system

Abstract

We provide the system. [Solution] Means for obtaining work information and product information, A means of generating an optimal work schedule using generation AI, A means of displaying the generated work schedule on the user terminal, A means to detect changes in real time and update the work schedule, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the logistics business, there are problems such as chronic labor shortages, inefficiencies in creating work schedules, and resulting productivity variations and business delays. In conventional systems, it is difficult to quickly generate a work schedule that appropriately takes into account the skills and workload of workers, and furthermore, it is required to flexibly respond to situations that change in real time. Solving such problems specific to the logistics business is an object of this invention.

Means for Solving the Problems

[0005] To solve this problem, the present invention provides a system equipped with means for acquiring work information and product information, and means for generating an optimal work schedule using a generation AI. Furthermore, by providing means for displaying the generated work schedule on a user terminal and detecting changes in real time to quickly update the work schedule, operational efficiency is improved. In addition, by providing means for predicting future labor demand and supply, and means for analyzing past performance data to improve operational efficiency, it enables improved productivity in logistics operations and flexible responses when problems occur.

[0006] "Work information" refers to information such as the schedules, assigned tasks, and progress of workers in logistics operations.

[0007] "Product information" refers to information about the attributes of products involved in the logistics process, such as size, weight, characteristics, and storage conditions.

[0008] "Generative AI" refers to generative artificial intelligence technology that analyzes large amounts of data, learns patterns, and performs predictions and optimizations.

[0009] "Work schedule" refers to a systematically planned schedule outlining the allocation and time distribution of tasks in logistics.

[0010] A "user terminal" refers to a computer device that displays generated information and allows users to operate and verify it.

[0011] "Real-time changes" refers to the system immediately responding to changes or events that are currently occurring or have occurred in the past.

[0012] "Labor demand and supply" refers to the number of workers needed for logistics operations and the availability of personnel who can provide that work.

[0013] "Performance data" refers to data that includes the results, progress, and work efficiency of tasks recorded in the past. [Brief explanation of the drawing]

[0014] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] [[ID=Z7]]It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0015] An example of an embodiment of the system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a numbered 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.

[0018] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] 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."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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".

[0035] This invention is implemented as a system for generating and updating efficient work schedules in logistics operations in real time. The system quickly acquires work information and product information, and automatically generates an optimal work schedule using an AI model based on this information. Furthermore, it displays this schedule on the user's terminal and has a mechanism to quickly respond to changes that occur in real time.

[0036] Specifically, the server first retrieves worker skills, past work performance, shift information, and product information from the database. This allows it to accumulate basic information about current staffing and work content. By verifying data integrity and performing necessary data cleaning at this stage, it becomes possible to create highly accurate schedules.

[0037] The server then passes the collected information to the generating AI, which generates an overall optimized schedule. The AI ​​takes into account the characteristics of each worker and creates an optimal work schedule based on the principle of putting the right person in the right place. This generated schedule clarifies the start time and person in charge of each task, streamlining the workflow.

[0038] The terminal then displays the generated schedule to the user in an interactive dashboard format. The user can use this information to issue necessary instructions to each worker, enabling smooth on-site operations.

[0039] Furthermore, the server monitors real-time data from the work site and logistics environment. This data includes worker attendance, the progress of incoming and outgoing shipments, and even unexpected changes. If a change is detected, the server restarts the AI ​​model and quickly generates a new schedule. The updated schedule is immediately notified to the user's terminal, allowing for quick adjustments to the workflow.

[0040] For example, in the event of a sudden staff shortage or an unexpected arrival of goods, the system quickly reallocates tasks to other workers or modifies work procedures to address the situation. This minimizes potential delays and disruptions while maintaining the overall efficiency of logistics operations. In this way, the invention provides the flexibility and efficiency required in the logistics industry, optimizing operations.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The server retrieves necessary data from the database, such as worker information, work processes, skill maps, and product information. Based on this information, it understands all current operational resources and requirements.

[0044] Step 2:

[0045] The server formats the acquired data and supplies it to the generated AI model. During this process, it performs a cleaning process to ensure there are no missing or inconsistent data, preparing the model for accurate input.

[0046] Step 3:

[0047] The server uses the formatted data to run a generation AI and create an optimal work schedule. The AI ​​takes into account the worker's skill level, current workload, and task priority, enabling efficient task assignment.

[0048] Step 4:

[0049] The terminal displays the generated work schedule to the user. The user can view assignments and timelines for each worker through an interactive dashboard.

[0050] Step 5:

[0051] The server monitors the real-time status of the work site and immediately detects any changes in attendance or work progress. Based on this information, a new schedule is generated in real time using a generation AI.

[0052] Step 6:

[0053] Users receive update information from the server and quickly update their on-site work instructions. If necessary changes occur, users can immediately implement countermeasures to avoid delays in their work.

[0054] (Example 1)

[0055] 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."

[0056] Modern logistics operations demand efficient schedule management and flexible, real-time responses. In particular, frequent revisions to plans due to changes in work and inventory information are necessary, and performing these revisions quickly and accurately is a challenge. Furthermore, appropriate personnel placement, considering each worker's skills and characteristics, is a crucial factor directly impacting operational efficiency. However, traditional methods often involve manual data consistency checks and detailed schedule generation / updates, making rapid response and optimization difficult.

[0057] 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.

[0058] In this invention, the server includes means for acquiring work information and item information, means for verifying data integrity and performing data cleaning when acquiring information from the database, and means for generating an optimal work schedule using a generation AI. This automates on-site schedule management and enables real-time optimization of operations and flexible responses.

[0059] "Work information" refers to information about individual tasks in logistics operations, their progress, the equipment used, and the skills required.

[0060] "Item information" refers to detailed information about goods handled in logistics operations, such as the type, quantity, storage location, and scheduled shipping time.

[0061] A "database" is a system for efficiently storing, searching, and updating large amounts of information that is managed and operated.

[0062] "Data integrity" means maintaining the consistency and accuracy of data and ensuring that there are no inconsistencies or irregularities between data.

[0063] "Data cleaning" is the process of removing or correcting duplicate, incomplete, or incorrect data within a database.

[0064] "Generative AI" is an artificial intelligence technology that learns from vast amounts of data and automatically formulates new plans and predictions.

[0065] A "work schedule" is a plan that outlines the start times and assignments for each task in logistics operations.

[0066] The system in this invention is designed to efficiently generate and update work schedules in real time in logistics operations. The server plays a primary role in collecting work information and item information from a database. Database operations such as SQL queries are used for this information collection. The acquired data is first checked for consistency, and inaccurate or duplicate data is removed or corrected in a data cleaning process.

[0067] The server then uses the verified data to input prompts into the generating AI model. An example of such a prompt might be, "Create a work schedule for tomorrow at the logistics center. The workers' skill data is as follows..." Based on the specified information, the generating AI model generates an overall optimized work schedule. In doing so, the AI ​​considers the characteristics and past performance of the workers to propose a schedule that is appropriate for each individual.

[0068] The generated schedule is displayed to the user via the device as an intuitive and easy-to-understand interactive dashboard. Based on this information, the user can issue specific instructions to each worker. Furthermore, the device monitors work progress and notifies the user of any necessary changes in real time.

[0069] The server also monitors the external environment and on-site conditions in real time, and if unexpected changes (such as worker absences or delays in the logistics schedule) are detected, it restarts the AI ​​model to quickly generate a new schedule. This allows users to always proceed with their work based on the latest information, significantly improving the efficiency and flexibility of the entire logistics operation.

[0070] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0071] Step 1:

[0072] The server collects work information and item information. It uses information obtained from a database as input. This information includes worker skills, past work performance, and product information. The server retrieves this data using SQL queries and subjects the resulting dataset to consistency checks and data cleaning. Specifically, it corrects incomplete data and removes duplicates.

[0073] Step 2:

[0074] The server passes data whose integrity has been verified to the generating AI model. The input is data that has been cleaned in the previous step. At this time, a prompt is given, such as "Create a work schedule for the logistics center. The worker's skill information is as follows..." The generating AI model uses this information to generate the optimal task assignment for the workers. The output is a work schedule that clearly specifies the start time and the person in charge.

[0075] Step 3:

[0076] The terminal displays the generated work schedule to the user. The input is a completed schedule sent from the server. The terminal converts this content into an interactive dashboard format, making it easy for the user to understand. Here, a graphical user interface is used to visually show the progress of the work. Specifically, the user can issue instructions to workers based on the displayed information.

[0077] Step 4:

[0078] The server monitors work status and the logistics environment in real time. Inputs include continuous data from sensors and management systems. The server monitors data such as attendance, task progress, and inventory fluctuations, and immediately instructs the AI ​​model to regenerate the schedule as needed. The output is the updated schedule information, which is immediately sent to the terminal. This allows users to quickly proceed with their work based on a work plan that reflects the latest situation.

[0079] (Application Example 1)

[0080] 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."

[0081] In logistics operations, a system that can respond flexibly while increasing productivity is essential, as it requires the optimization of work schedules and the ability to respond to changes in real time. However, existing systems make it difficult to provide work instructions to individual workers quickly and effectively, which limits the efficiency of operations.

[0082] 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.

[0083] In this invention, the server includes means for acquiring work information and product information, means for generating an optimal work schedule using a generation AI, means for displaying the generated work schedule through a user interface, means for detecting changes in real time and updating the work schedule, and means for presenting work instructions to workers in real time using a display device. This enables efficient schedule management and real-time presentation of work instructions in logistics operations.

[0084] "Work information" refers to data on workers' skills, past work performance, and current staffing levels in logistics operations.

[0085] "Product information" refers to data regarding the types, quantities, and delivery status of products handled at the logistics center.

[0086] "Generative AI" is an artificial intelligence model that automatically generates the optimal work schedule based on collected data.

[0087] A "user interface" is a screen display method that allows workers and administrators to view generated work schedules and operate them as needed.

[0088] "Means for detecting changes in real time" refers to sensors and data processing functions that instantly capture unexpected changes in the logistics field and the attendance status of workers, and reflect them in the schedule.

[0089] A "display device" is a visual display device that can be worn by a worker, and is hardware used to visually present work instructions.

[0090] This invention is designed to provide an efficient and flexible scheduling management system for logistics operations. The server retrieves work and product information from a database and processes this information. Specifically, a Python program collects this data, verifies data integrity, and performs necessary data cleaning. The cleaned data is then passed to a generative AI model to generate an optimal work schedule. This generative AI model can utilize advanced machine learning algorithms, such as OpenAI's GPT series.

[0091] The terminal displays the generated work schedule in real time through the user interface. Work instructions are visually presented using smart glasses worn by the worker as a display device. By utilizing APIs from Google® Glass® and Microsoft® HoloLens®, the user interface is interactively designed, allowing workers to access information hands-free.

[0092] Users can monitor the progress and changes in logistics operations in real time and issue appropriate instructions based on the new schedule generated by the system. This process allows for rapid response to fluctuations such as unexpected product arrivals or staff shortages. A concrete example of a prompt message is, "Use the following information to generate the optimal work schedule for the logistics center." This leads to improved productivity and more efficient logistics operations.

[0093] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0094] Step 1:

[0095] The server retrieves work information and product information from the database. This input information includes worker skills, past work performance, and product details. The server performs consistency checks and data cleaning on the retrieved data to prepare it as highly accurate input data for the AI ​​model.

[0096] Step 2:

[0097] The server passes the prepared data to the AI ​​model. This prompt message instructs the AI, for example, "Generate the optimal work schedule based on the current status of the logistics center." The AI ​​model analyzes the data according to the instructions and outputs an optimized work schedule.

[0098] Step 3:

[0099] The server sends the generated work schedule to the terminal. The terminal receives this information and displays it interactively through the user interface. This display visually shows the start time and assigned person for each task.

[0100] Step 4:

[0101] The terminal displays work instructions to the worker in real time through the smart glasses' display device. This allows the worker to check information and perform tasks hands-free.

[0102] Step 5:

[0103] Users monitor the real-time status within the logistics center. If changes such as unexpected product arrivals or worker absences are detected, the server uses the AI ​​model to generate a new schedule.

[0104] Step 6:

[0105] The server resends the new schedule to the terminal and modifies the work details as needed. The terminal then displays this updated information again on the smart glasses, quickly communicating instructions to the worker.

[0106] 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.

[0107] This invention is a system designed to improve the efficiency of logistics operations, optimizing work schedules while also considering user emotions. The system acquires work information and product information, and based on this, generates an optimal work schedule using an AI model. This process includes a function to detect changes in real time and dynamically update the work schedule.

[0108] Furthermore, this system incorporates an emotion engine that recognizes the user's emotions, adjusting the presentation of generated work schedules and the interface to match the user's psychological state. This emotion engine analyzes the user's emotions from their facial expressions, tone of voice, and input information, and optimizes the way tasks are presented based on that feedback.

[0109] The server retrieves worker skills, shift information, and product information from the database and formats it as input data for the generating AI model. Using this data, the AI ​​generates an efficient and balanced work schedule. At this stage, user emotional data is also taken into account, and the priority of tasks and assignment of personnel are adjusted to reduce psychological burden.

[0110] The terminal displays the generated work schedule to the user in an interactive format. This display is dynamically adjusted by an emotion engine to ensure the user does not experience stress. For example, if the system determines that the user is tired, it will provide a simplified view that is easier to read.

[0111] Users can check schedules via their terminals, issue appropriate instructions to each worker, and manage the progress of their work. Even in the event of real-time changes in work status or unexpected problems, the server instantly generates a new schedule and notifies the user. This enables flexible work progress.

[0112] For example, when unexpected workloads increase, the system immediately provides feedback, and the emotional engine adjusts the schedule and interface by adding explanations to alleviate user anxiety. As a result, users can respond to tasks quickly while reducing psychological stress. In this way, this system is a groundbreaking logistics support technology that balances efficiency and ergonomics.

[0113] The following describes the processing flow.

[0114] Step 1:

[0115] The server retrieves worker information, work processes, skill maps, and product information from the database. This collects the input data necessary for efficient schedule generation.

[0116] Step 2:

[0117] The server formats the acquired data and inputs it into the generating AI model. Here, it resolves data inconsistencies and converts the data into a format optimized for schedule generation.

[0118] Step 3:

[0119] Using a generative AI model, the server generates an optimal work schedule. The AI ​​considers the worker's skills and workload, as well as the priority of the tasks, to efficiently assign tasks.

[0120] Step 4:

[0121] The emotion engine collects emotional data from user reactions and input, and the server adjusts how the schedule is presented based on this information. For example, if the user is feeling stressed, important information may be displayed in a simplified format, or tasks may be presented in a step-by-step manner.

[0122] Step 5:

[0123] The device displays the generated schedule to the user. The display format reflects feedback from the sentiment engine, presenting information in the least burdensome way for the user.

[0124] Step 6:

[0125] Users can check the schedule on their terminal and communicate necessary instructions to each worker. They can also send feedback on the schedule to the system.

[0126] Step 7:

[0127] The server monitors the real-time situation on-site, and if any changes occur, it immediately restarts the generating AI model and emotion engine to regenerate a new schedule and presentation method. This new schedule is immediately sent to the terminal and notified to the user.

[0128] (Example 2)

[0129] 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".

[0130] Traditional logistics systems faced the challenge of balancing operational efficiency with minimizing the psychological burden on workers. Furthermore, they lacked real-time updates to work schedules and insufficient adjustments to work schedules that considered user emotions, thus limiting operational flexibility and human engineering capabilities.

[0131] 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.

[0132] In this invention, the server includes means for collecting work information and product information, means for generating an optimal work schedule using a generation AI model, and emotion analysis means for analyzing the user's psychological state and adjusting the way tasks are presented. This enables the generation of efficient work schedules, reduction of psychological burden, and dynamic real-time work adjustments.

[0133] "Work information" refers to information that shows the progress of work in logistics operations, the person in charge, and the details of the work.

[0134] "Product information" refers to information that shows detailed attributes and classifications of products related to logistics operations.

[0135] A "generative AI model" refers to artificial intelligence technology that generates an optimal work schedule based on given input data.

[0136] A "human-machine interface" refers to technologies that include screens and input devices for users to interact with computer systems.

[0137] "Emotional analysis methods" refer to technologies that analyze a user's facial expressions, tone of voice, and other factors to determine their psychological state.

[0138] "Performance information" refers to data that shows the history and results of past work.

[0139] This invention is a system designed to maximize the efficiency of logistics operations while reducing the psychological burden on workers. The server collects work information and product information. This collection includes a process of referencing a database to obtain worker skills, shift information, and product characteristics. The collected information is formatted into a format that can be processed by a generative AI model. The generative AI model utilizes commonly used artificial intelligence frameworks and pre-trained models.

[0140] The device is equipped with an emotion analysis engine to sense the user's psychological state. Using the camera and microphone, it collects the user's facial expressions and voice tone, which the emotion analysis engine then analyzes. This analysis is used when displaying the generated work schedule, and the interface is dynamically adjusted to minimize user stress.

[0141] Users can check their work schedules provided through their terminals and manage real-time progress and changes. In the event of unexpected work changes or additional tasks, the server generates a new schedule in real time and immediately notifies the user.

[0142] As a concrete example, consider a situation where a sudden additional order occurs. In this case, the server immediately inputs the updated information into the AI ​​model and creates a new, optimal schedule. The terminal interface is then adjusted based on sentiment analysis to present this schedule in a way that is easiest for the user to understand and causes the least psychological pressure.

[0143] An example of a prompt would be: "Generate an optimal work schedule that improves the efficiency of logistics operations while reducing the psychological burden on users. This schedule should take into account worker skills, shift information, product information, and user sentiment data." Using this prompt, the generating AI model can provide a more optimized output.

[0144] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0145] Step 1:

[0146] The server collects work information and product information from the database. Inputs include employee skill data, past shift information, and product characteristic information, and the output is a formatted dataset. Specifically, the server uses database queries to extract this information, complete missing data, and standardize the format.

[0147] Step 2:

[0148] The device collects and analyzes the user's emotional data. It takes the user's facial expressions as input via the camera and their voice tone via the microphone, and outputs the user's emotional status. Specifically, the device's emotional analysis engine processes this data in real time and assigns tags such as "stress" or "fatigue."

[0149] Step 3:

[0150] The server inputs formatted work information, product information, and user sentiment data into the AI ​​model. Based on this input, the AI ​​model generates an optimized work schedule. The output is an optimized work schedule. Specifically, the AI ​​model uses prompt statements to initiate the generation process and calculates the schedule based on the algorithm.

[0151] Step 4:

[0152] The terminal presents the generated work schedule to the user. The interface of the output schedule is adjusted according to the user's emotional status. Specifically, the emotional engine simplifies the schedule, among other measures, to reduce user stress.

[0153] Step 5:

[0154] Users check their schedules via their terminals and respond to changes and problems. Real-time work change information is provided to the server as input, and an updated work schedule is returned as output. Smooth workflow is maintained through user operation and instructions via the terminals.

[0155] (Application Example 2)

[0156] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0157] Logistics operations require the creation and real-time updating of efficient work schedules. However, conventional systems fail to consider the emotions and psychological state of workers, resulting in increased worker stress and decreased work efficiency. Furthermore, the inability to respond immediately to dynamically changing work situations makes real-time optimization of operations a challenge.

[0158] 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.

[0159] In this invention, the server includes means for acquiring work information and product information, means for generating an optimal work schedule using a generation AI, means for analyzing the user's psychological state using emotion recognition technology and adjusting the display of the work schedule, and means for providing a dynamically optimized work schedule using a visualization device. This enables efficient and flexible work progress in accordance with the worker's psychological state, thereby simultaneously achieving work optimization and worker stress reduction.

[0160] "Work information" refers to various data related to logistics operations, including information on the progress of work, worker assignments, and work content.

[0161] "Product information" refers to data about products managed within the logistics system, including information such as product name, quantity, origin and destination of shipment, and storage location.

[0162] "Generative AI" is a type of machine learning model that automatically generates optimal work schedules based on acquired data.

[0163] "User terminal" refers to a general term for computer devices and smart devices used by workers involved in logistics operations, specifically devices used to display work schedules.

[0164] "Real-time change detection" refers to a technology that instantly senses dynamic changes in circumstances that occur during logistics operations and processes that information within the system.

[0165] "Updating the work schedule" refers to the process of readjusting existing work schedules to optimize them based on information acquired in real time.

[0166] "Emotion recognition technology" is a technique that analyzes a user's psychological state from their facial expressions, tone of voice, etc., and is a method for acquiring emotional data.

[0167] "Visualization devices" is a general term for devices used to display information visually, and includes devices such as smart glasses and displays.

[0168] A "dynamically optimized work schedule" refers to a work plan that is constantly optimized, adjusted in real time based on acquired data, and taking into account the user's psychological burden.

[0169] The system implementing this invention utilizes a server, smart glasses as a visualization device, and a user terminal. The server retrieves work information and product information from a database. This data is input into a generating AI model to generate an optimal work schedule. The generating AI model incorporates emotion recognition technology to take into account the user's psychological state. This allows the server to adjust the work schedule based on the user's emotion recognition data.

[0170] User terminals, particularly smart glasses, function as devices that visualize the generated work schedule. The smart glasses display the real-time progress of the work within the user's field of view. They also automatically select a display mode based on the user's emotional state, incorporating features to reduce stress. For example, if the user is feeling fatigued, the information is displayed in a simplified form.

[0171] An example of a prompt might be the instruction, "Generate an optimal schedule that takes user sentiment into account, based on the current logistics tasks." Using this prompt, the generating AI model provides a work schedule tailored to the user form.

[0172] As a concrete example, in a logistics facility, when adjusting the work schedule during peak seasons, a flexible schedule designed to reduce the psychological burden on users is delivered along with real-time task information. This technology allows workers to perform their tasks efficiently while concentrating on their work without experiencing psychological stress.

[0173] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0174] Step 1:

[0175] The server collects work information and product information from the database. This input information includes work progress and product-related details. Based on this acquired data, the server processes the information to a standard format.

[0176] Step 2:

[0177] The server inputs formatted work and product information into a generating AI model. This AI model generates a work schedule based on the prompt "Generate an optimal schedule considering user sentiment based on the current logistics task." The output returns efficient schedule data.

[0178] Step 3:

[0179] Before sending the generated work schedule to the user's terminal, the server uses emotion recognition technology to analyze the user's psychological state. This analysis uses the user's facial expressions and tone of voice, and as a result, the user's emotional data is output.

[0180] Step 4:

[0181] The server adjusts how the generated work schedule is displayed based on the user's emotional data that has been output. Specifically, if user fatigue is detected, the server adjusts the display to show the information in a simplified format. The adjusted display settings are then output.

[0182] Step 5:

[0183] The user terminal, acting as smart glasses, displays the adjusted work schedule received from the server in real time within the user's field of view. Specifically, the information layout within the field of view is automatically applied, providing information in a way that enhances the user's work efficiency and comfort.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] [Second Embodiment]

[0188] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0189] 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.

[0190] 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).

[0191] 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.

[0192] 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.

[0193] 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).

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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".

[0200] This invention is implemented as a system for generating and updating efficient work schedules in logistics operations in real time. The system quickly acquires work information and product information, and automatically generates an optimal work schedule using an AI model based on this information. Furthermore, it displays this schedule on the user's terminal and has a mechanism to quickly respond to changes that occur in real time.

[0201] Specifically, the server first retrieves worker skills, past work performance, shift information, and product information from the database. This allows it to accumulate basic information about current staffing and work content. By verifying data integrity and performing necessary data cleaning at this stage, it becomes possible to create highly accurate schedules.

[0202] The server then passes the collected information to the generating AI, which generates an overall optimized schedule. The AI ​​takes into account the characteristics of each worker and creates an optimal work schedule based on the principle of putting the right person in the right place. This generated schedule clarifies the start time and person in charge of each task, streamlining the workflow.

[0203] The terminal then displays the generated schedule to the user in an interactive dashboard format. The user can use this information to issue necessary instructions to each worker, enabling smooth on-site operations.

[0204] Furthermore, the server monitors real-time data from the work site and logistics environment. This data includes worker attendance, the progress of incoming and outgoing shipments, and even unexpected changes. If a change is detected, the server restarts the AI ​​model and quickly generates a new schedule. The updated schedule is immediately notified to the user's terminal, allowing for quick adjustments to the workflow.

[0205] For example, in the event of a sudden staff shortage or an unexpected arrival of goods, the system quickly reallocates tasks to other workers or modifies work procedures to address the situation. This minimizes potential delays and disruptions while maintaining the overall efficiency of logistics operations. In this way, the invention provides the flexibility and efficiency required in the logistics industry, optimizing operations.

[0206] The following describes the processing flow.

[0207] Step 1:

[0208] The server retrieves necessary data from the database, such as worker information, work processes, skill maps, and product information. Based on this information, it understands all current operational resources and requirements.

[0209] Step 2:

[0210] The server formats the acquired data and supplies it to the generated AI model. During this process, it performs a cleaning process to ensure there are no missing or inconsistent data, preparing the model for accurate input.

[0211] Step 3:

[0212] The server uses the formatted data to run a generation AI that generates an optimal work schedule. The AI ​​considers the worker's skill level, current workload, and task priority, enabling efficient task assignment.

[0213] Step 4:

[0214] The terminal displays the generated work schedule to the user. The user can view assignments and timelines for each worker through an interactive dashboard.

[0215] Step 5:

[0216] The server monitors the real-time status of the work site and immediately detects any changes in attendance or work progress. Based on this information, a new schedule is generated in real time using a generation AI.

[0217] Step 6:

[0218] Users receive update information from the server and quickly update their on-site work instructions. If necessary changes occur, users can immediately implement countermeasures to avoid delays in their work.

[0219] (Example 1)

[0220] 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."

[0221] Modern logistics operations demand efficient schedule management and flexible, real-time responses. In particular, frequent revisions to plans due to changes in work and inventory information are necessary, and performing these revisions quickly and accurately is a challenge. Furthermore, appropriate personnel placement, considering each worker's skills and characteristics, is a crucial factor directly impacting operational efficiency. However, traditional methods often involve manual data consistency checks and detailed schedule generation / updates, making rapid response and optimization difficult.

[0222] 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.

[0223] In this invention, the server includes means for acquiring work information and item information, means for verifying data integrity and performing data cleaning when acquiring information from the database, and means for generating an optimal work schedule using a generation AI. This automates on-site schedule management and enables real-time optimization of operations and flexible responses.

[0224] "Work information" refers to information about individual tasks in logistics operations, their progress, the equipment used, and the skills required.

[0225] "Item information" refers to detailed information about goods handled in logistics operations, such as the type, quantity, storage location, and scheduled shipping time.

[0226] A "database" is a system for efficiently storing, searching, and updating large amounts of information that is managed and operated.

[0227] "Data integrity" means maintaining the consistency and accuracy of data and ensuring that there are no inconsistencies or irregularities between data.

[0228] "Data cleaning" is the process of removing or correcting duplicate, incomplete, or incorrect data within a database.

[0229] "Generative AI" is an artificial intelligence technology that learns from vast amounts of data and automatically formulates new plans and predictions.

[0230] A "work schedule" is a plan that outlines the start times and assignments for each task in logistics operations.

[0231] The system in this invention is designed to efficiently generate and update work schedules in real time in logistics operations. The server plays a primary role in collecting work information and item information from a database. Database operations such as SQL queries are used for this information collection. The acquired data is first checked for consistency, and inaccurate or duplicate data is removed or corrected in a data cleaning process.

[0232] The server then uses the verified data to input prompts into the generating AI model. An example of such a prompt might be, "Create a work schedule for tomorrow at the logistics center. The workers' skill data is as follows..." Based on the specified information, the generating AI model generates an overall optimized work schedule. In doing so, the AI ​​considers the characteristics and past performance of the workers to propose a schedule that is appropriate for each individual.

[0233] The generated schedule is displayed to the user via the device as an intuitive and easy-to-understand interactive dashboard. Based on this information, the user can issue specific instructions to each worker. Furthermore, the device monitors work progress and notifies the user of any necessary changes in real time.

[0234] The server also monitors the external environment and on-site conditions in real time, and if unexpected changes (such as worker absences or delays in the logistics schedule) are detected, it restarts the AI ​​model to quickly generate a new schedule. This allows users to always proceed with their work based on the latest information, significantly improving the efficiency and flexibility of the entire logistics operation.

[0235] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0236] Step 1:

[0237] The server collects work information and item information. It uses information obtained from a database as input. This information includes worker skills, past work performance, and product information. The server retrieves this data using SQL queries and subjects the resulting dataset to consistency checks and data cleaning. Specifically, it corrects incomplete data and removes duplicates.

[0238] Step 2:

[0239] The server passes data whose integrity has been verified to the generating AI model. The input is data that has been cleaned in the previous step. At this time, a prompt is given, such as "Create a work schedule for the logistics center. The worker's skill information is as follows..." The generating AI model uses this information to generate the optimal task assignment for the workers. The output is a work schedule that clearly specifies the start time and the person in charge.

[0240] Step 3:

[0241] The terminal displays the generated work schedule to the user. The input is a completed schedule sent from the server. The terminal converts this content into an interactive dashboard format, making it easy for the user to understand. Here, a graphical user interface is used to visually show the progress of the work. Specifically, the user can issue instructions to workers based on the displayed information.

[0242] Step 4:

[0243] The server monitors work status and the logistics environment in real time. Inputs include continuous data from sensors and management systems. The server monitors data such as attendance, task progress, and inventory fluctuations, and immediately instructs the AI ​​model to regenerate the schedule as needed. The output is the updated schedule information, which is immediately sent to the terminal. This allows users to quickly proceed with their work based on a work plan that reflects the latest situation.

[0244] (Application Example 1)

[0245] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0246] In logistics operations, a system that can respond flexibly while increasing productivity is essential, as it requires the optimization of work schedules and the ability to respond to changes in real time. However, existing systems make it difficult to provide work instructions to individual workers quickly and effectively, which limits the efficiency of operations.

[0247] 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.

[0248] In this invention, the server includes means for acquiring work information and product information, means for generating an optimal work schedule using a generation AI, means for displaying the generated work schedule through a user interface, means for detecting changes in real time and updating the work schedule, and means for presenting work instructions to workers in real time using a display device. This enables efficient schedule management and real-time presentation of work instructions in logistics operations.

[0249] "Work information" refers to data on workers' skills, past work performance, and current staffing levels in logistics operations.

[0250] "Product information" refers to data regarding the types, quantities, and delivery status of products handled at the logistics center.

[0251] "Generative AI" is an artificial intelligence model that automatically generates the optimal work schedule based on collected data.

[0252] A "user interface" is a screen display method that allows workers and administrators to view generated work schedules and operate them as needed.

[0253] "Means for detecting changes in real time" refers to sensors and data processing functions that instantly capture unexpected changes in the logistics field and the attendance status of workers, and reflect them in the schedule.

[0254] A "display device" is a visual display device that can be worn by a worker, and is hardware used to visually present work instructions.

[0255] This invention is designed to provide an efficient and flexible scheduling management system for logistics operations. The server retrieves work and product information from a database and processes this information. Specifically, a Python program collects this data, verifies data integrity, and performs necessary data cleaning. The cleaned data is then passed to a generative AI model to generate an optimal work schedule. This generative AI model can utilize advanced machine learning algorithms, such as OpenAI's GPT series.

[0256] The terminal displays the generated work schedule in real time through the user interface. Work instructions are visually presented using smart glasses worn by the worker as a display device. By utilizing APIs from Google Glass and Microsoft HoloLens, the user interface is interactively designed, allowing workers to access information hands-free.

[0257] Users can monitor the progress and changes in logistics operations in real time and issue appropriate instructions based on the new schedule generated by the system. This process allows for rapid response to fluctuations such as unexpected product arrivals or staff shortages. A concrete example of a prompt message is, "Use the following information to generate the optimal work schedule for the logistics center." This leads to improved productivity and more efficient logistics operations.

[0258] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0259] Step 1:

[0260] The server retrieves work information and product information from the database. This input information includes worker skills, past work performance, and product details. The server performs consistency checks and data cleaning on the retrieved data to prepare it as highly accurate input data for the AI ​​model.

[0261] Step 2:

[0262] The server passes the prepared data to the AI ​​model. This prompt message instructs the AI, for example, "Generate the optimal work schedule based on the current status of the logistics center." The AI ​​model analyzes the data according to the instructions and outputs an optimized work schedule.

[0263] Step 3:

[0264] The server sends the generated work schedule to the terminal. The terminal receives this information and displays it interactively through the user interface. This display visually shows the start time and assigned person for each task.

[0265] Step 4:

[0266] The terminal displays work instructions to the worker in real time through the smart glasses' display device. This allows the worker to check information and perform tasks hands-free.

[0267] Step 5:

[0268] Users monitor the real-time status within the logistics center. If changes such as unexpected product arrivals or worker absences are detected, the server uses the AI ​​model to generate a new schedule.

[0269] Step 6:

[0270] The server resends the new schedule to the terminal and modifies the work details as needed. The terminal then displays this updated information again on the smart glasses, quickly communicating instructions to the worker.

[0271] 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.

[0272] This invention is a system designed to improve the efficiency of logistics operations, optimizing work schedules while also considering user emotions. The system acquires work information and product information, and based on this, generates an optimal work schedule using an AI model. This process includes a function to detect changes in real time and dynamically update the work schedule.

[0273] Furthermore, this system incorporates an emotion engine that recognizes the user's emotions, adjusting the presentation of generated work schedules and the interface to match the user's psychological state. This emotion engine analyzes the user's emotions from their facial expressions, tone of voice, and input information, and optimizes the way tasks are presented based on that feedback.

[0274] The server retrieves worker skills, shift information, and product information from the database and formats it as input data for the generating AI model. Using this data, the AI ​​generates an efficient and balanced work schedule. At this stage, user emotional data is also taken into account, and the priority of tasks and assignment of personnel are adjusted to reduce psychological burden.

[0275] The terminal displays the generated work schedule to the user in an interactive format. This display is dynamically adjusted by an emotion engine to ensure the user does not experience stress. For example, if the system determines that the user is tired, it will provide a simplified view that is easier to read.

[0276] The user checks the schedule through the terminal, gives appropriate instructions to each worker, and manages the progress of the work. Even for the changing work situation in real time and unexpected troubles, the server immediately generates a new schedule and notifies the user of it. This enables the flexible progress of the work.

[0277] As a specific example, when there is a sudden increase in business, the system immediately feeds back this information, and the emotion engine adjusts the schedule and interface, such as adding an explanation to reduce the user's sense of uneasiness. As a result, the user can quickly respond to the work while reducing psychological stress. Thus, this system is an epoch-making logistics support technology that combines efficiency and ergonomics.

[0278] The following describes the processing flow.

[0279] Step 1:

[0280] The server obtains the information of the workers, work processes, skill maps, and product information from the database. Thereby, the input data necessary for efficient schedule generation is collected.

[0281] Step 2:

[0282] The server formats the obtained data and inputs it into the generation AI model. Here, the work of resolving data inconsistencies and converting it into the optimal format for schedule generation is performed.

[0283] Step 3:

[0284] Using the generation AI model, the server generates an optimal work schedule. The AI considers the skills and loads of the workers and the priorities of the work content, and performs efficient task allocation.

[0285] Step 4:

[0286] The emotion engine collects emotion data from the user's reactions and inputs, and based on this information, the server adjusts the presentation method of the schedule. For example, when the user is feeling stressed, important information is presented simply or tasks are presented step by step.

[0287] Step 5:

[0288] The terminal displays the generated schedule to the user. The display format here reflects the feedback from the emotion engine and presents the information in the least burdensome form for the user.

[0289] Step 6:

[0290] The user checks the schedule on the terminal and conveys the necessary instructions to each operator. The user can also send feedback on the schedule to the system.

[0291] Step 7: <able>

[0292] The server monitors the real-time situation at the site. When a change occurs, it immediately restarts the generated AI model and the emotion engine, and regenerates a new schedule and presentation method. This new schedule is immediately sent to the terminal and notified to the user.

[0293] (Example 2)

[0294] Next, Example 2 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".

[0295] In the conventional logistics business system, there was a problem that it was difficult to balance the efficiency of operations and the psychological burden of workers. In addition, the real-time update of the business schedule and the adjustment of the business schedule considering the user's emotions were insufficient, which restricted the flexibility of operations and human engineering.

[0296] 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.

[0297] In this invention, the server includes means for collecting work information and product information, means for generating an optimal work schedule using a generation AI model, and emotion analysis means for analyzing the user's psychological state and adjusting the way tasks are presented. This enables the generation of efficient work schedules, reduction of psychological burden, and dynamic real-time work adjustments.

[0298] "Work information" refers to information that shows the progress of work in logistics operations, the person in charge, and the details of the work.

[0299] "Product information" refers to information that shows detailed attributes and classifications of products related to logistics operations.

[0300] A "generative AI model" refers to artificial intelligence technology that generates an optimal work schedule based on given input data.

[0301] A "human-machine interface" refers to technologies that include screens and input devices for users to interact with computer systems.

[0302] "Emotional analysis methods" refer to technologies that analyze a user's facial expressions, tone of voice, and other factors to determine their psychological state.

[0303] "Performance information" refers to data that shows the history and results of past work.

[0304] This invention is a system for maximizing the efficiency of logistics operations while reducing the psychological burden on workers. The server collects work information and product information. This collection includes the process of obtaining the skills and shift information of workers and the characteristic information of products by referring to the database. The collected information is formatted into a form that can be processed by the generative AI model. As the generative AI model, generally used artificial intelligence frameworks and pre-trained models are utilized.

[0305] The terminal is equipped with a sentiment analysis engine for sensing the psychological state of the user. Using a camera and a microphone, the user's facial expressions and voice tone are collected, and the sentiment analysis engine analyzes them. The analysis results are utilized when displaying the generated work schedule, and the interface is dynamically adjusted to minimize the user's stress.

[0306] The user checks the work schedule provided through the terminal and manages the real-time progress and changes. Regarding unexpected work changes and additional responses that occur at this time, the server generates a new schedule in real time and notifies the user immediately.

[0307] As a specific example, a situation where a particularly urgent additional order occurs is cited. In this case, the server immediately inputs the updated information into the generative AI model and creates a new optimal schedule. The interface of the terminal is adjusted to present this schedule in a form that is most understandable to the user and has less psychological pressure based on sentiment analysis.

[0308] An example of a prompt sentence is: "Please generate an optimal work schedule for reducing the psychological burden of the user while improving the efficiency of logistics operations. At this time, please consider the skills of the workers, shift information, product information, and the user's sentiment data." By using this prompt, the generative AI model can provide more optimized output.

[0309] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0310] Step 1:

[0311] The server collects work information and product information from the database. Inputs include employee skill data, past shift information, and product characteristic information, and the output is a formatted dataset. Specifically, the server uses database queries to extract this information, complete missing data, and standardize the format.

[0312] Step 2:

[0313] The device collects and analyzes the user's emotional data. It takes the user's facial expressions as input via the camera and their voice tone via the microphone, and outputs the user's emotional status. Specifically, the device's emotional analysis engine processes this data in real time and assigns tags such as "stress" or "fatigue."

[0314] Step 3:

[0315] The server inputs formatted work information, product information, and user sentiment data into the AI ​​model. Based on this input, the AI ​​model generates an optimized work schedule. The output is an optimized work schedule. Specifically, the AI ​​model uses prompt statements to initiate the generation process and calculates the schedule based on the algorithm.

[0316] Step 4:

[0317] The terminal presents the generated work schedule to the user. The interface of the output schedule is adjusted according to the user's emotional status. Specifically, the emotional engine simplifies the schedule, among other measures, to reduce user stress.

[0318] Step 5:

[0319] Users check their schedules via their terminals and respond to changes and problems. Real-time work change information is provided to the server as input, and an updated work schedule is received as output. Smooth workflow is maintained through user operation and instruction via the terminals.

[0320] (Application Example 2)

[0321] 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."

[0322] Logistics operations require the creation and real-time updating of efficient work schedules. However, conventional systems fail to consider the emotions and psychological state of workers, resulting in increased worker stress and decreased work efficiency. Furthermore, the inability to respond immediately to dynamically changing work situations makes real-time optimization of operations a challenge.

[0323] 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.

[0324] In this invention, the server includes means for acquiring work information and product information, means for generating an optimal work schedule using a generation AI, means for analyzing the user's psychological state using emotion recognition technology and adjusting the display of the work schedule, and means for providing a dynamically optimized work schedule using a visualization device. This enables efficient and flexible work progress in accordance with the worker's psychological state, thereby simultaneously achieving work optimization and worker stress reduction.

[0325] "Work information" refers to various data related to logistics operations, including information on the progress of work, worker assignments, and work content.

[0326] "Product information" refers to data about products managed within the logistics system, including information such as product name, quantity, origin and destination of shipment, and storage location.

[0327] "Generative AI" is a type of machine learning model that automatically generates optimal work schedules based on acquired data.

[0328] "User terminal" refers to a general term for computer devices and smart devices used by workers involved in logistics operations, specifically devices used to display work schedules.

[0329] "Real-time change detection" refers to a technology that instantly senses dynamic changes in circumstances that occur during logistics operations and processes that information within the system.

[0330] "Updating the work schedule" refers to the process of readjusting existing work schedules to optimize them based on information acquired in real time.

[0331] "Emotion recognition technology" is a technique that analyzes a user's psychological state from their facial expressions, tone of voice, etc., and is a method for acquiring emotional data.

[0332] "Visualization devices" is a general term for devices used to display information visually, and includes devices such as smart glasses and displays.

[0333] A "dynamically optimized work schedule" refers to a work plan that is constantly optimized, adjusted in real time based on acquired data, and taking into account the user's psychological burden.

[0334] The system implementing this invention utilizes a server, smart glasses as a visualization device, and a user terminal. The server retrieves work information and product information from a database. This data is input into a generating AI model to generate an optimal work schedule. The generating AI model incorporates emotion recognition technology to take into account the user's psychological state. This allows the server to adjust the work schedule based on the user's emotion recognition data.

[0335] User terminals, particularly smart glasses, function as devices that visualize the generated work schedule. The smart glasses display the real-time progress of the work within the user's field of view. They also automatically select a display mode based on the user's emotional state, incorporating features to reduce stress. For example, if the user is feeling fatigued, the information is displayed in a simplified form.

[0336] An example of a prompt might be, "Based on the current logistics tasks, generate an optimal schedule that takes user sentiment into consideration." Using this prompt, the generating AI model provides a work schedule tailored to the user form.

[0337] As a concrete example, in a logistics facility, when adjusting the work schedule during peak seasons, a flexible schedule designed to reduce the psychological burden on users is delivered along with real-time task information. This technology allows workers to perform their tasks efficiently while concentrating on their work without experiencing psychological stress.

[0338] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0339] Step 1:

[0340] The server collects work information and product information from the database. This input information includes work progress and product-related details. Based on this acquired data, the server processes the information to a standard format.

[0341] Step 2:

[0342] The server inputs formatted work and product information into a generating AI model. This AI model generates a work schedule based on the prompt "Generate an optimal schedule considering user sentiment based on the current logistics task." The output returns efficient schedule data.

[0343] Step 3:

[0344] Before sending the generated work schedule to the user terminal, the server uses emotion recognition technology to analyze the user's psychological state. This analysis uses the user's facial expressions and tone of voice, and as a result, the user's emotional data is output.

[0345] Step 4:

[0346] The server adjusts how the generated work schedule is displayed based on the user's emotional data that has been output. Specifically, if user fatigue is detected, the server adjusts the display to show the information in a simplified format. The adjusted display settings are then output.

[0347] Step 5:

[0348] The user terminal, acting as smart glasses, displays the adjusted work schedule received from the server in real time within the user's field of view. Specifically, the information layout within the field of view is automatically applied, providing information in a way that enhances the user's work efficiency and comfort.

[0349] 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.

[0350] 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.

[0351] 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.

[0352] [Third Embodiment]

[0353] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0354] 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.

[0355] 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).

[0356] 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.

[0357] 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.

[0358] 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).

[0359] 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.

[0360] 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.

[0361] 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.

[0362] 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.

[0363] 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.

[0364] 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".

[0365] This invention is implemented as a system for generating and updating efficient work schedules in logistics operations in real time. The system quickly acquires work information and product information, and automatically generates an optimal work schedule using an AI model based on this information. Furthermore, it displays this schedule on the user's terminal and has a mechanism to quickly respond to changes that occur in real time.

[0366] Specifically, the server first retrieves worker skills, past work performance, shift information, and product information from the database. This allows it to accumulate basic information about current staffing and work content. By verifying data integrity and performing necessary data cleaning at this stage, it becomes possible to create highly accurate schedules.

[0367] The server then passes the collected information to the generating AI, which generates an overall optimized schedule. The AI ​​takes into account the characteristics of each worker and creates an optimal work schedule based on the principle of putting the right person in the right place. This generated schedule clarifies the start time and person in charge of each task, streamlining the workflow.

[0368] The terminal then displays the generated schedule to the user in an interactive dashboard format. The user can use this information to issue necessary instructions to each worker, enabling smooth on-site operations.

[0369] Furthermore, the server monitors real-time data from the work site and logistics environment. This data includes worker attendance, the progress of incoming and outgoing shipments, and even unexpected changes. If a change is detected, the server restarts the AI ​​model and quickly generates a new schedule. The updated schedule is immediately notified to the user's terminal, allowing for quick adjustments to the workflow.

[0370] For example, in the event of a sudden staff shortage or an unexpected arrival of goods, the system quickly reallocates tasks to other workers or modifies work procedures to address the situation. This minimizes potential delays and disruptions while maintaining the overall efficiency of logistics operations. In this way, the invention provides the flexibility and efficiency required in the logistics industry, optimizing operations.

[0371] The following describes the processing flow.

[0372] Step 1:

[0373] The server retrieves necessary data from the database, such as worker information, work processes, skill maps, and product information. Based on this information, it understands all current operational resources and requirements.

[0374] Step 2:

[0375] The server formats the acquired data and supplies it to the generated AI model. During this process, it performs a cleaning process to ensure there are no missing or inconsistent data, preparing the model for accurate input.

[0376] Step 3:

[0377] The server uses the formatted data to run a generation AI that generates an optimal work schedule. The AI ​​considers the worker's skill level, current workload, and task priority, enabling efficient task assignment.

[0378] Step 4:

[0379] The terminal displays the generated work schedule to the user. The user can view assignments and timelines for each worker through an interactive dashboard.

[0380] Step 5:

[0381] The server monitors the real-time status of the work site and immediately detects any changes in attendance or work progress. Based on this information, a new schedule is generated in real time using a generation AI.

[0382] Step 6:

[0383] Users receive update information from the server and quickly update their on-site work instructions. If necessary changes occur, users can immediately implement countermeasures to avoid delays in their work.

[0384] (Example 1)

[0385] 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."

[0386] Modern logistics operations demand efficient schedule management and flexible, real-time responses. In particular, frequent revisions to plans due to changes in work and inventory information are necessary, and performing these revisions quickly and accurately is a challenge. Furthermore, appropriate personnel placement, considering each worker's skills and characteristics, is a crucial factor directly impacting operational efficiency. However, traditional methods often involve manual data consistency checks and detailed schedule generation / updates, making rapid response and optimization difficult.

[0387] 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.

[0388] In this invention, the server includes means for acquiring work information and item information, means for verifying data integrity and performing data cleaning when acquiring information from the database, and means for generating an optimal work schedule using a generation AI. This automates on-site schedule management and enables real-time optimization of operations and flexible responses.

[0389] "Work information" refers to information about individual tasks in logistics operations, their progress, the equipment used, and the skills required.

[0390] "Item information" refers to detailed information about goods handled in logistics operations, such as the type, quantity, storage location, and scheduled shipping time.

[0391] A "database" is a system for efficiently storing, searching, and updating large amounts of information that is managed and operated.

[0392] "Data integrity" means maintaining the consistency and accuracy of data and ensuring that there are no inconsistencies or irregularities between data.

[0393] "Data cleaning" is the process of removing or correcting duplicate, incomplete, or incorrect data within a database.

[0394] "Generative AI" is an artificial intelligence technology that learns from vast amounts of data and automatically formulates new plans and predictions.

[0395] A "work schedule" is a plan that outlines the start times and assignments for each task in logistics operations.

[0396] The system in this invention is designed to efficiently generate and update work schedules in real time in logistics operations. The server plays a primary role in collecting work information and item information from a database. Database operations such as SQL queries are used for this information collection. The acquired data is first checked for consistency, and inaccurate or duplicate data is removed or corrected in a data cleaning process.

[0397] The server then uses the verified data to input prompts into the generating AI model. An example of such a prompt might be, "Create a work schedule for tomorrow at the logistics center. The workers' skill data is as follows..." Based on the specified information, the generating AI model generates an overall optimized work schedule. In doing so, the AI ​​considers the characteristics and past performance of the workers to propose a schedule that is appropriate for each individual.

[0398] The generated schedule is displayed to the user via the device as an intuitive and easy-to-understand interactive dashboard. Based on this information, the user can issue specific instructions to each worker. Furthermore, the device monitors work progress and notifies the user of any necessary changes in real time.

[0399] The server also monitors the external environment and on-site conditions in real time, and if unexpected changes (such as worker absences or delays in the logistics schedule) are detected, it restarts the AI ​​model to quickly generate a new schedule. This allows users to always proceed with their work based on the latest information, significantly improving the efficiency and flexibility of the entire logistics operation.

[0400] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0401] Step 1:

[0402] The server collects work information and item information. It uses information obtained from a database as input. This information includes worker skills, past work performance, and product information. The server retrieves this data using SQL queries and subjects the resulting dataset to consistency checks and data cleaning. Specifically, it corrects incomplete data and removes duplicates.

[0403] Step 2:

[0404] The server passes data whose integrity has been verified to the generating AI model. The input is data that has been cleaned in the previous step. At this time, a prompt is given, such as "Create a work schedule for the logistics center. The worker's skill information is as follows..." The generating AI model uses this information to generate the optimal task assignment for the workers. The output is a work schedule that clearly specifies the start time and the person in charge.

[0405] Step 3:

[0406] The terminal displays the generated work schedule to the user. The input is a completed schedule sent from the server. The terminal converts this content into an interactive dashboard format, making it easy for the user to understand. Here, a graphical user interface is used to visually show the progress of the work. Specifically, the user can issue instructions to workers based on the displayed information.

[0407] Step 4:

[0408] The server monitors work status and the logistics environment in real time. Inputs include continuous data from sensors and management systems. The server monitors data such as attendance, task progress, and inventory fluctuations, and immediately instructs the AI ​​model to regenerate the schedule as needed. The output is the updated schedule information, which is immediately sent to the terminal. This allows users to quickly proceed with their work based on a work plan that reflects the latest situation.

[0409] (Application Example 1)

[0410] 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."

[0411] In logistics operations, a system that can respond flexibly while increasing productivity is essential, as it requires the optimization of work schedules and the ability to respond to changes in real time. However, existing systems make it difficult to provide work instructions to individual workers quickly and effectively, which limits the efficiency of operations.

[0412] 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.

[0413] In this invention, the server includes means for acquiring work information and product information, means for generating an optimal work schedule using a generation AI, means for displaying the generated work schedule through a user interface, means for detecting changes in real time and updating the work schedule, and means for presenting work instructions to workers in real time using a display device. This enables efficient schedule management and real-time presentation of work instructions in logistics operations.

[0414] "Work information" refers to data on workers' skills, past work performance, and current staffing levels in logistics operations.

[0415] "Product information" refers to data regarding the types, quantities, and delivery status of products handled at the logistics center.

[0416] "Generative AI" is an artificial intelligence model that automatically generates the optimal work schedule based on collected data.

[0417] A "user interface" is a screen display method that allows workers and administrators to view generated work schedules and operate them as needed.

[0418] "Means for detecting changes in real time" refers to sensors and data processing functions that instantly capture unexpected changes in the logistics field and the attendance status of workers, and reflect them in the schedule.

[0419] A "display device" is a visual display device that can be worn by a worker, and is hardware used to visually present work instructions.

[0420] This invention is designed to provide an efficient and flexible scheduling management system for logistics operations. The server retrieves work and product information from a database and processes this information. Specifically, a Python program collects this data, verifies data integrity, and performs necessary data cleaning. The cleaned data is then passed to a generative AI model to generate an optimal work schedule. This generative AI model can utilize advanced machine learning algorithms, such as OpenAI's GPT series.

[0421] The terminal displays the generated work schedule in real time through the user interface. Work instructions are visually presented using smart glasses worn by the worker as a display device. By utilizing APIs from Google Glass and Microsoft HoloLens, the user interface is interactively designed, allowing workers to access information hands-free.

[0422] Users can monitor the progress and changes in logistics operations in real time and issue appropriate instructions based on the new schedule generated by the system. This process allows for rapid response to fluctuations such as unexpected product arrivals or staff shortages. A concrete example of a prompt message is, "Use the following information to generate the optimal work schedule for the logistics center." This leads to improved productivity and more efficient logistics operations.

[0423] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0424] Step 1:

[0425] The server retrieves work information and product information from the database. This input information includes worker skills, past work performance, and product details. The server performs consistency checks and data cleaning on the retrieved data to prepare it as highly accurate input data for the AI ​​model.

[0426] Step 2:

[0427] The server passes the prepared data to the AI ​​model. This prompt message instructs the AI, for example, "Generate the optimal work schedule based on the current status of the logistics center." The AI ​​model analyzes the data according to the instructions and outputs an optimized work schedule.

[0428] Step 3:

[0429] The server sends the generated work schedule to the terminal. The terminal receives this information and displays it interactively through the user interface. This display visually shows the start time and assigned person for each task.

[0430] Step 4:

[0431] The terminal displays work instructions to the worker in real time through the smart glasses' display device. This allows the worker to check information and perform tasks hands-free.

[0432] Step 5:

[0433] Users monitor the real-time status within the logistics center. If changes such as unexpected product arrivals or worker absences are detected, the server uses the AI ​​model to generate a new schedule.

[0434] Step 6:

[0435] The server resends the new schedule to the terminal and modifies the work details as needed. The terminal then displays this updated information again on the smart glasses, quickly communicating instructions to the worker.

[0436] 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.

[0437] This invention is a system designed to improve the efficiency of logistics operations, optimizing work schedules while also considering user emotions. The system acquires work information and product information, and based on this, generates an optimal work schedule using an AI model. This process includes a function to detect changes in real time and dynamically update the work schedule.

[0438] Furthermore, this system incorporates an emotion engine that recognizes the user's emotions, adjusting the presentation of generated work schedules and the interface to match the user's psychological state. This emotion engine analyzes the user's emotions from their facial expressions, tone of voice, and input information, and optimizes the way tasks are presented based on that feedback.

[0439] The server retrieves worker skills, shift information, and product information from the database and formats it as input data for the generating AI model. Using this data, the AI ​​generates an efficient and balanced work schedule. At this stage, user emotional data is also taken into account, and the priority of tasks and assignment of personnel are adjusted to reduce psychological burden.

[0440] The terminal displays the generated work schedule to the user in an interactive format. This display is dynamically adjusted by an emotion engine to ensure the user does not experience stress. For example, if the system determines that the user is tired, it will provide a simplified view that is easier to read.

[0441] Users can check schedules via their terminals, issue appropriate instructions to each worker, and manage the progress of their work. Even in the event of real-time changes in work status or unexpected problems, the server instantly generates a new schedule and notifies the user. This enables flexible work progress.

[0442] For example, when unexpected workloads increase, the system immediately provides feedback, and the emotional engine adjusts the schedule and interface by adding explanations to alleviate user anxiety. As a result, users can respond to tasks quickly while reducing psychological stress. In this way, this system is a groundbreaking logistics support technology that balances efficiency and ergonomics.

[0443] The following describes the processing flow.

[0444] Step 1:

[0445] The server retrieves worker information, work processes, skill maps, and product information from the database. This collects the input data necessary for efficient schedule generation.

[0446] Step 2:

[0447] The server formats the acquired data and inputs it into the generating AI model. Here, it resolves data inconsistencies and converts the data into a format optimized for schedule generation.

[0448] Step 3:

[0449] Using a generative AI model, the server generates an optimal work schedule. The AI ​​considers the worker's skills and workload, as well as the priority of the tasks, to efficiently assign tasks.

[0450] Step 4:

[0451] The emotion engine collects emotional data from user reactions and input, and the server adjusts how the schedule is presented based on this information. For example, if the user is feeling stressed, important information may be displayed in a simplified format, or tasks may be presented in a step-by-step manner.

[0452] Step 5:

[0453] The device displays the generated schedule to the user. The display format reflects feedback from the sentiment engine, presenting information in the least burdensome way for the user.

[0454] Step 6:

[0455] Users can check the schedule on their terminal and communicate necessary instructions to each worker. They can also send feedback on the schedule to the system.

[0456] Step 7:

[0457] The server monitors the real-time situation on-site, and if any changes occur, it immediately restarts the generating AI model and emotion engine to regenerate a new schedule and presentation method. This new schedule is immediately sent to the terminal and notified to the user.

[0458] (Example 2)

[0459] 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."

[0460] Traditional logistics systems faced the challenge of balancing operational efficiency with minimizing the psychological burden on workers. Furthermore, they lacked real-time updates to work schedules and insufficient adjustments to work schedules that considered user emotions, limiting operational flexibility and human engineering capabilities.

[0461] 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.

[0462] In this invention, the server includes means for collecting work information and product information, means for generating an optimal work schedule using a generation AI model, and emotion analysis means for analyzing the user's psychological state and adjusting the way tasks are presented. This enables the generation of efficient work schedules, reduction of psychological burden, and dynamic real-time work adjustments.

[0463] "Work information" refers to information that shows the progress of work in logistics operations, the person in charge, and the details of the work.

[0464] "Product information" refers to information that shows detailed attributes and classifications of products related to logistics operations.

[0465] A "generative AI model" refers to artificial intelligence technology that generates an optimal work schedule based on given input data.

[0466] A "human-machine interface" refers to technologies that include screens and input devices for users to interact with computer systems.

[0467] "Emotional analysis methods" refer to technologies that analyze a user's facial expressions, tone of voice, and other factors to determine their psychological state.

[0468] "Performance information" refers to data that shows the history and results of past work.

[0469] This invention is a system designed to maximize the efficiency of logistics operations while reducing the psychological burden on workers. The server collects work information and product information. This collection includes a process of referencing a database to obtain worker skills, shift information, and product characteristics. The collected information is formatted into a format that can be processed by a generative AI model. The generative AI model utilizes commonly used artificial intelligence frameworks and pre-trained models.

[0470] The device is equipped with an emotion analysis engine to sense the user's psychological state. Using the camera and microphone, it collects the user's facial expressions and voice tone, which the emotion analysis engine then analyzes. This analysis is used when displaying the generated work schedule, and the interface is dynamically adjusted to minimize user stress.

[0471] Users can check their work schedules provided through their terminals and manage real-time progress and changes. In the event of unexpected work changes or additional tasks, the server generates a new schedule in real time and immediately notifies the user.

[0472] As a concrete example, consider a situation where a sudden additional order occurs. In this case, the server immediately inputs the updated information into the AI ​​model and creates a new, optimal schedule. The terminal interface is then adjusted based on sentiment analysis to present this schedule in a way that is easiest for the user to understand and causes the least psychological pressure.

[0473] An example of a prompt would be: "Generate an optimal work schedule that improves the efficiency of logistics operations while reducing the psychological burden on users. This schedule should take into account worker skills, shift information, product information, and user sentiment data." Using this prompt, the generating AI model can provide a more optimized output.

[0474] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0475] Step 1:

[0476] The server collects work information and product information from the database. Inputs include employee skill data, past shift information, and product characteristic information, and the output is a formatted dataset. Specifically, the server uses database queries to extract this information, complete missing data, and standardize the format.

[0477] Step 2:

[0478] The device collects and analyzes the user's emotional data. It takes the user's facial expressions as input via the camera and their voice tone via the microphone, and outputs the user's emotional status. Specifically, the device's emotional analysis engine processes this data in real time and assigns tags such as "stress" or "fatigue."

[0479] Step 3:

[0480] The server inputs formatted work information, product information, and user sentiment data into the AI ​​model. Based on this input, the AI ​​model generates an optimized work schedule. The output is an optimized work schedule. Specifically, the AI ​​model uses prompt statements to initiate the generation process and calculates the schedule based on the algorithm.

[0481] Step 4:

[0482] The terminal presents the generated work schedule to the user. The interface of the output schedule is adjusted according to the user's emotional status. Specifically, the emotional engine simplifies the schedule, among other measures, to reduce user stress.

[0483] Step 5:

[0484] Users check their schedules via their terminals and respond to changes and problems. Real-time work change information is provided to the server as input, and an updated work schedule is received as output. Smooth workflow is maintained through user operation and instruction via the terminals.

[0485] (Application Example 2)

[0486] 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."

[0487] Logistics operations require the creation and real-time updating of efficient work schedules. However, conventional systems fail to consider the emotions and psychological state of workers, resulting in increased worker stress and decreased work efficiency. Furthermore, the inability to respond immediately to dynamically changing work situations makes real-time optimization of operations a challenge.

[0488] 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.

[0489] In this invention, the server includes means for acquiring work information and product information, means for generating an optimal work schedule using a generation AI, means for analyzing the user's psychological state using emotion recognition technology and adjusting the display of the work schedule, and means for providing a dynamically optimized work schedule using a visualization device. This enables efficient and flexible work progress in accordance with the worker's psychological state, thereby simultaneously achieving work optimization and worker stress reduction.

[0490] "Work information" refers to various data related to logistics operations, including information on the progress of work, worker assignments, and work content.

[0491] "Product information" refers to data about products managed within the logistics system, including information such as product name, quantity, origin and destination of shipment, and storage location.

[0492] "Generative AI" is a type of machine learning model that automatically generates optimal work schedules based on acquired data.

[0493] "User terminal" refers to a general term for computer devices and smart devices used by workers involved in logistics operations, specifically devices used to display work schedules.

[0494] "Real-time change detection" refers to a technology that instantly senses dynamic changes in circumstances that occur during logistics operations and processes that information within the system.

[0495] "Updating the work schedule" refers to the process of readjusting existing work schedules to optimize them based on information acquired in real time.

[0496] "Emotion recognition technology" is a technique that analyzes a user's psychological state from their facial expressions, tone of voice, etc., and is a method for acquiring emotional data.

[0497] "Visualization devices" is a general term for devices used to display information visually, and includes devices such as smart glasses and displays.

[0498] A "dynamically optimized work schedule" refers to a work plan that is constantly optimized, adjusted in real time based on acquired data, and taking into account the user's psychological burden.

[0499] The system implementing this invention utilizes a server, smart glasses as a visualization device, and a user terminal. The server retrieves work information and product information from a database. This data is input into a generating AI model to generate an optimal work schedule. The generating AI model incorporates emotion recognition technology to take into account the user's psychological state. This allows the server to adjust the work schedule based on the user's emotion recognition data.

[0500] User terminals, particularly smart glasses, function as devices that visualize the generated work schedule. The smart glasses display the real-time progress of the work within the user's field of view. They also automatically select a display mode based on the user's emotional state, incorporating features to reduce stress. For example, if the user is feeling fatigued, the information is displayed in a simplified form.

[0501] An example of a prompt might be, "Based on the current logistics tasks, generate an optimal schedule that takes user sentiment into consideration." Using this prompt, the generating AI model provides a work schedule tailored to the user form.

[0502] As a concrete example, in a logistics facility, when adjusting the work schedule during peak seasons, a flexible schedule designed to reduce the psychological burden on users is delivered along with real-time task information. This technology allows workers to perform their tasks efficiently while concentrating on their work without experiencing psychological stress.

[0503] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0504] Step 1:

[0505] The server collects work information and product information from the database. This input information includes work progress and product-related details. Based on this acquired data, the server processes the information to a standard format.

[0506] Step 2:

[0507] The server inputs formatted work and product information into a generating AI model. This AI model generates a work schedule based on the prompt "Generate an optimal schedule considering user sentiment based on the current logistics task." The output returns efficient schedule data.

[0508] Step 3:

[0509] Before sending the generated work schedule to the user terminal, the server uses emotion recognition technology to analyze the user's psychological state. This analysis uses the user's facial expressions and tone of voice, and as a result, the user's emotional data is output.

[0510] Step 4:

[0511] The server adjusts how the generated work schedule is displayed based on the user's emotional data that has been output. Specifically, if user fatigue is detected, the server adjusts the display to show the information in a simplified format. The adjusted display settings are then output.

[0512] Step 5:

[0513] The user terminal, acting as smart glasses, displays the adjusted work schedule received from the server in real time within the user's field of view. Specifically, the information layout within the field of view is automatically applied, providing information in a way that enhances the user's work efficiency and comfort.

[0514] 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.

[0515] 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.

[0516] 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.

[0517] [Fourth Embodiment]

[0518] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0519] 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.

[0520] 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).

[0521] 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.

[0522] 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.

[0523] 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).

[0524] 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.

[0525] 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.

[0526] 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.

[0527] 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.

[0528] 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.

[0529] 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.

[0530] 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".

[0531] This invention is implemented as a system for generating and updating efficient work schedules in logistics operations in real time. The system quickly acquires work information and product information, and automatically generates an optimal work schedule using an AI model based on this information. Furthermore, it displays this schedule on the user's terminal and has a mechanism to quickly respond to changes that occur in real time.

[0532] Specifically, the server first retrieves worker skills, past work performance, shift information, and product information from the database. This allows it to accumulate basic information about current staffing and work content. By verifying data integrity and performing necessary data cleaning at this stage, it becomes possible to create highly accurate schedules.

[0533] The server then passes the collected information to the generating AI, which generates an overall optimized schedule. The AI ​​takes into account the characteristics of each worker and creates an optimal work schedule based on the principle of putting the right person in the right place. This generated schedule clarifies the start time and person in charge of each task, streamlining the workflow.

[0534] The terminal then displays the generated schedule to the user in an interactive dashboard format. The user can use this information to issue necessary instructions to each worker, enabling smooth on-site operations.

[0535] Furthermore, the server monitors real-time data from the work site and logistics environment. This data includes worker attendance, the progress of incoming and outgoing shipments, and even unexpected changes. If a change is detected, the server restarts the AI ​​model and quickly generates a new schedule. The updated schedule is immediately notified to the user's terminal, allowing for quick adjustments to the workflow.

[0536] For example, in the event of a sudden staff shortage or an unexpected arrival of goods, the system quickly reallocates tasks to other workers or modifies work procedures to address the situation. This minimizes potential delays and disruptions while maintaining the overall efficiency of logistics operations. In this way, the invention provides the flexibility and efficiency required in the logistics industry, optimizing operations.

[0537] The following describes the processing flow.

[0538] Step 1:

[0539] The server retrieves necessary data from the database, such as worker information, work processes, skill maps, and product information. Based on this information, it understands all current operational resources and requirements.

[0540] Step 2:

[0541] The server formats the acquired data and supplies it to the generated AI model. During this process, it performs a cleaning process to ensure there are no missing or inconsistent data, preparing the model for accurate input.

[0542] Step 3:

[0543] The server uses the formatted data to run a generation AI that generates an optimal work schedule. The AI ​​considers the worker's skill level, current workload, and task priority, enabling efficient task assignment.

[0544] Step 4:

[0545] The terminal displays the generated work schedule to the user. The user can view assignments and timelines for each worker through an interactive dashboard.

[0546] Step 5:

[0547] The server monitors the real-time status of the work site and immediately detects any changes in attendance or work progress. Based on this information, a new schedule is generated in real time using a generation AI.

[0548] Step 6:

[0549] Users receive update information from the server and quickly update their on-site work instructions. If necessary changes occur, users can immediately implement countermeasures to avoid delays in their work.

[0550] (Example 1)

[0551] 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".

[0552] Modern logistics operations demand efficient schedule management and flexible, real-time responses. In particular, frequent revisions to plans due to changes in work and inventory information are necessary, and performing these revisions quickly and accurately is a challenge. Furthermore, appropriate personnel placement, considering each worker's skills and characteristics, is a crucial factor directly impacting operational efficiency. However, traditional methods often involve manual data consistency checks and detailed schedule generation / updates, making rapid response and optimization difficult.

[0553] 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.

[0554] In this invention, the server includes means for acquiring work information and item information, means for verifying data integrity and performing data cleaning when acquiring information from the database, and means for generating an optimal work schedule using a generation AI. This automates on-site schedule management and enables real-time optimization of operations and flexible responses.

[0555] "Work information" refers to information about individual tasks in logistics operations, their progress, the equipment used, and the skills required.

[0556] "Item information" refers to detailed information about goods handled in logistics operations, such as the type, quantity, storage location, and scheduled shipping time.

[0557] A "database" is a system for efficiently storing, searching, and updating large amounts of information that is managed and operated.

[0558] "Data integrity" means maintaining the consistency and accuracy of data and ensuring that there are no inconsistencies or irregularities between data.

[0559] "Data cleaning" is the process of removing or correcting duplicate, incomplete, or incorrect data within a database.

[0560] "Generative AI" is an artificial intelligence technology that learns from vast amounts of data and automatically formulates new plans and predictions.

[0561] A "work schedule" is a plan that outlines the start times and assignments for each task in logistics operations.

[0562] The system in this invention is designed to efficiently generate and update work schedules in real time in logistics operations. The server plays a primary role in collecting work information and item information from a database. Database operations such as SQL queries are used for this information collection. The acquired data is first checked for consistency, and inaccurate or duplicate data is removed or corrected in a data cleaning process.

[0563] The server then uses the verified data to input prompts into the generating AI model. An example of such a prompt might be, "Create a work schedule for tomorrow at the logistics center. The workers' skill data is as follows..." Based on the specified information, the generating AI model generates an overall optimized work schedule. In doing so, the AI ​​considers the characteristics and past performance of the workers to propose a schedule that is appropriate for each individual.

[0564] The generated schedule is displayed to the user via the device as an intuitive and easy-to-understand interactive dashboard. Based on this information, the user can issue specific instructions to each worker. Furthermore, the device monitors work progress and notifies the user of any necessary changes in real time.

[0565] The server also monitors the external environment and on-site conditions in real time, and if unexpected changes (such as worker absences or delays in the logistics schedule) are detected, it restarts the AI ​​model to quickly generate a new schedule. This allows users to always proceed with their work based on the latest information, significantly improving the efficiency and flexibility of the entire logistics operation.

[0566] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0567] Step 1:

[0568] The server collects work information and item information. It uses information obtained from a database as input. This information includes worker skills, past work performance, and product information. The server retrieves this data using SQL queries and subjects the resulting dataset to consistency checks and data cleaning. Specifically, it corrects incomplete data and removes duplicates.

[0569] Step 2:

[0570] The server passes data whose integrity has been verified to the generating AI model. The input is data that has been cleaned in the previous step. At this time, a prompt is given, such as "Create a work schedule for the logistics center. The worker's skill information is as follows..." The generating AI model uses this information to generate the optimal task assignment for the workers. The output is a work schedule that clearly specifies the start time and the person in charge.

[0571] Step 3:

[0572] The terminal displays the generated work schedule to the user. The input is a completed schedule sent from the server. The terminal converts this content into an interactive dashboard format, making it easy for the user to understand. Here, a graphical user interface is used to visually show the progress of the work. Specifically, the user can issue instructions to workers based on the displayed information.

[0573] Step 4:

[0574] The server monitors work status and the logistics environment in real time. Inputs include continuous data from sensors and management systems. The server monitors data such as attendance, task progress, and inventory fluctuations, and immediately instructs the AI ​​model to regenerate the schedule as needed. The output is the updated schedule information, which is immediately sent to the terminal. This allows users to quickly proceed with their work based on a work plan that reflects the latest situation.

[0575] (Application Example 1)

[0576] 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".

[0577] In logistics operations, a system that can respond flexibly while increasing productivity is essential, as it requires the optimization of work schedules and the ability to respond to changes in real time. However, existing systems make it difficult to provide work instructions to individual workers quickly and effectively, which limits the efficiency of operations.

[0578] 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.

[0579] In this invention, the server includes means for acquiring work information and product information, means for generating an optimal work schedule using a generation AI, means for displaying the generated work schedule through a user interface, means for detecting changes in real time and updating the work schedule, and means for presenting work instructions to workers in real time using a display device. This enables efficient schedule management and real-time presentation of work instructions in logistics operations.

[0580] "Work information" refers to data on workers' skills, past work performance, and current staffing levels in logistics operations.

[0581] "Product information" refers to data regarding the types, quantities, and delivery status of products handled at the logistics center.

[0582] "Generative AI" is an artificial intelligence model that automatically generates the optimal work schedule based on collected data.

[0583] A "user interface" is a screen display method that allows workers and administrators to view generated work schedules and operate them as needed.

[0584] "Means for detecting changes in real time" refers to sensors and data processing functions that instantly capture unexpected changes in the logistics field and the attendance status of workers, and reflect them in the schedule.

[0585] A "display device" is a visual display device that can be worn by a worker, and is hardware used to visually present work instructions.

[0586] This invention is designed to provide an efficient and flexible scheduling management system for logistics operations. The server retrieves work and product information from a database and processes this information. Specifically, a Python program collects this data, verifies data integrity, and performs necessary data cleaning. The cleaned data is then passed to a generative AI model to generate an optimal work schedule. This generative AI model can utilize advanced machine learning algorithms, such as OpenAI's GPT series.

[0587] The terminal displays the generated work schedule in real time through the user interface. Work instructions are visually presented using smart glasses worn by the worker as a display device. By utilizing APIs from Google Glass and Microsoft HoloLens, the user interface is interactively designed, allowing workers to access information hands-free.

[0588] Users can monitor the progress and changes in logistics operations in real time and issue appropriate instructions based on the new schedule generated by the system. This process allows for rapid response to fluctuations such as unexpected product arrivals or staff shortages. A concrete example of a prompt message is, "Use the following information to generate the optimal work schedule for the logistics center." This leads to improved productivity and more efficient logistics operations.

[0589] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0590] Step 1:

[0591] The server retrieves work information and product information from the database. This input information includes worker skills, past work performance, and product details. The server performs consistency checks and data cleaning on the retrieved data to prepare it as highly accurate input data for the AI ​​model.

[0592] Step 2:

[0593] The server passes the prepared data to the AI ​​model. This prompt message instructs the AI, for example, "Generate the optimal work schedule based on the current status of the logistics center." The AI ​​model analyzes the data according to the instructions and outputs an optimized work schedule.

[0594] Step 3:

[0595] The server sends the generated work schedule to the terminal. The terminal receives this information and displays it interactively through the user interface. This display visually shows the start time and assigned person for each task.

[0596] Step 4:

[0597] The terminal displays work instructions to the worker in real time through the smart glasses' display device. This allows the worker to check information and perform tasks hands-free.

[0598] Step 5:

[0599] Users monitor the real-time status within the logistics center. If changes such as unexpected product arrivals or worker absences are detected, the server uses the AI ​​model to generate a new schedule.

[0600] Step 6:

[0601] The server resends the new schedule to the terminal and modifies the work details as needed. The terminal then displays this updated information again on the smart glasses, quickly communicating instructions to the worker.

[0602] 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.

[0603] This invention is a system designed to improve the efficiency of logistics operations, optimizing work schedules while also considering user emotions. The system acquires work information and product information, and based on this, generates an optimal work schedule using an AI model. This process includes a function to detect changes in real time and dynamically update the work schedule.

[0604] Furthermore, this system incorporates an emotion engine that recognizes the user's emotions, adjusting the presentation of generated work schedules and the interface to match the user's psychological state. This emotion engine analyzes the user's emotions from their facial expressions, tone of voice, and input information, and optimizes the way tasks are presented based on that feedback.

[0605] The server retrieves worker skills, shift information, and product information from the database and formats it as input data for the generating AI model. Using this data, the AI ​​generates an efficient and balanced work schedule. At this stage, user emotional data is also taken into account, and the priority of tasks and assignment of personnel are adjusted to reduce psychological burden.

[0606] The terminal displays the generated work schedule to the user in an interactive format. This display is dynamically adjusted by an emotion engine to ensure the user does not experience stress. For example, if the system determines that the user is tired, it will provide a simplified view that is easier to read.

[0607] Users can check schedules via their terminals, issue appropriate instructions to each worker, and manage the progress of their work. Even in the event of real-time changes in work status or unexpected problems, the server instantly generates a new schedule and notifies the user. This enables flexible work progress.

[0608] For example, when unexpected workloads increase, the system immediately provides feedback, and the emotional engine adjusts the schedule and interface by adding explanations to alleviate user anxiety. As a result, users can respond to tasks quickly while reducing psychological stress. In this way, this system is a groundbreaking logistics support technology that balances efficiency and ergonomics.

[0609] The following describes the processing flow.

[0610] Step 1:

[0611] The server retrieves worker information, work processes, skill maps, and product information from the database. This collects the input data necessary for efficient schedule generation.

[0612] Step 2:

[0613] The server formats the acquired data and inputs it into the generating AI model. Here, it resolves data inconsistencies and converts the data into a format optimized for schedule generation.

[0614] Step 3:

[0615] Using a generative AI model, the server generates an optimal work schedule. The AI ​​considers the worker's skills and workload, as well as the priority of the tasks, to efficiently assign tasks.

[0616] Step 4:

[0617] The emotion engine collects emotional data from user reactions and input, and the server adjusts how the schedule is presented based on this information. For example, if the user is feeling stressed, important information may be displayed in a simplified format, or tasks may be presented in a step-by-step manner.

[0618] Step 5:

[0619] The device displays the generated schedule to the user. The display format reflects feedback from the sentiment engine, presenting information in the least burdensome way for the user.

[0620] Step 6:

[0621] Users can check the schedule on their terminal and communicate necessary instructions to each worker. They can also send feedback on the schedule to the system.

[0622] Step 7:

[0623] The server monitors the real-time situation on-site, and if any changes occur, it immediately restarts the generating AI model and emotion engine to regenerate a new schedule and presentation method. This new schedule is immediately sent to the terminal and notified to the user.

[0624] (Example 2)

[0625] 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".

[0626] Traditional logistics systems faced the challenge of balancing operational efficiency with minimizing the psychological burden on workers. Furthermore, they lacked real-time updates to work schedules and insufficient adjustments to work schedules that considered user emotions, limiting operational flexibility and human engineering capabilities.

[0627] 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.

[0628] In this invention, the server includes means for collecting work information and product information, means for generating an optimal work schedule using a generation AI model, and emotion analysis means for analyzing the user's psychological state and adjusting the way tasks are presented. This enables the generation of efficient work schedules, reduction of psychological burden, and dynamic real-time work adjustments.

[0629] "Work information" refers to information that shows the progress of work in logistics operations, the person in charge, and the details of the work.

[0630] "Product information" refers to information that shows detailed attributes and classifications of products related to logistics operations.

[0631] A "generative AI model" refers to artificial intelligence technology that generates an optimal work schedule based on given input data.

[0632] A "human-machine interface" refers to technologies that include screens and input devices for users to interact with computer systems.

[0633] "Emotional analysis methods" refer to technologies that analyze a user's facial expressions, tone of voice, and other factors to determine their psychological state.

[0634] "Performance information" refers to data that shows the history and results of past work.

[0635] This invention is a system designed to maximize the efficiency of logistics operations while reducing the psychological burden on workers. The server collects work information and product information. This collection includes a process of referencing a database to obtain worker skills, shift information, and product characteristics. The collected information is formatted into a format that can be processed by a generative AI model. The generative AI model utilizes commonly used artificial intelligence frameworks and pre-trained models.

[0636] The device is equipped with an emotion analysis engine to sense the user's psychological state. Using the camera and microphone, it collects the user's facial expressions and voice tone, which the emotion analysis engine then analyzes. This analysis is used when displaying the generated work schedule, and the interface is dynamically adjusted to minimize user stress.

[0637] Users can check their work schedules provided through their terminals and manage real-time progress and changes. In the event of unexpected work changes or additional tasks, the server generates a new schedule in real time and immediately notifies the user.

[0638] As a concrete example, consider a situation where a sudden additional order occurs. In this case, the server immediately inputs the updated information into the AI ​​model and creates a new, optimal schedule. The terminal interface is then adjusted based on sentiment analysis to present this schedule in a way that is easiest for the user to understand and causes the least psychological pressure.

[0639] An example of a prompt would be: "Generate an optimal work schedule that improves the efficiency of logistics operations while reducing the psychological burden on users. This schedule should take into account worker skills, shift information, product information, and user sentiment data." Using this prompt, the generating AI model can provide a more optimized output.

[0640] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0641] Step 1:

[0642] The server collects work information and product information from the database. Inputs include employee skill data, past shift information, and product characteristic information, and the output is a formatted dataset. Specifically, the server uses database queries to extract this information, complete missing data, and standardize the format.

[0643] Step 2:

[0644] The device collects and analyzes the user's emotional data. It takes the user's facial expressions as input via the camera and their voice tone via the microphone, and outputs the user's emotional status. Specifically, the device's emotional analysis engine processes this data in real time and assigns tags such as "stress" or "fatigue."

[0645] Step 3:

[0646] The server inputs formatted work information, product information, and user sentiment data into the AI ​​model. Based on this input, the AI ​​model generates an optimized work schedule. The output is an optimized work schedule. Specifically, the AI ​​model uses prompt statements to initiate the generation process and calculates the schedule based on the algorithm.

[0647] Step 4:

[0648] The terminal presents the generated work schedule to the user. The interface of the output schedule is adjusted according to the user's emotional status. Specifically, the emotional engine simplifies the schedule, among other measures, to reduce user stress.

[0649] Step 5:

[0650] Users check their schedules via their terminals and respond to changes and problems. Real-time work change information is provided to the server as input, and an updated work schedule is received as output. Smooth workflow is maintained through user operation and instruction via the terminals.

[0651] (Application Example 2)

[0652] 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".

[0653] Logistics operations require the creation and real-time updating of efficient work schedules. However, conventional systems fail to consider the emotions and psychological state of workers, resulting in increased worker stress and decreased work efficiency. Furthermore, the inability to respond immediately to dynamically changing work situations makes real-time optimization of operations a challenge.

[0654] 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.

[0655] In this invention, the server includes means for acquiring work information and product information, means for generating an optimal work schedule using a generation AI, means for analyzing the user's psychological state using emotion recognition technology and adjusting the display of the work schedule, and means for providing a dynamically optimized work schedule using a visualization device. This enables efficient and flexible work progress in accordance with the worker's psychological state, thereby simultaneously achieving work optimization and worker stress reduction.

[0656] "Work information" refers to various data related to logistics operations, including information on the progress of work, worker assignments, and work content.

[0657] "Product information" refers to data about products managed within the logistics system, including information such as product name, quantity, origin and destination of shipment, and storage location.

[0658] "Generative AI" is a type of machine learning model that automatically generates optimal work schedules based on acquired data.

[0659] "User terminal" refers to a general term for computer devices and smart devices used by workers involved in logistics operations, specifically devices used to display work schedules.

[0660] "Real-time change detection" refers to a technology that instantly senses dynamic changes in circumstances that occur during logistics operations and processes that information within the system.

[0661] "Updating the work schedule" refers to the process of readjusting existing work schedules to optimize them based on information acquired in real time.

[0662] "Emotion recognition technology" is a technique that analyzes a user's psychological state from their facial expressions, tone of voice, etc., and is a method for acquiring emotional data.

[0663] "Visualization devices" is a general term for devices used to display information visually, and includes devices such as smart glasses and displays.

[0664] A "dynamically optimized work schedule" refers to a work plan that is constantly optimized, adjusted in real time based on acquired data, and taking into account the user's psychological burden.

[0665] The system implementing this invention utilizes a server, smart glasses as a visualization device, and a user terminal. The server retrieves work information and product information from a database. This data is input into a generating AI model to generate an optimal work schedule. The generating AI model incorporates emotion recognition technology to take into account the user's psychological state. This allows the server to adjust the work schedule based on the user's emotion recognition data.

[0666] User terminals, particularly smart glasses, function as devices that visualize the generated work schedule. The smart glasses display the real-time progress of the work within the user's field of view. They also automatically select a display mode based on the user's emotional state, incorporating features to reduce stress. For example, if the user is feeling fatigued, the information is displayed in a simplified form.

[0667] An example of a prompt might be, "Based on the current logistics tasks, generate an optimal schedule that takes user sentiment into consideration." Using this prompt, the generating AI model provides a work schedule tailored to the user form.

[0668] As a concrete example, in a logistics facility, when adjusting the work schedule during peak seasons, a flexible schedule designed to reduce the psychological burden on users is delivered along with real-time task information. This technology allows workers to perform their tasks efficiently while concentrating on their work without experiencing psychological stress.

[0669] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0670] Step 1:

[0671] The server collects work information and product information from the database. This input information includes work progress and product-related details. Based on this acquired data, the server processes the information to a standard format.

[0672] Step 2:

[0673] The server inputs formatted work and product information into a generating AI model. This AI model generates a work schedule based on the prompt "Generate an optimal schedule considering user sentiment based on the current logistics task." The output returns efficient schedule data.

[0674] Step 3:

[0675] Before sending the generated work schedule to the user terminal, the server uses emotion recognition technology to analyze the user's psychological state. This analysis uses the user's facial expressions and tone of voice, and as a result, the user's emotional data is output.

[0676] Step 4:

[0677] The server adjusts how the generated work schedule is displayed based on the user's emotional data that has been output. Specifically, if user fatigue is detected, the server adjusts the display to show the information in a simplified format. The adjusted display settings are then output.

[0678] Step 5:

[0679] The user terminal, acting as smart glasses, displays the adjusted work schedule received from the server in real time within the user's field of view. Specifically, the information layout within the field of view is automatically applied, providing information in a way that enhances the user's work efficiency and comfort.

[0680] 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.

[0681] 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.

[0682] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0683] 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.

[0684] 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.

[0685] 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.

[0686] 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.

[0687] 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.

[0688] 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."

[0689] 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.

[0690] 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.

[0691] 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.

[0692] 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.

[0693] 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.

[0694] 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.

[0695] 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.

[0696] 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.

[0697] 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.

[0698] 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.

[0699] 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.

[0700] 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.

[0701] The following is further disclosed regarding the embodiments described above.

[0702] (Claim 1)

[0703] Means for obtaining work information and product information,

[0704] A means of generating an optimal work schedule using generation AI,

[0705] A means of displaying the generated work schedule on the user terminal,

[0706] A means to detect changes in real time and update the work schedule,

[0707] A system that includes this.

[0708] (Claim 2)

[0709] The system according to claim 1, further comprising means for predicting future labor demand and supply.

[0710] (Claim 3)

[0711] The system according to claim 1, further comprising means for improving operational efficiency by analyzing past performance data.

[0712] "Example 1"

[0713] (Claim 1)

[0714] Means for acquiring work information and item information,

[0715] A method for verifying data integrity and performing data cleaning when retrieving information from a database,

[0716] A means of generating an optimal work schedule using generation AI,

[0717] A means for interactively displaying the generated work schedule on the user's terminal,

[0718] A means of generating a work plan that considers the characteristics of the workers and places the right people in the right positions,

[0719] A means to detect changes in real time and update the work schedule,

[0720] A system that includes this.

[0721] (Claim 2)

[0722] The system according to claim 1, further comprising means for predicting future labor demand and supply.

[0723] (Claim 3)

[0724] The system according to claim 1, further comprising means for improving operational efficiency by analyzing past performance data.

[0725] "Application Example 1"

[0726] (Claim 1)

[0727] Means for obtaining work information and product information,

[0728] A means of generating an optimal work schedule using generation AI,

[0729] A means of displaying the generated work schedule through a user interface,

[0730] A means to detect changes in real time and update the work schedule,

[0731] A means of presenting work instructions to workers in real time using a display device,

[0732] A system that includes this.

[0733] (Claim 2)

[0734] The system according to claim 1, further comprising means for predicting future labor demand and supply.

[0735] (Claim 3)

[0736] The system according to claim 1, further comprising means for improving operational efficiency by analyzing past performance data.

[0737] "Example 2 of combining an emotion engine"

[0738] (Claim 1)

[0739] Means for collecting work information and product information,

[0740] A means of generating an optimal work schedule using a generative AI model,

[0741] A means for displaying the generated work schedule on a human-machine interface,

[0742] A means to detect changes in real time and dynamically update work schedules,

[0743] An emotion analysis tool that analyzes the user's psychological state and adjusts the way tasks are presented,

[0744] A system that includes this.

[0745] (Claim 2)

[0746] The system according to claim 1, further comprising means for predicting future labor demand and supply.

[0747] (Claim 3)

[0748] The system according to claim 1, further comprising means for analyzing accumulated performance information to improve operational efficiency.

[0749] "Application example 2 when combining with an emotional engine"

[0750] (Claim 1)

[0751] Means for obtaining work information and product information,

[0752] A means of generating an optimal work schedule using generation AI,

[0753] A means of displaying the generated work schedule on the user terminal,

[0754] A means to detect changes in real time and update the work schedule,

[0755] A means of analyzing the user's psychological state using emotion recognition technology and adjusting the display of work schedules,

[0756] A means of providing dynamically optimized work schedules using a visualization device,

[0757] A system that includes this.

[0758] (Claim 2)

[0759] The system according to claim 1, further comprising means for predicting future labor demand and supply.

[0760] (Claim 3)

[0761] The system according to claim 1, further comprising means for improving operational efficiency by analyzing past performance data. [Explanation of Symbols]

[0762] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means for obtaining work information and product information, A means of generating an optimal work schedule using generation AI, A means of displaying the generated work schedule on the user terminal, A means to detect changes in real time and update the work schedule, A system that includes this.

2. The system according to claim 1, further comprising means for predicting future labor demand and supply.

3. The system according to claim 1, further comprising means for improving operational efficiency by analyzing past performance data.

Images