system

Abstract

We provide the system. [Solution] A means of analyzing business process data using a generative model, A means for predicting areas for improvement in operations based on the aforementioned analysis results, A means for automating business processes based on the aforementioned predicted areas for improvement, A system that includes this.

Description

Technical Field

[0002] , , , , , , , ,

[0004] , , , , , , ,

[0005] , , , , , ,

[0003] , , , ,

[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

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

Means for Solving the Problems

[0006] A "generative model" is a machine learning model that learns patterns from data and can generate or predict new data.

[0007] A "business process" is a set of procedures or activities established within a company or organization to perform a specific task.

[0008] "Analysis" is the act of thoroughly investigating and analyzing data to reveal its characteristics and patterns.

[0009] "Prediction" refers to estimating future events or states based on past data and trends.

[0010] "Automation" refers to the automatic execution of tasks and processes using technologies such as artificial intelligence and machine learning, while minimizing human intervention.

[0011] "Normalization" is the process of unifying data from different formats and scales to ensure consistency.

[0012] "Integration" refers to combining multiple different data sources into a single, comprehensive format that can be used effectively. [Brief explanation of the drawing]

[0013] [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]It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0016] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, the labeled 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, and the like.

[0019] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

[0020] 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."

[0021] [First Embodiment]

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

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0028] 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.

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

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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".

[0034] This invention provides a technology for automating and optimizing various business processes within an enterprise using generative models. The following describes embodiments for carrying out the invention.

[0035] Data collection and preprocessing

[0036] The server collects data from multiple business systems within a company, such as human resources, finance, and logistics. This data is retrieved periodically using APIs and database queries. Next, the terminal preprocesses the collected data. By cleaning, normalizing, and integrating information from different data sources, a unified dataset is created. This preprocessing ensures the data consistency necessary for subsequent analysis.

[0037] Analysis and prediction using generative models

[0038] The server inputs pre-processed data into a generative model to analyze business processes. The generative model learns from historical data to identify bottlenecks and inefficiencies in the business. It also predicts areas for future improvement, enabling proactive measures. For example, the server might predict that manual operations in the monthly report creation process need to be reduced.

[0039] Implementation of automation

[0040] Users review improvement suggestions provided by the server and implement automation of business processes. For example, by introducing Robotic Process Automation (RPA) to automate the input of HR data, data entry errors can be reduced and processing time shortened. Implementing these suggestions results in substantial efficiency improvements and cost reductions.

[0041] Effectiveness measurement and feedback

[0042] After the improvement measures are implemented, the user measures their effectiveness. The server provides metrics for measuring effectiveness, and the user compares and evaluates whether the proposed effects were achieved. For example, metrics such as reductions in processing time and costs, and reductions in errors are used. This evaluation result is returned to the server as feedback and used to further improve the generative model.

[0043] In this way, the present invention enables the efficient and effective automation and optimization of corporate business processes.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The server collects data from various business systems within the company. It utilizes API calls and database queries to automatically extract data according to a specified schedule. Furthermore, the collected data is validated to check for outliers and missing values.

[0047] Step 2:

[0048] The terminal performs preprocessing of the collected data. Specifically, it cleans the data, appropriately imputing missing values ​​and removing outliers. Then, it normalizes the dataset, standardizing numerical data of different scales. Furthermore, it integrates information from multiple data sources to create a consistent dataset.

[0049] Step 3:

[0050] The server inputs pre-processed data into a generative model for analysis. The generative model analyzes business processes and identifies bottlenecks and inefficient processes. Next, it makes predictions based on the analysis results to identify processes that will need improvement in the future and areas that can be automated.

[0051] Step 4:

[0052] The server generates specific business improvement proposals based on the analysis results. During this process, it performs various simulations to predict the effects of implementing the proposals. It then notifies the user of the improvement proposals and provides specific instructions regarding the automation of business processes.

[0053] Step 5:

[0054] Users review the suggestions from the server and implement improvements to their business processes. For example, they may implement proposed automations by changing system settings or modifying business procedures. They may also consider introducing external tools or RPA as needed.

[0055] Step 6:

[0056] After improvements are implemented, the server collects various data again to measure their effectiveness. Based on the collected data, it quantitatively evaluates the effectiveness of the improvement proposals. Specifically, it calculates the process efficiency rate and the amount of cost reduction.

[0057] Step 7:

[0058] The user reviews the results of the performance measurement provided by the server and evaluates whether the improvements were made appropriately. The evaluation results are provided to the server as feedback to be used in considering further improvement measures in the future. Based on this, the server adjusts the parameters of the generative model to improve the accuracy of subsequent analyses.

[0059] (Example 1)

[0060] 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."

[0061] In modern business operations, the importance of streamlining and automating business processes is increasing. However, collecting information from multiple sources within a company and integrating it into a consistent dataset is time-consuming, and manual analysis and prediction can be inaccurate. Furthermore, actually measuring the effects of improvement measures and incorporating continuous feedback into generative models is extremely difficult. This invention aims to solve these problems and provide a means for efficiently and accurately optimizing and automating business processes.

[0062] 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.

[0063] In this invention, the server includes means for analyzing business procedure data using a generative model, means for acquiring data from different sources and preprocessing the data into a consistent data set, and means for predicting areas for improvement in business operations based on the analysis results. This makes it possible to automate the integration and analysis of information and the streamlining of operations, and to feed the results back into the generative model.

[0064] An "information processing device" is a computer system used for data collection, analysis, and integration, and it has the function of automatically optimizing operations using generative models.

[0065] A "generative model" is a mathematical model that uses machine learning algorithms to learn data patterns and predict improvements and enhancements to business processes.

[0066] A "data set" is a collection of data obtained from different sources that has been unified, organized, and given consistency.

[0067] "Business procedures" refer to the series of processes and activities that a company performs in its daily operations, and optimizing these procedures is key to improving operational efficiency.

[0068] "Analysis results" refer to information obtained through data analysis using generative models that indicates bottlenecks and areas for improvement in business operations.

[0069] "Resource reduction effect" refers to the amount of resource reduction, such as time, costs, and human effort, achieved through the automation of business procedures, as well as the improvement in efficiency.

[0070] "Feedback" refers to information used to improve the accuracy of an automated business process by returning evaluation results regarding its effectiveness and areas for improvement to the generative model.

[0071] A description of the embodiment for carrying out the invention will be provided.

[0072] This system aims to streamline and automate business procedures within a company. The server functions as an information processing unit, handling data collection, analysis, and the operation of generative models. Specifically, the hardware requires server equipment with a high-performance processor, and the software includes a database management system and a framework for implementing machine learning models.

[0073] The server first collects data from the company's business systems using APIs and database queries. Then, the terminal receives the collected data, cleans and normalizes it, and builds a unified data set. This ensures that data from different sources is processed in a consistent format.

[0074] Pre-processed data is input into a generative AI model by the server. This generative model includes, for example, a deep learning algorithm based on historical business process data. This model has the ability to identify bottlenecks and inefficiencies in business processes and propose specific improvement measures to the user. If the user accepts these suggestions, the business procedures are automated.

[0075] As a concrete example, let's consider a way to reduce manual operations when creating monthly reports. In this case, we can input the text "Please suggest ways to automate and streamline the manual parts of the monthly report creation process" as a prompt into the AI ​​model and obtain improvement suggestions.

[0076] Based on improvement suggestions from the server, users implement automation procedures they deem feasible. This results in substantial operational efficiency and cost reduction. After the improvements are implemented, the server evaluates their effectiveness and feeds the evaluation results back into the generative model, further improving the model's accuracy.

[0077] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0078] Step 1:

[0079] The server collects data from the company's business systems. Specifically, it periodically retrieves HR data, financial data, logistics data, etc., using APIs and database queries. The input for this step is the database of each business system, and the output is raw data stored in the server's temporary storage. The server extracts the necessary data points and prepares them for use in subsequent processing.

[0080] Step 2:

[0081] The terminal preprocesses the raw data received from the server. Specifically, it performs data cleaning, removing duplicate data and correcting outliers. It also normalizes data from different sources and converts it into a unified format. The input is the collected raw data, and the output is a clean and consistent data set. Through this processing, the terminal guarantees the reliability and consistency of the data.

[0082] Step 3:

[0083] The server inputs pre-processed data into a generative AI model. The generative model has the ability to analyze bottlenecks and inefficiencies in business processes based on past operational data and propose future improvement measures. The input is a set of pre-processed data, and the output is specific suggestions for business improvement. For example, it might suggest automating a time-consuming report generation process.

[0084] Step 4:

[0085] The user reviews the improvement suggestions provided by the server and selects those that are feasible. Next, they automate business procedures based on those suggestions. A specific example might be automating manual data entry tasks using a suggested RPA tool. The input is the improvement suggestions from the server, and the output is the automated business procedure. This improves the user's work efficiency.

[0086] Step 5:

[0087] After the improvement measures are implemented, the user evaluates their effectiveness. The server provides evaluation metrics for measuring effectiveness. The user measures the effectiveness based on factors such as reductions in processing time and cost, and a decrease in error rate, and feeds the evaluation results back to the server. The input is the automated business data, and the output is an evaluation report and feedback to the generative model. This feedback helps to improve the accuracy of the generative model.

[0088] (Application Example 1)

[0089] 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."

[0090] In modern manufacturing, multiple production lines exist, and the goal is to maximize the efficiency of each. However, manual process control and inefficient bottlenecks often occur throughout the entire production line, leading to decreased productivity. Furthermore, the lack of automated work instructions to quickly resolve these problems limits long-term cost reductions and efficiency improvements.

[0091] 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.

[0092] In this invention, the server includes means for analyzing business procedure data using a generative model, means for predicting areas for improvement in the business based on the analysis results, means for automating the business procedures based on the predicted areas for improvement, and means for automatically generating and distributing work instructions to improve the efficiency of manufacturing operations. This makes it possible to quickly identify and resolve bottlenecks in the manufacturing line, thereby improving production efficiency and reducing costs.

[0093] A "generative model" is an algorithm that learns past patterns based on collected data and uses that knowledge to make predictions and analyses about new data situations.

[0094] "Business procedures" refer to a set of work flows or processes defined within an organization or system to achieve a specific objective.

[0095] "Analysis results" refer to the information and insights obtained from data analyzed using generative models, and serve as important guidelines for business improvement.

[0096] "Areas for improvement" refers to parts or elements in business procedures that need to be changed or adjusted in order to improve efficiency or effectiveness.

[0097] "Automation" refers to the process of autonomously performing tasks and processes that were previously done manually, using digital technology and machinery.

[0098] "Work instructions" are instructional documents or information that summarize the procedures and points to be followed in a specific task or operation.

[0099] "Improving the efficiency of manufacturing operations" refers to measures taken to improve the productivity of the entire manufacturing process, reduce waste, and enhance quality.

[0100] To realize this invention, a server first collects data from multiple manufacturing lines. This data includes information such as the operating status of the manufacturing lines, material flow, and energy consumption. The data is acquired through sensors and IoT devices and integrated in real time using Apache® Kafka.

[0101] Next, the server preprocesses the data. This involves cleaning and shaping the data using the Python pandas library, generating a clean and consistent dataset.

[0102] The generative AI model is built using TENSORFLOW® and PyTorch. By inputting pre-processed data into this model, the system analyzes business procedures, identifies bottlenecks, and predicts areas for improvement. Based on the analysis, the server automatically generates the necessary work instructions to improve the efficiency of manufacturing operations and distributes them to the robots via the MQTT protocol.

[0103] As a result, users can quickly identify bottlenecks in their production lines and implement corrective measures in real time. For example, if material supply is delayed on a production line, the production model can identify the cause as a clogged pipe and issue instructions for maintenance in advance. In this way, production efficiency can be improved and unnecessary costs can be reduced.

[0104] An example of a prompt message is as follows:

[0105] "Please explain how to analyze factory production line data, identify bottlenecks in each work step, and optimize them in real time. Furthermore, please provide specific work instructions on what needs to be done to eliminate those bottlenecks."

[0106] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0107] Step 1:

[0108] The server collects data from each production line within the factory via sensors and IoT devices. Inputs include data on production line operation status, material flow, and energy consumption. This data is integrated using Apache Kafka to generate a real-time data stream. The output is an integrated dataset.

[0109] Step 2:

[0110] The server preprocesses the integrated dataset using the Python pandas library. It receives raw data requiring cleansing as input. Data cleaning involves removing outliers and normalizing the data. The data is then formatted into a consistent format, generating a well-formed dataset as output.

[0111] Step 3:

[0112] The server inputs a well-formed dataset into a generative AI model. The generative model, built using TensorFlow or PyTorch, analyzes the manufacturing line bottlenecks based on the data. The input is a pre-processed dataset, and the output is a prediction of identified bottlenecks and areas for improvement.

[0113] Step 4:

[0114] The server automatically generates work instructions necessary for improving the efficiency of manufacturing operations based on the analysis results from the generated AI model. The input is data predicting bottlenecks and areas for improvement. The generated work instructions include specific steps on which parts should be modified. As output, work instructions are prepared for distribution via the MQTT protocol.

[0115] Step 5:

[0116] The user receives work instructions delivered from the server and supervises and executes specific improvement tasks on the manufacturing line. The input is specific work instruction information. The output is the improvement actions taken in the actual manufacturing process, which leads to improved manufacturing efficiency.

[0117] 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.

[0118] This invention provides a system that effectively analyzes, predicts, and automates business processes by combining a generative model with an emotion engine. The embodiments for carrying out the invention are described in detail below.

[0119] Data collection and normalization

[0120] The server collects necessary data from various business systems within the company. During this process, it extracts information using APIs and database queries, while simultaneously obtaining user sentiment data. Sentiment data is acquired from user interface operation logs and feedback forms. The collected data is normalized and integrated in a unified format.

[0121] Analysis using generative models and emotion engines

[0122] The terminal applies a generative model to normalized business and emotional data to perform detailed analysis. The generative model identifies patterns and bottlenecks in the business flow. In addition, the emotional engine analyzes the user's emotional information and evaluates the need for business improvements based on the situation. For example, if a high workload is detected, the emotional engine will suggest ways to reduce the workload.

[0123] Predictions of areas for improvement

[0124] Based on analysis results from generative models and the sentiment engine, the server predicts areas for improvement in future business processes. These predictions offer users strategies to improve work efficiency and the work environment. Specifically, these include suggestions for automating parts of the workflow and reallocating tasks to reduce workload.

[0125] Process automation

[0126] Users automate business processes according to suggestions from the server. For example, they might implement tools to automate repetitive tasks and reduce working hours. They also improve work efficiency by reviewing processes and reallocating resources at appropriate times based on feedback from the emotional engine.

[0127] Effectiveness measurement and feedback

[0128] Subsequently, the server measures the effectiveness of the automated tasks and analyzes performance indicators. Users review the measurement results and evaluate the effectiveness of process improvements. This feedback is used to improve system accuracy and develop future business improvement measures. For example, this could include cases where business efficiency improves and user satisfaction increases.

[0129] This invention enables the simultaneous achievement of operational efficiency and improved work environment, thereby promoting the optimization of corporate operations.

[0130] The following describes the processing flow.

[0131] Step 1:

[0132] The server collects business data from various business systems within the company. It uses APIs and database queries to periodically retrieve necessary information. Simultaneously, it also acquires user sentiment data using a sentiment engine. Sentiment data is collected from operation logs and feedback forms on the user interface and recorded in conjunction with each business activity.

[0133] Step 2:

[0134] The terminal preprocesses the collected data. Data cleaning involves imputing missing values ​​with mean values ​​and removing outliers. Normalization standardizes data with different scales and adjusts the integrated dataset. Furthermore, it logically integrates data from different business systems and transforms it into an analyzable format in a consistent manner.

[0135] Step 3:

[0136] The server analyzes pre-processed data using a generative model. This analysis assesses the current state of business processes and identifies potential bottlenecks and inefficiencies. Next, it utilizes an emotion engine to measure work stress and burden based on user emotion data and evaluates the impact on the work environment.

[0137] Step 4:

[0138] The server generates specific business improvement suggestions based on the analysis results of the generative model and the sentiment engine. These suggestions include tasks that can be automated, tasks that need improvement, and measures to improve user experience based on sentiment data. The suggestions are communicated to the user and used as specific guidelines for business improvement.

[0139] Step 5:

[0140] Users implement improvement suggestions provided by the server. This includes introducing automation tools, reviewing and streamlining work procedures, and taking measures to optimize workloads and reduce employee stress based on insights from the emotion engine.

[0141] Step 6:

[0142] The server remeasures business performance after improvements have been implemented. It analyzes the efficiency gains and cost reductions from the newly collected data, quantitatively evaluating the effectiveness of the business improvements. The measurement results are automatically generated and presented to the user.

[0143] Step 7:

[0144] Users receive the server's analysis results and evaluate whether their business improvements were successful. Based on this feedback, they reconsider areas that require further improvement. This feedback is sent back to the server to improve the system's accuracy and train the sentiment engine, which helps in future analyses and recommendations.

[0145] (Example 2)

[0146] 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".

[0147] For many companies, streamlining business processes is a critical issue. However, analyzing business data and improving processes requires specialized knowledge, and proposing appropriate improvement measures that take into account employee emotions and workload is difficult. Therefore, there is a need for the development of automation systems that comprehensively consider the diverse elements of business operations.

[0148] 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.

[0149] In this invention, the server includes means for analyzing business process data using a generative model, means for predicting areas for business improvement based on the analysis results, and means for analyzing user sentiment data using a sentiment analysis engine and evaluating the need for business improvement. This enables comprehensive analysis of business processes based on business data and sentiment data, as well as concrete proposals for improvement and automation.

[0150] A "generative model" is a model that uses machine learning techniques to extract patterns from large datasets and then generates new data or analyzes existing data.

[0151] A "business process" refers to a series of business activities carried out within an organization, and is something that can be made more efficient or improved.

[0152] An "emotion analysis engine" is a technology that analyzes emotional data collected from users, evaluates trends and states, and uses this information to propose improvements to business operations.

[0153] "Data normalization" is the process of converting data recorded in different formats and units into a unified format, making it suitable for analysis.

[0154] "Predicting areas for business improvement" is the act of identifying specific improvement items to enhance the efficiency and effectiveness of current business processes, based on analyzed data.

[0155] "Automation" is a process that aims to improve efficiency and reduce errors by using technology to automate tasks that are currently performed manually.

[0156] "Effectiveness measurement" is the act of measuring how much success an implemented process improvement measure has brought about.

[0157] This invention is a system that combines a generative AI model and an emotion analysis engine to improve the efficiency and effectiveness of business processes. The embodiments are described in detail below.

[0158] The server retrieves business data and user feedback from the information management system using APIs and database queries. It then uses software to normalize this data and convert it into a unified format. This process utilizes universally accepted data management tools to maintain data integrity.

[0159] The terminal analyzes the normalized data through a generative AI model. This generative model identifies patterns and bottlenecks within the workflow and extracts areas for improvement to streamline processes. In parallel, a sentiment analysis engine analyzes the user's emotional data and assesses the need for business process improvement. If the user is experiencing stress in the workflow, specific improvement suggestions are formed at this stage.

[0160] As a concrete example, consider a digital marketing company implementing this system. They analyze employee work data to identify the reasons for declining advertising campaign effectiveness. In this process, emotional data might indicate that "the campaign content needs to be reviewed." Based on these results, a generative model develops a new campaign strategy, thereby improving advertising effectiveness.

[0161] Another example of a prompt is: "Analyze the company's internal business processes and generate specific suggestions to improve operational efficiency and user satisfaction."

[0162] This system enables sustainable organizational management by systematizing the improvement of operational efficiency and the work environment.

[0163] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0164] Step 1:

[0165] The server collects business data and user feedback from the information management system using APIs and database queries. Input consists of unstandardized data from various systems, and output is a set of raw data before processing. In this process, the server also acquires operation logs and feedback form information, collecting both quantitative and qualitative sentiment data related to actual business operations.

[0166] Step 2:

[0167] The server performs a process to normalize the collected data. The input is raw data before processing, and the output is standardized data in a unified format. Specifically, it performs tasks such as unifying different date formats and converting sentiment feedback into numerical scores. This conversion ensures that the data can be handled consistently in subsequent analysis processes.

[0168] Step 3:

[0169] The terminal receives normalized data and performs data analysis by applying a generative AI model. The input is a standardized dataset, and the output is analysis results and improvement suggestions regarding patterns and bottlenecks within the business flow. Specifically, it uses a pattern recognition algorithm to identify efficiency trends in the data and identify areas that need improvement.

[0170] Step 4:

[0171] The device uses an emotion analysis engine to analyze the user's emotional data in detail. The input is the user's emotion score, and the output is a determination of the urgency of business improvement based on emotional tendencies. For example, it can pinpoint the points where the user is experiencing stress and identify the business process that is causing it.

[0172] Step 5:

[0173] Based on the analysis results described above, the server predicts areas for improvement in business processes and proposes automation. The input consists of the results of a generative model and sentiment analysis engine, while the output is a list of automatable business processes and suggestions for task reallocation. Specifically, it generates automation proposals for routine data entry and report creation tasks, aiming to improve operational efficiency.

[0174] Step 6:

[0175] Users automate business processes based on improvements suggested by the server. The input is the server's automation suggestions, and the output is the highly automated business process. Specific implementations include introducing a "tool for automatically generating standardized text" to significantly reduce email response time.

[0176] Step 7:

[0177] The server measures the effectiveness of automated processes performed by users and analyzes performance metrics. Input is automated business data, and output is reports on improvements in operational efficiency and employee satisfaction. Based on the measurement results, further improvements and adjustments are made to achieve continuous optimization.

[0178] (Application Example 2)

[0179] 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".

[0180] In factory operations, there is a need to improve efficiency while reducing the burden on workers. However, currently, excessive workloads are placed on workers in order to increase productivity, which is resulting in a decline in quality and a deterioration of the working environment. Furthermore, there is a problem that the optimization of work processes has reached its limits because workers' emotions and stress are not taken into consideration.

[0181] 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.

[0182] In this invention, the server includes means for analyzing business process data using a generative model, means for predicting areas for improvement in business operations based on the analysis results, means for automating business processes based on the predicted areas for improvement, means for sentiment analysis for collecting and analyzing sentiment data, and means for making suggestions to adjust the workload using the sentiment analysis results. This enables both increased efficiency in business processes and reduced burden on workers, resulting in a better work environment and improved productivity.

[0183] A "generative model" is a machine learning algorithm that learns patterns and trends from data and generates new information.

[0184] A "business process" refers to a series of tasks and procedures within a company or organization, and is a method for carrying out activities efficiently.

[0185] "Analyzing" refers to the method of examining documents and data to understand their contents in detail.

[0186] "Areas for improvement" refers to parts of the current process or system that need improvement to enhance efficiency or effectiveness.

[0187] "Automating" means carrying out tasks or processes without human intervention, and being operated by machines or programs.

[0188] "Emotional data" refers to a representation of an individual's emotions and psychological state, converted into numerical values ​​and information.

[0189] "Analysis results" refer to the conclusions and insights obtained after analyzing data.

[0190] To "make a proposal" means to present new ideas or solutions regarding improvements to specific methods or processes.

[0191] In embodiments for carrying out this invention, a detailed explanation will be provided mainly for three elements: the server, the terminal, and the user.

[0192] The server incorporates a data collection module for gathering various data from within the factory. Specifically, it can collect data from various sensors installed in the factory and feedback from workers via APIs. The collected data is then normalized, integrated into a consistent format, and analyzed by a generative AI model. The generative AI model identifies bottlenecks and inefficiencies in business processes and predicts areas for improvement. This process utilizes data processing software running on the server.

[0193] The terminal displays data analyzed by a generated AI model and worker emotion data obtained using an emotion analysis engine. This allows users to check the worker's psychological state in real time and adjust work processes as needed. The emotion analysis engine collects emotion data from specific operation logs and feedback and suggests process improvements based on the emotional state.

[0194] Based on these analysis results and sentiment data, users can automate business processes. For example, when automation suggestions are made via a terminal, they can adjust worker break times or optimize production by robots. This simultaneously improves the efficiency of the entire business process and reduces the burden on workers, thereby improving the workplace environment.

[0195] As a concrete example, consider a business improvement that occurred on an assembly line for a certain part. In this case, the generative model analyzes data from the entire line and identifies that worker fatigue is high during specific time periods. As a result, the server, based on the analysis data from the emotion engine, proposes shift adjustments to automate processes using robots and allow workers to take breaks. An example of a prompt would be, "Based on the following dataset, evaluate the workers' stress levels and propose improvements to the production schedule."

[0196] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0197] Step 1:

[0198] The server collects operational data from sensors within the factory and worker feedback, and retrieves it via an API. Inputs are real-time data from sensors and worker feedback, while outputs are normalized data in a unified format. After collection, the data is normalized, noise is removed, and it is integrated into a format suitable for analysis.

[0199] Step 2:

[0200] The server inputs the normalized business data into a generation AI model to analyze the business process. The input is the data integrated in the previous step, and the output is the identification of bottlenecks and patterns in the business flow. In this process, machine learning algorithms extract features from the data and identify areas where business improvements are needed.

[0201] Step 3:

[0202] The server collects emotional data based on the analysis results and performs analysis using an emotional analysis engine. The input is emotional feedback data, and the output is an evaluation of the worker's psychological state and stress level. Based on this data, it detects when the workload is excessive and prepares appropriate improvement suggestions.

[0203] Step 4:

[0204] The terminal receives analysis results sent from the server and notifies the user in real time. Input is data sent from the server, and output is a visualized list of suggested work improvements displayed on the user's screen. It proposes work schedules that take into account the worker's emotional state and presents concrete action plans.

[0205] Step 5:

[0206] The user automates business processes based on the suggestions provided. Inputs are the schedule and improvement suggestions displayed on the terminal, and output is the adjusted business flow. This increases automation by robots and reduces the burden on workers. Specifically, the user uses the terminal to adjust shifts and, if necessary, changes the robot's operating time.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] [Second Embodiment]

[0211] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0212] 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.

[0213] 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).

[0214] 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.

[0215] 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.

[0216] 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).

[0217] 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.

[0218] 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.

[0219] 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.

[0220] 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.

[0221] 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.

[0222] 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".

[0223] This invention provides a technology for automating and optimizing various business processes within an enterprise using generative models. The following describes embodiments for carrying out the invention.

[0224] Data collection and preprocessing

[0225] The server collects data from multiple business systems within a company, such as human resources, finance, and logistics. This data is retrieved periodically using APIs and database queries. Next, the terminal preprocesses the collected data. By cleaning, normalizing, and integrating information from different data sources, a unified dataset is created. This preprocessing ensures the data consistency necessary for subsequent analysis.

[0226] Analysis and prediction using generative models

[0227] The server inputs pre-processed data into a generative model to analyze business processes. The generative model learns from historical data to identify bottlenecks and inefficiencies in the business. It also predicts areas for future improvement, enabling proactive measures. For example, the server might predict that manual operations in the monthly report creation process need to be reduced.

[0228] Implementation of automation

[0229] Users review improvement suggestions provided by the server and implement automation of business processes. For example, by introducing Robotic Process Automation (RPA) to automate the input of HR data, data entry errors can be reduced and processing time shortened. Implementing these suggestions results in substantial efficiency improvements and cost reductions.

[0230] Effectiveness measurement and feedback

[0231] After the improvement measures are implemented, the user measures their effectiveness. The server provides metrics for measuring effectiveness, and the user compares and evaluates whether the proposed effects were achieved. For example, metrics such as reductions in processing time and costs, and reductions in errors are used. This evaluation result is returned to the server as feedback and used to further improve the generative model.

[0232] In this way, the present invention enables the efficient and effective automation and optimization of corporate business processes.

[0233] The following describes the processing flow.

[0234] Step 1:

[0235] The server collects data from various business systems within the company. It utilizes API calls and database queries to automatically extract data according to a specified schedule. Furthermore, the collected data is validated to check for outliers and missing values.

[0236] Step 2:

[0237] The terminal performs preprocessing of the collected data. Specifically, it cleans the data, appropriately imputing missing values ​​and removing outliers. Then, it normalizes the dataset, standardizing numerical data of different scales. Furthermore, it integrates information from multiple data sources to create a consistent dataset.

[0238] Step 3:

[0239] The server inputs pre-processed data into a generative model for analysis. The generative model analyzes business processes and identifies bottlenecks and inefficient processes. Next, it makes predictions based on the analysis results to identify processes that will need improvement in the future and areas that can be automated.

[0240] Step 4:

[0241] The server generates specific business improvement proposals based on the analysis results. During this process, it performs various simulations to predict the effects of implementing the proposals. It then notifies the user of the improvement proposals and provides specific instructions regarding the automation of business processes.

[0242] Step 5:

[0243] Users review the suggestions from the server and implement improvements to their business processes. For example, they may implement proposed automations by changing system settings or modifying business procedures. They may also consider introducing external tools or RPA as needed.

[0244] Step 6:

[0245] After improvements are implemented, the server collects various data again to measure their effectiveness. Based on the collected data, it quantitatively evaluates the effectiveness of the improvement proposals. Specifically, it calculates the process efficiency rate and the amount of cost reduction.

[0246] Step 7:

[0247] The user reviews the results of the performance measurement provided by the server and evaluates whether the improvements were made appropriately. The evaluation results are provided to the server as feedback to be used in considering further improvement measures in the future. Based on this, the server adjusts the parameters of the generative model to improve the accuracy of subsequent analyses.

[0248] (Example 1)

[0249] 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."

[0250] In modern business operations, the importance of streamlining and automating business processes is increasing. However, collecting information from multiple sources within a company and integrating it into a consistent dataset is time-consuming, and manual analysis and prediction can be inaccurate. Furthermore, actually measuring the effects of improvement measures and incorporating continuous feedback into generative models is extremely difficult. This invention aims to solve these problems and provide a means for efficiently and accurately optimizing and automating business processes.

[0251] 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.

[0252] In this invention, the server includes means for analyzing business procedure data using a generative model, means for acquiring data from different sources and preprocessing the data into a consistent data set, and means for predicting areas for improvement in business operations based on the analysis results. This makes it possible to automate the integration and analysis of information and the streamlining of operations, and to feed the results back into the generative model.

[0253] An "information processing device" is a computer system used for data collection, analysis, and integration, and it has the function of automatically optimizing operations using generative models.

[0254] A "generative model" is a mathematical model that uses machine learning algorithms to learn data patterns and predict improvements and enhancements to business processes.

[0255] A "data set" is a collection of data obtained from different sources that has been unified, organized, and given consistency.

[0256] "Business procedures" refer to the series of processes and activities that a company performs in its daily operations, and optimizing these procedures is key to improving operational efficiency.

[0257] "Analysis results" refer to information obtained through data analysis using generative models that indicates bottlenecks and areas for improvement in business operations.

[0258] "Resource reduction effect" refers to the amount of resource reduction, such as time, costs, and human effort, achieved through the automation of business procedures, as well as the improvement in efficiency.

[0259] "Feedback" refers to information used to improve the accuracy of an automated business process by returning evaluation results regarding its effectiveness and areas for improvement to the generative model.

[0260] A description of the embodiment for carrying out the invention will be provided.

[0261] This system aims to streamline and automate business procedures within a company. The server functions as an information processing unit, handling data collection, analysis, and the operation of generative models. Specifically, the hardware requires server equipment with a high-performance processor, and the software includes a database management system and a framework for implementing machine learning models.

[0262] The server first collects data from the company's business systems using APIs and database queries. Then, the terminal receives the collected data, cleans and normalizes it, and builds a unified data set. This ensures that data from different sources is processed in a consistent format.

[0263] Pre-processed data is input into a generative AI model by the server. This generative model includes, for example, a deep learning algorithm based on historical business process data. This model has the ability to identify bottlenecks and inefficiencies in business processes and propose specific improvement measures to the user. If the user accepts these suggestions, the business procedures are automated.

[0264] As a concrete example, let's consider a way to reduce manual operations when creating monthly reports. In this case, we can input the text "Please suggest ways to automate and streamline the manual parts of the monthly report creation process" as a prompt into the AI ​​model and obtain improvement suggestions.

[0265] Based on improvement suggestions from the server, users implement automation procedures they deem feasible. This results in substantial operational efficiency and cost reduction. After the improvements are implemented, the server evaluates their effectiveness and feeds the evaluation results back into the generative model, further improving the model's accuracy.

[0266] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0267] Step 1:

[0268] The server collects data from the company's business systems. Specifically, it periodically retrieves HR data, financial data, logistics data, etc., using APIs and database queries. The input for this step is the database of each business system, and the output is raw data stored in the server's temporary storage. The server extracts the necessary data points and prepares them for use in subsequent processing.

[0269] Step 2:

[0270] The terminal preprocesses the raw data received from the server. Specifically, it performs data cleaning, removing duplicate data and correcting outliers. It also normalizes data from different sources and converts it into a unified format. The input is the collected raw data, and the output is a clean and consistent data set. Through this processing, the terminal guarantees the reliability and consistency of the data.

[0271] Step 3:

[0272] The server inputs pre-processed data into a generative AI model. The generative model has the ability to analyze bottlenecks and inefficiencies in business processes based on past operational data and propose future improvement measures. The input is a set of pre-processed data, and the output is specific suggestions for business improvement. For example, it might suggest automating a time-consuming report generation process.

[0273] Step 4:

[0274] The user reviews the improvement suggestions provided by the server and selects those that are feasible. Next, they automate business procedures based on those suggestions. A specific example might be automating manual data entry tasks using a suggested RPA tool. The input is the improvement suggestions from the server, and the output is the automated business procedure. This improves the user's work efficiency.

[0275] Step 5:

[0276] After the improvement measures are implemented, the user evaluates their effectiveness. The server provides evaluation metrics for measuring effectiveness. The user measures the effectiveness based on factors such as reductions in processing time and cost, and a decrease in error rate, and feeds the evaluation results back to the server. The input is the automated business data, and the output is an evaluation report and feedback to the generative model. This feedback helps to improve the accuracy of the generative model.

[0277] (Application Example 1)

[0278] 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."

[0279] In modern manufacturing, multiple production lines exist, and the goal is to maximize the efficiency of each. However, manual process control and inefficient bottlenecks often occur throughout the entire production line, leading to decreased productivity. Furthermore, the lack of automated work instructions to quickly resolve these problems limits long-term cost reductions and efficiency improvements.

[0280] 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.

[0281] In this invention, the server includes means for analyzing business procedure data using a generative model, means for predicting areas for improvement in the business based on the analysis results, means for automating the business procedures based on the predicted areas for improvement, and means for automatically generating and distributing work instructions to improve the efficiency of manufacturing operations. This makes it possible to quickly identify and resolve bottlenecks in the manufacturing line, thereby improving production efficiency and reducing costs.

[0282] A "generative model" is an algorithm that learns past patterns based on collected data and performs predictions and analyses on new data situations.

[0283] A "business procedure" is a series of work flows and processes defined within an organization or system to achieve a specific goal.

[0284] "Analysis results" are the information and insights obtained from the data analyzed by the generative model, and are important guidelines for business improvement.

[0285] "Improvement points" refer to the parts or elements that need to be changed or adjusted in the business procedure to improve efficiency and effectiveness.

[0286] "Automation" means making conventional manual operations and processes perform autonomously using digital technologies and machines.

[0287] "Work instructions" are the guiding documents or instruction information that summarize the procedures and precautions to be followed in specific operations or tasks.

[0288] "Efficiency improvement of manufacturing operations" is a measure to improve the productivity of the entire manufacturing process, reduce waste, and improve quality.

[0289] To implement this invention, first, the server collects data from multiple manufacturing lines. This data includes information such as the operating status of the manufacturing lines, the flow of materials, and energy consumption. The data is acquired through sensors and IoT devices and integrated in real time using Apache Kafka.

[0290] Next, the server preprocesses the data. For this task, data cleaning and shaping are performed using the pandas library in Python to generate a cleansed and consistent dataset.

[0291] The generative AI model is built using TensorFlow or PyTorch. By inputting pre-processed data into this model, it analyzes business procedures, identifies bottlenecks, and predicts areas for improvement. Based on the analysis, the server automatically generates the necessary work instructions to improve the efficiency of manufacturing operations and distributes them to robots via the MQTT protocol.

[0292] As a result, users can quickly identify bottlenecks in their production lines and implement corrective measures in real time. For example, if material supply is delayed on a production line, the production model can identify the cause as a clogged pipe and issue instructions for maintenance in advance. In this way, production efficiency can be improved and unnecessary costs can be reduced.

[0293] An example of a prompt message is as follows:

[0294] "Please explain how to analyze factory production line data, identify bottlenecks in each work step, and optimize them in real time. Furthermore, please provide specific work instructions on what needs to be done to eliminate those bottlenecks."

[0295] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0296] Step 1:

[0297] The server collects data from each production line within the factory via sensors and IoT devices. Inputs include data on production line operation status, material flow, and energy consumption. This data is integrated using Apache Kafka to generate a real-time data stream. The output is an integrated dataset.

[0298] Step 2:

[0299] The server preprocesses the integrated dataset using the Python pandas library. It receives raw data requiring cleansing as input. Data cleaning involves removing outliers and normalizing the data. The data is then formatted into a consistent format, generating a well-formed dataset as output.

[0300] Step 3:

[0301] The server inputs a well-formed dataset into a generative AI model. The generative model, built using TensorFlow or PyTorch, analyzes the manufacturing line bottlenecks based on the data. The input is a pre-processed dataset, and the output is a prediction of identified bottlenecks and areas for improvement.

[0302] Step 4:

[0303] The server automatically generates work instructions necessary for improving the efficiency of manufacturing operations based on the analysis results from the generated AI model. The input is data predicting bottlenecks and areas for improvement. The generated work instructions include specific steps on which parts should be modified. As output, work instructions are prepared for distribution via the MQTT protocol.

[0304] Step 5:

[0305] The user receives work instructions delivered from the server and supervises and executes specific improvement tasks on the manufacturing line. The input is specific work instruction information. The output is the improvement actions taken in the actual manufacturing process, which leads to improved manufacturing efficiency.

[0306] 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.

[0307] The present invention provides a system that effectively analyzes, predicts, and automates business processes by combining an emotion engine in addition to a generative model. The embodiments for implementing the invention will be described in detail below.

[0308] Data collection and normalization

[0309] The server collects the necessary data from various business systems within the enterprise. At this time, information is extracted using APIs and database queries, and at the same time, the emotion data of the user is obtained. The emotion data is obtained from operation logs of the user interface, feedback forms, etc. The collected data is normalized and integrated in a unified format.

[0310] Analysis by the generative model and the emotion engine

[0311] The terminal applies the generative model based on the normalized business data and emotion data for detailed analysis. The generative model identifies patterns and bottlenecks in the business process. In addition, the emotion engine analyzes the user's emotion information and evaluates the need for business improvement according to the situation. For example, when a state of high business load is detected, the emotion engine proposes to reduce the business load.

[0312] Prediction of improvement points

[0313] The server predicts improvement points for future business processes based on the analysis results obtained from the generative model and the emotion engine. This prediction presents measures to the user that are useful for improving business efficiency and the workplace environment. Specifically, it includes proposals to automate part of the business process and task redistribution to reduce the business burden.

[0314] Automation of the process

[0315] Users automate business processes according to suggestions from the server. For example, they might implement tools to automate repetitive tasks and reduce working hours. They also improve work efficiency by reviewing processes and reallocating resources at appropriate times based on feedback from the emotional engine.

[0316] Effectiveness measurement and feedback

[0317] Subsequently, the server measures the effectiveness of the automated tasks and analyzes performance indicators. Users review the measurement results and evaluate the effectiveness of process improvements. This feedback is used to improve system accuracy and develop future business improvement measures. For example, this could include cases where business efficiency improves and user satisfaction increases.

[0318] This invention enables the simultaneous achievement of operational efficiency and improved work environment, thereby promoting the optimization of corporate operations.

[0319] The following describes the processing flow.

[0320] Step 1:

[0321] The server collects business data from various business systems within the company. It uses APIs and database queries to periodically retrieve necessary information. Simultaneously, it also acquires user sentiment data using a sentiment engine. Sentiment data is collected from operation logs and feedback forms on the user interface and recorded in conjunction with each business activity.

[0322] Step 2:

[0323] The terminal preprocesses the collected data. Data cleaning involves imputing missing values ​​with mean values ​​and removing outliers. Normalization standardizes data with different scales and adjusts the integrated dataset. Furthermore, it logically integrates data from different business systems and transforms it into an analyzable format in a consistent manner.

[0324] Step 3:

[0325] The server analyzes pre-processed data using a generative model. This analysis assesses the current state of business processes and identifies potential bottlenecks and inefficiencies. Next, it utilizes an emotion engine to measure work stress and burden based on user emotion data and evaluates the impact on the work environment.

[0326] Step 4:

[0327] The server generates specific business improvement suggestions based on the analysis results of the generative model and the sentiment engine. These suggestions include tasks that can be automated, tasks that need improvement, and measures to improve user experience based on sentiment data. The suggestions are communicated to the user and used as specific guidelines for business improvement.

[0328] Step 5:

[0329] Users implement improvement suggestions provided by the server. This includes introducing automation tools, reviewing and streamlining work procedures, and taking measures to optimize workloads and reduce employee stress based on insights from the emotion engine.

[0330] Step 6:

[0331] The server remeasures business performance after improvements have been implemented. It analyzes the efficiency gains and cost reductions from the newly collected data, quantitatively evaluating the effectiveness of the business improvements. The measurement results are automatically generated and presented to the user.

[0332] Step 7:

[0333] Users receive the server's analysis results and evaluate whether their business improvements were successful. Based on this feedback, they reconsider areas that require further improvement. This feedback is sent back to the server to improve the system's accuracy and train the sentiment engine, which helps in future analyses and recommendations.

[0334] (Example 2)

[0335] 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".

[0336] For many companies, streamlining business processes is a critical issue. However, analyzing business data and improving processes requires specialized knowledge, and proposing appropriate improvement measures that take into account employee emotions and workload is difficult. Therefore, there is a need for the development of automation systems that comprehensively consider the diverse elements of business operations.

[0337] 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.

[0338] In this invention, the server includes means for analyzing business process data using a generative model, means for predicting areas for business improvement based on the analysis results, and means for analyzing user sentiment data using a sentiment analysis engine and evaluating the need for business improvement. This enables comprehensive analysis of business processes based on business data and sentiment data, as well as concrete proposals for improvement and automation.

[0339] A "generative model" is a model that uses machine learning techniques to extract patterns from large datasets and then generates new data or analyzes existing data.

[0340] A "business process" refers to a series of business activities carried out within an organization, and is something that can be made more efficient or improved.

[0341] An "emotion analysis engine" is a technology that analyzes emotional data collected from users, evaluates trends and states, and uses this information to propose improvements to business operations.

[0342] "Data normalization" is the process of converting data recorded in different formats and units into a unified format, making it suitable for analysis.

[0343] "Predicting areas for business improvement" is the act of identifying specific improvement items to enhance the efficiency and effectiveness of current business processes, based on analyzed data.

[0344] "Automation" is a process that aims to improve efficiency and reduce errors by using technology to automate tasks that are currently performed manually.

[0345] "Effectiveness measurement" is the act of measuring how much success an implemented process improvement measure has brought about.

[0346] This invention is a system that combines a generative AI model and an emotion analysis engine to improve the efficiency and effectiveness of business processes. The embodiments are described in detail below.

[0347] The server retrieves business data and user feedback from the information management system using APIs and database queries. It then uses software to normalize this data and convert it into a unified format. This process utilizes universally accepted data management tools to maintain data integrity.

[0348] The terminal analyzes the normalized data through a generative AI model. This generative model identifies patterns and bottlenecks within the workflow and extracts areas for improvement to streamline processes. In parallel, a sentiment analysis engine analyzes the user's emotional data and assesses the need for business process improvement. If the user is experiencing stress in the workflow, specific improvement suggestions are formed at this stage.

[0349] As a concrete example, consider a digital marketing company implementing this system. They analyze employee work data to identify the reasons for declining advertising campaign effectiveness. In this process, emotional data might indicate that "the campaign content needs to be reviewed." Based on these results, a generative model develops a new campaign strategy, thereby improving advertising effectiveness.

[0350] Another example of a prompt is: "Analyze the company's internal business processes and generate specific suggestions to improve operational efficiency and user satisfaction."

[0351] This system enables sustainable organizational management by systematizing the improvement of operational efficiency and the work environment.

[0352] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0353] Step 1:

[0354] The server collects business data and user feedback from the information management system using APIs and database queries. Input consists of unstandardized data from various systems, and output is a set of raw data before processing. In this process, the server also acquires operation logs and feedback form information, collecting both quantitative and qualitative sentiment data related to actual business operations.

[0355] Step 2:

[0356] The server performs a process to normalize the collected data. The input is raw data before processing, and the output is standardized data in a unified format. Specifically, it performs tasks such as unifying different date formats and converting sentiment feedback into numerical scores. This conversion ensures that the data can be handled consistently in subsequent analysis processes.

[0357] Step 3:

[0358] The terminal receives normalized data and performs data analysis by applying a generative AI model. The input is a standardized dataset, and the output is analysis results and improvement suggestions regarding patterns and bottlenecks within the business flow. Specifically, it uses a pattern recognition algorithm to identify efficiency trends in the data and identify areas that need improvement.

[0359] Step 4:

[0360] The device uses an emotion analysis engine to analyze the user's emotional data in detail. The input is the user's emotion score, and the output is a determination of the urgency of business improvement based on emotional tendencies. For example, it can pinpoint the points where the user is experiencing stress and identify the business process that is causing it.

[0361] Step 5:

[0362] Based on the analysis results described above, the server predicts areas for improvement in business processes and proposes automation. The input consists of the results of a generative model and sentiment analysis engine, while the output is a list of automatable business processes and suggestions for task reallocation. Specifically, it generates automation proposals for routine data entry and report creation tasks, aiming to improve operational efficiency.

[0363] Step 6:

[0364] Users automate business processes based on improvements suggested by the server. The input is the server's automation suggestions, and the output is the highly automated business process. Specific implementations include introducing a "tool for automatically generating standardized text" to significantly reduce email response time.

[0365] Step 7:

[0366] The server measures the effectiveness of automated processes performed by users and analyzes performance metrics. Input is automated business data, and output is reports on improvements in operational efficiency and employee satisfaction. Based on the measurement results, further improvements and adjustments are made to achieve continuous optimization.

[0367] (Application Example 2)

[0368] 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."

[0369] In factory operations, there is a need to improve efficiency while reducing the burden on workers. However, currently, excessive workloads are placed on workers in order to increase productivity, which is resulting in a decline in quality and a deterioration of the working environment. Furthermore, there is a problem that the optimization of work processes has reached its limits because workers' emotions and stress are not taken into consideration.

[0370] 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.

[0371] In this invention, the server includes means for analyzing business process data using a generative model, means for predicting areas for improvement in business operations based on the analysis results, means for automating business processes based on the predicted areas for improvement, means for sentiment analysis for collecting and analyzing sentiment data, and means for making suggestions to adjust the workload using the sentiment analysis results. This enables both increased efficiency in business processes and reduced burden on workers, resulting in a better work environment and improved productivity.

[0372] A "generative model" is a machine learning algorithm that learns patterns and trends from data and generates new information.

[0373] A "business process" refers to a series of tasks and procedures within a company or organization, and is a method for carrying out activities efficiently.

[0374] "Analyzing" refers to the method of examining documents and data to understand their contents in detail.

[0375] "Areas for improvement" refers to parts of the current process or system that need improvement to enhance efficiency or effectiveness.

[0376] "Automating" means carrying out tasks or processes without human intervention, and being operated by machines or programs.

[0377] "Emotional data" refers to a representation of an individual's emotions and psychological state, converted into numerical values ​​and information.

[0378] "Analysis results" refer to the conclusions and insights obtained after analyzing data.

[0379] To "make a proposal" means to present new ideas or solutions regarding improvements to specific methods or processes.

[0380] In embodiments for carrying out this invention, a detailed explanation will be provided mainly for three elements: the server, the terminal, and the user.

[0381] The server incorporates a data collection module for gathering various data from within the factory. Specifically, it can collect data from various sensors installed in the factory and feedback from workers via APIs. The collected data is then normalized, integrated into a consistent format, and analyzed by a generative AI model. The generative AI model identifies bottlenecks and inefficiencies in business processes and predicts areas for improvement. This process utilizes data processing software running on the server.

[0382] The terminal displays data analyzed by a generated AI model and worker emotion data obtained using an emotion analysis engine. This allows users to check the worker's psychological state in real time and adjust work processes as needed. The emotion analysis engine collects emotion data from specific operation logs and feedback and suggests process improvements based on the emotional state.

[0383] Based on these analysis results and sentiment data, users can automate business processes. For example, when automation suggestions are made via a terminal, they can adjust worker break times or optimize production by robots. This simultaneously improves the efficiency of the entire business process and reduces the burden on workers, thereby improving the workplace environment.

[0384] As a concrete example, consider a business improvement that occurred on an assembly line for a certain part. In this case, the generative model analyzes data from the entire line and identifies that worker fatigue is high during specific time periods. As a result, the server, based on the analysis data from the emotion engine, proposes shift adjustments to automate processes using robots and allow workers to take breaks. An example of a prompt would be, "Based on the following dataset, evaluate the workers' stress levels and propose improvements to the production schedule."

[0385] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0386] Step 1:

[0387] The server collects operational data from sensors within the factory and worker feedback, and retrieves it via an API. Inputs are real-time data from sensors and worker feedback, while outputs are normalized data in a unified format. After collection, the data is normalized, noise is removed, and it is integrated into a format suitable for analysis.

[0388] Step 2:

[0389] The server inputs the normalized business data into a generation AI model to analyze the business process. The input is the data integrated in the previous step, and the output is the identification of bottlenecks and patterns in the business flow. In this process, machine learning algorithms extract features from the data and identify areas where business improvements are needed.

[0390] Step 3:

[0391] The server collects emotional data based on the analysis results and performs analysis using an emotional analysis engine. The input is emotional feedback data, and the output is an evaluation of the worker's psychological state and stress level. Based on this data, it detects when the workload is excessive and prepares appropriate improvement suggestions.

[0392] Step 4:

[0393] The terminal receives analysis results sent from the server and notifies the user in real time. Input is data sent from the server, and output is a visualized list of suggested work improvements displayed on the user's screen. It proposes work schedules that take into account the worker's emotional state and presents concrete action plans.

[0394] Step 5:

[0395] The user automates business processes based on the suggestions provided. Inputs are the schedule and improvement suggestions displayed on the terminal, and output is the adjusted business flow. This increases automation by robots and reduces the burden on workers. Specifically, the user uses the terminal to adjust shifts and, if necessary, changes the robot's operating time.

[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 technology for automating and optimizing various business processes within an enterprise using generative models. The following describes embodiments for carrying out the invention.

[0413] Data collection and preprocessing

[0414] The server collects data from multiple business systems within a company, such as human resources, finance, and logistics. This data is retrieved periodically using APIs and database queries. Next, the terminal preprocesses the collected data. By cleaning, normalizing, and integrating information from different data sources, a unified dataset is created. This preprocessing ensures the data consistency necessary for subsequent analysis.

[0415] Analysis and prediction using generative models

[0416] The server inputs pre-processed data into a generative model to analyze business processes. The generative model learns from historical data to identify bottlenecks and inefficiencies in the business. It also predicts areas for future improvement, enabling proactive measures. For example, the server might predict that manual operations in the monthly report creation process need to be reduced.

[0417] Implementation of automation

[0418] Users review improvement suggestions provided by the server and implement automation of business processes. For example, by introducing Robotic Process Automation (RPA) to automate the input of HR data, data entry errors can be reduced and processing time shortened. Implementing these suggestions results in substantial efficiency improvements and cost reductions.

[0419] Effectiveness measurement and feedback

[0420] After the improvement measures are implemented, the user measures their effectiveness. The server provides metrics for measuring effectiveness, and the user compares and evaluates whether the proposed effects were achieved. For example, metrics such as reductions in processing time and costs, and reductions in errors are used. This evaluation result is returned to the server as feedback and used to further improve the generative model.

[0421] In this way, the present invention enables the efficient and effective automation and optimization of corporate business processes.

[0422] The following describes the processing flow.

[0423] Step 1:

[0424] The server collects data from various business systems within the company. It utilizes API calls and database queries to automatically extract data according to a specified schedule. Furthermore, the collected data is validated to check for outliers and missing values.

[0425] Step 2:

[0426] The terminal performs preprocessing of the collected data. Specifically, it cleans the data, appropriately imputing missing values ​​and removing outliers. Then, it normalizes the dataset, standardizing numerical data of different scales. Furthermore, it integrates information from multiple data sources to create a consistent dataset.

[0427] Step 3:

[0428] The server inputs pre-processed data into a generative model for analysis. The generative model analyzes business processes and identifies bottlenecks and inefficient processes. Next, it makes predictions based on the analysis results to identify processes that will need improvement in the future and areas that can be automated.

[0429] Step 4:

[0430] The server generates specific business improvement proposals based on the analysis results. During this process, it performs various simulations to predict the effects of implementing the proposals. It then notifies the user of the improvement proposals and provides specific instructions regarding the automation of business processes.

[0431] Step 5:

[0432] Users review the suggestions from the server and implement improvements to their business processes. For example, they may implement proposed automations by changing system settings or modifying business procedures. They may also consider introducing external tools or RPA as needed.

[0433] Step 6:

[0434] After improvements are implemented, the server collects various data again to measure their effectiveness. Based on the collected data, it quantitatively evaluates the effectiveness of the improvement proposals. Specifically, it calculates the process efficiency rate and the amount of cost reduction.

[0435] Step 7:

[0436] The user reviews the results of the performance measurement provided by the server and evaluates whether the improvements were made appropriately. The evaluation results are provided to the server as feedback to be used in considering further improvement measures in the future. Based on this, the server adjusts the parameters of the generative model to improve the accuracy of subsequent analyses.

[0437] (Example 1)

[0438] 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."

[0439] In modern business operations, the importance of streamlining and automating business processes is increasing. However, collecting information from multiple sources within a company and integrating it into a consistent dataset is time-consuming, and manual analysis and prediction can be inaccurate. Furthermore, actually measuring the effects of improvement measures and incorporating continuous feedback into generative models is extremely difficult. This invention aims to solve these problems and provide a means for efficiently and accurately optimizing and automating business processes.

[0440] 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.

[0441] In this invention, the server includes means for analyzing business procedure data using a generative model, means for acquiring data from different sources and preprocessing the data into a consistent data set, and means for predicting areas for improvement in business operations based on the analysis results. This makes it possible to automate the integration and analysis of information and the streamlining of operations, and to feed the results back into the generative model.

[0442] An "information processing device" is a computer system used for data collection, analysis, and integration, and it has the function of automatically optimizing operations using generative models.

[0443] A "generative model" is a mathematical model that uses machine learning algorithms to learn data patterns and predict improvements and enhancements to business processes.

[0444] A "data set" is a collection of data obtained from different sources that has been unified, organized, and given consistency.

[0445] "Business procedures" refer to the series of processes and activities that a company performs in its daily operations, and optimizing these procedures is key to improving operational efficiency.

[0446] "Analysis results" refer to information obtained through data analysis using generative models that indicates bottlenecks and areas for improvement in business operations.

[0447] "Resource reduction effect" refers to the amount of resource reduction, such as time, costs, and human effort, achieved through the automation of business procedures, as well as the improvement in efficiency.

[0448] "Feedback" refers to information used to improve the accuracy of an automated business process by returning evaluation results regarding its effectiveness and areas for improvement to the generative model.

[0449] A description of the embodiment for carrying out the invention will be provided.

[0450] This system aims to streamline and automate business procedures within a company. The server functions as an information processing unit, handling data collection, analysis, and the operation of generative models. Specifically, the hardware requires server equipment with a high-performance processor, and the software includes a database management system and a framework for implementing machine learning models.

[0451] The server first collects data from the company's business systems using APIs and database queries. Then, the terminal receives the collected data, cleans and normalizes it, and builds a unified data set. This ensures that data from different sources is processed in a consistent format.

[0452] Pre-processed data is input into a generative AI model by the server. This generative model includes, for example, a deep learning algorithm based on historical business process data. This model has the ability to identify bottlenecks and inefficiencies in business processes and propose specific improvement measures to the user. If the user accepts these suggestions, the business procedures are automated.

[0453] As a concrete example, let's consider a way to reduce manual operations when creating monthly reports. In this case, we can input the text "Please suggest ways to automate and streamline the manual parts of the monthly report creation process" as a prompt into the AI ​​model and obtain improvement suggestions.

[0454] Based on improvement suggestions from the server, users implement automation procedures they deem feasible. This results in substantial operational efficiency and cost reduction. After the improvements are implemented, the server evaluates their effectiveness and feeds the evaluation results back into the generative model, further improving the model's accuracy.

[0455] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0456] Step 1:

[0457] The server collects data from the company's business systems. Specifically, it periodically retrieves HR data, financial data, logistics data, etc., using APIs and database queries. The input for this step is the database of each business system, and the output is raw data stored in the server's temporary storage. The server extracts the necessary data points and prepares them for use in subsequent processing.

[0458] Step 2:

[0459] The terminal preprocesses the raw data received from the server. Specifically, it performs data cleaning, removing duplicate data and correcting outliers. It also normalizes data from different sources and converts it into a unified format. The input is the collected raw data, and the output is a clean and consistent data set. Through this processing, the terminal guarantees the reliability and consistency of the data.

[0460] Step 3:

[0461] The server inputs pre-processed data into a generative AI model. The generative model has the ability to analyze bottlenecks and inefficiencies in business processes based on past operational data and propose future improvement measures. The input is a set of pre-processed data, and the output is specific suggestions for business improvement. For example, it might suggest automating a time-consuming report generation process.

[0462] Step 4:

[0463] The user reviews the improvement suggestions provided by the server and selects those that are feasible. Next, they automate business procedures based on those suggestions. A specific example might be automating manual data entry tasks using a suggested RPA tool. The input is the improvement suggestions from the server, and the output is the automated business procedure. This improves the user's work efficiency.

[0464] Step 5:

[0465] After the improvement measures are implemented, the user evaluates their effectiveness. The server provides evaluation metrics for measuring effectiveness. The user measures the effectiveness based on factors such as reductions in processing time and cost, and a decrease in error rate, and feeds the evaluation results back to the server. The input is the automated business data, and the output is an evaluation report and feedback to the generative model. This feedback helps to improve the accuracy of the generative model.

[0466] (Application Example 1)

[0467] 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."

[0468] In modern manufacturing, multiple production lines exist, and the goal is to maximize the efficiency of each. However, manual process control and inefficient bottlenecks often occur throughout the entire production line, leading to decreased productivity. Furthermore, the lack of automated work instructions to quickly resolve these problems limits long-term cost reductions and efficiency improvements.

[0469] 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.

[0470] In this invention, the server includes means for analyzing business procedure data using a generative model, means for predicting areas for improvement in the business based on the analysis results, means for automating the business procedures based on the predicted areas for improvement, and means for automatically generating and distributing work instructions to improve the efficiency of manufacturing operations. This makes it possible to quickly identify and resolve bottlenecks in the manufacturing line, thereby improving production efficiency and reducing costs.

[0471] A "generative model" is an algorithm that learns past patterns based on collected data and uses that knowledge to make predictions and analyses about new data situations.

[0472] "Business procedures" refer to a set of work flows or processes defined within an organization or system to achieve a specific objective.

[0473] "Analysis results" refer to the information and insights obtained from data analyzed using generative models, and serve as important guidelines for business improvement.

[0474] "Areas for improvement" refers to parts or elements in business procedures that need to be changed or adjusted in order to improve efficiency or effectiveness.

[0475] "Automation" refers to the process of autonomously performing tasks and processes that were previously done manually, using digital technology and machinery.

[0476] "Work instructions" are instructional documents or information that summarize the procedures and points to be followed in a specific task or operation.

[0477] "Improving the efficiency of manufacturing operations" refers to measures taken to improve the productivity of the entire manufacturing process, reduce waste, and enhance quality.

[0478] To realize this invention, a server first collects data from multiple manufacturing lines. This data includes information such as the operating status of the manufacturing lines, material flow, and energy consumption. The data is acquired through sensors and IoT devices and integrated in real time using Apache Kafka.

[0479] Next, the server preprocesses the data. This involves cleaning and shaping the data using the Python pandas library, generating a clean and consistent dataset.

[0480] The generative AI model is built using TensorFlow or PyTorch. By inputting pre-processed data into this model, it analyzes business procedures, identifies bottlenecks, and predicts areas for improvement. Based on the analysis, the server automatically generates the necessary work instructions to improve the efficiency of manufacturing operations and distributes them to robots via the MQTT protocol.

[0481] As a result, users can quickly identify bottlenecks in their production lines and implement corrective measures in real time. For example, if material supply is delayed on a production line, the production model can identify the cause as a clogged pipe and issue instructions for maintenance in advance. In this way, production efficiency can be improved and unnecessary costs can be reduced.

[0482] An example of a prompt message is as follows:

[0483] "Please explain how to analyze factory production line data, identify bottlenecks in each work step, and optimize them in real time. Furthermore, please provide specific work instructions on what needs to be done to eliminate those bottlenecks."

[0484] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0485] Step 1:

[0486] The server collects data from each production line within the factory via sensors and IoT devices. Inputs include data on production line operation status, material flow, and energy consumption. This data is integrated using Apache Kafka to generate a real-time data stream. The output is an integrated dataset.

[0487] Step 2:

[0488] The server preprocesses the integrated dataset using the Python pandas library. It receives raw data requiring cleansing as input. Data cleaning involves removing outliers and normalizing the data. The data is then formatted into a consistent format, generating a well-formed dataset as output.

[0489] Step 3:

[0490] The server inputs a well-formed dataset into a generative AI model. The generative model, built using TensorFlow or PyTorch, analyzes the manufacturing line bottlenecks based on the data. The input is a pre-processed dataset, and the output is a prediction of identified bottlenecks and areas for improvement.

[0491] Step 4:

[0492] The server automatically generates work instructions necessary for improving the efficiency of manufacturing operations based on the analysis results from the generated AI model. The input is data predicting bottlenecks and areas for improvement. The generated work instructions include specific steps on which parts should be modified. As output, work instructions are prepared for distribution via the MQTT protocol.

[0493] Step 5:

[0494] The user receives work instructions delivered from the server and supervises and executes specific improvement tasks on the manufacturing line. The input is specific work instruction information. The output is the improvement actions taken in the actual manufacturing process, which leads to improved manufacturing efficiency.

[0495] 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.

[0496] This invention provides a system that effectively analyzes, predicts, and automates business processes by combining a generative model with an emotion engine. The embodiments for carrying out the invention are described in detail below.

[0497] Data collection and normalization

[0498] The server collects necessary data from various business systems within the company. During this process, it extracts information using APIs and database queries, while simultaneously obtaining user sentiment data. Sentiment data is acquired from user interface operation logs and feedback forms. The collected data is normalized and integrated in a unified format.

[0499] Analysis using generative models and emotion engines

[0500] The terminal applies a generative model to normalized business and emotional data to perform detailed analysis. The generative model identifies patterns and bottlenecks in the business flow. In addition, the emotional engine analyzes the user's emotional information and evaluates the need for business improvements based on the situation. For example, if a high workload is detected, the emotional engine will suggest ways to reduce the workload.

[0501] Predictions of areas for improvement

[0502] Based on analysis results from generative models and the sentiment engine, the server predicts areas for improvement in future business processes. These predictions offer users strategies to improve work efficiency and the work environment. Specifically, these include suggestions for automating parts of the workflow and reallocating tasks to reduce workload.

[0503] Process automation

[0504] Users automate business processes according to suggestions from the server. For example, they might implement tools to automate repetitive tasks and reduce working hours. They also improve work efficiency by reviewing processes and reallocating resources at appropriate times based on feedback from the emotional engine.

[0505] Effectiveness measurement and feedback

[0506] Subsequently, the server measures the effectiveness of the automated tasks and analyzes performance indicators. Users review the measurement results and evaluate the effectiveness of process improvements. This feedback is used to improve system accuracy and develop future business improvement measures. For example, this could include cases where business efficiency improves and user satisfaction increases.

[0507] This invention enables the simultaneous achievement of operational efficiency and improved work environment, thereby promoting the optimization of corporate operations.

[0508] The following describes the processing flow.

[0509] Step 1:

[0510] The server collects business data from various business systems within the company. It uses APIs and database queries to periodically retrieve necessary information. Simultaneously, it also acquires user sentiment data using a sentiment engine. Sentiment data is collected from operation logs and feedback forms on the user interface and recorded in conjunction with each business activity.

[0511] Step 2:

[0512] The terminal preprocesses the collected data. Data cleaning involves imputing missing values ​​with mean values ​​and removing outliers. Normalization standardizes data with different scales and adjusts the integrated dataset. Furthermore, it logically integrates data from different business systems and transforms it into an analyzable format in a consistent manner.

[0513] Step 3:

[0514] The server analyzes pre-processed data using a generative model. This analysis assesses the current state of business processes and identifies potential bottlenecks and inefficiencies. Next, it utilizes an emotion engine to measure work stress and burden based on user emotion data and evaluates the impact on the work environment.

[0515] Step 4:

[0516] The server generates specific business improvement suggestions based on the analysis results of the generative model and the sentiment engine. These suggestions include tasks that can be automated, tasks that need improvement, and measures to improve user experience based on sentiment data. The suggestions are communicated to the user and used as specific guidelines for business improvement.

[0517] Step 5:

[0518] Users implement improvement suggestions provided by the server. This includes introducing automation tools, reviewing and streamlining work procedures, and taking measures to optimize workloads and reduce employee stress based on insights from the emotion engine.

[0519] Step 6:

[0520] The server remeasures business performance after improvements have been implemented. It analyzes the efficiency gains and cost reductions from the newly collected data, quantitatively evaluating the effectiveness of the business improvements. The measurement results are automatically generated and presented to the user.

[0521] Step 7:

[0522] Users receive the server's analysis results and evaluate whether their business improvements were successful. Based on this feedback, they reconsider areas that require further improvement. This feedback is sent back to the server to improve the system's accuracy and train the sentiment engine, which helps in future analyses and recommendations.

[0523] (Example 2)

[0524] 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."

[0525] For many companies, streamlining business processes is a critical issue. However, analyzing business data and improving processes requires specialized knowledge, and proposing appropriate improvement measures that take into account employee emotions and workload is difficult. Therefore, there is a need for the development of automation systems that comprehensively consider the diverse elements of business operations.

[0526] 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.

[0527] In this invention, the server includes means for analyzing business process data using a generative model, means for predicting areas for business improvement based on the analysis results, and means for analyzing user sentiment data using a sentiment analysis engine and evaluating the need for business improvement. This enables comprehensive analysis of business processes based on business data and sentiment data, as well as concrete proposals for improvement and automation.

[0528] A "generative model" is a model that uses machine learning techniques to extract patterns from large datasets and then generates new data or analyzes existing data.

[0529] A "business process" refers to a series of business activities carried out within an organization, and is something that can be made more efficient or improved.

[0530] An "emotion analysis engine" is a technology that analyzes emotional data collected from users, evaluates trends and states, and uses this information to propose improvements to business operations.

[0531] "Data normalization" is the process of converting data recorded in different formats and units into a unified format, making it suitable for analysis.

[0532] "Predicting areas for business improvement" is the act of identifying specific improvement items to enhance the efficiency and effectiveness of current business processes, based on analyzed data.

[0533] "Automation" is a process that aims to improve efficiency and reduce errors by using technology to automate tasks that are currently performed manually.

[0534] "Effectiveness measurement" is the act of measuring how much success an implemented process improvement measure has brought about.

[0535] This invention is a system that combines a generative AI model and an emotion analysis engine to improve the efficiency and effectiveness of business processes. The embodiments are described in detail below.

[0536] The server retrieves business data and user feedback from the information management system using APIs and database queries. It then uses software to normalize this data and convert it into a unified format. This process utilizes universally accepted data management tools to maintain data integrity.

[0537] The terminal analyzes the normalized data through a generative AI model. This generative model identifies patterns and bottlenecks within the workflow and extracts areas for improvement to streamline processes. In parallel, a sentiment analysis engine analyzes the user's emotional data and assesses the need for business process improvement. If the user is experiencing stress in the workflow, specific improvement suggestions are formed at this stage.

[0538] As a concrete example, consider a digital marketing company implementing this system. They analyze employee work data to identify the reasons for declining advertising campaign effectiveness. In this process, emotional data might indicate that "the campaign content needs to be reviewed." Based on these results, a generative model develops a new campaign strategy, thereby improving advertising effectiveness.

[0539] Another example of a prompt is: "Analyze the company's internal business processes and generate specific suggestions to improve operational efficiency and user satisfaction."

[0540] This system enables sustainable organizational management by systematizing the improvement of operational efficiency and the work environment.

[0541] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0542] Step 1:

[0543] The server collects business data and user feedback from the information management system using APIs and database queries. Input consists of unstandardized data from various systems, and output is a set of raw data before processing. In this process, the server also acquires operation logs and feedback form information, collecting both quantitative and qualitative sentiment data related to actual business operations.

[0544] Step 2:

[0545] The server performs a process to normalize the collected data. The input is raw data before processing, and the output is standardized data in a unified format. Specifically, it performs tasks such as unifying different date formats and converting sentiment feedback into numerical scores. This conversion ensures that the data can be handled consistently in subsequent analysis processes.

[0546] Step 3:

[0547] The terminal receives normalized data and performs data analysis by applying a generative AI model. The input is a standardized dataset, and the output is analysis results and improvement suggestions regarding patterns and bottlenecks within the business flow. Specifically, it uses a pattern recognition algorithm to identify efficiency trends in the data and identify areas that need improvement.

[0548] Step 4:

[0549] The device uses an emotion analysis engine to analyze the user's emotional data in detail. The input is the user's emotion score, and the output is a determination of the urgency of business improvement based on emotional tendencies. For example, it can pinpoint the points where the user is experiencing stress and identify the business process that is causing it.

[0550] Step 5:

[0551] Based on the analysis results described above, the server predicts areas for improvement in business processes and proposes automation. The input consists of the results of a generative model and sentiment analysis engine, while the output is a list of automatable business processes and suggestions for task reallocation. Specifically, it generates automation proposals for routine data entry and report creation tasks, aiming to improve operational efficiency.

[0552] Step 6:

[0553] Users automate business processes based on improvements suggested by the server. The input is the server's automation suggestions, and the output is the highly automated business process. Specific implementations include introducing a "tool for automatically generating standardized text" to significantly reduce email response time.

[0554] Step 7:

[0555] The server measures the effectiveness of automated processes performed by users and analyzes performance metrics. Input is automated business data, and output is reports on improvements in operational efficiency and employee satisfaction. Based on the measurement results, further improvements and adjustments are made to achieve continuous optimization.

[0556] (Application Example 2)

[0557] 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."

[0558] In factory operations, there is a need to improve efficiency while reducing the burden on workers. However, currently, excessive workloads are placed on workers in order to increase productivity, which is resulting in a decline in quality and a deterioration of the working environment. Furthermore, there is a problem that the optimization of work processes has reached its limits because workers' emotions and stress are not taken into consideration.

[0559] 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.

[0560] In this invention, the server includes means for analyzing business process data using a generative model, means for predicting areas for improvement in business operations based on the analysis results, means for automating business processes based on the predicted areas for improvement, means for sentiment analysis for collecting and analyzing sentiment data, and means for making suggestions to adjust the workload using the sentiment analysis results. This enables both increased efficiency in business processes and reduced burden on workers, resulting in a better work environment and improved productivity.

[0561] A "generative model" is a machine learning algorithm that learns patterns and trends from data and generates new information.

[0562] A "business process" refers to a series of tasks and procedures within a company or organization, and is a method for carrying out activities efficiently.

[0563] "Analyzing" refers to the method of examining documents and data to understand their contents in detail.

[0564] "Areas for improvement" refers to parts of the current process or system that need improvement to enhance efficiency or effectiveness.

[0565] "Automating" means carrying out tasks or processes without human intervention, and being operated by machines or programs.

[0566] "Emotional data" refers to a representation of an individual's emotions and psychological state, converted into numerical values ​​and information.

[0567] "Analysis results" refer to the conclusions and insights obtained after analyzing data.

[0568] To "make a proposal" means to present new ideas or solutions regarding improvements to specific methods or processes.

[0569] In embodiments for carrying out this invention, a detailed explanation will be provided mainly for three elements: the server, the terminal, and the user.

[0570] The server incorporates a data collection module for gathering various data from within the factory. Specifically, it can collect data from various sensors installed in the factory and feedback from workers via APIs. The collected data is then normalized, integrated into a consistent format, and analyzed by a generative AI model. The generative AI model identifies bottlenecks and inefficiencies in business processes and predicts areas for improvement. This process utilizes data processing software running on the server.

[0571] The terminal displays data analyzed by a generated AI model and worker emotion data obtained using an emotion analysis engine. This allows users to check the worker's psychological state in real time and adjust work processes as needed. The emotion analysis engine collects emotion data from specific operation logs and feedback and suggests process improvements based on the emotional state.

[0572] Based on these analysis results and sentiment data, users can automate business processes. For example, when automation suggestions are made via a terminal, they can adjust worker break times or optimize production by robots. This simultaneously improves the efficiency of the entire business process and reduces the burden on workers, thereby improving the workplace environment.

[0573] As a concrete example, consider a business improvement that occurred on an assembly line for a certain part. In this case, the generative model analyzes data from the entire line and identifies that worker fatigue is high during specific time periods. As a result, the server, based on the analysis data from the emotion engine, proposes shift adjustments to automate processes using robots and allow workers to take breaks. An example of a prompt would be, "Based on the following dataset, evaluate the workers' stress levels and propose improvements to the production schedule."

[0574] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0575] Step 1:

[0576] The server collects operational data from sensors within the factory and worker feedback, and retrieves it via an API. Inputs are real-time data from sensors and worker feedback, while outputs are normalized data in a unified format. After collection, the data is normalized, noise is removed, and it is integrated into a format suitable for analysis.

[0577] Step 2:

[0578] The server inputs the normalized business data into a generation AI model to analyze the business process. The input is the data integrated in the previous step, and the output is the identification of bottlenecks and patterns in the business flow. In this process, machine learning algorithms extract features from the data and identify areas where business improvements are needed.

[0579] Step 3:

[0580] The server collects emotional data based on the analysis results and performs analysis using an emotional analysis engine. The input is emotional feedback data, and the output is an evaluation of the worker's psychological state and stress level. Based on this data, it detects when the workload is excessive and prepares appropriate improvement suggestions.

[0581] Step 4:

[0582] The terminal receives analysis results sent from the server and notifies the user in real time. Input is data sent from the server, and output is a visualized list of suggested work improvements displayed on the user's screen. It proposes work schedules that take into account the worker's emotional state and presents concrete action plans.

[0583] Step 5:

[0584] The user automates business processes based on the suggestions provided. Inputs are the schedule and improvement suggestions displayed on the terminal, and output is the adjusted business flow. This increases automation by robots and reduces the burden on workers. Specifically, the user uses the terminal to adjust shifts and, if necessary, changes the robot's operating time.

[0585] 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.

[0586] 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.

[0587] 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.

[0588] [Fourth Embodiment]

[0589] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0590] 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.

[0591] 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).

[0592] 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.

[0593] 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.

[0594] 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).

[0595] 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.

[0596] 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.

[0597] 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.

[0598] 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.

[0599] 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.

[0600] 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.

[0601] 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".

[0602] This invention provides a technology for automating and optimizing various business processes within an enterprise using generative models. The following describes embodiments for carrying out the invention.

[0603] Data collection and preprocessing

[0604] The server collects data from multiple business systems within a company, such as human resources, finance, and logistics. This data is retrieved periodically using APIs and database queries. Next, the terminal preprocesses the collected data. By cleaning, normalizing, and integrating information from different data sources, a unified dataset is created. This preprocessing ensures the data consistency necessary for subsequent analysis.

[0605] Analysis and prediction using generative models

[0606] The server inputs pre-processed data into a generative model to analyze business processes. The generative model learns from historical data to identify bottlenecks and inefficiencies in the business. It also predicts areas for future improvement, enabling proactive measures. For example, the server might predict that manual operations in the monthly report creation process need to be reduced.

[0607] Implementation of automation

[0608] Users review improvement suggestions provided by the server and implement automation of business processes. For example, by introducing Robotic Process Automation (RPA) to automate the input of HR data, data entry errors can be reduced and processing time shortened. Implementing these suggestions results in substantial efficiency improvements and cost reductions.

[0609] Effectiveness measurement and feedback

[0610] After the improvement measures are implemented, the user measures their effectiveness. The server provides metrics for measuring effectiveness, and the user compares and evaluates whether the proposed effects were achieved. For example, metrics such as reductions in processing time and costs, and reductions in errors are used. This evaluation result is returned to the server as feedback and used to further improve the generative model.

[0611] In this way, the present invention enables the efficient and effective automation and optimization of corporate business processes.

[0612] The following describes the processing flow.

[0613] Step 1:

[0614] The server collects data from various business systems within the company. It utilizes API calls and database queries to automatically extract data according to a specified schedule. Furthermore, the collected data is validated to check for outliers and missing values.

[0615] Step 2:

[0616] The terminal performs preprocessing of the collected data. Specifically, it cleans the data, appropriately imputing missing values ​​and removing outliers. Then, it normalizes the dataset, standardizing numerical data of different scales. Furthermore, it integrates information from multiple data sources to create a consistent dataset.

[0617] Step 3:

[0618] The server inputs pre-processed data into a generative model for analysis. The generative model analyzes business processes and identifies bottlenecks and inefficient processes. Next, it makes predictions based on the analysis results to identify processes that will need improvement in the future and areas that can be automated.

[0619] Step 4:

[0620] The server generates specific business improvement proposals based on the analysis results. During this process, it performs various simulations to predict the effects of implementing the proposals. It then notifies the user of the improvement proposals and provides specific instructions regarding the automation of business processes.

[0621] Step 5:

[0622] Users review the suggestions from the server and implement improvements to their business processes. For example, they may implement proposed automations by changing system settings or modifying business procedures. They may also consider introducing external tools or RPA as needed.

[0623] Step 6:

[0624] After improvements are implemented, the server collects various data again to measure their effectiveness. Based on the collected data, it quantitatively evaluates the effectiveness of the improvement proposals. Specifically, it calculates the process efficiency rate and the amount of cost reduction.

[0625] Step 7:

[0626] The user reviews the results of the performance measurement provided by the server and evaluates whether the improvements were made appropriately. The evaluation results are provided to the server as feedback to be used in considering further improvement measures in the future. Based on this, the server adjusts the parameters of the generative model to improve the accuracy of subsequent analyses.

[0627] (Example 1)

[0628] 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".

[0629] In modern business operations, the importance of streamlining and automating business processes is increasing. However, collecting information from multiple sources within a company and integrating it into a consistent dataset is time-consuming, and manual analysis and prediction can be inaccurate. Furthermore, actually measuring the effects of improvement measures and incorporating continuous feedback into generative models is extremely difficult. This invention aims to solve these problems and provide a means for efficiently and accurately optimizing and automating business processes.

[0630] 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.

[0631] In this invention, the server includes means for analyzing business procedure data using a generative model, means for acquiring data from different sources and preprocessing the data into a consistent data set, and means for predicting areas for improvement in business operations based on the analysis results. This makes it possible to automate the integration and analysis of information and the streamlining of operations, and to feed the results back into the generative model.

[0632] An "information processing device" is a computer system used for data collection, analysis, and integration, and it has the function of automatically optimizing operations using generative models.

[0633] A "generative model" is a mathematical model that uses machine learning algorithms to learn data patterns and predict improvements and enhancements to business processes.

[0634] A "data set" is a collection of data obtained from different sources that has been unified, organized, and given consistency.

[0635] "Business procedures" refer to the series of processes and activities that a company performs in its daily operations, and optimizing these procedures is key to improving operational efficiency.

[0636] "Analysis results" refer to information obtained through data analysis using generative models that indicates bottlenecks and areas for improvement in business operations.

[0637] "Resource reduction effect" refers to the amount of resource reduction, such as time, costs, and human effort, achieved through the automation of business procedures, as well as the improvement in efficiency.

[0638] "Feedback" refers to information used to improve the accuracy of an automated business process by returning evaluation results regarding its effectiveness and areas for improvement to the generative model.

[0639] A description of the embodiment for carrying out the invention will be provided.

[0640] This system aims to streamline and automate business procedures within a company. The server functions as an information processing unit, handling data collection, analysis, and the operation of generative models. Specifically, the hardware requires server equipment with a high-performance processor, and the software includes a database management system and a framework for implementing machine learning models.

[0641] The server first collects data from the company's business systems using APIs and database queries. Then, the terminal receives the collected data, cleans and normalizes it, and builds a unified data set. This ensures that data from different sources is processed in a consistent format.

[0642] Pre-processed data is input into a generative AI model by the server. This generative model includes, for example, a deep learning algorithm based on historical business process data. This model has the ability to identify bottlenecks and inefficiencies in business processes and propose specific improvement measures to the user. If the user accepts these suggestions, the business procedures are automated.

[0643] As a concrete example, let's consider a way to reduce manual operations when creating monthly reports. In this case, we can input the text "Please suggest ways to automate and streamline the manual parts of the monthly report creation process" as a prompt into the AI ​​model and obtain improvement suggestions.

[0644] Based on improvement suggestions from the server, users implement automation procedures they deem feasible. This results in substantial operational efficiency and cost reduction. After the improvements are implemented, the server evaluates their effectiveness and feeds the evaluation results back into the generative model, further improving the model's accuracy.

[0645] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0646] Step 1:

[0647] The server collects data from the company's business systems. Specifically, it periodically retrieves HR data, financial data, logistics data, etc., using APIs and database queries. The input for this step is the database of each business system, and the output is raw data stored in the server's temporary storage. The server extracts the necessary data points and prepares them for use in subsequent processing.

[0648] Step 2:

[0649] The terminal preprocesses the raw data received from the server. Specifically, it performs data cleaning, removing duplicate data and correcting outliers. It also normalizes data from different sources and converts it into a unified format. The input is the collected raw data, and the output is a clean and consistent data set. Through this processing, the terminal guarantees the reliability and consistency of the data.

[0650] Step 3:

[0651] The server inputs pre-processed data into a generative AI model. The generative model has the ability to analyze bottlenecks and inefficiencies in business processes based on past operational data and propose future improvement measures. The input is a set of pre-processed data, and the output is specific suggestions for business improvement. For example, it might suggest automating a time-consuming report generation process.

[0652] Step 4:

[0653] The user reviews the improvement suggestions provided by the server and selects those that are feasible. Next, they automate business procedures based on those suggestions. A specific example might be automating manual data entry tasks using a suggested RPA tool. The input is the improvement suggestions from the server, and the output is the automated business procedure. This improves the user's work efficiency.

[0654] Step 5:

[0655] After the improvement measures are implemented, the user evaluates their effectiveness. The server provides evaluation metrics for measuring effectiveness. The user measures the effectiveness based on factors such as reductions in processing time and cost, and a decrease in error rate, and feeds the evaluation results back to the server. The input is the automated business data, and the output is an evaluation report and feedback to the generative model. This feedback helps to improve the accuracy of the generative model.

[0656] (Application Example 1)

[0657] 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".

[0658] In modern manufacturing, multiple production lines exist, and the goal is to maximize the efficiency of each. However, manual process control and inefficient bottlenecks often occur throughout the entire production line, leading to decreased productivity. Furthermore, the lack of automated work instructions to quickly resolve these problems limits long-term cost reductions and efficiency improvements.

[0659] 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.

[0660] In this invention, the server includes means for analyzing business procedure data using a generative model, means for predicting areas for improvement in the business based on the analysis results, means for automating the business procedures based on the predicted areas for improvement, and means for automatically generating and distributing work instructions to improve the efficiency of manufacturing operations. This makes it possible to quickly identify and resolve bottlenecks in the manufacturing line, thereby improving production efficiency and reducing costs.

[0661] A "generative model" is an algorithm that learns past patterns based on collected data and uses that knowledge to make predictions and analyses about new data situations.

[0662] "Business procedures" refer to a set of work flows or processes defined within an organization or system to achieve a specific objective.

[0663] "Analysis results" refer to the information and insights obtained from data analyzed using generative models, and serve as important guidelines for business improvement.

[0664] "Areas for improvement" refers to parts or elements in business procedures that need to be changed or adjusted in order to improve efficiency or effectiveness.

[0665] "Automation" refers to the process of autonomously performing tasks and processes that were previously done manually, using digital technology and machinery.

[0666] "Work instructions" are instructional documents or information that summarize the procedures and points to be followed in a specific task or operation.

[0667] "Improving the efficiency of manufacturing operations" refers to measures taken to improve the productivity of the entire manufacturing process, reduce waste, and enhance quality.

[0668] To realize this invention, a server first collects data from multiple manufacturing lines. This data includes information such as the operating status of the manufacturing lines, material flow, and energy consumption. The data is acquired through sensors and IoT devices and integrated in real time using Apache Kafka.

[0669] Next, the server preprocesses the data. This involves cleaning and shaping the data using the Python pandas library, generating a clean and consistent dataset.

[0670] The generative AI model is built using TensorFlow or PyTorch. By inputting pre-processed data into this model, it analyzes business procedures, identifies bottlenecks, and predicts areas for improvement. Based on the analysis, the server automatically generates the necessary work instructions to improve the efficiency of manufacturing operations and distributes them to robots via the MQTT protocol.

[0671] As a result, users can quickly identify bottlenecks in their production lines and implement corrective measures in real time. For example, if material supply is delayed on a production line, the production model can identify the cause as a clogged pipe and issue instructions for maintenance in advance. In this way, production efficiency can be improved and unnecessary costs can be reduced.

[0672] An example of a prompt message is as follows:

[0673] "Please explain how to analyze factory production line data, identify bottlenecks in each work step, and optimize them in real time. Furthermore, please provide specific work instructions on what needs to be done to eliminate those bottlenecks."

[0674] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0675] Step 1:

[0676] The server collects data from each production line within the factory via sensors and IoT devices. Inputs include data on production line operation status, material flow, and energy consumption. This data is integrated using Apache Kafka to generate a real-time data stream. The output is an integrated dataset.

[0677] Step 2:

[0678] The server preprocesses the integrated dataset using the Python pandas library. It receives raw data requiring cleansing as input. Data cleaning involves removing outliers and normalizing the data. The data is then formatted into a consistent format, generating a well-formed dataset as output.

[0679] Step 3:

[0680] The server inputs a well-formed dataset into a generative AI model. The generative model, built using TensorFlow or PyTorch, analyzes the manufacturing line bottlenecks based on the data. The input is a pre-processed dataset, and the output is a prediction of identified bottlenecks and areas for improvement.

[0681] Step 4:

[0682] The server automatically generates work instructions necessary for improving the efficiency of manufacturing operations based on the analysis results from the generated AI model. The input is data predicting bottlenecks and areas for improvement. The generated work instructions include specific steps on which parts should be modified. As output, work instructions are prepared for distribution via the MQTT protocol.

[0683] Step 5:

[0684] The user receives work instructions delivered from the server and supervises and executes specific improvement tasks on the manufacturing line. The input is specific work instruction information. The output is the improvement actions taken in the actual manufacturing process, which leads to improved manufacturing efficiency.

[0685] 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.

[0686] This invention provides a system that effectively analyzes, predicts, and automates business processes by combining a generative model with an emotion engine. The embodiments for carrying out the invention are described in detail below.

[0687] Data collection and normalization

[0688] The server collects necessary data from various business systems within the company. During this process, it extracts information using APIs and database queries, while simultaneously obtaining user sentiment data. Sentiment data is acquired from user interface operation logs and feedback forms. The collected data is normalized and integrated in a unified format.

[0689] Analysis using generative models and emotion engines

[0690] The terminal applies a generative model to normalized business and emotional data to perform detailed analysis. The generative model identifies patterns and bottlenecks in the business flow. In addition, the emotional engine analyzes the user's emotional information and evaluates the need for business improvements based on the situation. For example, if a high workload is detected, the emotional engine will suggest ways to reduce the workload.

[0691] Predictions of areas for improvement

[0692] Based on analysis results from generative models and the sentiment engine, the server predicts areas for improvement in future business processes. These predictions offer users strategies to improve work efficiency and the work environment. Specifically, these include suggestions for automating parts of the workflow and reallocating tasks to reduce workload.

[0693] Process automation

[0694] Users automate business processes according to suggestions from the server. For example, they might implement tools to automate repetitive tasks and reduce working hours. They also improve work efficiency by reviewing processes and reallocating resources at appropriate times based on feedback from the emotional engine.

[0695] Effectiveness measurement and feedback

[0696] Subsequently, the server measures the effectiveness of the automated tasks and analyzes performance indicators. Users review the measurement results and evaluate the effectiveness of process improvements. This feedback is used to improve system accuracy and develop future business improvement measures. For example, this could include cases where business efficiency improves and user satisfaction increases.

[0697] This invention enables the simultaneous achievement of operational efficiency and improved work environment, thereby promoting the optimization of corporate operations.

[0698] The following describes the processing flow.

[0699] Step 1:

[0700] The server collects business data from various business systems within the company. It uses APIs and database queries to periodically retrieve necessary information. Simultaneously, it also acquires user sentiment data using a sentiment engine. Sentiment data is collected from operation logs and feedback forms on the user interface and recorded in conjunction with each business activity.

[0701] Step 2:

[0702] The terminal preprocesses the collected data. Data cleaning involves imputing missing values ​​with mean values ​​and removing outliers. Normalization standardizes data with different scales and adjusts the integrated dataset. Furthermore, it logically integrates data from different business systems and transforms it into an analyzable format in a consistent manner.

[0703] Step 3:

[0704] The server analyzes pre-processed data using a generative model. This analysis assesses the current state of business processes and identifies potential bottlenecks and inefficiencies. Next, it utilizes an emotion engine to measure work stress and burden based on user emotion data and evaluates the impact on the work environment.

[0705] Step 4:

[0706] The server generates specific business improvement suggestions based on the analysis results of the generative model and the sentiment engine. These suggestions include tasks that can be automated, tasks that need improvement, and measures to improve user experience based on sentiment data. The suggestions are communicated to the user and used as specific guidelines for business improvement.

[0707] Step 5:

[0708] Users implement improvement suggestions provided by the server. This includes introducing automation tools, reviewing and streamlining work procedures, and taking measures to optimize workloads and reduce employee stress based on insights from the emotion engine.

[0709] Step 6:

[0710] The server remeasures business performance after improvements have been implemented. It analyzes the efficiency gains and cost reductions from the newly collected data, quantitatively evaluating the effectiveness of the business improvements. The measurement results are automatically generated and presented to the user.

[0711] Step 7:

[0712] Users receive the server's analysis results and evaluate whether their business improvements were successful. Based on this feedback, they reconsider areas that require further improvement. This feedback is sent back to the server to improve the system's accuracy and train the sentiment engine, which helps in future analyses and recommendations.

[0713] (Example 2)

[0714] 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".

[0715] For many companies, streamlining business processes is a critical issue. However, analyzing business data and improving processes requires specialized knowledge, and proposing appropriate improvement measures that take into account employee emotions and workload is difficult. Therefore, there is a need for the development of automation systems that comprehensively consider the diverse elements of business operations.

[0716] 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.

[0717] In this invention, the server includes means for analyzing business process data using a generative model, means for predicting areas for business improvement based on the analysis results, and means for analyzing user sentiment data using a sentiment analysis engine and evaluating the need for business improvement. This enables comprehensive analysis of business processes based on business data and sentiment data, as well as concrete proposals for improvement and automation.

[0718] A "generative model" is a model that uses machine learning techniques to extract patterns from large datasets and then generates new data or analyzes existing data.

[0719] A "business process" refers to a series of business activities carried out within an organization, and is something that can be made more efficient or improved.

[0720] An "emotion analysis engine" is a technology that analyzes emotional data collected from users, evaluates trends and states, and uses this information to propose improvements to business operations.

[0721] "Data normalization" is the process of converting data recorded in different formats and units into a unified format, making it suitable for analysis.

[0722] "Predicting areas for business improvement" is the act of identifying specific improvement items to enhance the efficiency and effectiveness of current business processes, based on analyzed data.

[0723] "Automation" is a process that aims to improve efficiency and reduce errors by using technology to automate tasks that are currently performed manually.

[0724] "Effectiveness measurement" is the act of measuring how much success an implemented process improvement measure has brought about.

[0725] This invention is a system that combines a generative AI model and an emotion analysis engine to improve the efficiency and effectiveness of business processes. The embodiments are described in detail below.

[0726] The server retrieves business data and user feedback from the information management system using APIs and database queries. It then uses software to normalize this data and convert it into a unified format. This process utilizes universally accepted data management tools to maintain data integrity.

[0727] The terminal analyzes the normalized data through a generative AI model. This generative model identifies patterns and bottlenecks within the workflow and extracts areas for improvement to streamline processes. In parallel, a sentiment analysis engine analyzes the user's emotional data and assesses the need for business process improvement. If the user is experiencing stress in the workflow, specific improvement suggestions are formed at this stage.

[0728] As a concrete example, consider a digital marketing company implementing this system. They analyze employee work data to identify the reasons for declining advertising campaign effectiveness. In this process, emotional data might indicate that "the campaign content needs to be reviewed." Based on these results, a generative model develops a new campaign strategy, thereby improving advertising effectiveness.

[0729] Another example of a prompt is: "Analyze the company's internal business processes and generate specific suggestions to improve operational efficiency and user satisfaction."

[0730] This system enables sustainable organizational management by systematizing the improvement of operational efficiency and the work environment.

[0731] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0732] Step 1:

[0733] The server collects business data and user feedback from the information management system using APIs and database queries. Input consists of unstandardized data from various systems, and output is a set of raw data before processing. In this process, the server also acquires operation logs and feedback form information, collecting both quantitative and qualitative sentiment data related to actual business operations.

[0734] Step 2:

[0735] The server performs a process to normalize the collected data. The input is raw data before processing, and the output is standardized data in a unified format. Specifically, it performs tasks such as unifying different date formats and converting sentiment feedback into numerical scores. This conversion ensures that the data can be handled consistently in subsequent analysis processes.

[0736] Step 3:

[0737] The terminal receives normalized data and performs data analysis by applying a generative AI model. The input is a standardized dataset, and the output is analysis results and improvement suggestions regarding patterns and bottlenecks within the business flow. Specifically, it uses a pattern recognition algorithm to identify efficiency trends in the data and identify areas that need improvement.

[0738] Step 4:

[0739] The device uses an emotion analysis engine to analyze the user's emotional data in detail. The input is the user's emotion score, and the output is a determination of the urgency of business improvement based on emotional tendencies. For example, it can pinpoint the points where the user is experiencing stress and identify the business process that is causing it.

[0740] Step 5:

[0741] Based on the analysis results described above, the server predicts areas for improvement in business processes and proposes automation. The input consists of the results of a generative model and sentiment analysis engine, while the output is a list of automatable business processes and suggestions for task reallocation. Specifically, it generates automation proposals for routine data entry and report creation tasks, aiming to improve operational efficiency.

[0742] Step 6:

[0743] Users automate business processes based on improvements suggested by the server. The input is the server's automation suggestions, and the output is the highly automated business process. Specific implementations include introducing a "tool for automatically generating standardized text" to significantly reduce email response time.

[0744] Step 7:

[0745] The server measures the effectiveness of automated processes performed by users and analyzes performance metrics. Input is automated business data, and output is reports on improvements in operational efficiency and employee satisfaction. Based on the measurement results, further improvements and adjustments are made to achieve continuous optimization.

[0746] (Application Example 2)

[0747] 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".

[0748] In factory operations, there is a need to improve efficiency while reducing the burden on workers. However, currently, excessive workloads are placed on workers in order to increase productivity, which is resulting in a decline in quality and a deterioration of the working environment. Furthermore, there is a problem that the optimization of work processes has reached its limits because workers' emotions and stress are not taken into consideration.

[0749] 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.

[0750] In this invention, the server includes means for analyzing business process data using a generative model, means for predicting areas for improvement in business operations based on the analysis results, means for automating business processes based on the predicted areas for improvement, means for sentiment analysis for collecting and analyzing sentiment data, and means for making suggestions to adjust the workload using the sentiment analysis results. This enables both increased efficiency in business processes and reduced burden on workers, resulting in a better work environment and improved productivity.

[0751] A "generative model" is a machine learning algorithm that learns patterns and trends from data and generates new information.

[0752] A "business process" refers to a series of tasks and procedures within a company or organization, and is a method for carrying out activities efficiently.

[0753] "Analyzing" refers to the method of examining documents and data to understand their contents in detail.

[0754] "Areas for improvement" refers to parts of the current process or system that need improvement to enhance efficiency or effectiveness.

[0755] "Automating" means carrying out tasks or processes without human intervention, and being operated by machines or programs.

[0756] "Emotional data" refers to a representation of an individual's emotions and psychological state, converted into numerical values ​​and information.

[0757] "Analysis results" refer to the conclusions and insights obtained after analyzing data.

[0758] To "make a proposal" means to present new ideas or solutions regarding improvements to specific methods or processes.

[0759] In embodiments for carrying out this invention, a detailed explanation will be provided mainly for three elements: the server, the terminal, and the user.

[0760] The server incorporates a data collection module for gathering various data from within the factory. Specifically, it can collect data from various sensors installed in the factory and feedback from workers via APIs. The collected data is then normalized, integrated into a consistent format, and analyzed by a generative AI model. The generative AI model identifies bottlenecks and inefficiencies in business processes and predicts areas for improvement. This process utilizes data processing software running on the server.

[0761] The terminal displays data analyzed by a generated AI model and worker emotion data obtained using an emotion analysis engine. This allows users to check the worker's psychological state in real time and adjust work processes as needed. The emotion analysis engine collects emotion data from specific operation logs and feedback and suggests process improvements based on the emotional state.

[0762] Based on these analysis results and sentiment data, users can automate business processes. For example, when automation suggestions are made via a terminal, they can adjust worker break times or optimize production by robots. This simultaneously improves the efficiency of the entire business process and reduces the burden on workers, thereby improving the workplace environment.

[0763] As a concrete example, consider a business improvement that occurred on an assembly line for a certain part. In this case, the generative model analyzes data from the entire line and identifies that worker fatigue is high during specific time periods. As a result, the server, based on the analysis data from the emotion engine, proposes shift adjustments to automate processes using robots and allow workers to take breaks. An example of a prompt would be, "Based on the following dataset, evaluate the workers' stress levels and propose improvements to the production schedule."

[0764] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0765] Step 1:

[0766] The server collects operational data from sensors within the factory and worker feedback, and retrieves it via an API. Inputs are real-time data from sensors and worker feedback, while outputs are normalized data in a unified format. After collection, the data is normalized, noise is removed, and it is integrated into a format suitable for analysis.

[0767] Step 2:

[0768] The server inputs the normalized business data into a generation AI model to analyze the business process. The input is the data integrated in the previous step, and the output is the identification of bottlenecks and patterns in the business flow. In this process, machine learning algorithms extract features from the data and identify areas where business improvements are needed.

[0769] Step 3:

[0770] The server collects emotional data based on the analysis results and performs analysis using an emotional analysis engine. The input is emotional feedback data, and the output is an evaluation of the worker's psychological state and stress level. Based on this data, it detects when the workload is excessive and prepares appropriate improvement suggestions.

[0771] Step 4:

[0772] The terminal receives analysis results sent from the server and notifies the user in real time. Input is data sent from the server, and output is a visualized list of suggested work improvements displayed on the user's screen. It proposes work schedules that take into account the worker's emotional state and presents concrete action plans.

[0773] Step 5:

[0774] The user automates business processes based on the suggestions provided. Inputs are the schedule and improvement suggestions displayed on the terminal, and output is the adjusted business flow. This increases automation by robots and reduces the burden on workers. Specifically, the user uses the terminal to adjust shifts and, if necessary, changes the robot's operating time.

[0775] 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.

[0776] 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.

[0777] 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.

[0778] 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.

[0779] 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.

[0780] 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.

[0781] 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.

[0782] 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.

[0783] 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."

[0784] 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.

[0785] 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.

[0786] 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.

[0787] 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.

[0788] 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.

[0789] 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.

[0790] 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.

[0791] 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.

[0792] 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.

[0793] 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.

[0794] 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.

[0795] 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.

[0796] The following is further disclosed regarding the embodiments described above.

[0797] (Claim 1)

[0798] A means of analyzing business process data using a generative model,

[0799] A means for predicting areas for improvement in operations based on the aforementioned analysis results,

[0800] A means for automating business processes based on the aforementioned predicted areas for improvement,

[0801] A system that includes this.

[0802] (Claim 2)

[0803] The system according to claim 1, wherein the generation model includes means for normalizing and integrating data collected from different business systems.

[0804] (Claim 3)

[0805] The system according to claim 1, comprising means for evaluating the cost reduction effect through the automation of the aforementioned business process.

[0806] "Example 1"

[0807] (Claim 1)

[0808] A means for analyzing business procedure data using a generative model managed by an information processing device,

[0809] The aforementioned information processing device includes means for acquiring data from different information sources and preprocessing the data into a consistent data set,

[0810] A means for predicting areas for improvement in operations based on the aforementioned analysis results,

[0811] A means for automating business procedures based on the aforementioned predicted areas for improvement,

[0812] A means for evaluating the effectiveness of the automated business procedure and feeding the results back into improving the generation model,

[0813] A system that includes this.

[0814] (Claim 2)

[0815] The system according to claim 1, wherein the generative model includes means for normalizing and combining data obtained from different sources to create a consistent data set.

[0816] (Claim 3)

[0817] The system according to claim 1, which includes means for evaluating the resource reduction effect by automating the aforementioned business procedures and for aggregating the evaluation results in an information processing device.

[0818] "Application Example 1"

[0819] (Claim 1)

[0820] A method for analyzing business procedure data using a generative model,

[0821] A means for predicting areas for improvement in operations based on the aforementioned analysis results,

[0822] A means for automating business procedures based on the aforementioned predicted areas for improvement,

[0823] A means of automatically generating and distributing work instructions to improve the efficiency of manufacturing operations,

[0824] A system that includes this.

[0825] (Claim 2)

[0826] The system according to claim 1, wherein the generation model includes means for normalizing and integrating data collected from different business software.

[0827] (Claim 3)

[0828] The system according to claim 1, comprising means for evaluating the cost reduction effect through the automation of the aforementioned business procedures.

[0829] "Example 2 of combining an emotion engine"

[0830] (Claim 1)

[0831] A means of analyzing business process data using a generative model,

[0832] A means for predicting areas for improvement in operations based on the aforementioned analysis results,

[0833] A means for automating business processes based on the aforementioned predicted areas for improvement,

[0834] A means of analyzing user emotional data using an emotion analysis engine and evaluating the need for business improvement,

[0835] A means of measuring the effectiveness of automated tasks and evaluating performance,

[0836] A system that includes this.

[0837] (Claim 2)

[0838] The system according to claim 1, wherein the generation model includes means for normalizing and integrating data collected from different information management systems.

[0839] (Claim 3)

[0840] The system according to claim 1, comprising means for evaluating the cost and time reduction effects achieved by automating the aforementioned business process.

[0841] "Application example 2 when combining with an emotional engine"

[0842] (Claim 1)

[0843] A means of analyzing business process data using a generative model,

[0844] A means for predicting areas for improvement in operations based on the aforementioned analysis results,

[0845] A means for automating business processes based on the aforementioned predicted areas for improvement,

[0846] A means of sentiment analysis that collects sentiment data and analyzes that data,

[0847] A means for making suggestions to adjust workload using the aforementioned emotion analysis results,

[0848] A system that includes this.

[0849] (Claim 2)

[0850] The system according to claim 1, wherein the generation model includes means for normalizing and integrating data collected from different business systems.

[0851] (Claim 3)

[0852] The system according to claim 1, comprising means for evaluating the cost reduction effect through the automation of the aforementioned business process. [Explanation of Symbols]

[0853] 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. A means of analyzing business process data using a generative model, A means for predicting areas for improvement in business operations based on the aforementioned analysis results, A means for automating business processes based on the aforementioned predicted areas for improvement, A system that includes this.

2. The system according to claim 1, wherein the generation model includes means for normalizing and integrating data collected from different business systems.

3. The system according to claim 1, comprising means for evaluating the cost reduction effect through the automation of the aforementioned business process.

Images