system

Abstract

We provide the system. [Solution] Means of acquiring data on business operations, A means for analyzing business procedures using a generative model that analyzes the acquired data, A means for automatically generating a business manual based on the analyzed business procedures, A means to improve the automatically generated business manual using optimization methods based on examples from other companies, Means for providing the generated and improved business manuals, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot performed by at least one processor, including 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 as a 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 the operation of enterprises, the construction of efficient business procedures and the maintenance of unified service quality are required. However, in the conventional method, manually analyzing on-site video information and behavior information to create a business manual requires time and effort, and furthermore, it is often lacking in consistency because it is based on subjective judgment. Therefore, there is a need for a system that can automatically propose and document optimal business procedures according to the characteristics and implementation forms of each enterprise while improving business efficiency.

Means for Solving the Problems

[0005] The present invention solves the above problems with a system comprising means for acquiring data on corporate operations, means for analyzing business procedures using a generative model for analyzing the acquired data, means for automatically generating business manuals based on the analyzed business procedures, means for improving the automatically generated business manuals using optimization means based on examples from other companies, and means for providing the generated and improved business manuals. This system has a function for collecting video information and behavioral information, incorporates feedback based on the generated business manuals, and continuously updates the business manuals, thereby enabling the construction of efficient and unified business procedures.

[0006] "Corporate operational data" refers to information generated during the process of a company's daily operations and business activities, and specifically includes data sets such as sales data, customer information, work procedures, and video recordings.

[0007] A "generative model" is an algorithmic model based on machine learning or AI technology that is used to analyze collected data and extract useful business procedures and patterns from it.

[0008] "Business procedures" refer to a series of activities in a company's operations and processes, and are detailed instructions or flows that show how each task or work should be carried out.

[0009] An "operations manual" is a document that describes the business processes and procedures within an organization, and includes specific work procedures, roles and responsibilities, and precautions.

[0010] "Case studies from other companies" refer to specific examples of methods and initiatives that have been implemented and successfully carried out by companies other than your own in the past. This information is used as a reference for benchmarking and identifying areas for improvement.

[0011] "Optimization methods" refer to methods and tools for improving existing business procedures and processes to make them more efficient and effective, and in particular, methods that use AI to improve performance.

[0012] "Feedback" refers to the process of gathering results and opinions obtained from practical operation based on the operational manual, and returning that information and opinions to be used for the overall improvement and evaluation of the system. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] 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] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

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

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

[0016] In the following embodiments, 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.

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

[0018] In the following embodiments, 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.

[0019] 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).

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

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

[0023] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0030] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] This invention is an automated system for generating business manuals aimed at improving the operational efficiency of companies. Specifically, it operates in a form in which a server, a terminal, and a user work together, each playing a specific role.

[0035] Data acquisition and preprocessing

[0036] The server receives video data (e.g., footage of work sites) and behavioral data (e.g., operation logs) collected from each of the company's stores. Based on this, the server performs data preprocessing. At this stage, noise reduction and time synchronization are performed, and the data is adjusted to a format suitable for analysis.

[0037] Data Analysis

[0038] The server analyzes business procedures using a generative model based on pre-processed data. This AI model has the ability to identify actions within videos and identify efficient workflows from behavioral data. For example, it can extract customer service procedures on a restaurant floor and suggest the most effective service sequence.

[0039] Creation and optimization of business manuals

[0040] The server automatically generates operational manuals based on the analysis results. These manuals include specific work procedures and role assignments, designed to be easily implemented by users. Furthermore, optimization methods learned from other companies' case studies ensure that the generated manuals are customized to match the specific characteristics of each company.

[0041] Manual provision and feedback

[0042] The terminal provides users with generated work manuals and supports their viewing and implementation. Users perform tasks based on these manuals and send feedback on their actual work performance to the server. This feedback is then used by the server to update the manuals.

[0043] This system allows companies to maximize efficiency while maintaining consistency in their workflows. For example, it enables the standardization of business processes across all stores in a franchise chain, improving service quality while reducing training time and costs.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The server remotely acquires video data and employee behavior data captured from company stores and work sites. This includes data streams from cameras and sensors installed on-site, and the process begins when the server receives the data.

[0047] Step 2:

[0048] The server performs preprocessing on the received video and behavioral data. Preprocessing includes trimming unwanted parts, noise filtering, and adjusting the video clearance. This prepares a clean and consistent dataset for analysis.

[0049] Step 3:

[0050] The server applies a generative model to the pre-processed data and begins the analysis. Here, it detects the main steps of the business process from the video data and identifies employee behavior patterns. The results of this analysis provide foundational information for identifying efficient workflows.

[0051] Step 4:

[0052] The server automatically generates a work manual based on the analysis results. The generated manual includes detailed descriptions of work procedures and points to note, and is presented as a visually represented flowchart.

[0053] Step 5:

[0054] The server then optimizes the generated business manuals based on successful case studies from other companies. This process incorporates improvements to existing workflows, and the manuals are tailored to the specific characteristics of each company.

[0055] Step 6:

[0056] The terminal provides users with the final operational manual. The terminal presents information through a highly accessible interface to help users review the manual and utilize it in their daily work.

[0057] Step 7:

[0058] Users perform tasks based on the provided operational manuals and feed back the actual operational results to the server. This feedback is used by the server for subsequent analysis and manual updates, contributing to the automation of more accurate operational procedures.

[0059] (Example 1)

[0060] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0061] While businesses are required to improve efficiency and standardize each task, managing and improving individual business processes in a unified and efficient manner is a challenging task. In particular, when a company has numerous stores or branches, differences in work procedures at each location lead to decreased efficiency and inconsistent quality. This problem hinders overall productivity improvements and cost reductions for the company.

[0062] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0063] In this invention, the server includes a device for acquiring information related to business operations, a device for analyzing business flows using an artificial intelligence model that analyzes the acquired information, and a device for automatically generating business procedure manuals based on the analyzed business flows. This enables the standardization and efficiency improvement of business processes throughout the entire company.

[0064] "Business-related information" refers to data necessary for carrying out business activities and information that is useful for streamlining and improving business processes.

[0065] The term "device" refers to equipment or systems designed to perform a specific function.

[0066] An "artificial intelligence model" refers to a program or algorithm that uses machine learning and data analysis to mimic human intellectual behavior and perform problem-solving and decision-making.

[0067] A "business process flow" refers to a set of defined procedures or processes defined to achieve a specific objective.

[0068] A "work procedure manual" refers to a document that describes the procedures, methods, and points to note when performing a specific task.

[0069] "Optimized technologies based on other companies' case studies" refers to methods and technologies for making business processes more efficient, based on successful case studies and research from other companies.

[0070] "Distribution" refers to the act of sending certain information or data to a designated recipient.

[0071] "Evaluation information" refers to information regarding the results and performance of tasks performed based on the generated work procedures.

[0072] "Revision" refers to the act of reviewing existing documents, plans, procedures, etc., and making corrections as necessary.

[0073] This invention provides a system that achieves standardization and optimization of business processes in order to streamline corporate operations. Specifically, it is implemented through the cooperation of servers, terminals, and users.

[0074] 1. Data processing and analysis by the server

[0075] The server acquires operational information collected from each store and branch. This information includes video data and behavioral data. To obtain this data, the company can acquire it through cameras and operation recording devices placed within its stores. The acquired data is preprocessed on the server, such as noise reduction and time synchronization. This is done using media processing software such as FFmpeg.

[0076] Next, the server inputs the pre-processed data into a generating AI model to analyze the business flow. Here, machine learning algorithms are used to identify actions and procedures within the video and derive efficient business processes. Specifically, common algorithms such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs) are used as AI models. Based on the data obtained from this analysis, a business procedure manual is generated. For example, by inputting a prompt such as, "Analyze the efficient customer service procedures on the restaurant floor and suggest areas for improvement," the model can extract the ideal customer service procedure.

[0077] 2. Manuals provided via terminals

[0078] The terminal receives work procedure manuals generated from the server and displays them to the user in an easy-to-understand manner. These terminals include tablet computers, smartphones, and PCs. This allows users to easily understand and perform the instructed work procedures.

[0079] 3. User Feedback Collection and Improvement Process

[0080] Users perform tasks based on work procedures generated during actual work execution and observe the results. After completing a task, users send feedback to the server via a dedicated application. This feedback is stored on the server as data used to improve work procedures and is utilized in updating work procedures for future tasks. This leads to a continuous improvement in operational efficiency across the entire company.

[0081] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0082] Step 1:

[0083] Server data collection

[0084] The server receives video and behavioral data from each store via the internet. This includes data from cameras installed within the stores and user operation logs. This data is used as input for business process analysis. The server temporarily stores this raw data in preparation for subsequent processing.

[0085] Step 2:

[0086] Server data preprocessing

[0087] The server performs preprocessing on the collected video data, such as noise reduction and time synchronization. For example, it uses FFmpeg software to remove audio noise from the video and properly align the video frames. This process creates preprocessed data, preparing it for more accurate analysis.

[0088] Step 3:

[0089] Server Data Analysis

[0090] The server inputs pre-processed data into a generating AI model to perform operational analysis. Here, machine learning algorithms such as CNN and RNN are used as the AI ​​model. The model identifies actions within the video and extracts the workflow based on the behavioral data. Specifically, it analyzes customer service videos to output the optimal service sequence as the analysis result.

[0091] Step 4:

[0092] Server Business Procedure Manual Generation

[0093] The server automatically generates a work procedure manual based on the analysis results. The manual is in text format and includes specific work procedures and role assignments. The server saves this work procedure manual for the next step and applies optimization techniques that reflect best practices from other companies to improve accuracy during subsequent processing.

[0094] Step 5:

[0095] Display of work procedure manuals via terminal

[0096] The terminal displays the work procedure manual received from the server via a user interface. Users can then review the procedure manual to understand how to proceed with the work and any points to note. This function helps users to properly perform their intended tasks.

[0097] Step 6:

[0098] Collecting user feedback

[0099] Users send feedback on the tasks they perform to the server via a dedicated application. This feedback includes comments and data regarding problems and areas for improvement encountered during task execution. The server accumulates this feedback and uses it to further improve the procedures.

[0100] Step 7:

[0101] Updating the server's operational procedures manual.

[0102] The server analyzes feedback received from users and continuously updates the content of the work procedure manuals. This allows for the provision of improved manuals that reflect data analysis results using the generated AI model and the actual usage patterns of users.

[0103] (Application Example 1)

[0104] 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."

[0105] In modern manufacturing environments, the efficient operation of factory robots is essential. However, manually documenting robot operation procedures is time-consuming and labor-intensive, and extracting optimized procedures remains a challenging task. In particular, there is a need for a system that optimizes procedures for different environments and processes, and that quickly incorporates feedback from the factory floor, but concrete methods for achieving this are lacking.

[0106] 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.

[0107] In this invention, the server includes means for acquiring data on business operations, means for analyzing work procedures using a generative model that analyzes the acquired data, means for automatically generating an operation manual based on the analyzed work procedures, means for improving the automatically generated operation manual using optimization means based on examples from other companies, and means for receiving work result data from the robot as feedback and updating the operation manual. This enables the rapid generation and provision of efficient and optimized robot operation procedures, and allows for continuous optimization incorporating feedback from the field.

[0108] "Corporate operation data" refers to various types of information related to a company's activities and operations, including video footage from work sites and operation logs.

[0109] "Means of acquisition" refers to functions and devices used to collect data related to business operations.

[0110] A "generative model" refers to an algorithm for analyzing data based on AI technology, which uses video and behavioral data to extract business procedures.

[0111] "Work procedure" refers to the specific steps and processes necessary to effectively perform a particular task or operation.

[0112] An "operation manual" is a document that outlines work procedures and serves as a guide to support efficient work execution.

[0113] "Automatic generation" refers to a process in which a system processes and produces results without requiring manual intervention.

[0114] "Optimization measures" refer to the process or method of improving business manuals and procedures based on other examples and conditions.

[0115] "Feedback" refers to information and data provided by users or systems, based on their operational results and evaluations, that are used to make further improvements.

[0116] In this invention, a server collects and analyzes corporate operation data to generate efficient work procedures. The hardware used in the server must have the capability to process video data and operation log data in real time. Here, OpenCV is used to denoise and synchronize video data, and Tensorflow® is used to generate an AI model for operation analysis. Work procedures are automatically generated from the analysis results, and an operation manual is constructed based on these procedures.

[0117] The terminal, installed on smart glasses or mobile devices, has the function of providing generated operation manuals to users such as on-site robot engineers. Leveraging a neuro-network-based model, the terminal visually supports optimized procedures, helping users perform their tasks efficiently.

[0118] Users perform tasks based on the provided manual and send the results as feedback to the system. This feedback is used to further optimize the manual. For example, the assembly process of a specific product in a factory may involve sequential operations such as "Step 1: Accurately grasp component A" and "Step 2: Position it correctly on the line."

[0119] As an example of a prompt for a generated AI model, you could use a sentence like, "Generate the operating procedure for a robot that grasps and places bearings. Please point out any particularly efficient procedures or important points to note."

[0120] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0121] Step 1:

[0122] The server collects video data and activity logs provided by each of the company's stores. It receives video files and digital log data as input and stores them in their initial data format. This forms the foundation for data analysis.

[0123] Step 2:

[0124] The server uses OpenCV to apply noise reduction and time synchronization to the video data. It receives the video file saved in step 1 as input, and processes it to produce a clear video output with minimal unwanted noise. During this process, the video quality is transformed to a state suitable for analysis.

[0125] Step 3:

[0126] The server processes the organized data obtained in Step 2 through a generative AI model utilizing TensorFlow for analysis. The generative AI model receives high-quality video data and motion logs as input, analyzes them, and outputs workflows and motion patterns. This analysis makes it possible to evaluate the efficiency of each work step.

[0127] Step 4:

[0128] Based on the analysis results from Step 3, the server automatically generates an operation manual that reflects the work procedures. The input is the result of the motion analysis, and the output is the newly created operation manual. This manual will function as a work guide in the actual field.

[0129] Step 5:

[0130] The terminal displays the generated operation manual on smart glasses or a mobile device and provides it to the user. The input provided is the manual created in step 4, and the output to the user is instructional and support information via the device. This function allows the user to proceed with the work while visually confirming the steps.

[0131] Step 6:

[0132] Users perform on-site tasks using a terminal and send feedback obtained during the process to the server. Input consists of feedback data on the work results and areas for improvement, which is then output to the server. This feedback is used to further improve the operation manual.

[0133] Step 7:

[0134] The server processes user feedback and updates the operation manual as needed. The input is the information provided as feedback, and the output is the updated operation manual. This loop enables continuous optimization.

[0135] 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.

[0136] This invention is a system that automatically generates business manuals for companies, supporting efficient business operations, and further incorporates an emotion engine that recognizes user emotions. The server, terminals, and users each cooperate and play their own unique roles.

[0137] Data collection and emotion recognition

[0138] The server collects video data and employee behavior data from each store and work site, and also uses an emotion engine to obtain emotional data from employees' facial expressions and voices. This allows for the collection of emotional feedback on employees' work performance as well.

[0139] Data and sentiment analysis

[0140] The server preprocesses the acquired data and inputs it into a generative model to analyze business procedures. Furthermore, based on the emotional data analyzed by the emotion engine, it analyzes the relationship between employees' emotional states and work efficiency to design a more human-centered workflow. This analysis step is also important for identifying stress points experienced by employees and processes that need improvement.

[0141] Business manual generation and optimization that takes emotions into account.

[0142] The server automatically generates operational manuals based on the analysis results and further optimizes them using success stories from competitors and the acquired sentiment data. For example, if an alert is detected based on sentiment data, instructions to draw special attention to that section of the workflow are added.

[0143] Manual provision and feedback management

[0144] The terminal provides the user with a completed work manual. The user refers to this manual to perform their tasks and returns the resulting feedback to the server. Through this cycle, new insights, such as correlation analysis between emotional data and work efficiency, are accumulated on the server and used to improve subsequent manuals and systems.

[0145] This system achieves more flexible and effective improvements in operational efficiency by incorporating emotion recognition into conventional operational manual generation systems. For example, in a restaurant chain, it can improve workflows to reduce staff stress levels, enabling them to continue providing better service to customers.

[0146] The following describes the processing flow.

[0147] Step 1:

[0148] The server collects video data from company stores and work sites, employee behavior data, and sentiment data obtained using an emotion engine. This includes data streamed in real time from cameras and microphones installed on-site. The server extracts emotions from changes in employees' facial expressions and voices and integrates them with business data.

[0149] Step 2:

[0150] The server preprocesses the collected video, behavior, and emotion data. Videos are denoised and edited to make them clear and easy to analyze, and behavior data is aligned along a timeline. Emotion data is analyzed based on predetermined emotion classifications and compiled into quantified evaluation metrics.

[0151] Step 3:

[0152] The server feeds pre-processed video and behavioral data into a generative model to analyze work procedures. Here, image recognition and pattern analysis techniques are used to identify each step in the flow, extracting the most frequently performed processes and recommended procedures. Simultaneously, the analysis of emotional data is used to understand stressors and emotional changes during work.

[0153] Step 4:

[0154] The server automatically generates a work manual based on the analyzed business procedures. The manual includes not only optimized procedures but also advice for efficiency improvements derived from emotional data. For example, it might instruct users to "make more eye contact with customers during customer interactions," promoting emotionally positive interactions.

[0155] Step 5:

[0156] The server improves the content of the generated manuals by utilizing optimization methods based on best practices from other companies and sentiment data. Specifically, it refers to successful case studies from databases of companies in the same industry and adopts the most effective implementation methods. It also identifies procedures that are less emotionally burdensome and makes adjustments to maximize operational efficiency.

[0157] Step 6:

[0158] The terminal provides users with completed work manuals, making them available for viewing and implementation. Users refer to these manuals while performing their work activities and send daily feedback to the server via the terminal. This feedback includes suggestions for improvement based on the user's experience and is used for continuous business improvement.

[0159] Step 7:

[0160] The server receives user feedback and uses it for reanalysis and updating of operational manuals. This incorporates user experience based on emotional data, leading to the identification of new stress points and the strengthening of emotionally positive procedures. As a result, the quality and efficiency of operations improve in the long term.

[0161] (Example 2)

[0162] 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".

[0163] Achieving both improved work efficiency and consideration for employees' emotional well-being simultaneously is a challenge for companies. Traditional work manuals focus on the efficiency of work procedures but fail to consider the emotional burden on employees, which can increase stress during work and ultimately lead to decreased efficiency. Furthermore, there is a need for optimization of work processes through real-time feedback, rather than simply improving documents.

[0164] 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.

[0165] In this invention, the server includes means for acquiring information related to business activities, means for using a generative model to analyze work procedures by analyzing the acquired information, and means equipped with an emotion analysis function for analyzing the emotional state of employees. This enables not only the automatic generation of work guidelines based on information acquisition and analysis, but also dynamic work improvements that take into account the emotions of employees. This makes it possible to improve work efficiency while reducing employee stress.

[0166] "Information related to business activities" refers to various data related to the operation of a company, including activity status, employee behavior, and customer interactions.

[0167] A "generative model" is an algorithm or system that analyzes data as input and generates a specific output, and it is a model that uses machine learning or artificial intelligence techniques.

[0168] "Work guidelines" are documents consisting of procedures and policies that are instructed to ensure efficient and effective work execution within a company.

[0169] The "emotional analysis function" is a feature that analyzes employees' facial expressions and voices from data to identify and evaluate their emotions and mental state.

[0170] "Feedback" refers to opinions, impressions, and evaluation information based on work results and experiences obtained from users and employees, and is used to improve business processes.

[0171] An "optimization method" is a method or process that improves current procedures and processes based on existing data and case studies to obtain more efficient and effective results.

[0172] The embodiments for carrying out the present invention will be described in detail.

[0173] The server acquires data through various devices to collect information related to business activities. Specifically, it collects video and audio data using cameras and microphones. This data includes employee behavior, facial expressions, and voice, and serves as the basis for sentiment analysis. After preprocessing such as noise reduction, the collected data is managed within the server.

[0174] The server analyzes the collected data using generative models. These generative models utilize high-performance AI technology, such as large-scale pre-trained natural language processing models and image analysis models. This makes it possible to analyze work procedures and employee emotional states, and design human-centered work guidelines.

[0175] While typical cloud servers are used as hardware, local servers are also perfectly capable of handling the system. For software, TensorFlow and PyTorch are frequently employed as machine learning frameworks. For sentiment analysis, using API services allows for highly accurate analysis.

[0176] The terminal provides users with work guidelines generated and optimized by the server. Users view this information via the terminal and utilize it in their actual work. Feedback information from the terminal is sent to the server based on the user's experience.

[0177] A concrete example is analyzing the work procedures employees follow when serving food in a restaurant chain and designing an efficient and stress-free workflow. In this case, the server analyzes video information obtained from cameras within the store and provides optimized procedures to make employee movements smoother.

[0178] An example of a prompt to input into a generative AI model is, "Please suggest the optimal procedure for improving efficiency and safety in food preparation." By using such prompts, the generative model can present realistic and specific suggestions for improving business processes.

[0179] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0180] Step 1:

[0181] The server collects data related to business activities using cameras and sensors placed in stores and work sites. It takes video and audio data as input and temporarily stores it. Specifically, it records employee movements with cameras and captures audio through microphones. This provides real-time data on employee status and work environment.

[0182] Step 2:

[0183] The server preprocesses the collected raw data. It receives video and audio data as input and generates analyzable, formatted data as output. Specifically, it performs noise reduction and data format conversion. By removing unnecessary frames from video data and reducing background noise in audio data, it improves the accuracy of the analysis.

[0184] Step 3:

[0185] The server inputs pre-processed data into a generating AI model to analyze business procedures. It receives formatted video and audio data as input and proposes optimal business procedures as output. This process learns patterns and features from the data to design human-centered workflows. For example, it generates step-by-step guidelines for employees to work efficiently.

[0186] Step 4:

[0187] The server uses an emotion analysis engine to analyze the emotional state of employees. It further analyzes pre-processed data as input and outputs emotional data from facial expressions and voice tone. Specific operations include facial recognition technology and voice tone analysis, and emotional feedback is obtained by objectively evaluating the employee's emotions.

[0188] Step 5:

[0189] The server optimizes generated work procedures while taking emotional data into consideration. It receives emotional data and work procedures as input and provides an improved workflow as output. Specifically, it identifies procedures that cause particularly high stress and adds instructions to improve those parts. This process adjusts work procedures to make them more comfortable for employees.

[0190] Step 6:

[0191] The terminal provides users with optimized work guidelines. It receives data transmitted from the server as input and presents the information in a user-viewable format as output. Specifically, it displays visualized guidelines on a digital device, allowing users to immediately utilize them in their work.

[0192] Step 7:

[0193] Users perform tasks based on the provided work guidelines and generate feedback. They send the results and experiences of their completed tasks to the server as input, and provide feedback content to the server as output. This feedback includes evaluations of efficiency and areas for improvement.

[0194] Step 8:

[0195] The server incorporates feedback to continuously improve business guidelines and the overall system. It receives user feedback as input and generates improvement suggestions that will be reflected in future business guidelines as output. Specific actions include storing feedback in a database, analyzing it, and using the results to generate new guidelines.

[0196] (Application Example 2)

[0197] 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".

[0198] Traditional business support systems that ignore the impact of employees' emotional states on work efficiency have led to problems such as decreased work efficiency and reduced service quality due to the accumulation of stress and dissatisfaction. Furthermore, the inability to reflect improvements and guidance in work flows in real time makes rapid response difficult. To solve these problems, a flexible and adaptive business support system that takes employees' emotional states into account is necessary.

[0199] 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.

[0200] In this invention, the server includes a device for acquiring information on business operations, a device for analyzing business flows using a generation algorithm that analyzes the acquired information, and a device for automatically generating work instruction manuals based on the analyzed business flows. This makes it possible to analyze the emotional state of employees in real time and adaptively improve work instruction manuals based on emotional data.

[0201] "Information on business operations" refers to various data and information related to a company's daily operational activities, including business processes and employee behavior patterns.

[0202] A "generation algorithm" is a calculation process or method for automatically creating work instructions by analyzing the procedures and flow of work based on acquired information.

[0203] A "business process flow" refers to a series of steps or activities that show the flow of various tasks and processes performed within a company.

[0204] A "work instruction manual" is a document that contains instructions and guidelines generated based on a work flow, and is a tool for employees to perform their tasks efficiently.

[0205] "Examples from other organizations" refer to business processes and methods that have been successful in competitors or other organizations, and are used to improve one's own company's operational manuals.

[0206] An "optimization algorithm" is a calculation process or method used to adjust work instruction manuals to be more efficient and effective, based on examples from other organizations and acquired data.

[0207] "Emotional data" refers to information that quantitatively indicates an employee's psychological state and emotions, and is obtained from facial expressions and voice.

[0208] An "emotion engine" is a component that provides technologies and functions for analyzing emotional data and understanding the emotional state of employees.

[0209] "Devices including electronic equipment" refers to equipment that has built-in or connected electronic devices for displaying emotion-based guidance or information in real time.

[0210] This invention realizes a system for managing the emotional state of employees in physical stores and improving operational efficiency. The system utilizes smart glasses, a server, an emotion recognition engine, and a generative AI model to operate.

[0211] The server acquires operational information from employees at each store, including video and behavioral data. This information is collected in real time via the cameras and microphones of smart glasses. An emotion recognition engine analyzes the collected data to identify the emotional state of employees. The emotional data obtained through this process is then evaluated by the server to provide emotional feedback within the employee's workflow.

[0212] The server inputs acquired emotional data and other business data into a generation algorithm to analyze the business flow. Based on the analysis results, it automatically generates a work instruction manual and improves it using an optimization algorithm based on examples from other organizations. This instruction manual is displayed on the smart glasses' screen, providing real-time guidance to employees.

[0213] For example, if the smart glasses detect that a staff member is experiencing high levels of stress while interacting with a customer, they might display advice such as, "Relax, and next, ask the customer about the product's features." In this way, employees receive appropriate guidance based on their emotions, enabling them to provide better service to customers.

[0214] Examples of prompt statements include the following:

[0215] Emotional analysis results: High stress level

[0216] Work status: Currently assisting a customer.

[0217] Required instructions: Encouraging messages and guidance on the next steps.

[0218] Example output: Relax, and next, let's ask the customer about the product's features.

[0219] This format enables real-time work guidance that reflects the emotional state of employees in a physical store environment.

[0220] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0221] Step 1:

[0222] The server acquires real-time video and audio information transmitted from the smart glasses. This information reflects the employee's activity status and speech content. The input is data from the smart glasses' camera and microphone, and the output is raw data for analysis supplied to the emotion recognition engine.

[0223] Step 2:

[0224] The server inputs the acquired video and audio information into an emotion recognition engine, which analyzes the employee's emotional state from their facial expressions and tone of voice. This process uses data mining techniques to identify human emotional characteristics. The output is quantitative data indicating the employee's emotional state.

[0225] Step 3:

[0226] The server uses a generative AI model to integrate emotional data with existing workflow information and generate work instruction manuals. In this step, input data, including prompts, is supplied to the model, and specific instructional plans for improving work efficiency are output. The generated results are used as real-time work instruction tailored to the employee's situation.

[0227] Step 4:

[0228] The terminal (smart glasses) displays work instructions received from the server within the employee's field of vision. This display includes encouraging messages and guidance on the next steps to take. The input is instruction data from the server, and the output is visual information provided to the employee.

[0229] Step 5:

[0230] The user (employee) puts into practice the instructions received through smart glasses. This allows them to improve their emotional state while performing their duties according to the provided guidance. The output, as work outcomes, is improved emotional state and work efficiency.

[0231] Step 6:

[0232] The server receives user feedback and uses it to further optimize the workflow. This feedback includes whether the guidance was helpful and changes in emotional state. The input is user feedback data, and the output is a system improvement plan, including the next update of the work instruction manual.

[0233] 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.

[0234] 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.

[0235] 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.

[0236] [Second Embodiment]

[0237] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0238] 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.

[0239] 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).

[0240] 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.

[0241] 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.

[0242] 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).

[0243] 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.

[0244] 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.

[0245] 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.

[0246] 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.

[0247] 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.

[0248] 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".

[0249] This invention is an automated system for generating business manuals aimed at improving the operational efficiency of companies. Specifically, it operates in a form in which a server, a terminal, and a user work together, each playing a specific role.

[0250] Data acquisition and preprocessing

[0251] The server receives video data (e.g., footage of work sites) and behavioral data (e.g., operation logs) collected from each of the company's stores. Based on this, the server performs data preprocessing. At this stage, noise reduction and time synchronization are performed, and the data is adjusted to a format suitable for analysis.

[0252] Data Analysis

[0253] The server analyzes business procedures using a generative model based on pre-processed data. This AI model has the ability to identify actions within videos and identify efficient workflows from behavioral data. For example, it can extract customer service procedures on a restaurant floor and suggest the most effective service sequence.

[0254] Creation and optimization of business manuals

[0255] The server automatically generates operational manuals based on the analysis results. These manuals include specific work procedures and role assignments, designed to be easily implemented by users. Furthermore, optimization methods learned from other companies' case studies ensure that the generated manuals are customized to match the specific characteristics of each company.

[0256] Manual provision and feedback

[0257] The terminal provides users with generated work manuals and supports their viewing and implementation. Users perform tasks based on these manuals and send feedback on their actual work performance to the server. This feedback is then used by the server to update the manuals.

[0258] This system allows companies to maximize efficiency while maintaining consistency in their workflows. For example, it enables the standardization of business processes across all stores in a franchise chain, improving service quality while reducing training time and costs.

[0259] The following describes the processing flow.

[0260] Step 1:

[0261] The server remotely acquires video data and employee behavior data captured from company stores and work sites. This includes data streams from cameras and sensors installed on-site, and the process begins when the server receives the data.

[0262] Step 2:

[0263] The server performs preprocessing on the received video and behavioral data. Preprocessing includes trimming unwanted parts, noise filtering, and adjusting the video clearance. This prepares a clean and consistent dataset for analysis.

[0264] Step 3:

[0265] The server applies a generative model to the pre-processed data and begins the analysis. Here, it detects the main steps of the business process from the video data and identifies employee behavior patterns. The results of this analysis provide foundational information for identifying efficient workflows.

[0266] Step 4:

[0267] The server automatically generates a work manual based on the analysis results. The generated manual includes detailed descriptions of work procedures and points to note, and is presented as a visually represented flowchart.

[0268] Step 5:

[0269] The server then optimizes the generated business manuals based on successful case studies from other companies. This process incorporates improvements to existing workflows, and the manuals are tailored to the specific characteristics of each company.

[0270] Step 6:

[0271] The terminal provides users with the final operational manual. The terminal presents information through a highly accessible interface to help users review the manual and utilize it in their daily work.

[0272] Step 7:

[0273] Users perform tasks based on the provided operational manuals and feed back the actual operational results to the server. This feedback is used by the server for subsequent analysis and manual updates, contributing to the automation of more accurate operational procedures.

[0274] (Example 1)

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

[0276] While businesses are required to improve efficiency and standardize each task, managing and improving individual business processes in a unified and efficient manner is a challenging task. In particular, when a company has numerous stores or branches, differences in work procedures at each location lead to decreased efficiency and inconsistent quality. This problem hinders overall productivity improvements and cost reductions for the company.

[0277] 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.

[0278] In this invention, the server includes a device for acquiring information related to business operations, a device for analyzing business flows using an artificial intelligence model that analyzes the acquired information, and a device for automatically generating business procedure manuals based on the analyzed business flows. This enables the standardization and efficiency improvement of business processes throughout the entire company.

[0279] "Business-related information" refers to data necessary for carrying out business activities and information that is useful for streamlining and improving business processes.

[0280] "Device" refers to a device or system designed to perform a specific function.

[0281] "Artificial intelligence model" refers to a program or algorithm that mimics human intellectual behavior and performs problem-solving and decision-making through machine learning and data analysis.

[0282] "Business process" refers to a series of work procedures and process flows defined to achieve a specific goal.

[0283] "Business procedure manual" refers to a document that describes the procedures, methods, and precautions when performing a specific business.

[0284] "Optimization technology based on cases of other companies" refers to methods and technologies for making business processes more efficient based on successful cases and case studies in other companies.

[0285] "Distribution" refers to the act of sending certain information or data to designated recipients.

[0286] "Evaluation information" refers to information regarding the results and performance of operations carried out based on the generated business procedure manual.

[0287] "Revision" refers to the act of reviewing existing documents, plans, procedure manuals, etc., and making necessary corrections.

[0288] This invention provides a system for achieving standardization and optimization of business processes in order to improve the efficiency of corporate operations. Specifically, it is implemented through the cooperation of a server, a terminal, and a user.

[0289] 1. Data processing and analysis by the server

[0290] The server acquires operational information collected from each store and branch. This information includes video data and behavioral data. To obtain this data, the company can acquire it through cameras and operation recording devices placed within its stores. The acquired data is preprocessed on the server, such as noise reduction and time synchronization. This is done using media processing software such as FFmpeg.

[0291] Next, the server inputs the pre-processed data into a generating AI model to analyze the business flow. Here, machine learning algorithms are used to identify actions and procedures within the video and derive efficient business processes. Specifically, common algorithms such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs) are used as AI models. Based on the data obtained from this analysis, a business procedure manual is generated. For example, by inputting a prompt such as, "Analyze the efficient customer service procedures on the restaurant floor and suggest areas for improvement," the model can extract the ideal customer service procedure.

[0292] 2. Manuals provided via terminals

[0293] The terminal receives work procedure manuals generated from the server and displays them to the user in an easy-to-understand manner. These terminals include tablet computers, smartphones, and PCs. This allows users to easily understand and perform the instructed work procedures.

[0294] 3. User Feedback Collection and Improvement Process

[0295] Users perform tasks based on work procedures generated during actual work execution and observe the results. After completing a task, users send feedback to the server via a dedicated application. This feedback is stored on the server as data used to improve work procedures and is utilized in updating work procedures for future tasks. This leads to a continuous improvement in operational efficiency across the entire company.

[0296] The flow of the specific process in Example 1 will be described with reference to FIG. 11.

[0297] Step 1:

[0298] Data collection by the server

[0299] The server receives video data and behavior data from each store via the Internet. This includes cameras installed in the store and the operation logs of users. This data is used as input for business process analysis. The server temporarily stores these raw data in preparation for subsequent processing.

[0300] Step 2:

[0301] Data preprocessing by the server

[0302] The server performs preprocessing such as noise removal and time synchronization on the collected video data. For example, the FFmpeg software is used to remove the audio noise of the video and align the video frames appropriately. In this step, preprocessed data is created to prepare for improving the accuracy of the analysis process.

[0303] Step 3:

[0304] Data analysis by the server

[0305] The server inputs the preprocessed data into a generated AI model to perform an analysis of the business operations. Here, CNN and RNN, which are machine learning algorithms, are used as the AI model. The model identifies the actions in the video and extracts the business process based on the behavior data. Specifically, the optimal service order is output as the analysis result from the video of the customer service business.

[0306] Step 4:

[0307] Generation of the server's business procedure manual

[0308] The server automatically generates a work procedure manual based on the analysis results. The manual is in text format and includes specific work procedures and role assignments. The server saves this work procedure manual for the next step and applies optimization techniques that reflect best practices from other companies to improve accuracy during subsequent processing.

[0309] Step 5:

[0310] Display of work procedure manuals via terminal

[0311] The terminal displays the work procedure manual received from the server via a user interface. Users can then review the procedure manual to understand how to proceed with the work and any points to note. This function helps users to properly perform their intended tasks.

[0312] Step 6:

[0313] Collecting user feedback

[0314] Users send feedback on the tasks they perform to the server via a dedicated application. This feedback includes comments and data regarding problems and areas for improvement encountered during task execution. The server accumulates this feedback and uses it to further improve the procedures.

[0315] Step 7:

[0316] Updating the server's operational procedures manual.

[0317] The server analyzes feedback received from users and continuously updates the content of the work procedure manuals. This allows for the provision of improved manuals that reflect data analysis results using the generated AI model and the actual usage patterns of users.

[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] In modern manufacturing environments, the efficient operation of factory robots is essential. However, manually documenting robot operation procedures is time-consuming and labor-intensive, and extracting optimized procedures remains a challenging task. In particular, there is a need for a system that optimizes procedures for different environments and processes, and that quickly incorporates feedback from the factory floor, but concrete methods for achieving this are lacking.

[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 means for acquiring data on business operations, means for analyzing work procedures using a generative model that analyzes the acquired data, means for automatically generating an operation manual based on the analyzed work procedures, means for improving the automatically generated operation manual using optimization means based on examples from other companies, and means for receiving work result data from the robot as feedback and updating the operation manual. This enables the rapid generation and provision of efficient and optimized robot operation procedures, and allows for continuous optimization incorporating feedback from the field.

[0323] "Corporate operation data" refers to various types of information related to a company's activities and operations, including video footage from work sites and operation logs.

[0324] "Means of acquisition" refers to functions and devices used to collect data related to business operations.

[0325] A "generative model" refers to an algorithm for analyzing data based on AI technology, which uses video and behavioral data to extract business procedures.

[0326] "Work procedure" refers to the specific steps and processes necessary to effectively perform a particular task or operation.

[0327] An "operation manual" is a document that outlines work procedures and serves as a guide to support efficient work execution.

[0328] "Automatic generation" refers to a process in which a system processes and produces results without requiring manual intervention.

[0329] "Optimization measures" refer to the process or method of improving business manuals and procedures based on other examples and conditions.

[0330] "Feedback" refers to information and data provided by users or systems, based on their operational results and evaluations, that are used to make further improvements.

[0331] In this invention, a server collects and analyzes corporate operation data to generate efficient work procedures. The hardware used in the server must have the capability to process video data and operation log data in real time. Here, OpenCV is used to denoise and synchronize video data, and TensorFlow is used to generate an AI model for operation analysis. Work procedures are automatically generated from the analysis results, and an operation manual is constructed based on these procedures.

[0332] The terminal, installed on smart glasses or mobile devices, has the function of providing generated operation manuals to users such as on-site robot engineers. Leveraging a neuro-network-based model, the terminal visually supports optimized procedures, helping users perform their tasks efficiently.

[0333] Users perform tasks based on the provided manual and send the results as feedback to the system. This feedback is used to further optimize the manual. For example, the assembly process of a specific product in a factory may involve sequential operations such as "Step 1: Accurately grasp component A" and "Step 2: Position it correctly on the line."

[0334] As an example of a prompt for a generated AI model, you could use a sentence like, "Generate the operating procedure for a robot that grasps and places bearings. Please point out any particularly efficient procedures or important points to note."

[0335] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0336] Step 1:

[0337] The server collects video data and activity logs provided by each of the company's stores. It receives video files and digital log data as input and stores them in their initial data format. This forms the foundation for data analysis.

[0338] Step 2:

[0339] The server uses OpenCV to apply noise reduction and time synchronization to the video data. It receives the video file saved in step 1 as input, and processes it to produce a clear video output with minimal unwanted noise. During this process, the video quality is transformed to a state suitable for analysis.

[0340] Step 3:

[0341] The server processes the organized data obtained in Step 2 through a generative AI model utilizing TensorFlow for analysis. The generative AI model receives high-quality video data and motion logs as input, analyzes them, and outputs workflows and motion patterns. This analysis makes it possible to evaluate the efficiency of each work step.

[0342] Step 4:

[0343] Based on the analysis results from Step 3, the server automatically generates an operation manual that reflects the work procedures. The input is the result of the motion analysis, and the output is the newly created operation manual. This manual will function as a work guide in the actual field.

[0344] Step 5:

[0345] The terminal displays the generated operation manual on smart glasses or a mobile device and provides it to the user. The input provided is the manual created in step 4, and the output to the user is instructional and support information via the device. This function allows the user to proceed with the work while visually confirming the steps.

[0346] Step 6:

[0347] Users perform on-site tasks using a terminal and send feedback obtained during the process to the server. Input consists of feedback data on the work results and areas for improvement, which is then output to the server. This feedback is used to further improve the operation manual.

[0348] Step 7:

[0349] The server processes user feedback and updates the operation manual as needed. The input is the information provided as feedback, and the output is the updated operation manual. This loop enables continuous optimization.

[0350] 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.

[0351] This invention is a system that automatically generates business manuals for companies, supporting efficient business operations, and further incorporates an emotion engine that recognizes user emotions. The server, terminals, and users each cooperate and play their own unique roles.

[0352] Data collection and emotion recognition

[0353] The server collects video data and employee behavior data from each store and work site, and also uses an emotion engine to obtain emotional data from employees' facial expressions and voices. This allows for the collection of emotional feedback on employees' work performance as well.

[0354] Data and sentiment analysis

[0355] The server preprocesses the acquired data and inputs it into a generative model to analyze business procedures. Furthermore, based on the emotional data analyzed by the emotion engine, it analyzes the relationship between employees' emotional states and work efficiency to design a more human-centered workflow. This analysis step is also important for identifying stress points experienced by employees and processes that need improvement.

[0356] Business manual generation and optimization that takes emotions into account.

[0357] The server automatically generates operational manuals based on the analysis results and further optimizes them using success stories from competitors and the acquired sentiment data. For example, if an alert is detected based on sentiment data, instructions to draw special attention to that section of the workflow are added.

[0358] Manual provision and feedback management

[0359] The terminal provides the user with a completed work manual. The user refers to this manual to perform their tasks and returns the resulting feedback to the server. Through this cycle, new insights, such as correlation analysis between emotional data and work efficiency, are accumulated on the server and used to improve subsequent manuals and systems.

[0360] This system achieves more flexible and effective improvements in operational efficiency by incorporating emotion recognition into conventional operational manual generation systems. For example, in a restaurant chain, it can improve workflows to reduce staff stress levels, enabling them to continue providing better service to customers.

[0361] The following describes the processing flow.

[0362] Step 1:

[0363] The server collects video data from company stores and work sites, employee behavior data, and sentiment data obtained using an emotion engine. This includes data streamed in real time from cameras and microphones installed on-site. The server extracts emotions from changes in employees' facial expressions and voices and integrates them with business data.

[0364] Step 2:

[0365] The server preprocesses the collected video, behavior, and emotion data. Videos are denoised and edited to make them clear and easy to analyze, and behavior data is aligned along a timeline. Emotion data is analyzed based on predetermined emotion classifications and compiled into quantified evaluation metrics.

[0366] Step 3:

[0367] The server feeds pre-processed video and behavioral data into a generative model to analyze work procedures. Here, image recognition and pattern analysis techniques are used to identify each step in the flow, extracting the most frequently performed processes and recommended procedures. Simultaneously, the analysis of emotional data is used to understand stressors and emotional changes during work.

[0368] Step 4:

[0369] The server automatically generates a work manual based on the analyzed business procedures. The manual includes not only optimized procedures but also advice for efficiency improvements derived from emotional data. For example, it might instruct users to "make more eye contact with customers during customer interactions," promoting emotionally positive interactions.

[0370] Step 5:

[0371] The server improves the content of the generated manuals by utilizing optimization methods based on best practices from other companies and sentiment data. Specifically, it refers to successful case studies from databases of companies in the same industry and adopts the most effective implementation methods. It also identifies procedures that are less emotionally burdensome and makes adjustments to maximize operational efficiency.

[0372] Step 6:

[0373] The terminal provides users with completed work manuals, making them available for viewing and implementation. Users refer to these manuals while performing their work activities and send daily feedback to the server via the terminal. This feedback includes suggestions for improvement based on the user's experience and is used for continuous business improvement.

[0374] Step 7:

[0375] The server receives user feedback and uses it for reanalysis and updating of operational manuals. This incorporates user experience based on emotional data, leading to the identification of new stress points and the strengthening of emotionally positive procedures. As a result, the quality and efficiency of operations improve in the long term.

[0376] (Example 2)

[0377] 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".

[0378] Achieving both improved work efficiency and consideration for employees' emotional well-being simultaneously is a challenge for companies. Traditional work manuals focus on the efficiency of work procedures but fail to consider the emotional burden on employees, which can increase stress during work and ultimately lead to decreased efficiency. Furthermore, there is a need for optimization of work processes through real-time feedback, rather than simply improving documents.

[0379] 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.

[0380] In this invention, the server includes means for acquiring information related to business activities, means for using a generative model to analyze work procedures by analyzing the acquired information, and means equipped with an emotion analysis function for analyzing the emotional state of employees. This enables not only the automatic generation of work guidelines based on information acquisition and analysis, but also dynamic work improvements that take into account the emotions of employees. This makes it possible to improve work efficiency while reducing employee stress.

[0381] "Information related to business activities" refers to various data related to the operation of a company, including activity status, employee behavior, and customer interactions.

[0382] A "generative model" is an algorithm or system that analyzes data as input and generates a specific output, and it is a model that uses machine learning or artificial intelligence techniques.

[0383] "Work guidelines" are documents consisting of procedures and policies that are instructed to ensure efficient and effective work execution within a company.

[0384] The "emotional analysis function" is a feature that analyzes employees' facial expressions and voices from data to identify and evaluate their emotions and mental state.

[0385] "Feedback" refers to opinions, impressions, and evaluation information based on work results and experiences obtained from users and employees, and is used to improve business processes.

[0386] An "optimization method" is a method or process that improves current procedures and processes based on existing data and case studies to obtain more efficient and effective results.

[0387] The embodiments for carrying out the present invention will be described in detail.

[0388] The server acquires data through various devices to collect information related to business activities. Specifically, it collects video and audio data using cameras and microphones. This data includes employee behavior, facial expressions, and voice, and serves as the basis for sentiment analysis. After preprocessing such as noise reduction, the collected data is managed within the server.

[0389] The server analyzes the collected data using generative models. These generative models utilize high-performance AI technology, such as large-scale pre-trained natural language processing models and image analysis models. This makes it possible to analyze work procedures and employee emotional states, and design human-centered work guidelines.

[0390] While typical cloud servers are used as hardware, local servers are also perfectly capable of handling the system. For software, TensorFlow and PyTorch are frequently employed as machine learning frameworks. For sentiment analysis, using API services allows for highly accurate analysis.

[0391] The terminal provides users with work guidelines generated and optimized by the server. Users view this information via the terminal and utilize it in their actual work. Feedback information from the terminal is sent to the server based on the user's experience.

[0392] A concrete example is analyzing the work procedures employees follow when serving food in a restaurant chain and designing an efficient and stress-free workflow. In this case, the server analyzes video information obtained from cameras within the store and provides optimized procedures to make employee movements smoother.

[0393] An example of a prompt to input into a generative AI model is, "Please suggest the optimal procedure for improving efficiency and safety in food preparation." By using such prompts, the generative model can present realistic and specific suggestions for improving business processes.

[0394] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0395] Step 1:

[0396] The server collects data related to business activities using cameras and sensors placed in stores and work sites. It takes video and audio data as input and temporarily stores it. Specifically, it records employee movements with cameras and captures audio through microphones. This provides real-time data on employee status and work environment.

[0397] Step 2:

[0398] The server preprocesses the collected raw data. It receives video and audio data as input and generates analyzable, formatted data as output. Specifically, it performs noise reduction and data format conversion. By removing unnecessary frames from video data and reducing background noise in audio data, it improves the accuracy of the analysis.

[0399] Step 3:

[0400] The server inputs pre-processed data into a generating AI model to analyze business procedures. It receives formatted video and audio data as input and proposes optimal business procedures as output. This process learns patterns and features from the data to design human-centered workflows. For example, it generates step-by-step guidelines for employees to work efficiently.

[0401] Step 4:

[0402] The server uses an emotion analysis engine to analyze the emotional state of employees. It further analyzes pre-processed data as input and outputs emotional data from facial expressions and voice tone. Specific operations include facial recognition technology and voice tone analysis, and emotional feedback is obtained by objectively evaluating the employee's emotions.

[0403] Step 5:

[0404] The server optimizes generated work procedures while taking emotional data into consideration. It receives emotional data and work procedures as input and provides an improved workflow as output. Specifically, it identifies procedures that cause particularly high stress and adds instructions to improve those parts. This process adjusts work procedures to make them more comfortable for employees.

[0405] Step 6:

[0406] The terminal provides users with optimized work guidelines. It receives data transmitted from the server as input and presents the information in a user-viewable format as output. Specifically, it displays visualized guidelines on a digital device, allowing users to immediately utilize them in their work.

[0407] Step 7:

[0408] Users perform tasks based on the provided work guidelines and generate feedback. They send the results and experiences of their completed tasks to the server as input, and provide feedback content to the server as output. This feedback includes evaluations of efficiency and areas for improvement.

[0409] Step 8:

[0410] The server incorporates feedback to continuously improve business guidelines and the overall system. It receives user feedback as input and generates improvement suggestions that will be reflected in future business guidelines as output. Specific actions include storing feedback in a database, analyzing it, and using the results to generate new guidelines.

[0411] (Application Example 2)

[0412] 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."

[0413] Traditional business support systems that ignore the impact of employees' emotional states on work efficiency have led to problems such as decreased work efficiency and reduced service quality due to the accumulation of stress and dissatisfaction. Furthermore, the inability to reflect improvements and guidance in work flows in real time makes rapid response difficult. To solve these problems, a flexible and adaptive business support system that takes employees' emotional states into account is necessary.

[0414] 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.

[0415] In this invention, the server includes a device for acquiring information on business operations, a device for analyzing business flows using a generation algorithm that analyzes the acquired information, and a device for automatically generating work instruction manuals based on the analyzed business flows. This makes it possible to analyze the emotional state of employees in real time and adaptively improve work instruction manuals based on emotional data.

[0416] "Information on business operations" refers to various data and information related to a company's daily operational activities, including business processes and employee behavior patterns.

[0417] A "generation algorithm" is a calculation process or method for automatically creating work instructions by analyzing the procedures and flow of work based on acquired information.

[0418] A "business process flow" refers to a series of steps or activities that show the flow of various tasks and processes performed within a company.

[0419] A "work instruction manual" is a document that contains instructions and guidelines generated based on a work flow, and is a tool for employees to perform their tasks efficiently.

[0420] "Examples from other organizations" refer to business processes and methods that have been successful in competitors or other organizations, and are used to improve one's own company's operational manuals.

[0421] An "optimization algorithm" is a calculation process or method used to adjust work instruction manuals to be more efficient and effective, based on examples from other organizations and acquired data.

[0422] "Emotional data" refers to information that quantitatively indicates an employee's psychological state and emotions, and is obtained from facial expressions and voice.

[0423] An "emotion engine" is a component that provides technologies and functions for analyzing emotional data and understanding the emotional state of employees.

[0424] "Devices including electronic equipment" refers to equipment that has built-in or connected electronic devices for displaying emotion-based guidance or information in real time.

[0425] This invention realizes a system for managing the emotional state of employees in physical stores and improving operational efficiency. The system utilizes smart glasses, a server, and an emotion recognition engine and generative AI model to operate.

[0426] The server acquires operational information from employees at each store, including video and behavioral data. This information is collected in real time via the cameras and microphones of smart glasses. An emotion recognition engine analyzes the collected data to identify the emotional state of employees. The emotional data obtained through this process is then evaluated by the server to provide emotional feedback within the employee's workflow.

[0427] The server inputs acquired emotional data and other business data into a generation algorithm to analyze the business flow. Based on the analysis results, it automatically generates a work instruction manual and improves it using an optimization algorithm based on examples from other organizations. This instruction manual is displayed on the smart glasses' screen, providing real-time guidance to employees.

[0428] For example, if the smart glasses detect that a staff member is experiencing high levels of stress while interacting with a customer, they might display advice such as, "Relax, and next, ask the customer about the product's features." In this way, employees receive appropriate guidance based on their emotions, enabling them to provide better service to customers.

[0429] Examples of prompt statements include the following:

[0430] Emotional analysis results: High stress level

[0431] Work status: Currently assisting a customer.

[0432] Required instructions: Encouraging messages and guidance on the next steps.

[0433] Example output: Relax, and next, let's ask the customer about the product's features.

[0434] This format enables real-time work guidance that reflects the emotional state of employees in a physical store environment.

[0435] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0436] Step 1:

[0437] The server acquires real-time video and audio information transmitted from the smart glasses. This information reflects the employee's activity status and speech content. The input is data from the smart glasses' camera and microphone, and the output is raw data for analysis supplied to the emotion recognition engine.

[0438] Step 2:

[0439] The server inputs the acquired video and audio information into an emotion recognition engine, which analyzes the employee's emotional state from their facial expressions and tone of voice. This process uses data mining techniques to identify human emotional characteristics. The output is quantitative data indicating the employee's emotional state.

[0440] Step 3:

[0441] The server uses a generative AI model to integrate emotional data with existing workflow information and generate work instruction manuals. In this step, input data, including prompts, is supplied to the model, and specific instructional plans for improving work efficiency are output. The generated results are used as real-time work instruction tailored to the employee's situation.

[0442] Step 4:

[0443] The terminal (smart glasses) displays work instructions received from the server within the employee's field of vision. This display includes encouraging messages and guidance on the next steps to take. The input is instruction data from the server, and the output is visual information provided to the employee.

[0444] Step 5:

[0445] The user (employee) puts into practice the instructions received through smart glasses. This allows them to improve their emotional state while performing their duties according to the provided guidance. The output, as work outcomes, is improved emotional state and work efficiency.

[0446] Step 6:

[0447] The server receives user feedback and uses it to further optimize the workflow. This feedback includes whether the guidance was helpful and changes in emotional state. The input is user feedback data, and the output is a system improvement plan, including the next update of the work instruction manual.

[0448] 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.

[0449] 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.

[0450] 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.

[0451] [Third Embodiment]

[0452] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0453] 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.

[0454] 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).

[0455] 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.

[0456] 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.

[0457] 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).

[0458] 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.

[0459] 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.

[0460] 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.

[0461] 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.

[0462] 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.

[0463] 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".

[0464] This invention is an automated system for generating business manuals aimed at improving the operational efficiency of companies. Specifically, it operates in a form in which a server, a terminal, and a user work together, each playing a specific role.

[0465] Data acquisition and preprocessing

[0466] The server receives video data (e.g., footage of work sites) and behavioral data (e.g., operation logs) collected from each of the company's stores. Based on this, the server performs data preprocessing. At this stage, noise reduction and time synchronization are performed, and the data is adjusted to a format suitable for analysis.

[0467] Data Analysis

[0468] The server analyzes business procedures using a generative model based on pre-processed data. This AI model has the ability to identify actions within videos and identify efficient workflows from behavioral data. For example, it can extract customer service procedures on a restaurant floor and suggest the most effective service sequence.

[0469] Creation and optimization of business manuals

[0470] The server automatically generates operational manuals based on the analysis results. These manuals include specific work procedures and role assignments, designed to be easily implemented by users. Furthermore, optimization methods learned from other companies' case studies ensure that the generated manuals are customized to match the specific characteristics of each company.

[0471] Manual provision and feedback

[0472] The terminal provides users with generated work manuals and supports their viewing and implementation. Users perform tasks based on these manuals and send feedback on their actual work performance to the server. This feedback is then used by the server to update the manuals.

[0473] This system allows companies to maximize efficiency while maintaining consistency in their workflows. For example, it enables the standardization of business processes across all stores in a franchise chain, improving service quality while reducing training time and costs.

[0474] The following describes the processing flow.

[0475] Step 1:

[0476] The server remotely acquires video data and employee behavior data captured from company stores and work sites. This includes data streams from cameras and sensors installed on-site, and the process begins when the server receives the data.

[0477] Step 2:

[0478] The server performs preprocessing on the received video and behavioral data. Preprocessing includes trimming unwanted parts, noise filtering, and adjusting the video clearance. This prepares a clean and consistent dataset for analysis.

[0479] Step 3:

[0480] The server applies a generative model to the pre-processed data and begins the analysis. Here, it detects the main steps of the business process from the video data and identifies employee behavior patterns. The results of this analysis provide foundational information for identifying efficient workflows.

[0481] Step 4:

[0482] The server automatically generates a work manual based on the analysis results. The generated manual includes detailed descriptions of work procedures and points to note, and is presented as a visually represented flowchart.

[0483] Step 5:

[0484] The server then optimizes the generated business manuals based on successful case studies from other companies. This process incorporates improvements to existing workflows, and the manuals are tailored to the specific characteristics of each company.

[0485] Step 6:

[0486] The terminal provides users with the final operational manual. The terminal presents information through a highly accessible interface to help users review the manual and utilize it in their daily work.

[0487] Step 7:

[0488] Users perform tasks based on the provided operational manuals and feed back the actual operational results to the server. This feedback is used by the server for subsequent analysis and manual updates, contributing to the automation of more accurate operational procedures.

[0489] (Example 1)

[0490] 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."

[0491] While businesses are required to improve efficiency and standardize each task, managing and improving individual business processes in a unified and efficient manner is a challenging task. In particular, when a company has numerous stores or branches, differences in work procedures at each location lead to decreased efficiency and inconsistent quality. This problem hinders overall productivity improvements and cost reductions for the company.

[0492] 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.

[0493] In this invention, the server includes a device for acquiring information related to business operations, a device for analyzing business flows using an artificial intelligence model that analyzes the acquired information, and a device for automatically generating business procedure manuals based on the analyzed business flows. This enables the standardization and efficiency improvement of business processes throughout the entire company.

[0494] "Business-related information" refers to data necessary for carrying out business activities and information that is useful for streamlining and improving business processes.

[0495] The term "device" refers to equipment or systems designed to perform a specific function.

[0496] An "artificial intelligence model" refers to a program or algorithm that uses machine learning and data analysis to mimic human intellectual behavior and perform problem-solving and decision-making.

[0497] A "business process flow" refers to a set of defined procedures or processes defined to achieve a specific objective.

[0498] A "work procedure manual" refers to a document that describes the procedures, methods, and points to note when performing a specific task.

[0499] "Optimized technologies based on other companies' case studies" refers to methods and technologies for making business processes more efficient, based on successful case studies and research from other companies.

[0500] "Distribution" refers to the act of sending certain information or data to a designated recipient.

[0501] "Evaluation information" refers to information regarding the results and performance of tasks performed based on the generated work procedures.

[0502] "Revision" refers to the act of reviewing existing documents, plans, procedures, etc., and making corrections as necessary.

[0503] This invention provides a system that achieves standardization and optimization of business processes in order to streamline corporate operations. Specifically, it is implemented through the cooperation of servers, terminals, and users.

[0504] 1. Data processing and analysis by the server

[0505] The server acquires operational information collected from each store and branch. This information includes video data and behavioral data. To obtain this data, the company can acquire it through cameras and operation recording devices placed within its stores. The acquired data is preprocessed on the server, such as noise reduction and time synchronization. This is done using media processing software such as FFmpeg.

[0506] Next, the server inputs the pre-processed data into a generating AI model to analyze the business flow. Here, machine learning algorithms are used to identify actions and procedures within the video and derive efficient business processes. Specifically, common algorithms such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs) are used as AI models. Based on the data obtained from this analysis, a business procedure manual is generated. For example, by inputting a prompt such as, "Analyze the efficient customer service procedures on the restaurant floor and suggest areas for improvement," the model can extract the ideal customer service procedure.

[0507] 2. Manuals provided via terminals

[0508] The terminal receives work procedure manuals generated from the server and displays them to the user in an easy-to-understand manner. These terminals include tablet computers, smartphones, and PCs. This allows users to easily understand and perform the instructed work procedures.

[0509] 3. User Feedback Collection and Improvement Process

[0510] Users perform tasks based on work procedures generated during actual work execution and observe the results. After completing a task, users send feedback to the server via a dedicated application. This feedback is stored on the server as data used to improve work procedures and is utilized in updating work procedures for future tasks. This leads to a continuous improvement in operational efficiency across the entire company.

[0511] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0512] Step 1:

[0513] Server data collection

[0514] The server receives video and behavioral data from each store via the internet. This includes data from cameras installed within the stores and user operation logs. This data is used as input for business process analysis. The server temporarily stores this raw data in preparation for subsequent processing.

[0515] Step 2:

[0516] Server data preprocessing

[0517] The server performs preprocessing on the collected video data, such as noise reduction and time synchronization. For example, it uses FFmpeg software to remove audio noise from the video and properly align the video frames. This process creates preprocessed data, preparing it for more accurate analysis.

[0518] Step 3:

[0519] Server Data Analysis

[0520] The server inputs pre-processed data into a generating AI model to perform operational analysis. Here, machine learning algorithms such as CNN and RNN are used as the AI ​​model. The model identifies actions within the video and extracts the workflow based on the behavioral data. Specifically, it analyzes customer service videos to output the optimal service sequence as the analysis result.

[0521] Step 4:

[0522] Server Business Procedure Manual Generation

[0523] The server automatically generates a work procedure manual based on the analysis results. The manual is in text format and includes specific work procedures and role assignments. The server saves this work procedure manual for the next step and applies optimization techniques that reflect best practices from other companies to improve accuracy during subsequent processing.

[0524] Step 5:

[0525] Display of work procedure manuals via terminal

[0526] The terminal displays the work procedure manual received from the server via a user interface. Users can then review the procedure manual to understand how to proceed with the work and any points to note. This function helps users to properly perform their intended tasks.

[0527] Step 6:

[0528] Collecting user feedback

[0529] Users send feedback on the tasks they perform to the server via a dedicated application. This feedback includes comments and data regarding problems and areas for improvement encountered during task execution. The server accumulates this feedback and uses it to further improve the procedures.

[0530] Step 7:

[0531] Updating the server's operational procedures manual.

[0532] The server analyzes feedback received from users and continuously updates the content of the work procedure manuals. This allows for the provision of improved manuals that reflect data analysis results using the generated AI model and the actual usage patterns of users.

[0533] (Application Example 1)

[0534] 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."

[0535] In modern manufacturing environments, the efficient operation of factory robots is essential. However, manually documenting robot operation procedures is time-consuming and labor-intensive, and extracting optimized procedures remains a challenging task. In particular, there is a need for a system that optimizes procedures for different environments and processes, and that quickly incorporates feedback from the factory floor, but concrete methods for achieving this are lacking.

[0536] 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.

[0537] In this invention, the server includes means for acquiring data on business operations, means for analyzing work procedures using a generative model that analyzes the acquired data, means for automatically generating an operation manual based on the analyzed work procedures, means for improving the automatically generated operation manual using optimization means based on examples from other companies, and means for receiving work result data from the robot as feedback and updating the operation manual. This enables the rapid generation and provision of efficient and optimized robot operation procedures, and allows for continuous optimization incorporating feedback from the field.

[0538] "Corporate operation data" refers to various types of information related to a company's activities and operations, including video footage from work sites and operation logs.

[0539] "Means of acquisition" refers to functions and devices used to collect data related to business operations.

[0540] A "generative model" refers to an algorithm for analyzing data based on AI technology, which uses video and behavioral data to extract business procedures.

[0541] "Work procedure" refers to the specific steps and processes necessary to effectively perform a particular task or operation.

[0542] An "operation manual" is a document that outlines work procedures and serves as a guide to support efficient work execution.

[0543] "Automatic generation" refers to a process in which a system processes and produces results without requiring manual intervention.

[0544] "Optimization measures" refer to the process or method of improving business manuals and procedures based on other examples and conditions.

[0545] "Feedback" refers to information and data provided by users or systems, based on their operational results and evaluations, that are used to make further improvements.

[0546] In this invention, a server collects and analyzes corporate operation data to generate efficient work procedures. The hardware used in the server must have the capability to process video data and operation log data in real time. Here, OpenCV is used to denoise and synchronize video data, and TensorFlow is used to generate an AI model for operation analysis. Work procedures are automatically generated from the analysis results, and an operation manual is constructed based on these procedures.

[0547] The terminal, installed on smart glasses or mobile devices, has the function of providing generated operation manuals to users such as on-site robot engineers. Leveraging a neuro-network-based model, the terminal visually supports optimized procedures, helping users perform their tasks efficiently.

[0548] Users perform tasks based on the provided manual and send the results as feedback to the system. This feedback is used to further optimize the manual. For example, the assembly process of a specific product in a factory may involve sequential operations such as "Step 1: Accurately grasp component A" and "Step 2: Position it correctly on the line."

[0549] As an example of a prompt for a generated AI model, you could use a sentence like, "Generate the operating procedure for a robot that grasps and places bearings. Please point out any particularly efficient procedures or important points to note."

[0550] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0551] Step 1:

[0552] The server collects video data and activity logs provided by each of the company's stores. It receives video files and digital log data as input and stores them in their initial data format. This forms the foundation for data analysis.

[0553] Step 2:

[0554] The server uses OpenCV to apply noise reduction and time synchronization to the video data. It receives the video file saved in step 1 as input, and processes it to produce a clear video output with minimal unwanted noise. During this process, the video quality is transformed to a state suitable for analysis.

[0555] Step 3:

[0556] The server processes the organized data obtained in Step 2 through a generative AI model utilizing TensorFlow for analysis. The generative AI model receives high-quality video data and motion logs as input, analyzes them, and outputs workflows and motion patterns. This analysis makes it possible to evaluate the efficiency of each work step.

[0557] Step 4:

[0558] Based on the analysis results from Step 3, the server automatically generates an operation manual that reflects the work procedures. The input is the result of the motion analysis, and the output is the newly created operation manual. This manual will function as a work guide in the actual field.

[0559] Step 5:

[0560] The terminal displays the generated operation manual on smart glasses or a mobile device and provides it to the user. The input provided is the manual created in step 4, and the output to the user is instructional and support information via the device. This function allows the user to proceed with the work while visually confirming the steps.

[0561] Step 6:

[0562] Users perform on-site tasks using a terminal and send feedback obtained during the process to the server. Input consists of feedback data on the work results and areas for improvement, which is then output to the server. This feedback is used to further improve the operation manual.

[0563] Step 7:

[0564] The server processes user feedback and updates the operation manual as needed. The input is the information provided as feedback, and the output is the updated operation manual. This loop enables continuous optimization.

[0565] 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.

[0566] This invention is a system that automatically generates business manuals for companies, supporting efficient business operations, and further incorporates an emotion engine that recognizes user emotions. The server, terminals, and users each cooperate and play their own unique roles.

[0567] Data collection and emotion recognition

[0568] The server collects video data and employee behavior data from each store and work site, and also uses an emotion engine to obtain emotional data from employees' facial expressions and voices. This allows for the collection of emotional feedback on employees' work performance as well.

[0569] Data and sentiment analysis

[0570] The server preprocesses the acquired data and inputs it into a generative model to analyze business procedures. Furthermore, based on the emotional data analyzed by the emotion engine, it analyzes the relationship between employees' emotional states and work efficiency to design a more human-centered workflow. This analysis step is also important for identifying stress points experienced by employees and processes that need improvement.

[0571] Business manual generation and optimization that takes emotions into account.

[0572] The server automatically generates operational manuals based on the analysis results and further optimizes them using success stories from competitors and the acquired sentiment data. For example, if an alert is detected based on sentiment data, instructions to draw special attention to that section of the workflow are added.

[0573] Manual provision and feedback management

[0574] The terminal provides the user with a completed work manual. The user refers to this manual to perform their tasks and returns the resulting feedback to the server. Through this cycle, new insights, such as correlation analysis between emotional data and work efficiency, are accumulated on the server and used to improve subsequent manuals and systems.

[0575] This system achieves more flexible and effective improvements in operational efficiency by incorporating emotion recognition into conventional operational manual generation systems. For example, in a restaurant chain, it can improve workflows to reduce staff stress levels, enabling them to continue providing better service to customers.

[0576] The following describes the processing flow.

[0577] Step 1:

[0578] The server collects video data from company stores and work sites, employee behavior data, and sentiment data obtained using an emotion engine. This includes data streamed in real time from cameras and microphones installed on-site. The server extracts emotions from changes in employees' facial expressions and voices and integrates them with business data.

[0579] Step 2:

[0580] The server preprocesses the collected video, behavior, and emotion data. Videos are denoised and edited to make them clear and easy to analyze, and behavior data is aligned along a timeline. Emotion data is analyzed based on predetermined emotion classifications and compiled into quantified evaluation metrics.

[0581] Step 3:

[0582] The server feeds pre-processed video and behavioral data into a generative model to analyze work procedures. Here, image recognition and pattern analysis techniques are used to identify each step in the flow, extracting the most frequently performed processes and recommended procedures. Simultaneously, the analysis of emotional data is used to understand stressors and emotional changes during work.

[0583] Step 4:

[0584] The server automatically generates a work manual based on the analyzed business procedures. The manual includes not only optimized procedures but also advice for efficiency improvements derived from emotional data. For example, it might instruct users to "make more eye contact with customers during customer interactions," promoting emotionally positive interactions.

[0585] Step 5:

[0586] The server improves the content of the generated manuals by utilizing optimization methods based on best practices from other companies and sentiment data. Specifically, it refers to successful case studies from databases of companies in the same industry and adopts the most effective implementation methods. It also identifies procedures that are less emotionally burdensome and makes adjustments to maximize operational efficiency.

[0587] Step 6:

[0588] The terminal provides users with completed work manuals, making them available for viewing and implementation. Users refer to these manuals while performing their work activities and send daily feedback to the server via the terminal. This feedback includes suggestions for improvement based on the user's experience and is used for continuous business improvement.

[0589] Step 7:

[0590] The server receives user feedback and uses it for reanalysis and updating of operational manuals. This incorporates user experience based on emotional data, leading to the identification of new stress points and the strengthening of emotionally positive procedures. As a result, the quality and efficiency of operations improve in the long term.

[0591] (Example 2)

[0592] 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."

[0593] Achieving both improved work efficiency and consideration for employees' emotional well-being simultaneously is a challenge for companies. Traditional work manuals focus on the efficiency of work procedures but fail to consider the emotional burden on employees, which can increase stress during work and ultimately lead to decreased efficiency. Furthermore, there is a need for optimization of work processes through real-time feedback, rather than simply improving documents.

[0594] 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.

[0595] In this invention, the server includes means for acquiring information related to business activities, means for using a generative model to analyze work procedures by analyzing the acquired information, and means equipped with an emotion analysis function for analyzing the emotional state of employees. This enables not only the automatic generation of work guidelines based on information acquisition and analysis, but also dynamic work improvements that take into account the emotions of employees. This makes it possible to improve work efficiency while reducing employee stress.

[0596] "Information related to business activities" refers to various data related to the operation of a company, including activity status, employee behavior, and customer interactions.

[0597] A "generative model" is an algorithm or system that analyzes data as input and generates a specific output, and it is a model that uses machine learning or artificial intelligence techniques.

[0598] "Work guidelines" are documents consisting of procedures and policies that are instructed to ensure efficient and effective work execution within a company.

[0599] The "emotional analysis function" is a feature that analyzes employees' facial expressions and voices from data to identify and evaluate their emotions and mental state.

[0600] "Feedback" refers to opinions, impressions, and evaluation information based on work results and experiences obtained from users and employees, and is used to improve business processes.

[0601] An "optimization method" is a method or process that improves current procedures and processes based on existing data and case studies to obtain more efficient and effective results.

[0602] The embodiments for carrying out the present invention will be described in detail.

[0603] The server acquires data through various devices to collect information related to business activities. Specifically, it collects video and audio data using cameras and microphones. This data includes employee behavior, facial expressions, and voice, and serves as the basis for sentiment analysis. After preprocessing such as noise reduction, the collected data is managed within the server.

[0604] The server analyzes the collected data using generative models. These generative models utilize high-performance AI technology, such as large-scale pre-trained natural language processing models and image analysis models. This makes it possible to analyze work procedures and employee emotional states, and design human-centered work guidelines.

[0605] While typical cloud servers are used as hardware, local servers are also perfectly capable of handling the system. For software, TensorFlow and PyTorch are frequently employed as machine learning frameworks. For sentiment analysis, using API services allows for highly accurate analysis.

[0606] The terminal provides users with work guidelines generated and optimized by the server. Users view this information via the terminal and utilize it in their actual work. Feedback information from the terminal is sent to the server based on the user's experience.

[0607] A concrete example is analyzing the work procedures employees follow when serving food in a restaurant chain and designing an efficient and stress-free workflow. In this case, the server analyzes video information obtained from cameras within the store and provides optimized procedures to make employee movements smoother.

[0608] An example of a prompt to input into a generative AI model is, "Please suggest the optimal procedure for improving efficiency and safety in food preparation." By using such prompts, the generative model can present realistic and specific suggestions for improving business processes.

[0609] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0610] Step 1:

[0611] The server collects data related to business activities using cameras and sensors placed in stores and work sites. It takes video and audio data as input and temporarily stores it. Specifically, it records employee movements with cameras and captures audio through microphones. This provides real-time data on employee status and work environment.

[0612] Step 2:

[0613] The server preprocesses the collected raw data. It receives video and audio data as input and generates analyzable, formatted data as output. Specifically, it performs noise reduction and data format conversion. By removing unnecessary frames from video data and reducing background noise in audio data, it improves the accuracy of the analysis.

[0614] Step 3:

[0615] The server inputs pre-processed data into a generating AI model to analyze business procedures. It receives formatted video and audio data as input and proposes optimal business procedures as output. This process learns patterns and features from the data to design human-centered workflows. For example, it generates step-by-step guidelines for employees to work efficiently.

[0616] Step 4:

[0617] The server uses an emotion analysis engine to analyze the emotional state of employees. It further analyzes pre-processed data as input and outputs emotional data from facial expressions and voice tone. Specific operations include facial recognition technology and voice tone analysis, and emotional feedback is obtained by objectively evaluating the employee's emotions.

[0618] Step 5:

[0619] The server optimizes generated work procedures while taking emotional data into consideration. It receives emotional data and work procedures as input and provides an improved workflow as output. Specifically, it identifies procedures that cause particularly high stress and adds instructions to improve those parts. This process adjusts work procedures to make them more comfortable for employees.

[0620] Step 6:

[0621] The terminal provides users with optimized work guidelines. It receives data transmitted from the server as input and presents the information in a user-viewable format as output. Specifically, it displays visualized guidelines on a digital device, allowing users to immediately utilize them in their work.

[0622] Step 7:

[0623] Users perform tasks based on the provided work guidelines and generate feedback. They send the results and experiences of their completed tasks to the server as input, and provide feedback content to the server as output. This feedback includes evaluations of efficiency and areas for improvement.

[0624] Step 8:

[0625] The server incorporates feedback to continuously improve business guidelines and the overall system. It receives user feedback as input and generates improvement suggestions that will be reflected in future business guidelines as output. Specific actions include storing feedback in a database, analyzing it, and using the results to generate new guidelines.

[0626] (Application Example 2)

[0627] 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."

[0628] Traditional business support systems that ignore the impact of employees' emotional states on work efficiency have led to problems such as decreased work efficiency and reduced service quality due to the accumulation of stress and dissatisfaction. Furthermore, the inability to reflect improvements and guidance in work flows in real time makes rapid response difficult. To solve these problems, a flexible and adaptive business support system that takes employees' emotional states into account is necessary.

[0629] 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.

[0630] In this invention, the server includes a device for acquiring information on business operations, a device for analyzing business flows using a generation algorithm that analyzes the acquired information, and a device for automatically generating work instruction manuals based on the analyzed business flows. This makes it possible to analyze the emotional state of employees in real time and adaptively improve work instruction manuals based on emotional data.

[0631] "Information on business operations" refers to various data and information related to a company's daily operational activities, including business processes and employee behavior patterns.

[0632] A "generation algorithm" is a calculation process or method for automatically creating work instructions by analyzing the procedures and flow of work based on acquired information.

[0633] A "business process flow" refers to a series of steps or activities that show the flow of various tasks and processes performed within a company.

[0634] A "work instruction manual" is a document that contains instructions and guidelines generated based on a work flow, and is a tool for employees to perform their tasks efficiently.

[0635] "Examples from other organizations" refer to business processes and methods that have been successful in competitors or other organizations, and are used to improve one's own company's operational manuals.

[0636] An "optimization algorithm" is a calculation process or method used to adjust work instruction manuals to be more efficient and effective, based on examples from other organizations and acquired data.

[0637] "Emotional data" refers to information that quantitatively indicates an employee's psychological state and emotions, and is obtained from facial expressions and voice.

[0638] An "emotion engine" is a component that provides technologies and functions for analyzing emotional data and understanding the emotional state of employees.

[0639] "Devices including electronic equipment" refers to equipment that has built-in or connected electronic devices for displaying emotion-based guidance or information in real time.

[0640] This invention realizes a system for managing the emotional state of employees in physical stores and improving operational efficiency. The system utilizes smart glasses, a server, an emotion recognition engine, and a generative AI model to operate.

[0641] The server acquires operational information from employees at each store, including video and behavioral data. This information is collected in real time via the cameras and microphones of smart glasses. An emotion recognition engine analyzes the collected data to identify the emotional state of employees. The emotional data obtained through this process is then evaluated by the server to provide emotional feedback within the employee's workflow.

[0642] The server inputs acquired emotional data and other business data into a generation algorithm to analyze the business flow. Based on the analysis results, it automatically generates a work instruction manual and improves it using an optimization algorithm based on examples from other organizations. This instruction manual is displayed on the smart glasses' screen, providing real-time guidance to employees.

[0643] For example, if the smart glasses detect that a staff member is experiencing high levels of stress while interacting with a customer, they might display advice such as, "Relax, and next, ask the customer about the product's features." In this way, employees receive appropriate guidance based on their emotions, enabling them to provide better service to customers.

[0644] Examples of prompt statements include the following:

[0645] Emotional analysis results: High stress level

[0646] Work status: Currently assisting a customer.

[0647] Required instructions: Encouraging messages and guidance on the next steps.

[0648] Example output: Relax, and next, let's ask the customer about the product's features.

[0649] This format enables real-time work guidance that reflects the emotional state of employees in a physical store environment.

[0650] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0651] Step 1:

[0652] The server acquires real-time video and audio information transmitted from the smart glasses. This information reflects the employee's activity status and speech content. The input is data from the smart glasses' camera and microphone, and the output is raw data for analysis supplied to the emotion recognition engine.

[0653] Step 2:

[0654] The server inputs the acquired video and audio information into an emotion recognition engine, which analyzes the employee's emotional state from their facial expressions and tone of voice. This process uses data mining techniques to identify human emotional characteristics. The output is quantitative data indicating the employee's emotional state.

[0655] Step 3:

[0656] The server uses a generative AI model to integrate emotional data with existing workflow information and generate work instruction manuals. In this step, input data, including prompts, is supplied to the model, and specific instructional plans for improving work efficiency are output. The generated results are used as real-time work instruction tailored to the employee's situation.

[0657] Step 4:

[0658] The terminal (smart glasses) displays work instructions received from the server within the employee's field of vision. This display includes encouraging messages and guidance on the next steps to take. The input is instruction data from the server, and the output is visual information provided to the employee.

[0659] Step 5:

[0660] The user (employee) puts into practice the instructions received through smart glasses. This allows them to improve their emotional state while performing their duties according to the provided guidance. The output, as work outcomes, is improved emotional state and work efficiency.

[0661] Step 6:

[0662] The server receives user feedback and uses it to further optimize the workflow. This feedback includes whether the guidance was helpful and changes in emotional state. The input is user feedback data, and the output is a system improvement plan, including the next update of the work instruction manual.

[0663] 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.

[0664] 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.

[0665] 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.

[0666] [Fourth Embodiment]

[0667] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0668] 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.

[0669] 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).

[0670] 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.

[0671] 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.

[0672] 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).

[0673] 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.

[0674] 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.

[0675] 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.

[0676] 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.

[0677] 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.

[0678] 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.

[0679] 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".

[0680] This invention is an automated system for generating business manuals aimed at improving the operational efficiency of companies. Specifically, it operates in a form in which a server, a terminal, and a user work together, each playing a specific role.

[0681] Data acquisition and preprocessing

[0682] The server receives video data (e.g., footage of work sites) and behavioral data (e.g., operation logs) collected from each of the company's stores. Based on this, the server performs data preprocessing. At this stage, noise reduction and time synchronization are performed, and the data is adjusted to a format suitable for analysis.

[0683] Data Analysis

[0684] The server analyzes business procedures using a generative model based on pre-processed data. This AI model has the ability to identify actions within videos and identify efficient workflows from behavioral data. For example, it can extract customer service procedures on a restaurant floor and suggest the most effective service sequence.

[0685] Creation and optimization of business manuals

[0686] The server automatically generates operational manuals based on the analysis results. These manuals include specific work procedures and role assignments, designed to be easily implemented by users. Furthermore, optimization methods learned from other companies' case studies ensure that the generated manuals are customized to match the specific characteristics of each company.

[0687] Manual provision and feedback

[0688] The terminal provides users with generated work manuals and supports their viewing and implementation. Users perform tasks based on these manuals and send feedback on their actual work performance to the server. This feedback is then used by the server to update the manuals.

[0689] This system allows companies to maximize efficiency while maintaining consistency in their workflows. For example, it enables the standardization of business processes across all stores in a franchise chain, improving service quality while reducing training time and costs.

[0690] The following describes the processing flow.

[0691] Step 1:

[0692] The server remotely acquires video data and employee behavior data captured from company stores and work sites. This includes data streams from cameras and sensors installed on-site, and the process begins when the server receives the data.

[0693] Step 2:

[0694] The server performs preprocessing on the received video and behavioral data. Preprocessing includes trimming unwanted parts, noise filtering, and adjusting the video clearance. This prepares a clean and consistent dataset for analysis.

[0695] Step 3:

[0696] The server applies a generative model to the pre-processed data and begins the analysis. Here, it detects the main steps of the business process from the video data and identifies employee behavior patterns. The results of this analysis provide foundational information for identifying efficient workflows.

[0697] Step 4:

[0698] The server automatically generates a work manual based on the analysis results. The generated manual includes detailed descriptions of work procedures and points to note, and is presented as a visually represented flowchart.

[0699] Step 5:

[0700] The server then optimizes the generated business manuals based on successful case studies from other companies. This process incorporates improvements to existing workflows, and the manuals are tailored to the specific characteristics of each company.

[0701] Step 6:

[0702] The terminal provides users with the final operational manual. The terminal presents information through a highly accessible interface to help users review the manual and utilize it in their daily work.

[0703] Step 7:

[0704] Users perform tasks based on the provided operational manuals and feed back the actual operational results to the server. This feedback is used by the server for subsequent analysis and manual updates, contributing to the automation of more accurate operational procedures.

[0705] (Example 1)

[0706] 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".

[0707] While businesses are required to improve efficiency and standardize each task, managing and improving individual business processes in a unified and efficient manner is a challenging task. In particular, when a company has numerous stores or branches, differences in work procedures at each location lead to decreased efficiency and inconsistent quality. This problem hinders overall productivity improvements and cost reductions for the company.

[0708] 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.

[0709] In this invention, the server includes a device for acquiring information related to business operations, a device for analyzing business flows using an artificial intelligence model that analyzes the acquired information, and a device for automatically generating business procedure manuals based on the analyzed business flows. This enables the standardization and efficiency improvement of business processes throughout the entire company.

[0710] "Business-related information" refers to data necessary for carrying out business activities and information that is useful for streamlining and improving business processes.

[0711] The term "device" refers to equipment or systems designed to perform a specific function.

[0712] An "artificial intelligence model" refers to a program or algorithm that uses machine learning and data analysis to mimic human intellectual behavior and perform problem-solving and decision-making.

[0713] A "business process flow" refers to a set of defined procedures or processes defined to achieve a specific objective.

[0714] A "work procedure manual" refers to a document that describes the procedures, methods, and points to note when performing a specific task.

[0715] "Optimized technologies based on other companies' case studies" refers to methods and technologies for making business processes more efficient, based on successful case studies and research from other companies.

[0716] "Distribution" refers to the act of sending certain information or data to a designated recipient.

[0717] "Evaluation information" refers to information regarding the results and performance of tasks performed based on the generated work procedures.

[0718] "Revision" refers to the act of reviewing existing documents, plans, procedures, etc., and making corrections as necessary.

[0719] This invention provides a system that achieves standardization and optimization of business processes in order to streamline corporate operations. Specifically, it is implemented through the cooperation of servers, terminals, and users.

[0720] 1. Data processing and analysis by the server

[0721] The server acquires operational information collected from each store and branch. This information includes video data and behavioral data. To obtain this data, the company can acquire it through cameras and operation recording devices placed within its stores. The acquired data is preprocessed on the server, such as noise reduction and time synchronization. This is done using media processing software such as FFmpeg.

[0722] Next, the server inputs the pre-processed data into a generating AI model to analyze the business flow. Here, machine learning algorithms are used to identify actions and procedures within the video and derive efficient business processes. Specifically, common algorithms such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs) are used as AI models. Based on the data obtained from this analysis, a business procedure manual is generated. For example, by inputting a prompt such as, "Analyze the efficient customer service procedures on the restaurant floor and suggest areas for improvement," the model can extract the ideal customer service procedure.

[0723] 2. Manuals provided via terminals

[0724] The terminal receives work procedure manuals generated from the server and displays them to the user in an easy-to-understand manner. These terminals include tablet computers, smartphones, and PCs. This allows users to easily understand and perform the instructed work procedures.

[0725] 3. User Feedback Collection and Improvement Process

[0726] Users perform tasks based on work procedures generated during actual work execution and observe the results. After completing a task, users send feedback to the server via a dedicated application. This feedback is stored on the server as data used to improve work procedures and is utilized in updating work procedures for future tasks. This leads to a continuous improvement in operational efficiency across the entire company.

[0727] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0728] Step 1:

[0729] Server data collection

[0730] The server receives video and behavioral data from each store via the internet. This includes data from cameras installed within the stores and user operation logs. This data is used as input for business process analysis. The server temporarily stores this raw data in preparation for subsequent processing.

[0731] Step 2:

[0732] Server data preprocessing

[0733] The server performs preprocessing on the collected video data, such as noise reduction and time synchronization. For example, it uses FFmpeg software to remove audio noise from the video and properly align the video frames. This process creates preprocessed data, preparing it for more accurate analysis.

[0734] Step 3:

[0735] Server Data Analysis

[0736] The server inputs pre-processed data into a generating AI model to perform operational analysis. Here, machine learning algorithms such as CNN and RNN are used as the AI ​​model. The model identifies actions within the video and extracts the workflow based on the behavioral data. Specifically, it analyzes customer service videos to output the optimal service sequence as the analysis result.

[0737] Step 4:

[0738] Server Business Procedure Manual Generation

[0739] The server automatically generates a work procedure manual based on the analysis results. The manual is in text format and includes specific work procedures and role assignments. The server saves this work procedure manual for the next step and applies optimization techniques that reflect best practices from other companies to improve accuracy during subsequent processing.

[0740] Step 5:

[0741] Display of work procedure manuals via terminal

[0742] The terminal displays the work procedure manual received from the server via a user interface. Users can then review the procedure manual to understand how to proceed with the work and any points to note. This function helps users to properly perform their intended tasks.

[0743] Step 6:

[0744] Collecting user feedback

[0745] Users send feedback on the tasks they perform to the server via a dedicated application. This feedback includes comments and data regarding problems and areas for improvement encountered during task execution. The server accumulates this feedback and uses it to further improve the procedures.

[0746] Step 7:

[0747] Updating the server's operational procedures manual.

[0748] The server analyzes feedback received from users and continuously updates the content of the work procedure manuals. This allows for the provision of improved manuals that reflect data analysis results using the generated AI model and the actual usage patterns of users.

[0749] (Application Example 1)

[0750] 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".

[0751] In modern manufacturing environments, the efficient operation of factory robots is essential. However, manually documenting robot operation procedures is time-consuming and labor-intensive, and extracting optimized procedures remains a challenging task. In particular, there is a need for a system that optimizes procedures for different environments and processes, and that quickly incorporates feedback from the factory floor, but concrete methods for achieving this are lacking.

[0752] 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.

[0753] In this invention, the server includes means for acquiring data on business operations, means for analyzing work procedures using a generative model that analyzes the acquired data, means for automatically generating an operation manual based on the analyzed work procedures, means for improving the automatically generated operation manual using optimization means based on examples from other companies, and means for receiving work result data from the robot as feedback and updating the operation manual. This enables the rapid generation and provision of efficient and optimized robot operation procedures, and allows for continuous optimization incorporating feedback from the field.

[0754] "Corporate operation data" refers to various types of information related to a company's activities and operations, including video footage from work sites and operation logs.

[0755] "Means of acquisition" refers to functions and devices used to collect data related to business operations.

[0756] A "generative model" refers to an algorithm for analyzing data based on AI technology, which uses video and behavioral data to extract business procedures.

[0757] "Work procedure" refers to the specific steps and processes necessary to effectively perform a particular task or operation.

[0758] An "operation manual" is a document that outlines work procedures and serves as a guide to support efficient work execution.

[0759] "Automatic generation" refers to a process in which a system processes and produces results without requiring manual intervention.

[0760] "Optimization measures" refer to the process or method of improving business manuals and procedures based on other examples and conditions.

[0761] "Feedback" refers to information and data provided by users or systems, based on their operational results and evaluations, that are used to make further improvements.

[0762] In this invention, a server collects and analyzes corporate operation data to generate efficient work procedures. The hardware used in the server must have the capability to process video data and operation log data in real time. Here, OpenCV is used to denoise and synchronize video data, and TensorFlow is used to generate an AI model for operation analysis. Work procedures are automatically generated from the analysis results, and an operation manual is constructed based on these procedures.

[0763] The terminal, installed on smart glasses or mobile devices, has the function of providing generated operation manuals to users such as on-site robot engineers. Leveraging a neuro-network-based model, the terminal visually supports optimized procedures, helping users perform their tasks efficiently.

[0764] Users perform tasks based on the provided manual and send the results as feedback to the system. This feedback is used to further optimize the manual. For example, the assembly process of a specific product in a factory may involve sequential operations such as "Step 1: Accurately grasp component A" and "Step 2: Position it correctly on the line."

[0765] As an example of a prompt for a generated AI model, you could use a sentence like, "Generate the operating procedure for a robot that grasps and places bearings. Please point out any particularly efficient procedures or important points to note."

[0766] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0767] Step 1:

[0768] The server collects video data and activity logs provided by each of the company's stores. It receives video files and digital log data as input and stores them in their initial data format. This forms the foundation for data analysis.

[0769] Step 2:

[0770] The server uses OpenCV to apply noise reduction and time synchronization to the video data. It receives the video file saved in step 1 as input, and processes it to produce a clear video output with minimal unwanted noise. During this process, the video quality is transformed to a state suitable for analysis.

[0771] Step 3:

[0772] The server processes the organized data obtained in Step 2 through a generative AI model utilizing TensorFlow for analysis. The generative AI model receives high-quality video data and motion logs as input, analyzes them, and outputs workflows and motion patterns. This analysis makes it possible to evaluate the efficiency of each work step.

[0773] Step 4:

[0774] Based on the analysis results from Step 3, the server automatically generates an operation manual that reflects the work procedures. The input is the result of the motion analysis, and the output is the newly created operation manual. This manual will function as a work guide in the actual field.

[0775] Step 5:

[0776] The terminal displays the generated operation manual on smart glasses or a mobile device and provides it to the user. The input provided is the manual created in step 4, and the output to the user is instructional and support information via the device. This function allows the user to proceed with the work while visually confirming the steps.

[0777] Step 6:

[0778] Users perform on-site tasks using a terminal and send feedback obtained during the process to the server. Input consists of feedback data on the work results and areas for improvement, which is then output to the server. This feedback is used to further improve the operation manual.

[0779] Step 7:

[0780] The server processes user feedback and updates the operation manual as needed. The input is the information provided as feedback, and the output is the updated operation manual. This loop enables continuous optimization.

[0781] 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.

[0782] This invention is a system that automatically generates business manuals for companies, supporting efficient business operations, and further incorporates an emotion engine that recognizes user emotions. The server, terminals, and users each cooperate and play their own unique roles.

[0783] Data collection and emotion recognition

[0784] The server collects video data and employee behavior data from each store and work site, and also uses an emotion engine to obtain emotional data from employees' facial expressions and voices. This allows for the collection of emotional feedback on employees' work performance as well.

[0785] Data and sentiment analysis

[0786] The server preprocesses the acquired data and inputs it into a generative model to analyze business procedures. Furthermore, based on the emotional data analyzed by the emotion engine, it analyzes the relationship between employees' emotional states and work efficiency to design a more human-centered workflow. This analysis step is also important for identifying stress points experienced by employees and processes that need improvement.

[0787] Business manual generation and optimization that takes emotions into account.

[0788] The server automatically generates operational manuals based on the analysis results and further optimizes them using success stories from competitors and the acquired sentiment data. For example, if an alert is detected based on sentiment data, instructions to draw special attention to that section of the workflow are added.

[0789] Manual provision and feedback management

[0790] The terminal provides the user with a completed work manual. The user refers to this manual to perform their tasks and returns the resulting feedback to the server. Through this cycle, new insights, such as correlation analysis between emotional data and work efficiency, are accumulated on the server and used to improve subsequent manuals and systems.

[0791] This system achieves more flexible and effective improvements in operational efficiency by incorporating emotion recognition into conventional operational manual generation systems. For example, in a restaurant chain, it can improve workflows to reduce staff stress levels, enabling them to continue providing better service to customers.

[0792] The following describes the processing flow.

[0793] Step 1:

[0794] The server collects video data from company stores and work sites, employee behavior data, and sentiment data obtained using an emotion engine. This includes data streamed in real time from cameras and microphones installed on-site. The server extracts emotions from changes in employees' facial expressions and voices and integrates them with business data.

[0795] Step 2:

[0796] The server preprocesses the collected video, behavior, and emotion data. Videos are denoised and edited to make them clear and easy to analyze, and behavior data is aligned along a timeline. Emotion data is analyzed based on predetermined emotion classifications and compiled into quantified evaluation metrics.

[0797] Step 3:

[0798] The server feeds pre-processed video and behavioral data into a generative model to analyze work procedures. Here, image recognition and pattern analysis techniques are used to identify each step in the flow, extracting the most frequently performed processes and recommended procedures. Simultaneously, the analysis of emotional data is used to understand stressors and emotional changes during work.

[0799] Step 4:

[0800] The server automatically generates a work manual based on the analyzed business procedures. The manual includes not only optimized procedures but also advice for efficiency improvements derived from emotional data. For example, it might instruct users to "make more eye contact with customers during customer interactions," promoting emotionally positive interactions.

[0801] Step 5:

[0802] The server improves the content of the generated manuals by utilizing optimization methods based on best practices from other companies and sentiment data. Specifically, it refers to successful case studies from databases of companies in the same industry and adopts the most effective implementation methods. It also identifies procedures that are less emotionally burdensome and makes adjustments to maximize operational efficiency.

[0803] Step 6:

[0804] The terminal provides users with completed work manuals, making them available for viewing and implementation. Users refer to these manuals while performing their work activities and send daily feedback to the server via the terminal. This feedback includes suggestions for improvement based on the user's experience and is used for continuous business improvement.

[0805] Step 7:

[0806] The server receives user feedback and uses it for reanalysis and updating of operational manuals. This incorporates user experience based on emotional data, leading to the identification of new stress points and the strengthening of emotionally positive procedures. As a result, the quality and efficiency of operations improve in the long term.

[0807] (Example 2)

[0808] 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".

[0809] Achieving both improved work efficiency and consideration for employees' emotional well-being simultaneously is a challenge for companies. Traditional work manuals focus on the efficiency of work procedures but fail to consider the emotional burden on employees, which can increase stress during work and ultimately lead to decreased efficiency. Furthermore, there is a need for optimization of work processes through real-time feedback, rather than simply improving documents.

[0810] 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.

[0811] In this invention, the server includes means for acquiring information related to business activities, means for using a generative model to analyze work procedures by analyzing the acquired information, and means equipped with an emotion analysis function for analyzing the emotional state of employees. This enables not only the automatic generation of work guidelines based on information acquisition and analysis, but also dynamic work improvements that take into account the emotions of employees. This makes it possible to improve work efficiency while reducing employee stress.

[0812] "Information related to business activities" refers to various data related to the operation of a company, including activity status, employee behavior, and customer interactions.

[0813] A "generative model" is an algorithm or system that analyzes data as input and generates a specific output, and it is a model that uses machine learning or artificial intelligence techniques.

[0814] "Work guidelines" are documents consisting of procedures and policies that are instructed to ensure efficient and effective work execution within a company.

[0815] The "emotional analysis function" is a feature that analyzes employees' facial expressions and voices from data to identify and evaluate their emotions and mental state.

[0816] "Feedback" refers to opinions, impressions, and evaluation information based on work results and experiences obtained from users and employees, and is used to improve business processes.

[0817] An "optimization method" is a method or process that improves current procedures and processes based on existing data and case studies to obtain more efficient and effective results.

[0818] The embodiments for carrying out the present invention will be described in detail.

[0819] The server acquires data through various devices to collect information related to business activities. Specifically, it collects video and audio data using cameras and microphones. This data includes employee behavior, facial expressions, and voice, and serves as the basis for sentiment analysis. After preprocessing such as noise reduction, the collected data is managed within the server.

[0820] The server analyzes the collected data using generative models. These generative models utilize high-performance AI technology, such as large-scale pre-trained natural language processing models and image analysis models. This makes it possible to analyze work procedures and employee emotional states, and design human-centered work guidelines.

[0821] While typical cloud servers are used as hardware, local servers are also perfectly capable of handling the system. For software, TensorFlow and PyTorch are frequently employed as machine learning frameworks. For sentiment analysis, using API services allows for highly accurate analysis.

[0822] The terminal provides users with work guidelines generated and optimized by the server. Users view this information via the terminal and utilize it in their actual work. Feedback information from the terminal is sent to the server based on the user's experience.

[0823] A concrete example is analyzing the work procedures employees follow when serving food in a restaurant chain and designing an efficient and stress-free workflow. In this case, the server analyzes video information obtained from cameras within the store and provides optimized procedures to make employee movements smoother.

[0824] An example of a prompt to input into a generative AI model is, "Please suggest the optimal procedure for improving efficiency and safety in food preparation." By using such prompts, the generative model can present realistic and specific suggestions for improving business processes.

[0825] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0826] Step 1:

[0827] The server collects data related to business activities using cameras and sensors placed in stores and work sites. It takes video and audio data as input and temporarily stores it. Specifically, it records employee movements with cameras and captures audio through microphones. This provides real-time data on employee status and work environment.

[0828] Step 2:

[0829] The server preprocesses the collected raw data. It receives video and audio data as input and generates analyzable, formatted data as output. Specifically, it performs noise reduction and data format conversion. By removing unnecessary frames from video data and reducing background noise in audio data, it improves the accuracy of the analysis.

[0830] Step 3:

[0831] The server inputs pre-processed data into a generating AI model to analyze business procedures. It receives formatted video and audio data as input and proposes optimal business procedures as output. This process learns patterns and features from the data to design human-centered workflows. For example, it generates step-by-step guidelines for employees to work efficiently.

[0832] Step 4:

[0833] The server uses an emotion analysis engine to analyze the emotional state of employees. It further analyzes pre-processed data as input and outputs emotional data from facial expressions and voice tone. Specific operations include facial recognition technology and voice tone analysis, and emotional feedback is obtained by objectively evaluating the employee's emotions.

[0834] Step 5:

[0835] The server optimizes generated work procedures while taking emotional data into consideration. It receives emotional data and work procedures as input and provides an improved workflow as output. Specifically, it identifies procedures that cause particularly high stress and adds instructions to improve those parts. This process adjusts work procedures to make them more comfortable for employees.

[0836] Step 6:

[0837] The terminal provides users with optimized work guidelines. It receives data transmitted from the server as input and presents the information in a user-viewable format as output. Specifically, it displays visualized guidelines on a digital device, allowing users to immediately utilize them in their work.

[0838] Step 7:

[0839] Users perform tasks based on the provided work guidelines and generate feedback. They send the results and experiences of their completed tasks to the server as input, and provide feedback content to the server as output. This feedback includes evaluations of efficiency and areas for improvement.

[0840] Step 8:

[0841] The server incorporates feedback to continuously improve business guidelines and the overall system. It receives user feedback as input and generates improvement suggestions that will be reflected in future business guidelines as output. Specific actions include storing feedback in a database, analyzing it, and using the results to generate new guidelines.

[0842] (Application Example 2)

[0843] 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".

[0844] Traditional business support systems that ignore the impact of employees' emotional states on work efficiency have led to problems such as decreased work efficiency and reduced service quality due to the accumulation of stress and dissatisfaction. Furthermore, the inability to reflect improvements and guidance in work flows in real time makes rapid response difficult. To solve these problems, a flexible and adaptive business support system that takes employees' emotional states into account is necessary.

[0845] 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.

[0846] In this invention, the server includes a device for acquiring information on business operations, a device for analyzing business flows using a generation algorithm that analyzes the acquired information, and a device for automatically generating work instruction manuals based on the analyzed business flows. This makes it possible to analyze the emotional state of employees in real time and adaptively improve work instruction manuals based on emotional data.

[0847] "Information on business operations" refers to various data and information related to a company's daily operational activities, including business processes and employee behavior patterns.

[0848] A "generation algorithm" is a calculation process or method for automatically creating work instructions by analyzing the procedures and flow of work based on acquired information.

[0849] A "business process flow" refers to a series of steps or activities that show the flow of various tasks and processes performed within a company.

[0850] A "work instruction manual" is a document that contains instructions and guidelines generated based on a work flow, and is a tool for employees to perform their tasks efficiently.

[0851] "Examples from other organizations" refer to business processes and methods that have been successful in competitors or other organizations, and are used to improve one's own company's operational manuals.

[0852] An "optimization algorithm" is a calculation process or method used to adjust work instruction manuals to be more efficient and effective, based on examples from other organizations and acquired data.

[0853] "Emotional data" refers to information that quantitatively indicates an employee's psychological state and emotions, and is obtained from facial expressions and voice.

[0854] An "emotion engine" is a component that provides technologies and functions for analyzing emotional data and understanding the emotional state of employees.

[0855] "Devices including electronic equipment" refers to equipment that has built-in or connected electronic devices for displaying emotion-based guidance or information in real time.

[0856] This invention realizes a system for managing the emotional state of employees in physical stores and improving operational efficiency. The system utilizes smart glasses, a server, an emotion recognition engine, and a generative AI model to operate.

[0857] The server acquires operational information from employees at each store, including video and behavioral data. This information is collected in real time via the cameras and microphones of smart glasses. An emotion recognition engine analyzes the collected data to identify the emotional state of employees. The emotional data obtained through this process is then evaluated by the server to provide emotional feedback within the employee's workflow.

[0858] The server inputs acquired emotional data and other business data into a generation algorithm to analyze the business flow. Based on the analysis results, it automatically generates a work instruction manual and improves it using an optimization algorithm based on examples from other organizations. This instruction manual is displayed on the smart glasses' screen, providing real-time guidance to employees.

[0859] For example, if the smart glasses detect that a staff member is experiencing high levels of stress while interacting with a customer, they might display advice such as, "Relax, and next, ask the customer about the product's features." In this way, employees receive appropriate guidance based on their emotions, enabling them to provide better service to customers.

[0860] Examples of prompt statements include the following:

[0861] Emotional analysis results: High stress level

[0862] Work status: Currently assisting a customer.

[0863] Required instructions: Encouraging messages and guidance on the next steps.

[0864] Example output: Relax, and next, let's ask the customer about the product's features.

[0865] This format enables real-time work guidance that reflects the emotional state of employees in a physical store environment.

[0866] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0867] Step 1:

[0868] The server acquires real-time video and audio information transmitted from the smart glasses. This information reflects the employee's activity status and speech content. The input is data from the smart glasses' camera and microphone, and the output is raw data for analysis supplied to the emotion recognition engine.

[0869] Step 2:

[0870] The server inputs the acquired video and audio information into an emotion recognition engine, which analyzes the employee's emotional state from their facial expressions and tone of voice. This process uses data mining techniques to identify human emotional characteristics. The output is quantitative data indicating the employee's emotional state.

[0871] Step 3:

[0872] The server uses a generative AI model to integrate emotional data with existing workflow information and generate work instruction manuals. In this step, input data, including prompts, is supplied to the model, and specific instructional plans for improving work efficiency are output. The generated results are used as real-time work instruction tailored to the employee's situation.

[0873] Step 4:

[0874] The terminal (smart glasses) displays work instructions received from the server within the employee's field of vision. This display includes encouraging messages and guidance on the next steps to take. The input is instruction data from the server, and the output is visual information provided to the employee.

[0875] Step 5:

[0876] The user (employee) puts into practice the instructions received through smart glasses. This allows them to improve their emotional state while performing their duties according to the provided guidance. The output, as work outcomes, is improved emotional state and work efficiency.

[0877] Step 6:

[0878] The server receives user feedback and uses it to further optimize the workflow. This feedback includes whether the guidance was helpful and changes in emotional state. The input is user feedback data, and the output is a system improvement plan, including the next update of the work instruction manual.

[0879] 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.

[0880] 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.

[0881] 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.

[0882] 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.

[0883] 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.

[0884] 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.

[0885] 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.

[0886] 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.

[0887] 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."

[0888] 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.

[0889] 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.

[0890] 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.

[0891] 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.

[0892] 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.

[0893] 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.

[0894] 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.

[0895] 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.

[0896] 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.

[0897] 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.

[0898] 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.

[0899] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0900] The following is further disclosed regarding the embodiments described above.

[0901] (Claim 1)

[0902] Means of acquiring data on business operations,

[0903] A means for analyzing business procedures using a generative model that analyzes the acquired data,

[0904] A means for automatically generating a business manual based on the analyzed business procedures,

[0905] A means to improve the automatically generated business manual using optimization methods based on examples from other companies,

[0906] Means for providing the generated and improved business manuals,

[0907] A system that includes this.

[0908] (Claim 2)

[0909] The system according to claim 1, further comprising the data acquisition means having a function for collecting video information and behavioral information.

[0910] (Claim 3)

[0911] The system according to claim 1, further comprising a function to incorporate feedback based on the generated business manual and to continuously update the business manual.

[0912] "Example 1"

[0913] (Claim 1)

[0914] A device for acquiring information related to business operations,

[0915] A device that analyzes business workflows using an artificial intelligence model that analyzes the acquired information,

[0916] A device that automatically generates business procedure manuals based on the analyzed business flow,

[0917] A device for improving the generated work procedure manual using optimization technology based on examples from other companies,

[0918] A device for distributing the generated and improved work procedure manuals,

[0919] A device for updating work procedures based on feedback,

[0920] A system that includes this.

[0921] (Claim 2)

[0922] The system according to claim 1, further comprising the information acquisition device having a function for collecting video and motion information.

[0923] (Claim 3)

[0924] The system according to claim 1, comprising a function to import evaluation information based on the generated work procedure manuals and to continuously revise the said work procedure manuals.

[0925] "Application Example 1"

[0926] (Claim 1)

[0927] Means of acquiring data on business operations,

[0928] A means for analyzing the work procedure using a generative model that analyzes the acquired data,

[0929] A means for automatically generating an operation manual based on the analyzed work procedure,

[0930] A means for improving the automatically generated operation manual using optimization methods based on examples from other companies,

[0931] Means for providing the generated and improved operation manual,

[0932] A means for receiving work result data from the robot as feedback and updating the operation manual,

[0933] A system that includes this.

[0934] (Claim 2)

[0935] The system according to claim 1, further comprising the data acquisition means having a function for collecting video information and motion information.

[0936] (Claim 3)

[0937] The system according to claim 1, further comprising a function to incorporate feedback based on the generated operation manual and to continuously update the operation manual.

[0938] "Example 2 of combining an emotion engine"

[0939] (Claim 1)

[0940] Means of obtaining information related to business activities,

[0941] A means of using a generative model to analyze the work procedure by analyzing the acquired information,

[0942] A means for automatically generating work guidelines based on the analyzed work procedure,

[0943] A means to improve the automatically generated work guidelines using optimization methods based on examples from other companies,

[0944] Means for providing the generated and improved work guidelines,

[0945] A means equipped with an emotional analysis function for analyzing the emotional state of employees,

[0946] A means of adaptively improving the workflow based on the emotional data obtained,

[0947] A system that includes this.

[0948] (Claim 2)

[0949] The system according to claim 1, further comprising the information acquisition means having a function for collecting image information and motion information.

[0950] (Claim 3)

[0951] The system according to claim 1, further comprising a function to incorporate user feedback based on generated work guidelines and to continuously update the said work guidelines.

[0952] "Application example 2 when combining with an emotional engine"

[0953] (Claim 1)

[0954] A device for acquiring information on corporate operations,

[0955] A device that analyzes the business flow using a generation algorithm that analyzes the acquired information,

[0956] A device that automatically generates a work instruction manual based on the analyzed business flow,

[0957] A device for improving the automatically generated work instruction manual using an optimization algorithm based on examples from other organizations,

[0958] A device that collects emotional data and integrates an emotion engine to analyze the emotional state of employees,

[0959] A device including a device that displays employee emotion-based guidance in real time,

[0960] A device for providing the generated and improved work instruction manuals,

[0961] A system that includes this.

[0962] (Claim 2)

[0963] The system according to claim 1, further comprising a device capable of collecting video information and motion information, and further capable of analyzing emotional states.

[0964] (Claim 3)

[0965] The system according to claim 1, further comprising a function to continuously update the work instruction manual by incorporating feedback based on the generated work instruction manual and adding sentiment analysis data. [Explanation of Symbols]

[0966] 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. Means of acquiring data on business operations, A means for analyzing business procedures using a generative model that analyzes the acquired data, A means for automatically generating a business manual based on the analyzed business procedures, A means to improve the automatically generated business manual using optimization methods based on examples from other companies, Means for providing the generated and improved business manuals, A system that includes this.

2. The system according to claim 1, further comprising the data acquisition means having a function for collecting video information and behavioral information.

3. The system according to claim 1, further comprising a function to continuously update the business manual by incorporating feedback based on the generated business manual.

Images