system

Abstract

We provide the system. [Solution] A means of acquiring video and audio data of work in a work environment, A means for preprocessing acquired video and audio data to remove noise, A means for analyzing business operation patterns using pre-processed data and recognizing operation patterns, A means of identifying areas in business processes where efficiency improvements can be made based on recognized behavioral patterns, A means of generating real-time feedback on identified areas where efficiency improvements can be made, and providing workers with information including improvement suggestions, A system that includes means for generating efficiency improvement proposals and visual guide videos, and demonstrating methods for optimizing work processes.

Description

Technical Field

[0004] , , , ,

[0005] , , , , ,

[0003] , ,

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a conventional business environment, it is difficult to accurately grasp waste and inefficiency in business processes, and there is a problem that it is difficult to quickly and effectively implement unified improvement activities. In addition, although a significant reduction in man-hours is required, there is a lack of specific and feasible improvement approaches. Therefore, it is necessary to quickly identify the inefficiency of operations and clearly show improvement measures to improve the efficiency and quality of processes.

Means for Solving the Problems

[0005] This invention provides a system that acquires work video data in a work environment, removes noise by preprocessing the data, and analyzes work patterns using a multimodal AI model. This system performs work pattern analysis by integrating video and audio data and converting it into text data. Based on the analysis results, it identifies areas where work efficiency can be improved and provides this feedback in real time. Furthermore, it generates proposals and videos for the identified areas for improvement, presenting clear improvement measures to the user, thereby achieving process efficiency and reduction of man-hours.

[0006] "Work environment" refers to the physical or digital space within a company or organization where business activities take place.

[0007] "Work video data" refers to visual data recorded of work being performed during work hours.

[0008] "Preprocessing" refers to the process of removing noise and unnecessary information from raw data to prepare it for analysis.

[0009] A "multimodal AI model" refers to an artificial intelligence model that simultaneously analyzes data in different formats, such as video and audio.

[0010] A "work pattern" refers to a series of actions or procedures that are repeatedly observed in work activities.

[0011] "Efficiency improvement" refers to efforts to increase productivity by making business processes faster and using fewer resources.

[0012] "Real-time feedback" refers to improvement suggestions and warnings provided immediately during the process of carrying out a task.

[0013] A "proposal" refers to a document that summarizes improvement measures or efficiency improvements for a specific business process.

[0014] "Video" refers to a medium that provides visual information as moving images. In this case, it refers to a playable video that demonstrates improvements. [Brief explanation of the drawing]

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

[0016] 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.

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

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

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

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

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

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

[0023] [First Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0036] The business efficiency system of the present invention is designed to be implemented in various business environments, such as manufacturing and service industries. The system operates in cooperation with multiple devices via a network. A specific embodiment of the system is described below.

[0037] First, the server acquires video and audio data from network cameras and microphones installed in the work environment. This allows for real-time monitoring of worker movements and ambient sounds. This data is then processed to remove noise and organized.

[0038] Next, the server inputs the pre-processed data into a multimodal AI model to analyze work patterns. This AI model can recognize work procedures from video and instructions and communication content from audio. In this way, it comprehensively analyzes various aspects of the work and learns patterns.

[0039] Based on the analysis results, the AI ​​agent (server) identifies areas in the business process where efficiency improvements are needed. For example, this might include situations where a specific work procedure is unnecessarily redundant, or where the same task is being performed redundantly by multiple workers.

[0040] The server then generates real-time feedback on areas for improvement and notifies the user. This feedback details specific steps to be taken for improvement and, where possible, the possibility of automation. The terminal displays this feedback on its screen, allowing the user to understand the situation immediately.

[0041] Furthermore, based on the identified areas for improvement, the server generates proposals and videos outlining specific ways to streamline the process. These include the resources required for improvement and the expected effects. The proposals and videos are accessible to the user via their terminal, providing a roadmap for initiating improvement activities.

[0042] As a concrete example, suppose a server in a manufacturing line identifies a tendency for a particular worker to frequently make procedural errors at a certain stage of the process. Based on this information, the AI ​​agent (server) recommends adding visual guidance, and the terminal can display this guidance to the user. In this way, the present invention achieves substantial improvements to business processes and increases labor productivity.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The server continuously acquires video and audio data from network cameras and microphones installed in the work environment. This enables real-time monitoring.

[0046] Step 2:

[0047] The server preprocesses the acquired video and audio data by applying a noise reduction algorithm to make the data clearer. This process improves the accuracy of the analysis.

[0048] Step 3:

[0049] The server inputs pre-processed data into a multimodal AI model to analyze work patterns. Specifically, it extracts work procedures from video and recognizes instructions and communication content from audio as text.

[0050] Step 4:

[0051] The AI ​​agent (server) identifies areas in business processes that need improvement based on the analysis results. For example, it detects waiting times between tasks and unnecessary movements, and identifies points that can be improved.

[0052] Step 5:

[0053] The server generates and sends real-time feedback on identified efficiency points to the terminal. This feedback includes specific improvement suggestions and points to note.

[0054] Step 6:

[0055] The device notifies the user of the feedback received from the server and displays it on the screen. The user can then refer to this information and immediately understand the necessary improvements.

[0056] Step 7:

[0057] The server generates a more detailed proposal and video, outlining specific improvement activities the user should undertake. The proposal details the expected effects and necessary tools.

[0058] Step 8:

[0059] Users review proposals and videos through their devices and actively work on improving their business processes. This leads to increased efficiency and improved quality.

[0060] (Example 1)

[0061] 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."

[0062] In order to improve work efficiency in the work environment, it is necessary to appropriately identify inefficient parts of business processes and promptly propose improvements. However, currently, the complexity and diversity of work make it difficult to identify points for efficiency improvement and propose improvement measures. It is necessary to solve this problem and improve work productivity.

[0063] 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.

[0064] In this invention, the server includes means for acquiring data, means for preprocessing the data to remove noise, and means for analyzing business patterns using the preprocessed data and recognizing the patterns. This makes it possible to identify areas in business processes where efficiency improvements can be made and to provide specific improvement suggestions to the user in real time.

[0065] "Means of acquiring data" refer to devices and processes for collecting necessary information in the work environment, which enable an understanding of the actual state of operations.

[0066] "Methods for preprocessing data to remove noise" refer to the process of removing unnecessary noise and inaccurate elements from collected information and organizing it into a format that is easy to analyze.

[0067] "Means for analyzing and recognizing business patterns" refers to a process that analyzes the progress and procedures of business operations based on pre-processed information, and identifies standard patterns and anomalies.

[0068] "Methods for identifying areas where efficiency can be improved" refers to methods for identifying specific locations and procedures from analyzed work patterns that can be improved to enhance work efficiency.

[0069] "Providing improvement suggestions to users in real time" means presenting specific measures for identified problems and areas for improvement in a way that users can immediately see and use, thereby providing information that can be utilized right away.

[0070] The business efficiency system of this invention aims to streamline work processes in the work environment and improve productivity. This system collects data from multiple devices and proposes efficiency improvements based on the analysis results.

[0071] The server acquires data from the work environment through multiple sensor devices. This involves using common hardware such as network cameras and microphones to record the actions and voices of workers. For example, commercially available general-purpose cameras and microphones are used. The acquired data is pre-processed to remove noise.

[0072] The pre-processed data is analyzed using a generative AI model. This AI model is used to analyze work procedures from video data and to identify instructions and communication content from audio data. Common AI models incorporated include open-source tools and commercial AI models.

[0073] After the analysis is complete, the server generates real-time feedback based on the identified areas for improvement and notifies the user. This feedback is presented to the user via the screen of their mobile device or computer terminal, showing them specific steps for improvement.

[0074] Furthermore, the server generates effective improvement proposals and visual guidance videos based on the analysis results. This allows users to understand actionable improvement measures and quickly begin taking action to improve operational efficiency.

[0075] For example, if the server detects a tendency for workers to make procedural errors on a factory production line, it can suggest adding visual guidance. This guidance is then communicated to the user in real time via a terminal. An example of a prompt could be: "Please suggest specific guidance to reduce procedural errors in the manufacturing process."

[0076] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0077] Step 1:

[0078] The server acquires data from sensor devices within the work environment via the network. This data includes video data from network cameras and audio data from microphones. Specifically, the video data records the movements of workers, and the audio data records conversations and ambient sounds. The input data is the raw data transmitted from the cameras and microphones, and the following processing steps are performed based on this data.

[0079] Step 2:

[0080] The server performs preprocessing on the acquired data. Specifically, it performs noise filtering to remove noise from audio data and optimizes the resolution and removes unnecessary frames from video data. The input is the raw data acquired in step 1, and the output is clean audio and video data. This preprocessed data enables more accurate analysis.

[0081] Step 3:

[0082] The server inputs pre-processed data into a generating AI model to analyze work patterns. Specifically, the AI ​​model extracts work procedures and actions from video and analyzes instructions and communication content from audio data. Pre-processed data is used as input, and the output is the analysis results of work patterns. Based on these analysis results, it is possible to recognize standard work patterns and points of anomaly.

[0083] Step 4:

[0084] The AI ​​agent (server) identifies areas within the business process where efficiency improvements can be made, based on the analysis results. Specifically, this includes detecting redundancy and duplication in the procedures identified by the AI ​​model. The input is the analysis results from step 3, and the output is a list of points where efficiency improvements are possible.

[0085] Step 5:

[0086] The server generates and sends feedback based on the identified efficiency points to the terminal. Specifically, this includes visual guides and detailed improvement steps as improvement suggestions. The input is the efficiency improvement points from step 4, and the output generates improvement feedback to be presented to the user.

[0087] Step 6:

[0088] The user reviews feedback sent from the server via their device. Specifically, they are required to understand and implement the improvement steps displayed on the device's screen. In this step, the user gains immediately applicable improvement solutions. The input is the feedback information from the server, and the output is the user's action.

[0089] (Application Example 1)

[0090] 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."

[0091] In modern industrial processes, automation technologies are advancing to improve work efficiency, but many workplaces still have inefficient work procedures, which can lead to decreased productivity. This invention aims to solve the problem of improving the efficiency of work processes by monitoring work conditions in real time, identifying unnecessary actions and time lags, and proposing improvements.

[0092] 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.

[0093] In this invention, the server includes means for acquiring work video data and audio data in the work environment; means for preprocessing the acquired video data and audio data to remove noise; means for analyzing work operation patterns using the preprocessed data and recognizing operation patterns; means for identifying areas where the efficiency of the work process can be improved based on the recognized operation patterns; means for generating real-time feedback for the identified areas where efficiency can be improved and providing information including improvement suggestions to the worker; and means for generating efficiency improvement proposals and visual guide videos and demonstrating methods for optimizing the work process. This makes it possible to improve work efficiency and optimize productivity in a factory.

[0094] "Work environment" refers to the physical and technical location and conditions for performing work, such as a manufacturing site or office, where the actual work takes place.

[0095] "Work video data" refers to visual information that records the flow and actions of work in a work environment, and is mainly data acquired using cameras.

[0096] "Audio data" refers to auditory information recorded using a microphone, specifically the voices of workers and ambient sounds in the work environment.

[0097] "Preprocessing" refers to the initial data processing performed to prepare acquired raw data for analysis, and includes processes such as noise reduction and format standardization.

[0098] "Noise removal techniques" refer to technologies and methods for reducing unnecessary information contained in data and extracting only the useful data necessary for analysis.

[0099] A "work pattern" refers to a series of repetitive actions or procedures performed by a worker in a work environment, and represents standard behavior for a particular task or process.

[0100] "Means of analysis" refers to techniques for analyzing data using specific methods and tools in order to process the data and extract meaningful information.

[0101] "Means of recognizing behavioral patterns" refers to technologies and algorithms for identifying specific actions or procedures from collected data, and for classifying and understanding them.

[0102] "Areas where efficiency can be improved" refers to parts of a business where work time can be reduced or resources can be saved, and these are segments that have been identified as having room for improvement.

[0103] "Means of generating feedback" refers to the technologies and processes used to create useful information and improvement suggestions for users based on analysis results.

[0104] "Information including improvement suggestions" refers to information that describes specific improvement measures and procedures proposed to workers based on identified opportunities for efficiency improvements.

[0105] A "visual guide video" refers to video materials designed to clearly communicate streamlined procedures and improvements to workers, and is visual content created for users to learn from or refer to.

[0106] To implement this invention, close cooperation between the server, terminal, and user is necessary. The server acquires video and audio data of the work using network cameras and microphones placed in the work environment. Once this data is collected, noise is removed as a preprocessing step to prepare the data for improved analysis quality.

[0107] Next, the server uses pre-processed data to recognize work action patterns using a multimodal AI model. By using AI frameworks such as TENSORFLOW®, it analyzes work actions from video and instructions from audio to grasp complex work action patterns.

[0108] Once the operating patterns are identified, the server reveals areas within the business process where efficiency improvements can be made. This identification process utilizes data streaming technologies such as Apache® Kafka to identify inefficient parts in real time and point out areas that need improvement.

[0109] Based on these analysis results, the server generates feedback and displays it to the user via the terminal. The terminal's display provides the user with identified areas for improvement as a visual guide video, clearly explaining how to make improvements. For example, if an worker is repeating unnecessary movements in the same process, a guide video is generated showing specific steps to reduce those movements.

[0110] By viewing proposals and videos, users can begin reviewing workflows and optimizing operations based on the suggested improvements. This entire process can significantly improve productivity and efficiency at the work site.

[0111] Examples of prompts for the generated AI model include specific instructions such as, "Analyze the video footage of the factory robot's movements and generate suggestions for improvements to increase efficiency. Focus especially on areas with many unnecessary movements." This allows the server to provide the user with optimized movement patterns.

[0112] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0113] Step 1:

[0114] The server collects video and audio data in real time from network cameras and microphones. This data includes resource usage in the work environment and worker movements. Raw video and audio frames are provided as input. The output is stored as raw data that can be pre-processed for noise reduction.

[0115] Step 2:

[0116] The server removes noise from the collected raw data. This step uses a filtering algorithm to reduce audio and video noise that is unnecessary for business analysis. The input is the video and audio data acquired in step 1, and the output is the clear, pre-processed data.

[0117] Step 3:

[0118] The server uses pre-processed data to input into a multimodal AI model and analyzes behavioral patterns. This process uses machine learning libraries such as TensorFlow to analyze the relationships between multiple data modals. The input is pre-processed visual and audio data, and the output is a list of recognized behavioral patterns.

[0119] Step 4:

[0120] The server identifies areas where efficiency can be improved based on the recognized operating patterns. By reviewing the output of Step 3 and investigating redundant operations and time lags, points that can be improved are identified. The input is the recognition result from Step 3, and the output is a list of candidate points where efficiency can be improved.

[0121] Step 5:

[0122] The server generates real-time feedback based on identified efficiency points. This feedback includes improvement suggestions that the worker should follow. The input is a list of candidate efficiency points, and the output is the specific improvement suggestions presented to the user.

[0123] Step 6:

[0124] The device visually presents the generated feedback to the user. This presentation takes place on the display and supports real-time work improvement. The feedback output in step 5 is the input, and the output is the visual information received by the user.

[0125] Step 7:

[0126] The server generates efficiency improvement proposals and guide videos and provides them to the user via the terminal. In this step, a presentation tool is used to visualize the improvement steps in detail. The inputs are the identified points from step 4, and the output is the improvement guide document and video that the user can view.

[0127] 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.

[0128] This invention is a system aimed at improving work processes in the work environment. It identifies points for improving work efficiency by comprehensively analyzing video and audio data. Furthermore, by combining it with an emotion engine that evaluates the user's emotional state, it improves the accuracy and effectiveness of feedback. This system mainly consists of multiple devices and a server communicating via the internet.

[0129] The server collects video footage from network cameras and audio data from microphones at the work site. This data is temporarily stored in storage and undergoes pre-processing such as noise reduction. After pre-processing, the data is analyzed by an AI model to identify specific patterns in the work process.

[0130] Subsequently, the server identifies areas requiring optimization based on the analyzed business patterns. Simultaneously, the emotion engine (server) analyzes the user's facial expressions and tone of voice to recognize their emotional state. This allows the feedback to be adapted to the user's emotions.

[0131] The server generates appropriate and effective feedback in real time based on identified efficiency points and recognized emotional states. The terminal notifies the user of this feedback, displaying specific suggestions for improvement and points to note. This allows the user to quickly take action based on the information.

[0132] The server also generates a video containing efficiency improvement proposals and operation guides. These proposals detail the benefits of the improvements and the resources required for implementation, and users can view them through their terminals.

[0133] As a concrete example, in customer service operations, the server analyzes the audio and video of the operator's interactions to identify processes that can be made more efficient in customer interactions. At the same time, an emotion engine detects the operator's stress level, and the feedback includes simple techniques and suggestions for improvement to reduce stress. In this way, the system provides a solution that considers both operational improvements and employee well-being.

[0134] The following describes the processing flow.

[0135] Step 1:

[0136] The server acquires real-time video and audio data from network cameras and microphones installed at the work site. This data is used to accurately capture the work environment and conditions.

[0137] Step 2:

[0138] The server performs preprocessing to prepare the acquired video and audio data for analysis. Specifically, it performs noise reduction and data cleaning, and uses signal processing techniques to improve quality.

[0139] Step 3:

[0140] The server inputs pre-processed video and audio into a multimodal AI model to analyze work patterns. This analysis makes it possible to recognize and record work content, procedures, and communication flows.

[0141] Step 4:

[0142] The AI ​​agent (server) uses the analysis results to identify inefficiencies in business processes. This step prioritizes detecting redundant procedures and activities that take too much time.

[0143] Step 5:

[0144] The emotion engine (server) performs facial expression and voice analysis on the user to recognize their emotional state. This information is used to understand the user's psychological state while they are performing their work.

[0145] Step 6:

[0146] The server generates customized real-time feedback based on identified inefficiencies and the user's emotional state. This process creates appropriate advice and improvement suggestions that take emotions into account.

[0147] Step 7:

[0148] The terminal notifies the user of feedback generated by the server and displays it on the screen. The user can receive this feedback immediately and use it to improve their work.

[0149] Step 8:

[0150] The server prepares efficiency improvement proposals and related videos, detailing the proposed improvements. The proposals describe specific methods and expected effects, and users can access them through their devices.

[0151] Step 9:

[0152] Users can review proposals and videos on their devices and implement recommended improvements. Only after this step can the streamlining of business processes be achieved.

[0153] (Example 2)

[0154] 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 will be referred to as the "terminal."

[0155] In today's work environment, while efficiency is demanded, there is a lack of mechanisms to appropriately evaluate work processes and the emotional state of users, and to provide timely feedback. This can lead to decreased work efficiency and increased user stress. To address these challenges, it is necessary to comprehensively analyze diverse data and immediately propose efficiency improvements.

[0156] 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.

[0157] In this invention, the server includes sensing means for acquiring work data in the work environment, data filtering means for preprocessing the acquired data to remove noise, and AI analysis means for analyzing work procedures using the preprocessed data and learning specific patterns. This makes it possible to accurately identify points for improving work efficiency and generate feedback and suggestions adapted to the user's emotional state in real time.

[0158] "Sensing means" refers to devices or methods for acquiring work data in a work environment.

[0159] A "data filtering means" refers to a processing device or method for removing noise from acquired data and preparing it for analysis.

[0160] "AI analysis means" refers to devices or methods that use artificial intelligence technology to analyze business procedures using pre-processed data and learn specific patterns.

[0161] "Analysis tools" are devices or methods for identifying areas for improving the efficiency of work procedures based on learned patterns.

[0162] "Generation means" refers to devices or methods for generating real-time feedback based on efficiency improvement points.

[0163] "Notification means" refers to devices or methods for displaying generated feedback to the user.

[0164] "Content generation means" refers to devices and methods for creating efficiency improvements and educational materials.

[0165] "Emotional analysis means" refers to devices or methods for recognizing a user's emotional state by comprehensively analyzing video and audio data.

[0166] A "user interface" is a device or method for users to display and view generated proposals and educational materials.

[0167] This invention is a system that improves efficiency by collecting and analyzing work data in real time within the work environment. Specifically, a server acquires video and audio data using sensing devices such as network cameras and microphones. This data is preprocessed and noise is removed by a data filtering means on the server. The preprocessed data is then analyzed by an AI analysis means to learn specific patterns in the work procedures.

[0168] Based on the analysis results, the server uses analytical tools to identify areas for improving work efficiency. It also uses emotion analysis tools to recognize the user's emotional state from their voice and facial expressions. This allows a generation tool to generate feedback in real time that is tailored to the efficiency improvements and the emotional state. The generated feedback is then notified to the user via their terminal.

[0169] As a concrete example, in customer service operations, the server analyzes the operator's video and audio during their work. This identifies processes that can be made more efficient in customer interactions. The AI ​​model also performs emotion analysis, and if the operator is experiencing stress, it provides feedback that includes specific advice on stress reduction. An example of a prompt might be, "Please suggest relaxation techniques that the operator can use if they are experiencing stress while interacting with a customer."

[0170] Furthermore, the server generates efficiency suggestions and educational materials using content generation mechanisms. These materials are viewable on terminals through a user interface, allowing users to learn specific methods for improving efficiency. This enables both improved work efficiency and user emotional well-being to be achieved simultaneously.

[0171] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0172] Step 1:

[0173] The server uses network cameras and microphones to acquire video and audio data from the work site in real time. At this stage, the input is raw data from multiple cameras and microphones, and the output is unprocessed video and audio data. Specifically, the server records the acquired data along with a timestamp to storage.

[0174] Step 2:

[0175] The server performs preprocessing on the acquired video and audio data, such as noise reduction and format conversion. At this stage, the raw data from step 1 is provided as input, and the output is data with noise removed and ready for analysis. Specifically, background noise is filtered from the audio data, and unnecessary frames are removed from the video data.

[0176] Step 3:

[0177] The server uses AI analysis tools to extract and learn patterns of business procedures from pre-processed data. The input for this step is pre-processed video and audio data, and the output is a basic pattern of the business process. Specifically, the AI ​​model applies machine learning algorithms to identify specific work procedures and abnormal behaviors.

[0178] Step 4:

[0179] The server uses the analysis results to identify areas for business efficiency improvement. At this stage, the input is the business pattern obtained in step 3, and the output shows specific business procedures that require optimization. The specific actions include comparing the current data with similar historical data and listing areas where efficiency improvements are expected.

[0180] Step 5:

[0181] The server analyzes the user's emotional state from their facial expressions and voice tone using emotion analysis tools. The input at this stage is the pre-processed data from step 2, and the output is the user's emotion evaluation result. Specifically, the AI ​​model uses facial recognition technology and voice emotion analysis technology to identify what emotional state the user is in.

[0182] Step 6:

[0183] The server uses a generation mechanism to generate feedback based on efficiency points and emotional states. The feedback output generated based on the input from steps 4 and 5 is the improvement suggestions and points of caution provided to the user. Specific actions include the generation AI model utilizing prompts to construct a feedback message appropriate for the user.

[0184] Step 7:

[0185] The terminal notifies the user of feedback sent from the server. The input is the feedback generated in step 6, and the output is a notification or display to the user. Specifically, the notification appears as a pop-up on the screen, and voice confirmation is also possible.

[0186] Step 8:

[0187] The server uses content generation tools to create efficiency proposals and educational videos, making them viewable by users through their terminals. The input for this stage is the information from steps 4 and 6, and the output provides users with specific improvement measures. Specifically, a generation AI model automatically assembles the proposal content and provides it as a visualized resource.

[0188] (Application Example 2)

[0189] 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".

[0190] In today's work environment, achieving efficient and effective work is a crucial challenge for many organizations. However, improving work efficiency requires not only optimizing work processes but also considering the emotional state of employees. Traditional systems, while focusing on work efficiency, have been limited in their ability to generate feedback that takes employees' emotional states into account. Therefore, there is a need for a system that can improve work efficiency while also providing flexible responses that are in line with the emotions of users.

[0191] 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.

[0192] In this invention, the server includes means for acquiring activity video information in the work environment, means for preprocessing the acquired video information to remove noise, means for analyzing work patterns using the preprocessed information and recognizing the patterns, means for identifying areas where the efficiency of the work process can be improved based on the recognized patterns, means for analyzing the emotional state of the user, means for adapting the content of the feedback based on the analyzed emotional state, and means for displaying the generated feedback on a video display device. This makes it possible to improve work efficiency while providing feedback that is tailored to the user's emotions, thereby simultaneously improving the work environment and increasing employee satisfaction.

[0193] The term "work environment" refers to the place where various tasks and activities are carried out within a company or organization, and includes the physical and virtual environments that support those tasks.

[0194] "Activity video information" refers to video data capturing the work and activities performed in the work environment, and is used for analyzing work processes.

[0195] "Noise reduction" is a preprocessing technique that removes unwanted interference information from acquired video and audio data to improve the accuracy of the necessary data.

[0196] "Work patterns" refer to certain regularities or tendencies that are obtained as a result of analyzing combinations of procedures and actions in specific tasks or activities performed in a work environment.

[0197] "Streamlining business processes" refers to improving or redesigning processes to maximize results while reducing the time and resources required for those processes.

[0198] "User emotional state" refers to information indicating the emotional state of employees or operators performing tasks, such as stress levels, satisfaction levels, and concentration levels. This information is analyzed to serve as a reference for improving work processes.

[0199] "Feedback" is information generated based on analyzed work patterns and the emotional state of users, and is provided to users as a means of improving work efficiency and providing solutions for improvement.

[0200] A "video display device" is a device used to visually present acquired feedback information to the user and assist in improving business operations.

[0201] The system for carrying out this invention is configured to integrally process video and audio information of activities in a work environment. The server acquires video and audio information in real time through cameras and microphones within the work environment. The raw data collected from these devices is temporarily stored in storage installed within the server.

[0202] Subsequently, the server preprocesses the video and audio information using a noise reduction algorithm. This process, for example, uses the OpenCV library to clear redundant parts from the video data and reduce unwanted background noise from the audio data.

[0203] The pre-processed information is analyzed by a dedicated AI model. This AI model identifies business patterns based on the initial training data and performs pattern recognition. Based on the recognized business patterns, the server identifies which parts of the business process can be made more efficient.

[0204] Furthermore, the server incorporates an emotion engine that evaluates the user's emotional state by analyzing their facial expressions and tone of voice. Based on this analysis, the feedback is tailored to the user's emotions. The feedback is displayed on a video display device, such as smart glasses worn by the user, and suggestions for efficiency improvements and other areas for improvement are presented in real time.

[0205] For example, when an employee assisting a customer uses this system, they can detect signs of customer dissatisfaction and immediately receive appropriate solutions on the display of their glasses. This can improve customer satisfaction.

[0206] An example of a prompt for a generative AI model is, "Generate feedback suggesting solutions for when a customer expresses dissatisfaction." This prompt allows the AI ​​model to generate appropriate solution-oriented feedback.

[0207] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0208] Step 1:

[0209] The server uses cameras and microphones within the work environment to acquire video and audio information about the activities. The input is raw data from the cameras and microphones, and the output is raw video and audio data stored in storage. In this step, initial processing is performed to properly capture data from the devices and to fully record the activities during work.

[0210] Step 2:

[0211] The server performs noise reduction on the acquired raw data. The input is the raw data saved in step 1, and the output is pre-processed data with reduced noise. In this step, data processing is performed to improve the accuracy of the analysis by clearing the video data and removing unnecessary background noise using libraries such as OpenCV.

[0212] Step 3:

[0213] The server analyzes pre-processed data using an AI model to recognize business patterns. The input is denoised video and audio data, and the output is the recognized business patterns. In this step, data calculations are performed so that the AI ​​model can analyze the data and learn specific behavioral rules and patterns that should be made more efficient.

[0214] Step 4:

[0215] The server identifies areas where efficiency improvements are possible based on recognized business patterns. The input is the pattern recognized in step 3, and the output is information about the business processes that need to be streamlined. In this step, the identified areas are investigated in detail, and preparations are made to propose specific measures for process improvement.

[0216] Step 5:

[0217] The server analyzes the user's emotional state using an emotion engine. The input is the pre-processed video and audio from step 2, and the output is the analyzed emotional state information. In this step, emotions are recognized from the user's facial expressions and voice, and data transformation is performed to reflect these in the feedback.

[0218] Step 6:

[0219] The server generates appropriate feedback based on areas that need improvement and the user's emotional state. The input is the location information from step 4 and the emotional state information from step 5, and the output is the feedback displayed to the user. In this step, a generative AI model is used to generate prompt sentences that create feedback that takes the user's emotions into consideration.

[0220] Step 7:

[0221] The terminal displays the generated feedback on the smart glasses' display. The input is the feedback generated in step 6, and the output is the information presented on the user's visual interface. In this step, the feedback is displayed in real time so that the user can immediately see and implement improvements while working.

[0222] 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.

[0223] 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.

[0224] 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.

[0225] [Second Embodiment]

[0226] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0227] 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.

[0228] 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).

[0229] 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.

[0230] 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.

[0231] 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).

[0232] 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.

[0233] 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.

[0234] 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.

[0235] 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.

[0236] 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.

[0237] 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".

[0238] The business efficiency system of the present invention is designed to be implemented in various business environments, such as manufacturing and service industries. The system operates in cooperation with multiple devices via a network. A specific embodiment of the system is described below.

[0239] First, the server acquires video and audio data from network cameras and microphones installed in the work environment. This allows for real-time monitoring of worker movements and ambient sounds. This data is then processed to remove noise and organized.

[0240] Next, the server inputs the pre-processed data into a multimodal AI model to analyze work patterns. This AI model can recognize work procedures from video and instructions and communication content from audio. In this way, it comprehensively analyzes various aspects of the work and learns patterns.

[0241] Based on the analysis results, the AI ​​agent (server) identifies areas in the business process where efficiency improvements are needed. For example, this might include situations where a specific work procedure is unnecessarily redundant, or where the same task is being performed redundantly by multiple workers.

[0242] The server then generates real-time feedback on areas for improvement and notifies the user. This feedback details specific steps to be taken for improvement and, where possible, the possibility of automation. The terminal displays this feedback on its screen, allowing the user to understand the situation immediately.

[0243] Furthermore, based on the identified areas for improvement, the server generates proposals and videos outlining specific ways to streamline the process. These include the resources required for improvement and the expected effects. The proposals and videos are accessible to the user via their terminal, providing a roadmap for initiating improvement activities.

[0244] As a concrete example, suppose a server in a manufacturing line identifies a tendency for a particular worker to frequently make procedural errors at a certain stage of the process. Based on this information, the AI ​​agent (server) recommends adding visual guidance, and the terminal can display this guidance to the user. In this way, the present invention achieves substantial improvements to business processes and increases labor productivity.

[0245] The following describes the processing flow.

[0246] Step 1:

[0247] The server continuously acquires video and audio data from network cameras and microphones installed in the work environment. This enables real-time monitoring.

[0248] Step 2:

[0249] The server preprocesses the acquired video and audio data by applying a noise reduction algorithm to make the data clearer. This process improves the accuracy of the analysis.

[0250] Step 3:

[0251] The server inputs pre-processed data into a multimodal AI model to analyze work patterns. Specifically, it extracts work procedures from video and recognizes instructions and communication content from audio as text.

[0252] Step 4:

[0253] The AI ​​agent (server) identifies areas in business processes that need improvement based on the analysis results. For example, it detects waiting times between tasks and unnecessary movements, and identifies points that can be improved.

[0254] Step 5:

[0255] The server generates and sends real-time feedback on identified efficiency points to the terminal. This feedback includes specific improvement suggestions and points to note.

[0256] Step 6:

[0257] The device notifies the user of the feedback received from the server and displays it on the screen. The user can then refer to this information and immediately understand the necessary improvements.

[0258] Step 7:

[0259] The server generates a more detailed proposal and video, outlining specific improvement activities the user should undertake. The proposal details the expected effects and necessary tools.

[0260] Step 8:

[0261] Users review proposals and videos through their devices and actively work on improving their business processes. This leads to increased efficiency and improved quality.

[0262] (Example 1)

[0263] 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".

[0264] In order to improve work efficiency in the work environment, it is necessary to appropriately identify inefficient parts of business processes and promptly propose improvements. However, currently, the complexity and diversity of work make it difficult to identify points for efficiency improvement and propose improvement measures. It is necessary to solve this problem and improve work productivity.

[0265] 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.

[0266] In this invention, the server includes means for acquiring data, means for preprocessing the data to remove noise, and means for analyzing business patterns using the preprocessed data and recognizing the patterns. This makes it possible to identify areas in business processes where efficiency improvements can be made and to provide specific improvement suggestions to the user in real time.

[0267] "Means of acquiring data" refer to devices and processes for collecting necessary information in the work environment, which enable an understanding of the actual state of operations.

[0268] "Methods for preprocessing data to remove noise" refer to the process of removing unnecessary noise and inaccurate elements from collected information and organizing it into a format that is easy to analyze.

[0269] "Means for analyzing and recognizing business patterns" refers to a process that analyzes the progress and procedures of business operations based on pre-processed information, and identifies standard patterns and anomalies.

[0270] "Methods for identifying areas where efficiency can be improved" refers to methods for identifying specific locations and procedures from analyzed work patterns that can be improved to enhance work efficiency.

[0271] "Providing improvement suggestions to users in real time" means presenting specific measures for identified problems and areas for improvement in a way that users can immediately see and use, thereby providing information that can be utilized right away.

[0272] The business efficiency system of this invention aims to streamline work processes in the work environment and improve productivity. This system collects data from multiple devices and proposes efficiency improvements based on the analysis results.

[0273] The server acquires data from the work environment through multiple sensor devices. This involves using common hardware such as network cameras and microphones to record the actions and voices of workers. For example, commercially available general-purpose cameras and microphones are used. The acquired data is pre-processed to remove noise.

[0274] The pre-processed data is analyzed using a generative AI model. This AI model is used to analyze work procedures from video data and to identify instructions and communication content from audio data. Common AI models incorporated include open-source tools and commercial AI models.

[0275] After the analysis is complete, the server generates real-time feedback based on the identified areas for improvement and notifies the user. This feedback is presented to the user via the screen of their mobile device or computer terminal, showing them specific steps for improvement.

[0276] Furthermore, the server generates effective improvement proposals and visual guidance videos based on the analysis results. This allows users to understand actionable improvement measures and quickly begin taking action to improve operational efficiency.

[0277] For example, if the server detects a tendency for workers to make procedural errors on a factory production line, it can suggest adding visual guidance. This guidance is then communicated to the user in real time via a terminal. An example of a prompt could be: "Please suggest specific guidance to reduce procedural errors in the manufacturing process."

[0278] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0279] Step 1:

[0280] The server acquires data from sensor devices within the work environment via the network. This data includes video data from network cameras and audio data from microphones. Specifically, the video data records the movements of workers, and the audio data records conversations and ambient sounds. The input data is the raw data transmitted from the cameras and microphones, and the following processing steps are performed based on this data.

[0281] Step 2:

[0282] The server performs preprocessing on the acquired data. Specifically, it performs noise filtering to remove noise from the audio data, and optimizes the resolution and deletes unnecessary frames for the video data. The input is the raw data acquired in Step 1, and as output, clean audio and video data can be obtained. This preprocessed data enables more accurate analysis.

[0283] Step 3:

[0284] The server inputs the preprocessed data into the generative AI model to analyze the business pattern. Specifically, the AI model extracts work procedures and actions from the video, and analyzes the instructions and communication content from the audio data. The preprocessed data is used as the input, and the analysis result of the business pattern is obtained as the output. Based on this analysis result, the standard pattern and abnormal points of the work can be recognized.

[0285] Step 4:

[0286] The AI agent (server) identifies areas within the business process where efficiency can be improved based on the analysis result. Specific actions include detecting redundancy and duplication in the procedures identified by the AI model. The input is the analysis result of Step 3, and as output, a list of points where efficiency can be improved is generated.

[0287] Step 5:

[0288] The server generates feedback based on the identified efficiency improvement points and sends it to the terminal. Specifically, it includes visual guides and details of improvement procedures as improvement proposals. The input is the efficiency improvement points of Step 4, and as output, improvement feedback for presentation to the user is generated.

[0289] Step 6:

[0290] The user reviews feedback sent from the server via their device. Specifically, they are required to understand and implement the improvement steps displayed on the device's screen. In this step, the user gains immediately applicable improvement solutions. The input is the feedback information from the server, and the output is the user's action.

[0291] (Application Example 1)

[0292] 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."

[0293] In modern industrial processes, automation technologies are advancing to improve work efficiency, but many workplaces still have inefficient work procedures, which can lead to decreased productivity. This invention aims to solve the problem of improving the efficiency of work processes by monitoring work conditions in real time, identifying unnecessary actions and time lags, and proposing improvements.

[0294] 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.

[0295] In this invention, the server includes means for acquiring work video data and audio data in the work environment; means for preprocessing the acquired video data and audio data to remove noise; means for analyzing work operation patterns using the preprocessed data and recognizing operation patterns; means for identifying areas where the efficiency of the work process can be improved based on the recognized operation patterns; means for generating real-time feedback for the identified areas where efficiency can be improved and providing information including improvement suggestions to the worker; and means for generating efficiency improvement proposals and visual guide videos and demonstrating methods for optimizing the work process. This makes it possible to improve work efficiency and optimize productivity in a factory.

[0296] "Work environment" refers to the physical and technical location and conditions for performing work, such as a manufacturing site or office, where the actual work takes place.

[0297] "Work video data" refers to visual information that records the flow and actions of work in a work environment, and is mainly data acquired using cameras.

[0298] "Audio data" refers to auditory information recorded using a microphone, specifically the voices of workers and ambient sounds in the work environment.

[0299] "Preprocessing" refers to the initial data processing performed to prepare acquired raw data for analysis, and includes processes such as noise reduction and format standardization.

[0300] "Noise removal techniques" refer to technologies and methods for reducing unnecessary information contained in data and extracting only the useful data necessary for analysis.

[0301] A "work pattern" refers to a series of repetitive actions or procedures performed by a worker in a work environment, and represents standard behavior for a particular task or process.

[0302] "Means of analysis" refers to techniques for analyzing data using specific methods and tools in order to process the data and extract meaningful information.

[0303] "Means of recognizing behavioral patterns" refers to technologies and algorithms for identifying specific actions or procedures from collected data, and for classifying and understanding them.

[0304] "Areas where efficiency can be improved" refers to parts of a business where work time can be reduced or resources can be saved, and these are segments that have been identified as having room for improvement.

[0305] "Means of generating feedback" refers to the technologies and processes used to create useful information and improvement suggestions for users based on analysis results.

[0306] "Information including improvement proposals" refers to information that describes specific improvement measures and procedures proposed to workers based on recognized opportunities for efficiency improvement.

[0307] "Visual guide video" refers to video materials for clearly conveying efficient procedures and improvement measures to workers, which are visual contents created for users to learn or refer to.

[0308] To implement this invention, close cooperation among the server, terminal, and user is required. The server uses network cameras and microphones placed in the business environment to acquire video data and audio data of the work. Once this data is collected, noise is removed as preprocessing to prepare a basis for improving the quality of analysis.

[0309] Subsequently, the server uses the preprocessed data to recognize the operation patterns of the work by leveraging a multimodal AI model. By using an AI framework such as TensorFlow to analyze work actions from video and instruction contents from audio, a complex business operation pattern is grasped.

[0310] Once the operation pattern is identified, the server reveals the parts where efficiency improvement can be expected within the business process. In this specific process, data streaming technologies such as Apache Kafka are utilized to identify inefficient parts in real time and point out areas for improvement.

[0311] Based on these analysis results, the server generates feedback and shows it to the user through the terminal. On the display part of the terminal, the identified improvement points are provided to the user as a visual guide video to specifically convey the improvement method. For example, when a worker repeats wasteful movements in the same process, a guide video showing specific procedures for reducing that part is generated.

[0312] By viewing proposals and videos, users can begin reviewing workflows and optimizing operations based on the suggested improvements. This entire process can significantly improve productivity and efficiency at the work site.

[0313] Examples of prompts for the generated AI model include specific instructions such as, "Analyze the video footage of the factory robot's movements and generate suggestions for improvements to increase efficiency. Focus especially on areas with many unnecessary movements." This allows the server to provide the user with optimized movement patterns.

[0314] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0315] Step 1:

[0316] The server collects video and audio data in real time from network cameras and microphones. This data includes resource usage in the work environment and worker movements. Raw video and audio frames are provided as input. The output is stored as raw data that can be pre-processed for noise reduction.

[0317] Step 2:

[0318] The server removes noise from the collected raw data. This step uses a filtering algorithm to reduce audio and video noise that is unnecessary for business analysis. The input is the video and audio data acquired in step 1, and the output is the clear, pre-processed data.

[0319] Step 3:

[0320] The server uses pre-processed data to input into a multimodal AI model and analyzes behavioral patterns. This process uses machine learning libraries such as TensorFlow to analyze the relationships between multiple data modals. The input is pre-processed visual and audio data, and the output is a list of recognized behavioral patterns.

[0321] Step 4:

[0322] The server identifies areas where efficiency can be improved based on the recognized operating patterns. By reviewing the output of Step 3 and investigating redundant operations and time lags, points that can be improved are identified. The input is the recognition result from Step 3, and the output is a list of candidate points where efficiency can be improved.

[0323] Step 5:

[0324] The server generates real-time feedback based on identified efficiency points. This feedback includes improvement suggestions that the worker should follow. The input is a list of candidate efficiency points, and the output is the specific improvement suggestions presented to the user.

[0325] Step 6:

[0326] The device visually presents the generated feedback to the user. This presentation takes place on the display and supports real-time work improvement. The feedback output in step 5 is the input, and the output is the visual information received by the user.

[0327] Step 7:

[0328] The server generates efficiency improvement proposals and guide videos and provides them to the user via the terminal. In this step, a presentation tool is used to visualize the improvement steps in detail. The inputs are the identified points from step 4, and the output is the improvement guide document and video that the user can view.

[0329] 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.

[0330] This invention is a system aimed at improving work processes in the work environment. It identifies points for improving work efficiency by comprehensively analyzing video and audio data. Furthermore, by combining it with an emotion engine that evaluates the user's emotional state, it improves the accuracy and effectiveness of feedback. This system mainly consists of multiple devices and a server communicating via the internet.

[0331] The server collects video footage from network cameras and audio data from microphones at the work site. This data is temporarily stored in storage and undergoes pre-processing such as noise reduction. After pre-processing, the data is analyzed by an AI model to identify specific patterns in the work process.

[0332] Subsequently, the server identifies areas requiring optimization based on the analyzed business patterns. Simultaneously, the emotion engine (server) analyzes the user's facial expressions and tone of voice to recognize their emotional state. This allows the feedback to be adapted to the user's emotions.

[0333] The server generates appropriate and effective feedback in real time based on identified efficiency points and recognized emotional states. The terminal notifies the user of this feedback, displaying specific suggestions for improvement and points to note. This allows the user to quickly take action based on the information.

[0334] The server also generates a video containing efficiency improvement proposals and operation guides. These proposals detail the benefits of the improvements and the resources required for implementation, and users can view them through their terminals.

[0335] As a concrete example, in customer service operations, the server analyzes the audio and video of the operator's interactions to identify processes that can be made more efficient in customer interactions. At the same time, an emotion engine detects the operator's stress level, and the feedback includes simple techniques and suggestions for improvement to reduce stress. In this way, the system provides a solution that considers both operational improvements and employee well-being.

[0336] The following describes the processing flow.

[0337] Step 1:

[0338] The server acquires real-time video and audio data from network cameras and microphones installed at the work site. This data is used to accurately capture the work environment and conditions.

[0339] Step 2:

[0340] The server performs preprocessing to prepare the acquired video and audio data for analysis. Specifically, it performs noise reduction and data cleaning, and uses signal processing techniques to improve quality.

[0341] Step 3:

[0342] The server inputs pre-processed video and audio into a multimodal AI model to analyze work patterns. This analysis makes it possible to recognize and record work content, procedures, and communication flows.

[0343] Step 4:

[0344] The AI ​​agent (server) uses the analysis results to identify inefficiencies in business processes. This step prioritizes detecting redundant procedures and activities that take too much time.

[0345] Step 5:

[0346] The emotion engine (server) performs facial expression and voice analysis on the user to recognize their emotional state. This information is used to understand the user's psychological state while they are performing their work.

[0347] Step 6:

[0348] The server generates customized real-time feedback based on identified inefficiencies and the user's emotional state. This process creates appropriate advice and improvement suggestions that take emotions into account.

[0349] Step 7:

[0350] The terminal notifies the user of feedback generated by the server and displays it on the screen. The user can receive this feedback immediately and use it to improve their work.

[0351] Step 8:

[0352] The server prepares efficiency improvement proposals and related videos, detailing the proposed improvements. The proposals describe specific methods and expected effects, and users can access them through their devices.

[0353] Step 9:

[0354] Users can review proposals and videos on their devices and implement recommended improvements. Only after this step can the streamlining of business processes be achieved.

[0355] (Example 2)

[0356] 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".

[0357] In today's work environment, while efficiency is demanded, there is a lack of mechanisms to appropriately evaluate work processes and the emotional state of users, and to provide timely feedback. This can lead to decreased work efficiency and increased user stress. To address these challenges, it is necessary to comprehensively analyze diverse data and immediately propose efficiency improvements.

[0358] 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.

[0359] In this invention, the server includes sensing means for acquiring work data in the work environment, data filtering means for preprocessing the acquired data to remove noise, and AI analysis means for analyzing work procedures using the preprocessed data and learning specific patterns. This makes it possible to accurately identify points for improving work efficiency and generate feedback and suggestions adapted to the user's emotional state in real time.

[0360] "Sensing means" refers to devices or methods for acquiring work data in a work environment.

[0361] A "data filtering means" refers to a processing device or method for removing noise from acquired data and preparing it for analysis.

[0362] "AI analysis means" refers to devices or methods that use artificial intelligence technology to analyze business procedures using pre-processed data and learn specific patterns.

[0363] "Analysis tools" are devices or methods for identifying areas for improving the efficiency of work procedures based on learned patterns.

[0364] "Generation means" refers to devices or methods for generating real-time feedback based on efficiency improvement points.

[0365] "Notification means" refers to devices or methods for displaying generated feedback to the user.

[0366] "Content generation means" refers to devices and methods for creating efficiency improvements and educational materials.

[0367] "Emotional analysis means" refers to devices or methods for recognizing a user's emotional state by comprehensively analyzing video and audio data.

[0368] A "user interface" is a device or method for users to display and view generated proposals and educational materials.

[0369] This invention is a system that improves efficiency by collecting and analyzing work data in real time within the work environment. Specifically, a server acquires video and audio data using sensing devices such as network cameras and microphones. This data is preprocessed and noise is removed by a data filtering means on the server. The preprocessed data is then analyzed by an AI analysis means to learn specific patterns in the work procedures.

[0370] Based on the analysis results, the server uses analytical tools to identify areas for improving work efficiency. It also uses emotion analysis tools to recognize the user's emotional state from their voice and facial expressions. This allows a generation tool to generate feedback in real time that is tailored to the efficiency improvements and the emotional state. The generated feedback is then notified to the user via their terminal.

[0371] As a concrete example, in customer service operations, the server analyzes the operator's video and audio during their work. This identifies processes that can be made more efficient in customer interactions. The AI ​​model also performs emotion analysis, and if the operator is experiencing stress, it provides feedback that includes specific advice on stress reduction. An example of a prompt might be, "Please suggest relaxation techniques that the operator can use if they are experiencing stress while interacting with a customer."

[0372] Furthermore, the server generates efficiency suggestions and educational materials using content generation mechanisms. These materials are viewable on terminals through a user interface, allowing users to learn specific methods for improving efficiency. This enables both improved work efficiency and user emotional well-being to be achieved simultaneously.

[0373] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0374] Step 1:

[0375] The server uses network cameras and microphones to acquire video and audio data from the work site in real time. At this stage, the input is raw data from multiple cameras and microphones, and the output is unprocessed video and audio data. Specifically, the server records the acquired data along with a timestamp to storage.

[0376] Step 2:

[0377] The server performs preprocessing on the acquired video and audio data, such as noise reduction and format conversion. At this stage, the raw data from step 1 is provided as input, and the output is data with noise removed and ready for analysis. Specifically, background noise is filtered from the audio data, and unnecessary frames are removed from the video data.

[0378] Step 3:

[0379] The server uses AI analysis tools to extract and learn patterns of business procedures from pre-processed data. The input for this step is pre-processed video and audio data, and the output is a basic pattern of the business process. Specifically, the AI ​​model applies machine learning algorithms to identify specific work procedures and abnormal behaviors.

[0380] Step 4:

[0381] The server uses the analysis results to identify areas for business efficiency improvement. At this stage, the input is the business pattern obtained in step 3, and the output shows specific business procedures that require optimization. The specific actions include comparing the current data with similar historical data and listing areas where efficiency improvements are expected.

[0382] Step 5:

[0383] The server analyzes the user's emotional state from their facial expressions and voice tone using emotion analysis tools. The input at this stage is the pre-processed data from step 2, and the output is the user's emotion evaluation result. Specifically, the AI ​​model uses facial recognition technology and voice emotion analysis technology to identify what emotional state the user is in.

[0384] Step 6:

[0385] The server uses a generation mechanism to generate feedback based on efficiency points and emotional states. The feedback output generated based on the input from steps 4 and 5 is the improvement suggestions and points of caution provided to the user. Specific actions include the generation AI model utilizing prompts to construct a feedback message appropriate for the user.

[0386] Step 7:

[0387] The terminal notifies the user of feedback sent from the server. The input is the feedback generated in step 6, and the output is a notification or display to the user. Specifically, the notification appears as a pop-up on the screen, and voice confirmation is also possible.

[0388] Step 8:

[0389] The server uses content generation tools to create efficiency proposals and educational videos, making them viewable by users through their terminals. The input for this stage is the information from steps 4 and 6, and the output provides users with specific improvement measures. Specifically, a generation AI model automatically assembles the proposal content and provides it as a visualized resource.

[0390] (Application Example 2)

[0391] 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 as the "terminal".

[0392] In today's work environment, achieving efficient and effective work is a crucial challenge for many organizations. However, improving work efficiency requires not only optimizing work processes but also considering the emotional state of employees. Traditional systems, while focusing on work efficiency, have been limited in their ability to generate feedback that takes employees' emotional states into account. Therefore, there is a need for a system that can improve work efficiency while also providing flexible responses that are in line with the emotions of users.

[0393] 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.

[0394] In this invention, the server includes means for acquiring activity video information in the work environment, means for preprocessing the acquired video information to remove noise, means for analyzing work patterns using the preprocessed information and recognizing the patterns, means for identifying areas where the efficiency of the work process can be improved based on the recognized patterns, means for analyzing the emotional state of the user, means for adapting the content of the feedback based on the analyzed emotional state, and means for displaying the generated feedback on a video display device. This makes it possible to improve work efficiency while providing feedback that is tailored to the user's emotions, thereby simultaneously improving the work environment and increasing employee satisfaction.

[0395] The term "work environment" refers to the place where various tasks and activities are carried out within a company or organization, and includes the physical and virtual environments that support those tasks.

[0396] "Activity video information" refers to video data capturing the work and activities performed in the work environment, and is used for analyzing work processes.

[0397] "Noise reduction" is a preprocessing technique that removes unwanted interference information from acquired video and audio data to improve the accuracy of the necessary data.

[0398] "Work patterns" refer to certain regularities or tendencies that are obtained as a result of analyzing combinations of procedures and actions in specific tasks or activities performed in a work environment.

[0399] "Streamlining business processes" refers to improving or redesigning processes to maximize results while reducing the time and resources required for those processes.

[0400] "User emotional state" refers to information indicating the emotional state of employees or operators performing tasks, such as stress levels, satisfaction levels, and concentration levels. This information is analyzed to serve as a reference for improving work processes.

[0401] "Feedback" is information generated based on analyzed work patterns and the emotional state of users, and is provided to users as a means of improving work efficiency and providing solutions for improvement.

[0402] A "video display device" is a device used to visually present acquired feedback information to the user and assist in improving business operations.

[0403] The system for carrying out this invention is configured to integrally process video and audio information of activities in a work environment. The server acquires video and audio information in real time through cameras and microphones within the work environment. The raw data collected from these devices is temporarily stored in storage installed within the server.

[0404] Subsequently, the server preprocesses the video and audio information using a noise reduction algorithm. This process, for example, uses the OpenCV library to clear redundant parts from the video data and reduce unwanted background noise from the audio data.

[0405] The pre-processed information is analyzed by a dedicated AI model. This AI model identifies business patterns based on the initial training data and performs pattern recognition. Based on the recognized business patterns, the server identifies which parts of the business process can be made more efficient.

[0406] Furthermore, the server incorporates an emotion engine that evaluates the user's emotional state by analyzing their facial expressions and tone of voice. Based on this analysis, the feedback is tailored to the user's emotions. The feedback is displayed on a video display device, such as smart glasses worn by the user, and suggestions for efficiency improvements and other areas for improvement are presented in real time.

[0407] For example, when an employee assisting a customer uses this system, they can detect signs of customer dissatisfaction and immediately receive appropriate solutions on the display of their glasses. This can improve customer satisfaction.

[0408] An example of a prompt for a generative AI model is, "Generate feedback suggesting solutions for when a customer expresses dissatisfaction." This prompt allows the AI ​​model to generate appropriate solution-oriented feedback.

[0409] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0410] Step 1:

[0411] The server uses cameras and microphones within the work environment to acquire video and audio information about the activities. The input is raw data from the cameras and microphones, and the output is raw video and audio data stored in storage. In this step, initial processing is performed to properly capture data from the devices and to fully record the activities during work.

[0412] Step 2:

[0413] The server performs noise reduction on the acquired raw data. The input is the raw data saved in step 1, and the output is pre-processed data with reduced noise. In this step, data processing is performed to improve the accuracy of the analysis by clearing the video data and removing unnecessary background noise using libraries such as OpenCV.

[0414] Step 3:

[0415] The server analyzes pre-processed data using an AI model to recognize business patterns. The input is denoised video and audio data, and the output is the recognized business patterns. In this step, data calculations are performed so that the AI ​​model can analyze the data and learn specific behavioral rules and patterns that should be made more efficient.

[0416] Step 4:

[0417] The server identifies areas where efficiency improvements are possible based on recognized business patterns. The input is the pattern recognized in step 3, and the output is information about the business processes that need to be streamlined. In this step, the identified areas are investigated in detail, and preparations are made to propose specific measures for process improvement.

[0418] Step 5:

[0419] The server analyzes the user's emotional state using an emotion engine. The input is the pre-processed video and audio from step 2, and the output is the analyzed emotional state information. In this step, emotions are recognized from the user's facial expressions and voice, and data transformation is performed to reflect these in the feedback.

[0420] Step 6:

[0421] The server generates appropriate feedback based on areas that need improvement and the user's emotional state. The input is the location information from step 4 and the emotional state information from step 5, and the output is the feedback displayed to the user. In this step, a generative AI model is used to generate prompt sentences that create feedback that takes the user's emotions into consideration.

[0422] Step 7:

[0423] The terminal displays the generated feedback on the smart glasses' display. The input is the feedback generated in step 6, and the output is the information presented on the user's visual interface. In this step, the feedback is displayed in real time so that the user can immediately see and implement improvements while working.

[0424] 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.

[0425] 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.

[0426] 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.

[0427] [Third Embodiment]

[0428] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0429] 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.

[0430] 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).

[0431] 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.

[0432] 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.

[0433] 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).

[0434] 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.

[0435] 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.

[0436] 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.

[0437] 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.

[0438] 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.

[0439] 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".

[0440] The business efficiency system of the present invention is designed to be implemented in various business environments, such as manufacturing and service industries. The system operates in cooperation with multiple devices via a network. A specific embodiment of the system is described below.

[0441] First, the server acquires video and audio data from network cameras and microphones installed in the work environment. This allows for real-time monitoring of worker movements and ambient sounds. This data is then processed to remove noise and organized.

[0442] Next, the server inputs the pre-processed data into a multimodal AI model to analyze work patterns. This AI model can recognize work procedures from video and instructions and communication content from audio. In this way, it comprehensively analyzes various aspects of the work and learns patterns.

[0443] Based on the analysis results, the AI ​​agent (server) identifies areas in the business process where efficiency improvements are needed. For example, this might include situations where a specific work procedure is unnecessarily redundant, or where the same task is being performed redundantly by multiple workers.

[0444] The server then generates real-time feedback on areas for improvement and notifies the user. This feedback details specific steps to be taken for improvement and, where possible, the possibility of automation. The terminal displays this feedback on its screen, allowing the user to understand the situation immediately.

[0445] Furthermore, based on the identified areas for improvement, the server generates proposals and videos outlining specific ways to streamline the process. These include the resources required for improvement and the expected effects. The proposals and videos are accessible to the user via their terminal, providing a roadmap for initiating improvement activities.

[0446] As a concrete example, suppose a server in a manufacturing line identifies a tendency for a particular worker to frequently make procedural errors at a certain stage of the process. Based on this information, the AI ​​agent (server) recommends adding visual guidance, and the terminal can display this guidance to the user. In this way, the present invention achieves substantial improvements to business processes and increases labor productivity.

[0447] The following describes the processing flow.

[0448] Step 1:

[0449] The server continuously acquires video and audio data from network cameras and microphones installed in the work environment. This enables real-time monitoring.

[0450] Step 2:

[0451] The server preprocesses the acquired video and audio data by applying a noise reduction algorithm to make the data clearer. This process improves the accuracy of the analysis.

[0452] Step 3:

[0453] The server inputs pre-processed data into a multimodal AI model to analyze work patterns. Specifically, it extracts work procedures from video and recognizes instructions and communication content from audio as text.

[0454] Step 4:

[0455] The AI ​​agent (server) identifies areas in business processes that need improvement based on the analysis results. For example, it detects waiting times between tasks and unnecessary movements, and identifies points that can be improved.

[0456] Step 5:

[0457] The server generates and sends real-time feedback on identified efficiency points to the terminal. This feedback includes specific improvement suggestions and points to note.

[0458] Step 6:

[0459] The device notifies the user of the feedback received from the server and displays it on the screen. The user can then refer to this information and immediately understand the necessary improvements.

[0460] Step 7:

[0461] The server generates a more detailed proposal and video, outlining specific improvement activities the user should undertake. The proposal details the expected effects and necessary tools.

[0462] Step 8:

[0463] Users review proposals and videos through their devices and actively work on improving their business processes. This leads to increased efficiency and improved quality.

[0464] (Example 1)

[0465] 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."

[0466] In order to improve work efficiency in the work environment, it is necessary to appropriately identify inefficient parts of business processes and promptly propose improvements. However, currently, the complexity and diversity of work make it difficult to identify points for efficiency improvement and propose improvement measures. It is necessary to solve this problem and improve work productivity.

[0467] 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.

[0468] In this invention, the server includes means for acquiring data, means for preprocessing the data to remove noise, and means for analyzing business patterns using the preprocessed data and recognizing the patterns. This makes it possible to identify areas in business processes where efficiency improvements can be made and to provide specific improvement suggestions to the user in real time.

[0469] "Means of acquiring data" refer to devices and processes for collecting necessary information in the work environment, which enable an understanding of the actual state of operations.

[0470] "Methods for preprocessing data to remove noise" refer to the process of removing unnecessary noise and inaccurate elements from collected information and organizing it into a format that is easy to analyze.

[0471] "Means for analyzing and recognizing business patterns" refers to a process that analyzes the progress and procedures of business operations based on pre-processed information, and identifies standard patterns and anomalies.

[0472] "Methods for identifying areas where efficiency can be improved" refers to methods for identifying specific locations and procedures from analyzed work patterns that can be improved to enhance work efficiency.

[0473] "Providing improvement suggestions to users in real time" means presenting specific measures for identified problems and areas for improvement in a way that users can immediately see and use, thereby providing information that can be utilized right away.

[0474] The business efficiency system of this invention aims to streamline work processes in the work environment and improve productivity. This system collects data from multiple devices and proposes efficiency improvements based on the analysis results.

[0475] The server acquires data from the work environment through multiple sensor devices. This involves using common hardware such as network cameras and microphones to record the actions and voices of workers. For example, commercially available general-purpose cameras and microphones are used. The acquired data is pre-processed to remove noise.

[0476] The pre-processed data is analyzed using a generative AI model. This AI model is used to analyze work procedures from video data and to identify instructions and communication content from audio data. Common AI models incorporated include open-source tools and commercial AI models.

[0477] After the analysis is complete, the server generates real-time feedback based on the identified areas for improvement and notifies the user. This feedback is presented to the user via the screen of their mobile device or computer terminal, showing them specific steps for improvement.

[0478] Furthermore, the server generates effective improvement proposals and visual guidance videos based on the analysis results. This allows users to understand actionable improvement measures and quickly begin taking action to improve operational efficiency.

[0479] For example, if the server detects a tendency for workers to make procedural errors on a factory production line, it can suggest adding visual guidance. This guidance is then communicated to the user in real time via a terminal. An example of a prompt could be: "Please suggest specific guidance to reduce procedural errors in the manufacturing process."

[0480] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0481] Step 1:

[0482] The server acquires data from sensor devices within the work environment via the network. This data includes video data from network cameras and audio data from microphones. Specifically, the video data records the movements of workers, and the audio data records conversations and ambient sounds. The input data is the raw data transmitted from the cameras and microphones, and the following processing steps are performed based on this data.

[0483] Step 2:

[0484] The server performs preprocessing on the acquired data. Specifically, it performs noise filtering to remove noise from audio data and optimizes the resolution and removes unnecessary frames from video data. The input is the raw data acquired in step 1, and the output is clean audio and video data. This preprocessed data enables more accurate analysis.

[0485] Step 3:

[0486] The server inputs pre-processed data into a generating AI model to analyze work patterns. Specifically, the AI ​​model extracts work procedures and actions from video and analyzes instructions and communication content from audio data. Pre-processed data is used as input, and the output is the analysis results of work patterns. Based on these analysis results, it is possible to recognize standard work patterns and points of anomaly.

[0487] Step 4:

[0488] The AI ​​agent (server) identifies areas within the business process where efficiency improvements can be made, based on the analysis results. Specifically, this includes detecting redundancy and duplication in the procedures identified by the AI ​​model. The input is the analysis results from step 3, and the output is a list of points where efficiency improvements are possible.

[0489] Step 5:

[0490] The server generates and sends feedback based on the identified efficiency points to the terminal. Specifically, this includes visual guides and detailed improvement steps as improvement suggestions. The input is the efficiency improvement points from step 4, and the output generates improvement feedback to be presented to the user.

[0491] Step 6:

[0492] The user reviews feedback sent from the server via their device. Specifically, they are required to understand and implement the improvement steps displayed on the device's screen. In this step, the user gains immediately applicable improvement solutions. The input is the feedback information from the server, and the output is the user's action.

[0493] (Application Example 1)

[0494] 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."

[0495] In modern industrial processes, automation technologies are advancing to improve work efficiency, but many workplaces still have inefficient work procedures, which can lead to decreased productivity. This invention aims to solve the problem of improving the efficiency of work processes by monitoring work conditions in real time, identifying unnecessary actions and time lags, and proposing improvements.

[0496] 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.

[0497] In this invention, the server includes means for acquiring work video data and audio data in the work environment; means for preprocessing the acquired video data and audio data to remove noise; means for analyzing work operation patterns using the preprocessed data and recognizing operation patterns; means for identifying areas where the efficiency of the work process can be improved based on the recognized operation patterns; means for generating real-time feedback for the identified areas where efficiency can be improved and providing information including improvement suggestions to the worker; and means for generating efficiency improvement proposals and visual guide videos and demonstrating methods for optimizing the work process. This makes it possible to improve work efficiency and optimize productivity in a factory.

[0498] "Work environment" refers to the physical and technical location and conditions for performing work, such as a manufacturing site or office, where the actual work takes place.

[0499] "Work video data" refers to visual information that records the flow and actions of work in a work environment, and is mainly data acquired using cameras.

[0500] "Audio data" refers to auditory information recorded using a microphone, specifically the voices of workers and ambient sounds in the work environment.

[0501] "Preprocessing" refers to the initial data processing performed to prepare acquired raw data for analysis, and includes processes such as noise reduction and format standardization.

[0502] "Noise removal techniques" refer to technologies and methods for reducing unnecessary information contained in data and extracting only the useful data necessary for analysis.

[0503] A "work pattern" refers to a series of repetitive actions or procedures performed by a worker in a work environment, and represents standard behavior for a particular task or process.

[0504] "Means of analysis" refers to techniques for analyzing data using specific methods and tools in order to process the data and extract meaningful information.

[0505] "Means of recognizing behavioral patterns" refers to technologies and algorithms for identifying specific actions or procedures from collected data, and for classifying and understanding them.

[0506] "Areas where efficiency can be improved" refers to parts of a business where work time can be reduced or resources can be saved, and these are segments that have been identified as having room for improvement.

[0507] "Means of generating feedback" refers to the technologies and processes used to create useful information and improvement suggestions for users based on analysis results.

[0508] "Information including improvement suggestions" refers to information that describes specific improvement measures and procedures proposed to workers based on identified opportunities for efficiency improvements.

[0509] A "visual guide video" refers to video materials designed to clearly communicate streamlined procedures and improvements to workers, and is visual content created for users to learn from or refer to.

[0510] To implement this invention, close cooperation between the server, terminal, and user is necessary. The server acquires video and audio data of the work using network cameras and microphones placed in the work environment. Once this data is collected, noise is removed as a preprocessing step to prepare the data for improved analysis quality.

[0511] Next, the server uses pre-processed data to recognize work action patterns using a multimodal AI model. By using AI frameworks such as TensorFlow, it analyzes work actions from video and instructions from audio to grasp complex work action patterns.

[0512] Once the operating patterns are identified, the server reveals areas within the business process where efficiency improvements can be made. This identification process utilizes data streaming technologies such as Apache Kafka to identify inefficiencies in real time and point out areas that need improvement.

[0513] Based on these analysis results, the server generates feedback and displays it to the user via the terminal. The terminal's display provides the user with identified areas for improvement as a visual guide video, clearly explaining how to make improvements. For example, if an worker is repeating unnecessary movements in the same process, a guide video is generated showing specific steps to reduce those movements.

[0514] By viewing proposals and videos, users can begin reviewing workflows and optimizing operations based on the suggested improvements. This entire process can significantly improve productivity and efficiency at the work site.

[0515] Examples of prompts for the generated AI model include specific instructions such as, "Analyze the video footage of the factory robot's movements and generate suggestions for improvements to increase efficiency. Focus especially on areas with many unnecessary movements." This allows the server to provide the user with optimized movement patterns.

[0516] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0517] Step 1:

[0518] The server collects video and audio data in real time from network cameras and microphones. This data includes resource usage in the work environment and worker movements. Raw video and audio frames are provided as input. The output is stored as raw data that can be pre-processed for noise reduction.

[0519] Step 2:

[0520] The server removes noise from the collected raw data. This step uses a filtering algorithm to reduce audio and video noise that is unnecessary for business analysis. The input is the video and audio data acquired in step 1, and the output is the clear, pre-processed data.

[0521] Step 3:

[0522] The server uses pre-processed data to input into a multimodal AI model and analyzes behavioral patterns. This process uses machine learning libraries such as TensorFlow to analyze the relationships between multiple data modals. The input is pre-processed visual and audio data, and the output is a list of recognized behavioral patterns.

[0523] Step 4:

[0524] The server identifies areas where efficiency can be improved based on the recognized operating patterns. By reviewing the output of Step 3 and investigating redundant operations and time lags, points that can be improved are identified. The input is the recognition result from Step 3, and the output is a list of candidate points where efficiency can be improved.

[0525] Step 5:

[0526] The server generates real-time feedback based on identified efficiency points. This feedback includes improvement suggestions that the worker should follow. The input is a list of candidate efficiency points, and the output is the specific improvement suggestions presented to the user.

[0527] Step 6:

[0528] The device visually presents the generated feedback to the user. This presentation takes place on the display and supports real-time work improvement. The feedback output in step 5 is the input, and the output is the visual information received by the user.

[0529] Step 7:

[0530] The server generates efficiency improvement proposals and guide videos and provides them to the user via the terminal. In this step, a presentation tool is used to visualize the improvement steps in detail. The inputs are the identified points from step 4, and the output is the improvement guide document and video that the user can view.

[0531] 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.

[0532] This invention is a system aimed at improving work processes in the work environment. It identifies points for improving work efficiency by comprehensively analyzing video and audio data. Furthermore, by combining it with an emotion engine that evaluates the user's emotional state, it improves the accuracy and effectiveness of feedback. This system mainly consists of multiple devices and a server communicating via the internet.

[0533] The server collects video footage from network cameras and audio data from microphones at the work site. This data is temporarily stored in storage and undergoes pre-processing such as noise reduction. After pre-processing, the data is analyzed by an AI model to identify specific patterns in the work process.

[0534] Subsequently, the server identifies areas requiring optimization based on the analyzed business patterns. Simultaneously, the emotion engine (server) analyzes the user's facial expressions and tone of voice to recognize their emotional state. This allows the feedback to be adapted to the user's emotions.

[0535] The server generates appropriate and effective feedback in real time based on identified efficiency points and recognized emotional states. The terminal notifies the user of this feedback, displaying specific suggestions for improvement and points to note. This allows the user to quickly take action based on the information.

[0536] The server also generates a video containing efficiency improvement proposals and operation guides. These proposals detail the benefits of the improvements and the resources required for implementation, and users can view them through their terminals.

[0537] As a concrete example, in customer service operations, the server analyzes the audio and video of the operator's interactions to identify processes that can be made more efficient in customer interactions. At the same time, an emotion engine detects the operator's stress level, and the feedback includes simple techniques and suggestions for improvement to reduce stress. In this way, the system provides a solution that considers both operational improvements and employee well-being.

[0538] The following describes the processing flow.

[0539] Step 1:

[0540] The server acquires real-time video and audio data from network cameras and microphones installed at the work site. This data is used to accurately capture the work environment and conditions.

[0541] Step 2:

[0542] The server performs preprocessing to prepare the acquired video and audio data for analysis. Specifically, it performs noise reduction and data cleaning, and uses signal processing techniques to improve quality.

[0543] Step 3:

[0544] The server inputs pre-processed video and audio into a multimodal AI model to analyze work patterns. This analysis makes it possible to recognize and record work content, procedures, and communication flows.

[0545] Step 4:

[0546] The AI ​​agent (server) uses the analysis results to identify inefficiencies in business processes. This step prioritizes detecting redundant procedures and activities that take too much time.

[0547] Step 5:

[0548] The emotion engine (server) performs facial expression and voice analysis on the user to recognize their emotional state. This information is used to understand the user's psychological state while they are performing their work.

[0549] Step 6:

[0550] The server generates customized real-time feedback based on identified inefficiencies and the user's emotional state. This process creates appropriate advice and improvement suggestions that take emotions into account.

[0551] Step 7:

[0552] The terminal notifies the user of feedback generated by the server and displays it on the screen. The user can receive this feedback immediately and use it to improve their work.

[0553] Step 8:

[0554] The server prepares efficiency improvement proposals and related videos, detailing the proposed improvements. The proposals describe specific methods and expected effects, and users can access them through their devices.

[0555] Step 9:

[0556] Users can review proposals and videos on their devices and implement recommended improvements. Only after this step can the streamlining of business processes be achieved.

[0557] (Example 2)

[0558] 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."

[0559] In today's work environment, while efficiency is demanded, there is a lack of mechanisms to appropriately evaluate work processes and the emotional state of users, and to provide timely feedback. This can lead to decreased work efficiency and increased user stress. To address these challenges, it is necessary to comprehensively analyze diverse data and immediately propose efficiency improvements.

[0560] 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.

[0561] In this invention, the server includes sensing means for acquiring work data in the work environment, data filtering means for preprocessing the acquired data to remove noise, and AI analysis means for analyzing work procedures using the preprocessed data and learning specific patterns. This makes it possible to accurately identify points for improving work efficiency and generate feedback and suggestions adapted to the user's emotional state in real time.

[0562] "Sensing means" refers to devices or methods for acquiring work data in a work environment.

[0563] A "data filtering means" refers to a processing device or method for removing noise from acquired data and preparing it for analysis.

[0564] "AI analysis means" refers to devices or methods that use artificial intelligence technology to analyze business procedures using pre-processed data and learn specific patterns.

[0565] "Analysis tools" are devices or methods for identifying areas for improving the efficiency of work procedures based on learned patterns.

[0566] "Generation means" refers to devices or methods for generating real-time feedback based on efficiency improvement points.

[0567] "Notification means" refers to devices or methods for displaying generated feedback to the user.

[0568] "Content generation means" refers to devices and methods for creating efficiency improvements and educational materials.

[0569] "Emotional analysis means" refers to devices or methods for recognizing a user's emotional state by comprehensively analyzing video and audio data.

[0570] A "user interface" is a device or method for users to display and view generated proposals and educational materials.

[0571] This invention is a system that improves efficiency by collecting and analyzing work data in real time within the work environment. Specifically, a server acquires video and audio data using sensing devices such as network cameras and microphones. This data is preprocessed and noise is removed by a data filtering means on the server. The preprocessed data is then analyzed by an AI analysis means to learn specific patterns in the work procedures.

[0572] Based on the analysis results, the server uses analytical tools to identify areas for improving work efficiency. It also uses emotion analysis tools to recognize the user's emotional state from their voice and facial expressions. This allows a generation tool to generate feedback in real time that is tailored to the efficiency improvements and the emotional state. The generated feedback is then notified to the user via their terminal.

[0573] As a concrete example, in customer service operations, the server analyzes the operator's video and audio during their work. This identifies processes that can be made more efficient in customer interactions. The AI ​​model also performs emotion analysis, and if the operator is experiencing stress, it provides feedback that includes specific advice on stress reduction. An example of a prompt might be, "Please suggest relaxation techniques that the operator can use if they are experiencing stress while interacting with a customer."

[0574] Furthermore, the server generates efficiency suggestions and educational materials using content generation mechanisms. These materials are viewable on terminals through a user interface, allowing users to learn specific methods for improving efficiency. This enables both improved work efficiency and user emotional well-being to be achieved simultaneously.

[0575] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0576] Step 1:

[0577] The server uses network cameras and microphones to acquire video and audio data from the work site in real time. At this stage, the input is raw data from multiple cameras and microphones, and the output is unprocessed video and audio data. Specifically, the server records the acquired data along with a timestamp to storage.

[0578] Step 2:

[0579] The server performs preprocessing on the acquired video and audio data, such as noise reduction and format conversion. At this stage, the raw data from step 1 is provided as input, and the output is data with noise removed and ready for analysis. Specifically, background noise is filtered from the audio data, and unnecessary frames are removed from the video data.

[0580] Step 3:

[0581] The server uses AI analysis tools to extract and learn patterns of business procedures from pre-processed data. The input for this step is pre-processed video and audio data, and the output is a basic pattern of the business process. Specifically, the AI ​​model applies machine learning algorithms to identify specific work procedures and abnormal behaviors.

[0582] Step 4:

[0583] The server uses the analysis results to identify areas for business efficiency improvement. At this stage, the input is the business pattern obtained in step 3, and the output shows specific business procedures that require optimization. The specific actions include comparing the current data with similar historical data and listing areas where efficiency improvements are expected.

[0584] Step 5:

[0585] The server analyzes the user's emotional state from their facial expressions and voice tone using emotion analysis tools. The input at this stage is the pre-processed data from step 2, and the output is the user's emotion evaluation result. Specifically, the AI ​​model uses facial recognition technology and voice emotion analysis technology to identify what emotional state the user is in.

[0586] Step 6:

[0587] The server uses a generation mechanism to generate feedback based on efficiency points and emotional states. The feedback output generated based on the input from steps 4 and 5 is the improvement suggestions and points of caution provided to the user. Specific actions include the generation AI model utilizing prompts to construct a feedback message appropriate for the user.

[0588] Step 7:

[0589] The terminal notifies the user of feedback sent from the server. The input is the feedback generated in step 6, and the output is a notification or display to the user. Specifically, the notification appears as a pop-up on the screen, and voice confirmation is also possible.

[0590] Step 8:

[0591] The server uses content generation tools to create efficiency proposals and educational videos, making them viewable by users through their terminals. The input for this stage is the information from steps 4 and 6, and the output provides users with specific improvement measures. Specifically, a generation AI model automatically assembles the proposal content and provides it as a visualized resource.

[0592] (Application Example 2)

[0593] 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."

[0594] In today's work environment, achieving efficient and effective work is a crucial challenge for many organizations. However, improving work efficiency requires not only optimizing work processes but also considering the emotional state of employees. Traditional systems, while focusing on work efficiency, have been limited in their ability to generate feedback that takes employees' emotional states into account. Therefore, there is a need for a system that can improve work efficiency while also providing flexible responses that are in line with the emotions of users.

[0595] 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.

[0596] In this invention, the server includes means for acquiring activity video information in the work environment, means for preprocessing the acquired video information to remove noise, means for analyzing work patterns using the preprocessed information and recognizing the patterns, means for identifying areas where the efficiency of the work process can be improved based on the recognized patterns, means for analyzing the emotional state of the user, means for adapting the content of the feedback based on the analyzed emotional state, and means for displaying the generated feedback on a video display device. This makes it possible to improve work efficiency while providing feedback that is tailored to the user's emotions, thereby simultaneously improving the work environment and increasing employee satisfaction.

[0597] The term "work environment" refers to the place where various tasks and activities are carried out within a company or organization, and includes the physical and virtual environments that support those tasks.

[0598] "Activity video information" refers to video data capturing the work and activities performed in the work environment, and is used for analyzing work processes.

[0599] "Noise reduction" is a preprocessing technique that removes unwanted interference information from acquired video and audio data to improve the accuracy of the necessary data.

[0600] "Work patterns" refer to certain regularities or tendencies that are obtained as a result of analyzing combinations of procedures and actions in specific tasks or activities performed in a work environment.

[0601] "Streamlining business processes" refers to improving or redesigning processes to maximize results while reducing the time and resources required for those processes.

[0602] "User emotional state" refers to information indicating the emotional state of employees or operators performing tasks, such as stress levels, satisfaction levels, and concentration levels. This information is analyzed to serve as a reference for improving work processes.

[0603] "Feedback" is information generated based on analyzed work patterns and the emotional state of users, and is provided to users as a means of improving work efficiency and providing solutions for improvement.

[0604] A "video display device" is a device used to visually present acquired feedback information to the user and assist in improving business operations.

[0605] The system for carrying out this invention is configured to integrally process video and audio information of activities in a work environment. The server acquires video and audio information in real time through cameras and microphones within the work environment. The raw data collected from these devices is temporarily stored in storage installed within the server.

[0606] Subsequently, the server preprocesses the video and audio information using a noise reduction algorithm. This process, for example, uses the OpenCV library to clear redundant parts from the video data and reduce unwanted background noise from the audio data.

[0607] The pre-processed information is analyzed by a dedicated AI model. This AI model identifies business patterns based on the initial training data and performs pattern recognition. Based on the recognized business patterns, the server identifies which parts of the business process can be made more efficient.

[0608] Furthermore, the server incorporates an emotion engine that evaluates the user's emotional state by analyzing their facial expressions and tone of voice. Based on this analysis, the feedback is tailored to the user's emotions. The feedback is displayed on a video display device, such as smart glasses worn by the user, and suggestions for efficiency improvements and other areas for improvement are presented in real time.

[0609] For example, when an employee assisting a customer uses this system, they can detect signs of customer dissatisfaction and immediately receive appropriate solutions on the display of their glasses. This can improve customer satisfaction.

[0610] An example of a prompt for a generative AI model is, "Generate feedback suggesting solutions for when a customer expresses dissatisfaction." This prompt allows the AI ​​model to generate appropriate solution-oriented feedback.

[0611] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0612] Step 1:

[0613] The server uses cameras and microphones within the work environment to acquire video and audio information about the activities. The input is raw data from the cameras and microphones, and the output is raw video and audio data stored in storage. In this step, initial processing is performed to properly capture data from the devices and to fully record the activities during work.

[0614] Step 2:

[0615] The server performs noise reduction on the acquired raw data. The input is the raw data saved in step 1, and the output is pre-processed data with reduced noise. In this step, data processing is performed to improve the accuracy of the analysis by clearing the video data and removing unnecessary background noise using libraries such as OpenCV.

[0616] Step 3:

[0617] The server analyzes pre-processed data using an AI model to recognize business patterns. The input is denoised video and audio data, and the output is the recognized business patterns. In this step, data calculations are performed so that the AI ​​model can analyze the data and learn specific behavioral rules and patterns that should be made more efficient.

[0618] Step 4:

[0619] The server identifies areas where efficiency improvements are possible based on recognized business patterns. The input is the pattern recognized in step 3, and the output is information about the business processes that need to be streamlined. In this step, the identified areas are investigated in detail, and preparations are made to propose specific measures for process improvement.

[0620] Step 5:

[0621] The server analyzes the user's emotional state using an emotion engine. The input is the pre-processed video and audio from step 2, and the output is the analyzed emotional state information. In this step, emotions are recognized from the user's facial expressions and voice, and data transformation is performed to reflect these in the feedback.

[0622] Step 6:

[0623] The server generates appropriate feedback based on areas that need improvement and the user's emotional state. The input is the location information from step 4 and the emotional state information from step 5, and the output is the feedback displayed to the user. In this step, a generative AI model is used to generate prompt sentences that create feedback that takes the user's emotions into consideration.

[0624] Step 7:

[0625] The terminal displays the generated feedback on the smart glasses' display. The input is the feedback generated in step 6, and the output is the information presented on the user's visual interface. In this step, the feedback is displayed in real time so that the user can immediately see and implement improvements while working.

[0626] 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.

[0627] 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.

[0628] 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.

[0629] [Fourth Embodiment]

[0630] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0631] 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.

[0632] 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).

[0633] 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.

[0634] 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.

[0635] 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).

[0636] 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.

[0637] 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.

[0638] 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.

[0639] 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.

[0640] 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.

[0641] 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.

[0642] 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".

[0643] The business efficiency system of the present invention is designed to be implemented in various business environments, such as manufacturing and service industries. The system operates in cooperation with multiple devices via a network. A specific embodiment of the system is described below.

[0644] First, the server acquires video and audio data from network cameras and microphones installed in the work environment. This allows for real-time monitoring of worker movements and ambient sounds. This data is then processed to remove noise and organized.

[0645] Next, the server inputs the pre-processed data into a multimodal AI model to analyze work patterns. This AI model can recognize work procedures from video and instructions and communication content from audio. In this way, it comprehensively analyzes various aspects of the work and learns patterns.

[0646] Based on the analysis results, the AI ​​agent (server) identifies areas in the business process where efficiency improvements are needed. For example, this might include situations where a specific work procedure is unnecessarily redundant, or where the same task is being performed redundantly by multiple workers.

[0647] The server then generates real-time feedback on areas for improvement and notifies the user. This feedback details specific steps to be taken for improvement and, where possible, the possibility of automation. The terminal displays this feedback on its screen, allowing the user to understand the situation immediately.

[0648] Furthermore, based on the identified areas for improvement, the server generates proposals and videos outlining specific ways to streamline the process. These include the resources required for improvement and the expected effects. The proposals and videos are accessible to the user via their terminal, providing a roadmap for initiating improvement activities.

[0649] As a concrete example, suppose a server in a manufacturing line identifies a tendency for a particular worker to frequently make procedural errors at a certain stage of the process. Based on this information, the AI ​​agent (server) recommends adding visual guidance, and the terminal can display this guidance to the user. In this way, the present invention achieves substantial improvements to business processes and increases labor productivity.

[0650] The following describes the processing flow.

[0651] Step 1:

[0652] The server continuously acquires video and audio data from network cameras and microphones installed in the work environment. This enables real-time monitoring.

[0653] Step 2:

[0654] The server preprocesses the acquired video and audio data by applying a noise reduction algorithm to make the data clearer. This process improves the accuracy of the analysis.

[0655] Step 3:

[0656] The server inputs pre-processed data into a multimodal AI model to analyze work patterns. Specifically, it extracts work procedures from video and recognizes instructions and communication content from audio as text.

[0657] Step 4:

[0658] The AI ​​agent (server) identifies areas in business processes that need improvement based on the analysis results. For example, it detects waiting times between tasks and unnecessary movements, and identifies points that can be improved.

[0659] Step 5:

[0660] The server generates and sends real-time feedback on identified efficiency points to the terminal. This feedback includes specific improvement suggestions and points to note.

[0661] Step 6:

[0662] The device notifies the user of the feedback received from the server and displays it on the screen. The user can then refer to this information and immediately understand the necessary improvements.

[0663] Step 7:

[0664] The server generates a more detailed proposal and video, outlining specific improvement activities the user should undertake. The proposal details the expected effects and necessary tools.

[0665] Step 8:

[0666] Users review proposals and videos through their devices and actively work on improving their business processes. This leads to increased efficiency and improved quality.

[0667] (Example 1)

[0668] 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".

[0669] In order to improve work efficiency in the work environment, it is necessary to appropriately identify inefficient parts of business processes and promptly propose improvements. However, currently, the complexity and diversity of work make it difficult to identify points for efficiency improvement and propose improvement measures. It is necessary to solve this problem and improve work productivity.

[0670] 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.

[0671] In this invention, the server includes means for acquiring data, means for preprocessing the data to remove noise, and means for analyzing business patterns using the preprocessed data and recognizing the patterns. This makes it possible to identify areas in business processes where efficiency improvements can be made and to provide specific improvement suggestions to the user in real time.

[0672] "Means of acquiring data" refer to devices and processes for collecting necessary information in the work environment, which enable an understanding of the actual state of operations.

[0673] "Methods for preprocessing data to remove noise" refer to the process of removing unnecessary noise and inaccurate elements from collected information and organizing it into a format that is easy to analyze.

[0674] "Means for analyzing and recognizing business patterns" refers to a process that analyzes the progress and procedures of business operations based on pre-processed information, and identifies standard patterns and anomalies.

[0675] "Methods for identifying areas where efficiency can be improved" refers to methods for identifying specific locations and procedures from analyzed work patterns that can be improved to enhance work efficiency.

[0676] "Providing improvement suggestions to users in real time" means presenting specific measures for identified problems and areas for improvement in a way that users can immediately see and use, thereby providing information that can be utilized right away.

[0677] The business efficiency system of this invention aims to streamline work processes in the work environment and improve productivity. This system collects data from multiple devices and proposes efficiency improvements based on the analysis results.

[0678] The server acquires data from the work environment through multiple sensor devices. This involves using common hardware such as network cameras and microphones to record the actions and voices of workers. For example, commercially available general-purpose cameras and microphones are used. The acquired data is pre-processed to remove noise.

[0679] The pre-processed data is analyzed using a generative AI model. This AI model is used to analyze work procedures from video data and to identify instructions and communication content from audio data. Common AI models incorporated include open-source tools and commercial AI models.

[0680] After the analysis is complete, the server generates real-time feedback based on the identified areas for improvement and notifies the user. This feedback is presented to the user via the screen of their mobile device or computer terminal, showing them specific steps for improvement.

[0681] Furthermore, the server generates effective improvement proposals and visual guidance videos based on the analysis results. This allows users to understand actionable improvement measures and quickly begin taking action to improve operational efficiency.

[0682] For example, if the server detects a tendency for workers to make procedural errors on a factory production line, it can suggest adding visual guidance. This guidance is then communicated to the user in real time via a terminal. An example of a prompt could be: "Please suggest specific guidance to reduce procedural errors in the manufacturing process."

[0683] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0684] Step 1:

[0685] The server acquires data from sensor devices within the work environment via the network. This data includes video data from network cameras and audio data from microphones. Specifically, the video data records the movements of workers, and the audio data records conversations and ambient sounds. The input data is the raw data transmitted from the cameras and microphones, and the following processing steps are performed based on this data.

[0686] Step 2:

[0687] The server performs preprocessing on the acquired data. Specifically, it performs noise filtering to remove noise from audio data and optimizes the resolution and removes unnecessary frames from video data. The input is the raw data acquired in step 1, and the output is clean audio and video data. This preprocessed data enables more accurate analysis.

[0688] Step 3:

[0689] The server inputs pre-processed data into a generating AI model to analyze work patterns. Specifically, the AI ​​model extracts work procedures and actions from video and analyzes instructions and communication content from audio data. Pre-processed data is used as input, and the output is the analysis results of work patterns. Based on these analysis results, it is possible to recognize standard work patterns and points of anomaly.

[0690] Step 4:

[0691] The AI ​​agent (server) identifies areas within the business process where efficiency improvements can be made, based on the analysis results. Specifically, this includes detecting redundancy and duplication in the procedures identified by the AI ​​model. The input is the analysis results from step 3, and the output is a list of points where efficiency improvements are possible.

[0692] Step 5:

[0693] The server generates and sends feedback based on the identified efficiency points to the terminal. Specifically, this includes visual guides and detailed improvement steps as improvement suggestions. The input is the efficiency improvement points from step 4, and the output generates improvement feedback to be presented to the user.

[0694] Step 6:

[0695] The user reviews feedback sent from the server via their device. Specifically, they are required to understand and implement the improvement steps displayed on the device's screen. In this step, the user gains immediately applicable improvement solutions. The input is the feedback information from the server, and the output is the user's action.

[0696] (Application Example 1)

[0697] 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".

[0698] In modern industrial processes, automation technologies are advancing to improve work efficiency, but many workplaces still have inefficient work procedures, which can lead to decreased productivity. This invention aims to solve the problem of improving the efficiency of work processes by monitoring work conditions in real time, identifying unnecessary actions and time lags, and proposing improvements.

[0699] 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.

[0700] In this invention, the server includes means for acquiring work video data and audio data in the work environment; means for preprocessing the acquired video data and audio data to remove noise; means for analyzing work operation patterns using the preprocessed data and recognizing operation patterns; means for identifying areas where the efficiency of the work process can be improved based on the recognized operation patterns; means for generating real-time feedback for the identified areas where efficiency can be improved and providing information including improvement suggestions to the worker; and means for generating efficiency improvement proposals and visual guide videos and demonstrating methods for optimizing the work process. This makes it possible to improve work efficiency and optimize productivity in a factory.

[0701] "Work environment" refers to the physical and technical location and conditions for performing work, such as a manufacturing site or office, where the actual work takes place.

[0702] "Work video data" refers to visual information that records the flow and actions of work in a work environment, and is mainly data acquired using cameras.

[0703] "Audio data" refers to auditory information recorded using a microphone, specifically the voices of workers and ambient sounds in the work environment.

[0704] "Preprocessing" refers to the initial data processing performed to prepare acquired raw data for analysis, and includes processes such as noise reduction and format standardization.

[0705] "Noise removal techniques" refer to technologies and methods for reducing unnecessary information contained in data and extracting only the useful data necessary for analysis.

[0706] A "work pattern" refers to a series of repetitive actions or procedures performed by a worker in a work environment, and represents standard behavior for a particular task or process.

[0707] "Means of analysis" refers to techniques for analyzing data using specific methods and tools in order to process the data and extract meaningful information.

[0708] "Means of recognizing behavioral patterns" refers to technologies and algorithms for identifying specific actions or procedures from collected data, and for classifying and understanding them.

[0709] "Areas where efficiency can be improved" refers to parts of a business where work time can be reduced or resources can be saved, and these are segments that have been identified as having room for improvement.

[0710] "Means of generating feedback" refers to the technologies and processes used to create useful information and improvement suggestions for users based on analysis results.

[0711] "Information including improvement suggestions" refers to information that describes specific improvement measures and procedures proposed to workers based on identified opportunities for efficiency improvements.

[0712] A "visual guide video" refers to video materials designed to clearly communicate streamlined procedures and improvements to workers, and is visual content created for users to learn from or refer to.

[0713] To implement this invention, close cooperation between the server, terminal, and user is necessary. The server acquires video and audio data of the work using network cameras and microphones placed in the work environment. Once this data is collected, noise is removed as a preprocessing step to prepare the data for improved analysis quality.

[0714] Next, the server uses pre-processed data to recognize work action patterns using a multimodal AI model. By using AI frameworks such as TensorFlow, it analyzes work actions from video and instructions from audio to grasp complex work action patterns.

[0715] Once the operating patterns are identified, the server reveals areas within the business process where efficiency improvements can be made. This identification process utilizes data streaming technologies such as Apache Kafka to identify inefficiencies in real time and point out areas that need improvement.

[0716] Based on these analysis results, the server generates feedback and displays it to the user via the terminal. The terminal's display provides the user with identified areas for improvement as a visual guide video, clearly explaining how to make improvements. For example, if an worker is repeating unnecessary movements in the same process, a guide video is generated showing specific steps to reduce those movements.

[0717] By viewing proposals and videos, users can begin reviewing workflows and optimizing operations based on the suggested improvements. This entire process can significantly improve productivity and efficiency at the work site.

[0718] Examples of prompts for the generated AI model include specific instructions such as, "Analyze the video footage of the factory robot's movements and generate suggestions for improvements to increase efficiency. Focus especially on areas with many unnecessary movements." This allows the server to provide the user with optimized movement patterns.

[0719] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0720] Step 1:

[0721] The server collects video and audio data in real time from network cameras and microphones. This data includes resource usage in the work environment and worker movements. Raw video and audio frames are provided as input. The output is stored as raw data that can be pre-processed for noise reduction.

[0722] Step 2:

[0723] The server removes noise from the collected raw data. This step uses a filtering algorithm to reduce audio and video noise that is unnecessary for business analysis. The input is the video and audio data acquired in step 1, and the output is the clear, pre-processed data.

[0724] Step 3:

[0725] The server uses pre-processed data to input into a multimodal AI model and analyzes behavioral patterns. This process uses machine learning libraries such as TensorFlow to analyze the relationships between multiple data modals. The input is pre-processed visual and audio data, and the output is a list of recognized behavioral patterns.

[0726] Step 4:

[0727] The server identifies areas where efficiency can be improved based on the recognized operating patterns. By reviewing the output of Step 3 and investigating redundant operations and time lags, points that can be improved are identified. The input is the recognition result from Step 3, and the output is a list of candidate points where efficiency can be improved.

[0728] Step 5:

[0729] The server generates real-time feedback based on identified efficiency points. This feedback includes improvement suggestions that the worker should follow. The input is a list of candidate efficiency points, and the output is the specific improvement suggestions presented to the user.

[0730] Step 6:

[0731] The device visually presents the generated feedback to the user. This presentation takes place on the display and supports real-time work improvement. The feedback output in step 5 is the input, and the output is the visual information received by the user.

[0732] Step 7:

[0733] The server generates efficiency improvement proposals and guide videos and provides them to the user via the terminal. In this step, a presentation tool is used to visualize the improvement steps in detail. The inputs are the identified points from step 4, and the output is the improvement guide document and video that the user can view.

[0734] 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.

[0735] This invention is a system aimed at improving work processes in the work environment. It identifies points for improving work efficiency by comprehensively analyzing video and audio data. Furthermore, by combining it with an emotion engine that evaluates the user's emotional state, it improves the accuracy and effectiveness of feedback. This system mainly consists of multiple devices and a server communicating via the internet.

[0736] The server collects video footage from network cameras and audio data from microphones at the work site. This data is temporarily stored in storage and undergoes pre-processing such as noise reduction. After pre-processing, the data is analyzed by an AI model to identify specific patterns in the work process.

[0737] Subsequently, the server identifies areas requiring optimization based on the analyzed business patterns. Simultaneously, the emotion engine (server) analyzes the user's facial expressions and tone of voice to recognize their emotional state. This allows the feedback to be adapted to the user's emotions.

[0738] The server generates appropriate and effective feedback in real time based on identified efficiency points and recognized emotional states. The terminal notifies the user of this feedback, displaying specific suggestions for improvement and points to note. This allows the user to quickly take action based on the information.

[0739] The server also generates a video containing efficiency improvement proposals and operation guides. These proposals detail the benefits of the improvements and the resources required for implementation, and users can view them through their terminals.

[0740] As a concrete example, in customer service operations, the server analyzes the audio and video of the operator's interactions to identify processes that can be made more efficient in customer interactions. At the same time, an emotion engine detects the operator's stress level, and the feedback includes simple techniques and suggestions for improvement to reduce stress. In this way, the system provides a solution that considers both operational improvements and employee well-being.

[0741] The following describes the processing flow.

[0742] Step 1:

[0743] The server acquires real-time video and audio data from network cameras and microphones installed at the work site. This data is used to accurately capture the work environment and conditions.

[0744] Step 2:

[0745] The server performs preprocessing to prepare the acquired video and audio data for analysis. Specifically, it performs noise reduction and data cleaning, and uses signal processing techniques to improve quality.

[0746] Step 3:

[0747] The server inputs pre-processed video and audio into a multimodal AI model to analyze work patterns. This analysis makes it possible to recognize and record work content, procedures, and communication flows.

[0748] Step 4:

[0749] The AI ​​agent (server) uses the analysis results to identify inefficiencies in business processes. This step prioritizes detecting redundant procedures and activities that take too much time.

[0750] Step 5:

[0751] The emotion engine (server) performs facial expression and voice analysis on the user to recognize their emotional state. This information is used to understand the user's psychological state while they are performing their work.

[0752] Step 6:

[0753] The server generates customized real-time feedback based on identified inefficiencies and the user's emotional state. This process creates appropriate advice and improvement suggestions that take emotions into account.

[0754] Step 7:

[0755] The terminal notifies the user of feedback generated by the server and displays it on the screen. The user can receive this feedback immediately and use it to improve their work.

[0756] Step 8:

[0757] The server prepares efficiency improvement proposals and related videos, detailing the proposed improvements. The proposals describe specific methods and expected effects, and users can access them through their devices.

[0758] Step 9:

[0759] Users can review proposals and videos on their devices and implement recommended improvements. Only after this step can the streamlining of business processes be achieved.

[0760] (Example 2)

[0761] 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".

[0762] In today's work environment, while efficiency is demanded, there is a lack of mechanisms to appropriately evaluate work processes and the emotional state of users, and to provide timely feedback. This can lead to decreased work efficiency and increased user stress. To address these challenges, it is necessary to comprehensively analyze diverse data and immediately propose efficiency improvements.

[0763] 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.

[0764] In this invention, the server includes sensing means for acquiring work data in the work environment, data filtering means for preprocessing the acquired data to remove noise, and AI analysis means for analyzing work procedures using the preprocessed data and learning specific patterns. This makes it possible to accurately identify points for improving work efficiency and generate feedback and suggestions adapted to the user's emotional state in real time.

[0765] "Sensing means" refers to devices or methods for acquiring work data in a work environment.

[0766] A "data filtering means" refers to a processing device or method for removing noise from acquired data and preparing it for analysis.

[0767] "AI analysis means" refers to devices or methods that use artificial intelligence technology to analyze business procedures using pre-processed data and learn specific patterns.

[0768] "Analysis tools" are devices or methods for identifying areas for improving the efficiency of work procedures based on learned patterns.

[0769] "Generation means" refers to devices or methods for generating real-time feedback based on efficiency improvement points.

[0770] "Notification means" refers to devices or methods for displaying generated feedback to the user.

[0771] "Content generation means" refers to devices and methods for creating efficiency improvements and educational materials.

[0772] "Emotional analysis means" refers to devices or methods for recognizing a user's emotional state by comprehensively analyzing video and audio data.

[0773] A "user interface" is a device or method for users to display and view generated proposals and educational materials.

[0774] This invention is a system that improves efficiency by collecting and analyzing work data in real time within the work environment. Specifically, a server acquires video and audio data using sensing devices such as network cameras and microphones. This data is preprocessed and noise is removed by a data filtering means on the server. The preprocessed data is then analyzed by an AI analysis means to learn specific patterns in the work procedures.

[0775] Based on the analysis results, the server uses analytical tools to identify areas for improving work efficiency. It also uses emotion analysis tools to recognize the user's emotional state from their voice and facial expressions. This allows a generation tool to generate feedback in real time that is tailored to the efficiency improvements and the emotional state. The generated feedback is then notified to the user via their terminal.

[0776] As a concrete example, in customer service operations, the server analyzes the operator's video and audio during their work. This identifies processes that can be made more efficient in customer interactions. The AI ​​model also performs emotion analysis, and if the operator is experiencing stress, it provides feedback that includes specific advice on stress reduction. An example of a prompt might be, "Please suggest relaxation techniques that the operator can use if they are experiencing stress while interacting with a customer."

[0777] Furthermore, the server generates efficiency suggestions and educational materials using content generation mechanisms. These materials are viewable on terminals through a user interface, allowing users to learn specific methods for improving efficiency. This enables both improved work efficiency and user emotional well-being to be achieved simultaneously.

[0778] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0779] Step 1:

[0780] The server uses network cameras and microphones to acquire video and audio data from the work site in real time. At this stage, the input is raw data from multiple cameras and microphones, and the output is unprocessed video and audio data. Specifically, the server records the acquired data along with a timestamp to storage.

[0781] Step 2:

[0782] The server performs preprocessing on the acquired video and audio data, such as noise reduction and format conversion. At this stage, the raw data from step 1 is provided as input, and the output is data with noise removed and ready for analysis. Specifically, background noise is filtered from the audio data, and unnecessary frames are removed from the video data.

[0783] Step 3:

[0784] The server uses AI analysis tools to extract and learn patterns of business procedures from pre-processed data. The input for this step is pre-processed video and audio data, and the output is a basic pattern of the business process. Specifically, the AI ​​model applies machine learning algorithms to identify specific work procedures and abnormal behaviors.

[0785] Step 4:

[0786] The server uses the analysis results to identify areas for business efficiency improvement. At this stage, the input is the business pattern obtained in step 3, and the output shows specific business procedures that require optimization. The specific actions include comparing the current data with similar historical data and listing areas where efficiency improvements are expected.

[0787] Step 5:

[0788] The server analyzes the user's emotional state from their facial expressions and voice tone using emotion analysis tools. The input at this stage is the pre-processed data from step 2, and the output is the user's emotion evaluation result. Specifically, the AI ​​model uses facial recognition technology and voice emotion analysis technology to identify what emotional state the user is in.

[0789] Step 6:

[0790] The server uses a generation mechanism to generate feedback based on efficiency points and emotional states. The feedback output generated based on the input from steps 4 and 5 is the improvement suggestions and points of caution provided to the user. Specific actions include the generation AI model utilizing prompts to construct a feedback message appropriate for the user.

[0791] Step 7:

[0792] The terminal notifies the user of feedback sent from the server. The input is the feedback generated in step 6, and the output is a notification or display to the user. Specifically, the notification appears as a pop-up on the screen, and voice confirmation is also possible.

[0793] Step 8:

[0794] The server uses content generation tools to create efficiency proposals and educational videos, making them viewable by users through their terminals. The input for this stage is the information from steps 4 and 6, and the output provides users with specific improvement measures. Specifically, a generation AI model automatically assembles the proposal content and provides it as a visualized resource.

[0795] (Application Example 2)

[0796] 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".

[0797] In today's work environment, achieving efficient and effective work is a crucial challenge for many organizations. However, improving work efficiency requires not only optimizing work processes but also considering the emotional state of employees. Traditional systems, while focusing on work efficiency, have been limited in their ability to generate feedback that takes employees' emotional states into account. Therefore, there is a need for a system that can improve work efficiency while also providing flexible responses that are in line with the emotions of users.

[0798] 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.

[0799] In this invention, the server includes means for acquiring activity video information in the work environment, means for preprocessing the acquired video information to remove noise, means for analyzing work patterns using the preprocessed information and recognizing the patterns, means for identifying areas where the efficiency of the work process can be improved based on the recognized patterns, means for analyzing the emotional state of the user, means for adapting the content of the feedback based on the analyzed emotional state, and means for displaying the generated feedback on a video display device. This makes it possible to improve work efficiency while providing feedback that is tailored to the user's emotions, thereby simultaneously improving the work environment and increasing employee satisfaction.

[0800] The term "work environment" refers to the place where various tasks and activities are carried out within a company or organization, and includes the physical and virtual environments that support those tasks.

[0801] "Activity video information" refers to video data capturing the work and activities performed in the work environment, and is used for analyzing work processes.

[0802] "Noise reduction" is a preprocessing technique that removes unwanted interference information from acquired video and audio data to improve the accuracy of the necessary data.

[0803] "Work patterns" refer to certain regularities or tendencies that are obtained as a result of analyzing combinations of procedures and actions in specific tasks or activities performed in a work environment.

[0804] "Streamlining business processes" refers to improving or redesigning processes to maximize results while reducing the time and resources required for those processes.

[0805] "User emotional state" refers to information indicating the emotional state of employees or operators performing tasks, such as stress levels, satisfaction levels, and concentration levels. This information is analyzed to serve as a reference for improving work processes.

[0806] "Feedback" is information generated based on analyzed work patterns and the emotional state of users, and is provided to users as a means of improving work efficiency and providing solutions for improvement.

[0807] A "video display device" is a device used to visually present acquired feedback information to the user and assist in improving business operations.

[0808] The system for carrying out this invention is configured to integrally process video and audio information of activities in a work environment. The server acquires video and audio information in real time through cameras and microphones within the work environment. The raw data collected from these devices is temporarily stored in storage installed within the server.

[0809] Subsequently, the server preprocesses the video and audio information using a noise reduction algorithm. This process, for example, uses the OpenCV library to clear redundant parts from the video data and reduce unwanted background noise from the audio data.

[0810] The pre-processed information is analyzed by a dedicated AI model. This AI model identifies business patterns based on the initial training data and performs pattern recognition. Based on the recognized business patterns, the server identifies which parts of the business process can be made more efficient.

[0811] Furthermore, the server incorporates an emotion engine that evaluates the user's emotional state by analyzing their facial expressions and tone of voice. Based on this analysis, the feedback is tailored to the user's emotions. The feedback is displayed on a video display device, such as smart glasses worn by the user, and suggestions for efficiency improvements and other areas for improvement are presented in real time.

[0812] For example, when an employee assisting a customer uses this system, they can detect signs of customer dissatisfaction and immediately receive appropriate solutions on the display of their glasses. This can improve customer satisfaction.

[0813] An example of a prompt for a generative AI model is, "Generate feedback suggesting solutions for when a customer expresses dissatisfaction." This prompt allows the AI ​​model to generate appropriate solution-oriented feedback.

[0814] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0815] Step 1:

[0816] The server uses cameras and microphones within the work environment to acquire video and audio information about the activities. The input is raw data from the cameras and microphones, and the output is raw video and audio data stored in storage. In this step, initial processing is performed to properly capture data from the devices and to fully record the activities during work.

[0817] Step 2:

[0818] The server performs noise reduction on the acquired raw data. The input is the raw data saved in step 1, and the output is pre-processed data with reduced noise. In this step, data processing is performed to improve the accuracy of the analysis by clearing the video data and removing unnecessary background noise using libraries such as OpenCV.

[0819] Step 3:

[0820] The server analyzes pre-processed data using an AI model to recognize business patterns. The input is denoised video and audio data, and the output is the recognized business patterns. In this step, data calculations are performed so that the AI ​​model can analyze the data and learn specific behavioral rules and patterns that should be made more efficient.

[0821] Step 4:

[0822] The server identifies areas where efficiency improvements are possible based on recognized business patterns. The input is the pattern recognized in step 3, and the output is information about the business processes that need to be streamlined. In this step, the identified areas are investigated in detail, and preparations are made to propose specific measures for process improvement.

[0823] Step 5:

[0824] The server analyzes the user's emotional state using an emotion engine. The input is the pre-processed video and audio from step 2, and the output is the analyzed emotional state information. In this step, emotions are recognized from the user's facial expressions and voice, and data transformation is performed to reflect these in the feedback.

[0825] Step 6:

[0826] The server generates appropriate feedback based on areas that need improvement and the user's emotional state. The input is the location information from step 4 and the emotional state information from step 5, and the output is the feedback displayed to the user. In this step, a generative AI model is used to generate prompt sentences that create feedback that takes the user's emotions into consideration.

[0827] Step 7:

[0828] The terminal displays the generated feedback on the smart glasses' display. The input is the feedback generated in step 6, and the output is the information presented on the user's visual interface. In this step, the feedback is displayed in real time so that the user can immediately see and implement improvements while working.

[0829] 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.

[0830] 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.

[0831] 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.

[0832] 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.

[0833] 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.

[0834] 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.

[0835] 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.

[0836] 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.

[0837] 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."

[0838] 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.

[0839] 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.

[0840] 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.

[0841] 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.

[0842] 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.

[0843] 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.

[0844] 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.

[0845] 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.

[0846] 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.

[0847] 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.

[0848] 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.

[0849] 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.

[0850] The following is further disclosed regarding the embodiments described above.

[0851] (Claim 1)

[0852] Means for acquiring work video data in the work environment,

[0853] A means of preprocessing acquired video data to remove noise,

[0854] A means for analyzing business patterns using pre-processed data and recognizing those patterns,

[0855] A means to identify areas in business processes where efficiency improvements can be made based on recognized patterns,

[0856] A means of generating real-time feedback on identified areas that can be made more efficient,

[0857] A means of presenting the generated feedback to the user,

[0858] A system including means for generating efficiency improvement proposals and videos.

[0859] (Claim 2)

[0860] The system according to claim 1, which comprehensively analyzes audio data together with video data and converts it into text data.

[0861] (Claim 3)

[0862] The system according to claim 1, comprising a user interface means for the user to display and view the generated proposals and videos.

[0863] "Example 1"

[0864] (Claim 1)

[0865] Means of acquiring data in the work environment,

[0866] A means of preprocessing the acquired data to remove noise,

[0867] A means for analyzing business patterns using pre-processed data and recognizing those patterns,

[0868] A means to identify areas in business processes where efficiency improvements can be made based on recognized patterns,

[0869] A means of generating real-time feedback on identified areas that can be made more efficient,

[0870] A means of presenting the generated feedback to the user,

[0871] A system including means for generating efficiency improvement proposals and visual guides.

[0872] (Claim 2)

[0873] The system according to claim 1, which comprehensively analyzes data and converts it into text data based on the generated analysis results.

[0874] (Claim 3)

[0875] The system according to claim 1, comprising a device for a user to display and view the generated proposal and visual guidance.

[0876] "Application Example 1"

[0877] (Claim 1)

[0878] A means of acquiring video and audio data of work in a work environment,

[0879] A means for preprocessing acquired video and audio data to remove noise,

[0880] A means for analyzing business operation patterns using pre-processed data and recognizing operation patterns,

[0881] A means of identifying areas in business processes where efficiency improvements can be made based on recognized behavioral patterns,

[0882] A means of generating real-time feedback on identified areas where efficiency improvements can be made, and providing workers with information including improvement suggestions,

[0883] A system that includes means for generating efficiency improvement proposals and visual guide videos, and demonstrating methods for optimizing work processes.

[0884] (Claim 2)

[0885] The system according to claim 1, which comprehensively analyzes video data and audio data to identify inefficient operation patterns in a work process and proposes improvements.

[0886] (Claim 3)

[0887] The system according to claim 1, comprising a user interface means for workers to display, view, and receive instruction on generated proposals and visual guide videos.

[0888] "Example 2 of combining an emotion engine"

[0889] (Claim 1)

[0890] Sensing means for acquiring work data in the work environment,

[0891] A data filtering means for preprocessing acquired data to remove noise,

[0892] An AI analysis method for analyzing business procedures using pre-processed data and learning specific patterns,

[0893] An analytical tool for identifying areas for improving the efficiency of business procedures based on learned patterns,

[0894] A generation means for generating real-time feedback based on identified efficiency points,

[0895] A notification mechanism for displaying the generated feedback to the user,

[0896] A system including a content generation means for generating efficiency suggestions and educational materials.

[0897] (Claim 2)

[0898] The system according to claim 1, comprising emotion analysis means for recognizing the emotional state of a user by integrally analyzing video data and audio data.

[0899] (Claim 3)

[0900] The system according to claim 1, comprising a user interface for users to display and view generated proposals and educational materials.

[0901] "Application example 2 when combining with an emotional engine"

[0902] (Claim 1)

[0903] Means for acquiring video information of activities in the work environment,

[0904] A means for preprocessing acquired video information to remove noise,

[0905] A means for analyzing work patterns using pre-processed information and recognizing patterns,

[0906] A means of identifying areas where business processes can be made more efficient based on recognized patterns,

[0907] A means of immediately generating feedback on identified areas where efficiency improvements can be made,

[0908] A means of presenting the generated feedback to the user,

[0909] A means for generating efficiency improvement proposals and video recordings,

[0910] A means of analyzing the emotional state of users,

[0911] A means of adapting the content of the feedback based on the analyzed emotional state,

[0912] A system including means for displaying feedback on a video display device.

[0913] (Claim 2)

[0914] The system according to claim 1, which comprehensively analyzes audio information along with video information and converts it into text information.

[0915] (Claim 3)

[0916] The system according to claim 1, comprising a user interface means for a user to display and view the generated proposal and video recording. [Explanation of Symbols]

[0917] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of acquiring video and audio data of work in a work environment, A means for preprocessing acquired video and audio data to remove noise, A means for analyzing business operation patterns using pre-processed data and recognizing operation patterns, A means of identifying areas in business processes where efficiency improvements can be made based on recognized behavioral patterns, A means of generating real-time feedback on identified areas where efficiency improvements can be made, and providing workers with information including improvement suggestions, A system that includes means for generating efficiency improvement proposals and visual guide videos, and demonstrating methods for optimizing work processes.

2. The system according to claim 1, which comprehensively analyzes video data and audio data to identify inefficient operation patterns in a work process and proposes improvements.

3. The system according to claim 1, comprising a user interface means for workers to display, view, and receive instruction on generated proposals and visual guide videos.

Images