system

Abstract

This system collects large amounts of business data, preprocesses it, and then performs feature extraction to analyze employees' work styles and know-how. [Solution] A system comprising: data collection means for collecting a large amount of business data; data preprocessing means for preprocessing the business data; feature extraction means for extracting features from the preprocessed data; pattern analysis means for analyzing business patterns based on the features; model training means for training an AI model based on the analysis results; robot generation means for generating a virtual copy robot using the AI ​​model; accuracy evaluation means for evaluating the accuracy of the answers generated by the copy robot; result presentation means for presenting the evaluation results; and data deficiency identification means for indicating missing data based on the presentation results.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In enterprises and organizations, due to changes, resignations, leaves of absence, etc. of employees, there is a risk that the business know-how possessed by individual employees will be lost, resulting in business stagnation and reduced efficiency. In addition, a lot of time and effort are required for business handover between employees, and if the handover is insufficient, there is also a possibility of mistakes and accidents due to misunderstandings of business contents. Means for solving these problems and achieving smooth continuation of business are required.

Means for Solving the Problems

[0005] This invention provides a system that analyzes employees' work styles and know-how by collecting large amounts of business data, preprocessing the data, and then performing feature extraction. Based on the analysis results, an AI model is trained, and this AI model is used to generate a virtual copy robot, thereby creating a system that mimics and supports employees' work. Furthermore, the accuracy of the answers generated by the copy robot is evaluated, and the evaluation results are presented to the user, thereby enabling the continuation and sharing of business know-how. In addition, missing data is clearly indicated based on the presented results, aiming to improve the overall accuracy of the system.

[0006] A "data collection method" is a mechanism for systematically collecting large amounts of business data from both inside and outside an organization.

[0007] "Data preprocessing means" refers to the process of formatting collected data into an analyzable form, removing unnecessary information, and standardizing the format.

[0008] A "feature extraction method" is a process that extracts useful features from pre-processed data and clarifies the essential points of the data.

[0009] A "pattern analysis method" is an algorithm used to identify recurring patterns and rules within data based on extracted features.

[0010] "Model training methods" refer to the process of training an AI model based on analysis results, aiming to improve its ability to accurately predict and judge even new data.

[0011] A "robot generation method" is a mechanism for generating copy robots that virtually mimic specific tasks by utilizing a trained AI model.

[0012] "Accuracy evaluation means" refers to a means of verifying the responses of the generated copy robot and evaluating their accuracy by comparing them with past data and standards.

[0013] A "results presentation method" is a method of presenting evaluated results to users in an easy-to-understand format to help support their work.

[0014] A "data deficiency detection method" is a mechanism that, based on the presentation of results, identifies the mechanisms and data necessary for further improving the accuracy of AI models and systems. [Brief explanation of the drawing]

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

Embodiment for Carrying Out the Invention

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

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

[0018] In the following embodiments, a 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), etc.

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

[0020] In the following embodiments, a 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, etc.

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

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

[0023] [First Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0036] As an embodiment of the present invention, a system utilizing AI for the purpose of supporting employees' work is provided. This system functions through the collaborative efforts of a server, a terminal, and a user.

[0037] First, the server collects various types of business data generated within the company or organization. This includes project management tools, emails, internal chats, and daily report data. The collected data is used as a record of work activities and communication history.

[0038] Next, the server preprocesses the collected data. By removing noise and imputing missing values, it prepares the data for highly accurate analysis. Features are extracted from the preprocessed data, revealing common patterns in business operations and specific decision-making styles.

[0039] Next, the server trains an AI model using a machine learning algorithm based on the feature extraction results. This AI model has the ability to generate the most appropriate response for a specific task or situation. After the model is sufficiently trained, a virtual copy robot is generated based on it.

[0040] Copy robots are generated to support business continuity and can mimic and supplement tasks according to employee instructions. They also predict and suggest solutions to challenges that arise during work execution, supporting rapid decision-making.

[0041] The server monitors the responses provided by the copy robot and evaluates their accuracy. This evaluation is performed through comparison with past data and matching with similar patterns. This allows for fine-tuning as needed while maintaining the accuracy of the responses.

[0042] Users can view evaluation results provided by the server on their devices. The evaluation results visualize trends and characteristics in business operations, with the aim of helping users improve their work processes. Furthermore, feedback provided by users is processed on the server and used to improve the accuracy of the AI ​​model.

[0043] As a concrete example, if an employee suddenly takes leave, a copy robot is generated to take over their duties. The user (supervisor or substitute employee) can then manage multiple tasks simultaneously while accepting suggestions from the server to continue working. In this way, the present invention makes it possible to improve the efficiency and continuity of operations within an organization.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The server collects business data from multiple sources within the company. It periodically extracts data from project management tools, email servers, chat applications, daily reporting systems, etc., and stores it in a central database.

[0047] Step 2:

[0048] The server performs data cleansing on the collected data. Specifically, it removes duplicate data, corrects data containing errors, and estimates and imputes missing values ​​to improve data integrity and accuracy.

[0049] Step 3:

[0050] The server extracts features from the pre-processed data. This involves using natural language processing techniques to identify keywords and themes from text data and generate elements to understand business patterns and trends.

[0051] Step 4:

[0052] The server uses the feature extraction results to train a machine learning model. In this process, a learning algorithm based on historical data is used to teach the model the optimal methods for handling business operations and solving problems.

[0053] Step 5:

[0054] The server generates virtual copy robots based on trained AI models. These copy robots have the ability to mimic the tasks performed by employees and provide support while maintaining consistency in those tasks.

[0055] Step 6:

[0056] Users review the business proposals and responses generated by the copy robot on their terminals and make revisions or approvals as needed. User feedback at this stage is sent to the server.

[0057] Step 7:

[0058] The server analyzes user feedback on the copy robot's responses and evaluates and adjusts the AI ​​model. This evaluation includes comparing it to past responses to verify accuracy.

[0059] Step 8:

[0060] The server presents users with trends derived from evaluation results and analysis of business data. This allows users to identify areas for improvement in their work and further streamline their operations.

[0061] (Example 1)

[0062] 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."

[0063] In modern business activities, the complexity of operations and the diversification of information are progressing, and consequently, efficient work execution is required. However, traditional methods require a great deal of time and effort, making it difficult to provide effective support for improving the continuity and productivity of operations. Furthermore, it is difficult to respond quickly to sudden handovers of tasks or problems that arise during the execution of tasks. As a result, the risk of business stagnation and errors is increasing.

[0064] 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.

[0065] In this invention, the server includes information gathering means for collecting various information related to the business, information preprocessing means for processing the information so that it can be analyzed with high accuracy, and feature extraction means for extracting important features from the preprocessed information. This enables the generation of an AI model that efficiently and continuously supports the business, and rapid problem solving by a virtual proxy agent.

[0066] "Information gathering means" refers to devices or software that have the function of efficiently collecting various types of business data related to corporate activities.

[0067] "Information preprocessing means" refers to means of performing data processing to improve the accuracy of collected business data and to convert it into an analyzable format.

[0068] A "feature extraction means" is a device or method for identifying important patterns and trends from pre-processed data and extracting features that can be used in business operations.

[0069] A "model formation method" is a means of constructing an AI model using machine learning based on extracted features.

[0070] "Agent generation means" refers to a device or method that generates a virtual proxy agent to provide business support using a trained AI model.

[0071] "Validity assessment means" refers to a device or method for evaluating the accuracy and applicability of a solution provided by a virtual proxy agent.

[0072] "Result delivery means" refers to a device or function for providing the results of a validity assessment to the user visually or informatively.

[0073] A "means for identifying information deficiencies" refers to a device or method for identifying and presenting information that is necessary for business operations but is lacking, based on the results provided.

[0074] "Regression information" refers to feedback provided by users, which is used to improve the system and rebuild the AI ​​model.

[0075] As an embodiment of the present invention, a system utilizing artificial intelligence (AI) for the purpose of supporting business operations is provided. This system functions through the cooperation of a server, terminals, and users. The server collects information from various data sources used within the company. In this embodiment, information is collected from project management tools, email, internal chat, daily reports, etc. API integration and database queries are used in this collection process.

[0076] The server processes the collected information, removing unnecessary data and filling in missing data. To create an environment that enables highly accurate data analysis, data cleaning techniques using Python and data formatting using SQL are employed. Next, the server extracts features from the pre-processed data to clarify important business patterns. Natural language processing techniques are used to analyze the text data and generate business-related keywords and phrases.

[0077] Next, the server forms a machine learning model based on the feature extraction results. This process utilizes machine learning libraries such as TENSORFLOW® and PyTorch to train the AI ​​model to adapt to specific business situations. The well-trained AI model is then used to generate a virtual surrogate agent. This agent complements the user's work and makes predictions and suggestions regarding the problem.

[0078] For example, if an employee suddenly takes leave, the server generates an agent to take over that employee's duties, helping the supervisor and the substitute employee (user) manage multiple tasks simultaneously. To further streamline this support process, the server evaluates the validity of the answers provided by the copy robot and allows the user to view the evaluation results on their terminal. The evaluation results include comparisons with past data and matching similar patterns.

[0079] User feedback is processed by the server as regression information and used to further improve the accuracy of the AI ​​model. This increases the efficiency and continuity of operations and provides higher quality AI services. In this embodiment, when evaluating the generated AI model and generating suggestions, a prompt message such as "Please suggest the next steps for the progress of Project X. The current issue is a lack of communication among members, which is causing schedule delays" can be used.

[0080] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0081] Step 1:

[0082] The server collects business-related information from sources such as the company's project management tools, emails, internal chats, and daily reports. Inputs include data obtained via APIs and database connections. Specifically, it collects information such as project task progress and email correspondence. This allows it to output basic data for understanding the overall business situation.

[0083] Step 2:

[0084] The server processes the collected data by removing noise and imputing missing values. The input is the raw business data collected in step 1. Specifically, it removes unnecessary HTML tags and duplicate data, and fills in missing values ​​with values ​​from similar past data to output clean, analyzable data.

[0085] Step 3:

[0086] The server extracts key features from pre-processed data. The input is clean, pre-processed data. For example, it might use natural language processing techniques to extract important keywords from email content or quantify project progress patterns. This process outputs feature data that includes business-specific key metrics.

[0087] Step 4:

[0088] The server trains an AI model using feature data. The input is the feature data extracted in step 3. Specifically, it uses TensorFlow to execute machine learning algorithms and learn decision-making criteria suitable for efficient task execution. As a result of this process, an AI model specialized for business support is output.

[0089] Step 5:

[0090] The server generates a virtual proxy agent from the trained AI model. The input is the AI ​​model obtained in step 4. Specifically, it outputs solutions that this agent provides while mimicking project task management and progress evaluation. This step outputs an agent in a format that allows the user to receive work assistance.

[0091] Step 6:

[0092] The server evaluates the agent's proposal and verifies its accuracy. The input is the solution provided by the agent. Specifically, it verifies its validity by comparing it with past data and outputs the evaluation results. This result can be used by the user as a basis for decision-making based on business performance and other factors.

[0093] Step 7:

[0094] Users view evaluation results on their devices and provide feedback. The input is the evaluation results from the server. Specifically, they send regression information to the server regarding the practicality and areas for improvement of the agent's solution. This generates feedback data that helps further improve the AI ​​model.

[0095] (Application Example 1)

[0096] 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."

[0097] Modern logistics centers require complex operational processes and diverse work procedures, necessitating support for efficient and accurate operation. In particular, providing real-time guidance on optimal work procedures to improve efficiency and ensure accuracy is a key challenge. To address this challenge, a business support system utilizing the latest technology is essential.

[0098] 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.

[0099] In this invention, the server includes information gathering means, information preprocessing means, and feature extraction means. This enables the presentation of optimal work procedures to workers in a logistics center in real time, allowing for efficient work execution.

[0100] "Information gathering methods" refer to the process of collecting various operational information at a logistics center and understanding the business processes.

[0101] "Information preprocessing means" refers to the process of removing noise and missing values ​​from collected information and preparing it for analysis.

[0102] "Feature extraction methods" are steps that identify important patterns and characteristics from pre-processed information and utilize them to improve business processes.

[0103] A "process analysis tool" is a function that analyzes business patterns in detail based on extracted characteristics and constructs the optimal procedure.

[0104] "Model training methods" refer to processes that utilize process analysis results to train AI models, enabling them to predict business procedures with high accuracy.

[0105] The "assistant generation method" is a process that generates a virtual business support assistant using a trained AI model.

[0106] "Accuracy evaluation methods" are techniques for evaluating whether the output generated by the assistant is accurate and for confirming the quality of the work.

[0107] A "procedure presentation method" is a function that presents the optimal work procedure to the worker via a smart terminal, thereby improving work efficiency.

[0108] "Information deficiency identification methods" are processes that aim to improve work accuracy by pointing out information deficiencies and areas for improvement based on the presented results.

[0109] The system for realizing this invention is a business support system utilizing smart terminals in a logistics center. The server collects a large amount of business information generated within the logistics center through information collection means. This information includes worker movement data and data related to the flow of goods. The collected information is converted into a format that is easy to analyze by removing noise and missing values ​​using information preprocessing means and organizing the data.

[0110] The server uses feature extraction means to extract features from pre-processed information. In this process, important patterns and characteristics in the logistics center's business processes become apparent. Based on this, process analysis means perform a detailed pattern analysis of the operations to derive the optimal work procedure.

[0111] By training an AI model from these analysis results using a model training method, efficient task execution becomes possible. The trained AI model uses an assistant generation method to create a virtual task support assistant, which provides generated instructions to the logged-in worker.

[0112] The smart terminals used by workers display the optimal work procedures in real time via a procedure presentation system, streamlining the workflow. Furthermore, the assistant's output is verified using an accuracy evaluation system to maintain the quality of work. Based on the presented procedures, a system for identifying missing information specifically points out necessary information and areas for improvement.

[0113] As a concrete example, worker B at a logistics center wears smart glasses, and the AI ​​presents work procedures to streamline a new packing process. Worker B performs the work according to the presented procedures, and the server receives the results along with feedback. Based on this feedback, the server fine-tunes the AI ​​model to further improve operational efficiency.

[0114] Examples of prompt statements are as follows:

[0115] "What is the optimal order of these work steps?"

[0116] "What instructions should I give to worker B?"

[0117] "How will the model be improved based on the feedback?"

[0118] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0119] Step 1:

[0120] The server collects operational and material flow data in real time from information gathering devices within the logistics center. This data is obtained via sensors and RFID from each work station on site. The input is raw data, and the output is pre-processed raw data.

[0121] Step 2:

[0122] The server denoises and imputes missing values ​​in the raw data collected using preprocessing tools. Filtering techniques are used for denoising, and missing values ​​are handled using mean imputation. The input is raw data, and the output is a clean, analyzable dataset.

[0123] Step 3:

[0124] The server utilizes feature extraction methods to apply statistical techniques to extract important features from a clean dataset. For example, it analyzes data distribution, frequency, and correlation. The input is clean data, and the output is a feature vector.

[0125] Step 4:

[0126] The server analyzes feature vectors using process analysis tools and detects patterns. Here, a machine learning clustering algorithm is used to categorize business processes. The input is feature vectors, and the output is a prototype of a business pattern.

[0127] Step 5:

[0128] The server trains a new AI model from the analysis results using a model training method. This AI model utilizes supervised learning to capture business patterns, which are the output. The input is a prototype of the business pattern, and the output is the trained AI model.

[0129] Step 6:

[0130] The server generates a virtual business support assistant from a trained AI model based on the assistant generation mechanism and sends it to the smart terminal. This assistant has the function of creating instructions for each work step. The input is the trained AI model, and the output is a program for the smart terminal acting as a business support assistant.

[0131] Step 7:

[0132] The terminal uses a procedure presentation system to provide the worker with work procedures optimized for them in real time. Visual information is displayed on the smart glasses' screen. Input is the instructions of the work support assistant, and output is the work procedure information provided to the worker.

[0133] Step 8:

[0134] The user evaluates the accuracy of the assistant's output through an accuracy evaluation tool and records the feedback on the terminal. The input consists of the instructions provided by the assistant and the user's work results, while the output is the result of the accuracy evaluation.

[0135] Step 9:

[0136] The server analyzes the feedback results using information deficiency detection mechanisms and specifies the additional information needed for the next cycle. This enables further improvement of the AI ​​model. The input is the accuracy evaluation result, and the output is a list of information deficiencies.

[0137] 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.

[0138] This invention provides a business support system that considers the processing of business data and the emotions of users. This system works collaboratively with servers, terminals, and users, and in particular, utilizes an emotion engine to reflect the user's state, thereby achieving more flexible and human-centered business support.

[0139] First, the server collects work data from tools that employees use on a daily basis. This includes project management software, email, chat systems, and daily report data. The collected data is stored in a central database and prepared for analysis.

[0140] Next, the data undergoes a series of preprocessing steps. The server performs data cleansing, corrects data defects, and prepares the data for feature extraction. By extracting features from the target data, business patterns are analyzed, and resources are prepared for use in training an AI model. The AI ​​model is then trained to support the most effective business decisions based on these features.

[0141] Based on a trained AI model, the server generates a virtual copy robot. This copy robot is responsible for maintaining consistency and quality of work while taking over the duties of an employee on leave. Simultaneously, the system incorporates an emotion engine that analyzes the user's emotional state in real time from facial recognition, voice tone, or input information.

[0142] The server receives the analysis results from the emotion engine and adjusts the content and tone of the copy robot's responses to match the user's emotional state. For example, if the user is feeling stressed, the system will provide high-priority support or simplified information.

[0143] Furthermore, users can review the information provided on their devices and provide immediate feedback, which is then used to retrain the AI ​​model. The interaction between user feedback and sentiment analysis can improve the overall accuracy of the system and user satisfaction.

[0144] For example, if a user expresses anxiety or stress as a project deadline approaches, the server will suggest ways to adjust task priorities or reallocate resources. In this way, the present invention provides the utilization of business data and flexible responses that respond to user emotions, thereby improving business efficiency and employee well-being.

[0145] The following describes the processing flow.

[0146] Step 1:

[0147] The server automatically collects employee work data from project management systems, email servers, chat tools, etc., and stores it in a database.

[0148] Step 2:

[0149] The server preprocesses the collected business data. It performs data cleansing, removing duplicates and imputing missing values ​​to create a ready dataset for analysis.

[0150] Step 3:

[0151] The server extracts features from pre-processed data. This process uses natural language processing techniques to detect important keywords and topics from text data, identifying business trends and frequently used actions.

[0152] Step 4:

[0153] The server utilizes the feature extraction results to train the AI ​​model. This training uses machine learning algorithms to predict optimal actions in business operations and improve the model's pattern recognition capabilities to enhance its usefulness.

[0154] Step 5:

[0155] The server generates virtual copy robots from trained AI models. These robots are capable of mimicking specific tasks and continuing normal operations.

[0156] Step 6:

[0157] The server activates an emotion engine to analyze the user's emotional state in real time from their facial expressions, tone of voice, and text input. Based on this analysis, it identifies the user's emotions.

[0158] Step 7:

[0159] Based on the sentiment analysis results, the server appropriately adjusts the tone and content of the responses provided by the copy robot. For example, if the user is feeling stressed, it will offer more friendly, concise, and gentle suggestions.

[0160] Step 8:

[0161] Users receive the provided business support information through their devices and make corrections or provide feedback as needed. This feedback is immediately transmitted to the server.

[0162] Step 9:

[0163] The server further retrains the AI ​​model based on user feedback and sentiment analysis results. This aims to improve the overall accuracy of the system and enhance user satisfaction.

[0164] (Example 2)

[0165] 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".

[0166] In today's work environment, vast amounts of data are generated, and efficient work execution and the maintenance of employees' mental health are required, but conventional systems have not adequately addressed these challenges. In particular, there is a problem in appropriately combining the effective use of data with feedback that responds to users' emotions. Therefore, there is a need to develop systems that provide more adaptive and human-centered work support.

[0167] 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.

[0168] In this invention, the server includes information gathering means for collecting business data, information preprocessing means for preprocessing the information, and feature extraction means for extracting features from the preprocessed information. This enables business support tailored to the user's emotional state, as well as effective business support based on the collected data.

[0169] "Information gathering means" refers to a function or process for automatically collecting data related to business operations from various information sources.

[0170] "Information preprocessing means" refers to a function that corrects or adjusts incomplete data in order to convert collected data into an analyzable format.

[0171] A "feature extraction method" is a technique for identifying important patterns and trends from pre-processed data and extracting elements necessary for analysis and model training.

[0172] "Analysis methods" refer to the process of systematically investigating business patterns from data obtained through feature extraction methods and deriving useful insights.

[0173] "Training methods" refer to the process of adjusting an AI model by applying machine learning algorithms based on the results obtained from analysis methods, so that the AI ​​model can function effectively.

[0174] A "generation method" is a mechanism for designing units that virtually perform tasks on behalf of others using trained AI models, and for providing them in an executable form.

[0175] "Emotion analysis means" refers to a technology used to determine a user's emotional state from various input data and to understand that state in real time.

[0176] "Response adjustment means" refers to a function that adjusts the system's response based on emotional data analyzed by emotion analysis means, in order to provide more appropriate support.

[0177] A "feedback system" is a mechanism that accepts user feedback and effectively utilizes that feedback to improve the performance of the system or model.

[0178] The embodiments for carrying out the invention are described in detail below.

[0179] This system provides business support through the collaboration of servers, terminals, and users. First, the server collects business-related data from various sources. These sources include project management tools, email systems, chat applications, and daily reporting systems. The collected data is stored in databases such as PostgreSQL and MySQL®.

[0180] The server performs several processes on the collected data. First, it cleanses the data, correcting incomplete data and organizing the necessary information. Next, it performs feature extraction using libraries such as Scikit-learn. This extracts important features of business activities, and then it trains an AI model using TensorFlow or PyTorch. The trained model generates a virtual replacement work unit, or copy robot, to perform the tasks on behalf of the business.

[0181] Users interact with the system using a terminal. The system incorporates emotion analysis capabilities, using a camera and microphone to estimate the user's emotional state from their face and voice. Based on this information, the server can adjust the copy robot's responses to provide appropriate information and support.

[0182] For example, if a user expresses anxiety as a project deadline approaches, the server will readjust the task priorities and suggest reallocating resources. This allows the user to perform their tasks with reduced stress. An example of a prompt message would be: "Project X is nearing its deadline, and user A is feeling anxious. How will the system respond?"

[0183] In this way, the present invention enables the realization of a system that provides effective and flexible business support by combining data collection, processing, analysis, and responses to user emotions.

[0184] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0185] Step 1:

[0186] The server automatically collects business data from sources such as project management tools, email, chat applications, and daily reports. The data received from these sources is imported into the server in a structured format (e.g., JSON, CSV). Input is raw data from various sources, and output is data stored in a central database.

[0187] Step 2:

[0188] The server first performs data cleansing on the collected data. Specifically, this involves correcting incomplete data and deleting unimportant data. The input is the collected raw data, and the output is clean data with defects corrected. This results in a dataset that can be analyzed and feature extracted.

[0189] Step 3:

[0190] The server performs feature extraction on clean data. During this process, it uses data analysis libraries such as Scikit-learn to extract business trends and patterns. The input is a clean dataset, and the output is a feature vector or an analyzable set of information. This information is then used to train an AI model.

[0191] Step 4:

[0192] The server trains an AI model based on the data obtained through feature extraction. For example, it uses TensorFlow or PyTorch to select an appropriate algorithm and optimize the model's parameters. The input is a feature vector and related information, and the output is a trained AI model for performing business support.

[0193] Step 5:

[0194] The server uses a trained AI model to generate a virtual alternative unit of work. This prepares it to take over tasks even when the user is absent or busy. The input is the trained AI model, and the output is a viable alternative unit of work.

[0195] Step 6:

[0196] When a user interacts with the device, the server activates an emotion analysis engine that analyzes the user's facial expressions and voice input. The input is real-time data about the user's emotional state, and the output is the analyzed emotion trend. This feeds the system with the user's emotional changes.

[0197] Step 7:

[0198] The server adjusts the content and tone of its alternative work units based on the user's emotions. For stressed users, it presents simplified, high-priority tasks. The input is user emotion analysis data, and the output is a user-specific response and support plan.

[0199] Step 8:

[0200] Users provide feedback on the information and support offered and send it to the server. Based on this feedback, the AI ​​model is retrained. The input is the user's feedback data, and the output is the improved AI model and the system's overall business support capabilities.

[0201] (Application Example 2)

[0202] 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".

[0203] Current business support systems do not take into account employees' emotions or stress levels, which can lead to decreased work efficiency. Furthermore, there is a lack of systems capable of analyzing emotions and providing appropriate work support based on those analyses.

[0204] 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.

[0205] In this invention, the server includes information acquisition means, information preprocessing means, feature extraction means, pattern analysis means, model training means, device generation means, accuracy evaluation means, result presentation means, information deficiency detection means, emotion analysis means, support information provision means, and work efficiency adjustment means. This makes it possible to analyze the emotional state of employees in real time and provide appropriate support information via smart devices when providing work support based on the acquisition and analysis of work information.

[0206] "Information acquisition means" refers to devices and methods for collecting large amounts of business information.

[0207] "Information preprocessing means" refers to methods or devices for preparing acquired business information into a state that can be analyzed.

[0208] A "feature extraction means" is a method or device for finding specific patterns or attributes from pre-processed business information.

[0209] A "pattern analysis tool" is a method or device for analyzing business processes and trends based on extracted features.

[0210] "Model training means" refers to methods and devices for constructing and optimizing AI models using analysis results.

[0211] "Device generation means" refers to a method or device that uses a trained AI model to create a virtual automated device.

[0212] "Accuracy evaluation means" refers to a method or apparatus for determining the accuracy of the response or operation of a generated device.

[0213] "Result presentation means" refers to methods or devices for visually or audibly showing the results of an evaluation to the user.

[0214] "Information deficiency identification methods" are methods or devices that identify missing information or data based on the presented results.

[0215] "Emotional analysis tools" refer to methods or devices that analyze facial expressions, voice tone, etc., in order to understand the emotional state of employees.

[0216] "Support information provision means" refers to methods or devices that present information to provide appropriate support based on the results of emotion analysis.

[0217] "Methods for adjusting work efficiency" refer to methods or devices that adjust work processes to maximize efficiency based on the emotional state of employees and analysis results.

[0218] In this invention, a server is central to realizing a business support system. First, information related to business operations is collected by an information acquisition means. This information includes employee work progress data and customer data. The server uses an information preprocessing means to organize the collected information and convert it into a format suitable for analysis. Specifically, a data preprocessing library is used as the software.

[0219] Next, the server uses feature extraction to extract specific patterns from the pre-processed information. These patterns play a crucial role in subsequent analysis. Pattern analysis is then used to analyze employee work patterns and customer behavior patterns. Machine learning algorithms are employed in this process.

[0220] Using a model training method, an AI model is trained based on the analysis results. This training optimizes how employees and customers respond based on the patterns discovered. The trained AI model then uses a device generation method to create a virtual automation device that provides business support.

[0221] Smart glasses and other devices are worn by employees and analyze their emotional state in real time through emotion analysis tools. They utilize facial recognition cameras and voice recognition microphones, and the software includes an emotion analysis engine. Based on the analysis results, the server transmits support information to the device via a support information provision system. This information enables employees to perform appropriate tasks.

[0222] As a concrete example, in a busy store on a Saturday afternoon, the AI ​​could suggest priority customer service or quicker procedures to employees who are feeling stressed. An example of a prompt message would be, "Analyze the employee's stress level and provide immediately available support information."

[0223] This will lead to improved work efficiency and reduced stress for employees.

[0224] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0225] Step 1:

[0226] The server uses data acquisition methods to collect raw data related to business operations. Inputs include employee work progress and customer data. Outputs are imported into the system as raw datasets. Specifically, data is collected from project management tools and customer management systems via APIs.

[0227] Step 2:

[0228] The server uses data preprocessing to format the collected raw data. The input is the raw dataset collected in step 1. The output is data processed into an analyzable format. Specifically, data cleansing is performed to remove duplicate data and impute missing data.

[0229] Step 3:

[0230] The server uses a feature extraction method to extract features from pre-processed data. The input is the data processed in step 2. The output is the feature data extracted for analysis. Specifically, it selects and quantifies features for machine learning.

[0231] Step 4:

[0232] The server uses pattern analysis tools to analyze patterns from the extracted feature data. The input is the feature data obtained in step 3. The output is business trends and predictive information. Specifically, it uses time series analysis and clustering techniques to analyze business progress and customer behavior patterns.

[0233] Step 5:

[0234] The server uses a model training method to train an AI model based on the analysis results. The input is the analysis results obtained in step 4. The output is the trained AI model. Specifically, it uses a neural network to optimize the model and improve prediction accuracy.

[0235] Step 6:

[0236] The server uses a device generation mechanism to generate a virtual automation device based on a trained AI model. The input is the AI ​​model trained in step 5. The output is a virtual automation device for business support. Specifically, the AI ​​model is deployed to a cloud environment and linked to business systems via an API.

[0237] Step 7:

[0238] The terminal uses emotion analysis capabilities to analyze the emotional state of employees in real time. The input is emotion data from the terminal's camera and microphone. The output is the analyzed emotional state data. Specifically, it analyzes facial expressions from a video stream and analyzes the tone of audio data.

[0239] Step 8:

[0240] The server uses a support information provision system to send support information to the terminal based on the emotional state. The input is the emotional state data obtained in step 7. The output is the support information displayed on the smart device. Specifically, the server generates support information and provides it to the terminal via push notification.

[0241] Step 9:

[0242] The user readjusts the efficiency of their work based on the support information provided through the work efficiency adjustment tool. The input is the support information presented in step 8. The output is the optimized work process. Specifically, this involves reviewing the schedule and resource allocation, and resetting the core of the work.

[0243] 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.

[0244] 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.

[0245] 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.

[0246] [Second Embodiment]

[0247] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0248] 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.

[0249] 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).

[0250] 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.

[0251] 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.

[0252] 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).

[0253] 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.

[0254] 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.

[0255] 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.

[0256] 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.

[0257] 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.

[0258] 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".

[0259] As an embodiment of the present invention, a system utilizing AI for the purpose of supporting employees' work is provided. This system functions through the collaborative efforts of a server, a terminal, and a user.

[0260] First, the server collects various types of business data generated within the company or organization. This includes project management tools, emails, internal chats, and daily report data. The collected data is used as a record of work activities and communication history.

[0261] Next, the server preprocesses the collected data. By removing noise and imputing missing values, it prepares the data for highly accurate analysis. Features are extracted from the preprocessed data, revealing common patterns in business operations and specific decision-making styles.

[0262] Next, the server trains an AI model using a machine learning algorithm based on the feature extraction results. This AI model has the ability to generate the most appropriate response for a specific task or situation. After the model is sufficiently trained, a virtual copy robot is generated based on it.

[0263] Copy robots are generated to support business continuity and can mimic and supplement tasks according to employee instructions. They also predict and suggest solutions to challenges that arise during work execution, supporting rapid decision-making.

[0264] The server monitors the responses provided by the copy robot and evaluates their accuracy. This evaluation is performed through comparison with past data and matching with similar patterns. This allows for fine-tuning as needed while maintaining the accuracy of the responses.

[0265] Users can view evaluation results provided by the server on their devices. The evaluation results visualize trends and characteristics in business operations, with the aim of helping users improve their work processes. Furthermore, feedback provided by users is processed on the server and used to improve the accuracy of the AI ​​model.

[0266] As a concrete example, if an employee suddenly takes leave, a copy robot is generated to take over their duties. The user (supervisor or substitute employee) can then manage multiple tasks simultaneously while accepting suggestions from the server to continue working. In this way, the present invention makes it possible to improve the efficiency and continuity of operations within an organization.

[0267] The following describes the processing flow.

[0268] Step 1:

[0269] The server collects business data from multiple sources within the company. It periodically extracts data from project management tools, email servers, chat applications, daily reporting systems, etc., and stores it in a central database.

[0270] Step 2:

[0271] The server performs data cleansing on the collected data. Specifically, it removes duplicate data, corrects data containing errors, and estimates and imputes missing values ​​to improve data integrity and accuracy.

[0272] Step 3:

[0273] The server extracts features from the pre-processed data. This involves using natural language processing techniques to identify keywords and themes from text data and generate elements to understand business patterns and trends.

[0274] Step 4:

[0275] The server uses the feature extraction results to train a machine learning model. In this process, a learning algorithm based on historical data is used to teach the model the optimal methods for handling business operations and solving problems.

[0276] Step 5:

[0277] The server generates virtual copy robots based on trained AI models. These copy robots have the ability to mimic the tasks performed by employees and provide support while maintaining consistency in those tasks.

[0278] Step 6:

[0279] Users review the business proposals and responses generated by the copy robot on their terminals and make revisions or approvals as needed. User feedback at this stage is sent to the server.

[0280] Step 7:

[0281] The server analyzes the user's feedback on the copy robot's answer and evaluates and adjusts the AI model. This evaluation includes the process of confirming the accuracy by comparing with past answers.

[0282] Step 8:

[0283] The server presents the user with the evaluation results and trends obtained from the analysis of business data. As a result, the user can grasp the improvement points of the business and further improve business efficiency.

[0284] (Example 1)

[0285] Next, Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0286] In modern corporate activities, the complexity of business and the diversification of information are progressing, and along with this, efficient business performance is required. However, conventional methods require a great deal of time and effort and have difficulty providing effective support for improving business continuity and productivity. It is also difficult to quickly respond to sudden handovers of work or problems that occur during business performance. As a result, the risk of business stagnation and mistakes is increasing.

[0287] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0288] In this invention, the server includes an information collection means for collecting various information related to business, an information preprocessing means for processing the information so that it can be analyzed with high accuracy, and a feature extraction means for extracting important features from the preprocessed information. As a result, it becomes possible to generate an AI model that efficiently and continuously supports business and to quickly solve problems by a virtual agent.

[0289] "Information gathering means" refers to devices or software that have the function of efficiently collecting various types of business data related to corporate activities.

[0290] "Information preprocessing means" refers to means of performing data processing to improve the accuracy of collected business data and to convert it into an analyzable format.

[0291] A "feature extraction means" is a device or method for identifying important patterns and trends from pre-processed data and extracting features that can be used in business operations.

[0292] A "model formation method" is a means of constructing an AI model using machine learning based on extracted features.

[0293] "Agent generation means" refers to a device or method that generates a virtual proxy agent to provide business support using a trained AI model.

[0294] "Validity assessment means" refers to a device or method for evaluating the accuracy and applicability of a solution provided by a virtual proxy agent.

[0295] "Result delivery means" refers to a device or function for providing the results of a validity assessment to the user visually or informatively.

[0296] A "means for identifying information deficiencies" refers to a device or method for identifying and presenting information that is necessary for business operations but is lacking, based on the results provided.

[0297] "Regression information" refers to feedback provided by users, which is used to improve the system and rebuild the AI ​​model.

[0298] As an embodiment of the present invention, a system utilizing artificial intelligence (AI) for the purpose of supporting business operations is provided. This system functions through the cooperation of a server, terminals, and users. The server collects information from various data sources used within the company. In this embodiment, information is collected from project management tools, email, internal chat, daily reports, etc. API integration and database queries are used in this collection process.

[0299] The server processes the collected information, removing unnecessary data and filling in missing data. To create an environment that enables highly accurate data analysis, data cleaning techniques using Python and data formatting using SQL are employed. Next, the server extracts features from the pre-processed data to clarify important business patterns. Natural language processing techniques are used to analyze the text data and generate business-related keywords and phrases.

[0300] Next, the server forms a machine learning model based on the feature extraction results. This process utilizes machine learning libraries such as TensorFlow and PyTorch to train the AI ​​model to adapt to specific business situations. The well-trained AI model is then used to generate a virtual surrogate agent. This agent complements the user's work and makes predictions and suggestions regarding the problem.

[0301] For example, if an employee suddenly takes leave, the server generates an agent to take over that employee's duties, helping the supervisor and the substitute employee (user) manage multiple tasks simultaneously. To further streamline this support process, the server evaluates the validity of the answers provided by the copy robot and allows the user to view the evaluation results on their terminal. The evaluation results include comparisons with past data and matching similar patterns.

[0302] Feedback from users is processed by the server as regression information and used to further improve the accuracy of the AI model. This enhances the efficiency and continuity of operations and provides higher-quality AI services. In this embodiment, when evaluating the generated AI model and generating proposals, a prompt sentence such as "I would like a proposal for the next step regarding the progress of Project X. The current issue is insufficient communication among team members and a delay in the schedule." can be used.

[0303] The flow of the specific process in Example 1 will be described using FIG. 11.

[0304] Step 1:

[0305] The server collects business-related information from the company's project management tools, emails, internal chats, daily reports, etc. The inputs include data groups obtained via APIs and database connections. Specifically, it collects the progress of project tasks, email exchanges, etc. This outputs basic data for understanding the overall situation of the business.

[0306] Step 2:

[0307] The server performs noise removal and imputation of missing values to format the collected data. The input is the raw business data collected in Step 1. Specifically, it deletes unnecessary HTML tags and duplicate data, and fills in missing parts with imputation values from past similar data, outputting clean and analyzable data.

[0308] Step 3:

[0309] The server extracts important features from the preprocessed data. The input is the preprocessed clean data. For example, it uses natural language processing techniques to extract important keywords from email content or digitizes the progress pattern of a project. Through this process, feature data containing important indicators specific to the business is output.

[0310] Step 4:

[0311] The server trains an AI model using feature data. The input is the feature data extracted in step 3. Specifically, it uses TensorFlow to execute machine learning algorithms and learn decision-making criteria suitable for efficient task execution. As a result of this process, an AI model specialized for business support is output.

[0312] Step 5:

[0313] The server generates a virtual proxy agent from the trained AI model. The input is the AI ​​model obtained in step 4. Specifically, it outputs solutions that this agent provides while mimicking project task management and progress evaluation. This step outputs an agent in a format that allows the user to receive work assistance.

[0314] Step 6:

[0315] The server evaluates the agent's proposal and verifies its accuracy. The input is the solution provided by the agent. Specifically, it verifies its validity by comparing it with past data and outputs the evaluation results. This result can be used by the user as a basis for decision-making based on business performance and other factors.

[0316] Step 7:

[0317] Users view evaluation results on their devices and provide feedback. The input is the evaluation results from the server. Specifically, they send regression information to the server regarding the practicality and areas for improvement of the agent's solution. This generates feedback data that helps further improve the AI ​​model.

[0318] (Application Example 1)

[0319] 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."

[0320] Modern logistics centers require complex operational processes and diverse work procedures, necessitating support for efficient and accurate operation. In particular, providing real-time guidance on optimal work procedures to improve efficiency and ensure accuracy is a key challenge. To address this challenge, a business support system utilizing the latest technology is essential.

[0321] 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.

[0322] In this invention, the server includes information gathering means, information preprocessing means, and feature extraction means. This enables the presentation of optimal work procedures to workers in a logistics center in real time, allowing for efficient work execution.

[0323] "Information gathering methods" refer to the process of collecting various operational information at a logistics center and understanding the business processes.

[0324] "Information preprocessing means" refers to the process of removing noise and missing values ​​from collected information and preparing it for analysis.

[0325] "Feature extraction methods" are steps that identify important patterns and characteristics from pre-processed information and utilize them to improve business processes.

[0326] A "process analysis tool" is a function that analyzes business patterns in detail based on extracted characteristics and constructs the optimal procedure.

[0327] "Model training methods" refer to processes that utilize process analysis results to train AI models, enabling them to predict business procedures with high accuracy.

[0328] The "assistant generation method" is a process that generates a virtual business support assistant using a trained AI model.

[0329] "Accuracy evaluation methods" are techniques for evaluating whether the output generated by the assistant is accurate and for confirming the quality of the work.

[0330] A "procedure presentation method" is a function that presents the optimal work procedure to the worker via a smart terminal, thereby improving work efficiency.

[0331] "Information deficiency identification methods" are processes that aim to improve work accuracy by pointing out information deficiencies and areas for improvement based on the presented results.

[0332] The system for realizing this invention is a business support system utilizing smart terminals in a logistics center. The server collects a large amount of business information generated within the logistics center through information collection means. This information includes worker movement data and data related to the flow of goods. The collected information is converted into a format that is easy to analyze by removing noise and missing values ​​using information preprocessing means and organizing the data.

[0333] The server uses feature extraction means to extract features from pre-processed information. In this process, important patterns and characteristics in the logistics center's business processes become apparent. Based on this, process analysis means perform a detailed pattern analysis of the operations to derive the optimal work procedure.

[0334] By training an AI model from these analysis results using a model training method, efficient task execution becomes possible. The trained AI model uses an assistant generation method to create a virtual task support assistant, which provides generated instructions to the logged-in worker.

[0335] The smart terminals used by workers display the optimal work procedures in real time via a procedure presentation system, streamlining the workflow. Furthermore, the assistant's output is verified using an accuracy evaluation system to maintain the quality of work. Based on the presented procedures, a system for identifying missing information specifically points out necessary information and areas for improvement.

[0336] As a concrete example, worker B at a logistics center wears smart glasses, and the AI ​​presents work procedures to streamline a new packing process. Worker B performs the work according to the presented procedures, and the server receives the results along with feedback. Based on this feedback, the server fine-tunes the AI ​​model to further improve operational efficiency.

[0337] Examples of prompt statements are as follows:

[0338] "What is the optimal order of these work steps?"

[0339] "What instructions should I give to worker B?"

[0340] "How will the model be improved based on the feedback?"

[0341] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0342] Step 1:

[0343] The server collects operational and material flow data in real time from information gathering devices within the logistics center. This data is obtained via sensors and RFID from each work station on site. The input is raw data, and the output is pre-processed raw data.

[0344] Step 2:

[0345] The server denoises and imputes missing values ​​in the raw data collected using preprocessing tools. Filtering techniques are used for denoising, and missing values ​​are handled using mean imputation. The input is raw data, and the output is a clean, analyzable dataset.

[0346] Step 3:

[0347] The server utilizes feature extraction methods to apply statistical techniques to extract important features from a clean dataset. For example, it analyzes data distribution, frequency, and correlation. The input is clean data, and the output is a feature vector.

[0348] Step 4:

[0349] The server analyzes feature vectors using process analysis tools and detects patterns. Here, a machine learning clustering algorithm is used to categorize business processes. The input is feature vectors, and the output is a prototype of a business pattern.

[0350] Step 5:

[0351] The server trains a new AI model from the analysis results using a model training method. This AI model utilizes supervised learning to capture business patterns, which are the output. The input is a prototype of the business pattern, and the output is the trained AI model.

[0352] Step 6:

[0353] The server generates a virtual business support assistant from a trained AI model based on the assistant generation mechanism and sends it to the smart terminal. This assistant has the function of creating instructions for each work step. The input is the trained AI model, and the output is a program for the smart terminal acting as a business support assistant.

[0354] Step 7:

[0355] The terminal uses a procedure presentation system to provide the worker with work procedures optimized for them in real time. Visual information is displayed on the smart glasses' screen. Input is the instructions of the work support assistant, and output is the work procedure information provided to the worker.

[0356] Step 8:

[0357] The user evaluates the accuracy of the assistant's output through an accuracy evaluation tool and records the feedback on the terminal. The input consists of the instructions provided by the assistant and the user's work results, while the output is the result of the accuracy evaluation.

[0358] Step 9:

[0359] The server analyzes the feedback results using information deficiency detection mechanisms and specifies the additional information needed for the next cycle. This enables further improvement of the AI ​​model. The input is the accuracy evaluation result, and the output is a list of information deficiencies.

[0360] 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.

[0361] This invention provides a business support system that considers the processing of business data and the emotions of users. This system works collaboratively with servers, terminals, and users, and in particular, utilizes an emotion engine to reflect the user's state, thereby achieving more flexible and human-centered business support.

[0362] First, the server collects work data from tools that employees use on a daily basis. This includes project management software, email, chat systems, and daily report data. The collected data is stored in a central database and prepared for analysis.

[0363] Next, the data undergoes a series of preprocessing steps. The server performs data cleansing, corrects data defects, and prepares the data for feature extraction. By extracting features from the target data, business patterns are analyzed, and resources are prepared for use in training an AI model. The AI ​​model is then trained to support the most effective business decisions based on these features.

[0364] Based on a trained AI model, the server generates a virtual copy robot. This copy robot is responsible for maintaining consistency and quality of work while taking over the duties of an employee on leave. Simultaneously, the system incorporates an emotion engine that analyzes the user's emotional state in real time from facial recognition, voice tone, or input information.

[0365] The server receives the analysis results from the emotion engine and adjusts the content and tone of the copy robot's responses to match the user's emotional state. For example, if the user is feeling stressed, the system will provide high-priority support or simplified information.

[0366] Furthermore, users can review the information provided on their devices and provide immediate feedback, which is then used to retrain the AI ​​model. The interaction between user feedback and sentiment analysis can improve the overall accuracy of the system and user satisfaction.

[0367] For example, if a user expresses anxiety or stress as a project deadline approaches, the server will suggest ways to adjust task priorities or reallocate resources. In this way, the present invention provides the utilization of business data and flexible responses that respond to user emotions, thereby improving business efficiency and employee well-being.

[0368] The following describes the processing flow.

[0369] Step 1:

[0370] The server automatically collects employee work data from project management systems, email servers, chat tools, etc., and stores it in a database.

[0371] Step 2:

[0372] The server preprocesses the collected business data. It performs data cleansing, removing duplicates and imputing missing values ​​to create a ready dataset for analysis.

[0373] Step 3:

[0374] The server extracts features from pre-processed data. This process uses natural language processing techniques to detect important keywords and topics from text data, identifying business trends and frequently used actions.

[0375] Step 4:

[0376] The server utilizes the feature extraction results to train the AI ​​model. This training uses machine learning algorithms to predict optimal actions in business operations and improve the model's pattern recognition capabilities to enhance its usefulness.

[0377] Step 5:

[0378] The server generates virtual copy robots from trained AI models. These robots are capable of mimicking specific tasks and continuing normal operations.

[0379] Step 6:

[0380] The server activates an emotion engine to analyze the user's emotional state in real time from their facial expressions, tone of voice, and text input. Based on this analysis, it identifies the user's emotions.

[0381] Step 7:

[0382] Based on the sentiment analysis results, the server appropriately adjusts the tone and content of the responses provided by the copy robot. For example, if the user is feeling stressed, it will offer more friendly, concise, and gentle suggestions.

[0383] Step 8:

[0384] Users receive the provided business support information through their devices and make corrections or provide feedback as needed. This feedback is immediately transmitted to the server.

[0385] Step 9:

[0386] The server further retrains the AI ​​model based on user feedback and sentiment analysis results. This aims to improve the overall accuracy of the system and enhance user satisfaction.

[0387] (Example 2)

[0388] 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".

[0389] In today's work environment, vast amounts of data are generated, and efficient work execution and the maintenance of employees' mental health are required, but conventional systems have not adequately addressed these challenges. In particular, there is a problem in appropriately combining the effective use of data with feedback that responds to users' emotions. Therefore, there is a need to develop systems that provide more adaptive and human-centered work support.

[0390] 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.

[0391] In this invention, the server includes information gathering means for collecting business data, information preprocessing means for preprocessing the information, and feature extraction means for extracting features from the preprocessed information. This enables business support tailored to the user's emotional state, as well as effective business support based on the collected data.

[0392] "Information gathering means" refers to a function or process for automatically collecting data related to business operations from various information sources.

[0393] "Information preprocessing means" refers to a function that corrects or adjusts incomplete data in order to convert collected data into an analyzable format.

[0394] A "feature extraction method" is a technique for identifying important patterns and trends from pre-processed data and extracting elements necessary for analysis and model training.

[0395] "Analysis methods" refer to the process of systematically investigating business patterns from data obtained through feature extraction methods and deriving useful insights.

[0396] "Training methods" refer to the process of adjusting an AI model by applying machine learning algorithms based on the results obtained from analysis methods, so that the AI ​​model can function effectively.

[0397] A "generation method" is a mechanism for designing units that virtually perform tasks on behalf of others using trained AI models, and for providing them in an executable form.

[0398] "Emotion analysis means" refers to a technology used to determine a user's emotional state from various input data and to understand that state in real time.

[0399] "Response adjustment means" refers to a function that adjusts the system's response based on emotional data analyzed by emotion analysis means, in order to provide more appropriate support.

[0400] A "feedback system" is a mechanism that accepts user feedback and effectively utilizes that feedback to improve the performance of the system or model.

[0401] The embodiments for carrying out the invention are described in detail below.

[0402] This system provides business support through the collaboration of servers, terminals, and users. First, the server collects business-related data from various sources. These sources include project management tools, email systems, chat applications, and daily reporting systems. The collected data is stored in databases such as PostgreSQL and MySQL.

[0403] The server performs several processes on the collected data. First, it cleanses the data, correcting incomplete data and organizing the necessary information. Next, it performs feature extraction using libraries such as Scikit-learn. This extracts important features of business activities, and then it trains an AI model using TensorFlow or PyTorch. The trained model generates a virtual replacement work unit, or copy robot, to perform the tasks on behalf of the business.

[0404] Users interact with the system using a terminal. The system incorporates emotion analysis capabilities, using a camera and microphone to estimate the user's emotional state from their face and voice. Based on this information, the server can adjust the copy robot's responses to provide appropriate information and support.

[0405] For example, if a user expresses anxiety as a project deadline approaches, the server will readjust the task priorities and suggest reallocating resources. This allows the user to perform their tasks with reduced stress. An example of a prompt message would be: "Project X is nearing its deadline, and user A is feeling anxious. How will the system respond?"

[0406] In this way, the present invention enables the realization of a system that provides effective and flexible business support by combining data collection, processing, analysis, and responses to user emotions.

[0407] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0408] Step 1:

[0409] The server automatically collects business data from sources such as project management tools, email, chat applications, and daily reports. The data received from these sources is imported into the server in a structured format (e.g., JSON, CSV). Input is raw data from various sources, and output is data stored in a central database.

[0410] Step 2:

[0411] The server first performs data cleansing on the collected data. Specifically, this involves correcting incomplete data and deleting unimportant data. The input is the collected raw data, and the output is clean data with defects corrected. This results in a dataset that can be analyzed and feature extracted.

[0412] Step 3:

[0413] The server performs feature extraction on clean data. During this process, it uses data analysis libraries such as Scikit-learn to extract business trends and patterns. The input is a clean dataset, and the output is a feature vector or an analyzable set of information. This information is then used to train an AI model.

[0414] Step 4:

[0415] The server trains an AI model based on the data obtained through feature extraction. For example, it uses TensorFlow or PyTorch to select an appropriate algorithm and optimize the model's parameters. The input is a feature vector and related information, and the output is a trained AI model for performing business support.

[0416] Step 5:

[0417] The server uses a trained AI model to generate a virtual alternative unit of work. This prepares it to take over tasks even when the user is absent or busy. The input is the trained AI model, and the output is a viable alternative unit of work.

[0418] Step 6:

[0419] When a user interacts with the device, the server activates an emotion analysis engine that analyzes the user's facial expressions and voice input. The input is real-time data about the user's emotional state, and the output is the analyzed emotion trend. This feeds the system with the user's emotional changes.

[0420] Step 7:

[0421] The server adjusts the content and tone of its alternative work units based on the user's emotions. For stressed users, it presents simplified, high-priority tasks. The input is user emotion analysis data, and the output is a user-specific response and support plan.

[0422] Step 8:

[0423] Users provide feedback on the information and support offered and send it to the server. Based on this feedback, the AI ​​model is retrained. The input is the user's feedback data, and the output is the improved AI model and the system's overall business support capabilities.

[0424] (Application Example 2)

[0425] 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."

[0426] Current business support systems do not take into account employees' emotions or stress levels, which can lead to decreased work efficiency. Furthermore, there is a lack of systems capable of analyzing emotions and providing appropriate work support based on those analyses.

[0427] 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.

[0428] In this invention, the server includes information acquisition means, information preprocessing means, feature extraction means, pattern analysis means, model training means, device generation means, accuracy evaluation means, result presentation means, information deficiency detection means, emotion analysis means, support information provision means, and work efficiency adjustment means. This makes it possible to analyze the emotional state of employees in real time and provide appropriate support information via smart devices when providing work support based on the acquisition and analysis of work information.

[0429] "Information acquisition means" refers to devices and methods for collecting large amounts of business information.

[0430] "Information preprocessing means" refers to methods or devices for preparing acquired business information into a state that can be analyzed.

[0431] A "feature extraction means" is a method or device for finding specific patterns or attributes from pre-processed business information.

[0432] A "pattern analysis tool" is a method or device for analyzing business processes and trends based on extracted features.

[0433] "Model training means" refers to methods and devices for constructing and optimizing AI models using analysis results.

[0434] "Device generation means" refers to a method or device that uses a trained AI model to create a virtual automated device.

[0435] "Accuracy evaluation means" refers to a method or apparatus for determining the accuracy of the response or operation of a generated device.

[0436] "Result presentation means" refers to methods or devices for visually or audibly showing the results of an evaluation to the user.

[0437] "Information deficiency identification methods" are methods or devices that identify missing information or data based on the presented results.

[0438] "Emotional analysis tools" refer to methods or devices that analyze facial expressions, voice tone, etc., in order to understand the emotional state of employees.

[0439] "Support information provision means" refers to methods or devices that present information to provide appropriate support based on the results of emotion analysis.

[0440] "Methods for adjusting work efficiency" refer to methods or devices that adjust work processes to maximize efficiency based on the emotional state of employees and analysis results.

[0441] In this invention, a server is central to realizing a business support system. First, information related to business operations is collected by an information acquisition means. This information includes employee work progress data and customer data. The server uses an information preprocessing means to organize the collected information and convert it into a format suitable for analysis. Specifically, a data preprocessing library is used as the software.

[0442] Next, the server uses feature extraction to extract specific patterns from the pre-processed information. These patterns play a crucial role in subsequent analysis. Pattern analysis is then used to analyze employee work patterns and customer behavior patterns. Machine learning algorithms are employed in this process.

[0443] Using a model training method, an AI model is trained based on the analysis results. This training optimizes how employees and customers respond based on the patterns discovered. The trained AI model then uses a device generation method to create a virtual automation device that provides business support.

[0444] Smart glasses and other devices are worn by employees and analyze their emotional state in real time through emotion analysis tools. They utilize facial recognition cameras and voice recognition microphones, and the software includes an emotion analysis engine. Based on the analysis results, the server transmits support information to the device via a support information provision system. This information enables employees to perform appropriate tasks.

[0445] As a concrete example, in a busy store on a Saturday afternoon, the AI ​​could suggest priority customer service or quicker procedures to employees who are feeling stressed. An example of a prompt message would be, "Analyze the employee's stress level and provide immediately available support information."

[0446] This will lead to improved work efficiency and reduced stress for employees.

[0447] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0448] Step 1:

[0449] The server uses data acquisition methods to collect raw data related to business operations. Inputs include employee work progress and customer data. Outputs are imported into the system as raw datasets. Specifically, data is collected from project management tools and customer management systems via APIs.

[0450] Step 2:

[0451] The server uses data preprocessing to format the collected raw data. The input is the raw dataset collected in step 1. The output is data processed into an analyzable format. Specifically, data cleansing is performed to remove duplicate data and impute missing data.

[0452] Step 3:

[0453] The server uses a feature extraction method to extract features from pre-processed data. The input is the data processed in step 2. The output is the feature data extracted for analysis. Specifically, it selects and quantifies features for machine learning.

[0454] Step 4:

[0455] The server uses pattern analysis tools to analyze patterns from the extracted feature data. The input is the feature data obtained in step 3. The output is business trends and predictive information. Specifically, it uses time series analysis and clustering techniques to analyze business progress and customer behavior patterns.

[0456] Step 5:

[0457] The server uses a model training method to train an AI model based on the analysis results. The input is the analysis results obtained in step 4. The output is the trained AI model. Specifically, it uses a neural network to optimize the model and improve prediction accuracy.

[0458] Step 6:

[0459] The server uses a device generation mechanism to generate a virtual automation device based on a trained AI model. The input is the AI ​​model trained in step 5. The output is a virtual automation device for business support. Specifically, the AI ​​model is deployed to a cloud environment and linked to business systems via an API.

[0460] Step 7:

[0461] The terminal uses emotion analysis capabilities to analyze the emotional state of employees in real time. The input is emotion data from the terminal's camera and microphone. The output is the analyzed emotional state data. Specifically, it analyzes facial expressions from a video stream and analyzes the tone of audio data.

[0462] Step 8:

[0463] The server uses a support information provision system to send support information to the terminal based on the emotional state. The input is the emotional state data obtained in step 7. The output is the support information displayed on the smart device. Specifically, the server generates support information and provides it to the terminal via push notification.

[0464] Step 9:

[0465] The user readjusts the efficiency of their work based on the support information provided through the work efficiency adjustment tool. The input is the support information presented in step 8. The output is the optimized work process. Specifically, this involves reviewing the schedule and resource allocation, and resetting the core of the work.

[0466] 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.

[0467] 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.

[0468] 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.

[0469] [Third Embodiment]

[0470] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0471] 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.

[0472] 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).

[0473] 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.

[0474] 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.

[0475] 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).

[0476] 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.

[0477] 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.

[0478] 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.

[0479] 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.

[0480] 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.

[0481] 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".

[0482] As an embodiment of the present invention, a system utilizing AI for the purpose of supporting employees' work is provided. This system functions through the collaborative efforts of a server, a terminal, and a user.

[0483] First, the server collects various types of business data generated within the company or organization. This includes project management tools, emails, internal chats, and daily report data. The collected data is used as a record of work activities and communication history.

[0484] Next, the server preprocesses the collected data. By removing noise and imputing missing values, it prepares the data for highly accurate analysis. Features are extracted from the preprocessed data, revealing common patterns in business operations and specific decision-making styles.

[0485] Next, the server trains an AI model using a machine learning algorithm based on the feature extraction results. This AI model has the ability to generate the most appropriate response for a specific task or situation. After the model is sufficiently trained, a virtual copy robot is generated based on it.

[0486] Copy robots are generated to support business continuity and can mimic and supplement tasks according to employee instructions. They also predict and suggest solutions to challenges that arise during work execution, supporting rapid decision-making.

[0487] The server monitors the responses provided by the copy robot and evaluates their accuracy. This evaluation is performed through comparison with past data and matching with similar patterns. This allows for fine-tuning as needed while maintaining the accuracy of the responses.

[0488] Users can view evaluation results provided by the server on their devices. The evaluation results visualize trends and characteristics in business operations, with the aim of helping users improve their work processes. Furthermore, feedback provided by users is processed on the server and used to improve the accuracy of the AI ​​model.

[0489] As a concrete example, if an employee suddenly takes leave, a copy robot is generated to take over their duties. The user (supervisor or substitute employee) can then manage multiple tasks simultaneously while accepting suggestions from the server to continue working. In this way, the present invention makes it possible to improve the efficiency and continuity of operations within an organization.

[0490] The following describes the processing flow.

[0491] Step 1:

[0492] The server collects business data from multiple sources within the company. It periodically extracts data from project management tools, email servers, chat applications, daily reporting systems, etc., and stores it in a central database.

[0493] Step 2:

[0494] The server performs data cleansing on the collected data. Specifically, it removes duplicate data, corrects data containing errors, and estimates and imputes missing values ​​to improve data integrity and accuracy.

[0495] Step 3:

[0496] The server extracts features from the pre-processed data. This involves using natural language processing techniques to identify keywords and themes from text data and generate elements to understand business patterns and trends.

[0497] Step 4:

[0498] The server uses the feature extraction results to train a machine learning model. In this process, a learning algorithm based on historical data is used to teach the model the optimal methods for handling business operations and solving problems.

[0499] Step 5:

[0500] The server generates virtual copy robots based on trained AI models. These copy robots have the ability to mimic the tasks performed by employees and provide support while maintaining consistency in those tasks.

[0501] Step 6:

[0502] Users review the business proposals and responses generated by the copy robot on their terminals and make revisions or approvals as needed. User feedback at this stage is sent to the server.

[0503] Step 7:

[0504] The server analyzes user feedback on the copy robot's responses and evaluates and adjusts the AI ​​model. This evaluation includes comparing it to past responses to verify accuracy.

[0505] Step 8:

[0506] The server presents users with trends derived from evaluation results and analysis of business data. This allows users to identify areas for improvement in their work and further streamline their operations.

[0507] (Example 1)

[0508] 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."

[0509] In modern business activities, the complexity of operations and the diversification of information are progressing, and consequently, efficient work execution is required. However, traditional methods require a great deal of time and effort, making it difficult to provide effective support for improving the continuity and productivity of operations. Furthermore, it is difficult to respond quickly to sudden handovers of tasks or problems that arise during the execution of tasks. As a result, the risk of business stagnation and errors is increasing.

[0510] 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.

[0511] In this invention, the server includes information gathering means for collecting various information related to the business, information preprocessing means for processing the information so that it can be analyzed with high accuracy, and feature extraction means for extracting important features from the preprocessed information. This enables the generation of an AI model that efficiently and continuously supports the business, and rapid problem solving by a virtual proxy agent.

[0512] "Information gathering means" refers to devices or software that have the function of efficiently collecting various types of business data related to corporate activities.

[0513] "Information preprocessing means" refers to means of performing data processing to improve the accuracy of collected business data and to convert it into an analyzable format.

[0514] A "feature extraction means" is a device or method for identifying important patterns and trends from pre-processed data and extracting features that can be used in business operations.

[0515] A "model formation method" is a means of constructing an AI model using machine learning based on extracted features.

[0516] "Agent generation means" refers to a device or method that generates a virtual proxy agent to provide business support using a trained AI model.

[0517] "Validity assessment means" refers to a device or method for evaluating the accuracy and applicability of a solution provided by a virtual proxy agent.

[0518] "Result delivery means" refers to a device or function for providing the results of a validity assessment to the user visually or informatively.

[0519] A "means for identifying information deficiencies" refers to a device or method for identifying and presenting information that is necessary for business operations but is lacking, based on the results provided.

[0520] "Regression information" refers to feedback provided by users, which is used to improve the system and rebuild the AI ​​model.

[0521] As an embodiment of the present invention, a system utilizing artificial intelligence (AI) for the purpose of supporting business operations is provided. This system functions through the cooperation of a server, terminals, and users. The server collects information from various data sources used within the company. In this embodiment, information is collected from project management tools, email, internal chat, daily reports, etc. API integration and database queries are used in this collection process.

[0522] The server processes the collected information, removing unnecessary data and filling in missing data. To create an environment that enables highly accurate data analysis, data cleaning techniques using Python and data formatting using SQL are employed. Next, the server extracts features from the pre-processed data to clarify important business patterns. Natural language processing techniques are used to analyze the text data and generate business-related keywords and phrases.

[0523] Next, the server forms a machine learning model based on the feature extraction results. This process utilizes machine learning libraries such as TensorFlow and PyTorch to train the AI ​​model to adapt to specific business situations. The well-trained AI model is then used to generate a virtual surrogate agent. This agent complements the user's work and makes predictions and suggestions regarding the problem.

[0524] For example, if an employee suddenly takes leave, the server generates an agent to take over that employee's duties, helping the supervisor and the substitute employee (user) manage multiple tasks simultaneously. To further streamline this support process, the server evaluates the validity of the answers provided by the copy robot and allows the user to view the evaluation results on their terminal. The evaluation results include comparisons with past data and matching similar patterns.

[0525] User feedback is processed by the server as regression information and used to further improve the accuracy of the AI ​​model. This increases the efficiency and continuity of operations and provides higher quality AI services. In this embodiment, when evaluating the generated AI model and generating suggestions, a prompt message such as "Please suggest the next steps for the progress of Project X. The current issue is a lack of communication among members, which is causing schedule delays" can be used.

[0526] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0527] Step 1:

[0528] The server collects business-related information from sources such as the company's project management tools, emails, internal chats, and daily reports. Inputs include data obtained via APIs and database connections. Specifically, it collects information such as project task progress and email correspondence. This allows it to output basic data for understanding the overall business situation.

[0529] Step 2:

[0530] The server processes the collected data by removing noise and imputing missing values. The input is the raw business data collected in step 1. Specifically, it removes unnecessary HTML tags and duplicate data, and fills in missing values ​​with values ​​from similar past data to output clean, analyzable data.

[0531] Step 3:

[0532] The server extracts key features from pre-processed data. The input is clean, pre-processed data. For example, it might use natural language processing techniques to extract important keywords from email content or quantify project progress patterns. This process outputs feature data that includes business-specific key metrics.

[0533] Step 4:

[0534] The server trains an AI model using feature data. The input is the feature data extracted in step 3. Specifically, it uses TensorFlow to execute machine learning algorithms and learn decision-making criteria suitable for efficient task execution. As a result of this process, an AI model specialized for business support is output.

[0535] Step 5:

[0536] The server generates a virtual proxy agent from the trained AI model. The input is the AI ​​model obtained in step 4. Specifically, it outputs solutions that this agent provides while mimicking project task management and progress evaluation. This step outputs an agent in a format that allows the user to receive work assistance.

[0537] Step 6:

[0538] The server evaluates the agent's proposal and verifies its accuracy. The input is the solution provided by the agent. Specifically, it verifies its validity by comparing it with past data and outputs the evaluation results. This result can be used by the user as a basis for decision-making based on business performance and other factors.

[0539] Step 7:

[0540] Users view evaluation results on their devices and provide feedback. The input is the evaluation results from the server. Specifically, they send regression information to the server regarding the practicality and areas for improvement of the agent's solution. This generates feedback data that helps further improve the AI ​​model.

[0541] (Application Example 1)

[0542] 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."

[0543] Modern logistics centers require complex operational processes and diverse work procedures, necessitating support for efficient and accurate operation. In particular, providing real-time guidance on optimal work procedures to improve efficiency and ensure accuracy is a key challenge. To address this challenge, a business support system utilizing the latest technology is essential.

[0544] 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.

[0545] In this invention, the server includes information gathering means, information preprocessing means, and feature extraction means. This enables the presentation of optimal work procedures to workers in a logistics center in real time, allowing for efficient work execution.

[0546] "Information gathering methods" refer to the process of collecting various operational information at a logistics center and understanding the business processes.

[0547] "Information preprocessing means" refers to the process of removing noise and missing values ​​from collected information and preparing it for analysis.

[0548] "Feature extraction methods" are steps that identify important patterns and characteristics from pre-processed information and utilize them to improve business processes.

[0549] A "process analysis tool" is a function that analyzes business patterns in detail based on extracted characteristics and constructs the optimal procedure.

[0550] "Model training methods" refer to processes that utilize process analysis results to train AI models, enabling them to predict business procedures with high accuracy.

[0551] The "assistant generation method" is a process that generates a virtual business support assistant using a trained AI model.

[0552] "Accuracy evaluation methods" are techniques for evaluating whether the output generated by the assistant is accurate and for confirming the quality of the work.

[0553] A "procedure presentation method" is a function that presents the optimal work procedure to the worker via a smart terminal, thereby improving work efficiency.

[0554] "Information deficiency identification methods" are processes that aim to improve work accuracy by pointing out information deficiencies and areas for improvement based on the presented results.

[0555] The system for realizing this invention is a business support system utilizing smart terminals in a logistics center. The server collects a large amount of business information generated within the logistics center through information collection means. This information includes worker movement data and data related to the flow of goods. The collected information is converted into a format that is easy to analyze by removing noise and missing values ​​using information preprocessing means and organizing the data.

[0556] The server uses feature extraction means to extract features from pre-processed information. In this process, important patterns and characteristics in the logistics center's business processes become apparent. Based on this, process analysis means perform a detailed pattern analysis of the operations to derive the optimal work procedure.

[0557] By training an AI model from these analysis results using a model training method, efficient task execution becomes possible. The trained AI model uses an assistant generation method to create a virtual task support assistant, which provides generated instructions to the logged-in worker.

[0558] The smart terminals used by workers display the optimal work procedures in real time via a procedure presentation system, streamlining the workflow. Furthermore, the assistant's output is verified using an accuracy evaluation system to maintain the quality of work. Based on the presented procedures, a system for identifying missing information specifically points out necessary information and areas for improvement.

[0559] As a concrete example, worker B at a logistics center wears smart glasses, and the AI ​​presents work procedures to streamline a new packing process. Worker B performs the work according to the presented procedures, and the server receives the results along with feedback. Based on this feedback, the server fine-tunes the AI ​​model to further improve operational efficiency.

[0560] Examples of prompt statements are as follows:

[0561] "What is the optimal order of these work steps?"

[0562] "What instructions should I give to worker B?"

[0563] "How will the model be improved based on the feedback?"

[0564] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0565] Step 1:

[0566] The server collects operational and material flow data in real time from information gathering devices within the logistics center. This data is obtained via sensors and RFID from each work station on site. The input is raw data, and the output is pre-processed raw data.

[0567] Step 2:

[0568] The server denoises and imputes missing values ​​in the raw data collected using preprocessing tools. Filtering techniques are used for denoising, and missing values ​​are handled using mean imputation. The input is raw data, and the output is a clean, analyzable dataset.

[0569] Step 3:

[0570] The server utilizes feature extraction methods to apply statistical techniques to extract important features from a clean dataset. For example, it analyzes data distribution, frequency, and correlation. The input is clean data, and the output is a feature vector.

[0571] Step 4:

[0572] The server analyzes feature vectors using process analysis tools and detects patterns. Here, a machine learning clustering algorithm is used to categorize business processes. The input is feature vectors, and the output is a prototype of a business pattern.

[0573] Step 5:

[0574] The server trains a new AI model from the analysis results using a model training method. This AI model utilizes supervised learning to capture business patterns, which are the output. The input is a prototype of the business pattern, and the output is the trained AI model.

[0575] Step 6:

[0576] The server generates a virtual business support assistant from a trained AI model based on the assistant generation mechanism and sends it to the smart terminal. This assistant has the function of creating instructions for each work step. The input is the trained AI model, and the output is a program for the smart terminal acting as a business support assistant.

[0577] Step 7:

[0578] The terminal uses a procedure presentation system to provide the worker with work procedures optimized for them in real time. Visual information is displayed on the smart glasses' screen. Input is the instructions of the work support assistant, and output is the work procedure information provided to the worker.

[0579] Step 8:

[0580] The user evaluates the accuracy of the assistant's output through an accuracy evaluation tool and records the feedback on the terminal. The input consists of the instructions provided by the assistant and the user's work results, while the output is the result of the accuracy evaluation.

[0581] Step 9:

[0582] The server analyzes the feedback results using information deficiency detection mechanisms and specifies the additional information needed for the next cycle. This enables further improvement of the AI ​​model. The input is the accuracy evaluation result, and the output is a list of information deficiencies.

[0583] 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.

[0584] This invention provides a business support system that considers the processing of business data and the emotions of users. This system works collaboratively with servers, terminals, and users, and in particular, utilizes an emotion engine to reflect the user's state, thereby achieving more flexible and human-centered business support.

[0585] First, the server collects work data from tools that employees use on a daily basis. This includes project management software, email, chat systems, and daily report data. The collected data is stored in a central database and prepared for analysis.

[0586] Next, the data undergoes a series of preprocessing steps. The server performs data cleansing, corrects data defects, and prepares the data for feature extraction. By extracting features from the target data, business patterns are analyzed, and resources are prepared for use in training an AI model. The AI ​​model is then trained to support the most effective business decisions based on these features.

[0587] Based on a trained AI model, the server generates a virtual copy robot. This copy robot is responsible for maintaining consistency and quality of work while taking over the duties of an employee on leave. Simultaneously, the system incorporates an emotion engine that analyzes the user's emotional state in real time from facial recognition, voice tone, or input information.

[0588] The server receives the analysis results from the emotion engine and adjusts the content and tone of the copy robot's responses to match the user's emotional state. For example, if the user is feeling stressed, the system will provide high-priority support or simplified information.

[0589] Furthermore, users can review the information provided on their devices and provide immediate feedback, which is then used to retrain the AI ​​model. The interaction between user feedback and sentiment analysis can improve the overall accuracy of the system and user satisfaction.

[0590] For example, if a user expresses anxiety or stress as a project deadline approaches, the server will suggest ways to adjust task priorities or reallocate resources. In this way, the present invention provides the utilization of business data and flexible responses that respond to user emotions, thereby improving business efficiency and employee well-being.

[0591] The following describes the processing flow.

[0592] Step 1:

[0593] The server automatically collects employee work data from project management systems, email servers, chat tools, etc., and stores it in a database.

[0594] Step 2:

[0595] The server preprocesses the collected business data. It performs data cleansing, removing duplicates and imputing missing values ​​to create a ready dataset for analysis.

[0596] Step 3:

[0597] The server extracts features from pre-processed data. This process uses natural language processing techniques to detect important keywords and topics from text data, identifying business trends and frequently used actions.

[0598] Step 4:

[0599] The server utilizes the feature extraction results to train the AI ​​model. This training uses machine learning algorithms to predict optimal actions in business operations and improve the model's pattern recognition capabilities to enhance its usefulness.

[0600] Step 5:

[0601] The server generates virtual copy robots from trained AI models. These robots are capable of mimicking specific tasks and continuing normal operations.

[0602] Step 6:

[0603] The server activates an emotion engine to analyze the user's emotional state in real time from their facial expressions, tone of voice, and text input. Based on this analysis, it identifies the user's emotions.

[0604] Step 7:

[0605] Based on the sentiment analysis results, the server appropriately adjusts the tone and content of the responses provided by the copy robot. For example, if the user is feeling stressed, it will offer more friendly, concise, and gentle suggestions.

[0606] Step 8:

[0607] Users receive the provided business support information through their devices and make corrections or provide feedback as needed. This feedback is immediately transmitted to the server.

[0608] Step 9:

[0609] The server further retrains the AI ​​model based on user feedback and sentiment analysis results. This aims to improve the overall accuracy of the system and enhance user satisfaction.

[0610] (Example 2)

[0611] 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."

[0612] In today's work environment, vast amounts of data are generated, and efficient work execution and the maintenance of employees' mental health are required, but conventional systems have not adequately addressed these challenges. In particular, there is a problem in appropriately combining the effective use of data with feedback that responds to users' emotions. Therefore, there is a need to develop systems that provide more adaptive and human-centered work support.

[0613] 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.

[0614] In this invention, the server includes information gathering means for collecting business data, information preprocessing means for preprocessing the information, and feature extraction means for extracting features from the preprocessed information. This enables business support tailored to the user's emotional state, as well as effective business support based on the collected data.

[0615] "Information gathering means" refers to a function or process for automatically collecting data related to business operations from various information sources.

[0616] "Information preprocessing means" refers to a function that corrects or adjusts incomplete data in order to convert collected data into an analyzable format.

[0617] A "feature extraction method" is a technique for identifying important patterns and trends from pre-processed data and extracting elements necessary for analysis and model training.

[0618] "Analysis methods" refer to the process of systematically investigating business patterns from data obtained through feature extraction methods and deriving useful insights.

[0619] "Training methods" refer to the process of adjusting an AI model by applying machine learning algorithms based on the results obtained from analysis methods, so that the AI ​​model can function effectively.

[0620] A "generation method" is a mechanism for designing units that virtually perform tasks on behalf of others using trained AI models, and for providing them in an executable form.

[0621] "Emotion analysis means" refers to a technology used to determine a user's emotional state from various input data and to understand that state in real time.

[0622] "Response adjustment means" refers to a function that adjusts the system's response based on emotional data analyzed by emotion analysis means, in order to provide more appropriate support.

[0623] A "feedback system" is a mechanism that accepts user feedback and effectively utilizes that feedback to improve the performance of the system or model.

[0624] The embodiments for carrying out the invention are described in detail below.

[0625] This system provides business support through the collaboration of servers, terminals, and users. First, the server collects business-related data from various sources. These sources include project management tools, email systems, chat applications, and daily reporting systems. The collected data is stored in databases such as PostgreSQL and MySQL.

[0626] The server performs several processes on the collected data. First, it cleanses the data, correcting incomplete data and organizing the necessary information. Next, it performs feature extraction using libraries such as Scikit-learn. This extracts important features of business activities, and then it trains an AI model using TensorFlow or PyTorch. The trained model generates a virtual replacement work unit, or copy robot, to perform the tasks on behalf of the business.

[0627] Users interact with the system using a terminal. The system incorporates emotion analysis capabilities, using a camera and microphone to estimate the user's emotional state from their face and voice. Based on this information, the server can adjust the copy robot's responses to provide appropriate information and support.

[0628] For example, if a user expresses anxiety as a project deadline approaches, the server will readjust the task priorities and suggest reallocating resources. This allows the user to perform their tasks with reduced stress. An example of a prompt message would be: "Project X is nearing its deadline, and user A is feeling anxious. How will the system respond?"

[0629] In this way, the present invention enables the realization of a system that provides effective and flexible business support by combining data collection, processing, analysis, and responses to user emotions.

[0630] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0631] Step 1:

[0632] The server automatically collects business data from sources such as project management tools, email, chat applications, and daily reports. The data received from these sources is imported into the server in a structured format (e.g., JSON, CSV). Input is raw data from various sources, and output is data stored in a central database.

[0633] Step 2:

[0634] The server first performs data cleansing on the collected data. Specifically, this involves correcting incomplete data and deleting unimportant data. The input is the collected raw data, and the output is clean data with defects corrected. This results in a dataset that can be analyzed and feature extracted.

[0635] Step 3:

[0636] The server performs feature extraction on clean data. During this process, it uses data analysis libraries such as Scikit-learn to extract business trends and patterns. The input is a clean dataset, and the output is a feature vector or an analyzable set of information. This information is then used to train an AI model.

[0637] Step 4:

[0638] The server trains an AI model based on the data obtained through feature extraction. For example, it uses TensorFlow or PyTorch to select an appropriate algorithm and optimize the model's parameters. The input is a feature vector and related information, and the output is a trained AI model for performing business support.

[0639] Step 5:

[0640] The server uses a trained AI model to generate a virtual alternative unit of work. This prepares it to take over tasks even when the user is absent or busy. The input is the trained AI model, and the output is a viable alternative unit of work.

[0641] Step 6:

[0642] When a user interacts with the device, the server activates an emotion analysis engine that analyzes the user's facial expressions and voice input. The input is real-time data about the user's emotional state, and the output is the analyzed emotion trend. This feeds the system with the user's emotional changes.

[0643] Step 7:

[0644] The server adjusts the content and tone of its alternative work units based on the user's emotions. For stressed users, it presents simplified, high-priority tasks. The input is user emotion analysis data, and the output is a user-specific response and support plan.

[0645] Step 8:

[0646] Users provide feedback on the information and support offered and send it to the server. Based on this feedback, the AI ​​model is retrained. The input is the user's feedback data, and the output is the improved AI model and the system's overall business support capabilities.

[0647] (Application Example 2)

[0648] 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."

[0649] Current business support systems do not take into account employees' emotions or stress levels, which can lead to decreased work efficiency. Furthermore, there is a lack of systems capable of analyzing emotions and providing appropriate work support based on those analyses.

[0650] 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.

[0651] In this invention, the server includes information acquisition means, information preprocessing means, feature extraction means, pattern analysis means, model training means, device generation means, accuracy evaluation means, result presentation means, information deficiency detection means, emotion analysis means, support information provision means, and work efficiency adjustment means. This makes it possible to analyze the emotional state of employees in real time and provide appropriate support information via smart devices when providing work support based on the acquisition and analysis of work information.

[0652] "Information acquisition means" refers to devices and methods for collecting large amounts of business information.

[0653] "Information preprocessing means" refers to methods or devices for preparing acquired business information into a state that can be analyzed.

[0654] A "feature extraction means" is a method or device for finding specific patterns or attributes from pre-processed business information.

[0655] A "pattern analysis tool" is a method or device for analyzing business processes and trends based on extracted features.

[0656] "Model training means" refers to methods and devices for constructing and optimizing AI models using analysis results.

[0657] "Device generation means" refers to a method or device that uses a trained AI model to create a virtual automated device.

[0658] "Accuracy evaluation means" refers to a method or apparatus for determining the accuracy of the response or operation of a generated device.

[0659] "Result presentation means" refers to methods or devices for visually or audibly showing the results of an evaluation to the user.

[0660] "Information deficiency identification methods" are methods or devices that identify missing information or data based on the presented results.

[0661] "Emotional analysis tools" refer to methods or devices that analyze facial expressions, voice tone, etc., in order to understand the emotional state of employees.

[0662] "Support information provision means" refers to methods or devices that present information to provide appropriate support based on the results of emotion analysis.

[0663] "Methods for adjusting work efficiency" refer to methods or devices that adjust work processes to maximize efficiency based on the emotional state of employees and analysis results.

[0664] In this invention, a server is central to realizing a business support system. First, information related to business operations is collected by an information acquisition means. This information includes employee work progress data and customer data. The server uses an information preprocessing means to organize the collected information and convert it into a format suitable for analysis. Specifically, a data preprocessing library is used as the software.

[0665] Next, the server uses feature extraction to extract specific patterns from the pre-processed information. These patterns play a crucial role in subsequent analysis. Pattern analysis is then used to analyze employee work patterns and customer behavior patterns. Machine learning algorithms are employed in this process.

[0666] Using a model training method, an AI model is trained based on the analysis results. This training optimizes how employees and customers respond based on the patterns discovered. The trained AI model then uses a device generation method to create a virtual automation device that provides business support.

[0667] Smart glasses and other devices are worn by employees and analyze their emotional state in real time through emotion analysis tools. They utilize facial recognition cameras and voice recognition microphones, and the software includes an emotion analysis engine. Based on the analysis results, the server transmits support information to the device via a support information provision system. This information enables employees to perform appropriate tasks.

[0668] As a concrete example, in a busy store on a Saturday afternoon, the AI ​​could suggest priority customer service or quicker procedures to employees who are feeling stressed. An example of a prompt message would be, "Analyze the employee's stress level and provide immediately available support information."

[0669] This will lead to improved work efficiency and reduced stress for employees.

[0670] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0671] Step 1:

[0672] The server uses data acquisition methods to collect raw data related to business operations. Inputs include employee work progress and customer data. Outputs are imported into the system as raw datasets. Specifically, data is collected from project management tools and customer management systems via APIs.

[0673] Step 2:

[0674] The server uses data preprocessing to format the collected raw data. The input is the raw dataset collected in step 1. The output is data processed into an analyzable format. Specifically, data cleansing is performed to remove duplicate data and impute missing data.

[0675] Step 3:

[0676] The server uses a feature extraction method to extract features from pre-processed data. The input is the data processed in step 2. The output is the feature data extracted for analysis. Specifically, it selects and quantifies features for machine learning.

[0677] Step 4:

[0678] The server uses pattern analysis tools to analyze patterns from the extracted feature data. The input is the feature data obtained in step 3. The output is business trends and predictive information. Specifically, it uses time series analysis and clustering techniques to analyze business progress and customer behavior patterns.

[0679] Step 5:

[0680] The server uses a model training method to train an AI model based on the analysis results. The input is the analysis results obtained in step 4. The output is the trained AI model. Specifically, it uses a neural network to optimize the model and improve prediction accuracy.

[0681] Step 6:

[0682] The server uses a device generation mechanism to generate a virtual automation device based on a trained AI model. The input is the AI ​​model trained in step 5. The output is a virtual automation device for business support. Specifically, the AI ​​model is deployed to a cloud environment and linked to business systems via an API.

[0683] Step 7:

[0684] The terminal uses emotion analysis capabilities to analyze the emotional state of employees in real time. The input is emotion data from the terminal's camera and microphone. The output is the analyzed emotional state data. Specifically, it analyzes facial expressions from a video stream and analyzes the tone of audio data.

[0685] Step 8:

[0686] The server uses a support information provision system to send support information to the terminal based on the emotional state. The input is the emotional state data obtained in step 7. The output is the support information displayed on the smart device. Specifically, the server generates support information and provides it to the terminal via push notification.

[0687] Step 9:

[0688] The user readjusts the efficiency of their work based on the support information provided through the work efficiency adjustment tool. The input is the support information presented in step 8. The output is the optimized work process. Specifically, this involves reviewing the schedule and resource allocation, and resetting the core of the work.

[0689] 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.

[0690] 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.

[0691] 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.

[0692] [Fourth Embodiment]

[0693] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0694] 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.

[0695] 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).

[0696] 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.

[0697] 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.

[0698] 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).

[0699] 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.

[0700] 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.

[0701] 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.

[0702] 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.

[0703] 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.

[0704] 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.

[0705] 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".

[0706] As an embodiment of the present invention, a system utilizing AI for the purpose of supporting employees' work is provided. This system functions through the collaborative efforts of a server, a terminal, and a user.

[0707] First, the server collects various types of business data generated within the company or organization. This includes project management tools, emails, internal chats, and daily report data. The collected data is used as a record of work activities and communication history.

[0708] Next, the server preprocesses the collected data. By removing noise and imputing missing values, it prepares the data for highly accurate analysis. Features are extracted from the preprocessed data, revealing common patterns in business operations and specific decision-making styles.

[0709] Next, the server trains an AI model using a machine learning algorithm based on the feature extraction results. This AI model has the ability to generate the most appropriate response for a specific task or situation. After the model is sufficiently trained, a virtual copy robot is generated based on it.

[0710] Copy robots are generated to support business continuity and can mimic and supplement tasks according to employee instructions. They also predict and suggest solutions to challenges that arise during work execution, supporting rapid decision-making.

[0711] The server monitors the responses provided by the copy robot and evaluates their accuracy. This evaluation is performed through comparison with past data and matching with similar patterns. This allows for fine-tuning as needed while maintaining the accuracy of the responses.

[0712] Users can view evaluation results provided by the server on their devices. The evaluation results visualize trends and characteristics in business operations, with the aim of helping users improve their work processes. Furthermore, feedback provided by users is processed on the server and used to improve the accuracy of the AI ​​model.

[0713] As a concrete example, if an employee suddenly takes leave, a copy robot is generated to take over their duties. The user (supervisor or substitute employee) can then manage multiple tasks simultaneously while accepting suggestions from the server to continue working. In this way, the present invention makes it possible to improve the efficiency and continuity of operations within an organization.

[0714] The following describes the processing flow.

[0715] Step 1:

[0716] The server collects business data from multiple sources within the company. It periodically extracts data from project management tools, email servers, chat applications, daily reporting systems, etc., and stores it in a central database.

[0717] Step 2:

[0718] The server performs data cleansing on the collected data. Specifically, it removes duplicate data, corrects data containing errors, and estimates and imputes missing values ​​to improve data integrity and accuracy.

[0719] Step 3:

[0720] The server extracts features from the pre-processed data. This involves using natural language processing techniques to identify keywords and themes from text data and generate elements to understand business patterns and trends.

[0721] Step 4:

[0722] The server uses the feature extraction results to train a machine learning model. In this process, a learning algorithm based on historical data is used to teach the model the optimal methods for handling business operations and solving problems.

[0723] Step 5:

[0724] The server generates virtual copy robots based on trained AI models. These copy robots have the ability to mimic the tasks performed by employees and provide support while maintaining consistency in those tasks.

[0725] Step 6:

[0726] Users review the business proposals and responses generated by the copy robot on their terminals and make revisions or approvals as needed. User feedback at this stage is sent to the server.

[0727] Step 7:

[0728] The server analyzes user feedback on the copy robot's responses and evaluates and adjusts the AI ​​model. This evaluation includes comparing it to past responses to verify accuracy.

[0729] Step 8:

[0730] The server presents users with trends derived from evaluation results and analysis of business data. This allows users to identify areas for improvement in their work and further streamline their operations.

[0731] (Example 1)

[0732] 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".

[0733] In modern business activities, the complexity of operations and the diversification of information are progressing, and consequently, efficient work execution is required. However, traditional methods require a great deal of time and effort, making it difficult to provide effective support for improving the continuity and productivity of operations. Furthermore, it is difficult to respond quickly to sudden handovers of tasks or problems that arise during the execution of tasks. As a result, the risk of business stagnation and errors is increasing.

[0734] 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.

[0735] In this invention, the server includes information gathering means for collecting various information related to the business, information preprocessing means for processing the information so that it can be analyzed with high accuracy, and feature extraction means for extracting important features from the preprocessed information. This enables the generation of an AI model that efficiently and continuously supports the business, and rapid problem solving by a virtual proxy agent.

[0736] "Information gathering means" refers to devices or software that have the function of efficiently collecting various types of business data related to corporate activities.

[0737] "Information preprocessing means" refers to means of performing data processing to improve the accuracy of collected business data and to convert it into an analyzable format.

[0738] A "feature extraction means" is a device or method for identifying important patterns and trends from pre-processed data and extracting features that can be used in business operations.

[0739] A "model formation method" is a means of constructing an AI model using machine learning based on extracted features.

[0740] "Agent generation means" refers to a device or method that generates a virtual proxy agent to provide business support using a trained AI model.

[0741] "Validity assessment means" refers to a device or method for evaluating the accuracy and applicability of a solution provided by a virtual proxy agent.

[0742] "Result delivery means" refers to a device or function for providing the results of a validity assessment to the user visually or informatively.

[0743] A "means for identifying information deficiencies" refers to a device or method for identifying and presenting information that is necessary for business operations but is lacking, based on the results provided.

[0744] "Regression information" refers to feedback provided by users, which is used to improve the system and rebuild the AI ​​model.

[0745] As an embodiment of the present invention, a system utilizing artificial intelligence (AI) for the purpose of supporting business operations is provided. This system functions through the cooperation of a server, terminals, and users. The server collects information from various data sources used within the company. In this embodiment, information is collected from project management tools, email, internal chat, daily reports, etc. API integration and database queries are used in this collection process.

[0746] The server processes the collected information, removing unnecessary data and filling in missing data. To create an environment that enables highly accurate data analysis, data cleaning techniques using Python and data formatting using SQL are employed. Next, the server extracts features from the pre-processed data to clarify important business patterns. Natural language processing techniques are used to analyze the text data and generate business-related keywords and phrases.

[0747] Next, the server forms a machine learning model based on the feature extraction results. This process utilizes machine learning libraries such as TensorFlow and PyTorch to train the AI ​​model to adapt to specific business situations. The well-trained AI model is then used to generate a virtual surrogate agent. This agent complements the user's work and makes predictions and suggestions regarding the problem.

[0748] For example, if an employee suddenly takes leave, the server generates an agent to take over that employee's duties, helping the supervisor and the substitute employee (user) manage multiple tasks simultaneously. To further streamline this support process, the server evaluates the validity of the answers provided by the copy robot and allows the user to view the evaluation results on their terminal. The evaluation results include comparisons with past data and matching similar patterns.

[0749] User feedback is processed by the server as regression information and used to further improve the accuracy of the AI ​​model. This increases the efficiency and continuity of operations and provides higher quality AI services. In this embodiment, when evaluating the generated AI model and generating suggestions, a prompt message such as "Please suggest the next steps for the progress of Project X. The current issue is a lack of communication among members, which is causing schedule delays" can be used.

[0750] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0751] Step 1:

[0752] The server collects business-related information from sources such as the company's project management tools, emails, internal chats, and daily reports. Inputs include data obtained via APIs and database connections. Specifically, it collects information such as project task progress and email correspondence. This allows it to output basic data for understanding the overall business situation.

[0753] Step 2:

[0754] The server processes the collected data by removing noise and imputing missing values. The input is the raw business data collected in step 1. Specifically, it removes unnecessary HTML tags and duplicate data, and fills in missing values ​​with values ​​from similar past data to output clean, analyzable data.

[0755] Step 3:

[0756] The server extracts key features from pre-processed data. The input is clean, pre-processed data. For example, it might use natural language processing techniques to extract important keywords from email content or quantify project progress patterns. This process outputs feature data that includes business-specific key metrics.

[0757] Step 4:

[0758] The server trains an AI model using feature data. The input is the feature data extracted in step 3. Specifically, it uses TensorFlow to execute machine learning algorithms and learn decision-making criteria suitable for efficient task execution. As a result of this process, an AI model specialized for business support is output.

[0759] Step 5:

[0760] The server generates a virtual proxy agent from the trained AI model. The input is the AI ​​model obtained in step 4. Specifically, it outputs solutions that this agent provides while mimicking project task management and progress evaluation. This step outputs an agent in a format that allows the user to receive work assistance.

[0761] Step 6:

[0762] The server evaluates the agent's proposal and verifies its accuracy. The input is the solution provided by the agent. Specifically, it verifies its validity by comparing it with past data and outputs the evaluation results. This result can be used by the user as a basis for decision-making based on business performance and other factors.

[0763] Step 7:

[0764] Users view evaluation results on their devices and provide feedback. The input is the evaluation results from the server. Specifically, they send regression information to the server regarding the practicality and areas for improvement of the agent's solution. This generates feedback data that helps further improve the AI ​​model.

[0765] (Application Example 1)

[0766] 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".

[0767] Modern logistics centers require complex operational processes and diverse work procedures, necessitating support for efficient and accurate operation. In particular, providing real-time guidance on optimal work procedures to improve efficiency and ensure accuracy is a key challenge. To address this challenge, a business support system utilizing the latest technology is essential.

[0768] 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.

[0769] In this invention, the server includes information gathering means, information preprocessing means, and feature extraction means. This enables the presentation of optimal work procedures to workers in a logistics center in real time, allowing for efficient work execution.

[0770] "Information gathering methods" refer to the process of collecting various operational information at a logistics center and understanding the business processes.

[0771] "Information preprocessing means" refers to the process of removing noise and missing values ​​from collected information and preparing it for analysis.

[0772] "Feature extraction methods" are steps that identify important patterns and characteristics from pre-processed information and utilize them to improve business processes.

[0773] A "process analysis tool" is a function that analyzes business patterns in detail based on extracted characteristics and constructs the optimal procedure.

[0774] "Model training methods" refer to processes that utilize process analysis results to train AI models, enabling them to predict business procedures with high accuracy.

[0775] The "assistant generation method" is a process that generates a virtual business support assistant using a trained AI model.

[0776] "Accuracy evaluation methods" are techniques for evaluating whether the output generated by the assistant is accurate and for confirming the quality of the work.

[0777] A "procedure presentation method" is a function that presents the optimal work procedure to the worker via a smart terminal, thereby improving work efficiency.

[0778] "Information deficiency identification methods" are processes that aim to improve work accuracy by pointing out information deficiencies and areas for improvement based on the presented results.

[0779] The system for realizing this invention is a business support system utilizing smart terminals in a logistics center. The server collects a large amount of business information generated within the logistics center through information collection means. This information includes worker movement data and data related to the flow of goods. The collected information is converted into a format that is easy to analyze by removing noise and missing values ​​using information preprocessing means and organizing the data.

[0780] The server uses feature extraction means to extract features from pre-processed information. In this process, important patterns and characteristics in the logistics center's business processes become apparent. Based on this, process analysis means perform a detailed pattern analysis of the operations to derive the optimal work procedure.

[0781] By training an AI model from these analysis results using a model training method, efficient task execution becomes possible. The trained AI model uses an assistant generation method to create a virtual task support assistant, which provides generated instructions to the logged-in worker.

[0782] The smart terminals used by workers display the optimal work procedures in real time via a procedure presentation system, streamlining the workflow. Furthermore, the assistant's output is verified using an accuracy evaluation system to maintain the quality of work. Based on the presented procedures, a system for identifying missing information specifically points out necessary information and areas for improvement.

[0783] As a concrete example, worker B at a logistics center wears smart glasses, and the AI ​​presents work procedures to streamline a new packing process. Worker B performs the work according to the presented procedures, and the server receives the results along with feedback. Based on this feedback, the server fine-tunes the AI ​​model to further improve operational efficiency.

[0784] Examples of prompt statements are as follows:

[0785] "What is the optimal order of these work steps?"

[0786] "What instructions should I give to worker B?"

[0787] "How will the model be improved based on the feedback?"

[0788] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0789] Step 1:

[0790] The server collects operational and material flow data in real time from information gathering devices within the logistics center. This data is obtained via sensors and RFID from each work station on site. The input is raw data, and the output is pre-processed raw data.

[0791] Step 2:

[0792] The server denoises and imputes missing values ​​in the raw data collected using preprocessing tools. Filtering techniques are used for denoising, and missing values ​​are handled using mean imputation. The input is raw data, and the output is a clean, analyzable dataset.

[0793] Step 3:

[0794] The server utilizes feature extraction methods to apply statistical techniques to extract important features from a clean dataset. For example, it analyzes data distribution, frequency, and correlation. The input is clean data, and the output is a feature vector.

[0795] Step 4:

[0796] The server analyzes feature vectors using process analysis tools and detects patterns. Here, a machine learning clustering algorithm is used to categorize business processes. The input is feature vectors, and the output is a prototype of a business pattern.

[0797] Step 5:

[0798] The server trains a new AI model from the analysis results using a model training method. This AI model utilizes supervised learning to capture business patterns, which are the output. The input is a prototype of the business pattern, and the output is the trained AI model.

[0799] Step 6:

[0800] The server generates a virtual business support assistant from a trained AI model based on the assistant generation mechanism and sends it to the smart terminal. This assistant has the function of creating instructions for each work step. The input is the trained AI model, and the output is a program for the smart terminal acting as a business support assistant.

[0801] Step 7:

[0802] The terminal uses a procedure presentation system to provide the worker with work procedures optimized for them in real time. Visual information is displayed on the smart glasses' screen. Input is the instructions of the work support assistant, and output is the work procedure information provided to the worker.

[0803] Step 8:

[0804] The user evaluates the accuracy of the assistant's output through an accuracy evaluation tool and records the feedback on the terminal. The input consists of the instructions provided by the assistant and the user's work results, while the output is the result of the accuracy evaluation.

[0805] Step 9:

[0806] The server analyzes the feedback results using information deficiency detection mechanisms and specifies the additional information needed for the next cycle. This enables further improvement of the AI ​​model. The input is the accuracy evaluation result, and the output is a list of information deficiencies.

[0807] 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.

[0808] This invention provides a business support system that considers the processing of business data and the emotions of users. This system works collaboratively with servers, terminals, and users, and in particular, utilizes an emotion engine to reflect the user's state, thereby achieving more flexible and human-centered business support.

[0809] First, the server collects work data from tools that employees use on a daily basis. This includes project management software, email, chat systems, and daily report data. The collected data is stored in a central database and prepared for analysis.

[0810] Next, the data undergoes a series of preprocessing steps. The server performs data cleansing, corrects data defects, and prepares the data for feature extraction. By extracting features from the target data, business patterns are analyzed, and resources are prepared for use in training an AI model. The AI ​​model is then trained to support the most effective business decisions based on these features.

[0811] Based on a trained AI model, the server generates a virtual copy robot. This copy robot is responsible for maintaining consistency and quality of work while taking over the duties of an employee on leave. Simultaneously, the system incorporates an emotion engine that analyzes the user's emotional state in real time from facial recognition, voice tone, or input information.

[0812] The server receives the analysis results from the emotion engine and adjusts the content and tone of the copy robot's responses to match the user's emotional state. For example, if the user is feeling stressed, the system will provide high-priority support or simplified information.

[0813] Furthermore, users can review the information provided on their devices and provide immediate feedback, which is then used to retrain the AI ​​model. The interaction between user feedback and sentiment analysis can improve the overall accuracy of the system and user satisfaction.

[0814] For example, if a user expresses anxiety or stress as a project deadline approaches, the server will suggest ways to adjust task priorities or reallocate resources. In this way, the present invention provides the utilization of business data and flexible responses that respond to user emotions, thereby improving business efficiency and employee well-being.

[0815] The following describes the processing flow.

[0816] Step 1:

[0817] The server automatically collects employee work data from project management systems, email servers, chat tools, etc., and stores it in a database.

[0818] Step 2:

[0819] The server preprocesses the collected business data. It performs data cleansing, removing duplicates and imputing missing values ​​to create a ready dataset for analysis.

[0820] Step 3:

[0821] The server extracts features from pre-processed data. This process uses natural language processing techniques to detect important keywords and topics from text data, identifying business trends and frequently used actions.

[0822] Step 4:

[0823] The server utilizes the feature extraction results to train the AI ​​model. This training uses machine learning algorithms to predict optimal actions in business operations and improve the model's pattern recognition capabilities to enhance its usefulness.

[0824] Step 5:

[0825] The server generates virtual copy robots from trained AI models. These robots are capable of mimicking specific tasks and continuing normal operations.

[0826] Step 6:

[0827] The server activates an emotion engine to analyze the user's emotional state in real time from their facial expressions, tone of voice, and text input. Based on this analysis, it identifies the user's emotions.

[0828] Step 7:

[0829] Based on the sentiment analysis results, the server appropriately adjusts the tone and content of the responses provided by the copy robot. For example, if the user is feeling stressed, it will offer more friendly, concise, and gentle suggestions.

[0830] Step 8:

[0831] Users receive the provided business support information through their devices and make corrections or provide feedback as needed. This feedback is immediately transmitted to the server.

[0832] Step 9:

[0833] The server further retrains the AI ​​model based on user feedback and sentiment analysis results. This aims to improve the overall accuracy of the system and enhance user satisfaction.

[0834] (Example 2)

[0835] 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".

[0836] In today's work environment, vast amounts of data are generated, and efficient work execution and the maintenance of employees' mental health are required, but conventional systems have not adequately addressed these challenges. In particular, there is a problem in appropriately combining the effective use of data with feedback that responds to users' emotions. Therefore, there is a need to develop systems that provide more adaptive and human-centered work support.

[0837] 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.

[0838] In this invention, the server includes information gathering means for collecting business data, information preprocessing means for preprocessing the information, and feature extraction means for extracting features from the preprocessed information. This enables business support tailored to the user's emotional state, as well as effective business support based on the collected data.

[0839] "Information gathering means" refers to a function or process for automatically collecting data related to business operations from various information sources.

[0840] "Information preprocessing means" refers to a function that corrects or adjusts incomplete data in order to convert collected data into an analyzable format.

[0841] A "feature extraction method" is a technique for identifying important patterns and trends from pre-processed data and extracting elements necessary for analysis and model training.

[0842] "Analysis methods" refer to the process of systematically investigating business patterns from data obtained through feature extraction methods and deriving useful insights.

[0843] "Training methods" refer to the process of adjusting an AI model by applying machine learning algorithms based on the results obtained from analysis methods, so that the AI ​​model can function effectively.

[0844] A "generation method" is a mechanism for designing units that virtually perform tasks on behalf of others using trained AI models, and for providing them in an executable form.

[0845] "Emotion analysis means" refers to a technology used to determine a user's emotional state from various input data and to understand that state in real time.

[0846] "Response adjustment means" refers to a function that adjusts the system's response based on emotional data analyzed by emotion analysis means, in order to provide more appropriate support.

[0847] A "feedback system" is a mechanism that accepts user feedback and effectively utilizes that feedback to improve the performance of the system or model.

[0848] The embodiments for carrying out the invention are described in detail below.

[0849] This system provides business support through the collaboration of servers, terminals, and users. First, the server collects business-related data from various sources. These sources include project management tools, email systems, chat applications, and daily reporting systems. The collected data is stored in databases such as PostgreSQL and MySQL.

[0850] The server performs several processes on the collected data. First, it cleanses the data, correcting incomplete data and organizing the necessary information. Next, it performs feature extraction using libraries such as Scikit-learn. This extracts important features of business activities, and then it trains an AI model using TensorFlow or PyTorch. The trained model generates a virtual replacement work unit, or copy robot, to perform the tasks on behalf of the business.

[0851] Users interact with the system using a terminal. The system incorporates emotion analysis capabilities, using a camera and microphone to estimate the user's emotional state from their face and voice. Based on this information, the server can adjust the copy robot's responses to provide appropriate information and support.

[0852] For example, if a user expresses anxiety as a project deadline approaches, the server will readjust the task priorities and suggest reallocating resources. This allows the user to perform their tasks with reduced stress. An example of a prompt message would be: "Project X is nearing its deadline, and user A is feeling anxious. How will the system respond?"

[0853] In this way, the present invention enables the realization of a system that provides effective and flexible business support by combining data collection, processing, analysis, and responses to user emotions.

[0854] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0855] Step 1:

[0856] The server automatically collects business data from sources such as project management tools, email, chat applications, and daily reports. The data received from these sources is imported into the server in a structured format (e.g., JSON, CSV). Input is raw data from various sources, and output is data stored in a central database.

[0857] Step 2:

[0858] The server first performs data cleansing on the collected data. Specifically, this involves correcting incomplete data and deleting unimportant data. The input is the collected raw data, and the output is clean data with defects corrected. This results in a dataset that can be analyzed and feature extracted.

[0859] Step 3:

[0860] The server performs feature extraction on clean data. During this process, it uses data analysis libraries such as Scikit-learn to extract business trends and patterns. The input is a clean dataset, and the output is a feature vector or an analyzable set of information. This information is then used to train an AI model.

[0861] Step 4:

[0862] The server trains an AI model based on the data obtained through feature extraction. For example, it uses TensorFlow or PyTorch to select an appropriate algorithm and optimize the model's parameters. The input is a feature vector and related information, and the output is a trained AI model for performing business support.

[0863] Step 5:

[0864] The server uses a trained AI model to generate a virtual alternative unit of work. This prepares it to take over tasks even when the user is absent or busy. The input is the trained AI model, and the output is a viable alternative unit of work.

[0865] Step 6:

[0866] When a user interacts with the device, the server activates an emotion analysis engine that analyzes the user's facial expressions and voice input. The input is real-time data about the user's emotional state, and the output is the analyzed emotion trend. This feeds the system with the user's emotional changes.

[0867] Step 7:

[0868] The server adjusts the content and tone of its alternative work units based on the user's emotions. For stressed users, it presents simplified, high-priority tasks. The input is user emotion analysis data, and the output is a user-specific response and support plan.

[0869] Step 8:

[0870] Users provide feedback on the information and support offered and send it to the server. Based on this feedback, the AI ​​model is retrained. The input is the user's feedback data, and the output is the improved AI model and the system's overall business support capabilities.

[0871] (Application Example 2)

[0872] 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".

[0873] Current business support systems do not take into account employees' emotions or stress levels, which can lead to decreased work efficiency. Furthermore, there is a lack of systems capable of analyzing emotions and providing appropriate work support based on those analyses.

[0874] 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.

[0875] In this invention, the server includes information acquisition means, information preprocessing means, feature extraction means, pattern analysis means, model training means, device generation means, accuracy evaluation means, result presentation means, information deficiency detection means, emotion analysis means, support information provision means, and work efficiency adjustment means. This makes it possible to analyze the emotional state of employees in real time and provide appropriate support information via smart devices when providing work support based on the acquisition and analysis of work information.

[0876] "Information acquisition means" refers to devices and methods for collecting large amounts of business information.

[0877] "Information preprocessing means" refers to methods or devices for preparing acquired business information into a state that can be analyzed.

[0878] A "feature extraction means" is a method or device for finding specific patterns or attributes from pre-processed business information.

[0879] A "pattern analysis tool" is a method or device for analyzing business processes and trends based on extracted features.

[0880] "Model training means" refers to methods and devices for constructing and optimizing AI models using analysis results.

[0881] "Device generation means" refers to a method or device that uses a trained AI model to create a virtual automated device.

[0882] "Accuracy evaluation means" refers to a method or apparatus for determining the accuracy of the response or operation of a generated device.

[0883] "Result presentation means" refers to methods or devices for visually or audibly showing the results of an evaluation to the user.

[0884] "Information deficiency identification methods" are methods or devices that identify missing information or data based on the presented results.

[0885] "Emotional analysis tools" refer to methods or devices that analyze facial expressions, voice tone, etc., in order to understand the emotional state of employees.

[0886] "Support information provision means" refers to methods or devices that present information to provide appropriate support based on the results of emotion analysis.

[0887] "Methods for adjusting work efficiency" refer to methods or devices that adjust work processes to maximize efficiency based on the emotional state of employees and analysis results.

[0888] In this invention, a server is central to realizing a business support system. First, information related to business operations is collected by an information acquisition means. This information includes employee work progress data and customer data. The server uses an information preprocessing means to organize the collected information and convert it into a format suitable for analysis. Specifically, a data preprocessing library is used as the software.

[0889] Next, the server uses feature extraction to extract specific patterns from the pre-processed information. These patterns play a crucial role in subsequent analysis. Pattern analysis is then used to analyze employee work patterns and customer behavior patterns. Machine learning algorithms are employed in this process.

[0890] Using a model training method, an AI model is trained based on the analysis results. This training optimizes how employees and customers respond based on the patterns discovered. The trained AI model then uses a device generation method to create a virtual automation device that provides business support.

[0891] Smart glasses and other devices are worn by employees and analyze their emotional state in real time through emotion analysis tools. They utilize facial recognition cameras and voice recognition microphones, and the software includes an emotion analysis engine. Based on the analysis results, the server transmits support information to the device via a support information provision system. This information enables employees to perform appropriate tasks.

[0892] As a concrete example, in a busy store on a Saturday afternoon, the AI ​​could suggest priority customer service or quicker procedures to employees who are feeling stressed. An example of a prompt message would be, "Analyze the employee's stress level and provide immediately available support information."

[0893] This will lead to improved work efficiency and reduced stress for employees.

[0894] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0895] Step 1:

[0896] The server uses data acquisition methods to collect raw data related to business operations. Inputs include employee work progress and customer data. Outputs are imported into the system as raw datasets. Specifically, data is collected from project management tools and customer management systems via APIs.

[0897] Step 2:

[0898] The server uses data preprocessing to format the collected raw data. The input is the raw dataset collected in step 1. The output is data processed into an analyzable format. Specifically, data cleansing is performed to remove duplicate data and impute missing data.

[0899] Step 3:

[0900] The server uses a feature extraction method to extract features from pre-processed data. The input is the data processed in step 2. The output is the feature data extracted for analysis. Specifically, it selects and quantifies features for machine learning.

[0901] Step 4:

[0902] The server uses pattern analysis tools to analyze patterns from the extracted feature data. The input is the feature data obtained in step 3. The output is business trends and predictive information. Specifically, it uses time series analysis and clustering techniques to analyze business progress and customer behavior patterns.

[0903] Step 5:

[0904] The server uses a model training method to train an AI model based on the analysis results. The input is the analysis results obtained in step 4. The output is the trained AI model. Specifically, it uses a neural network to optimize the model and improve prediction accuracy.

[0905] Step 6:

[0906] The server uses a device generation mechanism to generate a virtual automation device based on a trained AI model. The input is the AI ​​model trained in step 5. The output is a virtual automation device for business support. Specifically, the AI ​​model is deployed to a cloud environment and linked to business systems via an API.

[0907] Step 7:

[0908] The terminal uses emotion analysis capabilities to analyze the emotional state of employees in real time. The input is emotion data from the terminal's camera and microphone. The output is the analyzed emotional state data. Specifically, it analyzes facial expressions from a video stream and analyzes the tone of audio data.

[0909] Step 8:

[0910] The server uses a support information provision system to send support information to the terminal based on the emotional state. The input is the emotional state data obtained in step 7. The output is the support information displayed on the smart device. Specifically, the server generates support information and provides it to the terminal via push notification.

[0911] Step 9:

[0912] The user readjusts the efficiency of their work based on the support information provided through the work efficiency adjustment tool. The input is the support information presented in step 8. The output is the optimized work process. Specifically, this involves reviewing the schedule and resource allocation, and resetting the core of the work.

[0913] 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.

[0914] 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.

[0915] 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.

[0916] 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.

[0917] 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.

[0918] 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.

[0919] 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.

[0920] 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.

[0921] 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."

[0922] 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.

[0923] 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.

[0924] 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.

[0925] 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.

[0926] 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.

[0927] 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.

[0928] 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.

[0929] 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.

[0930] 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.

[0931] 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.

[0932] 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.

[0933] 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 as being incorporated by reference.

[0934] The following is further disclosed regarding the embodiments described above.

[0935] (Claim 1)

[0936] Data collection methods for collecting large amounts of business data,

[0937] A data preprocessing means for preprocessing the aforementioned business data,

[0938] A feature extraction means for extracting features from the aforementioned preprocessed data,

[0939] A pattern analysis means for analyzing business patterns based on the aforementioned characteristics,

[0940] A model training means for training an AI model based on the aforementioned analysis results,

[0941] A robot generation means that generates a virtual copy robot using the aforementioned AI model,

[0942] Accuracy evaluation means for evaluating the accuracy of the response generated by the copy robot,

[0943] A result presentation means for presenting the aforementioned evaluation results,

[0944] A data deficiency detection means that clearly indicates missing data based on the aforementioned presentation results,

[0945] A system that includes this.

[0946] (Claim 2)

[0947] The system according to claim 1, wherein the results presentation means provides the user with trends and characteristics of business data and accepts feedback from the user.

[0948] (Claim 3)

[0949] The system according to claim 1, which retrains the AI ​​model based on the aforementioned feedback to improve the overall accuracy of the system.

[0950] "Example 1"

[0951] (Claim 1)

[0952] Information gathering means for collecting various information related to business operations,

[0953] Information preprocessing means for processing the aforementioned information so that it can be analyzed with high accuracy,

[0954] A feature extraction means for extracting important features from the aforementioned pre-processed information,

[0955] A model formation means that performs machine learning based on the aforementioned characteristics to form an AI model,

[0956] An agent generation means that generates a virtual proxy agent to support business operations using the aforementioned AI model,

[0957] A validity evaluation means for evaluating the validity of the solution provided by the aforementioned agency agent,

[0958] A means for providing the evaluation results to the user,

[0959] Information deficiency identification means for identifying missing information based on the results provided above,

[0960] A system that includes this.

[0961] (Claim 2)

[0962] The system according to claim 1, wherein the results providing means provides the user with information trends and characteristics in business operations and receives regression information from the user.

[0963] (Claim 3)

[0964] The system according to claim 1, which reconstructs the AI ​​model based on the regression information and improves the overall accuracy of the system.

[0965] "Application Example 1"

[0966] (Claim 1)

[0967] Information gathering methods for collecting large amounts of information,

[0968] Information preprocessing means for preprocessing the aforementioned information,

[0969] A feature extraction means for extracting features from the aforementioned pre-processed information,

[0970] A process analysis means for analyzing business processes based on the aforementioned characteristics,

[0971] A model training means for training an AI model based on the aforementioned analysis results,

[0972] An assistant generation means that generates a virtual assistant using the aforementioned AI model,

[0973] Accuracy evaluation means for evaluating the accuracy of the output generated by the assistant,

[0974] A procedure presentation means that presents the optimal work procedure via a smart device,

[0975] A means for identifying missing information based on the aforementioned presentation results,

[0976] A system that includes this.

[0977] (Claim 2)

[0978] The system according to claim 1, wherein the procedure presentation means provides the user with trends and characteristics of work information and accepts feedback from the user.

[0979] (Claim 3)

[0980] The system according to claim 1, which retrains the AI ​​model based on the aforementioned opinions and improves the overall accuracy of the system.

[0981] "Example 2 of combining an emotion engine"

[0982] (Claim 1)

[0983] Information gathering methods for collecting business data,

[0984] Information preprocessing means for preprocessing the aforementioned information,

[0985] A feature extraction means for extracting features from the aforementioned pre-processed information,

[0986] An analytical means for analyzing business patterns based on the aforementioned characteristics,

[0987] A training means for training a processing model based on the aforementioned analysis results,

[0988] A generation means for generating a virtual alternative work unit using the aforementioned trained model,

[0989] A means of analyzing the emotional state of a user,

[0990] A response adjustment means that adjusts the response of the alternative work unit based on the emotion analysis results,

[0991] A means of incorporating user feedback to update the model,

[0992] A system that includes this.

[0993] (Claim 2)

[0994] The system according to claim 1, wherein the response adjustment means provides business support in accordance with the user's emotions.

[0995] (Claim 3)

[0996] The system according to claim 1, wherein the accuracy of the system is continuously improved using the aforementioned feedback means.

[0997] "Application example 2 when combining with an emotional engine"

[0998] (Claim 1)

[0999] Information acquisition methods for obtaining large amounts of business information,

[1000] Information preprocessing means for preprocessing the aforementioned business information,

[1001] A feature extraction means for extracting features from the aforementioned pre-processed information,

[1002] A pattern analysis means for analyzing business patterns based on the aforementioned characteristics,

[1003] A model training means for training an AI model based on the aforementioned analysis results,

[1004] A device generation means that generates a virtual automated device using the aforementioned AI model,

[1005] Accuracy evaluation means for evaluating the accuracy of the response generated by the device,

[1006] A result presentation means for presenting the aforementioned evaluation results,

[1007] A means for identifying missing information based on the aforementioned presentation results,

[1008] An emotion analysis tool that detects and analyzes the emotional state of employees,

[1009] A means of providing support information to contact persons via a smart device, which provides support information tailored to their emotional state.

[1010] A means for adjusting the work efficiency of employees based on the aforementioned support information,

[1011] A system that includes this.

[1012] (Claim 2)

[1013] The system according to claim 1, wherein the results presentation means provides the user with trends and characteristics of business information and accepts feedback from the user.

[1014] (Claim 3)

[1015] The system according to claim 1, which retrains the AI ​​model based on the aforementioned feedback to improve the overall accuracy of the system. [Explanation of Symbols]

[1016] 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. Data collection methods for collecting large amounts of business data, A data preprocessing means for preprocessing the aforementioned business data, A feature extraction means for extracting features from the aforementioned preprocessed data, A pattern analysis means for analyzing business patterns based on the aforementioned characteristics, A model training means for training an AI model based on the aforementioned analysis results, A robot generation means that generates a virtual copy robot using the aforementioned AI model, Accuracy evaluation means for evaluating the accuracy of the response generated by the copy robot, A result presentation means for presenting the aforementioned evaluation results, A data deficiency detection means that clearly indicates missing data based on the aforementioned presentation results, A system that includes this.

2. The system according to claim 1, wherein the results presentation means provides the user with trends and characteristics of business data and accepts feedback from the user.

3. The system according to claim 1, which retrains the AI ​​model based on the aforementioned feedback to improve the overall accuracy of the system.

Images