system

Abstract

We provide the system. [Solution] Image acquisition means for recording conditions within the work environment, An analysis means for analyzing the recorded image data to identify the work content, An instruction means that outputs voice instructions to the worker based on the aforementioned analysis results, An evaluation means for evaluating the efficiency of the aforementioned work and generating improvement suggestions, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document  discloses a persona chatbot control method performed by at least one processor, including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of 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

[0006] "Image acquisition means" refers to a device or method for photographing the conditions within the work environment and collecting image data.

[0007] "Analysis means" refers to a device or method that processes acquired image data to identify and analyze the work content.

[0008] "Instruction means" refers to a device or system that provides instructions to an operator in voice or other format based on the analysis results.

[0009] "Evaluation means" refers to a device or system that evaluates the efficiency of work based on analyzed work data and generates improvement measures.

[0010] A "standard operating manual" is a manual consisting of documents, images, and videos created based on analysis data, and it describes standard work procedures. [Brief explanation of the drawing]

[0011] [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] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0012] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0013] First, let's explain the terminology used in the following explanation.

[0014] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0015] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0016] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0017] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), etc.

[0018] 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."

[0019] [First Embodiment]

[0020] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0021] 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.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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.

[0027] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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".

[0032] This invention provides a system for improving the efficiency and standardization of operations in the logistics industry. The system mainly consists of a server, terminals, and users.

[0033] Server operation

[0034] The server collects image data in real time from cameras installed within the warehouse. This image data records the movements of workers and the work environment. The server analyzes the collected image data and uses an AI model to understand the work being done. Specifically, it identifies work events such as picking, packing, and moving. The analysis results are stored in a database and used to evaluate the progress of work and productivity.

[0035] Based on the analysis results, the server generates improvement suggestions to enhance work efficiency. These suggestions include optimizing work flows and reallocating resources. The server also automatically generates standard operating manuals based on the analysis data. This provides an environment where workers can quickly learn new procedures.

[0036] Terminal operation

[0037] The terminal receives analysis results transmitted from the server and provides real-time voice instructions to the worker. These voice instructions clearly communicate the next steps and points to note for the user. The content of the voice instructions is customized according to the work situation and the individual worker's skill level. This enables workers to proceed with their tasks efficiently.

[0038] User actions

[0039] Users perform tasks according to instructions from the terminal. Voice instructions allow them to learn about work procedures and precautions in real time, improving work efficiency and reducing human error. Furthermore, users can standardize their work by referring to standard work manuals, enabling consistent work quality across different workers.

[0040] This system aims to improve the efficiency of logistics operations and enable the maximum utilization of limited human resources.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The server collects image data in real time from cameras installed within the warehouse. The images are captured to cover the entire work environment and sent to the server.

[0044] Step 2:

[0045] The server preprocesses the received image data, performing tasks such as noise reduction and sharpness adjustment. This preprocessing improves the accuracy of the analysis.

[0046] Step 3:

[0047] The server inputs pre-processed image data into a deep learning model to analyze the work performed. Specifically, it identifies work events such as picking, packing, and moving, and records their start and end times.

[0048] Step 4:

[0049] The server stores the work event information obtained through analysis in a database. This includes worker ID, work type, timestamp, and other details.

[0050] Step 5:

[0051] The terminal provides real-time voice assistance to the worker based on the analysis results received from the server. This voice guidance makes it easier for the worker to understand the next steps to take.

[0052] Step 6:

[0053] The user proceeds with the task by following voice instructions from the device. These instructions include points for safety checks and suggestions for improving efficiency.

[0054] Step 7:

[0055] The server analyzes accumulated work data and evaluates productivity and work efficiency. Based on this evaluation, it identifies areas for improvement and proposes specific improvement measures.

[0056] Step 8:

[0057] The server automatically generates a standard operating manual based on the analysis results. The manual visually presents efficient work procedures and important points to note.

[0058] Step 9:

[0059] Users utilize the generated standard operating manuals to standardize their daily tasks. This reduces variations in work and helps maintain consistent work 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] To improve work efficiency, reduce human error, and rapidly standardize work processes in the work environment, it is necessary to accurately understand worker actions in real time and provide optimal instructions. However, conventional systems have shortcomings in terms of accuracy in identifying actions and customization of instructions, and therefore do not adequately respond to the skills of workers or the work environment.

[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 information acquisition means for understanding the situation in the workspace, information analysis means for analyzing the acquired information to identify the work content, and voice output means for providing instructions to the worker based on the analysis results. This makes it possible to analyze the worker's movements in detail and provide appropriate work instructions in real time.

[0065] "Information acquisition means" refers to the processes and devices used to collect information necessary to understand the situation within the workspace.

[0066] "Information analysis means" refers to technologies and methods for identifying and evaluating work content based on acquired information.

[0067] "Voice output means" refers to devices or systems that provide necessary instructions and information to workers via voice based on the analyzed results.

[0068] "Evaluation tools" refer to functions that generate improvement suggestions based on acquired data and analyze the workflow in order to optimize work efficiency.

[0069] "Methods for automatically creating standard operating procedures" refers to a process that automatically generates operating procedures based on data analysis results, aiming to standardize and streamline operations.

[0070] A "generative AI model" refers to a machine learning model that analyzes collected data and understands the nature of the work being done.

[0071] A "prompt" refers to the input text given to a generative AI model to obtain a specific output.

[0072] This invention provides a system in which a server, terminal, and user each play a specific role in order to improve the efficiency and standardization of work within the work environment. This system enables real-time work monitoring, data analysis, and work instructions.

[0073] Server configuration and operation

[0074] The server primarily consists of information acquisition, information analysis, and evaluation means. It collects information from devices such as cameras installed in warehouses and work areas, and the image data is analyzed by a generative AI model using deep learning. This generative AI model identifies the type and progress of work from the collected data and identifies each work event. For example, when the server identifies an action such as "taking an item from a shelf," it classifies it as "picking." The analysis results are stored in a database, and improvement suggestions are generated based on this data. An example of a prompt is "Propose ways to improve the efficiency of logistics operations."

[0075] Terminal configuration and operation

[0076] The terminal generates voice instructions based on analysis data sent from the server and provides them to the user. Using speech synthesis technology, the instructions created from the analysis results are conveyed to the user in natural language. A concrete example of such instructions might be, "Please pick the next item from shelf B."

[0077] User configuration and behavior

[0078] Users efficiently perform tasks by following real-time instructions from their terminals. By referring to standard operating procedures provided by the system, tasks can be standardized. This allows users to quickly learn new operating procedures while maintaining work quality.

[0079] The introduction of this system will improve work efficiency and productivity by reviewing existing work processes and automatically generating optimized work flows. An example of a prompt sentence to be input into the generating AI model is, "List the improvements needed to improve work efficiency."

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

[0081] Step 1:

[0082] The server acquires image data in real time from cameras installed within the work environment. The input camera footage shows the movements of workers and the work environment. The server converts the format and adjusts the resolution of this video data, preparing it for input into the generated AI model. Specifically, the server extracts important scenes, selects frames with significant movement, and supplies them to the next process.

[0083] Step 2:

[0084] The server inputs image data into a generating AI model and analyzes the work performed. The model extracts features from the input data and applies machine learning algorithms to classify each action. The output is an analysis result that shows what kind of work events are taking place. For example, the server recognizes the action of "taking an item from a shelf" as "picking" and generates an event list.

[0085] Step 3:

[0086] The server generates improvement suggestions based on the analysis results. The analysis data is input to the AI ​​model along with the prompt message "Propose ways to improve the efficiency of logistics operations," and the output is improved work flow suggestions. Specifically, the server compiles suggestions such as shortening movement paths and revising work procedures into a suggestion list.

[0087] Step 4:

[0088] The terminal generates voice output based on improvement suggestions and work instructions sent from the server. The input instruction data is converted into voice using speech synthesis technology. The output is specific work instructions for the user. Specifically, the terminal generates a voice message such as, "Next, take inventory of the items on shelf B," and conveys it to the user.

[0089] Step 5:

[0090] The user performs the actual task by following voice instructions from the terminal. Any problems or insights gained during the task are input as feedback to the server via the terminal. As output, the server updates the database in real time and reflects this in the next analysis and instruction generation. For example, the user reports that "the location of the specified product is incorrect," and this information is shared throughout the entire system.

[0091] (Application Example 1)

[0092] 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."

[0093] The logistics industry is facing a need to improve operational efficiency and reduce variations in quality. In particular, it is necessary to improve work efficiency and accuracy by providing optimal work instructions tailored to individual workers in real time. However, conventional systems struggle to flexibly adapt to changes in worker skills and warehouse environments, leaving room for improvement.

[0094] 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.

[0095] In this invention, the server includes sensor acquisition means for recording conditions within the work environment, data analysis means for analyzing the recorded data to identify the work content, and instruction output means for outputting voice and visual instructions to the worker based on the analysis results. This makes it possible to grasp the work situation in real time and provide optimal work instructions tailored to each individual worker.

[0096] A "sensor acquisition means" is a means used to record the conditions within the work environment in real time.

[0097] "Data analysis means" refers to methods for analyzing recorded data to identify specific work content or situations.

[0098] "Instruction output means" refers to means for providing instructions to the worker via voice or visual means based on the analysis results.

[0099] "Performance evaluation methods" are means for evaluating work efficiency and generating improvement suggestions based on the results.

[0100] A "device" is a device that transmits data to a server in real time and presents instructions visually.

[0101] The specific system for implementing this invention is as follows:

[0102] The server acquires data from sensors installed within the work environment. This data includes detailed information about the worker's movements and the work environment. The server uses "data analysis tools" to analyze this data and identify specific work events. Specifically, it uses an AI model to identify events such as picking and packing, and evaluates efficiency based on the analysis results.

[0103] The server generates improvement suggestions to enhance work efficiency based on the evaluation results. These suggestions include optimizing work flow and appropriate resource allocation, and also function as instructional materials for the work site. Furthermore, it supports work standardization by automatically generating standardized work guidelines based on the analysis data.

[0104] The terminal device receives instructions sent from the server and outputs instructions to the worker via voice or visual means. This allows the worker to proceed with their work efficiently and contributes to reducing human error. Smart glasses are expected to be used as the device, monitoring the progress of the work in real time and feeding that information back to the server.

[0105] As a concrete example, imagine a scenario where a warehouse worker receives instructions via smart glasses, such as "Please select the next item to pack," and visual guidelines are displayed. This allows the worker to check the information without using their hands, enabling them to perform their tasks more smoothly.

[0106] An example of a prompt message given to the AI ​​model is, "Analyze the movements of all workers in the image and generate the next work step." This allows the data analysis tool to suggest the most suitable task.

[0107] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0108] Step 1:

[0109] The server collects data from sensors in the work environment. This data includes images of the worker's movements and the environment. Upon receiving this input data, the server not only stores it but also uses it as material for the next analysis step.

[0110] Step 2:

[0111] The server analyzes the collected data using a "data analysis tool." Specifically, it uses an AI model to extract specific work events from image data and identify the progress of the work for each event. The input for this data analysis is the image data acquired in step 1, and the output is the identified work content.

[0112] Step 3:

[0113] The server evaluates work efficiency based on the analysis results and generates improvement suggestions. Specifically, it makes suggestions such as optimizing work flows and reallocating resources. In this step, the evaluated procedures and results are saved to a database, and the suggestions are generated as output.

[0114] Step 4:

[0115] The terminal device receives instruction data transmitted from the server and outputs audio and visual instructions to the worker. Based on this input data, the worker can confirm efficient work procedures in real time, and the next action to be taken is clearly indicated as output.

[0116] Step 5:

[0117] The user, acting as the worker, performs each task based on instructions from the device. In this step, actions are carried out according to specific work procedures, improving work efficiency. The user's reactions are input into the next data collection and used in the overall system feedback loop.

[0118] 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.

[0119] This invention provides a system for improving worker efficiency and safety in logistics and manufacturing work environments. The system combines image acquisition means for recording work status, analysis means for analyzing image data to identify work content, instruction means for outputting voice instructions to workers based on the analysis results, and evaluation means for evaluating work efficiency and generating improvement suggestions. Furthermore, by incorporating an emotion engine for recognizing workers' emotions, the system enables more nuanced management of the entire work environment.

[0120] Server operation

[0121] The server continuously acquires video footage from cameras installed in the warehouse and processes the data using analytical tools. This analysis allows the server to understand what actions workers are taking and what stage of work they are in. The server also analyzes the workers' facial expressions based on the acquired video data and uses an emotion engine to identify their emotional state. Based on this state, the server evaluates work efficiency and generates improvement suggestions if necessary.

[0122] Terminal operation

[0123] The terminal receives analysis results from the server and provides necessary voice instructions to the worker. These voice instructions are flexibly adjusted according to the worker's emotional state and can include content that alleviates stress or increases motivation. For example, if the worker is feeling tired or stressed, it can suggest a temporary break. In this way, the terminal supports an environment in which workers can work comfortably.

[0124] User actions

[0125] Users proceed with their tasks by following voice instructions provided by the device. These voice instructions clearly indicate the next step, allowing users to concentrate on their work. Furthermore, feedback from an emotional engine enables users to objectively assess their own state and adjust their work pace as needed.

[0126] This system improves operational efficiency in logistics sites and reduces the psychological and physical burden on workers. Ultimately, it aims to increase overall organizational productivity and provide a healthier work environment.

[0127] The following describes the processing flow.

[0128] Step 1:

[0129] The server collects video data from multiple cameras installed within the warehouse. The video covers the work area and captures not only the movements of the workers but also the surrounding environment.

[0130] Step 2:

[0131] The server preprocesses the collected video data and extracts the necessary parts. Preprocessing includes noise reduction and brightness adjustment. During this process, data unnecessary for analysis is removed.

[0132] Step 3:

[0133] The server inputs pre-processed data into the analysis system to identify the work content. Using an AI algorithm, the type of work and its progress are analyzed in real time. The analysis results are stored in a database.

[0134] Step 4:

[0135] The server uses an emotion engine to analyze the worker's facial expression data and identify their emotional state. It uses facial recognition technology to identify emotions such as joy, surprise, anger, sadness, and fatigue.

[0136] Step 5:

[0137] The terminal provides voice instructions to the worker based on analysis results sent from the server. The voice instructions are adjusted according to the worker's emotional state; for example, a worker experiencing stress will receive instructions in a calm tone and receive words of encouragement.

[0138] Step 6:

[0139] Users perform tasks while listening to voice instructions from the terminal. The instructions include work procedures and precautions, allowing workers to efficiently complete tasks based on these instructions.

[0140] Step 7:

[0141] The server generates work efficiency evaluations and improvement suggestions based on the analyzed data. The evaluation includes the user's work speed, accuracy, and emotional state, and these data are combined to suggest improvement measures.

[0142] Step 8:

[0143] The server automatically generates standard operating manuals and provides them to users via terminals or other media. The manuals clearly explain efficient work procedures, allowing workers to refer to them while continuing their tasks.

[0144] Step 9:

[0145] Users refer to standard operating manuals to optimize their own work. This prevents variations in work and maintains consistent work quality.

[0146] (Example 2)

[0147] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0148] In logistics and manufacturing work environments, there is a need to improve worker efficiency and safety, as well as to recognize workers' emotional states and optimize instructions accordingly. However, current systems cannot provide instructions that take workers' emotional states into account, making it difficult to provide an efficient work environment. As a result, the improvement in work efficiency and reduction of worker burden are not being fully achieved, which is a challenge.

[0149] 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.

[0150] In this invention, the server includes an image acquisition means for recording the conditions within the work environment, an analysis means for analyzing the recorded image data to identify the work content, and an emotion recognition means for analyzing the worker's facial expressions to identify their emotional state. This makes it possible to optimize voice instructions according to the worker's emotional state, thereby improving work efficiency and reducing the burden on the worker.

[0151] "Image acquisition means" refers to devices or groups of devices installed to record conditions within the work environment, and includes cameras and sensors.

[0152] "Analysis means" refers to software or algorithms that process recorded image data to identify the work content and detect work progress and anomalies.

[0153] "Instruction means" refers to devices or software that output instructions to workers, either verbally or visually, based on the analyzed data.

[0154] "Emotion recognition means" refers to algorithms and software that analyze a worker's facial expressions and behavior to identify their current emotional state.

[0155] "Evaluation means" refers to processes and systems for measuring work efficiency based on analysis results and emotional states, and for generating improvement suggestions when necessary.

[0156] This invention is a system aimed at improving work efficiency and safety in logistics and manufacturing sites. By having servers, terminals, and users cooperate to monitor and improve the work environment, it enables smoother and more efficient operations.

[0157] Server Role

[0158] The server acquires video data in real time from network-enabled cameras installed within the work environment. AI image analysis software (e.g., OpenCV or TENSORFLOW®) is used to analyze the video data and identify the worker's actions and stage. The server also analyzes the worker's facial expressions from the same video data and uses emotion recognition tools (e.g., emotion recognition APIs) to identify the worker's emotional state. Based on this information, the server evaluates work efficiency and generates improvement suggestions as needed. These suggestions may utilize a generative AI model, and optimization is performed during the data processing process.

[0159] Terminal role

[0160] The terminal receives data from the server and uses speech synthesis software (e.g., speech synthesis API) to provide voice instructions to the worker. These voice instructions are customized according to the worker's emotional state, aiming to increase motivation or reduce stress. For example, if the worker is tired, it can give specific instructions such as, "I recommend you take a short break."

[0161] User roles

[0162] Users proceed with their work by following instructions from the terminal. The instructions clearly indicate the next steps, making it easier for users to concentrate on their work. Furthermore, feedback allows users to understand their mental and physical state and adjust their work pace as needed. This maximizes work efficiency while reducing the burden on the worker.

[0163] As a concrete example, consider the case where this system is implemented in a logistics center. If the server monitors and the emotion recognition system determines that a worker is feeling fatigued from carrying heavy loads, the terminal will tell the worker to "slow down your work pace and take a break." This allows the worker to continue their work without overexerting themselves.

[0164] An example of a prompt to input into the generating AI model is, "Please suggest a method for generating optimal work instructions that take into account the emotional state of the worker."

[0165] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0166] Step 1:

[0167] The server acquires real-time video data from network-enabled cameras within the warehouse. The input is a video stream from the cameras, which the server temporarily records. Specifically, the operation here involves capturing video from the camera device and storing it as digital data within the server.

[0168] Step 2:

[0169] The server analyzes the acquired video data using AI image analysis software. The input is the recorded video data, and the output is the analysis results, including worker movements and location information. This analysis can identify what movements the worker is performing and which stage of work they are in. Specifically, this involves using an image recognition algorithm to detect the worker's movements in each frame and storing the data in a database.

[0170] Step 3:

[0171] The server analyzes the worker's facial expressions from the same video data and identifies their emotional state using emotion recognition technology. The input is again video data, and the output is an evaluation of the worker's emotional state. In this step, facial recognition technology is used to analyze the worker's facial expressions and infer psychological states such as fatigue and stress. Specifically, an emotion recognition API is called to generate an emotion score, which is then fed back to the system.

[0172] Step 4:

[0173] The server evaluates work efficiency based on analysis results and emotional state, and generates improvement suggestions if necessary using a generative AI model. The input is the action analysis results and emotional evaluation, and the output is the improvement suggestions. In this step, current work performance is evaluated in comparison to past data, and optimized suggestions are created by the generative AI model. Specifically, the data is input to the generative AI model as prompt sentences, and suggestions are output.

[0174] Step 5:

[0175] The terminal receives analysis results and improvement suggestions from the server and provides voice instructions to the worker using speech synthesis software. The input is the analysis results and improvement suggestions, and the output is voice instructions. In this step, a speech synthesis API is used to generate speech in a pre-configured language and output it through the speaker. Specifically, it provides real-time instructions to the worker, such as "Please proceed to the next step."

[0176] Step 6:

[0177] The user proceeds with the task by following the voice instructions provided by the terminal. The input is the voice instructions from the terminal, and the output is the execution of the task. The user listens to the instructions, confirms the next action, and then actually performs the task. Specific actions include moving objects or operating equipment based on the instructions.

[0178] (Application Example 2)

[0179] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0180] In logistics and manufacturing, the challenge lies in improving worker efficiency while reducing psychological and physical burden during work, thereby creating a safe and comfortable working environment. In particular, there is a need to develop systems that appropriately assess worker fatigue and stress, and provide instructions that consider both work efficiency and worker health maintenance.

[0181] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0182] In this invention, the server includes: information acquisition means for recording the conditions within the work environment; analysis means for analyzing the recorded information data to identify the work content; instruction means for outputting voice instructions to the worker and visually displaying the worker's state based on the analysis results; evaluation means for evaluating the efficiency of the work and generating improvement suggestions; and emotion recognition means for identifying the worker's emotions from the information data. This makes it possible to analyze the worker's actions and emotional state in real time and flexibly provide individual work instructions and appropriate break suggestions.

[0183] "Information acquisition means" refers to devices or functions for recording the conditions of the work environment as digital data.

[0184] "Analysis means" refers to the technology and functions used to process recorded information data in detail and identify the content of the work.

[0185] A "command system" is a system that provides workers with necessary information visually and audibly based on analysis results, with the aim of improving work efficiency.

[0186] An "evaluation tool" is a function that quantitatively or qualitatively assesses the efficiency of work and generates suggestions for areas that need improvement.

[0187] "Emotion recognition means" refers to technology that analyzes information data to understand the emotional state of workers by analyzing their facial expressions and gestures.

[0188] To implement this invention, it is necessary to build a system that utilizes wearable devices such as smart glasses in logistics centers and manufacturing sites. The specific method is described below.

[0189] The server records the worker's movements through information acquisition devices installed in the work environment. These devices include cameras and sensors. This data is transmitted to the server and processed by analysis tools. Specifically, image analysis software (e.g., OpenCV) is used to identify the worker's movements and location. Additionally, emotion recognition AI (e.g., Azure® Emotion API) is used to determine the worker's emotional state.

[0190] The smart glasses, acting as a terminal, receive analysis results from a server, output appropriate voice instructions to the worker, and display information on the screen. These instructions not only maximize work efficiency but also offer suggestions for breaks based on the worker's emotional state. The voice instruction function uses speech synthesis technology (e.g., Google® Text-to-Speech). The specific operating procedures are adjusted to help the worker efficiently move to the next step while reducing excessive burden.

[0191] Users can follow visual and audio instructions from smart glasses to complete their tasks. This improves work efficiency and allows them to objectively understand their own emotional state and adjust their work pace as needed.

[0192] As a concrete example, in a logistics center, workers stand on the packing line and are instructed on the location and quantity of the next product to pick up through smart glasses. Furthermore, if a worker shows signs of fatigue, a break is automatically suggested immediately. This ensures both smooth workflow and the health management of the workers.

[0193] Example prompts for generative AI models:

[0194] "Please develop a smart glasses app to improve work efficiency in logistics centers. It should analyze workers' movements and emotions in real time, providing voice instructions and visual information as needed. Additionally, it should suggest breaks if it detects fatigue or stress in workers."

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

[0196] Step 1:

[0197] The server acquires video data of the work environment through information acquisition devices. The input is real-time video data obtained from cameras and sensors, which is stored in a database. The server then prepares this data for the next step.

[0198] Step 2:

[0199] The server processes the acquired video data using an analysis tool. The input is the video data acquired in step 1, and image analysis software such as OpenCV is used to identify the worker's movements and location information. The output is the analyzed movement information, with the data structured.

[0200] Step 3:

[0201] The server analyzes the worker's emotions using emotion recognition technology. The input is the same video data acquired in step 1, and the Azure Emotion API is used to determine the emotional state from the facial expressions. The output is data on the worker's emotional state.

[0202] Step 4:

[0203] Based on the analysis results, the server generates appropriate instructions for the worker via a control device. The input is the output from steps 2 and 3. Voice instructions are created using Google Text-to-Speech, and visual information is displayed on the smart glasses display. The output is provided to the worker as both voice instructions and visual information.

[0204] Step 5:

[0205] The smart glasses, acting as a terminal, receive instructions from the server and present them to the worker. Input consists of voice instructions and visual information transmitted from the server. The smart glasses play the audio through a speaker and display the information on a screen. Output is a user-friendly interface that is easy for the worker to understand.

[0206] Step 6:

[0207] The user follows instructions from the terminal to complete the task. Input consists of voice instructions and visual information provided by smart glasses. Based on this, the user improves the efficiency of the task by executing the specified procedures. The output is the realization of efficient and safe work.

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

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

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

[0211] [Second Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0224] This invention provides a system for improving the efficiency and standardization of operations in the logistics industry. The system mainly consists of a server, terminals, and users.

[0225] Server operation

[0226] The server collects image data in real time from cameras installed within the warehouse. This image data records the movements of workers and the work environment. The server analyzes the collected image data and uses an AI model to understand the work being done. Specifically, it identifies work events such as picking, packing, and moving. The analysis results are stored in a database and used to evaluate the progress of work and productivity.

[0227] Based on the analysis results, the server generates improvement suggestions to enhance work efficiency. These suggestions include optimizing work flows and reallocating resources. The server also automatically generates standard operating manuals based on the analysis data. This provides an environment where workers can quickly learn new procedures.

[0228] Terminal operation

[0229] The terminal receives analysis results transmitted from the server and provides real-time voice instructions to the worker. These voice instructions clearly communicate the next steps and points to note for the user. The content of the voice instructions is customized according to the work situation and the individual worker's skill level. This enables workers to proceed with their tasks efficiently.

[0230] User actions

[0231] Users perform tasks according to instructions from the terminal. Voice instructions allow them to learn about work procedures and precautions in real time, improving work efficiency and reducing human error. Furthermore, users can standardize their work by referring to standard work manuals, enabling consistent work quality across different workers.

[0232] This system aims to improve the efficiency of logistics operations and enable the maximum utilization of limited human resources.

[0233] The following describes the processing flow.

[0234] Step 1:

[0235] The server collects image data in real time from cameras installed within the warehouse. The images are captured to cover the entire work environment and sent to the server.

[0236] Step 2:

[0237] The server preprocesses the received image data, performing tasks such as noise reduction and sharpness adjustment. This preprocessing improves the accuracy of the analysis.

[0238] Step 3:

[0239] The server inputs pre-processed image data into a deep learning model to analyze the work performed. Specifically, it identifies work events such as picking, packing, and moving, and records their start and end times.

[0240] Step 4:

[0241] The server stores the work event information obtained through analysis in a database. This includes worker ID, work type, timestamp, and other details.

[0242] Step 5:

[0243] The terminal provides real-time voice assistance to the worker based on the analysis results received from the server. This voice guidance makes it easier for the worker to understand the next steps to take.

[0244] Step 6:

[0245] The user proceeds with the task by following voice instructions from the device. These instructions include points for safety checks and suggestions for improving efficiency.

[0246] Step 7:

[0247] The server analyzes accumulated work data and evaluates productivity and work efficiency. Based on this evaluation, it identifies areas for improvement and proposes specific improvement measures.

[0248] Step 8:

[0249] The server automatically generates a standard operating manual based on the analysis results. The manual visually presents efficient work procedures and important points to note.

[0250] Step 9:

[0251] Users utilize the generated standard operating manuals to standardize their daily tasks. This reduces variations in work and helps maintain consistent work quality.

[0252] (Example 1)

[0253] 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."

[0254] To improve work efficiency, reduce human error, and rapidly standardize work processes in the work environment, it is necessary to accurately understand worker actions in real time and provide optimal instructions. However, conventional systems have shortcomings in terms of accuracy in identifying actions and customization of instructions, and therefore do not adequately respond to the skills of workers or the work environment.

[0255] 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.

[0256] In this invention, the server includes information acquisition means for understanding the situation in the workspace, information analysis means for analyzing the acquired information to identify the work content, and voice output means for providing instructions to the worker based on the analysis results. This makes it possible to analyze the worker's movements in detail and provide appropriate work instructions in real time.

[0257] "Information acquisition means" refers to the processes and devices used to collect information necessary to understand the situation within the workspace.

[0258] "Information analysis means" refers to technologies and methods for identifying and evaluating work content based on acquired information.

[0259] "Voice output means" refers to devices or systems that provide necessary instructions and information to workers via voice based on the analyzed results.

[0260] "Evaluation tools" refer to functions that generate improvement suggestions based on acquired data and analyze the workflow in order to optimize work efficiency.

[0261] "Methods for automatically creating standard operating procedures" refers to a process that automatically generates operating procedures based on data analysis results, aiming to standardize and streamline operations.

[0262] A "generative AI model" refers to a machine learning model that analyzes collected data and understands the nature of the work being done.

[0263] A "prompt" refers to the input text given to a generative AI model to obtain a specific output.

[0264] This invention provides a system in which a server, terminal, and user each play a specific role in order to improve the efficiency and standardization of work within the work environment. This system enables real-time work monitoring, data analysis, and work instructions.

[0265] Server configuration and operation

[0266] The server primarily consists of information acquisition, information analysis, and evaluation means. It collects information from devices such as cameras installed in warehouses and work areas, and the image data is analyzed by a generative AI model using deep learning. This generative AI model identifies the type and progress of work from the collected data and identifies each work event. For example, when the server identifies an action such as "taking an item from a shelf," it classifies it as "picking." The analysis results are stored in a database, and improvement suggestions are generated based on this data. An example of a prompt is "Propose ways to improve the efficiency of logistics operations."

[0267] Terminal configuration and operation

[0268] The terminal generates voice instructions based on analysis data sent from the server and provides them to the user. Using speech synthesis technology, the instructions created from the analysis results are conveyed to the user in natural language. A concrete example of such instructions might be, "Please pick the next item from shelf B."

[0269] User configuration and behavior

[0270] Users efficiently perform tasks by following real-time instructions from their terminals. By referring to standard operating procedures provided by the system, tasks can be standardized. This allows users to quickly learn new operating procedures while maintaining work quality.

[0271] The introduction of this system will improve work efficiency and productivity by reviewing existing work processes and automatically generating optimized work flows. An example of a prompt sentence to be input into the generating AI model is, "List the improvements needed to improve work efficiency."

[0272] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0273] Step 1:

[0274] The server acquires image data in real time from cameras installed within the work environment. The input camera footage shows the movements of workers and the work environment. The server converts the format and adjusts the resolution of this video data, preparing it for input into the generated AI model. Specifically, the server extracts important scenes, selects frames with significant movement, and supplies them to the next process.

[0275] Step 2:

[0276] The server inputs image data into a generating AI model and analyzes the work performed. The model extracts features from the input data and applies machine learning algorithms to classify each action. The output is an analysis result that shows what kind of work events are taking place. For example, the server recognizes the action of "taking an item from a shelf" as "picking" and generates an event list.

[0277] Step 3:

[0278] The server generates improvement suggestions based on the analysis results. The analysis data is input to the AI ​​model along with the prompt message "Propose ways to improve the efficiency of logistics operations," and the output is improved work flow suggestions. Specifically, the server compiles suggestions such as shortening movement paths and revising work procedures into a suggestion list.

[0279] Step 4:

[0280] The terminal generates voice output based on improvement suggestions and work instructions sent from the server. The input instruction data is converted into voice using speech synthesis technology. The output is specific work instructions for the user. Specifically, the terminal generates a voice message such as, "Next, take inventory of the items on shelf B," and conveys it to the user.

[0281] Step 5:

[0282] The user executes actual operations according to voice instructions from the terminal. The problems and findings arising from the operations are input as feedback to the server through the terminal. As output, the server updates the database in real time and reflects it in the next analysis and instruction generation. As a specific operation, the user reports that "there is a deviation in the position of the specified product", and that information is shared throughout the system.

[0283] (Application Example 1)

[0284] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0285] There is a need to improve the efficiency of operations and reduce the variation in quality in the logistics industry. In particular, it is necessary to improve work efficiency and accuracy by providing optimal work instructions in real time according to individual workers. However, in conventional systems, it is difficult to flexibly respond to changes in the skills of workers and the warehouse environment, and there is room for improvement.

[0286] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following respective means.

[0287] In this invention, the server includes a sensor acquisition means for recording the situation in the work environment, a data analysis means for analyzing the recorded data to identify the work content, and an instruction output means for outputting voice and visual instructions to the worker based on the analysis result. As a result, it becomes possible to grasp the work situation in real time and provide optimal work instructions tailored to individual workers.

[0288] The "sensor acquisition means" is a means used to record the situation in the work environment in real time.

[0289] The "data analysis means" is a means for analyzing the recorded data to identify specific work content and situations.

[0290] "Instruction output means" refers to means for providing instructions to the worker via voice or visual means based on the analysis results.

[0291] "Performance evaluation methods" are means for evaluating work efficiency and generating improvement suggestions based on the results.

[0292] A "device" is a device that transmits data to a server in real time and presents instructions visually.

[0293] The specific system for implementing this invention is as follows:

[0294] The server acquires data from sensors installed within the work environment. This data includes detailed information about the worker's movements and the work environment. The server uses "data analysis tools" to analyze this data and identify specific work events. Specifically, it uses an AI model to identify events such as picking and packing, and evaluates efficiency based on the analysis results.

[0295] The server generates improvement suggestions to enhance work efficiency based on the evaluation results. These suggestions include optimizing work flow and appropriate resource allocation, and also function as instructional materials for the work site. Furthermore, it supports work standardization by automatically generating standardized work guidelines based on the analysis data.

[0296] The terminal device receives instructions sent from the server and outputs instructions to the worker via voice or visual means. This allows the worker to proceed with their work efficiently and contributes to reducing human error. Smart glasses are expected to be used as the device, monitoring the progress of the work in real time and feeding that information back to the server.

[0297] As a concrete example, imagine a scenario where a warehouse worker receives instructions via smart glasses, such as "Please select the next item to pack," and visual guidelines are displayed. This allows the worker to check the information without using their hands, enabling them to perform their tasks more smoothly.

[0298] An example of a prompt message given to the AI ​​model is, "Analyze the movements of all workers in the image and generate the next work step." This allows the data analysis tool to suggest the most suitable task.

[0299] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0300] Step 1:

[0301] The server collects data from sensors in the work environment. This data includes images of the worker's movements and the environment. Upon receiving this input data, the server not only stores it but also uses it as material for the next analysis step.

[0302] Step 2:

[0303] The server analyzes the collected data using a "data analysis tool." Specifically, it uses an AI model to extract specific work events from image data and identify the progress of the work for each event. The input for this data analysis is the image data acquired in step 1, and the output is the identified work content.

[0304] Step 3:

[0305] The server evaluates work efficiency based on the analysis results and generates improvement suggestions. Specifically, it makes suggestions such as optimizing work flows and reallocating resources. In this step, the evaluated procedures and results are saved to a database, and the suggestions are generated as output.

[0306] Step 4:

[0307] A device as a terminal receives the instruction data sent from the server and outputs voice and visual instructions to the operator. Based on this input data, the operator can confirm an efficient work procedure in real time, and the actions to be taken next are explicitly shown as the output.

[0308] · Step 5:

[0309] The operator, who is the user, executes each task based on the instructions from the device. In this step, operations are carried out according to specific work procedures, and work efficiency is improved. The user's reaction is input into the next data collection and utilized in the feedback loop of the entire system.

[0310] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion recognition model 59 and perform specific processing using the user's emotion.

[0311] This invention provides a system for improving the efficiency and safety of operators in a work environment of logistics and manufacturing. This invention is a system that combines an image acquisition means for recording the work situation, an analysis means for analyzing the image data to identify the work content, an instruction means for outputting voice instructions to the operator based on the analysis result, and an evaluation means for evaluating the work efficiency and generating improvement proposals. Furthermore, by combining an emotion engine for recognizing the operator's emotion, it is possible to manage the entire work environment more delicately.

[0312] Operation of the server

[0313] The server continuously acquires video footage from cameras installed in the warehouse and processes the data using analytical tools. This analysis allows the server to understand what actions workers are taking and what stage of work they are in. The server also analyzes the workers' facial expressions based on the acquired video data and uses an emotion engine to identify their emotional state. Based on this state, the server evaluates work efficiency and generates improvement suggestions if necessary.

[0314] Terminal operation

[0315] The terminal receives analysis results from the server and provides necessary voice instructions to the worker. These voice instructions are flexibly adjusted according to the worker's emotional state and can include content that alleviates stress or increases motivation. For example, if the worker is feeling tired or stressed, it can suggest a temporary break. In this way, the terminal supports an environment in which workers can work comfortably.

[0316] User actions

[0317] Users proceed with their tasks by following voice instructions provided by the device. These voice instructions clearly indicate the next step, allowing users to concentrate on their work. Furthermore, feedback from an emotional engine enables users to objectively assess their own state and adjust their work pace as needed.

[0318] This system improves operational efficiency in logistics sites and reduces the psychological and physical burden on workers. Ultimately, it aims to increase overall organizational productivity and provide a healthier work environment.

[0319] The following describes the processing flow.

[0320] Step 1:

[0321] The server collects video data from multiple cameras installed within the warehouse. The video covers the work area and captures not only the movements of the workers but also the surrounding environment.

[0322] Step 2:

[0323] The server preprocesses the collected video data and extracts the necessary parts. Preprocessing includes noise reduction and brightness adjustment. During this process, data unnecessary for analysis is removed.

[0324] Step 3:

[0325] The server inputs pre-processed data into the analysis system to identify the work content. Using an AI algorithm, the type of work and its progress are analyzed in real time. The analysis results are stored in a database.

[0326] Step 4:

[0327] The server uses an emotion engine to analyze the worker's facial expression data and identify their emotional state. It uses facial recognition technology to identify emotions such as joy, surprise, anger, sadness, and fatigue.

[0328] Step 5:

[0329] The terminal provides voice instructions to the worker based on analysis results sent from the server. The voice instructions are adjusted according to the worker's emotional state; for example, a worker experiencing stress will receive instructions in a calm tone and receive words of encouragement.

[0330] Step 6:

[0331] Users perform tasks while listening to voice instructions from the terminal. The instructions include work procedures and precautions, allowing workers to efficiently complete tasks based on these instructions.

[0332] Step 7:

[0333] The server generates work efficiency evaluations and improvement suggestions based on the analyzed data. The evaluation includes the user's work speed, accuracy, and emotional state, and these data are combined to suggest improvement measures.

[0334] Step 8:

[0335] The server automatically generates standard operating manuals and provides them to users via terminals or other media. The manuals clearly explain efficient work procedures, allowing workers to refer to them while continuing their tasks.

[0336] Step 9:

[0337] Users refer to standard operating manuals to optimize their own work. This prevents variations in work and maintains consistent work quality.

[0338] (Example 2)

[0339] 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".

[0340] In logistics and manufacturing work environments, there is a need to improve worker efficiency and safety, as well as to recognize workers' emotional states and optimize instructions accordingly. However, current systems cannot provide instructions that take workers' emotional states into account, making it difficult to provide an efficient work environment. As a result, the improvement in work efficiency and reduction of worker burden are not being fully achieved, which is a challenge.

[0341] 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.

[0342] In this invention, the server includes an image acquisition means for recording the conditions within the work environment, an analysis means for analyzing the recorded image data to identify the work content, and an emotion recognition means for analyzing the worker's facial expressions to identify their emotional state. This makes it possible to optimize voice instructions according to the worker's emotional state, thereby improving work efficiency and reducing the burden on the worker.

[0343] "Image acquisition means" refers to devices or groups of devices installed to record conditions within the work environment, and includes cameras and sensors.

[0344] "Analysis means" refers to software or algorithms that process recorded image data to identify the work content and detect work progress and anomalies.

[0345] "Instruction means" refers to devices or software that output instructions to workers, either verbally or visually, based on the analyzed data.

[0346] "Emotion recognition means" refers to algorithms and software that analyze a worker's facial expressions and behavior to identify their current emotional state.

[0347] "Evaluation means" refers to processes and systems for measuring work efficiency based on analysis results and emotional states, and for generating improvement suggestions when necessary.

[0348] This invention is a system aimed at improving work efficiency and safety in logistics and manufacturing sites. By having servers, terminals, and users cooperate to monitor and improve the work environment, it enables smoother and more efficient operations.

[0349] Server Role

[0350] The server acquires video data in real time from network-enabled cameras installed within the work environment. AI image analysis software (e.g., OpenCV or TensorFlow) is used to analyze the video data and identify the worker's actions and stage. The server also analyzes the worker's facial expressions from the same video data and uses emotion recognition tools (e.g., emotion recognition APIs) to identify the worker's emotional state. Based on this information, the server evaluates work efficiency and generates improvement suggestions as needed. These suggestions may utilize a generative AI model, and optimization is performed during the data processing process.

[0351] Terminal role

[0352] The terminal receives data from the server and uses speech synthesis software (e.g., speech synthesis API) to provide voice instructions to the worker. These voice instructions are customized according to the worker's emotional state, aiming to increase motivation or reduce stress. For example, if the worker is tired, it can give specific instructions such as, "I recommend you take a short break."

[0353] User roles

[0354] Users proceed with their work by following instructions from the terminal. The instructions clearly indicate the next steps, making it easier for users to concentrate on their work. Furthermore, feedback allows users to understand their mental and physical state and adjust their work pace as needed. This maximizes work efficiency while reducing the burden on the worker.

[0355] As a concrete example, consider the case where this system is implemented in a logistics center. If the server monitors and the emotion recognition system determines that a worker is feeling fatigued from carrying heavy loads, the terminal will tell the worker to "slow down your work pace and take a break." This allows the worker to continue their work without overexerting themselves.

[0356] An example of a prompt to input into the generating AI model is, "Please suggest a method for generating optimal work instructions that take into account the emotional state of the worker."

[0357] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0358] Step 1:

[0359] The server acquires real-time video data from network-enabled cameras within the warehouse. The input is a video stream from the cameras, which the server temporarily records. Specifically, the operation here involves capturing video from the camera device and storing it as digital data within the server.

[0360] Step 2:

[0361] The server analyzes the acquired video data using AI image analysis software. The input is the recorded video data, and the output is the analysis results, including worker movements and location information. This analysis can identify what movements the worker is performing and which stage of work they are in. Specifically, this involves using an image recognition algorithm to detect the worker's movements in each frame and storing the data in a database.

[0362] Step 3:

[0363] The server analyzes the worker's facial expressions from the same video data and identifies their emotional state using emotion recognition technology. The input is again video data, and the output is an evaluation of the worker's emotional state. In this step, facial recognition technology is used to analyze the worker's facial expressions and infer psychological states such as fatigue and stress. Specifically, an emotion recognition API is called to generate an emotion score, which is then fed back to the system.

[0364] Step 4:

[0365] The server evaluates work efficiency based on analysis results and emotional state, and generates improvement suggestions if necessary using a generative AI model. The input is the action analysis results and emotional evaluation, and the output is the improvement suggestions. In this step, current work performance is evaluated in comparison to past data, and optimized suggestions are created by the generative AI model. Specifically, the data is input to the generative AI model as prompt sentences, and suggestions are output.

[0366] Step 5:

[0367] The terminal receives analysis results and improvement suggestions from the server and provides voice instructions to the worker using speech synthesis software. The input is the analysis results and improvement suggestions, and the output is voice instructions. In this step, a speech synthesis API is used to generate speech in a pre-configured language and output it through the speaker. Specifically, it provides real-time instructions to the worker, such as "Please proceed to the next step."

[0368] Step 6:

[0369] The user proceeds with the task by following the voice instructions provided by the terminal. The input is the voice instructions from the terminal, and the output is the execution of the task. The user listens to the instructions, confirms the next action, and then actually performs the task. Specific actions include moving objects or operating equipment based on the instructions.

[0370] (Application Example 2)

[0371] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0372] In logistics and manufacturing, the challenge lies in improving worker efficiency while reducing psychological and physical burden during work, thereby creating a safe and comfortable working environment. In particular, there is a need to develop systems that appropriately assess worker fatigue and stress, and provide instructions that consider both work efficiency and worker health maintenance.

[0373] 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.

[0374] In this invention, the server includes: information acquisition means for recording the conditions within the work environment; analysis means for analyzing the recorded information data to identify the work content; instruction means for outputting voice instructions to the worker and visually displaying the worker's state based on the analysis results; evaluation means for evaluating the efficiency of the work and generating improvement suggestions; and emotion recognition means for identifying the worker's emotions from the information data. This makes it possible to analyze the worker's actions and emotional state in real time and flexibly provide individual work instructions and appropriate break suggestions.

[0375] "Information acquisition means" refers to devices or functions for recording the conditions of the work environment as digital data.

[0376] "Analysis means" refers to the technology and functions used to process recorded information data in detail and identify the content of the work.

[0377] A "command system" is a system that provides workers with necessary information visually and audibly based on analysis results, with the aim of improving work efficiency.

[0378] An "evaluation tool" is a function that quantitatively or qualitatively assesses the efficiency of work and generates suggestions for areas that need improvement.

[0379] "Emotion recognition means" refers to technology that analyzes information data to understand the emotional state of workers by analyzing their facial expressions and gestures.

[0380] To implement this invention, it is necessary to build a system that utilizes wearable devices such as smart glasses in logistics centers and manufacturing sites. The specific method is described below.

[0381] The server records the worker's movements through information acquisition devices installed in the work environment. These devices include cameras and sensors. This data is transmitted to the server and processed by analysis tools. Specifically, image analysis software (e.g., OpenCV) is used to identify the worker's movements and location. Additionally, emotion recognition AI (e.g., Azure Emotion API) is used to determine the worker's emotional state.

[0382] The smart glasses, acting as a terminal, receive analysis results from a server, output appropriate voice instructions to the worker, and display information on the screen. These instructions not only maximize work efficiency but also offer suggestions for breaks based on the worker's emotional state. The voice instruction function uses speech synthesis technology (e.g., Google Text-to-Speech). The specific operating procedures are adjusted to help the worker efficiently move to the next step while reducing excessive burden.

[0383] Users can follow visual and audio instructions from smart glasses to complete their tasks. This improves work efficiency and allows them to objectively understand their own emotional state and adjust their work pace as needed.

[0384] As a concrete example, in a logistics center, workers stand on the packing line and are instructed on the location and quantity of the next product to pick up through smart glasses. Furthermore, if a worker shows signs of fatigue, a break is automatically suggested immediately. This ensures both smooth workflow and the health management of the workers.

[0385] Example prompts for generative AI models:

[0386] "Please develop a smart glasses app to improve work efficiency in logistics centers. It should analyze workers' movements and emotions in real time, providing voice instructions and visual information as needed. Additionally, it should suggest breaks if it detects fatigue or stress in workers."

[0387] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0388] Step 1:

[0389] The server acquires video data of the work environment through information acquisition devices. The input is real-time video data obtained from cameras and sensors, which is stored in a database. The server then prepares this data for the next step.

[0390] Step 2:

[0391] The server processes the acquired video data using an analysis tool. The input is the video data acquired in step 1, and image analysis software such as OpenCV is used to identify the worker's movements and location information. The output is the analyzed movement information, with the data structured.

[0392] Step 3:

[0393] The server analyzes the worker's emotions using emotion recognition technology. The input is the same video data acquired in step 1, and the Azure Emotion API is used to determine the emotional state from the facial expressions. The output is data on the worker's emotional state.

[0394] Step 4:

[0395] Based on the analysis results, the server generates appropriate instructions for the worker via a control device. The input is the output from steps 2 and 3. Voice instructions are created using Google Text-to-Speech, and visual information is displayed on the smart glasses display. The output is provided to the worker as both voice instructions and visual information.

[0396] Step 5:

[0397] The smart glasses, acting as a terminal, receive instructions from the server and present them to the worker. Input consists of voice instructions and visual information transmitted from the server. The smart glasses play the audio through a speaker and display the information on a screen. Output is a user-friendly interface that is easy for the worker to understand.

[0398] Step 6:

[0399] The user follows instructions from the terminal to complete the task. Input consists of voice instructions and visual information provided by smart glasses. Based on this, the user improves the efficiency of the task by executing the specified procedures. The output is the realization of efficient and safe work.

[0400] 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.

[0401] 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.

[0402] 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.

[0403] [Third Embodiment]

[0404] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0405] 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.

[0406] 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).

[0407] 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.

[0408] 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.

[0409] 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).

[0410] 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.

[0411] 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.

[0412] 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.

[0413] 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.

[0414] 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.

[0415] 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".

[0416] This invention provides a system for improving the efficiency and standardization of operations in the logistics industry. The system mainly consists of a server, terminals, and users.

[0417] Server operation

[0418] The server collects image data in real time from cameras installed within the warehouse. This image data records the movements of workers and the work environment. The server analyzes the collected image data and uses an AI model to understand the work being done. Specifically, it identifies work events such as picking, packing, and moving. The analysis results are stored in a database and used to evaluate the progress of work and productivity.

[0419] Based on the analysis results, the server generates improvement suggestions to enhance work efficiency. These suggestions include optimizing work flows and reallocating resources. The server also automatically generates standard operating manuals based on the analysis data. This provides an environment where workers can quickly learn new procedures.

[0420] Terminal operation

[0421] The terminal receives analysis results transmitted from the server and provides real-time voice instructions to the worker. These voice instructions clearly communicate the next steps and points to note for the user. The content of the voice instructions is customized according to the work situation and the individual worker's skill level. This enables workers to proceed with their tasks efficiently.

[0422] User actions

[0423] Users perform tasks according to instructions from the terminal. Voice instructions allow them to learn about work procedures and precautions in real time, improving work efficiency and reducing human error. Furthermore, users can standardize their work by referring to standard work manuals, enabling consistent work quality across different workers.

[0424] This system aims to improve the efficiency of logistics operations and enable the maximum utilization of limited human resources.

[0425] The following describes the processing flow.

[0426] Step 1:

[0427] The server collects image data in real time from cameras installed within the warehouse. The images are captured to cover the entire work environment and sent to the server.

[0428] Step 2:

[0429] The server preprocesses the received image data, performing tasks such as noise reduction and sharpness adjustment. This preprocessing improves the accuracy of the analysis.

[0430] Step 3:

[0431] The server inputs pre-processed image data into a deep learning model to analyze the work performed. Specifically, it identifies work events such as picking, packing, and moving, and records their start and end times.

[0432] Step 4:

[0433] The server stores the work event information obtained through analysis in a database. This includes worker ID, work type, timestamp, and other details.

[0434] Step 5:

[0435] The terminal provides real-time voice assistance to the worker based on the analysis results received from the server. This voice guidance makes it easier for the worker to understand the next steps to take.

[0436] Step 6:

[0437] The user proceeds with the task by following voice instructions from the device. These instructions include points for safety checks and suggestions for improving efficiency.

[0438] Step 7:

[0439] The server analyzes accumulated work data and evaluates productivity and work efficiency. Based on this evaluation, it identifies areas for improvement and proposes specific improvement measures.

[0440] Step 8:

[0441] The server automatically generates a standard operating manual based on the analysis results. The manual visually presents efficient work procedures and important points to note.

[0442] Step 9:

[0443] Users utilize the generated standard operating manuals to standardize their daily tasks. This reduces variations in work and helps maintain consistent work quality.

[0444] (Example 1)

[0445] 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."

[0446] To improve work efficiency, reduce human error, and rapidly standardize work processes in the work environment, it is necessary to accurately understand worker actions in real time and provide optimal instructions. However, conventional systems have shortcomings in terms of accuracy in identifying actions and customization of instructions, and therefore do not adequately respond to the skills of workers or the work environment.

[0447] 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.

[0448] In this invention, the server includes information acquisition means for understanding the situation in the workspace, information analysis means for analyzing the acquired information to identify the work content, and voice output means for providing instructions to the worker based on the analysis results. This makes it possible to analyze the worker's movements in detail and provide appropriate work instructions in real time.

[0449] "Information acquisition means" refers to the processes and devices used to collect information necessary to understand the situation within the workspace.

[0450] "Information analysis means" refers to technologies and methods for identifying and evaluating work content based on acquired information.

[0451] "Voice output means" refers to devices or systems that provide necessary instructions and information to workers via voice based on the analyzed results.

[0452] "Evaluation tools" refer to functions that generate improvement suggestions based on acquired data and analyze the workflow in order to optimize work efficiency.

[0453] "Methods for automatically creating standard operating procedures" refers to a process that automatically generates operating procedures based on data analysis results, aiming to standardize and streamline operations.

[0454] A "generative AI model" refers to a machine learning model that analyzes collected data and understands the nature of the work being done.

[0455] A "prompt" refers to the input text given to a generative AI model to obtain a specific output.

[0456] This invention provides a system in which a server, terminal, and user each play a specific role in order to improve the efficiency and standardization of work within the work environment. This system enables real-time work monitoring, data analysis, and work instructions.

[0457] Server configuration and operation

[0458] The server primarily consists of information acquisition, information analysis, and evaluation means. It collects information from devices such as cameras installed in warehouses and work areas, and the image data is analyzed by a generative AI model using deep learning. This generative AI model identifies the type and progress of work from the collected data and identifies each work event. For example, when the server identifies an action such as "taking an item from a shelf," it classifies it as "picking." The analysis results are stored in a database, and improvement suggestions are generated based on this data. An example of a prompt is "Propose ways to improve the efficiency of logistics operations."

[0459] Terminal configuration and operation

[0460] The terminal generates voice instructions based on analysis data sent from the server and provides them to the user. Using speech synthesis technology, the instructions created from the analysis results are conveyed to the user in natural language. A concrete example of such instructions might be, "Please pick the next item from shelf B."

[0461] User configuration and behavior

[0462] Users efficiently perform tasks by following real-time instructions from their terminals. By referring to standard operating procedures provided by the system, tasks can be standardized. This allows users to quickly learn new operating procedures while maintaining work quality.

[0463] The introduction of this system will improve work efficiency and productivity by reviewing existing work processes and automatically generating optimized work flows. An example of a prompt sentence to be input into the generating AI model is, "List the improvements needed to improve work efficiency."

[0464] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0465] Step 1:

[0466] The server acquires image data in real time from cameras installed within the work environment. The input camera footage shows the movements of workers and the work environment. The server converts the format and adjusts the resolution of this video data, preparing it for input into the generated AI model. Specifically, the server extracts important scenes, selects frames with significant movement, and supplies them to the next process.

[0467] Step 2:

[0468] The server inputs image data into a generating AI model and analyzes the work performed. The model extracts features from the input data and applies machine learning algorithms to classify each action. The output is an analysis result that shows what kind of work events are taking place. For example, the server recognizes the action of "taking an item from a shelf" as "picking" and generates an event list.

[0469] Step 3:

[0470] The server generates improvement suggestions based on the analysis results. The analysis data is input to the AI ​​model along with the prompt message "Propose ways to improve the efficiency of logistics operations," and the output is improved work flow suggestions. Specifically, the server compiles suggestions such as shortening movement paths and revising work procedures into a suggestion list.

[0471] Step 4:

[0472] The terminal generates voice output based on improvement suggestions and work instructions sent from the server. The input instruction data is converted into voice using speech synthesis technology. The output is specific work instructions for the user. Specifically, the terminal generates a voice message such as, "Next, take inventory of the items on shelf B," and conveys it to the user.

[0473] Step 5:

[0474] The user performs the actual task by following voice instructions from the terminal. Any problems or insights gained during the task are input as feedback to the server via the terminal. As output, the server updates the database in real time and reflects this in the next analysis and instruction generation. For example, the user reports that "the location of the specified product is incorrect," and this information is shared throughout the entire system.

[0475] (Application Example 1)

[0476] 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."

[0477] The logistics industry is facing a need to improve operational efficiency and reduce variations in quality. In particular, it is necessary to improve work efficiency and accuracy by providing optimal work instructions tailored to individual workers in real time. However, conventional systems struggle to flexibly adapt to changes in worker skills and warehouse environments, leaving room for improvement.

[0478] 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.

[0479] In this invention, the server includes sensor acquisition means for recording conditions within the work environment, data analysis means for analyzing the recorded data to identify the work content, and instruction output means for outputting voice and visual instructions to the worker based on the analysis results. This makes it possible to grasp the work situation in real time and provide optimal work instructions tailored to each individual worker.

[0480] A "sensor acquisition means" is a means used to record the conditions within the work environment in real time.

[0481] "Data analysis means" refers to methods for analyzing recorded data to identify specific work content or situations.

[0482] "Instruction output means" refers to means for providing instructions to the worker via voice or visual means based on the analysis results.

[0483] "Performance evaluation methods" are means for evaluating work efficiency and generating improvement suggestions based on the results.

[0484] A "device" is a device that transmits data to a server in real time and presents instructions visually.

[0485] The specific system for implementing this invention is as follows:

[0486] The server acquires data from sensors installed within the work environment. This data includes detailed information about the worker's movements and the work environment. The server uses "data analysis tools" to analyze this data and identify specific work events. Specifically, it uses an AI model to identify events such as picking and packing, and evaluates efficiency based on the analysis results.

[0487] The server generates improvement suggestions to enhance work efficiency based on the evaluation results. These suggestions include optimizing work flow and appropriate resource allocation, and also function as instructional materials for the work site. Furthermore, it supports work standardization by automatically generating standardized work guidelines based on the analysis data.

[0488] The terminal device receives instructions sent from the server and outputs instructions to the worker via voice or visual means. This allows the worker to proceed with their work efficiently and contributes to reducing human error. Smart glasses are expected to be used as the device, monitoring the progress of the work in real time and feeding that information back to the server.

[0489] As a concrete example, imagine a scenario where a warehouse worker receives instructions via smart glasses, such as "Please select the next item to pack," and visual guidelines are displayed. This allows the worker to check the information without using their hands, enabling them to perform their tasks more smoothly.

[0490] An example of a prompt message given to the AI ​​model is, "Analyze the movements of all workers in the image and generate the next work step." This allows the data analysis tool to suggest the most suitable task.

[0491] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0492] Step 1:

[0493] The server collects data from sensors in the work environment. This data includes images of the worker's movements and the environment. Upon receiving this input data, the server not only stores it but also uses it as material for the next analysis step.

[0494] Step 2:

[0495] The server analyzes the collected data using a "data analysis tool." Specifically, it uses an AI model to extract specific work events from image data and identify the progress of the work for each event. The input for this data analysis is the image data acquired in step 1, and the output is the identified work content.

[0496] Step 3:

[0497] The server evaluates work efficiency based on the analysis results and generates improvement suggestions. Specifically, it makes suggestions such as optimizing work flows and reallocating resources. In this step, the evaluated procedures and results are saved to a database, and the suggestions are generated as output.

[0498] Step 4:

[0499] The terminal device receives instruction data transmitted from the server and outputs audio and visual instructions to the worker. Based on this input data, the worker can confirm efficient work procedures in real time, and the next action to be taken is clearly indicated as output.

[0500] Step 5:

[0501] The user, acting as the worker, performs each task based on instructions from the device. In this step, actions are carried out according to specific work procedures, improving work efficiency. The user's reactions are input into the next data collection and used in the overall system feedback loop.

[0502] 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.

[0503] This invention provides a system for improving worker efficiency and safety in logistics and manufacturing work environments. The system combines image acquisition means for recording work status, analysis means for analyzing image data to identify work content, instruction means for outputting voice instructions to workers based on the analysis results, and evaluation means for evaluating work efficiency and generating improvement suggestions. Furthermore, by incorporating an emotion engine for recognizing workers' emotions, the system enables more nuanced management of the entire work environment.

[0504] Server operation

[0505] The server continuously acquires video footage from cameras installed in the warehouse and processes the data using analytical tools. This analysis allows the server to understand what actions workers are taking and what stage of work they are in. The server also analyzes the workers' facial expressions based on the acquired video data and uses an emotion engine to identify their emotional state. Based on this state, the server evaluates work efficiency and generates improvement suggestions if necessary.

[0506] Terminal operation

[0507] The terminal receives analysis results from the server and provides necessary voice instructions to the worker. These voice instructions are flexibly adjusted according to the worker's emotional state and can include content that alleviates stress or increases motivation. For example, if the worker is feeling tired or stressed, it can suggest a temporary break. In this way, the terminal supports an environment in which workers can work comfortably.

[0508] User actions

[0509] Users proceed with their tasks by following voice instructions provided by the device. These voice instructions clearly indicate the next step, allowing users to concentrate on their work. Furthermore, feedback from an emotional engine enables users to objectively assess their own state and adjust their work pace as needed.

[0510] This system improves operational efficiency in logistics sites and reduces the psychological and physical burden on workers. Ultimately, it aims to increase overall organizational productivity and provide a healthier work environment.

[0511] The following describes the processing flow.

[0512] Step 1:

[0513] The server collects video data from multiple cameras installed within the warehouse. The video covers the work area and captures not only the movements of the workers but also the surrounding environment.

[0514] Step 2:

[0515] The server preprocesses the collected video data and extracts the necessary parts. Preprocessing includes noise reduction and brightness adjustment. During this process, data unnecessary for analysis is removed.

[0516] Step 3:

[0517] The server inputs pre-processed data into the analysis system to identify the work content. Using an AI algorithm, the type of work and its progress are analyzed in real time. The analysis results are stored in a database.

[0518] Step 4:

[0519] The server uses an emotion engine to analyze the worker's facial expression data and identify their emotional state. It uses facial recognition technology to identify emotions such as joy, surprise, anger, sadness, and fatigue.

[0520] Step 5:

[0521] The terminal provides voice instructions to the worker based on analysis results sent from the server. The voice instructions are adjusted according to the worker's emotional state; for example, a worker experiencing stress will receive instructions in a calm tone and receive words of encouragement.

[0522] Step 6:

[0523] Users perform tasks while listening to voice instructions from the terminal. The instructions include work procedures and precautions, allowing workers to efficiently complete tasks based on these instructions.

[0524] Step 7:

[0525] The server generates work efficiency evaluations and improvement suggestions based on the analyzed data. The evaluation includes the user's work speed, accuracy, and emotional state, and these data are combined to suggest improvement measures.

[0526] Step 8:

[0527] The server automatically generates standard operating manuals and provides them to users via terminals or other media. The manuals clearly explain efficient work procedures, allowing workers to refer to them while continuing their tasks.

[0528] Step 9:

[0529] Users refer to standard operating manuals to optimize their own work. This prevents variations in work and maintains consistent work quality.

[0530] (Example 2)

[0531] 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."

[0532] In logistics and manufacturing work environments, there is a need to improve worker efficiency and safety, as well as to recognize workers' emotional states and optimize instructions accordingly. However, current systems cannot provide instructions that take workers' emotional states into account, making it difficult to provide an efficient work environment. As a result, the improvement in work efficiency and reduction of worker burden are not being fully achieved, which is a challenge.

[0533] 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.

[0534] In this invention, the server includes an image acquisition means for recording the conditions within the work environment, an analysis means for analyzing the recorded image data to identify the work content, and an emotion recognition means for analyzing the worker's facial expressions to identify their emotional state. This makes it possible to optimize voice instructions according to the worker's emotional state, thereby improving work efficiency and reducing the burden on the worker.

[0535] "Image acquisition means" refers to devices or groups of devices installed to record conditions within the work environment, and includes cameras and sensors.

[0536] "Analysis means" refers to software or algorithms that process recorded image data to identify the work content and detect work progress and anomalies.

[0537] "Instruction means" refers to devices or software that output instructions to workers, either verbally or visually, based on the analyzed data.

[0538] "Emotion recognition means" refers to algorithms and software that analyze a worker's facial expressions and behavior to identify their current emotional state.

[0539] "Evaluation means" refers to processes and systems for measuring work efficiency based on analysis results and emotional states, and for generating improvement suggestions when necessary.

[0540] This invention is a system aimed at improving work efficiency and safety in logistics and manufacturing sites. By having servers, terminals, and users cooperate to monitor and improve the work environment, it enables smoother and more efficient operations.

[0541] Server Role

[0542] The server acquires video data in real time from network-enabled cameras installed within the work environment. AI image analysis software (e.g., OpenCV or TensorFlow) is used to analyze the video data and identify the worker's actions and stage. The server also analyzes the worker's facial expressions from the same video data and uses emotion recognition tools (e.g., emotion recognition APIs) to identify the worker's emotional state. Based on this information, the server evaluates work efficiency and generates improvement suggestions as needed. These suggestions may utilize a generative AI model, and optimization is performed during the data processing process.

[0543] Terminal role

[0544] The terminal receives data from the server and uses speech synthesis software (e.g., speech synthesis API) to provide voice instructions to the worker. These voice instructions are customized according to the worker's emotional state, aiming to increase motivation or reduce stress. For example, if the worker is tired, it can give specific instructions such as, "I recommend you take a short break."

[0545] User roles

[0546] Users proceed with their work by following instructions from the terminal. The instructions clearly indicate the next steps, making it easier for users to concentrate on their work. Furthermore, feedback allows users to understand their mental and physical state and adjust their work pace as needed. This maximizes work efficiency while reducing the burden on the worker.

[0547] As a concrete example, consider the case where this system is implemented in a logistics center. If the server monitors and the emotion recognition system determines that a worker is feeling fatigued from carrying heavy loads, the terminal will tell the worker to "slow down your work pace and take a break." This allows the worker to continue their work without overexerting themselves.

[0548] An example of a prompt to input into the generating AI model is, "Please suggest a method for generating optimal work instructions that take into account the emotional state of the worker."

[0549] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0550] Step 1:

[0551] The server acquires real-time video data from network-enabled cameras within the warehouse. The input is a video stream from the cameras, which the server temporarily records. Specifically, the operation here involves capturing video from the camera device and storing it as digital data within the server.

[0552] Step 2:

[0553] The server analyzes the acquired video data using AI image analysis software. The input is the recorded video data, and the output is the analysis results, including worker movements and location information. This analysis can identify what movements the worker is performing and which stage of work they are in. Specifically, this involves using an image recognition algorithm to detect the worker's movements in each frame and storing the data in a database.

[0554] Step 3:

[0555] The server analyzes the worker's facial expressions from the same video data and identifies their emotional state using emotion recognition technology. The input is again video data, and the output is an evaluation of the worker's emotional state. In this step, facial recognition technology is used to analyze the worker's facial expressions and infer psychological states such as fatigue and stress. Specifically, an emotion recognition API is called to generate an emotion score, which is then fed back to the system.

[0556] Step 4:

[0557] The server evaluates work efficiency based on analysis results and emotional state, and generates improvement suggestions if necessary using a generative AI model. The input is the action analysis results and emotional evaluation, and the output is the improvement suggestions. In this step, current work performance is evaluated in comparison to past data, and optimized suggestions are created by the generative AI model. Specifically, the data is input to the generative AI model as prompt sentences, and suggestions are output.

[0558] Step 5:

[0559] The terminal receives analysis results and improvement suggestions from the server and provides voice instructions to the worker using speech synthesis software. The input is the analysis results and improvement suggestions, and the output is voice instructions. In this step, a speech synthesis API is used to generate speech in a pre-configured language and output it through the speaker. Specifically, it provides real-time instructions to the worker, such as "Please proceed to the next step."

[0560] Step 6:

[0561] The user proceeds with the task by following the voice instructions provided by the terminal. The input is the voice instructions from the terminal, and the output is the execution of the task. The user listens to the instructions, confirms the next action, and then actually performs the task. Specific actions include moving objects or operating equipment based on the instructions.

[0562] (Application Example 2)

[0563] 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."

[0564] In logistics and manufacturing, the challenge lies in improving worker efficiency while reducing psychological and physical burden during work, thereby creating a safe and comfortable working environment. In particular, there is a need to develop systems that appropriately assess worker fatigue and stress, and provide instructions that consider both work efficiency and worker health maintenance.

[0565] 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.

[0566] In this invention, the server includes: information acquisition means for recording the conditions within the work environment; analysis means for analyzing the recorded information data to identify the work content; instruction means for outputting voice instructions to the worker and visually displaying the worker's state based on the analysis results; evaluation means for evaluating the efficiency of the work and generating improvement suggestions; and emotion recognition means for identifying the worker's emotions from the information data. This makes it possible to analyze the worker's actions and emotional state in real time and flexibly provide individual work instructions and appropriate break suggestions.

[0567] "Information acquisition means" refers to devices or functions for recording the conditions of the work environment as digital data.

[0568] "Analysis means" refers to the technology and functions used to process recorded information data in detail and identify the content of the work.

[0569] A "command system" is a system that provides workers with necessary information visually and audibly based on analysis results, with the aim of improving work efficiency.

[0570] An "evaluation tool" is a function that quantitatively or qualitatively assesses the efficiency of work and generates suggestions for areas that need improvement.

[0571] "Emotion recognition means" refers to technology that analyzes information data to understand the emotional state of workers by analyzing their facial expressions and gestures.

[0572] To implement this invention, it is necessary to build a system that utilizes wearable devices such as smart glasses in logistics centers and manufacturing sites. The specific method is described below.

[0573] The server records the worker's movements through information acquisition devices installed in the work environment. These devices include cameras and sensors. This data is transmitted to the server and processed by analysis tools. Specifically, image analysis software (e.g., OpenCV) is used to identify the worker's movements and location. Additionally, emotion recognition AI (e.g., Azure Emotion API) is used to determine the worker's emotional state.

[0574] The smart glasses, acting as a terminal, receive analysis results from a server, output appropriate voice instructions to the worker, and display information on the screen. These instructions not only maximize work efficiency but also offer suggestions for breaks based on the worker's emotional state. The voice instruction function uses speech synthesis technology (e.g., Google Text-to-Speech). The specific operating procedures are adjusted to help the worker efficiently move to the next step while reducing excessive burden.

[0575] Users can follow visual and audio instructions from smart glasses to complete their tasks. This improves work efficiency and allows them to objectively understand their own emotional state and adjust their work pace as needed.

[0576] As a concrete example, in a logistics center, workers stand on the packing line and are instructed on the location and quantity of the next product to pick up through smart glasses. Furthermore, if a worker shows signs of fatigue, a break is automatically suggested immediately. This ensures both smooth workflow and the health management of the workers.

[0577] Example prompts for generative AI models:

[0578] "Please develop a smart glasses app to improve work efficiency in logistics centers. It should analyze workers' movements and emotions in real time, providing voice instructions and visual information as needed. Additionally, it should suggest breaks if it detects fatigue or stress in workers."

[0579] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0580] Step 1:

[0581] The server acquires video data of the work environment through information acquisition devices. The input is real-time video data obtained from cameras and sensors, which is stored in a database. The server then prepares this data for the next step.

[0582] Step 2:

[0583] The server processes the acquired video data using an analysis tool. The input is the video data acquired in step 1, and image analysis software such as OpenCV is used to identify the worker's movements and location information. The output is the analyzed movement information, with the data structured.

[0584] Step 3:

[0585] The server analyzes the worker's emotions using emotion recognition technology. The input is the same video data acquired in step 1, and the Azure Emotion API is used to determine the emotional state from the facial expressions. The output is data on the worker's emotional state.

[0586] Step 4:

[0587] Based on the analysis results, the server generates appropriate instructions for the worker via a control device. The input is the output from steps 2 and 3. Voice instructions are created using Google Text-to-Speech, and visual information is displayed on the smart glasses display. The output is provided to the worker as both voice instructions and visual information.

[0588] Step 5:

[0589] The smart glasses, acting as a terminal, receive instructions from the server and present them to the worker. Input consists of voice instructions and visual information transmitted from the server. The smart glasses play the audio through a speaker and display the information on a screen. Output is a user-friendly interface that is easy for the worker to understand.

[0590] Step 6:

[0591] The user follows instructions from the terminal to complete the task. Input consists of voice instructions and visual information provided by smart glasses. Based on this, the user improves the efficiency of the task by executing the specified procedures. The output is the realization of efficient and safe work.

[0592] 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.

[0593] 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.

[0594] 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.

[0595] [Fourth Embodiment]

[0596] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0597] 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.

[0598] 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).

[0599] 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.

[0600] 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.

[0601] 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).

[0602] 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.

[0603] 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.

[0604] 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.

[0605] 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.

[0606] 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.

[0607] 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.

[0608] 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".

[0609] This invention provides a system for improving the efficiency and standardization of operations in the logistics industry. The system mainly consists of a server, terminals, and users.

[0610] Server operation

[0611] The server collects image data in real time from cameras installed within the warehouse. This image data records the movements of workers and the work environment. The server analyzes the collected image data and uses an AI model to understand the work being done. Specifically, it identifies work events such as picking, packing, and moving. The analysis results are stored in a database and used to evaluate the progress of work and productivity.

[0612] Based on the analysis results, the server generates improvement suggestions to enhance work efficiency. These suggestions include optimizing work flows and reallocating resources. The server also automatically generates standard operating manuals based on the analysis data. This provides an environment where workers can quickly learn new procedures.

[0613] Terminal operation

[0614] The terminal receives analysis results transmitted from the server and provides real-time voice instructions to the worker. These voice instructions clearly communicate the next steps and points to note for the user. The content of the voice instructions is customized according to the work situation and the individual worker's skill level. This enables workers to proceed with their tasks efficiently.

[0615] User actions

[0616] Users perform tasks according to instructions from the terminal. Voice instructions allow them to learn about work procedures and precautions in real time, improving work efficiency and reducing human error. Furthermore, users can standardize their work by referring to standard work manuals, enabling consistent work quality across different workers.

[0617] This system aims to improve the efficiency of logistics operations and enable the maximum utilization of limited human resources.

[0618] The following describes the processing flow.

[0619] Step 1:

[0620] The server collects image data in real time from cameras installed within the warehouse. The images are captured to cover the entire work environment and sent to the server.

[0621] Step 2:

[0622] The server preprocesses the received image data, performing tasks such as noise reduction and sharpness adjustment. This preprocessing improves the accuracy of the analysis.

[0623] Step 3:

[0624] The server inputs pre-processed image data into a deep learning model to analyze the work performed. Specifically, it identifies work events such as picking, packing, and moving, and records their start and end times.

[0625] Step 4:

[0626] The server stores the work event information obtained through analysis in a database. This includes worker ID, work type, timestamp, and other details.

[0627] Step 5:

[0628] The terminal provides real-time voice assistance to the worker based on the analysis results received from the server. This voice guidance makes it easier for the worker to understand the next steps to take.

[0629] Step 6:

[0630] The user proceeds with the task by following voice instructions from the device. These instructions include points for safety checks and suggestions for improving efficiency.

[0631] Step 7:

[0632] The server analyzes accumulated work data and evaluates productivity and work efficiency. Based on this evaluation, it identifies areas for improvement and proposes specific improvement measures.

[0633] Step 8:

[0634] The server automatically generates a standard operating manual based on the analysis results. The manual visually presents efficient work procedures and important points to note.

[0635] Step 9:

[0636] Users utilize the generated standard operating manuals to standardize their daily tasks. This reduces variations in work and helps maintain consistent work quality.

[0637] (Example 1)

[0638] 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".

[0639] To improve work efficiency, reduce human error, and rapidly standardize work processes in the work environment, it is necessary to accurately understand worker actions in real time and provide optimal instructions. However, conventional systems have shortcomings in terms of accuracy in identifying actions and customization of instructions, and therefore do not adequately respond to the skills of workers or the work environment.

[0640] 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.

[0641] In this invention, the server includes information acquisition means for understanding the situation in the workspace, information analysis means for analyzing the acquired information to identify the work content, and voice output means for providing instructions to the worker based on the analysis results. This makes it possible to analyze the worker's movements in detail and provide appropriate work instructions in real time.

[0642] "Information acquisition means" refers to the processes and devices used to collect information necessary to understand the situation within the workspace.

[0643] "Information analysis means" refers to technologies and methods for identifying and evaluating work content based on acquired information.

[0644] "Voice output means" refers to devices or systems that provide necessary instructions and information to workers via voice based on the analyzed results.

[0645] "Evaluation tools" refer to functions that generate improvement suggestions based on acquired data and analyze the workflow in order to optimize work efficiency.

[0646] "Methods for automatically creating standard operating procedures" refers to a process that automatically generates operating procedures based on data analysis results, aiming to standardize and streamline operations.

[0647] A "generative AI model" refers to a machine learning model that analyzes collected data and understands the nature of the work being done.

[0648] A "prompt" refers to the input text given to a generative AI model to obtain a specific output.

[0649] This invention provides a system in which a server, terminal, and user each play a specific role in order to improve the efficiency and standardization of work within the work environment. This system enables real-time work monitoring, data analysis, and work instructions.

[0650] Server configuration and operation

[0651] The server primarily consists of information acquisition, information analysis, and evaluation means. It collects information from devices such as cameras installed in warehouses and work areas, and the image data is analyzed by a generative AI model using deep learning. This generative AI model identifies the type and progress of work from the collected data and identifies each work event. For example, when the server identifies an action such as "taking an item from a shelf," it classifies it as "picking." The analysis results are stored in a database, and improvement suggestions are generated based on this data. An example of a prompt is "Propose ways to improve the efficiency of logistics operations."

[0652] Terminal configuration and operation

[0653] The terminal generates voice instructions based on analysis data sent from the server and provides them to the user. Using speech synthesis technology, the instructions created from the analysis results are conveyed to the user in natural language. A concrete example of such instructions might be, "Please pick the next item from shelf B."

[0654] User configuration and behavior

[0655] Users efficiently perform tasks by following real-time instructions from their terminals. By referring to standard operating procedures provided by the system, tasks can be standardized. This allows users to quickly learn new operating procedures while maintaining work quality.

[0656] The introduction of this system will improve work efficiency and productivity by reviewing existing work processes and automatically generating optimized work flows. An example of a prompt sentence to be input into the generating AI model is, "List the improvements needed to improve work efficiency."

[0657] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0658] Step 1:

[0659] The server acquires image data in real time from cameras installed within the work environment. The input camera footage shows the movements of workers and the work environment. The server converts the format and adjusts the resolution of this video data, preparing it for input into the generated AI model. Specifically, the server extracts important scenes, selects frames with significant movement, and supplies them to the next process.

[0660] Step 2:

[0661] The server inputs image data into a generating AI model and analyzes the work performed. The model extracts features from the input data and applies machine learning algorithms to classify each action. The output is an analysis result that shows what kind of work events are taking place. For example, the server recognizes the action of "taking an item from a shelf" as "picking" and generates an event list.

[0662] Step 3:

[0663] The server generates improvement suggestions based on the analysis results. The analysis data is input to the AI ​​model along with the prompt message "Propose ways to improve the efficiency of logistics operations," and the output is improved work flow suggestions. Specifically, the server compiles suggestions such as shortening movement paths and revising work procedures into a suggestion list.

[0664] Step 4:

[0665] The terminal generates voice output based on improvement suggestions and work instructions sent from the server. The input instruction data is converted into voice using speech synthesis technology. The output is specific work instructions for the user. Specifically, the terminal generates a voice message such as, "Next, take inventory of the items on shelf B," and conveys it to the user.

[0666] Step 5:

[0667] The user performs the actual task by following voice instructions from the terminal. Any problems or insights gained during the task are input as feedback to the server via the terminal. As output, the server updates the database in real time and reflects this in the next analysis and instruction generation. For example, the user reports that "the location of the specified product is incorrect," and this information is shared throughout the entire system.

[0668] (Application Example 1)

[0669] 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".

[0670] The logistics industry is facing a need to improve operational efficiency and reduce variations in quality. In particular, it is necessary to improve work efficiency and accuracy by providing optimal work instructions tailored to individual workers in real time. However, conventional systems struggle to flexibly adapt to changes in worker skills and warehouse environments, leaving room for improvement.

[0671] 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.

[0672] In this invention, the server includes sensor acquisition means for recording conditions within the work environment, data analysis means for analyzing the recorded data to identify the work content, and instruction output means for outputting voice and visual instructions to the worker based on the analysis results. This makes it possible to grasp the work situation in real time and provide optimal work instructions tailored to each individual worker.

[0673] A "sensor acquisition means" is a means used to record the conditions within the work environment in real time.

[0674] "Data analysis means" refers to methods for analyzing recorded data to identify specific work content or situations.

[0675] "Instruction output means" refers to means for providing instructions to the worker via voice or visual means based on the analysis results.

[0676] "Performance evaluation methods" are means for evaluating work efficiency and generating improvement suggestions based on the results.

[0677] A "device" is a device that transmits data to a server in real time and presents instructions visually.

[0678] The specific system for implementing this invention is as follows:

[0679] The server acquires data from sensors installed within the work environment. This data includes detailed information about the worker's movements and the work environment. The server uses "data analysis tools" to analyze this data and identify specific work events. Specifically, it uses an AI model to identify events such as picking and packing, and evaluates efficiency based on the analysis results.

[0680] The server generates improvement suggestions to enhance work efficiency based on the evaluation results. These suggestions include optimizing work flow and appropriate resource allocation, and also function as instructional materials for the work site. Furthermore, it supports work standardization by automatically generating standardized work guidelines based on the analysis data.

[0681] The terminal device receives instructions sent from the server and outputs instructions to the worker via voice or visual means. This allows the worker to proceed with their work efficiently and contributes to reducing human error. Smart glasses are expected to be used as the device, monitoring the progress of the work in real time and feeding that information back to the server.

[0682] As a concrete example, imagine a scenario where a warehouse worker receives instructions via smart glasses, such as "Please select the next item to pack," and visual guidelines are displayed. This allows the worker to check the information without using their hands, enabling them to perform their tasks more smoothly.

[0683] An example of a prompt message given to the AI ​​model is, "Analyze the movements of all workers in the image and generate the next work step." This allows the data analysis tool to suggest the most suitable task.

[0684] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0685] Step 1:

[0686] The server collects data from sensors in the work environment. This data includes images of the worker's movements and the environment. Upon receiving this input data, the server not only stores it but also uses it as material for the next analysis step.

[0687] Step 2:

[0688] The server analyzes the collected data using a "data analysis tool." Specifically, it uses an AI model to extract specific work events from image data and identify the progress of the work for each event. The input for this data analysis is the image data acquired in step 1, and the output is the identified work content.

[0689] Step 3:

[0690] The server evaluates work efficiency based on the analysis results and generates improvement suggestions. Specifically, it makes suggestions such as optimizing work flows and reallocating resources. In this step, the evaluated procedures and results are saved to a database, and the suggestions are generated as output.

[0691] Step 4:

[0692] The terminal device receives instruction data transmitted from the server and outputs audio and visual instructions to the worker. Based on this input data, the worker can confirm efficient work procedures in real time, and the next action to be taken is clearly indicated as output.

[0693] Step 5:

[0694] The user, acting as the worker, performs each task based on instructions from the device. In this step, actions are carried out according to specific work procedures, improving work efficiency. The user's reactions are input into the next data collection and used in the overall system feedback loop.

[0695] 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.

[0696] This invention provides a system for improving worker efficiency and safety in logistics and manufacturing work environments. The system combines image acquisition means for recording work status, analysis means for analyzing image data to identify work content, instruction means for outputting voice instructions to workers based on the analysis results, and evaluation means for evaluating work efficiency and generating improvement suggestions. Furthermore, by incorporating an emotion engine for recognizing workers' emotions, the system enables more nuanced management of the entire work environment.

[0697] Server operation

[0698] The server continuously acquires video footage from cameras installed in the warehouse and processes the data using analytical tools. This analysis allows the server to understand what actions workers are taking and what stage of work they are in. The server also analyzes the workers' facial expressions based on the acquired video data and uses an emotion engine to identify their emotional state. Based on this state, the server evaluates work efficiency and generates improvement suggestions if necessary.

[0699] Terminal operation

[0700] The terminal receives analysis results from the server and provides necessary voice instructions to the worker. These voice instructions are flexibly adjusted according to the worker's emotional state and can include content that alleviates stress or increases motivation. For example, if the worker is feeling tired or stressed, it can suggest a temporary break. In this way, the terminal supports an environment in which workers can work comfortably.

[0701] User actions

[0702] Users proceed with their tasks by following voice instructions provided by the device. These voice instructions clearly indicate the next step, allowing users to concentrate on their work. Furthermore, feedback from an emotional engine enables users to objectively assess their own state and adjust their work pace as needed.

[0703] This system improves operational efficiency in logistics sites and reduces the psychological and physical burden on workers. Ultimately, it aims to increase overall organizational productivity and provide a healthier work environment.

[0704] The following describes the processing flow.

[0705] Step 1:

[0706] The server collects video data from multiple cameras installed within the warehouse. The video covers the work area and captures not only the movements of the workers but also the surrounding environment.

[0707] Step 2:

[0708] The server preprocesses the collected video data and extracts the necessary parts. Preprocessing includes noise reduction and brightness adjustment. During this process, data unnecessary for analysis is removed.

[0709] Step 3:

[0710] The server inputs pre-processed data into the analysis system to identify the work content. Using an AI algorithm, the type of work and its progress are analyzed in real time. The analysis results are stored in a database.

[0711] Step 4:

[0712] The server uses an emotion engine to analyze the worker's facial expression data and identify their emotional state. It uses facial recognition technology to identify emotions such as joy, surprise, anger, sadness, and fatigue.

[0713] Step 5:

[0714] The terminal provides voice instructions to the worker based on analysis results sent from the server. The voice instructions are adjusted according to the worker's emotional state; for example, a worker experiencing stress will receive instructions in a calm tone and receive words of encouragement.

[0715] Step 6:

[0716] Users perform tasks while listening to voice instructions from the terminal. The instructions include work procedures and precautions, allowing workers to efficiently complete tasks based on these instructions.

[0717] Step 7:

[0718] The server generates work efficiency evaluations and improvement suggestions based on the analyzed data. The evaluation includes the user's work speed, accuracy, and emotional state, and these data are combined to suggest improvement measures.

[0719] Step 8:

[0720] The server automatically generates standard operating manuals and provides them to users via terminals or other media. The manuals clearly explain efficient work procedures, allowing workers to refer to them while continuing their tasks.

[0721] Step 9:

[0722] Users refer to standard operating manuals to optimize their own work. This prevents variations in work and maintains consistent work quality.

[0723] (Example 2)

[0724] 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".

[0725] In logistics and manufacturing work environments, there is a need to improve worker efficiency and safety, as well as to recognize workers' emotional states and optimize instructions accordingly. However, current systems cannot provide instructions that take workers' emotional states into account, making it difficult to provide an efficient work environment. As a result, the improvement in work efficiency and reduction of worker burden are not being fully achieved, which is a challenge.

[0726] 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.

[0727] In this invention, the server includes an image acquisition means for recording the conditions within the work environment, an analysis means for analyzing the recorded image data to identify the work content, and an emotion recognition means for analyzing the worker's facial expressions to identify their emotional state. This makes it possible to optimize voice instructions according to the worker's emotional state, thereby improving work efficiency and reducing the burden on the worker.

[0728] "Image acquisition means" refers to devices or groups of devices installed to record conditions within the work environment, and includes cameras and sensors.

[0729] "Analysis means" refers to software or algorithms that process recorded image data to identify the work content and detect work progress and anomalies.

[0730] "Instruction means" refers to devices or software that output instructions to workers, either verbally or visually, based on the analyzed data.

[0731] "Emotion recognition means" refers to algorithms and software that analyze a worker's facial expressions and behavior to identify their current emotional state.

[0732] "Evaluation means" refers to processes and systems for measuring work efficiency based on analysis results and emotional states, and for generating improvement suggestions when necessary.

[0733] This invention is a system aimed at improving work efficiency and safety in logistics and manufacturing sites. By having servers, terminals, and users cooperate to monitor and improve the work environment, it enables smoother and more efficient operations.

[0734] Server Role

[0735] The server acquires video data in real time from network-enabled cameras installed within the work environment. AI image analysis software (e.g., OpenCV or TensorFlow) is used to analyze the video data and identify the worker's actions and stage. The server also analyzes the worker's facial expressions from the same video data and uses emotion recognition tools (e.g., emotion recognition APIs) to identify the worker's emotional state. Based on this information, the server evaluates work efficiency and generates improvement suggestions as needed. These suggestions may utilize a generative AI model, and optimization is performed during the data processing process.

[0736] Terminal role

[0737] The terminal receives data from the server and uses speech synthesis software (e.g., speech synthesis API) to provide voice instructions to the worker. These voice instructions are customized according to the worker's emotional state, aiming to increase motivation or reduce stress. For example, if the worker is tired, it can give specific instructions such as, "I recommend you take a short break."

[0738] User roles

[0739] Users proceed with their work by following instructions from the terminal. The instructions clearly indicate the next steps, making it easier for users to concentrate on their work. Furthermore, feedback allows users to understand their mental and physical state and adjust their work pace as needed. This maximizes work efficiency while reducing the burden on the worker.

[0740] As a concrete example, consider the case where this system is implemented in a logistics center. If the server monitors and the emotion recognition system determines that a worker is feeling fatigued from carrying heavy loads, the terminal will tell the worker to "slow down your work pace and take a break." This allows the worker to continue their work without overexerting themselves.

[0741] An example of a prompt to input into the generating AI model is, "Please suggest a method for generating optimal work instructions that take into account the emotional state of the worker."

[0742] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0743] Step 1:

[0744] The server acquires real-time video data from network-enabled cameras within the warehouse. The input is a video stream from the cameras, which the server temporarily records. Specifically, the operation here involves capturing video from the camera device and storing it as digital data within the server.

[0745] Step 2:

[0746] The server analyzes the acquired video data using AI image analysis software. The input is the recorded video data, and the output is the analysis results, including worker movements and location information. This analysis can identify what movements the worker is performing and which stage of work they are in. Specifically, this involves using an image recognition algorithm to detect the worker's movements in each frame and storing the data in a database.

[0747] Step 3:

[0748] The server analyzes the worker's facial expressions from the same video data and identifies their emotional state using emotion recognition technology. The input is again video data, and the output is an evaluation of the worker's emotional state. In this step, facial recognition technology is used to analyze the worker's facial expressions and infer psychological states such as fatigue and stress. Specifically, an emotion recognition API is called to generate an emotion score, which is then fed back to the system.

[0749] Step 4:

[0750] The server evaluates work efficiency based on analysis results and emotional state, and generates improvement suggestions if necessary using a generative AI model. The input is the action analysis results and emotional evaluation, and the output is the improvement suggestions. In this step, current work performance is evaluated in comparison to past data, and optimized suggestions are created by the generative AI model. Specifically, the data is input to the generative AI model as prompt sentences, and suggestions are output.

[0751] Step 5:

[0752] The terminal receives analysis results and improvement suggestions from the server and provides voice instructions to the worker using speech synthesis software. The input is the analysis results and improvement suggestions, and the output is voice instructions. In this step, a speech synthesis API is used to generate speech in a pre-configured language and output it through the speaker. Specifically, it provides real-time instructions to the worker, such as "Please proceed to the next step."

[0753] Step 6:

[0754] The user proceeds with the task by following the voice instructions provided by the terminal. The input is the voice instructions from the terminal, and the output is the execution of the task. The user listens to the instructions, confirms the next action, and then actually performs the task. Specific actions include moving objects or operating equipment based on the instructions.

[0755] (Application Example 2)

[0756] 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".

[0757] In logistics and manufacturing, the challenge lies in improving worker efficiency while reducing psychological and physical burden during work, thereby creating a safe and comfortable working environment. In particular, there is a need to develop systems that appropriately assess worker fatigue and stress, and provide instructions that consider both work efficiency and worker health maintenance.

[0758] 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.

[0759] In this invention, the server includes: information acquisition means for recording the conditions within the work environment; analysis means for analyzing the recorded information data to identify the work content; instruction means for outputting voice instructions to the worker and visually displaying the worker's state based on the analysis results; evaluation means for evaluating the efficiency of the work and generating improvement suggestions; and emotion recognition means for identifying the worker's emotions from the information data. This makes it possible to analyze the worker's actions and emotional state in real time and flexibly provide individual work instructions and appropriate break suggestions.

[0760] "Information acquisition means" refers to devices or functions for recording the conditions of the work environment as digital data.

[0761] "Analysis means" refers to the technology and functions used to process recorded information data in detail and identify the content of the work.

[0762] A "command system" is a system that provides workers with necessary information visually and audibly based on analysis results, with the aim of improving work efficiency.

[0763] An "evaluation tool" is a function that quantitatively or qualitatively assesses the efficiency of work and generates suggestions for areas that need improvement.

[0764] "Emotion recognition means" refers to technology that analyzes information data to understand the emotional state of workers by analyzing their facial expressions and gestures.

[0765] To implement this invention, it is necessary to build a system that utilizes wearable devices such as smart glasses in logistics centers and manufacturing sites. The specific method is described below.

[0766] The server records the worker's movements through information acquisition devices installed in the work environment. These devices include cameras and sensors. This data is transmitted to the server and processed by analysis tools. Specifically, image analysis software (e.g., OpenCV) is used to identify the worker's movements and location. Additionally, emotion recognition AI (e.g., Azure Emotion API) is used to determine the worker's emotional state.

[0767] The smart glasses, acting as a terminal, receive analysis results from a server, output appropriate voice instructions to the worker, and display information on the screen. These instructions not only maximize work efficiency but also offer suggestions for breaks based on the worker's emotional state. The voice instruction function uses speech synthesis technology (e.g., Google Text-to-Speech). The specific operating procedures are adjusted to help the worker efficiently move to the next step while reducing excessive burden.

[0768] Users can follow visual and audio instructions from smart glasses to complete their tasks. This improves work efficiency and allows them to objectively understand their own emotional state and adjust their work pace as needed.

[0769] As a concrete example, in a logistics center, workers stand on the packing line and are instructed on the location and quantity of the next product to pick up through smart glasses. Furthermore, if a worker shows signs of fatigue, a break is automatically suggested immediately. This ensures both smooth workflow and the health management of the workers.

[0770] Example prompts for generative AI models:

[0771] "Please develop a smart glasses app to improve work efficiency in logistics centers. It should analyze workers' movements and emotions in real time, providing voice instructions and visual information as needed. Additionally, it should suggest breaks if it detects fatigue or stress in workers."

[0772] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0773] Step 1:

[0774] The server acquires video data of the work environment through information acquisition devices. The input is real-time video data obtained from cameras and sensors, which is stored in a database. The server then prepares this data for the next step.

[0775] Step 2:

[0776] The server processes the acquired video data using an analysis tool. The input is the video data acquired in step 1, and image analysis software such as OpenCV is used to identify the worker's movements and location information. The output is the analyzed movement information, with the data structured.

[0777] Step 3:

[0778] The server analyzes the worker's emotions using emotion recognition technology. The input is the same video data acquired in step 1, and the Azure Emotion API is used to determine the emotional state from the facial expressions. The output is data on the worker's emotional state.

[0779] Step 4:

[0780] Based on the analysis results, the server generates appropriate instructions for the worker via a control device. The input is the output from steps 2 and 3. Voice instructions are created using Google Text-to-Speech, and visual information is displayed on the smart glasses display. The output is provided to the worker as both voice instructions and visual information.

[0781] Step 5:

[0782] The smart glasses, acting as a terminal, receive instructions from the server and present them to the worker. Input consists of voice instructions and visual information transmitted from the server. The smart glasses play the audio through a speaker and display the information on a screen. Output is a user-friendly interface that is easy for the worker to understand.

[0783] Step 6:

[0784] The user follows instructions from the terminal to complete the task. Input consists of voice instructions and visual information provided by smart glasses. Based on this, the user improves the efficiency of the task by executing the specified procedures. The output is the realization of efficient and safe work.

[0785] 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.

[0786] 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.

[0787] 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 robot 414.

[0788] 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.

[0789] 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.

[0790] 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.

[0791] 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.

[0792] 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.

[0793] 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."

[0794] 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.

[0795] 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.

[0796] 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.

[0797] 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.

[0798] 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.

[0799] 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.

[0800] 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.

[0801] 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.

[0802] 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.

[0803] 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.

[0804] 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.

[0805] 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.

[0806] The following is further disclosed regarding the embodiments described above.

[0807] (Claim 1)

[0808] Image acquisition means for recording conditions within the work environment,

[0809] An analysis means for analyzing the recorded image data to identify the work content,

[0810] An instruction means that outputs voice instructions to the worker based on the aforementioned analysis results,

[0811] An evaluation means for evaluating the efficiency of the aforementioned work and generating improvement suggestions,

[0812] A system that includes this.

[0813] (Claim 2)

[0814] The system according to claim 1, wherein the instruction means customizes the optimal work instructions based on productivity data for each worker.

[0815] (Claim 3)

[0816] The system according to claim 1, wherein the evaluation means automatically generates a standard operating manual based on the analysis results.

[0817] "Example 1"

[0818] (Claim 1)

[0819] A means of acquiring information to understand the situation within the workspace,

[0820] Information analysis means for analyzing the acquired information to identify the work content,

[0821] A voice output means that provides instructions to the worker based on the analysis results,

[0822] An evaluation means for generating proposals to optimize the effectiveness of the aforementioned work,

[0823] A means for automatically creating standard operating procedures based on data analysis results,

[0824] A system that includes this.

[0825] (Claim 2)

[0826] The system according to claim 1, wherein the voice output means customizes optimal work instructions based on work efficiency data for each worker.

[0827] (Claim 3)

[0828] The system according to claim 1, wherein the information analysis means performs analysis using a generated AI model to precisely grasp the content of the work.

[0829] "Application Example 1"

[0830] (Claim 1)

[0831] A sensor acquisition means for recording conditions within the work environment,

[0832] A data analysis means that analyzes the recorded data to identify the work content,

[0833] An instruction output means that outputs voice and visual instructions to the worker based on the analysis results,

[0834] A means for evaluating the efficiency of the aforementioned work and generating improvement suggestions,

[0835] A device that transmits the aforementioned data to a server in real time and has the potential to visually present instructions,

[0836] A system that includes this.

[0837] (Claim 2)

[0838] The system according to claim 1, wherein the instruction output means customizes the optimal work instructions based on individual worker data.

[0839] (Claim 3)

[0840] The system according to claim 1, wherein the performance evaluation means automatically generates standardization work guidelines based on the analysis results.

[0841] "Example 2 of combining an emotion engine"

[0842] (Claim 1)

[0843] Image acquisition means for recording conditions within the work environment,

[0844] An analysis means for analyzing the recorded image data to identify the work content,

[0845] An instruction means that outputs voice instructions to the worker based on the aforementioned analysis results,

[0846] An emotion recognition method that analyzes the facial expressions of workers and identifies their emotional state,

[0847] An evaluation means for evaluating the efficiency of the aforementioned work and generating improvement suggestions,

[0848] A system that includes this.

[0849] (Claim 2)

[0850] The system according to claim 1, wherein the instruction means customizes voice instructions according to the emotional state of the worker.

[0851] (Claim 3)

[0852] The system according to claim 1, wherein the evaluation means automatically generates standard work guidelines based on the analysis results.

[0853] "Application example 2 when combining with an emotional engine"

[0854] (Claim 1)

[0855] A means of acquiring information to record the conditions within the work environment,

[0856] An analysis means for analyzing the recorded information data to identify the work content,

[0857] An instruction means that outputs voice instructions to the worker based on the analysis results and visually displays the worker's status,

[0858] An evaluation means for evaluating the efficiency of the aforementioned work and generating improvement suggestions,

[0859] An emotion recognition means for identifying the worker's emotions from the aforementioned information data,

[0860] A system that includes this.

[0861] (Claim 2)

[0862] The system according to claim 1, wherein the instruction means customizes optimal work instructions based on productivity information for each worker and suggests breaks according to the emotional state of the workers.

[0863] (Claim 3)

[0864] The system according to claim 1, wherein the evaluation means automatically generates standard work standards based on the analysis results and makes improvement suggestions that take into account the emotional state of the workers. [Explanation of symbols]

[0865] 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. Image acquisition means for recording conditions within the work environment, An analysis means for analyzing the recorded image data to identify the work content, An instruction means that outputs voice instructions to the worker based on the aforementioned analysis results, An evaluation means for evaluating the efficiency of the aforementioned work and generating improvement suggestions, A system that includes this.

2. The system according to claim 1, wherein the instruction means customizes the optimal work instructions based on productivity data for each worker.

3. The system according to claim 1, wherein the evaluation means automatically generates a standard operating manual based on the analysis results.

Images