch data to predict the success rate of a new product.

[1342] Decision-making simulation tools

[1343] The server sets up multiple decision-making scenarios based on the trained model and runs simulations. It calculates the probability of success and return on investment (ROI) for each scenario and selects the optimal decision. For example, it simulates scenarios that change the timing of new product launches, pricing, marketing strategies, etc.

[1344] Presentation of results

[1345] The server generates a dashboard to present the optimal decision-making results to the user. The dashboard displays visual reports and concrete action plans. For example, the server uses the Matplotlib library to draw graphs and present information in an easy-to-understand format to the user.

[1346] emotion recognition means

[1347] The server uses an emotion engine to collect and analyze the user's facial expression data and tone of voice in real time. This allows it to understand the user's emotional state and adjust the explanation and presentation of the decision-making scenario accordingly. For example, if the user is feeling anxious, the server will take that emotion into account and provide a more thorough explanation.

[1348] Specific examples

[1349] For example, if a company is considering launching a new product, the process using this system would proceed as follows:

[1350] 1. The server automatically collects sales data, customer purchase history, current market trends, competitor activity, etc.

[1351] 2. The server cleanses the collected data, imputes missing values, filters outliers, and consolidates the data into a unified format.

[1352] 3. The server uses the split data to train a machine learning model, for example, to predict the success rate of a new product based on past market launch data.

[1353] 4. The server simulates multiple scenarios that change the timing of new product launches, pricing, and marketing strategies, and calculates the probability of success and return on investment (ROI) for each scenario.

[1354] 5. The server uses an emotion engine to analyze the user's facial expressions and tone of voice to recognize their emotional state in real time. For example, if the user is feeling anxious, the server will adjust the explanation of the decision-making scenario to take that emotion into account.

[1355] 6. The server recommends the most effective strategy to the user (e.g., "Launch at full price in April and conduct a large-scale marketing campaign") and provides the reasons for the recommendation and the expected results in detail via a dashboard.

[1356] Prompt Sentence Examples

[1357] You are considering launching a new product. Based on sales data, customer purchase history, and current market trend data, please predict the following:

[1358] 1. Optimal time to market

[1359] 2. Optimal pricing level

[1360] 3. Optimal marketing strategies

[1361] Furthermore, based on these scenarios, we would like you to analyze the user's reactions using an emotion engine and suggest optimal decisions.

[1362] In this way, the system provides an effective means for making data-driven decisions, and by taking user emotions into account, it supports more reliable decision-making.

[1363] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1364] Step 1:

[1365] The server collects the necessary data from a sales database, a customer relationship management system (CRM), a market trend data API, an industry report API, etc. For example, the server runs an SQL query against the sales database to retrieve sales data for the past five years. It also sends an API request to retrieve the latest market trend data. This gives the server an input dataset to integrate data from each data source.

[1366] Step 2:

[1367] The server preprocesses the collected data by completing missing values, removing noise, and unifying different data formats. Specifically, it uses Python's Pandas library to convert data from different sources into DataFrame format, and then uses Scikit-learn's Imputer class to complete missing values. It also performs outlier filtering, scaling, and normalizing the data. The server then outputs a preprocessed dataset in a format suitable for analysis.

[1368] Step 3:

[1369] The server splits the preprocessed dataset into training data and test data. Specifically, it uses Scikit-learn's train_test_split function to set 80% of the data as training data and 20% as test data. The server then trains a model using a machine learning algorithm. For example, it uses a random forest algorithm to create a model that predicts the success rate of a new product based on historical market data. Through this training process, the server outputs a predictive model.

[1370] Step 4:

[1371] The server uses the trained predictive model to simulate multiple decision-making scenarios. Specifically, it tests various patterns of pricing, launch timing, and marketing strategies for new products, and calculates the success probability and return on investment (ROI) for each. For example, it uses the Markov Chain Monte Carlo (MCMC) method to simulate the success probability for various scenarios. The server then outputs the simulation results for each scenario.

[1372] Step 5:

[1373] The server uses an emotion engine to collect and analyze the user's emotional data (facial expressions and tone of voice) in real time. Specifically, it uses an emotion analysis API to process data acquired from the camera and microphone to understand the user's emotional state. For example, if the user is feeling anxious, that emotional data is taken as input and works with other modules in the system to take appropriate action. The server then outputs the user's emotional data.

[1374] Step 6:

[1375] The server presents the optimal decision-making result to the user based on the simulation results and the user's emotional state. Specifically, it generates a dashboard and displays visual reports and specific action plans. For example, it uses the Matplotlib library to draw graphs of success probability and ROI, providing information in an intuitive format for the user. This allows the server to output the optimal decision-making result and present it to the user.

[1376] Through the above process, this system supports data-driven decision-making while also supporting more accurate decision-making that takes into account the user's emotions.

[1377] (Application example 2)

[1378] 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."

[1379] While conventional data-driven decision-making systems use data analysis and machine learning to make efficient decisions, they do not take into account the emotional state of the user, which means they ignore the impact that the mental and physical state of managers and workers, in particular, has on the results. Furthermore, in factory production management, there is a lack of a way to present optimal production schedules that reflect the stress and fatigue levels of workers, which risks reducing labor productivity and work efficiency. To solve this problem, a system is needed that recognizes the user's emotional state in real time and adjusts decision-making based on that.

[1380] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting necessary data, means for preprocessing the collected data, means for training a machine learning model using the preprocessed data, means for simulating multiple decision-making scenarios, means for presenting optimal decision-making results to the user, means for recognizing the user's emotional state, and means for adjusting decision-making based on the recognized emotional state. This enables more appropriate decision-making that takes the user's physical and mental state into consideration, and can also improve labor productivity in factory production management while reducing worker stress and fatigue.

[1381] "Means of collecting data" refers to devices and systems for collecting a variety of information, such as production data within the factory, equipment operation data, and worker work history and emotional data.

[1382] "Means for preprocessing data" refers to devices or systems that cleanse collected data, fill in missing values, remove noise, and format the data in a way that is suitable for analysis.

[1383] A "means for training a machine learning model" is a device or system that uses preprocessed data to learn various patterns and create and optimize models that can be used for subsequent decision-making.

[1384] A "means for simulating decision-making scenarios" is a device or system that assumes multiple possible scenarios and performs calculations to predict the outcomes.

[1385] The "means for presenting optimal decision-making results to the user" refers to a device or system equipped with a dashboard or interface for analyzing the simulation results and presenting them to the user in an easy-to-understand format.

[1386] The "means for recognizing the user's emotional state" refers to a device or system equipped with an emotion engine or sensor that analyzes the facial expressions and tone of voice of workers and managers to recognize their emotional state in real time.

[1387] A "means for adjusting decision-making based on emotional state" is a device or system that adjusts the explanation or proposal content of a decision-making scenario according to the recognized emotional state, thereby supporting more appropriate decision-making.

[1388] This invention relates to a system for managing production within a factory. This system collects and preprocesses necessary data, such as production data, equipment operation data, and worker work history, and then trains a machine learning model to simulate multiple decision-making scenarios and present the optimal results to the user. The system can also recognize the user's emotional state and adjust decision-making based on that.

[1389] System Configuration

[1390] Hardware

[1391] The server is equipped with a database for collecting and storing data, a high-performance CPU and GPU for training and running machine learning models, and sensors such as cameras and microphones for detecting the emotional state of workers.

[1392] software

[1393] The software used includes Pandas for data preprocessing, scikit-learn and TensorFlow for creating machine learning models, and EmotionEngine for emotion recognition.

[1394] Data collection and preprocessing

[1395] The server collects production data, equipment operation data, and worker work history in real time from sensors installed on each piece of equipment and work station in the factory. The collected data is preprocessed using Pandas to cleanse the data, fill in missing values, and remove noise. This generates clean data suitable for analysis.

[1396] Training the model

[1397] The preprocessed data is used to train a machine learning model using scikit-learn and TensorFlow. Data used to train the model is used to optimize production schedules and provide predictive maintenance functions for equipment. This makes it possible to predict optimal production plans and maintenance timing.

[1398] Decision-making simulation

[1399] Using the trained model, multiple decision-making scenarios are simulated on the server, including scenarios for changes to production schedules and marketing strategies. The results of each scenario are compared, and the most effective decision is presented to the user.

[1400] Emotion recognition and decision-making regulation

[1401] The server uses the EmotionEngine, an emotion recognition engine, to analyze the worker's facial expressions and tone of voice to recognize their emotional state in real time. Based on the recognized emotional state, the server adjusts the decision-making scenario and presents the optimal action plan that takes into account the user's mental health.

[1402] Presentation of results

[1403] The server presents the optimal decision-making results to the user via a dashboard, where the user can view the details of the proposed strategy and the expected results. A concrete action plan is also provided, allowing the user to take immediate action.

[1404] Examples of concrete examples and prompts

[1405] For example, consider a situation where a problem occurs on a factory production line and an urgent readjustment of the production schedule is required. In this case, the emotion recognition engine detects the stress of the workers, and the system proposes an optimal production schedule and break plan.

[1406] Example prompts to input to a generative AI model:

[1407] "Please suggest optimal production schedules and break plans based on current production line data, equipment status, and worker emotional states."

[1408] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1409] Step 1:

[1410] The server collects production data, equipment operation data, and worker work history in real time from sensors installed on each piece of equipment and work station in the factory. This includes the specific operation of sending the data acquired from each sensor to the collection server via a network. The input is sensor data, and the output is collected and accumulated data.

[1411] Step 2:

[1412] The server performs data preprocessing. It cleanses the collected production data, equipment operation data, and worker work history data, filling in missing values ​​and removing noise. At this stage, Pandas is used to unify the data format and format it into a form that is easy to analyze. The input is the collected data, and the output is preprocessed, clean data.

[1413] Step 3:

[1414] The server uses the preprocessed data to train a machine learning model. Specifically, it splits the dataset into training data and test data using scikit-learn or TensorFlow, and then uses a machine learning algorithm to create and train the optimal model. The input is the preprocessed data, and the output is a trained machine learning model.

[1415] Step 4:

[1416] The server uses the trained model to simulate multiple decision-making scenarios. For example, it predicts and compares the outcomes of each scenario when changes are made to production schedules or equipment maintenance schedules. The inputs are the trained machine learning model and scenario data, and the output is the simulation results for each scenario.

[1417] Step 5:

[1418] The server uses an emotion recognition engine to recognize the emotional state of workers in real time. Specifically, it uses the Emotion Engine to analyze facial expressions and tone of voice obtained from cameras and microphones to identify the worker's stress level and fatigue state. The input is sensor data from the cameras and microphones, and the output is the worker's emotional state.

[1419] Step 6:

[1420] The server adjusts the decision-making scenario based on the recognized emotional state. For example, if a worker is experiencing high stress or fatigue, the server reevaluates and adjusts the production schedule or rest plan. The inputs are emotional state data and simulation results, and the output is the adjusted decision-making scenario.

[1421] Step 7:

[1422] The server presents the optimal decision-making results to the user. Specifically, it uses a dashboard to visually present the user with optimal production schedules, equipment maintenance schedules, worker care plans, etc. The input is the adjusted decision-making scenario, and the output is a specific action plan presented to the user.

[1423] 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.

[1424] 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.

[1425] 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.

[1426] 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.

[1427] FIG. 9 illustrates 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 behaviors 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.

[1428] 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.

[1429] 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).

[1430] 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.

[1431] 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."

[1432] 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.

[1433] 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).

[1434] 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.

[1435] 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.

[1436] 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.

[1437] 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.

[1438] 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.

[1439] 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.

[1440] 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.

[1441] 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.

[1442] 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.

[1443] 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.

[1444] The following is further disclosed regarding the above embodiment.

[1445] (Claim 1)

[1446] means of collecting the necessary data;

[1447] a means for pre-processing the collected data;

[1448] a means for training a machine learning model using the preprocessed data; and

[1449] a means for simulating multiple decision-making scenarios;

[1450] A means for presenting an optimal decision-making result to a user;

[1451] A system including:

[1452] (Claim 2)

[1453] 10. The system of claim 1, further comprising means for detecting and filtering noise in the data.

[1454] (Claim 3)

[1455] 10. The system of claim 1, further comprising means for scraping market trend data.

[1456] "Example 1"

[1457] (Claim 1)

[1458] means of collecting the necessary data;

[1459] a means for pre-processing the collected data;

[1460] A means of training a machine learning model using the preprocessed data; and

[1461] a means for simulating multiple decision-making scenarios;

[1462] A means for presenting optimal decision-making results to users;

[1463] A system including:

[1464] (Claim 2)

[1465] 10. The system of claim 1, further comprising means for detecting and filtering noise in the data.

[1466] (Claim 3)

[1467] 10. The system of claim 1, further comprising means for splitting the dataset into training data and test data and for creating and training a model using a machine learning algorithm.

[1468] (Claim 4)

[1469] 10. The system of claim 1, further comprising means for collecting data from multiple data sources, both internal and external to the enterprise, using APIs.

[1470] (Claim 5)

[1471] 10. The system according to claim 1, further comprising means for calculating the probability of success and return on investment for each decision-making scenario and for comparatively analyzing optimal strategies.

[1472] (Claim 6)

[1473] 10. The system of claim 1, further comprising means for visualizing and displaying simulation results through a dashboard.

[1474] "Application Example 1"

[1475] (Claim 1)

[1476] means of collecting the necessary data;

[1477] a means for pre-processing the collected data;

[1478] a means for training a machine learning model using the preprocessed data; and

[1479] A means of acquiring current traffic data and simulating multiple route optimization scenarios;

[1480] means for presenting an optimal route to a user;

[1481] A system including:

[1482] (Claim 2)

[1483] 10. The system of claim 1, further comprising means for detecting and filtering noise in the data.

[1484] (Claim 3)

[1485] 10. The system of claim 1, further comprising means for obtaining and analyzing real-time traffic data.

[1486] "Example 2: Combining Emotion Engines"

[1487] (Claim 1)

[1488] means of collecting the necessary data;

[1489] a means for pre-processing the collected data;

[1490] a means for training a machine learning model using the preprocessed data; and

[1491] a means for simulating multiple decision-making scenarios;

[1492] A means for presenting an optimal decision-making result to a user;

[1493] means for collecting and analyzing user emotion data;

[1494] a means of adjusting decision-making scenarios based on emotional data;

[1495] A system including:

[1496] (Claim 2)

[1497] 10. The system of claim 1, further comprising means for detecting and filtering noise in the data.

[1498] (Claim 3)

[1499] 10. The system of claim 1, further comprising means for scraping market trend data.

[1500] "Application example 2 when combining emotion engines"

[1501] (Claim 1)

[1502] means of collecting the necessary data;

[1503] a means for pre-processing the collected data;

[1504] a means for training a machine learning model using the preprocessed data; and

[1505] a means for simulating multiple decision-making scenarios;

[1506] A means for presenting an optimal decision-making result to a user;

[1507] means for recognizing the emotional state of a user;

[1508] a means for adjusting decision-making based on perceived emotional states;

[1509] A system including:

[1510] (Claim 2)

[1511] 10. The system of claim 1, further comprising means for detecting and filtering noise in the data.

[1512] (Claim 3)

[1513] 10. The system of claim 1, further comprising means for scraping market trend data. [Explanation of symbols]

[1514] 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. means of collecting the necessary data; a means for pre-processing the collected data; a means for training a machine learning model using the preprocessed data; and a means for simulating multiple decision-making scenarios; A means for presenting an optimal decision-making result to a user; A system including:

2. The system of claim 1 further comprising means for detecting and filtering noise in the data.

3. The system of claim 1 , further comprising means for scraping market trend data.

Images