system

Abstract

We provide the system. [Solution] The information processing device is a means of collecting diverse data related to multiple businesses, A means of cleaning up and standardizing inaccurate data using collected data, A means for training and updating generative artificial intelligence models based on cleaned and standardized data, A means of automatically determining whether a business can continue using a trained model, A means for generating and reporting a report that includes the judgment results and recommendations, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Due to the diversification of businesses and changes in the market environment, it is required to accurately grasp the profitability and marketability of each business and enable optimal allocation of limited management resources. However, it is difficult to judge whether to continue a business with low or difficult-to-realize profits due to information bias and emotional bias. In particular, there is a problem that effective management decisions cannot be made because there is a lack of appropriate tools for grasping market trends and competitive situations and objectively evaluating them.

Means for Solving the Problems

[0005] This invention provides a business continuity decision system using an information processing device. This system collects diverse data related to multiple businesses, cleanses and standardizes the data, and builds a highly accurate analytical foundation. By training and updating a generative artificial intelligence model based on the collected data, it objectively evaluates the profitability and market position of each business and automatically determines whether or not to continue. Furthermore, by generating a detailed report that includes the decision results and recommendations and reporting it for management decision-making, it enables the optimization of management resources without being influenced by information bias or emotional factors.

[0006] An "information processing device" is a set of hardware and software components that automatically collect, process, and analyze data.

[0007] "Collection means" refers to the mechanisms and processes for collecting the target data, including application programming interfaces and database connections.

[0008] Standardization is the process of transforming data into a consistent format by unifying different data formats and units.

[0009] A "generative artificial intelligence model" is a model that uses machine learning algorithms to learn patterns in data, enabling predictions and classifications based on new data.

[0010] "Training" is the process by which an artificial intelligence model learns using a vast amount of data and improves its performance for a specific task.

[0011] "Evaluation" is the activity of using a trained artificial intelligence model to measure business performance based on a specific dataset and to support optimal decision-making.

[0012] "Automatic decision-making" refers to a function that makes decisions based on a pre-programmed algorithm, without requiring manual intervention from the user.

[0013] A "report" is a document generated by the system that includes analysis results, recommendations, and the data that supports them.

[0014] "Means of reporting" refers to methods and channels for notifying users of generated reports and information in an appropriate format. [Brief explanation of the drawing]

[0015] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Mode for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), etc.

[0019] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0028] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0035] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0036] This invention provides a system that automates business continuity decisions by executing a program running on an information processing device. This system has a server-centric structure and supports management decisions by performing real-time data collection and analysis.

[0037] First, the server automatically collects data related to multiple businesses from various sources. This includes sales data, expense data, market trend data, and customer feedback data. The server retrieves this data through application programming interfaces and database connections and standardizes it to ensure data consistency.

[0038] Next, the server uses a generative artificial intelligence model to analyze the collected data. During this analysis process, the AI ​​model is trained and, considering past business performance and market trends, predicts the profitability and market position of each business. This allows for an objective evaluation of three options: continue the business, not continue it, or wait and see.

[0039] The server automatically makes decisions based on the analysis results and compiles the results, along with the reasoning, into a detailed report. This report is notified to the user via their terminal and can be used to review business strategies and efficiently allocate resources.

[0040] For example, a user might want to identify underperforming products from their multiple product lines. The server collects all relevant product data and analyzes it using a generative AI model. The server evaluates the profitability and market share of each product line and provides a report summarizing the reasons for the underperformance. The user can then use this report to implement improvements to the underperforming products or decide to discontinue them.

[0041] In this way, a system is provided that eliminates information bias and emotional judgments, enabling rational and data-driven management decisions.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The server identifies sources for collecting sales data, expense data, market trend data, and customer feedback data related to each business. To this end, it configures application programming interfaces and database connections, enabling the automation of data retrieval.

[0045] Step 2:

[0046] The server cleans the collected data, correcting or removing inaccurate data. Furthermore, it standardizes different data formats and units, converting them into a consistent format suitable for analysis. This process also includes imputing missing data values.

[0047] Step 3:

[0048] The server trains a generative artificial intelligence model based on standardized data. This model learns from historical business performance data and market trends, and is optimized to evaluate the profitability and market competitiveness of the business.

[0049] Step 4:

[0050] The server uses trained AI models to predict the current and future performance of each business. The models analyze profitability, risk assessment, and business continuity in response to market changes, providing decisions on whether to continue, not continue, or wait and see.

[0051] Step 5:

[0052] The server generates a detailed report based on the analysis results of the AI ​​model. This report includes a summary of the analysis, a decision on whether each business can be continued, and the reasons for those decisions.

[0053] Step 6:

[0054] The terminal notifies the user of the generated report. The user can use the terminal to review the report and use it as material for specific business decisions. This reporting function allows the user to review the allocation of management resources and strategies based on objective data.

[0055] (Example 1)

[0056] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0057] In today's business environment, a vast amount of information is available, demanding quick and accurate management decisions. However, it is difficult to select highly relevant information from a massive dataset and make rational decisions based on it. Furthermore, information is easily influenced by biases and emotional factors, making it challenging to make objective, data-driven judgments.

[0058] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0059] In this invention, the server includes means for collecting diverse information related to multiple business operations, means for performing predictive analysis using generative artificial intelligence based on standardized information, and means for generating and providing reports to users that include evaluation results and the reasons for those results. This eliminates information bias and enables objective, data-driven management decisions.

[0060] An "information processing device" is a device that collects, processes, and analyzes data and generates output tailored to a specific purpose.

[0061] "Generative artificial intelligence" refers to artificial intelligence that has the ability to generate new information based on past data, and is a technology used for prediction and analysis.

[0062] "Predictive analytics" is an analytical method used to predict future events and outcomes based on collected data.

[0063] Standardization is the process of ensuring data consistency and converting it into a comparable format.

[0064] A "report" is a document that organizes the results of an analysis and the reasoning behind the decisions, and provides them to the user.

[0065] A "prompt message" is an instruction that a user enters into the system, intended to prompt specific analysis or processing.

[0066] A "terminal" is a device used by a user to obtain information or input data.

[0067] This invention is a system that automates the decision-making process for continuing operations using an information processing device. This system has a server-centric structure and supports management decisions through real-time information collection and analysis. The system utilizes generative artificial intelligence to efficiently analyze data.

[0068] First, the server automatically collects business-related information from various sources via APIs and database connections. This system retrieves data from a variety of sources, including customer relationship management tools and sales management software. This allows for the collection of information such as sales, expenses, market trends, and customer feedback.

[0069] The server then standardizes the collected data and converts it into a consistent format. This unifies data from different information sources, making it comparable. The server then uses the standardized data to perform predictive analytics using generative artificial intelligence models. This process utilizes libraries such as Python's TENSORFLOW® to perform data analysis based on past performance and market trends, enabling objective evaluation.

[0070] For example, a user might want to know which of their multiple business lines is underperforming. In this case, the server collects data related to each business line and analyzes it using a generative AI model. As a result, a detailed report is generated indicating which businesses are experiencing profitability problems. Based on this report, the user can then formulate further improvement measures or consider shutting down the business.

[0071] An example of a prompt message that can be entered into the system is: "Based on current sales data and market trends, identify the least profitable business line and analyze the cause."

[0072] In this way, the system of the present invention eliminates information bias and emotional judgments, and supports rational and data-driven management decisions.

[0073] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0074] Step 1:

[0075] The server collects business-related data from multiple sources. Specifically, it obtains sales, expenses, market trends, and customer feedback data from various services and platforms via APIs and database connections. The input data consists of this information and is temporarily stored in storage after collection. The output is the raw dataset used in subsequent standardization processes.

[0076] Step 2:

[0077] The server standardizes the collected data. This is the process of converting data in different formats and units into a consistent format. For example, it converts all numerical data to a common currency unit and unifies date formats. It also applies appropriate imputation if outliers or missing values ​​exist. The input is the original dataset from step 1, and the output is the standardized dataset.

[0078] Step 3:

[0079] The server performs predictive analysis using a generative artificial intelligence model based on standardized data. Specifically, the server inputs data into the generative AI model and predicts future profitability and market share by comparing it with past performance data and market trends. The Python TensorFlow library is used in this process. The input is the standardized dataset from step 2, and the output is the analysis results showing the continuity and potential risks of each business.

[0080] Step 4:

[0081] Based on the predictive analytics results, the server generates a detailed report containing three options: continue operations, suspend operations, or wait and see. This report also includes reasoning and recommendations. The input is the analysis results from step 3, and the output is a report designed to facilitate user decision-making.

[0082] Step 5:

[0083] The terminal notifies the user of reports received from the server. This process is designed to display new information in real time on the dashboard. The input is the report generated in step 4, and the output is a visual notification on the user interface.

[0084] Step 6:

[0085] Users review reports on the dashboard and revise their strategies based on the presented data. In this step, users can enter new prompts to instruct further detailed analysis and hypothesis testing. The input is the report presented on the device, and the output is the user's strategic decision.

[0086] (Application Example 1)

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

[0088] In manufacturing, multiple production lines are operated simultaneously, making it difficult to maintain optimal production efficiency for each. In particular, increased product defect rates and energy consumption can lead to decreased profits, necessitating automated systems to quickly identify and address these issues. However, traditional methods have limitations in providing consistent real-time monitoring and efficient improvement suggestions. Therefore, new technological means are needed to improve factory production efficiency.

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

[0090] In this invention, the server includes means for an information processing module to collect diverse information related to multiple tasks, means for deleting and unifying erroneous data using the collected information, means for training and updating a generative artificial intelligence model based on the deleted and unified information, means for collecting and analyzing production data from a manufacturing line in real time, and means for evaluating the efficiency of the manufacturing line and proposing improvement suggestions. This enables efficient monitoring of the operation status of the production line, early detection of problems, and rapid proposal of improvement measures.

[0091] An "information processing module" is a device or program that has the function of collecting, organizing, and analyzing data.

[0092] "Information" refers to data or collections of data used for analysis and decision-making.

[0093] "Inaccurate data" refers to data that lacks accuracy due to inconsistencies in the collection process or records.

[0094] "Deletion" is the process of removing erroneous data from the system and purifying the dataset.

[0095] "Standardization" is the process of converting data from different formats and units into a consistent format.

[0096] A "generative artificial intelligence model" is a model of algorithms that learns from data and is created to support prediction and decision-making.

[0097] "Training" is the process by which a machine learning algorithm acquires appropriate predictive capabilities based on data.

[0098] "Updating" is the process of improving the performance of a machine learning model using the latest data.

[0099] "Production data" refers to information regarding the operating rate, product quality, and energy consumption in the manufacturing process.

[0100] "Real-time collection" refers to the process of acquiring information almost simultaneously with its generation.

[0101] "Analysis" is the process of evaluating collected information and deriving meaningful interpretations from it.

[0102] "Efficiency" is a measure of how effectively a manufacturing line is using resources to achieve its goals.

[0103] An "improvement suggestion" refers to specific measures taken to solve problems and improve production efficiency.

[0104] The system implementing this invention features an information processing module running on a server and aims to improve production efficiency in the manufacturing industry. The server collects real-time production data from the manufacturing line through sensors and existing data management systems. This includes operating rates, product quality indicators, and energy consumption.

[0105] Once the data is aggregated on the server, erroneous data is removed and the data is standardized. Specifically, a data processing script using Python is essential, and the Pandas library is used to filter out erroneous data. The clean data is then analyzed by a generative artificial intelligence model. TensorFlow or PyTorch is used to train and update the model, which enables the prediction and improvement suggestions of production efficiency based on historical data.

[0106] Based on the analysis, the server evaluates the efficiency of each production line and generates improvement suggestions. These suggestions are communicated to the user through a web application. The user interface is built using the Django framework for this purpose. This allows users to access detailed reports in real time and make necessary decisions quickly.

[0107] For example, a manufacturing line may be found to have consistently high operating rates, yet its energy consumption is abnormally high compared to other lines. This information is immediately communicated to managers, prompting them to consider measures to optimize energy use.

[0108] Example of a prompt:

[0109] "Based on the current operating status of the manufacturing line, please submit suggestions for improving production efficiency."

[0110] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0111] Step 1:

[0112] The server collects data in real time from sensors installed on the manufacturing line and from existing data management systems. The input is raw data from the sensors, such as operating rates, quality indicators, and energy consumption. The output is the storage of the collected data in the server's database. Specifically, sensor data is transferred to the server using a RESTful API or MQTT protocol.

[0113] Step 2:

[0114] The server removes erroneous data from the collected raw data and standardizes it. The input is the raw data obtained in step 1. The Pandas library is used to filter outliers and missing values ​​and standardize the data format. The output is a clean and standardized dataset.

[0115] Step 3:

[0116] The server trains and updates a generative AI model based on clean, standardized data. By training the AI ​​model using TensorFlow, a predictive model capable of handling diverse manufacturing situations is built. The input is the clean dataset obtained in step 2, and the output is the trained AI model.

[0117] Step 4:

[0118] The server uses a trained AI model to analyze the efficiency of the manufacturing line in real time. The input is newly collected real-time data, and the output is an efficiency evaluation for each manufacturing line. Specifically, the server inputs the current data into the AI ​​model and calculates an efficiency score.

[0119] Step 5:

[0120] The server generates improvement suggestions based on the analysis results. The input is the efficiency evaluation results obtained in step 4. The output is specific suggestions for optimizing the operation of the manufacturing line. Improvement suggestions include methods for adjusting the operating rate and optimizing power consumption. The generated suggestions are presented to the user via prompt messages.

[0121] Step 6:

[0122] The terminal displays improvement suggestions notified from the server to the user via a web application. A user interface is built using Django to visually present the suggestions. Input is suggestion data from the server, and output is a detailed report viewable by the user.

[0123] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0124] This invention constructs a business continuity decision system that incorporates an emotion engine into an information processing device. This system, centered around a server, handles everything from data collection and emotion recognition to the generation of a final report.

[0125] First, the server collects various business-related data through an application programming interface or database connection. This data includes sales, expenses, market trends, and customer reviews, and is standardized as needed. The server then uses this data to train a generative artificial intelligence model to automatically determine whether the business is viable to continue.

[0126] Next, a server equipped with an emotion engine acquires user emotional feedback and uses natural language processing technology to recognize and evaluate those emotions. This enables a comprehensive approach to business decision-making that is data-driven yet takes human emotions into consideration.

[0127] The server integrates analytical results and sentiment insights to generate a comprehensive report. This report includes the current state of the business, future proposals, and specific recommendations based on user sentiment. The report is notified to the user via their terminal, allowing them to review their business strategy based on it.

[0128] For example, if a project is stalled due to a lack of resources, the server evaluates the project's viability based on relevant data. In this process, the emotion engine measures the project manager's stress level and other factors through emotional reviews, and recommends the need for additional resources based on their emotional state. This enables efficient resource allocation and management that considers team morale.

[0129] In this way, the present invention provides a system that integrates data analysis and emotion recognition to support balanced management decisions.

[0130] The following describes the processing flow.

[0131] Step 1:

[0132] The server identifies data sources relevant to each business as part of its preparation for data collection. This involves configuring application programming interfaces and database connections, and establishing automated processes for collecting sales data, cost data, market trends, and customer reviews.

[0133] Step 2:

[0134] The server cleans the collected data, correcting or removing inaccurate data and missing values. It also standardizes data formats and units, preparing the data for use in subsequent analysis processes. Algorithms are used throughout this process to ensure data consistency and accuracy.

[0135] Step 3:

[0136] The server trains a generative artificial intelligence model based on cleaned and standardized data. This model uses historical business performance data and market trend data to assess the profitability and market competitiveness of the business and determine whether the business is viable to continue.

[0137] Step 4:

[0138] The server collects feedback and comments from users. Next, it uses an emotion engine to analyze this feedback and recognize the user's emotional state. Natural language processing techniques are used to classify positive, negative, and neutral emotions and evaluate their intensity.

[0139] Step 5:

[0140] The server integrates the business continuity decision with user sentiment ratings obtained from the sentiment engine. Based on this, it generates a comprehensive report on the current state and future prospects of the business. The report includes specific recommendations based on sentiment.

[0141] Step 6:

[0142] The device notifies the user of the generated report. The user reviews this report through the device and uses it as information necessary for business strategy and decision-making. This enables data-driven, emotion-insensitive, and balanced decision-making.

[0143] (Example 2)

[0144] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0145] Current business continuity decision-making systems using information processing equipment must not only collect and analyze vast amounts of data, but also consider emotional insights. However, conventional systems struggle to effectively implement such a comprehensive approach that includes emotional insights, resulting in the challenge of being unable to make balanced management decisions.

[0146] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0147] In this invention, the server includes means for collecting information in various ways, means for training and updating a generative intelligence model based on standardized information, and means for recognizing and evaluating emotional feedback from users. This enables balanced management decisions that are data-driven and take emotional insights into account.

[0148] An "information processing device" is a hardware and software system for collecting, analyzing, and processing digital data.

[0149] A "generative intelligence model" is a form of artificial intelligence that uses machine learning algorithms to analyze large amounts of data and make predictions and decisions.

[0150] "Emotional feedback" refers to comments and data that reflect the user's emotional state, and is information analyzed using natural language processing technology.

[0151] "Natural language processing technology" refers to the technology that enables computer systems to understand, interpret, and manipulate human language.

[0152] A "report" is a document that summarizes analyzed information and recommendations, and is used for reviewing business strategies, etc.

[0153] "Notification" refers to a means of informing users of information or reports, and is typically done via email or digital devices.

[0154] This invention constructs a system for making business continuity decisions using an information processing device. This system operates primarily around a server and enables comprehensive business decisions that integrate diverse data and take emotional feedback into consideration.

[0155] The server first collects diverse information. This collection is done through application programming interfaces (APIs) and data storage connections, and includes sales data, customer reviews, and expense information. This data is used to train generative intelligence models using machine learning techniques with frameworks such as TensorFlow, in order to predict business risks and sustainability.

[0156] Next, the server uses an emotion engine to obtain emotional feedback from users. Data is collected through forms embedded in the employee portal, and natural language processing technology is used to recognize and evaluate those emotions. This enables balanced decision-making that is data-driven yet takes emotional aspects into account.

[0157] The generated judgments and emotional insights are compiled into a comprehensive report. The server generates this report and notifies the user via their terminal. The notification is sent via email or the company portal, allowing the user to review their business strategy based on it.

[0158] For example, if a project is stalled due to a lack of resources, the server will evaluate the project's prospects based on relevant information. In this process, the emotion engine can analyze the project manager's stress level and recommend whether additional resources are needed.

[0159] An example of a prompt message could be, "Based on the latest information on Project X and the manager's sentiment review, assess the need for additional resources and generate recommendations." In this way, the present invention provides a system that supports sophisticated business decisions by combining technical and emotional elements.

[0160] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0161] Step 1:

[0162] The server collects business-related data through application programming interfaces (APIs) and data storage connections. This data includes sales, expenses, market trends, etc. Each data source is retrieved as input via API calls, and the output is obtained by converting its contents into a unified format (e.g., JSON).

[0163] Step 2:

[0164] The server uses the collected data to clean and standardize inaccurate data. The input is the unified formatted data collected in step 1, and the server uses a data cleaning algorithm to remove outliers and impute missing values. As a result, it outputs a standardized dataset suitable for analysis.

[0165] Step 3:

[0166] The server trains a generative AI model using standardized data. The input is the dataset created in step 2, and the model is trained using a machine learning framework (e.g., TensorFlow). After training is complete, it outputs a skilled model for determining business continuity.

[0167] Step 4:

[0168] The server acquires user emotional feedback. The input is emotional data provided by the user through an employee portal form, which is then analyzed using natural language processing technology. The analysis results output a quantified emotional evaluation.

[0169] Step 5:

[0170] The server integrates the results of the trained generative AI model and the analysis of emotional feedback to automatically determine whether the business can be continued. The inputs are the model output in step 3 and the emotional evaluation in step 4, which are used to assess the business's riskiness. The final decision result is then output.

[0171] Step 6:

[0172] The server generates a comprehensive report based on the judgment results and sentiment insights. The input is the judgment results and recommendations from step 5, and the document generation algorithm outputs a report in PDF format.

[0173] Step 7:

[0174] The terminal notifies the user of the report. The input is the report generated in step 6, which is delivered to the user via email or the employee portal. The final output is in the form of a link accessible to the user.

[0175] Step 8:

[0176] The user reviews their business strategy based on the notified report. The input is the report delivered in step 7, and by reviewing it in detail, they can reallocate resources, consider new measures, and obtain output that allows them to formulate a more appropriate business strategy.

[0177] (Application Example 2)

[0178] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0179] In modern e-commerce, providing truly personalized product recommendations that meet user needs is challenging. Furthermore, the inability to consider human emotions in business continuity decisions makes it difficult to make objective, data-driven judgments. This makes it difficult for companies to make efficient decisions and limits their ability to improve user satisfaction.

[0180] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0181] In this invention, the server includes means for an information processing device to collect diverse information related to multiple businesses; means for cleaning up inaccurate content and standardizing the collected information; means for training and updating a generative artificial intelligence model based on the cleaned and standardized information; means for automatically determining whether or not to continue a business using the trained model; means for generating and reporting a report containing the determination result and recommendations; means for analyzing the user's emotional response and recognizing and evaluating emotions using natural language processing technology; and means for integrating information based on the emotional recognition result and making customized product suggestions. This enables more accurate and personalized decision-making and product suggestions by utilizing both data and emotional information.

[0182] An "information processing device" is a general term for electronic devices that collect, analyze, and process digital data and output the results.

[0183] "Diverse information" refers to a collection of digital data with different characteristics, such as sales, expenses, market trends, and customer reviews.

[0184] "Means of cleaning up inaccurate content and standardizing it" refers to methods or techniques for carrying out the process of correcting errors in data and unifying data formats.

[0185] A "generative artificial intelligence model" refers to an artificial intelligence algorithm or framework that makes predictions and decisions based on pre-provided data.

[0186] "Means for automatically determining whether a business can continue" refers to a method that uses collected data to determine, through a mechanical process, whether or not a business can continue.

[0187] "Means for generating and reporting reports" refers to methods or techniques for creating a report summarizing the analysis results and presenting it to relevant parties.

[0188] "A means of analyzing user emotional responses and recognizing and evaluating emotions using natural language processing technology" refers to a method of analyzing user feedback and using natural language processing to understand their emotional state.

[0189] "Methods for providing customized product recommendations" refer to methods of recommending the most suitable products and services based on the individual user's needs and feelings.

[0190] The system that realizes this application consists of an information processing unit. The server has a mechanism to automatically collect various business-related information through application program interfaces and information connections. The collected information is cleaned and standardized within the server to remove any inaccuracies. This prepares a unified data format.

[0191] Next, the server uses the cleaned and standardized information to train and update data using a generative artificial intelligence model. This AI model is created using frameworks such as TensorFlow and operates to automatically determine whether a business can continue. This process enables current business analysis and future predictions.

[0192] Furthermore, the server analyzes users' emotional responses, recognizing and evaluating emotions using natural language processing technologies such as NLTK and spaCy. Specifically, it analyzes reviews and feedback collected from users to identify positive or negative emotions and incorporates them into the business decision-making process.

[0193] The server integrates emotion recognition results and data analysis results to provide users with customized product recommendations. These recommendations are generated based on the individual user's needs and emotions. For example, if a user provides positive feedback, similar products or upsell items will be suggested.

[0194] As an example of a prompt, a message like, "Suggest similar products to the item the user is currently viewing, based on their purchase history and sentiment feedback," would enable the server to make sophisticated decisions accordingly.

[0195] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0196] Step 1:

[0197] The server automatically collects diverse business-related information through application program interfaces and information connections. Inputs include raw data such as sales, expenses, market trends, and customer reviews, while outputs are in a standardized data format. During the data collection process, information is extracted from various data sources and stored in a database on the server.

[0198] Step 2:

[0199] The server cleanses and standardizes inaccurate content. The input is the diverse information collected in Step 1, and the output is standardized data with errors corrected. The data cleansing and standardization process involves imputing missing values, correcting outliers, and transforming data formats to generate a consistent dataset.

[0200] Step 3:

[0201] The server trains and updates a generative artificial intelligence model based on standardized information. The input is the standardized data obtained in step 2, and the output is the trained AI model. During the AI ​​model training process, it learns data patterns and creates a predictive model to determine whether a business can continue.

[0202] Step 4:

[0203] The server automatically determines whether a business can be continued using an AI model. The input is real-time updated information, and the output is the result of the decision on whether or not to continue. In the model's prediction process, it evaluates current market conditions and past performance to make the optimal decision.

[0204] Step 5:

[0205] The server analyzes user emotional responses and recognizes and evaluates emotions using natural language processing techniques. Input is user reviews and feedback, and output is a positive or negative emotional evaluation. The emotional analysis process involves analyzing text and calculating an emotional score.

[0206] Step 6:

[0207] The server provides customized product recommendations based on emotion recognition results and data analysis results. The input is emotion evaluation and the AI ​​model's judgment, while the output is product recommendations optimized for each individual user. During the recommendation process, products are selected and a recommendation list is generated, taking into account the user's emotional state and past behavioral history.

[0208] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0209] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0210] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0211] [Second Embodiment]

[0212] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0213] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0214] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0215] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0216] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0217] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0218] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0219] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0220] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0221] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0222] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0223] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0224] This invention provides a system that automates business continuity decisions by executing a program running on an information processing device. This system has a server-centric structure and supports management decisions by performing real-time data collection and analysis.

[0225] First, the server automatically collects data related to multiple businesses from various sources. This includes sales data, expense data, market trend data, and customer feedback data. The server retrieves this data through application programming interfaces and database connections and standardizes it to ensure data consistency.

[0226] Next, the server uses a generative artificial intelligence model to analyze the collected data. During this analysis process, the AI ​​model is trained and, considering past business performance and market trends, predicts the profitability and market position of each business. This allows for an objective evaluation of three options: continue the business, not continue it, or wait and see.

[0227] The server automatically makes decisions based on the analysis results and compiles the results, along with the reasoning, into a detailed report. This report is notified to the user via their terminal and can be used to review business strategies and efficiently allocate resources.

[0228] For example, a user might want to identify underperforming products from their multiple product lines. The server collects all relevant product data and analyzes it using a generative AI model. The server evaluates the profitability and market share of each product line and provides a report summarizing the reasons for the underperformance. The user can then use this report to implement improvements to the underperforming products or decide to discontinue them.

[0229] In this way, a system is provided that eliminates information bias and emotional judgments, enabling rational and data-driven management decisions.

[0230] The following describes the processing flow.

[0231] Step 1:

[0232] The server identifies sources for collecting sales data, expense data, market trend data, and customer feedback data related to each business. To this end, it configures application programming interfaces and database connections, enabling the automation of data retrieval.

[0233] Step 2:

[0234] The server cleans the collected data, correcting or removing inaccurate data. Furthermore, it standardizes different data formats and units, converting them into a consistent format suitable for analysis. This process also includes imputing missing data values.

[0235] Step 3:

[0236] The server trains a generative artificial intelligence model based on standardized data. This model learns from historical business performance data and market trends, and is optimized to evaluate the profitability and market competitiveness of the business.

[0237] Step 4:

[0238] The server uses trained AI models to predict the current and future performance of each business. The models analyze profitability, risk assessment, and business continuity in response to market changes, providing decisions on whether to continue, not continue, or wait and see.

[0239] Step 5:

[0240] The server generates a detailed report based on the analysis results of the AI ​​model. This report includes a summary of the analysis, a decision on whether each business can be continued, and the reasons for those decisions.

[0241] Step 6:

[0242] The terminal notifies the user of the generated report. The user can use the terminal to review the report and use it as material for specific business decisions. This reporting function allows the user to review the allocation of management resources and strategies based on objective data.

[0243] (Example 1)

[0244] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0245] In today's business environment, a vast amount of information is available, demanding quick and accurate management decisions. However, it is difficult to select highly relevant information from a massive dataset and make rational decisions based on it. Furthermore, information is easily influenced by biases and emotional factors, making it challenging to make objective, data-driven judgments.

[0246] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0247] In this invention, the server includes means for collecting diverse information related to multiple business operations, means for performing predictive analysis using generative artificial intelligence based on standardized information, and means for generating and providing reports to users that include evaluation results and the reasons for those results. This eliminates information bias and enables objective, data-driven management decisions.

[0248] An "information processing device" is a device that collects, processes, and analyzes data and generates output tailored to a specific purpose.

[0249] "Generative artificial intelligence" refers to artificial intelligence that has the ability to generate new information based on past data, and is a technology used for prediction and analysis.

[0250] "Predictive analytics" is an analytical method used to predict future events and outcomes based on collected data.

[0251] Standardization is the process of ensuring data consistency and converting it into a comparable format.

[0252] A "report" is a document that organizes the results of an analysis and the reasoning behind the decisions, and provides them to the user.

[0253] A "prompt message" is an instruction that a user enters into the system, intended to prompt specific analysis or processing.

[0254] A "terminal" is a device used by a user to obtain information or input data.

[0255] This invention is a system that automates the decision-making process for continuing operations using an information processing device. This system has a server-centric structure and supports management decisions through real-time information collection and analysis. The system utilizes generative artificial intelligence to efficiently analyze data.

[0256] First, the server automatically collects business-related information from various sources via APIs and database connections. This system retrieves data from a variety of sources, including customer relationship management tools and sales management software. This allows for the collection of information such as sales, expenses, market trends, and customer feedback.

[0257] The server then standardizes the collected data and converts it into a consistent format. This unifies data from different information sources, making it comparable. The server then uses the standardized data to perform predictive analytics using generative artificial intelligence models. This process utilizes libraries such as Python's TensorFlow, and objective evaluation becomes possible by performing data analysis based on past performance and market trends.

[0258] For example, a user might want to know which of their multiple business lines is underperforming. In this case, the server collects data related to each business line and analyzes it using a generative AI model. As a result, a detailed report is generated indicating which businesses are experiencing profitability problems. Based on this report, the user can then formulate further improvement measures or consider shutting down the business.

[0259] An example of a prompt message that can be entered into the system is: "Based on current sales data and market trends, identify the least profitable business line and analyze the cause."

[0260] In this way, the system of the present invention eliminates information bias and emotional judgments, and supports rational and data-driven management decisions.

[0261] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0262] Step 1:

[0263] The server collects business-related data from multiple sources. Specifically, it obtains sales, expenses, market trends, and customer feedback data from various services and platforms via APIs and database connections. The input data consists of this information and is temporarily stored in storage after collection. The output is the raw dataset used in subsequent standardization processes.

[0264] Step 2:

[0265] The server standardizes the collected data. This is the process of converting data in different formats and units into a consistent format. For example, it converts all numerical data to a common currency unit and unifies date formats. It also applies appropriate imputation if outliers or missing values ​​exist. The input is the original dataset from step 1, and the output is the standardized dataset.

[0266] Step 3:

[0267] The server performs predictive analysis using a generative artificial intelligence model based on standardized data. Specifically, the server inputs data into the generative AI model and predicts future profitability and market share by comparing it with past performance data and market trends. The Python TensorFlow library is used in this process. The input is the standardized dataset from step 2, and the output is the analysis results showing the continuity and potential risks of each business.

[0268] Step 4:

[0269] Based on the predictive analytics results, the server generates a detailed report containing three options: continue operations, suspend operations, or wait and see. This report also includes reasoning and recommendations. The input is the analysis results from step 3, and the output is a report designed to facilitate user decision-making.

[0270] Step 5:

[0271] The terminal notifies the user of reports received from the server. This process is designed to display new information in real time on the dashboard. The input is the report generated in step 4, and the output is a visual notification on the user interface.

[0272] Step 6:

[0273] Users review reports on the dashboard and revise their strategies based on the presented data. In this step, users can enter new prompts to instruct further detailed analysis and hypothesis testing. The input is the report presented on the device, and the output is the user's strategic decision.

[0274] (Application Example 1)

[0275] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0276] In manufacturing, multiple production lines are operated simultaneously, making it difficult to maintain optimal production efficiency for each. In particular, increased product defect rates and energy consumption can lead to decreased profits, necessitating automated systems to quickly identify and address these issues. However, traditional methods have limitations in providing consistent real-time monitoring and efficient improvement suggestions. Therefore, new technological means are needed to improve factory production efficiency.

[0277] The specific processing by the specific processing unit 290 of the data processing apparatus 12 in Application Example 1 is realized by the following respective means.

[0278] In this invention, the server includes: means for an information processing module to collect various information related to a plurality of operations; means for deleting and unifying erroneous data using the collected information; means for training and updating a generative artificial intelligence model based on the deleted and unified information; means for collecting and analyzing production data of a manufacturing line in real time; and means for evaluating the efficiency of the manufacturing line and presenting improvement proposals. Thereby, it becomes possible to efficiently monitor the operation status of the production line, detect problems at an early stage, and quickly propose improvement measures.

[0279] The "information processing module" is a device or program having a function of collecting, organizing, and analyzing data.

[0280] "Information" is data or a set thereof used for analysis and judgment.

[0281] "Erroneous data" is data lacking accuracy due to inconsistencies in the collection process or records.

[0282] "Deletion" is a process of excluding error data from the system and purifying the data set.

[0283] "Unification" is a process of converting data in different formats or units into a consistent format.

[0284] The "generative artificial intelligence model" is a model of an algorithm created to learn from data and support prediction and judgment.

[0285] "Training" is a process for a machine learning algorithm to obtain appropriate prediction ability based on data.

[0286] "Update" refers to the process of improving the performance of a machine learning model using the latest data.

[0287] "Production data" refers to information regarding the operating rate, product quality, energy consumption, etc. in the manufacturing process.

[0288] "Collecting in real time" refers to the process of acquiring information almost simultaneously when the information is generated.

[0289] "Analysis" refers to the process of evaluating the collected information and deriving meaningful implications.

[0290] "Efficiency" is a measure indicating how effectively a manufacturing line uses resources in relation to the target.

[0291] "Improvement proposals" refer to specific measures for solving problems and improving production efficiency.

[0292] The system for implementing this invention has an information processing module operating on a server, aiming to improve production efficiency in the manufacturing industry. The server collects production data of the manufacturing line in real time through sensors and existing data management systems. This includes the operating rate, product quality indicators, energy consumption, etc.

[0293] When the data is aggregated on the server, deletion and unification of incorrect data are performed. Specifically, a data processing script using Python is essential, and the Pandas library is used to filter out incorrect data. Thereafter, the clean data is analyzed by a generative artificial intelligence model. TensorFlow or PyTorch is used for training and updating the model, enabling prediction of production efficiency and improvement proposals based on past data.

[0294] Based on the analysis, the server evaluates the efficiency of each production line and generates improvement suggestions. These suggestions are communicated to the user through a web application. The user interface is built using the Django framework for this purpose. This allows users to access detailed reports in real time and make necessary decisions quickly.

[0295] For example, a manufacturing line may be found to have consistently high operating rates, yet its energy consumption is abnormally high compared to other lines. This information is immediately communicated to managers, prompting them to consider measures to optimize energy use.

[0296] Example of a prompt:

[0297] "Based on the current operating status of the manufacturing line, please submit suggestions for improving production efficiency."

[0298] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0299] Step 1:

[0300] The server collects data in real time from sensors installed on the manufacturing line and from existing data management systems. The input is raw data from the sensors, such as operating rates, quality indicators, and energy consumption. The output is the storage of the collected data in the server's database. Specifically, sensor data is transferred to the server using a RESTful API or MQTT protocol.

[0301] Step 2:

[0302] The server removes erroneous data from the collected raw data and standardizes it. The input is the raw data obtained in step 1. The Pandas library is used to filter outliers and missing values ​​and standardize the data format. The output is a clean and standardized dataset.

[0303] Step 3:

[0304] The server trains and updates the generated AI model based on clean and standardized data. By training the AI model using TensorFlow, a prediction model that can handle various manufacturing situations is constructed. The input is the clean dataset obtained in Step 2, and the output is the trained AI model.

[0305] Step 4:

[0306] The server uses the trained AI model to analyze the efficiency of the production line in real time. The input is the newly collected real-time data, and the output is the efficiency evaluation for each production line. As a specific operation, the server inputs the current data into the AI model and calculates the efficiency score.

[0307] Step 5:

[0308] The server generates improvement suggestions based on the analysis results. The input is the efficiency evaluation result obtained in Step 4. The output is specific suggestions for optimizing the operation of the production line. The improvement suggestions include adjustments to the operating rate and methods for optimizing power consumption. The generated suggestions are presented to the user via a prompt message.

[0309] Step 6:

[0310] The terminal displays the improvement suggestions notified by the server to the user through a web application. Using Django, a user interface is constructed to visually present the content of the suggestions. The input is the suggestion data from the server, and the output is a detailed report that can be viewed by the user.

[0311] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0312] This invention constructs a business continuity decision system that incorporates an emotion engine into an information processing device. This system, centered around a server, handles everything from data collection and emotion recognition to the generation of a final report.

[0313] First, the server collects various business-related data through an application programming interface or database connection. This data includes sales, expenses, market trends, and customer reviews, and is standardized as needed. The server then uses this data to train a generative artificial intelligence model to automatically determine whether the business is viable to continue.

[0314] Next, a server equipped with an emotion engine acquires user emotional feedback and uses natural language processing technology to recognize and evaluate those emotions. This enables a comprehensive approach to business decision-making that is data-driven yet takes human emotions into consideration.

[0315] The server integrates analytical results and sentiment insights to generate a comprehensive report. This report includes the current state of the business, future proposals, and specific recommendations based on user sentiment. The report is notified to the user via their terminal, allowing them to review their business strategy based on it.

[0316] For example, if a project is stalled due to a lack of resources, the server evaluates the project's viability based on relevant data. In this process, the emotion engine measures the project manager's stress level and other factors through emotional reviews, and recommends the need for additional resources based on their emotional state. This enables efficient resource allocation and management that considers team morale.

[0317] In this way, the present invention provides a system that integrates data analysis and emotion recognition to support balanced management decisions.

[0318] The following describes the processing flow.

[0319] Step 1:

[0320] The server identifies data sources relevant to each business as part of its preparation for data collection. This involves configuring application programming interfaces and database connections, and establishing automated processes for collecting sales data, cost data, market trends, and customer reviews.

[0321] Step 2:

[0322] The server cleans the collected data, correcting or removing inaccurate data and missing values. It also standardizes data formats and units, preparing the data for use in subsequent analysis processes. Algorithms are used throughout this process to ensure data consistency and accuracy.

[0323] Step 3:

[0324] The server trains a generative artificial intelligence model based on cleaned and standardized data. This model uses historical business performance data and market trend data to assess the profitability and market competitiveness of the business and determine whether the business is viable to continue.

[0325] Step 4:

[0326] The server collects feedback and comments from users. Next, it uses an emotion engine to analyze this feedback and recognize the user's emotional state. Natural language processing techniques are used to classify positive, negative, and neutral emotions and evaluate their intensity.

[0327] Step 5:

[0328] The server integrates the business continuity decision with user sentiment ratings obtained from the sentiment engine. Based on this, it generates a comprehensive report on the current state and future prospects of the business. The report includes specific recommendations based on sentiment.

[0329] Step 6:

[0330] The device notifies the user of the generated report. The user reviews this report through the device and uses it as information necessary for business strategy and decision-making. This enables data-driven, emotion-insensitive, and balanced decision-making.

[0331] (Example 2)

[0332] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0333] Current business continuity decision-making systems using information processing equipment must not only collect and analyze vast amounts of data, but also consider emotional insights. However, conventional systems struggle to effectively implement such a comprehensive approach that includes emotional insights, resulting in the challenge of being unable to make balanced management decisions.

[0334] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0335] In this invention, the server includes means for collecting information in various ways, means for training and updating a generative intelligence model based on standardized information, and means for recognizing and evaluating emotional feedback from users. This enables balanced management decisions that are data-driven and take emotional insights into account.

[0336] An "information processing device" is a hardware and software system for collecting, analyzing, and processing digital data.

[0337] A "generative intelligence model" is a form of artificial intelligence that uses machine learning algorithms to analyze large amounts of data and make predictions and decisions.

[0338] "Emotional feedback" refers to comments and data that reflect the user's emotional state, and is information analyzed using natural language processing technology.

[0339] "Natural language processing technology" refers to the technology that enables computer systems to understand, interpret, and manipulate human language.

[0340] A "report" is a document that summarizes analyzed information and recommendations, and is used for reviewing business strategies, etc.

[0341] "Notification" refers to a means of informing users of information or reports, and is typically done via email or digital devices.

[0342] This invention constructs a system for making business continuity decisions using an information processing device. This system operates primarily around a server and enables comprehensive business decisions that integrate diverse data and take emotional feedback into consideration.

[0343] The server first collects diverse information. This collection is done through application programming interfaces (APIs) and data storage connections, and includes sales data, customer reviews, and expense information. This data is used to train generative intelligence models using machine learning techniques with frameworks such as TensorFlow, in order to predict business risks and sustainability.

[0344] Next, the server uses an emotion engine to obtain emotional feedback from users. Data is collected through forms embedded in the employee portal, and natural language processing technology is used to recognize and evaluate those emotions. This enables balanced decision-making that is data-driven yet takes emotional aspects into account.

[0345] The generated judgments and emotional insights are compiled into a comprehensive report. The server generates this report and notifies the user via their terminal. The notification is sent via email or the company portal, allowing the user to review their business strategy based on it.

[0346] For example, if a project is stalled due to a lack of resources, the server will evaluate the project's prospects based on relevant information. In this process, the emotion engine can analyze the project manager's stress level and recommend whether additional resources are needed.

[0347] An example of a prompt message could be, "Based on the latest information on Project X and the manager's sentiment review, assess the need for additional resources and generate recommendations." In this way, the present invention provides a system that supports sophisticated business decisions by combining technical and emotional elements.

[0348] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0349] Step 1:

[0350] The server collects business-related data through application programming interfaces (APIs) and data storage connections. This data includes sales, expenses, market trends, etc. Each data source is retrieved as input via API calls, and the output is obtained by converting its contents into a unified format (e.g., JSON).

[0351] Step 2:

[0352] The server uses the collected data to clean and standardize inaccurate data. The input is the unified formatted data collected in step 1, and the server uses a data cleaning algorithm to remove outliers and impute missing values. As a result, it outputs a standardized dataset suitable for analysis.

[0353] Step 3:

[0354] The server trains a generative AI model using standardized data. The input is the dataset created in step 2, and the model is trained using a machine learning framework (e.g., TensorFlow). After training is complete, it outputs a skilled model for determining business continuity.

[0355] Step 4:

[0356] The server acquires user emotional feedback. The input is emotional data provided by the user through an employee portal form, which is then analyzed using natural language processing technology. The analysis results output a quantified emotional evaluation.

[0357] Step 5:

[0358] The server integrates the results of the trained generative AI model and the analysis of emotional feedback to automatically determine whether the business can be continued. The inputs are the model output in step 3 and the emotional evaluation in step 4, which are used to assess the business's riskiness. The final decision result is then output.

[0359] Step 6:

[0360] The server generates a comprehensive report based on the judgment results and sentiment insights. The input is the judgment results and recommendations from step 5, and the document generation algorithm outputs a report in PDF format.

[0361] Step 7:

[0362] The terminal notifies the user of the report. The input is the report generated in step 6, which is delivered to the user via email or the employee portal. The final output is in the form of a link accessible to the user.

[0363] Step 8:

[0364] The user reviews their business strategy based on the notified report. The input is the report delivered in step 7, and by reviewing it in detail, they can reallocate resources, consider new measures, and obtain output that allows them to formulate a more appropriate business strategy.

[0365] (Application Example 2)

[0366] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0367] In modern e-commerce, providing truly personalized product recommendations that meet user needs is challenging. Furthermore, the inability to consider human emotions in business continuity decisions makes it difficult to make objective, data-driven judgments. This makes it difficult for companies to make efficient decisions and limits their ability to improve user satisfaction.

[0368] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0369] In this invention, the server includes means for an information processing device to collect diverse information related to multiple businesses; means for cleaning up inaccurate content and standardizing the collected information; means for training and updating a generative artificial intelligence model based on the cleaned and standardized information; means for automatically determining whether or not to continue a business using the trained model; means for generating and reporting a report containing the determination result and recommendations; means for analyzing the user's emotional response and recognizing and evaluating emotions using natural language processing technology; and means for integrating information based on the emotional recognition result and making customized product suggestions. This enables more accurate and personalized decision-making and product suggestions by utilizing both data and emotional information.

[0370] An "information processing device" is a general term for electronic devices that collect, analyze, and process digital data and output the results.

[0371] "Diverse information" refers to a collection of digital data with different characteristics, such as sales, expenses, market trends, and customer reviews.

[0372] "Means of cleaning up inaccurate content and standardizing it" refers to methods or techniques for carrying out the process of correcting errors in data and unifying data formats.

[0373] A "generative artificial intelligence model" refers to an artificial intelligence algorithm or framework that makes predictions and decisions based on pre-provided data.

[0374] "Means for automatically determining whether a business can continue" refers to a method that uses collected data to determine, through a mechanical process, whether or not a business can continue.

[0375] "Means for generating and reporting reports" refers to methods or techniques for creating a report summarizing the analysis results and presenting it to relevant parties.

[0376] "A means of analyzing user emotional responses and recognizing and evaluating emotions using natural language processing technology" refers to a method of analyzing user feedback and using natural language processing to understand their emotional state.

[0377] "Methods for providing customized product recommendations" refer to methods of recommending the most suitable products and services based on the individual user's needs and feelings.

[0378] The system that realizes this application consists of an information processing unit. The server has a mechanism to automatically collect various business-related information through application program interfaces and information connections. The collected information is cleaned and standardized within the server to remove any inaccuracies. This prepares a unified data format.

[0379] Next, the server uses the cleaned and standardized information to train and update data using a generative artificial intelligence model. This AI model is created using frameworks such as TensorFlow and operates to automatically determine whether a business can continue. This process enables current business analysis and future predictions.

[0380] Furthermore, the server analyzes users' emotional responses, recognizing and evaluating emotions using natural language processing technologies such as NLTK and spaCy. Specifically, it analyzes reviews and feedback collected from users to identify positive or negative emotions and incorporates them into the business decision-making process.

[0381] The server integrates emotion recognition results and data analysis results to provide users with customized product recommendations. These recommendations are generated based on the individual user's needs and emotions. For example, if a user provides positive feedback, similar products or upsell items will be suggested.

[0382] As an example of a prompt, a message like, "Suggest similar products to the item the user is currently viewing, based on their purchase history and sentiment feedback," would enable the server to make sophisticated decisions accordingly.

[0383] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0384] Step 1:

[0385] The server automatically collects diverse business-related information through application program interfaces and information connections. Inputs include raw data such as sales, expenses, market trends, and customer reviews, while outputs are in a standardized data format. During the data collection process, information is extracted from various data sources and stored in a database on the server.

[0386] Step 2:

[0387] The server cleanses and standardizes inaccurate content. The input is the diverse information collected in Step 1, and the output is standardized data with errors corrected. The data cleansing and standardization process involves imputing missing values, correcting outliers, and transforming data formats to generate a consistent dataset.

[0388] Step 3:

[0389] The server trains and updates a generative artificial intelligence model based on standardized information. The input is the standardized data obtained in step 2, and the output is the trained AI model. During the AI ​​model training process, it learns data patterns and creates a predictive model to determine whether a business can continue.

[0390] Step 4:

[0391] The server automatically determines whether a business can be continued using an AI model. The input is real-time updated information, and the output is the result of the decision on whether or not to continue. In the model's prediction process, it evaluates current market conditions and past performance to make the optimal decision.

[0392] Step 5:

[0393] The server analyzes user emotional responses and recognizes and evaluates emotions using natural language processing techniques. Input is user reviews and feedback, and output is a positive or negative emotional evaluation. The emotional analysis process involves analyzing text and calculating an emotional score.

[0394] Step 6:

[0395] The server provides customized product recommendations based on emotion recognition results and data analysis results. The input is emotion evaluation and the AI ​​model's judgment, while the output is product recommendations optimized for each individual user. During the recommendation process, products are selected and a recommendation list is generated, taking into account the user's emotional state and past behavioral history.

[0396] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0397] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0398] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0399] [Third Embodiment]

[0400] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0401] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0402] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0403] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0404] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0405] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0406] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0407] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0408] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0409] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0410] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0411] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0412] This invention provides a system that automates business continuity decisions by executing a program running on an information processing device. This system has a server-centric structure and supports management decisions by performing real-time data collection and analysis.

[0413] First, the server automatically collects data related to multiple businesses from various sources. This includes sales data, expense data, market trend data, and customer feedback data. The server retrieves this data through application programming interfaces and database connections and standardizes it to ensure data consistency.

[0414] Next, the server uses a generative artificial intelligence model to analyze the collected data. During this analysis process, the AI ​​model is trained and, considering past business performance and market trends, predicts the profitability and market position of each business. This allows for an objective evaluation of three options: continue the business, not continue it, or wait and see.

[0415] The server automatically makes decisions based on the analysis results and compiles the results, along with the reasoning, into a detailed report. This report is notified to the user via their terminal and can be used to review business strategies and efficiently allocate resources.

[0416] For example, a user might want to identify underperforming products from their multiple product lines. The server collects all relevant product data and analyzes it using a generative AI model. The server evaluates the profitability and market share of each product line and provides a report summarizing the reasons for the underperformance. The user can then use this report to implement improvements to the underperforming products or decide to discontinue them.

[0417] In this way, a system is provided that eliminates information bias and emotional judgments, enabling rational and data-driven management decisions.

[0418] The following describes the processing flow.

[0419] Step 1:

[0420] The server identifies sources for collecting sales data, expense data, market trend data, and customer feedback data related to each business. To this end, it configures application programming interfaces and database connections, enabling the automation of data retrieval.

[0421] Step 2:

[0422] The server cleans the collected data, correcting or removing inaccurate data. Furthermore, it standardizes different data formats and units, converting them into a consistent format suitable for analysis. This process also includes imputing missing data values.

[0423] Step 3:

[0424] The server trains a generative artificial intelligence model based on standardized data. This model learns from historical business performance data and market trends, and is optimized to evaluate the profitability and market competitiveness of the business.

[0425] Step 4:

[0426] The server uses trained AI models to predict the current and future performance of each business. The models analyze profitability, risk assessment, and business continuity in response to market changes, providing decisions on whether to continue, not continue, or wait and see.

[0427] Step 5:

[0428] The server generates a detailed report based on the analysis results of the AI ​​model. This report includes a summary of the analysis, a decision on whether each business can be continued, and the reasons for those decisions.

[0429] Step 6:

[0430] The terminal notifies the user of the generated report. The user can use the terminal to review the report and use it as material for specific business decisions. This reporting function allows the user to review the allocation of management resources and strategies based on objective data.

[0431] (Example 1)

[0432] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0433] In today's business environment, a vast amount of information is available, demanding quick and accurate management decisions. However, it is difficult to select highly relevant information from a massive dataset and make rational decisions based on it. Furthermore, information is easily influenced by biases and emotional factors, making it challenging to make objective, data-driven judgments.

[0434] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0435] In this invention, the server includes means for collecting diverse information related to multiple business operations, means for performing predictive analysis using generative artificial intelligence based on standardized information, and means for generating and providing reports to users that include evaluation results and the reasons for those results. This eliminates information bias and enables objective, data-driven management decisions.

[0436] An "information processing device" is a device that collects, processes, and analyzes data and generates output tailored to a specific purpose.

[0437] "Generative artificial intelligence" refers to artificial intelligence that has the ability to generate new information based on past data, and is a technology used for prediction and analysis.

[0438] "Predictive analytics" is an analytical method used to predict future events and outcomes based on collected data.

[0439] Standardization is the process of ensuring data consistency and converting it into a comparable format.

[0440] A "report" is a document that organizes the results of an analysis and the reasoning behind the decisions, and provides them to the user.

[0441] A "prompt message" is an instruction that a user enters into the system, intended to prompt specific analysis or processing.

[0442] A "terminal" is a device used by a user to obtain information or input data.

[0443] This invention is a system that automates the decision-making process for continuing operations using an information processing device. This system has a server-centric structure and supports management decisions through real-time information collection and analysis. The system utilizes generative artificial intelligence to efficiently analyze data.

[0444] First, the server automatically collects business-related information from various sources via APIs and database connections. This system retrieves data from a variety of sources, including customer relationship management tools and sales management software. This allows for the collection of information such as sales, expenses, market trends, and customer feedback.

[0445] The server then standardizes the collected data and converts it into a consistent format. This unifies data from different information sources, making it comparable. The server then uses the standardized data to perform predictive analytics using generative artificial intelligence models. This process utilizes libraries such as Python's TensorFlow, and objective evaluation becomes possible by performing data analysis based on past performance and market trends.

[0446] For example, a user might want to know which of their multiple business lines is underperforming. In this case, the server collects data related to each business line and analyzes it using a generative AI model. As a result, a detailed report is generated indicating which businesses are experiencing profitability problems. Based on this report, the user can then formulate further improvement measures or consider shutting down the business.

[0447] An example of a prompt message that can be entered into the system is: "Based on current sales data and market trends, identify the least profitable business line and analyze the cause."

[0448] In this way, the system of the present invention eliminates information bias and emotional judgments, and supports rational and data-driven management decisions.

[0449] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0450] Step 1:

[0451] The server collects business-related data from multiple sources. Specifically, it obtains sales, expenses, market trends, and customer feedback data from various services and platforms via APIs and database connections. The input data consists of this information and is temporarily stored in storage after collection. The output is the raw dataset used in subsequent standardization processes.

[0452] Step 2:

[0453] The server standardizes the collected data. This is the process of converting data in different formats and units into a consistent format. For example, it converts all numerical data to a common currency unit and unifies date formats. It also applies appropriate imputation if outliers or missing values ​​exist. The input is the original dataset from step 1, and the output is the standardized dataset.

[0454] Step 3:

[0455] The server performs predictive analysis using a generative artificial intelligence model based on standardized data. Specifically, the server inputs data into the generative AI model and predicts future profitability and market share by comparing it with past performance data and market trends. The Python TensorFlow library is used in this process. The input is the standardized dataset from step 2, and the output is the analysis results showing the continuity and potential risks of each business.

[0456] Step 4:

[0457] Based on the predictive analytics results, the server generates a detailed report containing three options: continue operations, suspend operations, or wait and see. This report also includes reasoning and recommendations. The input is the analysis results from step 3, and the output is a report designed to facilitate user decision-making.

[0458] Step 5:

[0459] The terminal notifies the user of reports received from the server. This process is designed to display new information in real time on the dashboard. The input is the report generated in step 4, and the output is a visual notification on the user interface.

[0460] Step 6:

[0461] Users review reports on the dashboard and revise their strategies based on the presented data. In this step, users can enter new prompts to instruct further detailed analysis and hypothesis testing. The input is the report presented on the device, and the output is the user's strategic decision.

[0462] (Application Example 1)

[0463] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0464] In manufacturing, multiple production lines are operated simultaneously, making it difficult to maintain optimal production efficiency for each. In particular, increased product defect rates and energy consumption can lead to decreased profits, necessitating automated systems to quickly identify and address these issues. However, traditional methods have limitations in providing consistent real-time monitoring and efficient improvement suggestions. Therefore, new technological means are needed to improve factory production efficiency.

[0465] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0466] In this invention, the server includes means for an information processing module to collect diverse information related to multiple tasks, means for deleting and unifying erroneous data using the collected information, means for training and updating a generative artificial intelligence model based on the deleted and unified information, means for collecting and analyzing production data from a manufacturing line in real time, and means for evaluating the efficiency of the manufacturing line and proposing improvement suggestions. This enables efficient monitoring of the operation status of the production line, early detection of problems, and rapid proposal of improvement measures.

[0467] An "information processing module" is a device or program that has the function of collecting, organizing, and analyzing data.

[0468] "Information" refers to data or collections of data used for analysis and decision-making.

[0469] "Inaccurate data" refers to data that lacks accuracy due to inconsistencies in the collection process or records.

[0470] "Deletion" is the process of removing erroneous data from the system and purifying the dataset.

[0471] "Standardization" is the process of converting data from different formats and units into a consistent format.

[0472] A "generative artificial intelligence model" is a model of algorithms that learns from data and is created to support prediction and decision-making.

[0473] "Training" is the process by which a machine learning algorithm acquires appropriate predictive capabilities based on data.

[0474] "Updating" is the process of improving the performance of a machine learning model using the latest data.

[0475] "Production data" refers to information regarding the operating rate, product quality, and energy consumption in the manufacturing process.

[0476] "Real-time collection" refers to the process of acquiring information almost simultaneously with its generation.

[0477] "Analysis" is the process of evaluating collected information and deriving meaningful interpretations from it.

[0478] "Efficiency" is a measure of how effectively a manufacturing line is using resources to achieve its goals.

[0479] An "improvement suggestion" refers to specific measures taken to solve problems and improve production efficiency.

[0480] The system implementing this invention features an information processing module running on a server and aims to improve production efficiency in the manufacturing industry. The server collects real-time production data from the manufacturing line through sensors and existing data management systems. This includes operating rates, product quality indicators, and energy consumption.

[0481] Once the data is aggregated on the server, erroneous data is removed and the data is standardized. Specifically, a data processing script using Python is essential, and the Pandas library is used to filter out erroneous data. The clean data is then analyzed by a generative artificial intelligence model. TensorFlow or PyTorch is used to train and update the model, which enables the prediction and improvement suggestions of production efficiency based on historical data.

[0482] Based on the analysis, the server evaluates the efficiency of each production line and generates improvement suggestions. These suggestions are communicated to the user through a web application. The user interface is built using the Django framework for this purpose. This allows users to access detailed reports in real time and make necessary decisions quickly.

[0483] For example, a manufacturing line may be found to have consistently high operating rates, yet its energy consumption is abnormally high compared to other lines. This information is immediately communicated to managers, prompting them to consider measures to optimize energy use.

[0484] Example of a prompt:

[0485] "Based on the current operating status of the manufacturing line, please submit suggestions for improving production efficiency."

[0486] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0487] Step 1:

[0488] The server collects data in real time from sensors installed on the manufacturing line and from existing data management systems. The input is raw data from the sensors, such as operating rates, quality indicators, and energy consumption. The output is the storage of the collected data in the server's database. Specifically, sensor data is transferred to the server using a RESTful API or MQTT protocol.

[0489] Step 2:

[0490] The server removes erroneous data from the collected raw data and standardizes it. The input is the raw data obtained in step 1. The Pandas library is used to filter outliers and missing values ​​and standardize the data format. The output is a clean and standardized dataset.

[0491] Step 3:

[0492] The server trains and updates a generative AI model based on clean, standardized data. By training the AI ​​model using TensorFlow, a predictive model capable of handling diverse manufacturing situations is built. The input is the clean dataset obtained in step 2, and the output is the trained AI model.

[0493] Step 4:

[0494] The server uses a trained AI model to analyze the efficiency of the manufacturing line in real time. The input is newly collected real-time data, and the output is an efficiency evaluation for each manufacturing line. Specifically, the server inputs the current data into the AI ​​model and calculates an efficiency score.

[0495] Step 5:

[0496] The server generates improvement suggestions based on the analysis results. The input is the efficiency evaluation results obtained in step 4. The output is specific suggestions for optimizing the operation of the manufacturing line. Improvement suggestions include methods for adjusting the operating rate and optimizing power consumption. The generated suggestions are presented to the user via prompt messages.

[0497] Step 6:

[0498] The terminal displays improvement suggestions notified from the server to the user via a web application. A user interface is built using Django to visually present the suggestions. Input is suggestion data from the server, and output is a detailed report viewable by the user.

[0499] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0500] This invention constructs a business continuity decision system that incorporates an emotion engine into an information processing device. This system, centered around a server, handles everything from data collection and emotion recognition to the generation of a final report.

[0501] First, the server collects various business-related data through an application programming interface or database connection. This data includes sales, expenses, market trends, and customer reviews, and is standardized as needed. The server then uses this data to train a generative artificial intelligence model to automatically determine whether the business is viable to continue.

[0502] Next, a server equipped with an emotion engine acquires user emotional feedback and uses natural language processing technology to recognize and evaluate those emotions. This enables a comprehensive approach to business decision-making that is data-driven yet takes human emotions into consideration.

[0503] The server integrates analytical results and sentiment insights to generate a comprehensive report. This report includes the current state of the business, future proposals, and specific recommendations based on user sentiment. The report is notified to the user via their terminal, allowing them to review their business strategy based on it.

[0504] For example, if a project is stalled due to a lack of resources, the server evaluates the project's viability based on relevant data. In this process, the emotion engine measures the project manager's stress level and other factors through emotional reviews, and recommends the need for additional resources based on their emotional state. This enables efficient resource allocation and management that considers team morale.

[0505] In this way, the present invention provides a system that integrates data analysis and emotion recognition to support balanced management decisions.

[0506] The following describes the processing flow.

[0507] Step 1:

[0508] The server identifies data sources relevant to each business as part of its preparation for data collection. This involves configuring application programming interfaces and database connections, and establishing automated processes for collecting sales data, cost data, market trends, and customer reviews.

[0509] Step 2:

[0510] The server cleans the collected data, correcting or removing inaccurate data and missing values. It also standardizes data formats and units, preparing the data for use in subsequent analysis processes. Algorithms are used throughout this process to ensure data consistency and accuracy.

[0511] Step 3:

[0512] The server trains a generative artificial intelligence model based on cleaned and standardized data. This model uses historical business performance data and market trend data to assess the profitability and market competitiveness of the business and determine whether the business is viable to continue.

[0513] Step 4:

[0514] The server collects feedback and comments from users. Next, it uses an emotion engine to analyze this feedback and recognize the user's emotional state. Natural language processing techniques are used to classify positive, negative, and neutral emotions and evaluate their intensity.

[0515] Step 5:

[0516] The server integrates the business continuity decision with user sentiment ratings obtained from the sentiment engine. Based on this, it generates a comprehensive report on the current state and future prospects of the business. The report includes specific recommendations based on sentiment.

[0517] Step 6:

[0518] The device notifies the user of the generated report. The user reviews this report through the device and uses it as information necessary for business strategy and decision-making. This enables data-driven, emotion-insensitive, and balanced decision-making.

[0519] (Example 2)

[0520] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0521] Current business continuity decision-making systems using information processing equipment must not only collect and analyze vast amounts of data, but also consider emotional insights. However, conventional systems struggle to effectively implement such a comprehensive approach that includes emotional insights, resulting in the challenge of being unable to make balanced management decisions.

[0522] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0523] In this invention, the server includes means for collecting information in various ways, means for training and updating a generative intelligence model based on standardized information, and means for recognizing and evaluating emotional feedback from users. This enables balanced management decisions that are data-driven and take emotional insights into account.

[0524] An "information processing device" is a hardware and software system for collecting, analyzing, and processing digital data.

[0525] A "generative intelligence model" is a form of artificial intelligence that uses machine learning algorithms to analyze large amounts of data and make predictions and decisions.

[0526] "Emotional feedback" refers to comments and data that reflect the user's emotional state, and is information analyzed using natural language processing technology.

[0527] "Natural language processing technology" refers to the technology that enables computer systems to understand, interpret, and manipulate human language.

[0528] A "report" is a document that summarizes analyzed information and recommendations, and is used for reviewing business strategies, etc.

[0529] "Notification" refers to a means of informing users of information or reports, and is typically done via email or digital devices.

[0530] This invention constructs a system for making business continuity decisions using an information processing device. This system operates primarily around a server and enables comprehensive business decisions that integrate diverse data and take emotional feedback into consideration.

[0531] The server first collects diverse information. This collection is done through application programming interfaces (APIs) and data storage connections, and includes sales data, customer reviews, and expense information. This data is used to train generative intelligence models using machine learning techniques with frameworks such as TensorFlow, in order to predict business risks and sustainability.

[0532] Next, the server uses an emotion engine to obtain emotional feedback from users. Data is collected through forms embedded in the employee portal, and natural language processing technology is used to recognize and evaluate those emotions. This enables balanced decision-making that is data-driven yet takes emotional aspects into account.

[0533] The generated judgments and emotional insights are compiled into a comprehensive report. The server generates this report and notifies the user via their terminal. The notification is sent via email or the company portal, allowing the user to review their business strategy based on it.

[0534] For example, if a project is stalled due to a lack of resources, the server will evaluate the project's prospects based on relevant information. In this process, the emotion engine can analyze the project manager's stress level and recommend whether additional resources are needed.

[0535] An example of a prompt message could be, "Based on the latest information on Project X and the manager's sentiment review, assess the need for additional resources and generate recommendations." In this way, the present invention provides a system that supports sophisticated business decisions by combining technical and emotional elements.

[0536] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0537] Step 1:

[0538] The server collects business-related data through application programming interfaces (APIs) and data storage connections. This data includes sales, expenses, market trends, etc. Each data source is retrieved as input via API calls, and the output is obtained by converting its contents into a unified format (e.g., JSON).

[0539] Step 2:

[0540] The server uses the collected data to clean and standardize inaccurate data. The input is the unified formatted data collected in step 1, and the server uses a data cleaning algorithm to remove outliers and impute missing values. As a result, it outputs a standardized dataset suitable for analysis.

[0541] Step 3:

[0542] The server trains a generative AI model using standardized data. The input is the dataset created in step 2, and the model is trained using a machine learning framework (e.g., TensorFlow). After training is complete, it outputs a skilled model for determining business continuity.

[0543] Step 4:

[0544] The server acquires user emotional feedback. The input is emotional data provided by the user through an employee portal form, which is then analyzed using natural language processing technology. The analysis results output a quantified emotional evaluation.

[0545] Step 5:

[0546] The server integrates the results of the trained generative AI model and the analysis of emotional feedback to automatically determine whether the business can be continued. The inputs are the model output in step 3 and the emotional evaluation in step 4, which are used to assess the business's riskiness. The final decision result is then output.

[0547] Step 6:

[0548] The server generates a comprehensive report based on the judgment results and sentiment insights. The input is the judgment results and recommendations from step 5, and the document generation algorithm outputs a report in PDF format.

[0549] Step 7:

[0550] The terminal notifies the user of the report. The input is the report generated in step 6, which is delivered to the user via email or the employee portal. The final output is in the form of a link accessible to the user.

[0551] Step 8:

[0552] The user reviews their business strategy based on the notified report. The input is the report delivered in step 7, and by reviewing it in detail, they can reallocate resources, consider new measures, and obtain output that allows them to formulate a more appropriate business strategy.

[0553] (Application Example 2)

[0554] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0555] In modern e-commerce, providing truly personalized product recommendations that meet user needs is challenging. Furthermore, the inability to consider human emotions in business continuity decisions makes it difficult to make objective, data-driven judgments. This makes it difficult for companies to make efficient decisions and limits their ability to improve user satisfaction.

[0556] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0557] In this invention, the server includes means for an information processing device to collect diverse information related to multiple businesses; means for cleaning up inaccurate content and standardizing the collected information; means for training and updating a generative artificial intelligence model based on the cleaned and standardized information; means for automatically determining whether or not to continue a business using the trained model; means for generating and reporting a report containing the determination result and recommendations; means for analyzing the user's emotional response and recognizing and evaluating emotions using natural language processing technology; and means for integrating information based on the emotional recognition result and making customized product suggestions. This enables more accurate and personalized decision-making and product suggestions by utilizing both data and emotional information.

[0558] An "information processing device" is a general term for electronic devices that collect, analyze, and process digital data and output the results.

[0559] "Diverse information" refers to a collection of digital data with different characteristics, such as sales, expenses, market trends, and customer reviews.

[0560] "Means of cleaning up inaccurate content and standardizing it" refers to methods or techniques for carrying out the process of correcting errors in data and unifying data formats.

[0561] A "generative artificial intelligence model" refers to an artificial intelligence algorithm or framework that makes predictions and decisions based on pre-provided data.

[0562] "Means for automatically determining whether a business can continue" refers to a method that uses collected data to determine, through a mechanical process, whether or not a business can continue.

[0563] "Means for generating and reporting reports" refers to methods or techniques for creating a report summarizing the analysis results and presenting it to relevant parties.

[0564] "A means of analyzing user emotional responses and recognizing and evaluating emotions using natural language processing technology" refers to a method of analyzing user feedback and using natural language processing to understand their emotional state.

[0565] "Methods for providing customized product recommendations" refer to methods of recommending the most suitable products and services based on the individual user's needs and feelings.

[0566] The system that realizes this application consists of an information processing unit. The server has a mechanism to automatically collect various business-related information through application program interfaces and information connections. The collected information is cleaned and standardized within the server to remove any inaccuracies. This prepares a unified data format.

[0567] Next, the server uses the cleaned and standardized information to train and update data using a generative artificial intelligence model. This AI model is created using frameworks such as TensorFlow and operates to automatically determine whether a business can continue. This process enables current business analysis and future predictions.

[0568] Furthermore, the server analyzes users' emotional responses, recognizing and evaluating emotions using natural language processing technologies such as NLTK and spaCy. Specifically, it analyzes reviews and feedback collected from users to identify positive or negative emotions and incorporates them into the business decision-making process.

[0569] The server integrates emotion recognition results and data analysis results to provide users with customized product recommendations. These recommendations are generated based on the individual user's needs and emotions. For example, if a user provides positive feedback, similar products or upsell items will be suggested.

[0570] As an example of a prompt, a message like, "Suggest similar products to the item the user is currently viewing, based on their purchase history and sentiment feedback," would enable the server to make sophisticated decisions accordingly.

[0571] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0572] Step 1:

[0573] The server automatically collects diverse business-related information through application program interfaces and information connections. Inputs include raw data such as sales, expenses, market trends, and customer reviews, while outputs are in a standardized data format. During the data collection process, information is extracted from various data sources and stored in a database on the server.

[0574] Step 2:

[0575] The server cleanses and standardizes inaccurate content. The input is the diverse information collected in Step 1, and the output is standardized data with errors corrected. The data cleansing and standardization process involves imputing missing values, correcting outliers, and transforming data formats to generate a consistent dataset.

[0576] Step 3:

[0577] The server trains and updates a generative artificial intelligence model based on standardized information. The input is the standardized data obtained in step 2, and the output is the trained AI model. During the AI ​​model training process, it learns data patterns and creates a predictive model to determine whether a business can continue.

[0578] Step 4:

[0579] The server automatically determines whether a business can be continued using an AI model. The input is real-time updated information, and the output is the result of the decision on whether or not to continue. In the model's prediction process, it evaluates current market conditions and past performance to make the optimal decision.

[0580] Step 5:

[0581] The server analyzes user emotional responses and recognizes and evaluates emotions using natural language processing techniques. Input is user reviews and feedback, and output is a positive or negative emotional evaluation. The emotional analysis process involves analyzing text and calculating an emotional score.

[0582] Step 6:

[0583] The server provides customized product recommendations based on emotion recognition results and data analysis results. The input is emotion evaluation and the AI ​​model's judgment, while the output is product recommendations optimized for each individual user. During the recommendation process, products are selected and a recommendation list is generated, taking into account the user's emotional state and past behavioral history.

[0584] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0585] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0586] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0587] [Fourth Embodiment]

[0588] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0589] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0590] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0591] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0592] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0593] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0594] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0595] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0596] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0597] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0598] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0599] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0600] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0601] This invention provides a system that automates business continuity decisions by executing a program running on an information processing device. This system has a server-centric structure and supports management decisions by performing real-time data collection and analysis.

[0602] First, the server automatically collects data related to multiple businesses from various sources. This includes sales data, expense data, market trend data, and customer feedback data. The server retrieves this data through application programming interfaces and database connections and standardizes it to ensure data consistency.

[0603] Next, the server uses a generative artificial intelligence model to analyze the collected data. During this analysis process, the AI ​​model is trained and, considering past business performance and market trends, predicts the profitability and market position of each business. This allows for an objective evaluation of three options: continue the business, not continue it, or wait and see.

[0604] The server automatically makes decisions based on the analysis results and compiles the results, along with the reasoning, into a detailed report. This report is notified to the user via their terminal and can be used to review business strategies and efficiently allocate resources.

[0605] For example, a user might want to identify underperforming products from their multiple product lines. The server collects all relevant product data and analyzes it using a generative AI model. The server evaluates the profitability and market share of each product line and provides a report summarizing the reasons for the underperformance. The user can then use this report to implement improvements to the underperforming products or decide to discontinue them.

[0606] In this way, a system is provided that eliminates information bias and emotional judgments, enabling rational and data-driven management decisions.

[0607] The following describes the processing flow.

[0608] Step 1:

[0609] The server identifies sources for collecting sales data, expense data, market trend data, and customer feedback data related to each business. To this end, it configures application programming interfaces and database connections, enabling the automation of data retrieval.

[0610] Step 2:

[0611] The server cleans the collected data, correcting or removing inaccurate data. Furthermore, it standardizes different data formats and units, converting them into a consistent format suitable for analysis. This process also includes imputing missing data values.

[0612] Step 3:

[0613] The server trains a generative artificial intelligence model based on standardized data. This model learns from historical business performance data and market trends, and is optimized to evaluate the profitability and market competitiveness of the business.

[0614] Step 4:

[0615] The server uses trained AI models to predict the current and future performance of each business. The models analyze profitability, risk assessment, and business continuity in response to market changes, providing decisions on whether to continue, not continue, or wait and see.

[0616] Step 5:

[0617] The server generates a detailed report based on the analysis results of the AI ​​model. This report includes a summary of the analysis, a decision on whether each business can be continued, and the reasons for those decisions.

[0618] Step 6:

[0619] The terminal notifies the user of the generated report. The user can use the terminal to review the report and use it as material for specific business decisions. This reporting function allows the user to review the allocation of management resources and strategies based on objective data.

[0620] (Example 1)

[0621] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0622] In today's business environment, a vast amount of information is available, demanding quick and accurate management decisions. However, it is difficult to select highly relevant information from a massive dataset and make rational decisions based on it. Furthermore, information is easily influenced by biases and emotional factors, making it challenging to make objective, data-driven judgments.

[0623] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0624] In this invention, the server includes means for collecting diverse information related to multiple business operations, means for performing predictive analysis using generative artificial intelligence based on standardized information, and means for generating and providing reports to users that include evaluation results and the reasons for those results. This eliminates information bias and enables objective, data-driven management decisions.

[0625] An "information processing device" is a device that collects, processes, and analyzes data and generates output tailored to a specific purpose.

[0626] "Generative artificial intelligence" refers to artificial intelligence that has the ability to generate new information based on past data, and is a technology used for prediction and analysis.

[0627] "Predictive analytics" is an analytical method used to predict future events and outcomes based on collected data.

[0628] Standardization is the process of ensuring data consistency and converting it into a comparable format.

[0629] A "report" is a document that organizes the results of an analysis and the reasoning behind the decisions, and provides them to the user.

[0630] A "prompt message" is an instruction that a user enters into the system, intended to prompt specific analysis or processing.

[0631] A "terminal" is a device used by a user to obtain information or input data.

[0632] This invention is a system that automates the decision-making process for continuing operations using an information processing device. This system has a server-centric structure and supports management decisions through real-time information collection and analysis. The system utilizes generative artificial intelligence to efficiently analyze data.

[0633] First, the server automatically collects business-related information from various sources via APIs and database connections. This system retrieves data from a variety of sources, including customer relationship management tools and sales management software. This allows for the collection of information such as sales, expenses, market trends, and customer feedback.

[0634] The server then standardizes the collected data and converts it into a consistent format. This unifies data from different information sources, making it comparable. The server then uses the standardized data to perform predictive analytics using generative artificial intelligence models. This process utilizes libraries such as Python's TensorFlow, and objective evaluation becomes possible by performing data analysis based on past performance and market trends.

[0635] For example, a user might want to know which of their multiple business lines is underperforming. In this case, the server collects data related to each business line and analyzes it using a generative AI model. As a result, a detailed report is generated indicating which businesses are experiencing profitability problems. Based on this report, the user can then formulate further improvement measures or consider shutting down the business.

[0636] An example of a prompt message that can be entered into the system is: "Based on current sales data and market trends, identify the least profitable business line and analyze the cause."

[0637] In this way, the system of the present invention eliminates information bias and emotional judgments, and supports rational and data-driven management decisions.

[0638] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0639] Step 1:

[0640] The server collects business-related data from multiple sources. Specifically, it obtains sales, expenses, market trends, and customer feedback data from various services and platforms via APIs and database connections. The input data consists of this information and is temporarily stored in storage after collection. The output is the raw dataset used in subsequent standardization processes.

[0641] Step 2:

[0642] The server standardizes the collected data. This is the process of converting data in different formats and units into a consistent format. For example, it converts all numerical data to a common currency unit and unifies date formats. It also applies appropriate imputation if outliers or missing values ​​exist. The input is the original dataset from step 1, and the output is the standardized dataset.

[0643] Step 3:

[0644] The server performs predictive analysis using a generative artificial intelligence model based on standardized data. Specifically, the server inputs data into the generative AI model and predicts future profitability and market share by comparing it with past performance data and market trends. The Python TensorFlow library is used in this process. The input is the standardized dataset from step 2, and the output is the analysis results showing the continuity and potential risks of each business.

[0645] Step 4:

[0646] Based on the predictive analytics results, the server generates a detailed report containing three options: continue operations, suspend operations, or wait and see. This report also includes reasoning and recommendations. The input is the analysis results from step 3, and the output is a report designed to facilitate user decision-making.

[0647] Step 5:

[0648] The terminal notifies the user of reports received from the server. This process is designed to display new information in real time on the dashboard. The input is the report generated in step 4, and the output is a visual notification on the user interface.

[0649] Step 6:

[0650] Users review reports on the dashboard and revise their strategies based on the presented data. In this step, users can enter new prompts to instruct further detailed analysis and hypothesis testing. The input is the report presented on the device, and the output is the user's strategic decision.

[0651] (Application Example 1)

[0652] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0653] In manufacturing, multiple production lines are operated simultaneously, making it difficult to maintain optimal production efficiency for each. In particular, increased product defect rates and energy consumption can lead to decreased profits, necessitating automated systems to quickly identify and address these issues. However, traditional methods have limitations in providing consistent real-time monitoring and efficient improvement suggestions. Therefore, new technological means are needed to improve factory production efficiency.

[0654] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0655] In this invention, the server includes means for an information processing module to collect diverse information related to multiple tasks, means for deleting and unifying erroneous data using the collected information, means for training and updating a generative artificial intelligence model based on the deleted and unified information, means for collecting and analyzing production data from a manufacturing line in real time, and means for evaluating the efficiency of the manufacturing line and proposing improvement suggestions. This enables efficient monitoring of the operation status of the production line, early detection of problems, and rapid proposal of improvement measures.

[0656] An "information processing module" is a device or program that has the function of collecting, organizing, and analyzing data.

[0657] "Information" refers to data or collections of data used for analysis and decision-making.

[0658] "Inaccurate data" refers to data that lacks accuracy due to inconsistencies in the collection process or records.

[0659] "Deletion" is the process of removing erroneous data from the system and purifying the dataset.

[0660] "Standardization" is the process of converting data from different formats and units into a consistent format.

[0661] A "generative artificial intelligence model" is a model of algorithms that learns from data and is created to support prediction and decision-making.

[0662] "Training" is the process by which a machine learning algorithm acquires appropriate predictive capabilities based on data.

[0663] "Updating" is the process of improving the performance of a machine learning model using the latest data.

[0664] "Production data" refers to information regarding the operating rate, product quality, and energy consumption in the manufacturing process.

[0665] "Real-time collection" refers to the process of acquiring information almost simultaneously with its generation.

[0666] "Analysis" is the process of evaluating collected information and deriving meaningful interpretations from it.

[0667] "Efficiency" is a measure of how effectively a manufacturing line is using resources to achieve its goals.

[0668] An "improvement suggestion" refers to specific measures taken to solve problems and improve production efficiency.

[0669] The system implementing this invention features an information processing module running on a server and aims to improve production efficiency in the manufacturing industry. The server collects real-time production data from the manufacturing line through sensors and existing data management systems. This includes operating rates, product quality indicators, and energy consumption.

[0670] Once the data is aggregated on the server, erroneous data is removed and the data is standardized. Specifically, a data processing script using Python is essential, and the Pandas library is used to filter out erroneous data. The clean data is then analyzed by a generative artificial intelligence model. TensorFlow or PyTorch is used to train and update the model, which enables the prediction and improvement suggestions of production efficiency based on historical data.

[0671] Based on the analysis, the server evaluates the efficiency of each production line and generates improvement suggestions. These suggestions are communicated to the user through a web application. The user interface is built using the Django framework for this purpose. This allows users to access detailed reports in real time and make necessary decisions quickly.

[0672] For example, a manufacturing line may be found to have consistently high operating rates, yet its energy consumption is abnormally high compared to other lines. This information is immediately communicated to managers, prompting them to consider measures to optimize energy use.

[0673] Example of a prompt:

[0674] "Based on the current operating status of the manufacturing line, please submit suggestions for improving production efficiency."

[0675] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0676] Step 1:

[0677] The server collects data in real time from sensors installed on the manufacturing line and from existing data management systems. The input is raw data from the sensors, such as operating rates, quality indicators, and energy consumption. The output is the storage of the collected data in the server's database. Specifically, sensor data is transferred to the server using a RESTful API or MQTT protocol.

[0678] Step 2:

[0679] The server removes erroneous data from the collected raw data and standardizes it. The input is the raw data obtained in step 1. The Pandas library is used to filter outliers and missing values ​​and standardize the data format. The output is a clean and standardized dataset.

[0680] Step 3:

[0681] The server trains and updates a generative AI model based on clean, standardized data. By training the AI ​​model using TensorFlow, a predictive model capable of handling diverse manufacturing situations is built. The input is the clean dataset obtained in step 2, and the output is the trained AI model.

[0682] Step 4:

[0683] The server uses a trained AI model to analyze the efficiency of the manufacturing line in real time. The input is newly collected real-time data, and the output is an efficiency evaluation for each manufacturing line. Specifically, the server inputs the current data into the AI ​​model and calculates an efficiency score.

[0684] Step 5:

[0685] The server generates improvement suggestions based on the analysis results. The input is the efficiency evaluation results obtained in step 4. The output is specific suggestions for optimizing the operation of the manufacturing line. Improvement suggestions include methods for adjusting the operating rate and optimizing power consumption. The generated suggestions are presented to the user via prompt messages.

[0686] Step 6:

[0687] The terminal displays improvement suggestions notified from the server to the user via a web application. A user interface is built using Django to visually present the suggestions. Input is suggestion data from the server, and output is a detailed report viewable by the user.

[0688] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0689] This invention constructs a business continuity decision system that incorporates an emotion engine into an information processing device. This system, centered around a server, handles everything from data collection and emotion recognition to the generation of a final report.

[0690] First, the server collects various business-related data through an application programming interface or database connection. This data includes sales, expenses, market trends, and customer reviews, and is standardized as needed. The server then uses this data to train a generative artificial intelligence model to automatically determine whether the business is viable to continue.

[0691] Next, a server equipped with an emotion engine acquires user emotional feedback and uses natural language processing technology to recognize and evaluate those emotions. This enables a comprehensive approach to business decision-making that is data-driven yet takes human emotions into consideration.

[0692] The server integrates analytical results and sentiment insights to generate a comprehensive report. This report includes the current state of the business, future proposals, and specific recommendations based on user sentiment. The report is notified to the user via their terminal, allowing them to review their business strategy based on it.

[0693] For example, if a project is stalled due to a lack of resources, the server evaluates the project's viability based on relevant data. In this process, the emotion engine measures the project manager's stress level and other factors through emotional reviews, and recommends the need for additional resources based on their emotional state. This enables efficient resource allocation and management that considers team morale.

[0694] In this way, the present invention provides a system that integrates data analysis and emotion recognition to support balanced management decisions.

[0695] The following describes the processing flow.

[0696] Step 1:

[0697] The server identifies data sources relevant to each business as part of its preparation for data collection. This involves configuring application programming interfaces and database connections, and establishing automated processes for collecting sales data, cost data, market trends, and customer reviews.

[0698] Step 2:

[0699] The server cleans the collected data, correcting or removing inaccurate data and missing values. It also standardizes data formats and units, preparing the data for use in subsequent analysis processes. Algorithms are used throughout this process to ensure data consistency and accuracy.

[0700] Step 3:

[0701] The server trains a generative artificial intelligence model based on cleaned and standardized data. This model uses historical business performance data and market trend data to assess the profitability and market competitiveness of the business and determine whether the business is viable to continue.

[0702] Step 4:

[0703] The server collects feedback and comments from users. Next, it uses an emotion engine to analyze this feedback and recognize the user's emotional state. Natural language processing techniques are used to classify positive, negative, and neutral emotions and evaluate their intensity.

[0704] Step 5:

[0705] The server integrates the business continuity decision with user sentiment ratings obtained from the sentiment engine. Based on this, it generates a comprehensive report on the current state and future prospects of the business. The report includes specific recommendations based on sentiment.

[0706] Step 6:

[0707] The device notifies the user of the generated report. The user reviews this report through the device and uses it as information necessary for business strategy and decision-making. This enables data-driven, emotion-insensitive, and balanced decision-making.

[0708] (Example 2)

[0709] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0710] Current business continuity decision-making systems using information processing equipment must not only collect and analyze vast amounts of data, but also consider emotional insights. However, conventional systems struggle to effectively implement such a comprehensive approach that includes emotional insights, resulting in the challenge of being unable to make balanced management decisions.

[0711] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0712] In this invention, the server includes means for collecting information in various ways, means for training and updating a generative intelligence model based on standardized information, and means for recognizing and evaluating emotional feedback from users. This enables balanced management decisions that are data-driven and take emotional insights into account.

[0713] An "information processing device" is a hardware and software system for collecting, analyzing, and processing digital data.

[0714] A "generative intelligence model" is a form of artificial intelligence that uses machine learning algorithms to analyze large amounts of data and make predictions and decisions.

[0715] "Emotional feedback" refers to comments and data that reflect the user's emotional state, and is information analyzed using natural language processing technology.

[0716] "Natural language processing technology" refers to the technology that enables computer systems to understand, interpret, and manipulate human language.

[0717] A "report" is a document that summarizes analyzed information and recommendations, and is used for reviewing business strategies, etc.

[0718] "Notification" refers to a means of informing users of information or reports, and is typically done via email or digital devices.

[0719] This invention constructs a system for making business continuity decisions using an information processing device. This system operates primarily around a server and enables comprehensive business decisions that integrate diverse data and take emotional feedback into consideration.

[0720] The server first collects diverse information. This collection is done through application programming interfaces (APIs) and data storage connections, and includes sales data, customer reviews, and expense information. This data is used to train generative intelligence models using machine learning techniques with frameworks such as TensorFlow, in order to predict business risks and sustainability.

[0721] Next, the server uses an emotion engine to obtain emotional feedback from users. Data is collected through forms embedded in the employee portal, and natural language processing technology is used to recognize and evaluate those emotions. This enables balanced decision-making that is data-driven yet takes emotional aspects into account.

[0722] The generated judgments and emotional insights are compiled into a comprehensive report. The server generates this report and notifies the user via their terminal. The notification is sent via email or the company portal, allowing the user to review their business strategy based on it.

[0723] For example, if a project is stalled due to a lack of resources, the server will evaluate the project's prospects based on relevant information. In this process, the emotion engine can analyze the project manager's stress level and recommend whether additional resources are needed.

[0724] An example of a prompt message could be, "Based on the latest information on Project X and the manager's sentiment review, assess the need for additional resources and generate recommendations." In this way, the present invention provides a system that supports sophisticated business decisions by combining technical and emotional elements.

[0725] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0726] Step 1:

[0727] The server collects business-related data through application programming interfaces (APIs) and data storage connections. This data includes sales, expenses, market trends, etc. Each data source is retrieved as input via API calls, and the output is obtained by converting its contents into a unified format (e.g., JSON).

[0728] Step 2:

[0729] The server uses the collected data to clean and standardize inaccurate data. The input is the unified formatted data collected in step 1, and the server uses a data cleaning algorithm to remove outliers and impute missing values. As a result, it outputs a standardized dataset suitable for analysis.

[0730] Step 3:

[0731] The server trains a generative AI model using standardized data. The input is the dataset created in step 2, and the model is trained using a machine learning framework (e.g., TensorFlow). After training is complete, it outputs a skilled model for determining business continuity.

[0732] Step 4:

[0733] The server acquires user emotional feedback. The input is emotional data provided by the user through an employee portal form, which is then analyzed using natural language processing technology. The analysis results output a quantified emotional evaluation.

[0734] Step 5:

[0735] The server integrates the results of the trained generative AI model and the analysis of emotional feedback to automatically determine whether the business can be continued. The inputs are the model output in step 3 and the emotional evaluation in step 4, which are used to assess the business's riskiness. The final decision result is then output.

[0736] Step 6:

[0737] The server generates a comprehensive report based on the judgment results and sentiment insights. The input is the judgment results and recommendations from step 5, and the document generation algorithm outputs a report in PDF format.

[0738] Step 7:

[0739] The terminal notifies the user of the report. The input is the report generated in step 6, which is delivered to the user via email or the employee portal. The final output is in the form of a link accessible to the user.

[0740] Step 8:

[0741] The user reviews their business strategy based on the notified report. The input is the report delivered in step 7, and by reviewing it in detail, they can reallocate resources, consider new measures, and obtain output that allows them to formulate a more appropriate business strategy.

[0742] (Application Example 2)

[0743] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0744] In modern e-commerce, providing truly personalized product recommendations that meet user needs is challenging. Furthermore, the inability to consider human emotions in business continuity decisions makes it difficult to make objective, data-driven judgments. This makes it difficult for companies to make efficient decisions and limits their ability to improve user satisfaction.

[0745] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0746] In this invention, the server includes means for an information processing device to collect diverse information related to multiple businesses; means for cleaning up inaccurate content and standardizing the collected information; means for training and updating a generative artificial intelligence model based on the cleaned and standardized information; means for automatically determining whether or not to continue a business using the trained model; means for generating and reporting a report containing the determination result and recommendations; means for analyzing the user's emotional response and recognizing and evaluating emotions using natural language processing technology; and means for integrating information based on the emotional recognition result and making customized product suggestions. This enables more accurate and personalized decision-making and product suggestions by utilizing both data and emotional information.

[0747] An "information processing device" is a general term for electronic devices that collect, analyze, and process digital data and output the results.

[0748] "Diverse information" refers to a collection of digital data with different characteristics, such as sales, expenses, market trends, and customer reviews.

[0749] "Means of cleaning up inaccurate content and standardizing it" refers to methods or techniques for carrying out the process of correcting errors in data and unifying data formats.

[0750] A "generative artificial intelligence model" refers to an artificial intelligence algorithm or framework that makes predictions and decisions based on pre-provided data.

[0751] "Means for automatically determining whether a business can continue" refers to a method that uses collected data to determine, through a mechanical process, whether or not a business can continue.

[0752] "Means for generating and reporting reports" refers to methods or techniques for creating a report summarizing the analysis results and presenting it to relevant parties.

[0753] "A means of analyzing user emotional responses and recognizing and evaluating emotions using natural language processing technology" refers to a method of analyzing user feedback and using natural language processing to understand their emotional state.

[0754] "Methods for providing customized product recommendations" refer to methods of recommending the most suitable products and services based on the individual user's needs and feelings.

[0755] The system that realizes this application consists of an information processing unit. The server has a mechanism to automatically collect various business-related information through application program interfaces and information connections. The collected information is cleaned and standardized within the server to remove any inaccuracies. This prepares a unified data format.

[0756] Next, the server uses the cleaned and standardized information to train and update data using a generative artificial intelligence model. This AI model is created using frameworks such as TensorFlow and operates to automatically determine whether a business can continue. This process enables current business analysis and future predictions.

[0757] Furthermore, the server analyzes users' emotional responses, recognizing and evaluating emotions using natural language processing technologies such as NLTK and spaCy. Specifically, it analyzes reviews and feedback collected from users to identify positive or negative emotions and incorporates them into the business decision-making process.

[0758] The server integrates emotion recognition results and data analysis results to provide users with customized product recommendations. These recommendations are generated based on the individual user's needs and emotions. For example, if a user provides positive feedback, similar products or upsell items will be suggested.

[0759] As an example of a prompt, a message like, "Suggest similar products to the item the user is currently viewing, based on their purchase history and sentiment feedback," would enable the server to make sophisticated decisions accordingly.

[0760] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0761] Step 1:

[0762] The server automatically collects diverse business-related information through application program interfaces and information connections. Inputs include raw data such as sales, expenses, market trends, and customer reviews, while outputs are in a standardized data format. During the data collection process, information is extracted from various data sources and stored in a database on the server.

[0763] Step 2:

[0764] The server cleanses and standardizes inaccurate content. The input is the diverse information collected in Step 1, and the output is standardized data with errors corrected. The data cleansing and standardization process involves imputing missing values, correcting outliers, and transforming data formats to generate a consistent dataset.

[0765] Step 3:

[0766] The server trains and updates a generative artificial intelligence model based on standardized information. The input is the standardized data obtained in step 2, and the output is the trained AI model. During the AI ​​model training process, it learns data patterns and creates a predictive model to determine whether a business can continue.

[0767] Step 4:

[0768] The server automatically determines whether a business can be continued using an AI model. The input is real-time updated information, and the output is the result of the decision on whether or not to continue. In the model's prediction process, it evaluates current market conditions and past performance to make the optimal decision.

[0769] Step 5:

[0770] The server analyzes user emotional responses and recognizes and evaluates emotions using natural language processing techniques. Input is user reviews and feedback, and output is a positive or negative emotional evaluation. The emotional analysis process involves analyzing text and calculating an emotional score.

[0771] Step 6:

[0772] The server provides customized product recommendations based on emotion recognition results and data analysis results. The input is emotion evaluation and the AI ​​model's judgment, while the output is product recommendations optimized for each individual user. During the recommendation process, products are selected and a recommendation list is generated, taking into account the user's emotional state and past behavioral history.

[0773] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0774] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0775] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0776] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0777] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0778] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0779] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0780] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0781] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0782] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0783] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0784] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0785] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0786] 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.

[0787] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0788] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0789] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0790] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0791] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0792] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0793] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0794] The following is further disclosed regarding the embodiments described above.

[0795] (Claim 1)

[0796] The information processing device is a means of collecting diverse data related to multiple businesses,

[0797] A means of cleaning up and standardizing inaccurate data using collected data,

[0798] A means for training and updating generative artificial intelligence models based on cleaned and standardized data,

[0799] A means of automatically determining whether a business can continue using a trained model,

[0800] A means for generating and reporting a report that includes the judgment results and recommendations,

[0801] A system that includes this.

[0802] (Claim 2)

[0803] The system according to claim 1, characterized in that the collection means automatically acquires data through an application programming interface or a database connection.

[0804] (Claim 3)

[0805] The system according to claim 1, characterized in that the decision-making means is configured to evaluate and present three options: continue, not continue, and wait and see.

[0806] "Example 1"

[0807] (Claim 1)

[0808] The information processing device provides means for collecting diverse information related to multiple tasks,

[0809] A means of using collected information to purify inaccurate information and standardize it,

[0810] A method for performing predictive analysis using generative artificial intelligence based on standardized information,

[0811] A means for automatically evaluating three options—continue operations, suspend operations, and wait and see—based on predictive analysis,

[0812] A means of generating and providing to users a report that includes the evaluation results and the reasons for them,

[0813] A terminal for displaying report notifications in real time,

[0814] A means for the user to enter a prompt message to review their strategy,

[0815] A system that includes this.

[0816] (Claim 2)

[0817] The system according to claim 1, characterized in that the collection means automatically acquires information through a program interface or an information base connection.

[0818] (Claim 3)

[0819] The system according to claim 1, characterized in that the predictive analysis means compares data based on past performance and market trends and proposes a decision as a result.

[0820] "Application Example 1"

[0821] (Claim 1)

[0822] The information processing module provides a means for collecting diverse information related to multiple tasks,

[0823] A means of deleting and standardizing erroneous data using the collected information,

[0824] A means for training and updating generative artificial intelligence models based on deleted and unified information,

[0825] A means of automatically performing continuous evaluation of operations using a trained model,

[0826] A means of creating and notifying a report that includes the evaluation results and recommendations,

[0827] A means of collecting and analyzing production data from manufacturing lines in real time,

[0828] A means of evaluating the efficiency of a manufacturing line and proposing improvement suggestions,

[0829] A system that includes this.

[0830] (Claim 2)

[0831] The system according to claim 1, characterized in that the data collection means automatically acquires information through a communication interface or connection to an information storage device.

[0832] (Claim 3)

[0833] The system according to claim 1, characterized in that the decision-making means is configured to evaluate and present three options: continue, stop, and wait and see.

[0834] "Example 2 of combining an emotion engine"

[0835] (Claim 1)

[0836] The information processing device is a means of collecting diverse information related to multiple businesses,

[0837] A means of using collected information to clean up inaccurate information and standardize it,

[0838] A means for training and updating generative intelligence models based on cleaned and standardized information,

[0839] A means of automatically determining whether a business can continue using a trained model,

[0840] A means of obtaining emotional feedback from users and recognizing and evaluating those emotions using natural language processing technology,

[0841] A means for generating and reporting a report that includes judgment results, emotional insights, and recommendations,

[0842] A means of notifying via a terminal that the generated report will be delivered,

[0843] A system that includes this.

[0844] (Claim 2)

[0845] The system according to claim 1, characterized in that the collection means automatically acquires information through an application programming interface or a data storage connection.

[0846] (Claim 3)

[0847] The system according to claim 1, characterized in that the decision-making means is configured to evaluate and present three options: continue, not continue, and wait and see.

[0848] "Application example 2 when combining with an emotional engine"

[0849] (Claim 1)

[0850] The information processing device is a means of collecting diverse information related to multiple businesses,

[0851] A means of cleaning up inaccurate content and standardizing it using the collected information,

[0852] A means for training and updating generative artificial intelligence models based on cleaned and standardized information,

[0853] A means of automatically determining whether a business can continue using a trained model,

[0854] A means for generating and reporting a report that includes the judgment results and recommendations,

[0855] A means of analyzing users' emotional responses and recognizing and evaluating emotions using natural language processing technology,

[0856] A means of integrating information based on emotional recognition results to provide customized product suggestions,

[0857] A system that includes this.

[0858] (Claim 2)

[0859] The system according to claim 1, characterized in that the collection means automatically acquires information through an application program interface or information connection.

[0860] (Claim 3)

[0861] The system according to claim 1, characterized in that the decision-making means is configured to evaluate and present three options: continue, not continue, and wait and see. [Explanation of Symbols]

[0862] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. The information processing device is a means of collecting diverse data related to multiple businesses, A means of cleaning up and standardizing inaccurate data using collected data, A means for training and updating generative artificial intelligence models based on cleaned and standardized data, A means of automatically determining whether a business can continue using a trained model, A means for generating and reporting a report that includes the judgment results and recommendations, A system that includes this.

2. The system according to claim 1, characterized in that the collection means automatically acquires data through an application programming interface or a database connection.

3. The system according to claim 1, characterized in that the decision-making means is configured to evaluate and present three options: continue, not continue, and wait and see.

Images