system

Abstract

We provide the system. [Solution] A means of analyzing image data to extract visual information and automatically generating tasks in multimedia production, A means for evaluating the workload and suitability of various workers based on extracted information, and assigning tasks to the most suitable workers, A means of automatically creating documents related to work contracts using text generation algorithms and quickly obtaining agreement between the relevant parties, A means of analyzing stakeholder demands using natural language processing technology and reflecting them in the multimedia production process, 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 persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In multimedia production, inefficiency in work progress and an excessive burden on workers have become problems. In particular, there is no proper schedule management or task allocation for workers, resulting in work delays and quality degradation. Also, the process of creating and reaching agreement on related documents is often done manually, requiring time and labor. In order to solve such problems, automatic generation of tasks and efficient allocation to workers, as well as speeding up document processing, are required.

Means for Solving the Problems

[0005] This invention provides a system that extracts visual information by analyzing image data and automatically generates tasks. Based on the extracted information, it evaluates each worker's schedule and skills and automates the optimal assignment. It also generates work contracts using a text generation algorithm, enabling rapid agreement. Furthermore, by using natural language processing, it can accurately analyze the requirements of stakeholders and reflect them in the production process. This system achieves increased work efficiency and reduced workload.

[0006] "Image data" refers to data that represents visual information in a digital format and is used for processing such as image analysis.

[0007] "Visual information" refers to the visually appealing elements contained in images such as paintings and photographs, and includes abstract information and detailed shapes.

[0008] A "task" refers to the specific actions and procedures that should be performed within a particular work process.

[0009] "Workers" refers to personnel who actually perform hands-on tasks and are involved in the implementation of a multimedia project.

[0010] A "schedule" refers to the allocation of tasks and related activities within a certain period of time, and is a plan used to manage their progress.

[0011] A "text generation algorithm" is a type of computer program that automatically generates natural language text based on input data.

[0012] A "work contract" is a document that outlines the work performed and the compensation agreed upon between a worker and an employer.

[0013] "Natural language processing" is a field of technology that enables computers to understand and process human language, and includes speech recognition and text analysis. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

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

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

[0017] In the following embodiments, a labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

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

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

[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 provides a system that streamlines the workflow of multimedia production projects and reduces the burden on workers. This system analyzes image data to extract visual information and automatically generates tasks. Furthermore, it efficiently manages project progress by evaluating workers' schedules and skills and assigning optimal tasks.

[0036] System Configuration

[0037] The present invention consists of the following elements.

[0038] 1. Server

[0039] The server receives image data and extracts visual information using image analysis algorithms. Based on this information, it automatically generates a task list.

[0040] 2. Terminal

[0041] The terminal receives task lists sent from the server and displays them to the user responsible for managing the work. It also manages the worker's schedule and skill information and sends it to the server.

[0042] 3. User

[0043] Users operate the terminal to manage projects and assign tasks to workers. Furthermore, they can review and customize generated contracts, facilitating consensus building with stakeholders.

[0044] Program processing flow

[0045] The server first analyzes the image data and extracts visual features from each scene. Based on this information, it generates detailed tasks. The terminal then displays the generated task list and presents it to the person in charge of managing the work. Information about the worker's schedule and skills is provided from the terminal to the server, and the server automatically assigns the most suitable tasks.

[0046] For example, in the storyboarding of a battle scene, the server generates detailed tasks regarding the enemy character's movements and background effects. These tasks are assigned to the relevant workers via terminals, and their progress is constantly monitored. Furthermore, if a user submits a new request regarding the project, the server analyzes the request and adjusts the necessary tasks accordingly.

[0047] This system will streamline the workflow in multimedia production, reduce the burden on workers, and ensure the consistent delivery of high-quality results.

[0048] The following describes the processing flow.

[0049] Step 1:

[0050] The server receives image data uploaded by users. This image data often consists of storyboard images for various scenes involved in multimedia production.

[0051] Step 2:

[0052] The server analyzes the image data using an image recognition algorithm. Here, it extracts visual features for each scene, character placement information, and other relevant details.

[0053] Step 3:

[0054] The server automatically generates relevant tasks based on the extracted information. For example, it might list tasks related to instructing character movements or changing the background.

[0055] Step 4:

[0056] The terminal displays a task list sent from the server to the user. Based on this information, the user can see the overall picture of the project.

[0057] Step 5:

[0058] The terminal transmits the worker's schedule and skill information to the server. This data also includes information about projects the worker has worked on in the past.

[0059] Step 6:

[0060] The server automatically assigns tasks to the most suitable workers based on the received schedule and skill information. It efficiently distributes tasks, taking into account skill suitability and current workload.

[0061] Step 7:

[0062] The terminal notifies each worker of their assigned task. Workers can then schedule their work based on the tasks they receive and begin their tasks.

[0063] Step 8:

[0064] The user reviews the work contract generated via their device and customizes it as needed. They then send the contract to the relevant parties to reach an agreement.

[0065] Step 9:

[0066] The server monitors the overall project progress and updates the task list accordingly if there are any new requests or changes. These updates are then notified to the user via their terminal.

[0067] (Example 1)

[0068] 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."

[0069] Digital content creation requires the processing of diverse visual data and the appropriate placement of workers in the right roles, but managing these aspects is a time-consuming and laborious process. Furthermore, there is a lack of means to quickly incorporate stakeholder demands into the production process, which contributes to project delays and a decline in quality.

[0070] 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.

[0071] In this invention, the server includes means for analyzing image data to extract visual features and automatically generating activity instructions in digital content production; means for evaluating the workload and suitability of various workers based on the extracted information and assigning activities to the most suitable workers; and means for analyzing the demands of stakeholders using natural language processing technology and reflecting them in the digital content production process. This makes it possible to improve the efficiency of production projects and reduce the burden on workers.

[0072] "Image data" refers to digital data containing visual information, whether still images or moving images, stored in a format that can be processed by a computer.

[0073] "Visual features" refer to attributes such as color, shape, and pattern extracted from image data, and are fundamental information for directing activities in digital content creation.

[0074] "Digital content creation" refers to the planning, design, and production of various digital content formats (e.g., graphics, videos, animations, etc.) using computers.

[0075] "Activity instructions" are instructions that define the specific tasks to be performed during the production process, and are automatically generated based on visual characteristics.

[0076] "Workload" refers to the amount and difficulty of work assigned to a specific worker, and is an indicator that shows the workload within the scope that the worker is capable of performing.

[0077] "Aptitude" refers to the criteria used to evaluate whether a worker possesses the ability and characteristics necessary to perform a specific task, and is a factor considered in order to efficiently assign tasks.

[0078] "Natural language processing technology" is a technology that uses computers to understand, generate, and analyze human language, and is a method used to incorporate the demands of stakeholders into the production process.

[0079] "Requirements" refer to the conditions and specifications that stakeholders expect from digital content, and the needs that should be incorporated into each stage of the production process.

[0080] "Schedule information" refers to information about a specific worker's work plan and time allocation, and serves as basic data for assigning activities optimally.

[0081] "Skills information" refers to data on the individual technical abilities and specialized knowledge of workers, and is used as reference for making appropriate work assignments.

[0082] This invention relates to a system that improves work efficiency in digital content creation and reduces the burden on those involved. The system consists of three elements: a server, a terminal, and a user, each element playing a specific role.

[0083] The server receives image data and analyzes it using a generative AI model that employs natural language processing technology. Specifically, it uses image analysis software (e.g., TENSORFLOW® or OpenCV) to extract visual features from the image data. Based on this information, the server automatically generates activity instructions, which include the content, priority, and deadline of each task.

[0084] The terminal receives instructions from the server and displays necessary information to the worker. Users manage worker schedule and skill information through the terminal and provide this information to the server. The terminal also provides a progress monitoring dashboard, allowing for real-time monitoring of work progress.

[0085] The user manages the entire project through the system. For example, if a new stakeholder makes a request, the user can input this information as a prompt, and the server can analyze it to appropriately incorporate it into the project plan. An example of a prompt might be, "Please add a new character design and have it ready for next week's review."

[0086] This invention aims to improve the efficiency of digital content creation by having each element work together, thereby reducing the workload and improving quality.

[0087] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0088] Step 1:

[0089] The server receives image data from users via the network. The received image data is first checked and converted to a standard format that facilitates analysis. After conversion, the server extracts visual features using an image analysis library (e.g., OpenCV). During this process, features such as color, shape, and important objects are analyzed to generate data that forms the basis for activity instructions.

[0090] Step 2:

[0091] The server utilizes a generative AI model to automatically generate activity instructions based on extracted visual features. This process includes designing and prioritizing tasks based on the generated data. Specifically, it sets work tasks such as "adjusting character color schemes" and "adding background details." The generated activity instructions are sent to the terminal as a task list.

[0092] Step 3:

[0093] The terminal displays the task list received from the server on the user interface. The user checks the task list through the terminal and refers to each worker's schedule and skills information. Based on this information, the terminal provides worker availability and skills to the server via a scheduling tool (e.g., Google® Calendar). This information is used to optimize task assignment.

[0094] Step 4:

[0095] The server uses a generated AI model to optimally assign tasks based on the worker's schedule and skill information obtained from the terminal. In doing so, it considers each worker's past performance and current workload to ensure efficient and appropriate task allocation. Once a task is assigned, the result is sent to the terminal and the worker is notified.

[0096] Step 5:

[0097] Users monitor project task progress using their terminals. Progress is displayed in real time in a dashboard format, and users can issue new instructions or make adjustments as needed. If necessary, users can enter prompt messages to register stakeholder requests, allowing the entire system to respond flexibly accordingly. Sending specific prompts, such as "Add a new scene and make it available for review by next week's meeting," triggers server-side analysis and task adjustments.

[0098] (Application Example 1)

[0099] 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."

[0100] In recent years, multimedia production and content distribution services have involved vast amounts of information and numerous workers, necessitating efficient task generation and optimal work allocation. Furthermore, rapid content recommendations tailored to viewer interests are also crucial. A system is needed to address these challenges and deliver high-quality deliverables.

[0101] 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.

[0102] In this invention, the server includes means for analyzing image data to extract visual information and automatically generating tasks in multimedia production; means for evaluating the workload and suitability of various workers based on the extracted information and assigning tasks to the most suitable workers; and means for automating content recommendations based on the user's visual characteristics. This makes it possible to improve work efficiency and provide users with the most suitable content.

[0103] "Image data" refers to digital data that contains visual information.

[0104] "Visual information" refers to characteristic information such as structure, color, and shape extracted from image data.

[0105] "Multimedia production" is the process of creating a work by combining multiple media such as video, music, and graphic design.

[0106] "Methods for automatically generating tasks" refers to a function in the system that defines and lists various tasks for a project based on image data.

[0107] "Evaluating the workload and suitability of workers" means analyzing the current workload and skills of individual workers.

[0108] "Assigning tasks to the most suitable workers" is the process of distributing the appropriate tasks to the most suitable workers based on evaluation results.

[0109] "Automating content recommendations based on the user's visual characteristics" refers to a function that analyzes the user's past viewing history and preferences to suggest the most suitable content.

[0110] A "system" is a collection of multiple components designed to perform a specific function.

[0111] This invention is a system that enables efficient task management in multimedia production and content distribution, and provides optimal content to users, by extracting visual information through the analysis of image data.

[0112] The server first analyzes image data using an image processing library to extract visual features. This makes it possible to automatically generate tasks necessary for a project. For example, it can create detailed work instructions for each scene in a storyboard based on the visual features. Based on the extracted features, the server takes into account the worker's schedule and skill information and automatically assigns tasks to the most suitable worker. This reduces the workload on workers and ensures the smooth progress of the project.

[0113] The terminal has the function of receiving task lists sent from the server and presenting them visually to the person in charge of managing the work. By operating the terminal, the user can manage the work project and advance the project based on the generated task list.

[0114] Furthermore, the server uses a generative AI model to analyze viewing history based on the user's visual characteristics and automatically recommends content best suited to each individual user. This makes it easy for users to discover new content tailored to their preferences.

[0115] For example, if a user frequently watches action movies, the system can extract their visual characteristics and automatically recommend movies and TV shows in a similar action genre. An example of a prompt message would be, "Please suggest relevant content considering this user's viewing history."

[0116] As described above, this system streamlines the multimedia production and content distribution processes and improves the user experience.

[0117] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0118] Step 1:

[0119] The server uses an image processing algorithm (e.g., the OpenCV library) to analyze the received image data as input. This process extracts visual features from the image (e.g., color and shape information) and outputs them to a database.

[0120] Step 2:

[0121] The server automatically generates a task list based on the extracted visual features using a generative AI model. At this stage, specific tasks are set according to each feature. The generated task list is output as data necessary for project management.

[0122] Step 3:

[0123] The terminal receives the task list sent from the server and displays it to the person in charge of managing the task. This display is visually easy to understand and provides information that enables the worker to proceed with the work efficiently.

[0124] Step 4:

[0125] The server uses the worker schedule and skill information it already possesses as input to assign tasks to the most suitable workers. Here, it evaluates the availability of schedules and the suitability of skills to output the optimal assignment result.

[0126] Step 5:

[0127] Users can use their terminals to check the progress of the entire project and adjust the task list as needed. Progress information is updated continuously by the server, reflecting the latest status.

[0128] Step 6:

[0129] The server provides the user's viewing history and extracted visual features as input to a generating AI model, which then recommends the most suitable content. This process outputs new recommended content to the user, improving the content consumption experience.

[0130] 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.

[0131] This invention not only streamlines the workflow in multimedia production but also provides a system that recognizes the emotions of workers and users to aid in project management. The system begins with analyzing image data, evaluates the user's emotions using an emotion engine, and adjusts tasks and provides feedback as needed.

[0132] System Configuration

[0133] 1. Server

[0134] The server receives image data and extracts visual information using an image recognition algorithm. Based on this, it automatically generates a task list and incorporates it into the project's progress.

[0135] 2. Terminal

[0136] The terminal manages user input data and worker information, and handles task distribution and schedule management through communication with the server. In addition, it provides appropriate support to users based on feedback from the emotion engine.

[0137] 3. User

[0138] Users give project instructions and receive personalized suggestions based on their emotional state, as recognized by the emotion engine. They can change task priorities and adjust resource allocation as needed.

[0139] 4. Emotional Engine

[0140] The emotion engine analyzes the user's emotional state from their behavior, voice, and text, and sends the results to the server. This information is used for task allocation and feedback generation, contributing to stress management and improved motivation among workers.

[0141] Program processing flow

[0142] The server first analyzes visual information from image data and generates tasks. Next, the terminal provides these tasks to the user and requests the server to optimize task assignments based on the user's schedule and worker information. Furthermore, the emotion engine recognizes the user's current emotional state, and the server uses this information to adjust task priorities and distribution.

[0143] For example, if the emotion engine determines that a user is experiencing stress, the server adjusts the task volume and provides appropriate feedback to the user or worker through the terminal. In this way, the system not only supports the smooth progress of the project and improves the quality of work, but also enables a human-centered process through emotion management.

[0144] The following describes the processing flow.

[0145] Step 1:

[0146] The server receives image data provided by the user. This includes important visual information necessary for the project's progress.

[0147] Step 2:

[0148] The server analyzes the received image data using an image recognition algorithm. Through this analysis, it extracts visual information related to the scene setting and character movements.

[0149] Step 3:

[0150] The server automatically generates the necessary tasks based on the extracted visual information. Specifically, this includes things like character animation and background design.

[0151] Step 4:

[0152] The terminal displays a task list sent from the server to the user. Through this display, the user can grasp the overall picture of the project.

[0153] Step 5:

[0154] The terminal transmits the worker's schedule and skill information, provided by the user, to the server. This information is crucial for efficient task assignment.

[0155] Step 6:

[0156] The server automatically assigns tasks to the most suitable workers based on schedule and skill information, taking into particular consideration the workers' current workload and expertise.

[0157] Step 7:

[0158] The emotion engine activates, recognizing the user's emotional state from their behavioral data and voice. This information is designed to aid in the overall operation of the system.

[0159] Step 8:

[0160] The server uses emotional information provided by the emotion engine to provide appropriate feedback and task adjustments. This reduces user stress and provides a better work environment.

[0161] Step 9:

[0162] The terminal notifies users and workers of adjusted tasks and feedback. This allows all members to understand the current expected behavior and respond to any necessary changes.

[0163] (Example 2)

[0164] 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".

[0165] In multimedia production projects, there is a need to simultaneously achieve increased work efficiency and reduced mental burden on workers. However, traditional methods involve generating and assigning tasks individually, making it difficult to maximize overall work efficiency, and project management does not take into account the emotional state of the workers. As a result, project progress may be delayed, worker stress may increase, and the quality of work may decline.

[0166] 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.

[0167] In this invention, the server includes means for analyzing image data to extract visual information and automatically generating tasks for multimedia production; means for evaluating the workload and suitability of multiple workers based on the extracted information and assigning tasks to the most suitable workers; and means for evaluating the emotional state of users using emotion analysis technology and integrating that information into the project plan. This enables efficient project progress and appropriate management based on the emotional state of workers.

[0168] "Image data" refers to electronic data containing visual information, including photographs, illustrations, and diagrams.

[0169] "Analysis" is a process performed to extract or classify specific information from data.

[0170] "Visual information" refers to the visual features contained in image data, such as color, shape, pattern, and objects.

[0171] "Multimedia production" is the process of creating content by integrating multiple media such as text, images, audio, and video.

[0172] A "task" is an individual unit of work necessary for the progress of a project.

[0173] "Automatic generation" refers to the process where algorithms or software generate tasks or data without human intervention.

[0174] "Workload" refers to the amount and difficulty level of work that a worker must complete within a specific period.

[0175] "Aptitude" refers to the extent to which a worker possesses the necessary skills and qualifications to perform a particular task.

[0176] "Assigning" refers to the act of assigning a specific task or resource to a specific worker or group.

[0177] "Emotional analysis technology" is a technology that reads a user's emotional state from data and patterns and analyzes that information.

[0178] "Emotional state" refers to the user's psychological and emotional state.

[0179] A "project plan" is a detailed plan that outlines the policies, resource allocation, and timeline for achieving the project's objectives.

[0180] This invention provides a system that analyzes image data, extracts visual information, automatically generates tasks in multimedia production, and streamlines project management. The embodiments for carrying out this invention are shown below.

[0181] The server first receives image data sent from users or workers. Image data is typically acquired using input devices such as digital cameras or scanners. The server uses existing algorithms known as generative AI models to execute image recognition algorithms. These algorithms have the ability to analyze color, shape, and object patterns from image data and visually extract information based on them.

[0182] The terminal receives a task list generated from the server based on visual information and presents it to the user. The terminal notifies the user of the task content, importance, and deadline in a visually easy-to-understand format. The user can then review this information and take appropriate action based on their schedule and circumstances.

[0183] Furthermore, an emotion engine incorporating emotion analysis technology evaluates the user's emotional state using user input data, voice, or text. This emotional information is used by the server to optimize project planning. For example, if the server determines that the user is in a high-stress state, it readjusts tasks and takes measures to reduce the burden.

[0184] As a concrete example, when a user edits a specific image in a project, related editing tasks are automatically generated based on the analysis results of that image. By using a prompt message such as "Please tell me the important information that should be extracted from this image," the image recognition algorithm automatically extracts the necessary information and reflects it in the task list.

[0185] In this way, the system can streamline project management and provide support tailored to the user's emotions and circumstances, thereby improving the quality and efficiency of multimedia production projects.

[0186] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0187] Step 1:

[0188] The server receives image data from users or workers. This input image data is acquired from digital devices. Based on the received image data, the server executes an image recognition algorithm. This process uses a generative AI model to analyze color, shape, and pattern from the image and extract visual features. As output, metadata containing the visual features is generated.

[0189] Step 2:

[0190] The server automatically generates a task list based on visual features. The extracted visual features are used as input for this task list generation. Specific tasks, such as "tagging people in an image" or "adjusting background color," are generated. As a result, a task list containing multiple specific tasks is output and sent to the terminal.

[0191] Step 3:

[0192] The terminal displays a task list received from the server to the user. The input here is the task list sent from the server; the terminal does not need to repeatedly confirm this, but it presents it in detail. The user has the ability to proceed with their work based on this list and send feedback to the system. The output is a list of executable tasks presented to the user.

[0193] Step 4:

[0194] The emotion engine analyzes emotional data obtained from the user. Inputs include user voice, text, and interaction data. Based on this data, a generative AI model performs emotion analysis to determine the user's emotional state. The output is evaluation data indicating the emotional state.

[0195] Step 5:

[0196] The server adjusts the task list using sentiment evaluation data obtained from the sentiment engine. This sentiment data serves as input, taking into account states such as high stress and fatigue. The server repriors tasks as needed and transfers tasks to other members. This results in an adjusted task list being output and sent back to the terminal.

[0197] (Application Example 2)

[0198] 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".

[0199] Providing prompt and efficient public services in urban areas is a common challenge for many cities. Especially in densely populated areas, accurately understanding residents' needs and emotional states and providing appropriate services based on that understanding is crucial. However, conventional systems struggle to make rapid service improvements and suggestions that take emotional fluctuations into account. Therefore, there is a need for a system that analyzes residents' emotional states and provides personalized suggestions.

[0200] 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.

[0201] In this invention, the server includes means for analyzing image data to extract visual information and automatically generating tasks related to urban residents; means for determining the emotional state of residents based on the extracted information and proposing optimal citizen services; and means for providing individually tailored recommendations for urban residents based on the generated feedback. This makes it possible to analyze the emotional state of residents in real time, provide optimal services, and improve resident satisfaction.

[0202] "Image data" refers to digital data containing visual information that is analyzed by a computer.

[0203] "Visual information" refers to information such as shape, color, and pattern that is extracted from image data and obtained through analysis.

[0204] A "task" is a set of actions or tasks necessary to achieve a specific goal.

[0205] A "worker" refers to an individual or team performing a task, possessing specific skills or aptitudes.

[0206] A "text generation algorithm" is a computer program that automatically generates documents in natural language.

[0207] "Natural language processing technology" is a technology that processes human language using computers, and is used in applications such as speech recognition and translation.

[0208] "Emotion recognition technology" is a technology that analyzes and identifies an individual's emotional state, and utilizes data such as voice and facial expressions.

[0209] "Feedback" refers to the information and responses that a system provides to a user, which are used to improve behavior or conditions.

[0210] A "city resident" is an individual who has their base of operations in a specific city and is involved with the services and environment of that area.

[0211] "Citizen services" refer to various services provided by local governments and public institutions to residents, with the aim of improving their quality of life.

[0212] This invention is a system for analyzing the emotional state of urban residents and providing appropriate public services. The system consists of three elements: a server, a terminal, and a user. The specific role of each element will be explained below.

[0213] The server is primarily responsible for data analysis and task generation. Specifically, it receives image data and uses OpenCV to extract visual information. This visual information is used for automated task generation and emotion recognition. Emotion recognition technology is implemented using Google Cloud's natural language processing API to analyze the emotional state of residents. Based on the analysis results, a program is constructed to propose optimal citizen services. In addition, AWS (registered trademark) is used for data processing and storage to support scalable service operation.

[0214] The terminal primarily collects user input data and communicates with the server. Mobile devices such as smartphones and smart glasses are used to collect user image and audio data. The data acquired from these devices is transferred to the server in real time and used for analysis and providing feedback. The feedback is provided to the user through the terminal, and personalized recommendations are made.

[0215] Through interaction with the system, users receive civic services based on their emotional state. If the system determines that a user's stress level is high, appropriate relaxation events and resources are recommended. For example, notifications about relaxation workshops held in the user's area are sent to their device.

[0216] An example of a prompt is: "Analyze recent selfies and voice memos taken with the user's smartphone camera to determine if they are feeling stressed and suggest events that would be effective for relaxation." Using this prompt, the generative AI model generates feedback and service suggestions.

[0217] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0218] Step 1:

[0219] The device collects image and audio data from the user. Using the camera and microphone built into the device, it captures the user's facial expressions and voice in real time. This data is temporarily stored on the device for use in the next processing step. The input consists of image and audio data, while the output is data sent to the server.

[0220] Step 2:

[0221] The server receives image data sent from the terminal. It uses OpenCV to extract visual information from the image data. Specifically, it analyzes the user's facial expressions and facial muscle movements to estimate their emotional state. The input is image data, and the output is the extracted visual information.

[0222] Step 3:

[0223] The server analyzes the audio data using Google Cloud's natural language processing API. It analyzes the tone of voice and word choice to identify potential emotional indicators. This process evaluates the user's emotional state based on the audio data. The input is audio data, and the output is emotional indicators.

[0224] Step 4:

[0225] The server integrates visual information and auditory emotional indicators to evaluate the user's overall emotional state. This allows for the quantification of the user's current stress level, happiness level, and other factors. The input consists of visual information and auditory emotional indicators, while the output is the result of the integrated emotional state evaluation.

[0226] Step 5:

[0227] The server generates suggestions for civic services tailored to the user based on the evaluation results. Using a generative AI model, it creates optimal feedback and event suggestions according to prompts. Specifically, it recommends information on relaxation events when the user's stress level is high. The input is the integrated sentiment evaluation result, and the output is the service suggestion.

[0228] Step 6:

[0229] The server sends the generated proposal to the terminal and notifies the user. The terminal receives this and displays it on the screen for the user to confirm. The input is the service proposal, and the output is the notification to the user.

[0230] Step 7:

[0231] The user reviews the suggestions received from the device and utilizes the suggested resources if necessary. Through the device's interface, the user can directly access events of interest or obtain additional information. Input is the user's notification, and output is the user's chosen action.

[0232] 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.

[0233] 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.

[0234] 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.

[0235] [Second Embodiment]

[0236] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0237] 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.

[0238] 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).

[0239] 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.

[0240] 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.

[0241] 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).

[0242] 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.

[0243] 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.

[0244] 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.

[0245] 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.

[0246] 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.

[0247] 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".

[0248] This invention provides a system that streamlines the workflow of multimedia production projects and reduces the burden on workers. This system analyzes image data to extract visual information and automatically generates tasks. Furthermore, it efficiently manages project progress by evaluating workers' schedules and skills and assigning optimal tasks.

[0249] System Configuration

[0250] The present invention consists of the following elements.

[0251] 1. Server

[0252] The server receives image data and extracts visual information using image analysis algorithms. Based on this information, it automatically generates a task list.

[0253] 2. Terminal

[0254] The terminal receives task lists sent from the server and displays them to the user responsible for managing the work. It also manages the worker's schedule and skill information and sends it to the server.

[0255] 3. User

[0256] Users operate the terminal to manage projects and assign tasks to workers. Furthermore, they can review and customize generated contracts, facilitating consensus building with stakeholders.

[0257] Program processing flow

[0258] The server first analyzes the image data and extracts visual features from each scene. Based on this information, it generates detailed tasks. The terminal then displays the generated task list and presents it to the person in charge of managing the work. Information about the worker's schedule and skills is provided from the terminal to the server, and the server automatically assigns the most suitable tasks.

[0259] For example, in the storyboarding of a battle scene, the server generates detailed tasks regarding the enemy character's movements and background effects. These tasks are assigned to the relevant workers via terminals, and their progress is constantly monitored. Furthermore, if a user submits a new request regarding the project, the server analyzes the request and adjusts the necessary tasks accordingly.

[0260] This system will streamline the workflow in multimedia production, reduce the burden on workers, and ensure the consistent delivery of high-quality results.

[0261] The following describes the processing flow.

[0262] Step 1:

[0263] The server receives image data uploaded by users. This image data often consists of storyboard images for various scenes involved in multimedia production.

[0264] Step 2:

[0265] The server analyzes the image data using an image recognition algorithm. Here, it extracts visual features for each scene, character placement information, and other relevant details.

[0266] Step 3:

[0267] The server automatically generates relevant tasks based on the extracted information. For example, it might list tasks related to instructing character movements or changing the background.

[0268] Step 4:

[0269] The terminal displays a task list sent from the server to the user. Based on this information, the user can see the overall picture of the project.

[0270] Step 5:

[0271] The terminal transmits the worker's schedule and skill information to the server. This data also includes information about projects the worker has worked on in the past.

[0272] Step 6:

[0273] The server automatically assigns tasks to the most suitable workers based on the received schedule and skill information. It efficiently distributes tasks, taking into account skill suitability and current workload.

[0274] Step 7:

[0275] The terminal notifies each worker of their assigned task. Workers can then schedule their work based on the tasks they receive and begin their tasks.

[0276] Step 8:

[0277] The user reviews the work contract generated via their device and customizes it as needed. They then send the contract to the relevant parties to reach an agreement.

[0278] Step 9:

[0279] The server monitors the overall project progress and updates the task list accordingly if there are any new requests or changes. These updates are then notified to the user via their terminal.

[0280] (Example 1)

[0281] 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."

[0282] Digital content creation requires the processing of diverse visual data and the appropriate placement of workers in the right roles, but managing these aspects is a time-consuming and laborious process. Furthermore, there is a lack of means to quickly incorporate stakeholder demands into the production process, which contributes to project delays and a decline in quality.

[0283] 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.

[0284] In this invention, the server includes means for analyzing image data to extract visual features and automatically generating activity instructions in digital content production, means for evaluating the work burden and suitability of various workers based on the extracted information and assigning activities to the optimal workers, and means for analyzing the requirements of stakeholders using natural language processing technology and reflecting them in the digital content production process. This enables the efficiency of the production project to be improved and the burden on workers to be reduced.

[0285] "Image data" refers to digital-form data containing visual information, which is a still image or video stored in a format processable by a computer.

[0286] "Visual features" are those extracted from image data, referring to attributes such as color, shape, and pattern, and are the information that forms the basis of activity instructions in digital content production.

[0287] "Digital content production" refers to the activities of planning, designing, and producing various digital-form contents (such as graphics, videos, animations, etc.) using a computer.

[0288] "Activity instructions" are instructions that define the specific work content to be executed in the production process and are automatically generated based on visual features.

[0289] "Work burden" refers to the amount of work and difficulty assigned to a specific worker and is an indicator showing the load within the range that the worker can perform.

[0290] "Suitability" is a criterion for evaluating whether a worker has the ability and characteristics to handle a specific task and is an element considered for efficient task allocation.

[0291] "Natural language processing technology" is a technology for enabling a computer to understand, generate, and analyze human language and is a method used to incorporate the requirements of stakeholders into the production process.

[0292] "Requirements" refer to the conditions and specifications that stakeholders expect from digital content, and the needs that should be incorporated into each stage of the production process.

[0293] "Schedule information" refers to information about a specific worker's work plan and time allocation, and serves as basic data for assigning activities optimally.

[0294] "Skills information" refers to data on the individual technical abilities and specialized knowledge of workers, and is used as reference for making appropriate work assignments.

[0295] This invention relates to a system that improves work efficiency in digital content creation and reduces the burden on those involved. The system consists of three elements: a server, a terminal, and a user, each element playing a specific role.

[0296] The server receives image data and analyzes it using a generative AI model that employs natural language processing techniques. Specifically, it uses image analysis software (e.g., TensorFlow or OpenCV) to extract visual features from the image data. Based on this information, the server automatically generates activity instructions, which include the content, priority, and deadline of each task.

[0297] The terminal receives instructions from the server and displays necessary information to the worker. Users manage worker schedule and skill information through the terminal and provide this information to the server. The terminal also provides a progress monitoring dashboard, allowing for real-time monitoring of work progress.

[0298] The user manages the entire project through the system. For example, if a new stakeholder makes a request, the user can input this information as a prompt, and the server can analyze it to appropriately incorporate it into the project plan. An example of a prompt might be, "Please add a new character design and have it ready for next week's review."

[0299] This invention aims to improve the efficiency of digital content creation by having each element work together, thereby reducing the workload and improving quality.

[0300] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0301] Step 1:

[0302] The server receives image data from users via the network. The received image data is first checked and converted to a standard format that facilitates analysis. After conversion, the server extracts visual features using an image analysis library (e.g., OpenCV). During this process, features such as color, shape, and important objects are analyzed to generate data that forms the basis for activity instructions.

[0303] Step 2:

[0304] The server utilizes a generative AI model to automatically generate activity instructions based on extracted visual features. This process includes designing and prioritizing tasks based on the generated data. Specifically, it sets work tasks such as "adjusting character color schemes" and "adding background details." The generated activity instructions are sent to the terminal as a task list.

[0305] Step 3:

[0306] The terminal displays the task list received from the server on the user interface. The user checks the task list through the terminal and refers to the schedule information and skill information of each worker. Based on this information, the terminal provides the server with the availability and skills of the workers through a schedule management tool (e.g., Google Calendar). This information is used for optimizing task allocation.

[0307] Step 4:

[0308] Based on the schedule information and skill information of the workers obtained from the terminal, the server executes optimal task allocation using a generative AI model. At this time, considering the past performance and current load status of each worker, efficient and appropriate task distribution is carried out. When a task is assigned, the result is sent to the terminal and notified to the worker.

[0309] Step 5:

[0310] The user monitors the progress of the project tasks using the terminal. The progress status is displayed in real-time in the form of a dashboard, and the user gives new instructions and adjustments according to the situation. If necessary, the user can input prompt text to register the requirements of the stakeholders, enabling the entire system to take flexible responses accordingly. By sending commands such as "Add a new scene and make it reviewable by next week's meeting" as specific prompts, analysis and task adjustment by the server are performed.

[0311] (Application Example 1)

[0312] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0313] In recent years, multimedia production and content distribution services have involved vast amounts of information and numerous workers, necessitating efficient task generation and optimal work allocation. Furthermore, rapid content recommendations tailored to viewer interests are also crucial. A system is needed to address these challenges and deliver high-quality deliverables.

[0314] 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.

[0315] In this invention, the server includes means for analyzing image data to extract visual information and automatically generating tasks in multimedia production; means for evaluating the workload and suitability of various workers based on the extracted information and assigning tasks to the most suitable workers; and means for automating content recommendations based on the user's visual characteristics. This makes it possible to improve work efficiency and provide users with the most suitable content.

[0316] "Image data" refers to digital data that contains visual information.

[0317] "Visual information" refers to characteristic information such as structure, color, and shape extracted from image data.

[0318] "Multimedia production" is the process of creating a work by combining multiple media such as video, music, and graphic design.

[0319] "Methods for automatically generating tasks" refers to a function in the system that defines and lists various tasks for a project based on image data.

[0320] "Evaluating the workload and suitability of workers" means analyzing the current workload and skills of individual workers.

[0321] "Assigning tasks to the most suitable workers" is the process of distributing the appropriate tasks to the most suitable workers based on evaluation results.

[0322] "Automating content recommendations based on the user's visual characteristics" refers to a function that analyzes the user's past viewing history and preferences to suggest the most suitable content.

[0323] A "system" is a collection of multiple components designed to perform a specific function.

[0324] This invention is a system that enables efficient task management in multimedia production and content distribution, and provides optimal content to users, by extracting visual information through the analysis of image data.

[0325] The server first analyzes image data using an image processing library to extract visual features. This makes it possible to automatically generate tasks necessary for a project. For example, it can create detailed work instructions for each scene in a storyboard based on the visual features. Based on the extracted features, the server takes into account the worker's schedule and skill information and automatically assigns tasks to the most suitable worker. This reduces the workload on workers and ensures the smooth progress of the project.

[0326] The terminal has the function of receiving task lists sent from the server and presenting them visually to the person in charge of managing the work. By operating the terminal, the user can manage the work project and advance the project based on the generated task list.

[0327] Furthermore, the server uses a generative AI model to analyze viewing history based on the user's visual characteristics and automatically recommends content best suited to each individual user. This makes it easy for users to discover new content tailored to their preferences.

[0328] For example, if a user frequently watches action movies, the system can extract their visual characteristics and automatically recommend movies and TV shows in a similar action genre. An example of a prompt message would be, "Please suggest relevant content considering this user's viewing history."

[0329] As described above, this system streamlines the multimedia production and content distribution processes and improves the user experience.

[0330] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0331] Step 1:

[0332] The server uses an image processing algorithm (e.g., the OpenCV library) to analyze the received image data as input. This process extracts visual features from the image (e.g., color and shape information) and outputs them to a database.

[0333] Step 2:

[0334] The server automatically generates a task list based on the extracted visual features using a generative AI model. At this stage, specific tasks are set according to each feature. The generated task list is output as data necessary for project management.

[0335] Step 3:

[0336] The terminal receives the task list sent from the server and displays it to the person in charge of managing the task. This display is visually easy to understand and provides information that enables the worker to proceed with the work efficiently.

[0337] Step 4:

[0338] The server uses the worker schedule and skill information it already possesses as input to assign tasks to the most suitable workers. Here, it evaluates the availability of schedules and the suitability of skills to output the optimal assignment result.

[0339] Step 5:

[0340] Users can use their terminals to check the progress of the entire project and adjust the task list as needed. Progress information is updated continuously by the server, reflecting the latest status.

[0341] Step 6:

[0342] The server provides the user's viewing history and extracted visual features as input to a generating AI model, which then recommends the most suitable content. This process outputs new recommended content to the user, improving the content consumption experience.

[0343] 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.

[0344] This invention not only streamlines the workflow in multimedia production but also provides a system that recognizes the emotions of workers and users to aid in project management. The system begins with analyzing image data, evaluates the user's emotions using an emotion engine, and adjusts tasks and provides feedback as needed.

[0345] System Configuration

[0346] 1. Server

[0347] The server receives image data and extracts visual information using an image recognition algorithm. Based on this, it automatically generates a task list and incorporates it into the project's progress.

[0348] 2. Terminal

[0349] The terminal manages user input data and worker information, and handles task distribution and schedule management through communication with the server. In addition, it provides appropriate support to users based on feedback from the emotion engine.

[0350] 3. User

[0351] Users give project instructions and receive personalized suggestions based on their emotional state, as recognized by the emotion engine. They can change task priorities and adjust resource allocation as needed.

[0352] 4. Emotional Engine

[0353] The emotion engine analyzes the user's emotional state from their behavior, voice, and text, and sends the results to the server. This information is used for task allocation and feedback generation, contributing to stress management and improved motivation among workers.

[0354] Program processing flow

[0355] The server first analyzes visual information from image data and generates tasks. Next, the terminal provides these tasks to the user and requests the server to optimize task assignments based on the user's schedule and worker information. Furthermore, the emotion engine recognizes the user's current emotional state, and the server uses this information to adjust task priorities and distribution.

[0356] For example, if the emotion engine determines that a user is experiencing stress, the server adjusts the task volume and provides appropriate feedback to the user or worker through the terminal. In this way, the system not only supports the smooth progress of the project and improves the quality of work, but also enables a human-centered process through emotion management.

[0357] The following describes the processing flow.

[0358] Step 1:

[0359] The server receives image data provided by the user. This includes important visual information necessary for the project's progress.

[0360] Step 2:

[0361] The server analyzes the received image data using an image recognition algorithm. Through this analysis, it extracts visual information related to the scene setting and character movements.

[0362] Step 3:

[0363] The server automatically generates the necessary tasks based on the extracted visual information. Specifically, this includes things like character animation and background design.

[0364] Step 4:

[0365] The terminal displays a task list sent from the server to the user. Through this display, the user can grasp the overall picture of the project.

[0366] Step 5:

[0367] The terminal transmits the worker's schedule and skill information, provided by the user, to the server. This information is crucial for efficient task assignment.

[0368] Step 6:

[0369] The server automatically assigns tasks to the most suitable workers based on schedule and skill information, taking into particular consideration the workers' current workload and expertise.

[0370] Step 7:

[0371] The emotion engine activates, recognizing the user's emotional state from their behavioral data and voice. This information is designed to aid in the overall operation of the system.

[0372] Step 8:

[0373] The server uses emotional information provided by the emotion engine to provide appropriate feedback and task adjustments. This reduces user stress and provides a better work environment.

[0374] Step 9:

[0375] The terminal notifies users and workers of adjusted tasks and feedback. This allows all members to understand the current expected behavior and respond to any necessary changes.

[0376] (Example 2)

[0377] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0378] In multimedia production projects, there is a need to simultaneously achieve increased work efficiency and reduced mental burden on workers. However, traditional methods involve generating and assigning tasks individually, making it difficult to maximize overall work efficiency, and project management does not take into account the emotional state of the workers. As a result, project progress may be delayed, worker stress may increase, and the quality of work may decline.

[0379] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0380] In this invention, the server includes means for analyzing image data to extract visual information and automatically generating tasks for multimedia production; means for evaluating the workload and suitability of multiple workers based on the extracted information and assigning tasks to the most suitable workers; and means for evaluating the emotional state of users using emotion analysis technology and integrating that information into the project plan. This enables efficient project progress and appropriate management based on the emotional state of workers.

[0381] "Image data" refers to electronic data containing visual information, including photographs, illustrations, and diagrams.

[0382] "Analysis" is a process performed to extract or classify specific information from data.

[0383] "Visual information" refers to the visual features contained in image data, such as color, shape, pattern, and objects.

[0384] "Multimedia production" is the process of creating content by integrating multiple media such as text, images, audio, and video.

[0385] A "task" is an individual unit of work necessary for the progress of a project.

[0386] "Automatic generation" refers to the process where algorithms or software generate tasks or data without human intervention.

[0387] "Workload" refers to the amount and difficulty level of work that a worker must complete within a specific period.

[0388] "Aptitude" refers to the extent to which a worker possesses the necessary skills and qualifications to perform a particular task.

[0389] "Assigning" refers to the act of assigning a specific task or resource to a specific worker or group.

[0390] "Emotional analysis technology" is a technology that reads a user's emotional state from data and patterns and analyzes that information.

[0391] "Emotional state" refers to the user's psychological and emotional state.

[0392] A "project plan" is a detailed plan that outlines the policies, resource allocation, and timeline for achieving the project's objectives.

[0393] This invention provides a system that analyzes image data, extracts visual information, automatically generates tasks in multimedia production, and streamlines project management. The embodiments for carrying out this invention are shown below.

[0394] The server first receives image data sent from users or workers. Image data is typically acquired using input devices such as digital cameras or scanners. The server uses existing algorithms known as generative AI models to execute image recognition algorithms. These algorithms have the ability to analyze color, shape, and object patterns from image data and visually extract information based on them.

[0395] The terminal receives a task list generated from the server based on visual information and presents it to the user. The terminal notifies the user of the task content, importance, and deadline in a visually easy-to-understand format. The user can then review this information and take appropriate action based on their schedule and circumstances.

[0396] Furthermore, an emotion engine incorporating emotion analysis technology evaluates the user's emotional state using user input data, voice, or text. This emotional information is used by the server to optimize project planning. For example, if the server determines that the user is in a high-stress state, it readjusts tasks and takes measures to reduce the burden.

[0397] As a concrete example, when a user edits a specific image in a project, related editing tasks are automatically generated based on the analysis results of that image. By using a prompt message such as "Please tell me the important information that should be extracted from this image," the image recognition algorithm automatically extracts the necessary information and reflects it in the task list.

[0398] In this way, the system can streamline project management and provide support tailored to the user's emotions and circumstances, thereby improving the quality and efficiency of multimedia production projects.

[0399] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0400] Step 1:

[0401] The server receives image data from users or workers. This input image data is acquired from digital devices. Based on the received image data, the server executes an image recognition algorithm. This process uses a generative AI model to analyze color, shape, and pattern from the image and extract visual features. As output, metadata containing the visual features is generated.

[0402] Step 2:

[0403] The server automatically generates a task list based on visual features. The extracted visual features are used as input for this task list generation. Specific tasks, such as "tagging people in an image" or "adjusting background color," are generated. As a result, a task list containing multiple specific tasks is output and sent to the terminal.

[0404] Step 3:

[0405] The terminal displays a task list received from the server to the user. The input here is the task list sent from the server; the terminal does not need to repeatedly confirm this, but it presents it in detail. The user has the ability to proceed with their work based on this list and send feedback to the system. The output is a list of executable tasks presented to the user.

[0406] Step 4:

[0407] The emotion engine analyzes emotional data obtained from the user. Inputs include user voice, text, and interaction data. Based on this data, a generative AI model performs emotion analysis to determine the user's emotional state. The output is evaluation data indicating the emotional state.

[0408] Step 5:

[0409] The server adjusts the task list using sentiment evaluation data obtained from the sentiment engine. This sentiment data serves as input, taking into account states such as high stress and fatigue. The server repriors tasks as needed and transfers tasks to other members. This results in an adjusted task list being output and sent back to the terminal.

[0410] (Application Example 2)

[0411] 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."

[0412] Providing prompt and efficient public services in urban areas is a common challenge for many cities. Especially in densely populated areas, accurately understanding residents' needs and emotional states and providing appropriate services based on that understanding is crucial. However, conventional systems struggle to make rapid service improvements and suggestions that take emotional fluctuations into account. Therefore, there is a need for a system that analyzes residents' emotional states and provides personalized suggestions.

[0413] 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.

[0414] In this invention, the server includes means for analyzing image data to extract visual information and automatically generating tasks related to urban residents; means for determining the emotional state of residents based on the extracted information and proposing optimal citizen services; and means for providing individually tailored recommendations for urban residents based on the generated feedback. This makes it possible to analyze the emotional state of residents in real time, provide optimal services, and improve resident satisfaction.

[0415] "Image data" refers to digital data containing visual information that is analyzed by a computer.

[0416] "Visual information" refers to information such as shape, color, and pattern that is extracted from image data and obtained through analysis.

[0417] A "task" is a set of actions or tasks necessary to achieve a specific goal.

[0418] A "worker" refers to an individual or team performing a task, possessing specific skills or aptitudes.

[0419] A "text generation algorithm" is a computer program that automatically generates documents in natural language.

[0420] "Natural language processing technology" is a technology that processes human language using computers, and is used in applications such as speech recognition and translation.

[0421] "Emotion recognition technology" is a technology that analyzes and identifies an individual's emotional state, and utilizes data such as voice and facial expressions.

[0422] "Feedback" refers to the information and responses that a system provides to a user, which are used to improve behavior or conditions.

[0423] A "city resident" is an individual who has their base of operations in a specific city and is involved with the services and environment of that area.

[0424] "Citizen services" refer to various services provided by local governments and public institutions to residents, with the aim of improving their quality of life.

[0425] This invention is a system for analyzing the emotional state of urban residents and providing appropriate public services. The system consists of three elements: a server, a terminal, and a user. The specific role of each element will be explained below.

[0426] The server is primarily responsible for data analysis and task generation. Specifically, it receives image data and uses OpenCV to extract visual information. This visual information is used for automated task generation and emotion recognition. Emotion recognition technology is implemented using Google Cloud's natural language processing API to analyze the emotional state of residents. Based on the analysis results, a program is constructed to propose optimal citizen services. In addition, AWS is used for data processing and storage to support scalable service operation.

[0427] The terminal primarily collects user input data and communicates with the server. Mobile devices such as smartphones and smart glasses are used to collect user image and audio data. The data acquired from these devices is transferred to the server in real time and used for analysis and providing feedback. The feedback is provided to the user through the terminal, and personalized recommendations are made.

[0428] Through interaction with the system, users receive civic services based on their emotional state. If the system determines that a user's stress level is high, appropriate relaxation events and resources are recommended. For example, notifications about relaxation workshops held in the user's area are sent to their device.

[0429] An example of a prompt is: "Analyze recent selfies and voice memos taken with the user's smartphone camera to determine if they are feeling stressed and suggest events that would be effective for relaxation." Using this prompt, the generative AI model generates feedback and service suggestions.

[0430] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0431] Step 1:

[0432] The device collects image and audio data from the user. Using the camera and microphone built into the device, it captures the user's facial expressions and voice in real time. This data is temporarily stored on the device for use in the next processing step. The input consists of image and audio data, while the output is data sent to the server.

[0433] Step 2:

[0434] The server receives image data sent from the terminal. It uses OpenCV to extract visual information from the image data. Specifically, it analyzes the user's facial expressions and facial muscle movements to estimate their emotional state. The input is image data, and the output is the extracted visual information.

[0435] Step 3:

[0436] The server analyzes the audio data using Google Cloud's natural language processing API. It analyzes the tone of voice and word choice to identify potential emotional indicators. This process evaluates the user's emotional state based on the audio data. The input is audio data, and the output is emotional indicators.

[0437] Step 4:

[0438] The server integrates visual information and auditory emotional indicators to evaluate the user's overall emotional state. This allows for the quantification of the user's current stress level, happiness level, and other factors. The input consists of visual information and auditory emotional indicators, while the output is the result of the integrated emotional state evaluation.

[0439] Step 5:

[0440] The server generates suggestions for civic services tailored to the user based on the evaluation results. Using a generative AI model, it creates optimal feedback and event suggestions according to prompts. Specifically, it recommends information on relaxation events when the user's stress level is high. The input is the integrated sentiment evaluation result, and the output is the service suggestion.

[0441] Step 6:

[0442] The server sends the generated proposal to the terminal and notifies the user. The terminal receives this and displays it on the screen for the user to confirm. The input is the service proposal, and the output is the notification to the user.

[0443] Step 7:

[0444] The user reviews the suggestions received from the device and utilizes the suggested resources if necessary. Through the device's interface, the user can directly access events of interest or obtain additional information. Input is the user's notification, and output is the user's chosen action.

[0445] 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.

[0446] 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.

[0447] 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.

[0448] [Third Embodiment]

[0449] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0450] 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.

[0451] 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).

[0452] 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.

[0453] 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.

[0454] 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).

[0455] 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.

[0456] 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.

[0457] 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.

[0458] 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.

[0459] 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.

[0460] 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".

[0461] This invention provides a system that streamlines the workflow of multimedia production projects and reduces the burden on workers. This system analyzes image data to extract visual information and automatically generates tasks. Furthermore, it efficiently manages project progress by evaluating workers' schedules and skills and assigning optimal tasks.

[0462] System Configuration

[0463] The present invention consists of the following elements.

[0464] 1. Server

[0465] The server receives image data and extracts visual information using image analysis algorithms. Based on this information, it automatically generates a task list.

[0466] 2. Terminal

[0467] The terminal receives task lists sent from the server and displays them to the user responsible for managing the work. It also manages the worker's schedule and skill information and sends it to the server.

[0468] 3. User

[0469] Users operate the terminal to manage projects and assign tasks to workers. Furthermore, they can review and customize generated contracts, facilitating consensus building with stakeholders.

[0470] Program processing flow

[0471] The server first analyzes the image data and extracts visual features from each scene. Based on this information, it generates detailed tasks. The terminal then displays the generated task list and presents it to the person in charge of managing the work. Information about the worker's schedule and skills is provided from the terminal to the server, and the server automatically assigns the most suitable tasks.

[0472] For example, in the storyboarding of a battle scene, the server generates detailed tasks regarding the enemy character's movements and background effects. These tasks are assigned to the relevant workers via terminals, and their progress is constantly monitored. Furthermore, if a user submits a new request regarding the project, the server analyzes the request and adjusts the necessary tasks accordingly.

[0473] This system will streamline the workflow in multimedia production, reduce the burden on workers, and ensure the consistent delivery of high-quality results.

[0474] The following describes the processing flow.

[0475] Step 1:

[0476] The server receives image data uploaded by users. This image data often consists of storyboard images for various scenes involved in multimedia production.

[0477] Step 2:

[0478] The server analyzes the image data using an image recognition algorithm. Here, it extracts visual features for each scene, character placement information, and other relevant details.

[0479] Step 3:

[0480] The server automatically generates relevant tasks based on the extracted information. For example, it might list tasks related to instructing character movements or changing the background.

[0481] Step 4:

[0482] The terminal displays a task list sent from the server to the user. Based on this information, the user can see the overall picture of the project.

[0483] Step 5:

[0484] The terminal transmits the worker's schedule and skill information to the server. This data also includes information about projects the worker has worked on in the past.

[0485] Step 6:

[0486] The server automatically assigns tasks to the most suitable workers based on the received schedule and skill information. It efficiently distributes tasks, taking into account skill suitability and current workload.

[0487] Step 7:

[0488] The terminal notifies each worker of their assigned task. Workers can then schedule their work based on the tasks they receive and begin their tasks.

[0489] Step 8:

[0490] The user reviews the work contract generated via their device and customizes it as needed. They then send the contract to the relevant parties to reach an agreement.

[0491] Step 9:

[0492] The server monitors the overall project progress and updates the task list accordingly if there are any new requests or changes. These updates are then notified to the user via their terminal.

[0493] (Example 1)

[0494] 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."

[0495] Digital content creation requires the processing of diverse visual data and the appropriate placement of workers in the right roles, but managing these aspects is a time-consuming and laborious process. Furthermore, there is a lack of means to quickly incorporate stakeholder demands into the production process, which contributes to project delays and a decline in quality.

[0496] 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.

[0497] In this invention, the server includes means for analyzing image data to extract visual features and automatically generating activity instructions in digital content production; means for evaluating the workload and suitability of various workers based on the extracted information and assigning activities to the most suitable workers; and means for analyzing the demands of stakeholders using natural language processing technology and reflecting them in the digital content production process. This makes it possible to improve the efficiency of production projects and reduce the burden on workers.

[0498] "Image data" refers to digital data containing visual information, whether still images or moving images, stored in a format that can be processed by a computer.

[0499] "Visual features" refer to attributes such as color, shape, and pattern extracted from image data, and are fundamental information for directing activities in digital content creation.

[0500] "Digital content creation" refers to the planning, design, and production of various digital content formats (e.g., graphics, videos, animations, etc.) using computers.

[0501] "Activity instructions" are instructions that define the specific tasks to be performed during the production process, and are automatically generated based on visual characteristics.

[0502] "Workload" refers to the amount and difficulty of work assigned to a specific worker, and is an indicator that shows the workload within the scope that the worker is capable of performing.

[0503] "Aptitude" refers to the criteria used to evaluate whether a worker possesses the ability and characteristics necessary to perform a specific task, and is a factor considered in order to efficiently assign tasks.

[0504] "Natural language processing technology" is a technology that uses computers to understand, generate, and analyze human language, and is a method used to incorporate the demands of stakeholders into the production process.

[0505] "Requirements" refer to the conditions and specifications that stakeholders expect from digital content, and the needs that should be incorporated into each stage of the production process.

[0506] "Schedule information" refers to information about a specific worker's work plan and time allocation, and serves as basic data for assigning activities optimally.

[0507] "Skills information" refers to data on the individual technical abilities and specialized knowledge of workers, and is used as reference for making appropriate work assignments.

[0508] This invention relates to a system that improves work efficiency in digital content creation and reduces the burden on those involved. The system consists of three elements: a server, a terminal, and a user, each element playing a specific role.

[0509] The server receives image data and analyzes it using a generative AI model that employs natural language processing techniques. Specifically, it uses image analysis software (e.g., TensorFlow or OpenCV) to extract visual features from the image data. Based on this information, the server automatically generates activity instructions, which include the content, priority, and deadline of each task.

[0510] The terminal receives instructions from the server and displays necessary information to the worker. Users manage worker schedule and skill information through the terminal and provide this information to the server. The terminal also provides a progress monitoring dashboard, allowing for real-time monitoring of work progress.

[0511] The user manages the entire project through the system. For example, if a new stakeholder makes a request, the user can input this information as a prompt, and the server can analyze it to appropriately incorporate it into the project plan. An example of a prompt might be, "Please add a new character design and have it ready for next week's review."

[0512] This invention aims to improve the efficiency of digital content creation by having each element work together, thereby reducing the workload and improving quality.

[0513] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0514] Step 1:

[0515] The server receives image data from users via the network. The received image data is first checked and converted to a standard format that facilitates analysis. After conversion, the server extracts visual features using an image analysis library (e.g., OpenCV). During this process, features such as color, shape, and important objects are analyzed to generate data that forms the basis for activity instructions.

[0516] Step 2:

[0517] The server utilizes a generative AI model to automatically generate activity instructions based on extracted visual features. This process includes designing and prioritizing tasks based on the generated data. Specifically, it sets work tasks such as "adjusting character color schemes" and "adding background details." The generated activity instructions are sent to the terminal as a task list.

[0518] Step 3:

[0519] The terminal displays the task list received from the server in its user interface. The user reviews the task list through the terminal and accesses each worker's schedule and skills information. Based on this information, the terminal provides the server with worker availability and skills information via a scheduling tool (e.g., Google Calendar). This information is used to optimize task assignment.

[0520] Step 4:

[0521] The server uses a generated AI model to optimally assign tasks based on the worker's schedule and skill information obtained from the terminal. In doing so, it considers each worker's past performance and current workload to ensure efficient and appropriate task allocation. Once a task is assigned, the result is sent to the terminal and the worker is notified.

[0522] Step 5:

[0523] Users monitor project task progress using their terminals. Progress is displayed in real time in a dashboard format, and users can issue new instructions or make adjustments as needed. If necessary, users can enter prompt messages to register stakeholder requests, allowing the entire system to respond flexibly accordingly. Sending specific prompts, such as "Add a new scene and make it available for review by next week's meeting," triggers server-side analysis and task adjustments.

[0524] (Application Example 1)

[0525] 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."

[0526] In recent years, multimedia production and content distribution services have involved vast amounts of information and numerous workers, necessitating efficient task generation and optimal work allocation. Furthermore, rapid content recommendations tailored to viewer interests are also crucial. A system is needed to address these challenges and deliver high-quality deliverables.

[0527] 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.

[0528] In this invention, the server includes means for analyzing image data to extract visual information and automatically generating tasks in multimedia production; means for evaluating the workload and suitability of various workers based on the extracted information and assigning tasks to the most suitable workers; and means for automating content recommendations based on the user's visual characteristics. This makes it possible to improve work efficiency and provide users with the most suitable content.

[0529] "Image data" refers to digital data that contains visual information.

[0530] "Visual information" refers to characteristic information such as structure, color, and shape extracted from image data.

[0531] "Multimedia production" is the process of creating a work by combining multiple media such as video, music, and graphic design.

[0532] "Methods for automatically generating tasks" refers to a function in the system that defines and lists various tasks for a project based on image data.

[0533] "Evaluating the workload and suitability of workers" means analyzing the current workload and skills of individual workers.

[0534] "Assigning tasks to the most suitable workers" is the process of distributing the appropriate tasks to the most suitable workers based on evaluation results.

[0535] "Automating content recommendations based on the user's visual characteristics" refers to a function that analyzes the user's past viewing history and preferences to suggest the most suitable content.

[0536] A "system" is a collection of multiple components designed to perform a specific function.

[0537] This invention is a system that enables efficient task management in multimedia production and content distribution, and provides optimal content to users, by extracting visual information through the analysis of image data.

[0538] The server first analyzes image data using an image processing library to extract visual features. This makes it possible to automatically generate tasks necessary for a project. For example, it can create detailed work instructions for each scene in a storyboard based on the visual features. Based on the extracted features, the server takes into account the worker's schedule and skill information and automatically assigns tasks to the most suitable worker. This reduces the workload on workers and ensures the smooth progress of the project.

[0539] The terminal has the function of receiving task lists sent from the server and presenting them visually to the person in charge of managing the work. By operating the terminal, the user can manage the work project and advance the project based on the generated task list.

[0540] Furthermore, the server uses a generative AI model to analyze viewing history based on the user's visual characteristics and automatically recommends content best suited to each individual user. This makes it easy for users to discover new content tailored to their preferences.

[0541] For example, if a user frequently watches action movies, the system can extract their visual characteristics and automatically recommend movies and TV shows in a similar action genre. An example of a prompt message would be, "Please suggest relevant content considering this user's viewing history."

[0542] As described above, this system streamlines the multimedia production and content distribution processes and improves the user experience.

[0543] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0544] Step 1:

[0545] The server uses an image processing algorithm (e.g., the OpenCV library) to analyze the received image data as input. This process extracts visual features from the image (e.g., color and shape information) and outputs them to a database.

[0546] Step 2:

[0547] The server automatically generates a task list based on the extracted visual features using a generative AI model. At this stage, specific tasks are set according to each feature. The generated task list is output as data necessary for project management.

[0548] Step 3:

[0549] The terminal receives the task list sent from the server and displays it to the person in charge of managing the task. This display is visually easy to understand and provides information that enables the worker to proceed with the work efficiently.

[0550] Step 4:

[0551] The server uses the worker schedule and skill information it already possesses as input to assign tasks to the most suitable workers. Here, it evaluates the availability of schedules and the suitability of skills to output the optimal assignment result.

[0552] Step 5:

[0553] Users can use their terminals to check the progress of the entire project and adjust the task list as needed. Progress information is updated continuously by the server, reflecting the latest status.

[0554] Step 6:

[0555] The server provides the user's viewing history and extracted visual features as input to a generating AI model, which then recommends the most suitable content. This process outputs new recommended content to the user, improving the content consumption experience.

[0556] 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.

[0557] This invention not only streamlines the workflow in multimedia production but also provides a system that recognizes the emotions of workers and users to aid in project management. The system begins with analyzing image data, evaluates the user's emotions using an emotion engine, and adjusts tasks and provides feedback as needed.

[0558] System Configuration

[0559] 1. Server

[0560] The server receives image data and extracts visual information using an image recognition algorithm. Based on this, it automatically generates a task list and incorporates it into the project's progress.

[0561] 2. Terminal

[0562] The terminal manages user input data and worker information, and handles task distribution and schedule management through communication with the server. In addition, it provides appropriate support to users based on feedback from the emotion engine.

[0563] 3. User

[0564] Users give project instructions and receive personalized suggestions based on their emotional state, as recognized by the emotion engine. They can change task priorities and adjust resource allocation as needed.

[0565] 4. Emotional Engine

[0566] The emotion engine analyzes the user's emotional state from their behavior, voice, and text, and sends the results to the server. This information is used for task allocation and feedback generation, contributing to stress management and improved motivation among workers.

[0567] Program processing flow

[0568] The server first analyzes visual information from image data and generates tasks. Next, the terminal provides these tasks to the user and requests the server to optimize task assignments based on the user's schedule and worker information. Furthermore, the emotion engine recognizes the user's current emotional state, and the server uses this information to adjust task priorities and distribution.

[0569] For example, if the emotion engine determines that a user is experiencing stress, the server adjusts the task volume and provides appropriate feedback to the user or worker through the terminal. In this way, the system not only supports the smooth progress of the project and improves the quality of work, but also enables a human-centered process through emotion management.

[0570] The following describes the processing flow.

[0571] Step 1:

[0572] The server receives image data provided by the user. This includes important visual information necessary for the project's progress.

[0573] Step 2:

[0574] The server analyzes the received image data using an image recognition algorithm. Through this analysis, it extracts visual information related to the scene setting and character movements.

[0575] Step 3:

[0576] The server automatically generates the necessary tasks based on the extracted visual information. Specifically, this includes things like character animation and background design.

[0577] Step 4:

[0578] The terminal displays a task list sent from the server to the user. Through this display, the user can grasp the overall picture of the project.

[0579] Step 5:

[0580] The terminal transmits the worker's schedule and skill information, provided by the user, to the server. This information is crucial for efficient task assignment.

[0581] Step 6:

[0582] The server automatically assigns tasks to the most suitable workers based on schedule and skill information, taking into particular consideration the workers' current workload and expertise.

[0583] Step 7:

[0584] The emotion engine activates, recognizing the user's emotional state from their behavioral data and voice. This information is designed to aid in the overall operation of the system.

[0585] Step 8:

[0586] The server uses emotional information provided by the emotion engine to provide appropriate feedback and task adjustments. This reduces user stress and provides a better work environment.

[0587] Step 9:

[0588] The terminal notifies users and workers of adjusted tasks and feedback. This allows all members to understand the current expected behavior and respond to any necessary changes.

[0589] (Example 2)

[0590] 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."

[0591] In multimedia production projects, there is a need to simultaneously achieve increased work efficiency and reduced mental burden on workers. However, traditional methods involve generating and assigning tasks individually, making it difficult to maximize overall work efficiency, and project management does not take into account the emotional state of the workers. As a result, project progress may be delayed, worker stress may increase, and the quality of work may decline.

[0592] 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.

[0593] In this invention, the server includes means for analyzing image data to extract visual information and automatically generating tasks for multimedia production; means for evaluating the workload and suitability of multiple workers based on the extracted information and assigning tasks to the most suitable workers; and means for evaluating the emotional state of users using emotion analysis technology and integrating that information into the project plan. This enables efficient project progress and appropriate management based on the emotional state of workers.

[0594] "Image data" refers to electronic data containing visual information, including photographs, illustrations, and diagrams.

[0595] "Analysis" is a process performed to extract or classify specific information from data.

[0596] "Visual information" refers to the visual features contained in image data, such as color, shape, pattern, and objects.

[0597] "Multimedia production" is the process of creating content by integrating multiple media such as text, images, audio, and video.

[0598] A "task" is an individual unit of work necessary for the progress of a project.

[0599] "Automatic generation" refers to the process where algorithms or software generate tasks or data without human intervention.

[0600] "Workload" refers to the amount and difficulty level of work that a worker must complete within a specific period.

[0601] "Aptitude" refers to the extent to which a worker possesses the necessary skills and qualifications to perform a particular task.

[0602] "Assigning" refers to the act of assigning a specific task or resource to a specific worker or group.

[0603] "Emotional analysis technology" is a technology that reads a user's emotional state from data and patterns and analyzes that information.

[0604] "Emotional state" refers to the user's psychological and emotional state.

[0605] A "project plan" is a detailed plan that outlines the policies, resource allocation, and timeline for achieving the project's objectives.

[0606] This invention provides a system that analyzes image data, extracts visual information, automatically generates tasks in multimedia production, and streamlines project management. The embodiments for carrying out this invention are shown below.

[0607] The server first receives image data sent from users or workers. Image data is typically acquired using input devices such as digital cameras or scanners. The server uses existing algorithms known as generative AI models to execute image recognition algorithms. These algorithms have the ability to analyze color, shape, and object patterns from image data and visually extract information based on them.

[0608] The terminal receives a task list generated from the server based on visual information and presents it to the user. The terminal notifies the user of the task content, importance, and deadline in a visually easy-to-understand format. The user can then review this information and take appropriate action based on their schedule and circumstances.

[0609] Furthermore, an emotion engine incorporating emotion analysis technology evaluates the user's emotional state using user input data, voice, or text. This emotional information is used by the server to optimize project planning. For example, if the server determines that the user is in a high-stress state, it readjusts tasks and takes measures to reduce the burden.

[0610] As a concrete example, when a user edits a specific image in a project, related editing tasks are automatically generated based on the analysis results of that image. By using a prompt message such as "Please tell me the important information that should be extracted from this image," the image recognition algorithm automatically extracts the necessary information and reflects it in the task list.

[0611] In this way, the system can streamline project management and provide support tailored to the user's emotions and circumstances, thereby improving the quality and efficiency of multimedia production projects.

[0612] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0613] Step 1:

[0614] The server receives image data from users or workers. This input image data is acquired from digital devices. Based on the received image data, the server executes an image recognition algorithm. This process uses a generative AI model to analyze color, shape, and pattern from the image and extract visual features. As output, metadata containing the visual features is generated.

[0615] Step 2:

[0616] The server automatically generates a task list based on visual features. The extracted visual features are used as input for this task list generation. Specific tasks, such as "tagging people in an image" or "adjusting background color," are generated. As a result, a task list containing multiple specific tasks is output and sent to the terminal.

[0617] Step 3:

[0618] The terminal displays a task list received from the server to the user. The input here is the task list sent from the server; the terminal does not need to repeatedly confirm this, but it presents it in detail. The user has the ability to proceed with their work based on this list and send feedback to the system. The output is a list of executable tasks presented to the user.

[0619] Step 4:

[0620] The emotion engine analyzes emotional data obtained from the user. Inputs include user voice, text, and interaction data. Based on this data, a generative AI model performs emotion analysis to determine the user's emotional state. The output is evaluation data indicating the emotional state.

[0621] Step 5:

[0622] The server adjusts the task list using sentiment evaluation data obtained from the sentiment engine. This sentiment data serves as input, taking into account states such as high stress and fatigue. The server repriors tasks as needed and transfers tasks to other members. This results in an adjusted task list being output and sent back to the terminal.

[0623] (Application Example 2)

[0624] 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."

[0625] Providing prompt and efficient public services in urban areas is a common challenge for many cities. Especially in densely populated areas, accurately understanding residents' needs and emotional states and providing appropriate services based on that understanding is crucial. However, conventional systems struggle to make rapid service improvements and suggestions that take emotional fluctuations into account. Therefore, there is a need for a system that analyzes residents' emotional states and provides personalized suggestions.

[0626] 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.

[0627] In this invention, the server includes means for analyzing image data to extract visual information and automatically generating tasks related to urban residents; means for determining the emotional state of residents based on the extracted information and proposing optimal citizen services; and means for providing individually tailored recommendations for urban residents based on the generated feedback. This makes it possible to analyze the emotional state of residents in real time, provide optimal services, and improve resident satisfaction.

[0628] "Image data" refers to digital data containing visual information that is analyzed by a computer.

[0629] "Visual information" refers to information such as shape, color, and pattern that is extracted from image data and obtained through analysis.

[0630] A "task" is a set of actions or tasks necessary to achieve a specific goal.

[0631] A "worker" refers to an individual or team performing a task, possessing specific skills or aptitudes.

[0632] A "text generation algorithm" is a computer program that automatically generates documents in natural language.

[0633] "Natural language processing technology" is a technology that processes human language using computers, and is used in applications such as speech recognition and translation.

[0634] "Emotion recognition technology" is a technology that analyzes and identifies an individual's emotional state, and utilizes data such as voice and facial expressions.

[0635] "Feedback" refers to the information and responses that a system provides to a user, which are used to improve behavior or conditions.

[0636] A "city resident" is an individual who has their base of operations in a specific city and is involved with the services and environment of that area.

[0637] "Citizen services" refer to various services provided by local governments and public institutions to residents, with the aim of improving their quality of life.

[0638] This invention is a system for analyzing the emotional state of urban residents and providing appropriate public services. The system consists of three elements: a server, a terminal, and a user. The specific role of each element will be explained below.

[0639] The server is primarily responsible for data analysis and task generation. Specifically, it receives image data and uses OpenCV to extract visual information. This visual information is used for automated task generation and emotion recognition. Emotion recognition technology is implemented using Google Cloud's natural language processing API to analyze the emotional state of residents. Based on the analysis results, a program is constructed to propose optimal citizen services. In addition, AWS is used for data processing and storage to support scalable service operation.

[0640] The terminal primarily collects user input data and communicates with the server. Mobile devices such as smartphones and smart glasses are used to collect user image and audio data. The data acquired from these devices is transferred to the server in real time and used for analysis and providing feedback. The feedback is provided to the user through the terminal, and personalized recommendations are made.

[0641] Through interaction with the system, users receive civic services based on their emotional state. If the system determines that a user's stress level is high, appropriate relaxation events and resources are recommended. For example, notifications about relaxation workshops held in the user's area are sent to their device.

[0642] An example of a prompt is: "Analyze recent selfies and voice memos taken with the user's smartphone camera to determine if they are feeling stressed and suggest events that would be effective for relaxation." Using this prompt, the generative AI model generates feedback and service suggestions.

[0643] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0644] Step 1:

[0645] The device collects image and audio data from the user. Using the camera and microphone built into the device, it captures the user's facial expressions and voice in real time. This data is temporarily stored on the device for use in the next processing step. The input consists of image and audio data, while the output is data sent to the server.

[0646] Step 2:

[0647] The server receives image data sent from the terminal. It uses OpenCV to extract visual information from the image data. Specifically, it analyzes the user's facial expressions and facial muscle movements to estimate their emotional state. The input is image data, and the output is the extracted visual information.

[0648] Step 3:

[0649] The server analyzes the audio data using Google Cloud's natural language processing API. It analyzes the tone of voice and word choice to identify potential emotional indicators. This process evaluates the user's emotional state based on the audio data. The input is audio data, and the output is emotional indicators.

[0650] Step 4:

[0651] The server integrates visual information and auditory emotional indicators to evaluate the user's overall emotional state. This allows for the quantification of the user's current stress level, happiness level, and other factors. The input consists of visual information and auditory emotional indicators, while the output is the result of the integrated emotional state evaluation.

[0652] Step 5:

[0653] The server generates suggestions for civic services tailored to the user based on the evaluation results. Using a generative AI model, it creates optimal feedback and event suggestions according to prompts. Specifically, it recommends information on relaxation events when the user's stress level is high. The input is the integrated sentiment evaluation result, and the output is the service suggestion.

[0654] Step 6:

[0655] The server sends the generated proposal to the terminal and notifies the user. The terminal receives this and displays it on the screen for the user to confirm. The input is the service proposal, and the output is the notification to the user.

[0656] Step 7:

[0657] The user reviews the suggestions received from the device and utilizes the suggested resources if necessary. Through the device's interface, the user can directly access events of interest or obtain additional information. Input is the user's notification, and output is the user's chosen action.

[0658] 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.

[0659] 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.

[0660] 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.

[0661] [Fourth Embodiment]

[0662] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0663] 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.

[0664] 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).

[0665] 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.

[0666] 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.

[0667] 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).

[0668] 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.

[0669] 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.

[0670] 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.

[0671] 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.

[0672] 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.

[0673] 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.

[0674] 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".

[0675] This invention provides a system that streamlines the workflow of multimedia production projects and reduces the burden on workers. This system analyzes image data to extract visual information and automatically generates tasks. Furthermore, it efficiently manages project progress by evaluating workers' schedules and skills and assigning optimal tasks.

[0676] System Configuration

[0677] The present invention consists of the following elements.

[0678] 1. Server

[0679] The server receives image data and extracts visual information using image analysis algorithms. Based on this information, it automatically generates a task list.

[0680] 2. Terminal

[0681] The terminal receives task lists sent from the server and displays them to the user responsible for managing the work. It also manages the worker's schedule and skill information and sends it to the server.

[0682] 3. User

[0683] Users operate the terminal to manage projects and assign tasks to workers. Furthermore, they can review and customize generated contracts, facilitating consensus building with stakeholders.

[0684] Program processing flow

[0685] The server first analyzes the image data and extracts visual features from each scene. Based on this information, it generates detailed tasks. The terminal then displays the generated task list and presents it to the person in charge of managing the work. Information about the worker's schedule and skills is provided from the terminal to the server, and the server automatically assigns the most suitable tasks.

[0686] For example, in the storyboarding of a battle scene, the server generates detailed tasks regarding the enemy character's movements and background effects. These tasks are assigned to the relevant workers via terminals, and their progress is constantly monitored. Furthermore, if a user submits a new request regarding the project, the server analyzes the request and adjusts the necessary tasks accordingly.

[0687] This system will streamline the workflow in multimedia production, reduce the burden on workers, and ensure the consistent delivery of high-quality results.

[0688] The following describes the processing flow.

[0689] Step 1:

[0690] The server receives image data uploaded by users. This image data often consists of storyboard images for various scenes involved in multimedia production.

[0691] Step 2:

[0692] The server analyzes the image data using an image recognition algorithm. Here, it extracts visual features for each scene, character placement information, and other relevant details.

[0693] Step 3:

[0694] The server automatically generates relevant tasks based on the extracted information. For example, it might list tasks related to instructing character movements or changing the background.

[0695] Step 4:

[0696] The terminal displays a task list sent from the server to the user. Based on this information, the user can see the overall picture of the project.

[0697] Step 5:

[0698] The terminal transmits the worker's schedule and skill information to the server. This data also includes information about projects the worker has worked on in the past.

[0699] Step 6:

[0700] The server automatically assigns tasks to the most suitable workers based on the received schedule and skill information. It efficiently distributes tasks, taking into account skill suitability and current workload.

[0701] Step 7:

[0702] The terminal notifies each worker of their assigned task. Workers can then schedule their work based on the tasks they receive and begin their tasks.

[0703] Step 8:

[0704] The user reviews the work contract generated via their device and customizes it as needed. They then send the contract to the relevant parties to reach an agreement.

[0705] Step 9:

[0706] The server monitors the overall project progress and updates the task list accordingly if there are any new requests or changes. These updates are then notified to the user via their terminal.

[0707] (Example 1)

[0708] 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".

[0709] Digital content creation requires the processing of diverse visual data and the appropriate placement of workers in the right roles, but managing these aspects is a time-consuming and laborious process. Furthermore, there is a lack of means to quickly incorporate stakeholder demands into the production process, which contributes to project delays and a decline in quality.

[0710] 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.

[0711] In this invention, the server includes means for analyzing image data to extract visual features and automatically generating activity instructions in digital content production; means for evaluating the workload and suitability of various workers based on the extracted information and assigning activities to the most suitable workers; and means for analyzing the demands of stakeholders using natural language processing technology and reflecting them in the digital content production process. This makes it possible to improve the efficiency of production projects and reduce the burden on workers.

[0712] "Image data" refers to digital data containing visual information, whether still images or moving images, stored in a format that can be processed by a computer.

[0713] "Visual features" refer to attributes such as color, shape, and pattern extracted from image data, and are fundamental information for directing activities in digital content creation.

[0714] "Digital content creation" refers to the planning, design, and production of various digital content formats (e.g., graphics, videos, animations, etc.) using computers.

[0715] "Activity instructions" are instructions that define the specific tasks to be performed during the production process, and are automatically generated based on visual characteristics.

[0716] "Workload" refers to the amount and difficulty of work assigned to a specific worker, and is an indicator that shows the workload within the scope that the worker is capable of performing.

[0717] "Aptitude" refers to the criteria used to evaluate whether a worker possesses the ability and characteristics necessary to perform a specific task, and is a factor considered in order to efficiently assign tasks.

[0718] "Natural language processing technology" is a technology that uses computers to understand, generate, and analyze human language, and is a method used to incorporate the demands of stakeholders into the production process.

[0719] "Requirements" refer to the conditions and specifications that stakeholders expect from digital content, and the needs that should be incorporated into each stage of the production process.

[0720] "Schedule information" refers to information about a specific worker's work plan and time allocation, and serves as basic data for assigning activities optimally.

[0721] "Skills information" refers to data on the individual technical abilities and specialized knowledge of workers, and is used as reference for making appropriate work assignments.

[0722] This invention relates to a system that improves work efficiency in digital content creation and reduces the burden on those involved. The system consists of three elements: a server, a terminal, and a user, each element playing a specific role.

[0723] The server receives image data and analyzes it using a generative AI model that employs natural language processing techniques. Specifically, it uses image analysis software (e.g., TensorFlow or OpenCV) to extract visual features from the image data. Based on this information, the server automatically generates activity instructions, which include the content, priority, and deadline of each task.

[0724] The terminal receives instructions from the server and displays necessary information to the worker. Users manage worker schedule and skill information through the terminal and provide this information to the server. The terminal also provides a progress monitoring dashboard, allowing for real-time monitoring of work progress.

[0725] The user manages the entire project through the system. For example, if a new stakeholder makes a request, the user can input this information as a prompt, and the server can analyze it to appropriately incorporate it into the project plan. An example of a prompt might be, "Please add a new character design and have it ready for next week's review."

[0726] This invention aims to improve the efficiency of digital content creation by having each element work together, thereby reducing the workload and improving quality.

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

[0728] Step 1:

[0729] The server receives image data from users via the network. The received image data is first checked and converted to a standard format that facilitates analysis. After conversion, the server extracts visual features using an image analysis library (e.g., OpenCV). During this process, features such as color, shape, and important objects are analyzed to generate data that forms the basis for activity instructions.

[0730] Step 2:

[0731] The server utilizes a generative AI model to automatically generate activity instructions based on extracted visual features. This process includes designing and prioritizing tasks based on the generated data. Specifically, it sets work tasks such as "adjusting character color schemes" and "adding background details." The generated activity instructions are sent to the terminal as a task list.

[0732] Step 3:

[0733] The terminal displays the task list received from the server in its user interface. The user reviews the task list through the terminal and accesses each worker's schedule and skills information. Based on this information, the terminal provides the server with worker availability and skills information via a scheduling tool (e.g., Google Calendar). This information is used to optimize task assignment.

[0734] Step 4:

[0735] The server uses a generated AI model to optimally assign tasks based on the worker's schedule and skill information obtained from the terminal. In doing so, it considers each worker's past performance and current workload to ensure efficient and appropriate task allocation. Once a task is assigned, the result is sent to the terminal and the worker is notified.

[0736] Step 5:

[0737] Users monitor project task progress using their terminals. Progress is displayed in real time in a dashboard format, and users can issue new instructions or make adjustments as needed. If necessary, users can enter prompt messages to register stakeholder requests, allowing the entire system to respond flexibly accordingly. Sending specific prompts, such as "Add a new scene and make it available for review by next week's meeting," triggers server-side analysis and task adjustments.

[0738] (Application Example 1)

[0739] 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".

[0740] In recent years, multimedia production and content distribution services have involved vast amounts of information and numerous workers, necessitating efficient task generation and optimal work allocation. Furthermore, rapid content recommendations tailored to viewer interests are also crucial. A system is needed to address these challenges and deliver high-quality deliverables.

[0741] 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.

[0742] In this invention, the server includes means for analyzing image data to extract visual information and automatically generating tasks in multimedia production; means for evaluating the workload and suitability of various workers based on the extracted information and assigning tasks to the most suitable workers; and means for automating content recommendations based on the user's visual characteristics. This makes it possible to improve work efficiency and provide users with the most suitable content.

[0743] "Image data" refers to digital data that contains visual information.

[0744] "Visual information" refers to characteristic information such as structure, color, and shape extracted from image data.

[0745] "Multimedia production" is the process of creating a work by combining multiple media such as video, music, and graphic design.

[0746] "Methods for automatically generating tasks" refers to a function in the system that defines and lists various tasks for a project based on image data.

[0747] "Evaluating the workload and suitability of workers" means analyzing the current workload and skills of individual workers.

[0748] "Assigning tasks to the most suitable workers" is the process of distributing the appropriate tasks to the most suitable workers based on evaluation results.

[0749] "Automating content recommendations based on the user's visual characteristics" refers to a function that analyzes the user's past viewing history and preferences to suggest the most suitable content.

[0750] A "system" is a collection of multiple components designed to perform a specific function.

[0751] This invention is a system that enables efficient task management in multimedia production and content distribution, and provides optimal content to users, by extracting visual information through the analysis of image data.

[0752] The server first analyzes image data using an image processing library to extract visual features. This makes it possible to automatically generate tasks necessary for a project. For example, it can create detailed work instructions for each scene in a storyboard based on the visual features. Based on the extracted features, the server takes into account the worker's schedule and skill information and automatically assigns tasks to the most suitable worker. This reduces the workload on workers and ensures the smooth progress of the project.

[0753] The terminal has the function of receiving task lists sent from the server and presenting them visually to the person in charge of managing the work. By operating the terminal, the user can manage the work project and advance the project based on the generated task list.

[0754] Furthermore, the server uses a generative AI model to analyze viewing history based on the user's visual characteristics and automatically recommends content best suited to each individual user. This makes it easy for users to discover new content tailored to their preferences.

[0755] For example, if a user frequently watches action movies, the system can extract their visual characteristics and automatically recommend movies and TV shows in a similar action genre. An example of a prompt message would be, "Please suggest relevant content considering this user's viewing history."

[0756] As described above, this system streamlines the multimedia production and content distribution processes and improves the user experience.

[0757] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0758] Step 1:

[0759] The server uses an image processing algorithm (e.g., the OpenCV library) to analyze the received image data as input. This process extracts visual features from the image (e.g., color and shape information) and outputs them to a database.

[0760] Step 2:

[0761] The server automatically generates a task list based on the extracted visual features using a generative AI model. At this stage, specific tasks are set according to each feature. The generated task list is output as data necessary for project management.

[0762] Step 3:

[0763] The terminal receives the task list sent from the server and displays it to the person in charge of managing the task. This display is visually easy to understand and provides information that enables the worker to proceed with the work efficiently.

[0764] Step 4:

[0765] The server uses the worker schedule and skill information it already possesses as input to assign tasks to the most suitable workers. Here, it evaluates the availability of schedules and the suitability of skills to output the optimal assignment result.

[0766] Step 5:

[0767] Users can use their terminals to check the progress of the entire project and adjust the task list as needed. Progress information is updated continuously by the server, reflecting the latest status.

[0768] Step 6:

[0769] The server provides the user's viewing history and extracted visual features as input to a generating AI model, which then recommends the most suitable content. This process outputs new recommended content to the user, improving the content consumption experience.

[0770] 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.

[0771] This invention not only streamlines the workflow in multimedia production but also provides a system that recognizes the emotions of workers and users to aid in project management. The system begins with analyzing image data, evaluates the user's emotions using an emotion engine, and adjusts tasks and provides feedback as needed.

[0772] System Configuration

[0773] 1. Server

[0774] The server receives image data and extracts visual information using an image recognition algorithm. Based on this, it automatically generates a task list and incorporates it into the project's progress.

[0775] 2. Terminal

[0776] The terminal manages user input data and worker information, and handles task distribution and schedule management through communication with the server. In addition, it provides appropriate support to users based on feedback from the emotion engine.

[0777] 3. User

[0778] Users give project instructions and receive personalized suggestions based on their emotional state, as recognized by the emotion engine. They can change task priorities and adjust resource allocation as needed.

[0779] 4. Emotional Engine

[0780] The emotion engine analyzes the user's emotional state from their behavior, voice, and text, and sends the results to the server. This information is used for task allocation and feedback generation, contributing to stress management and improved motivation among workers.

[0781] Program processing flow

[0782] The server first analyzes visual information from image data and generates tasks. Next, the terminal provides these tasks to the user and requests the server to optimize task assignments based on the user's schedule and worker information. Furthermore, the emotion engine recognizes the user's current emotional state, and the server uses this information to adjust task priorities and distribution.

[0783] For example, if the emotion engine determines that a user is experiencing stress, the server adjusts the task volume and provides appropriate feedback to the user or worker through the terminal. In this way, the system not only supports the smooth progress of the project and improves the quality of work, but also enables a human-centered process through emotion management.

[0784] The following describes the processing flow.

[0785] Step 1:

[0786] The server receives image data provided by the user. This includes important visual information necessary for the project's progress.

[0787] Step 2:

[0788] The server analyzes the received image data using an image recognition algorithm. Through this analysis, it extracts visual information related to the scene setting and character movements.

[0789] Step 3:

[0790] The server automatically generates the necessary tasks based on the extracted visual information. Specifically, this includes things like character animation and background design.

[0791] Step 4:

[0792] The terminal displays a task list sent from the server to the user. Through this display, the user can grasp the overall picture of the project.

[0793] Step 5:

[0794] The terminal transmits the worker's schedule and skill information, provided by the user, to the server. This information is crucial for efficient task assignment.

[0795] Step 6:

[0796] The server automatically assigns tasks to the most suitable workers based on schedule and skill information, taking into particular consideration the workers' current workload and expertise.

[0797] Step 7:

[0798] The emotion engine activates, recognizing the user's emotional state from their behavioral data and voice. This information is designed to aid in the overall operation of the system.

[0799] Step 8:

[0800] The server uses emotional information provided by the emotion engine to provide appropriate feedback and task adjustments. This reduces user stress and provides a better work environment.

[0801] Step 9:

[0802] The terminal notifies users and workers of adjusted tasks and feedback. This allows all members to understand the current expected behavior and respond to any necessary changes.

[0803] (Example 2)

[0804] 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".

[0805] In multimedia production projects, there is a need to simultaneously achieve increased work efficiency and reduced mental burden on workers. However, traditional methods involve generating and assigning tasks individually, making it difficult to maximize overall work efficiency, and project management does not take into account the emotional state of the workers. As a result, project progress may be delayed, worker stress may increase, and the quality of work may decline.

[0806] 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.

[0807] In this invention, the server includes means for analyzing image data to extract visual information and automatically generating tasks for multimedia production; means for evaluating the workload and suitability of multiple workers based on the extracted information and assigning tasks to the most suitable workers; and means for evaluating the emotional state of users using emotion analysis technology and integrating that information into the project plan. This enables efficient project progress and appropriate management based on the emotional state of workers.

[0808] "Image data" refers to electronic data containing visual information, including photographs, illustrations, and diagrams.

[0809] "Analysis" is a process performed to extract or classify specific information from data.

[0810] "Visual information" refers to the visual features contained in image data, such as color, shape, pattern, and objects.

[0811] "Multimedia production" is the process of creating content by integrating multiple media such as text, images, audio, and video.

[0812] A "task" is an individual unit of work necessary for the progress of a project.

[0813] "Automatic generation" refers to the process where algorithms or software generate tasks or data without human intervention.

[0814] "Workload" refers to the amount and difficulty level of work that a worker must complete within a specific period.

[0815] "Aptitude" refers to the extent to which a worker possesses the necessary skills and qualifications to perform a particular task.

[0816] "Assigning" refers to the act of assigning a specific task or resource to a specific worker or group.

[0817] "Emotional analysis technology" is a technology that reads a user's emotional state from data and patterns and analyzes that information.

[0818] "Emotional state" refers to the user's psychological and emotional state.

[0819] A "project plan" is a detailed plan that outlines the policies, resource allocation, and timeline for achieving the project's objectives.

[0820] This invention provides a system that analyzes image data, extracts visual information, automatically generates tasks in multimedia production, and streamlines project management. The embodiments for carrying out this invention are shown below.

[0821] The server first receives image data sent from users or workers. Image data is typically acquired using input devices such as digital cameras or scanners. The server uses existing algorithms known as generative AI models to execute image recognition algorithms. These algorithms have the ability to analyze color, shape, and object patterns from image data and visually extract information based on them.

[0822] The terminal receives a task list generated from the server based on visual information and presents it to the user. The terminal notifies the user of the task content, importance, and deadline in a visually easy-to-understand format. The user can then review this information and take appropriate action based on their schedule and circumstances.

[0823] Furthermore, an emotion engine incorporating emotion analysis technology evaluates the user's emotional state using user input data, voice, or text. This emotional information is used by the server to optimize project planning. For example, if the server determines that the user is in a high-stress state, it readjusts tasks and takes measures to reduce the burden.

[0824] As a concrete example, when a user edits a specific image in a project, related editing tasks are automatically generated based on the analysis results of that image. By using a prompt message such as "Please tell me the important information that should be extracted from this image," the image recognition algorithm automatically extracts the necessary information and reflects it in the task list.

[0825] In this way, the system can streamline project management and provide support tailored to the user's emotions and circumstances, thereby improving the quality and efficiency of multimedia production projects.

[0826] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0827] Step 1:

[0828] The server receives image data from users or workers. This input image data is acquired from digital devices. Based on the received image data, the server executes an image recognition algorithm. This process uses a generative AI model to analyze color, shape, and pattern from the image and extract visual features. As output, metadata containing the visual features is generated.

[0829] Step 2:

[0830] The server automatically generates a task list based on visual features. The extracted visual features are used as input for this task list generation. Specific tasks, such as "tagging people in an image" or "adjusting background color," are generated. As a result, a task list containing multiple specific tasks is output and sent to the terminal.

[0831] Step 3:

[0832] The terminal displays a task list received from the server to the user. The input here is the task list sent from the server; the terminal does not need to repeatedly confirm this, but it presents it in detail. The user has the ability to proceed with their work based on this list and send feedback to the system. The output is a list of executable tasks presented to the user.

[0833] Step 4:

[0834] The emotion engine analyzes emotional data obtained from the user. Inputs include user voice, text, and interaction data. Based on this data, a generative AI model performs emotion analysis to determine the user's emotional state. The output is evaluation data indicating the emotional state.

[0835] Step 5:

[0836] The server adjusts the task list using sentiment evaluation data obtained from the sentiment engine. This sentiment data serves as input, taking into account states such as high stress and fatigue. The server repriors tasks as needed and transfers tasks to other members. This results in an adjusted task list being output and sent back to the terminal.

[0837] (Application Example 2)

[0838] 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".

[0839] Providing prompt and efficient public services in urban areas is a common challenge for many cities. Especially in densely populated areas, accurately understanding residents' needs and emotional states and providing appropriate services based on that understanding is crucial. However, conventional systems struggle to make rapid service improvements and suggestions that take emotional fluctuations into account. Therefore, there is a need for a system that analyzes residents' emotional states and provides personalized suggestions.

[0840] 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.

[0841] In this invention, the server includes means for analyzing image data to extract visual information and automatically generating tasks related to urban residents; means for determining the emotional state of residents based on the extracted information and proposing optimal citizen services; and means for providing individually tailored recommendations for urban residents based on the generated feedback. This makes it possible to analyze the emotional state of residents in real time, provide optimal services, and improve resident satisfaction.

[0842] "Image data" refers to digital data containing visual information that is analyzed by a computer.

[0843] "Visual information" refers to information such as shape, color, and pattern that is extracted from image data and obtained through analysis.

[0844] A "task" is a set of actions or tasks necessary to achieve a specific goal.

[0845] A "worker" refers to an individual or team performing a task, possessing specific skills or aptitudes.

[0846] A "text generation algorithm" is a computer program that automatically generates documents in natural language.

[0847] "Natural language processing technology" is a technology that processes human language using computers, and is used in applications such as speech recognition and translation.

[0848] "Emotion recognition technology" is a technology that analyzes and identifies an individual's emotional state, and utilizes data such as voice and facial expressions.

[0849] "Feedback" refers to the information and responses that a system provides to a user, which are used to improve behavior or conditions.

[0850] A "city resident" is an individual who has their base of operations in a specific city and is involved with the services and environment of that area.

[0851] "Citizen services" refer to various services provided by local governments and public institutions to residents, with the aim of improving their quality of life.

[0852] This invention is a system for analyzing the emotional state of urban residents and providing appropriate public services. The system consists of three elements: a server, a terminal, and a user. The specific role of each element will be explained below.

[0853] The server is primarily responsible for data analysis and task generation. Specifically, it receives image data and uses OpenCV to extract visual information. This visual information is used for automated task generation and emotion recognition. Emotion recognition technology is implemented using Google Cloud's natural language processing API to analyze the emotional state of residents. Based on the analysis results, a program is constructed to propose optimal citizen services. In addition, AWS is used for data processing and storage to support scalable service operation.

[0854] The terminal primarily collects user input data and communicates with the server. Mobile devices such as smartphones and smart glasses are used to collect user image and audio data. The data acquired from these devices is transferred to the server in real time and used for analysis and providing feedback. The feedback is provided to the user through the terminal, and personalized recommendations are made.

[0855] Through interaction with the system, users receive civic services based on their emotional state. If the system determines that a user's stress level is high, appropriate relaxation events and resources are recommended. For example, notifications about relaxation workshops held in the user's area are sent to their device.

[0856] An example of a prompt is: "Analyze recent selfies and voice memos taken with the user's smartphone camera to determine if they are feeling stressed and suggest events that would be effective for relaxation." Using this prompt, the generative AI model generates feedback and service suggestions.

[0857] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0858] Step 1:

[0859] The device collects image and audio data from the user. Using the camera and microphone built into the device, it captures the user's facial expressions and voice in real time. This data is temporarily stored on the device for use in the next processing step. The input consists of image and audio data, while the output is data sent to the server.

[0860] Step 2:

[0861] The server receives image data sent from the terminal. It uses OpenCV to extract visual information from the image data. Specifically, it analyzes the user's facial expressions and facial muscle movements to estimate their emotional state. The input is image data, and the output is the extracted visual information.

[0862] Step 3:

[0863] The server analyzes the audio data using Google Cloud's natural language processing API. It analyzes the tone of voice and word choice to identify potential emotional indicators. This process evaluates the user's emotional state based on the audio data. The input is audio data, and the output is emotional indicators.

[0864] Step 4:

[0865] The server integrates visual information and auditory emotional indicators to evaluate the user's overall emotional state. This allows for the quantification of the user's current stress level, happiness level, and other factors. The input consists of visual information and auditory emotional indicators, while the output is the result of the integrated emotional state evaluation.

[0866] Step 5:

[0867] The server generates suggestions for civic services tailored to the user based on the evaluation results. Using a generative AI model, it creates optimal feedback and event suggestions according to prompts. Specifically, it recommends information on relaxation events when the user's stress level is high. The input is the integrated sentiment evaluation result, and the output is the service suggestion.

[0868] Step 6:

[0869] The server sends the generated proposal to the terminal and notifies the user. The terminal receives this and displays it on the screen for the user to confirm. The input is the service proposal, and the output is the notification to the user.

[0870] Step 7:

[0871] The user reviews the suggestions received from the device and utilizes the suggested resources if necessary. Through the device's interface, the user can directly access events of interest or obtain additional information. Input is the user's notification, and output is the user's chosen action.

[0872] 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.

[0873] 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.

[0874] 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.

[0875] 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.

[0876] 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.

[0877] 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.

[0878] 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.

[0879] 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.

[0880] 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."

[0881] 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.

[0882] 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.

[0883] 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.

[0884] 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.

[0885] 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.

[0886] 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.

[0887] 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.

[0888] 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.

[0889] 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.

[0890] 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.

[0891] 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.

[0892] 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.

[0893] The following is further disclosed regarding the embodiments described above.

[0894] (Claim 1)

[0895] A means of analyzing image data to extract visual information and automatically generating tasks in multimedia production,

[0896] A means for evaluating the workload and suitability of various workers based on extracted information, and assigning tasks to the most suitable workers,

[0897] A means of automatically creating documents related to work contracts using text generation algorithms and quickly obtaining agreement between the relevant parties,

[0898] A means of analyzing stakeholder demands using natural language processing technology and reflecting them in the multimedia production process,

[0899] A system that includes this.

[0900] (Claim 2)

[0901] The system according to claim 1, which manages the schedules and skill information of workers and enables efficient work assignment.

[0902] (Claim 3)

[0903] The system according to claim 1, which monitors the progress of the entire work project based on the generated task list and provides an optimal work plan.

[0904] "Example 1"

[0905] (Claim 1)

[0906] A means of analyzing image data to extract visual features and automatically generating activity instructions in digital content creation,

[0907] A means of evaluating the workload and suitability of various workers based on extracted information, and assigning activities to the most suitable workers,

[0908] A means of analyzing stakeholder demands using natural language processing technology and reflecting them in the digital content creation process,

[0909] A means of managing schedule and skill information and enabling efficient activity assignment,

[0910] A system that includes this.

[0911] (Claim 2)

[0912] The system according to claim 1, which monitors the progress of the entire work plan based on the generated activity instructions and provides an optimal work plan.

[0913] (Claim 3)

[0914] The system according to claim 1, which optimizes the analysis process by checking the received image data and converting it to a standard format.

[0915] "Application Example 1"

[0916] (Claim 1)

[0917] A means of analyzing image data to extract visual information and automatically generating tasks in multimedia production,

[0918] A means for evaluating the workload and suitability of various workers based on extracted information, and assigning tasks to the most suitable workers,

[0919] A method for automating content recommendations based on the user's visual characteristics,

[0920] A means of analyzing stakeholder demands using natural language processing technology and reflecting them in the multimedia production process,

[0921] A system that includes this.

[0922] (Claim 2)

[0923] The system according to claim 1, which manages the schedules and skill information of workers and enables efficient work assignment.

[0924] (Claim 3)

[0925] The system according to claim 1, which monitors the progress of the entire work project based on the generated task list and provides an optimal work plan.

[0926] "Example 2 of combining an emotion engine"

[0927] (Claim 1)

[0928] A means of analyzing image data to extract visual information and automatically generating tasks in multimedia production,

[0929] A means for evaluating the workload and suitability of multiple workers based on extracted information and assigning tasks to the most suitable workers,

[0930] A method for distributing the generated task list to terminals and requesting optimization based on the worker's schedule,

[0931] A means of evaluating the emotional state of users using emotion analysis technology and integrating that information into the project plan,

[0932] A system that includes this.

[0933] (Claim 2)

[0934] The system according to claim 1, which manages the schedules and technical information of workers and enables efficient work assignment.

[0935] (Claim 3)

[0936] The system according to claim 1, which dynamically adjusts the priority of a generated task list based on feedback from an emotion engine.

[0937] "Application example 2 when combining with an emotional engine"

[0938] (Claim 1)

[0939] A means of analyzing image data to extract visual information and automatically generating tasks in multimedia production,

[0940] A means for evaluating the workload and suitability of various workers based on extracted information, and assigning tasks to the most suitable workers,

[0941] A means of automatically creating documents related to work contracts using text generation algorithms and quickly obtaining agreement between the relevant parties,

[0942] A means of analyzing stakeholder demands using natural language processing technology and reflecting them in the multimedia production process,

[0943] A means of improving the content of citizen services by using emotion recognition technology to determine the emotional state of users,

[0944] A means of providing individually tailored recommendations for urban residents using the generated feedback,

[0945] A system that includes this.

[0946] (Claim 2)

[0947] The system according to claim 1, which manages the schedules and skill information of workers and enables efficient work assignment.

[0948] (Claim 3)

[0949] The system according to claim 1, which monitors the progress of the entire work project based on the generated task list and provides an optimal work plan. [Explanation of symbols]

[0950] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of analyzing image data to extract visual information and automatically generating tasks in multimedia production, A means for evaluating the workload and suitability of various workers based on extracted information, and assigning tasks to the most suitable workers, A means of automatically creating documents related to work contracts using text generation algorithms and quickly obtaining agreement between the relevant parties, A means of analyzing stakeholder demands using natural language processing technology and reflecting them in the multimedia production process, A system that includes this.

2. The system according to claim 1, which manages the schedules and skill information of workers and enables efficient work assignment.

3. The system according to claim 1, which monitors the progress of the entire work project based on the generated task list and provides an optimal work plan.

Images