system

Abstract

Provide a system. A means for users to upload AI-generated works; means for the server to classify uploaded works based on format; A means for the server to execute a dedicated evaluation flow for each format; A means for the server to aggregate and rank the evaluation results; a means for disclosing the evaluation results and rankings to users; A system including:

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the 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] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] In recent years, the quality of content generated by artificial intelligence (AI) has rapidly improved, making the evaluation of AI-generated works (e.g., images, music, and manga) an important issue. However, when evaluating these works using conventional methods, the creative and technical aspects unique to AI generation are often not fully taken into account. Furthermore, there is a lack of systems that can verify whether works uploaded by users are truly AI-generated and properly classify and evaluate them. Therefore, there is a need for an efficient system that can accurately and fairly evaluate AI-generated works and make the results public to users. [Means for solving the problem]

[0005] To solve this problem, the present invention provides the following means.

[0006] The system includes a means for users to upload AI-generated works, a means for a server to classify the uploaded works based on their format, a means for the server to execute a dedicated evaluation flow for each format, a means for the server to tally and rank the evaluation results, and a means for the server to disclose the evaluation results and rankings to users.

[0007] Furthermore, the server includes a means for determining whether an uploaded work is AI-generated, ensuring that the work being evaluated is accurately AI-generated. The evaluation flow also includes a score generation means including evaluation criteria for color, composition, creativity, and technical aspects; a score generation means including evaluation criteria for rhythm, melody, creativity, and sound quality; and a score generation means including evaluation criteria for story, character quality, art style, and creativity, allowing for appropriate evaluation of each type of work. Evaluation results are recorded in a database, and a means for notifying users of the evaluation results is provided, allowing users to easily check how their work was evaluated.

[0008] "User" means a person or entity that uses the system to upload AI-generated works and receive evaluation results.

[0009] "AI-generated works" refers to content such as images, music, and comics generated using artificial intelligence technology.

[0010] "Server" is a central control device in the system, and is a computer device that processes uploading of works, categorization, evaluation, and publication of results.

[0011] "Upload" refers to the act of a user sending data from their own device to a server.

[0012] "Format" refers to the type of uploaded work (e.g., image, music, manga, etc.) and is a classification standard for adapting to the evaluation flow.

[0013] "Evaluation flow" refers to a series of evaluation processing steps that the server performs on works in each format.

[0014] "Color" is one of the evaluation criteria for an image work, and is a standard for evaluating color balance and the beauty of color schemes.

[0015] "Composition" is a standard for evaluating the balance of the visual arrangement and layout of an image.

[0016] "Creativity" is a criterion for evaluating the originality and novelty of a work, and is an evaluation item used commonly across all formats.

[0017] "Technical aspects" is a criterion used to evaluate the level of skill with which a work is produced, and is used particularly for visual works.

[0018] "Rhythm" is one of the evaluation criteria for musical works, and is a standard for assessing the accuracy of the tempo and beat of the music.

[0019] "Melody" is a criterion for evaluating the main melody part of a musical work.

[0020] "Sound quality" is a measure of the quality of the sound in a musical work.

[0021] "Story quality" is one of the evaluation criteria for manga works, and is a standard for assessing the quality of the story and the entertainment value of the development.

[0022] "Character quality" is a standard for evaluating the design and appeal of characters that appear in manga.

[0023] "Art style" is a standard for evaluating the visual expression and style of a manga.

[0024] The "evaluation result" is data that constitutes the final evaluation, calculated by tallying up the scores generated by the server based on each evaluation item.

[0025] "Ranking" refers to the process of comparing the evaluation results of multiple works and ranking them.

[0026] "Notification" refers to the act of sending a message or email to a user informing them of the evaluation results or other information from the system.

[0027] A "database" is a storage device within a computer that manages and stores various data in a system. [Brief explanation of the drawings]

[0028] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0029] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0030] First, the terms used in the following description will be explained.

[0031] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0032] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0033] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0034] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0035] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0036] [First embodiment]

[0037] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0038] 1, a 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.

[0039] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0040] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0041] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the 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.

[0042] 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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0043] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0044] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0045] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

[0046] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0047] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0048] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0049] The system of this invention allows users to fairly evaluate AI-generated works. The system begins with the user uploading the work, and then the server classifies the work, executes the appropriate evaluation flow, and compiles and publishes the results.

[0050] 1. Upload your work

[0051] Users use their devices to upload AI-generated images, music, comics, and other works to the system. On the upload screen, users enter metadata such as the work's name, description, and category. The device then sends the uploaded data to the server.

[0052] 2. Classification of works

[0053] The server receives the uploaded work and verifies that it is AI-generated. This verification is done using a deep learning model. This model analyzes the characteristics of the work and determines the likelihood that it was generated by AI. This prevents non-AI-generated works from proceeding to the next step.

[0054] Works that are confirmed to be AI-generated are classified into their format (images, music, manga, etc.) and assigned to the appropriate evaluation flow.

[0055] 3. Dedicated evaluation flow

[0056] The server then applies the appropriate evaluation flow to the classified works. For images, it evaluates color, composition, creativity, and technical aspects. For music, it evaluates melody, rhythm, creativity, and sound quality. For manga, it evaluates story, character quality, art style, and creativity.

[0057] For example, when an image is uploaded, the server uses a color detection algorithm to evaluate color balance and facial detection technology to evaluate composition, generating a separate score based on each evaluation factor.

[0058] 4. Calculation and ranking of evaluation results

[0059] The server aggregates the evaluation results for each work. For example, for an image work, it aggregates each score such as "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Technique: 6 / 10," and calculates an overall evaluation score. Each work is ranked based on the calculated overall score.

[0060] 5. Publication of evaluation results

[0061] The aggregated evaluation results are stored in a database, and the server makes these results available for users to view. Users can check the evaluation results from their own devices using a web interface or application.

[0062] As a concrete example, consider the case where User A uploads an image titled "Spring Scenery." The server confirms that this image is AI-generated and evaluates it according to an evaluation flow specifically for images. The evaluation results are "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Technology: 6 / 10," resulting in an overall evaluation score of "30 / 40." These evaluation results are ranked, and User A can check from his or her device how "Spring Scenery" is ranked.

[0063] In this way, the system of the present invention accurately and fairly evaluates AI-generated works uploaded by users and appropriately discloses the evaluation results to users, thereby improving the quality of AI-generated works and ensuring transparency and fairness in the evaluation process.

[0064] The processing flow will be explained below.

[0065] Step 1:

[0066] Users upload AI-generated artworks using their devices. They select artworks such as images, music, and manga from a file selection screen via a web form or dedicated application. They also enter metadata such as the artwork's name, description, and category.

[0067] Step 2:

[0068] The device sends the entered work data and metadata to the server via HTTP requests or API calls.

[0069] Step 3:

[0070] The server receives the work data. After receiving it, the server checks the data size and file format, checking whether it is in a standard format, such as JPG or PNG for images, or MP3 or WAV for music.

[0071] Step 4:

[0072] The server records the received work data and metadata in a database, along with additional information such as the work ID and timestamp.

[0073] Step 5:

[0074] The server analyzes the stored artwork data and uses a deep learning model to determine whether the artwork is AI-generated. The model analyzes the artwork's characteristics and outputs a score indicating the likelihood of AI generation.

[0075] Step 6:

[0076] The server automatically classifies the work by format, such as image, music, or manga, and then assigns it to the corresponding evaluation flow based on the classification results.

[0077] Step 7:

[0078] The server executes the evaluation flow for each method. For example, in the case of an image, it evaluates color balance using a color detection algorithm and composition using face detection technology. A score is generated based on each evaluation item.

[0079] Step 8:

[0080] The server aggregates the scores for each evaluation item and calculates an overall evaluation score. The final score is calculated by summing or averaging the scores for each evaluation item.

[0081] Step 9:

[0082] The server compares the overall scores of all works and ranks them. The ranking results are updated in the database, and each work is given a rank.

[0083] Step 10:

[0084] The server publishes the evaluation results and rankings to users by generating a web page for publication, and users can view the evaluation results by accessing that page.

[0085] Step 11:

[0086] The server will notify the user of the evaluation results via email or the app's notification function.

[0087] Step 12:

[0088] Users can check the evaluation results on their own devices. Users will receive a notification and can access the detailed evaluation result page via a specified link or in-app menu to check the evaluation content and ranking.

[0089] Example 1

[0090] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0091] In recent years, advances in generative AI technology have led to an increase in the number of AI-generated works in a variety of formats. However, due to the lack of a standard system for fairly and objectively evaluating these works, quality evaluations and rankings of works often lack transparency and fairness. As a result, it is difficult for users to accurately grasp the quality of their own works. In addition, the lack of consistency in the evaluation process makes it difficult to compare works of different formats.

[0092] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0093] In this invention, the server includes: a means for users to upload AI-generated works; a means for a terminal to send metadata of the uploaded works to the server; a means for the server to verify that the uploaded works are AI-generated using a deep learning model; a means for the server to classify the works based on their format; a means for the server to execute a dedicated evaluation flow for each format; a means for the server to generate scores based on evaluation criteria such as color, composition, creativity, and technical aspects; a means for the server to aggregate and rank the evaluation results; and a means for the server to disclose the evaluation results and rankings to users. This enables transparent and consistent evaluation of AI-generated works, allowing users to accurately determine the merits of their own works. Furthermore, fair ranking based on the scores generated during the evaluation process makes it easier to compare works of different formats.

[0094] "User" means an individual or entity that accesses the System and uploads AI-generated Works.

[0095] A "terminal" is a device (computer, smartphone, tablet, etc.) that a user uses to input a work and send metadata to a server.

[0096] A "server" is a computer system that receives, categorizes, evaluates, and aggregates uploaded works, and then makes the evaluation results available to users.

[0097] "AI-generated works" are images, music, comics, and other creative works that are automatically or semi-automatically generated using artificial intelligence technology.

[0098] "Metadata" is additional information related to a work, such as the work's name, description, and category.

[0099] A "deep learning model" is an algorithm or network based on deep learning, a technology used to analyze and recognize AI-generated works.

[0100] "Classification" is the process of dividing uploaded works into categories based on their format (e.g., images, music, comics, etc.).

[0101] An "evaluation flow" is a series of procedures or algorithms that evaluate the quality and characteristics of a work based on evaluation criteria defined for each format.

[0102] A "score" is a score or evaluation value for a specific evaluation item that is generated through an evaluation flow.

[0103] The "color detection algorithm" is an algorithm for analyzing and evaluating the color balance and color placement of a work.

[0104] "Face detection technology" is a technology for identifying the position and number of faces in an image.

[0105] "Tallying" is the process of adding up the scores for each evaluation item to calculate an overall evaluation score.

[0106] "Ranking" is the process of determining the relative order of works based on their overall evaluation scores.

[0107] "Public" means to display and provide evaluation results and ranking information so that users can view them.

[0108] The system of this invention allows users to fairly evaluate AI-generated works. The system begins with the user uploading the work, and then the server classifies the work, executes the appropriate evaluation flow, and compiles and publishes the evaluation results.

[0109] First, a user uses a device to upload AI-generated images, music, manga, or other works to the system. Specifically, the user enters metadata such as the "work name," "work description," and "work category" on the upload screen, and the device then sends the work file along with this data to the server.

[0110] The server receives the uploaded data, analyzes the raw artwork file and metadata, and uses a deep learning model to confirm whether the artwork is AI-generated. Typical deep learning models used are TENSORFLOW (registered trademark) and PyTorch. This model analyzes the artwork's feature vector and calculates the probability of AI generation. Based on this result, the server will not proceed to the next step if the artwork is confirmed not to be AI-generated, and will notify the user.

[0111] The server categorizes works confirmed to be AI-generated based on their format, such as images, music, or comics. A dedicated evaluation process is applied to each classified work. For images, the server evaluates color balance using a color detection algorithm (e.g., OpenCV) and composition using face detection technology. It also evaluates creativity and technical aspects using machine learning models.

[0112] The server then calculates an overall score by adding up the scores generated for each evaluation item. For example, for an image work, the server would add up scores such as "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Technique: 6 / 10" to give an overall score of "30 / 40."

[0113] Finally, the server ranks the works based on these evaluation results and stores the information in a database. The evaluation results and rankings are made publicly accessible to users. Specifically, when a user accesses the system using a terminal and clicks the "View Evaluation Results" button, a screen will appear displaying the aggregated scores and ranks.

[0114] As a concrete example, consider the case where User A uploads an image titled "Spring Landscape." The server confirms that the image is AI-generated and performs color detection, face detection, and creativity and technical evaluation according to an evaluation flow specifically for images. The evaluation results are "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Technology: 6 / 10," resulting in an overall evaluation score of "30 / 40." The rankings are updated based on these scores, and User A can check from his or her device where "Spring Landscape" ranks.

[0115] As described above, the system of the present invention can accurately and fairly evaluate AI-generated works uploaded by users and quickly make the evaluation results available to users, thereby improving the quality of AI-generated works and ensuring transparency and fairness in the evaluation process.

[0116] Example prompt sentence:

[0117] "Run this image evaluation flow to generate and rank scores based on color, composition, creativity, and technique."

[0118] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0119] Step 1:

[0120] The user uses the device to access the upload screen. On the upload screen, they enter metadata such as the "work name," "work description," and "work category." After completing the entry, the user selects the work file and clicks the upload button. This sends the work file and metadata from the device to the server.

[0121] Input: User-entered work name, work description, work category, work file

[0122] Output: Upload data sent to the server

[0123] Step 2:

[0124] The server receives the uploaded data sent by the user. The server first checks the integrity of the data and analyzes the received metadata and the format of the work file. Next, it uses a deep learning model (e.g., TensorFlow or PyTorch) to confirm whether the work is AI-generated. Works that are confirmed to be AI-generated proceed to the next step.

[0125] Input: Upload data sent by the user

[0126] Output: AI generation confirmation result (True / False), work format classification

[0127] Step 3:

[0128] The server classifies works that are confirmed to be AI-generated based on their format (images, music, manga, etc.) using pre-defined rules and algorithms. Works of each type are then assigned to their own evaluation flow.

[0129] Input: AI generation confirmation result, work format

[0130] Output: Classification results (images, music, manga, etc.)

[0131] Step 4:

[0132] The server applies a dedicated evaluation flow to each classified work. For example, for image works, it evaluates color balance using a color detection algorithm (using OpenCV) and composition using face detection technology. Other creative and technical aspects are also analyzed and evaluated using machine learning models.

[0133] Input: Classified works

[0134] Output: Score for each evaluation item (color, composition, creativity, technique, etc.)

[0135] Step 5:

[0136] The server aggregates the scores generated for each evaluation category. For example, for an image, the scores might be "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Technique: 6 / 10." These scores are then added together to calculate an overall evaluation score.

[0137] Input: Score for each evaluation item

[0138] Output: Overall evaluation score

[0139] Step 6:

[0140] The server automatically ranks the works based on the total score, and the ranking information is stored in a database.

[0141] Input: Overall evaluation score

[0142] Output: Ranked work information

[0143] Step 7:

[0144] The server stores the evaluation results and rankings in a database and makes them available for viewing by users. Users can access the system using their devices and click the "View Evaluation Results" button to check the evaluation results and rankings of their own works.

[0145] Input: Saved evaluation results and ranking information

[0146] Output: Evaluation results and ranking information displayed on the user screen

[0147] (Application example 1)

[0148] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0149] Food delivery services are required to improve the efficiency of new menu development and promotional activities by fairly evaluating and ranking the quality and appeal of AI-generated food images and menus. In current systems, such evaluations are often done manually, which lacks fairness and transparency. Furthermore, there is a possibility that images that are not AI-generated may be mixed in, making it difficult to ensure reliability.

[0150] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0151] In this invention, the server includes a means for users to upload AI-generated creations, a means for the server to classify the uploaded creations based on their format, and a means for the server to execute a dedicated evaluation flow for each format, thereby enabling a food delivery service to fairly and efficiently evaluate the color, composition, creativity, and delicious appearance of AI-generated food images and menus, and to aggregate and rank the evaluation results.

[0152] "User" means an individual or legal entity that uses the system to upload AI-generated works.

[0153] A "server" is a computer device that receives uploaded works, categorizes them, executes an evaluation flow, and aggregates and ranks the evaluation results.

[0154] "Works" are creative works such as AI-generated images, music, and comics uploaded by users.

[0155] "Classification" is the process by which the server identifies works received based on their format and places them into appropriate categories.

[0156] The "evaluation flow" is a series of evaluation processes that the server carries out on classified works, with different evaluation items set for each format.

[0157] "Evaluation results" refer to the aggregated scores for each evaluation item generated by the evaluation flow.

[0158] "Ranking" refers to ranking works based on the evaluation results.

[0159] "Food delivery service" refers to a service business that delivers food to customers who order it.

[0160] "Food images" are images of the appearance of food provided by food delivery services, and are important for stimulating the user's appetite.

[0161] A "menu" is a list of food and drinks offered by a food delivery service, showing the items that a customer can choose from.

[0162] "Color" is an item that evaluates the arrangement and balance of colors in a work.

[0163] "Composition" is an item that evaluates how the elements of a work are arranged.

[0164] "Creativity" is an item that evaluates how original and innovative a work is.

[0165] "Appetizing appearance" is an item that evaluates how visually appetizing a food image is.

[0166] This invention is a system for impartially evaluating AI-generated food images and menus for food delivery services. This system involves the steps of a user uploading AI-generated food images and menus, a server classifying, evaluating, and ranking the images, and publishing the results.

[0167] System Configuration

[0168] The system mainly consists of a user device, a server, and software that runs the evaluation flow. User devices are smartphones or PCs, while the server is a high-performance computer. The software used is a deep learning framework such as TensorFlow or a web framework such as Flask.

[0169] Processing steps

[0170] 1. Upload an image

[0171] Users upload AI-generated food images and menus to the system from their own devices, along with metadata such as the dish name, description, and category (e.g., appetizer, main dish, dessert, etc.).

[0172] 2. AI-generated judgment

[0173] The server uses a deep learning model (for example, a model built with TensorFlow) to determine whether the uploaded image is AI-generated. Only images that are recognized as AI-generated are allowed to proceed to the next step.

[0174] 3. Image Classification

[0175] Images that are confirmed to be AI-generated are then sorted into categories according to their format, which is based on the type of food (appetizer, main dish, dessert, etc.).

[0176] 4. Execute the evaluation flow

[0177] The server then runs an evaluation flow on the classified images, using algorithms to evaluate criteria such as color, composition, creativity, and appetizing appearance.

[0178] 5. Calculation and ranking of evaluation results

[0179] A score is generated for each item, and these scores are then aggregated to calculate an overall score. Based on the overall score, food images and menus are ranked.

[0180] 6. Publication of evaluation results

[0181] The evaluation results are stored on a server in a form that can be viewed by food delivery service administrators and users, and are made public through a web interface or application.

[0182] Specific examples

[0183] For example, consider a new menu item, "Spring Salad," generated using AI. A user uploads this image to the system as "Spring Salad." The server uses a TensorFlow model to verify that the image is AI-generated, and then evaluates it based on factors such as color balance, composition, creativity, and appetizing appearance. Finally, the server assigns ratings such as "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Appetizing: 9 / 10," resulting in an overall score of "33 / 40." These scores are reflected in the rankings, allowing administrators and users to see which menu items received the highest ratings.

[0184] Prompt Sentence Examples

[0185] "We used AI to generate food images for a new food delivery menu. Please rate these images on color, composition, creativity, and whether they look delicious."

[0186] This system will enable food delivery services to fairly and efficiently evaluate the appeal of new menu items, helping them with promotional activities and menu development.

[0187] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0188] Step 1:

[0189] Users upload AI-generated food images and menus to the system from their own devices. On the upload screen, users also enter metadata such as the dish name, description, and category (e.g., appetizer, main dish, dessert, etc.). The entered data and images are sent to the server.

[0190] Step 2:

[0191] The server uses a deep learning model (TensorFlow model) to determine whether an uploaded image is AI-generated. Specifically, the server inputs the image into the model and outputs a probability of whether it is AI-generated. If the result exceeds a threshold, the image is recognized as AI-generated. The input data is the image and its metadata, and the output data is the result of the AI-generated determination.

[0192] Step 3:

[0193] The server classifies images that are certified as AI-generated based on their format (category). Specifically, they are sorted according to food category (appetizer, main dish, dessert, etc.). The input data is the image and metadata, and the output data is the classification result, which is category information.

[0194] Step 4:

[0195] The server then runs an evaluation flow on the classified images, using algorithms to evaluate color, composition, creativity, and delicious appearance. The evaluation process analyzes color balance, evaluates the placement of elements, judges creativity, and evaluates how appetizing the food looks. The input data is the classified image, and the output data is the score for each evaluation item.

[0196] Step 5:

[0197] The server aggregates the scores for each evaluation item and calculates an overall score. For example, adding up evaluation scores such as "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Appetizing: 9 / 10," the overall score is "33 / 40." The input data is the score for each evaluation item, and the output data is the overall score.

[0198] Step 6:

[0199] The server ranks each food image and menu item based on the evaluation results (total score). Specifically, it lists all evaluation results and sorts them in ascending or descending order based on the score. The input data is the total score, and the output data is the ranked list.

[0200] Step 7:

[0201] The server publishes the evaluation results and rankings in a form that can be viewed by food delivery service administrators and users. Specifically, it makes them accessible through a web interface or application. Administrators and users can check the evaluation results from their own devices and use them to develop new menu items and promote their activities. The input data is a ranked list, and the output data is the evaluation results that can be viewed by users.

[0202] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0203] The system of this invention allows users to fairly evaluate AI-generated works, and by combining it with an emotion engine that recognizes the user's emotions, it provides a more personalized experience. The system flow is as follows:

[0204] 1. Upload your work

[0205] Users use their devices to upload AI-generated works such as images, music, and comics to the system. On the upload screen, users enter metadata such as the work's name, description, and category. When uploading, the emotion engine analyzes the user's emotions and sends the analysis results to the server as metadata. For example, emotional information such as whether the user is excited or happy is included in the metadata.

[0206] 2. Classification of works

[0207] The server receives the uploaded work and uses a deep learning model to determine whether the work is AI-generated. Once confirmed, the work is classified into its format and sent through a dedicated evaluation flow.

[0208] 3. Dedicated evaluation flow

[0209] The server then applies an appropriate evaluation process to each classified work. For example, for image works, it evaluates color, composition, creativity, and technical aspects. For music works, it evaluates melody, rhythm, creativity, and sound quality. For manga works, it evaluates story, character quality, art style, and creativity.

[0210] The emotion engine analyzes the user's emotions in real time during the evaluation and records changes in their emotions. This emotional information influences the evaluation results, and is an important factor, especially for subjective evaluation items such as creativity.

[0211] 4. Calculation and ranking of evaluation results

[0212] The server aggregates the evaluation results for each work. For example, for an image work, it aggregates the individual scores, such as "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Technique: 6 / 10," and calculates an overall evaluation score. Each work is ranked based on the calculated overall score. The user's emotional information may also be taken into account.

[0213] 5. Publication and notification of evaluation results

[0214] The server stores the evaluation results in a database and makes them available for users to view. Users can use a web interface or application to check the evaluation results from their own devices. Furthermore, the emotion engine optimizes the notification method based on the user's emotional state and sends notifications in a more appropriate format.

[0215] Specific examples

[0216] For example, consider the case where User A uploads an image titled "Spring Scenery." At the time of uploading, the emotion engine analyzes User A's current emotion (e.g., joy or excitement) and sends this as metadata to the server. The server confirms that the image is AI-generated and evaluates it according to an evaluation flow specifically for images. The evaluation results are "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Technique: 6 / 10," resulting in an overall evaluation score of "30 / 40." These evaluation results are ranked, and User A can check how "Spring Scenery" is ranked from his or her own device.

[0217] Furthermore, the notification method is optimized based on User A's emotional information, so that, for example, User A will receive a notification that is designed to avoid surprise when receiving the evaluation result. In this way, the system of the present invention accurately and fairly evaluates the AI-generated works uploaded by users and appropriately discloses the evaluation results to the users. By combining the emotion engine, it is possible to improve the user experience and provide a personalized evaluation process.

[0218] The processing flow will be explained below.

[0219] Step 1:

[0220] Users upload AI-generated artworks using their devices. They then select images, music, manga, etc. from a file selection screen via an application or web form. They also enter metadata such as the artwork's name, description, and category.

[0221] Step 2:

[0222] The device sends the uploaded content data and metadata to the server, typically via an HTTP request or API call.

[0223] Step 3:

[0224] The server receives the work data. After receiving it, the server checks the data size and file format (JPEG, PNG, MP3, WAV, etc.) to see if the format is within the allowed range, and generates an error message if the format is invalid.

[0225] Step 4:

[0226] The server stores the received artwork data and metadata in a database, along with additional information such as artwork ID, timestamp, and user information.

[0227] Step 5:

[0228] The server uses an emotion engine to analyze the user's emotions during and after uploading, and records the results as metadata. For example, the emotion engine analyzes the user's facial expressions and tone of voice to determine whether the user is currently "happy" or "nervous."

[0229] Step 6:

[0230] The server analyzes the artwork data and determines whether the artwork is AI-generated. It uses a deep learning model to analyze the artwork's characteristics and outputs a score indicating the likelihood of AI generation.

[0231] Step 7:

[0232] The server automatically classifies the work by format (image, music, manga, etc.), identifies which category the work belongs to, and assigns it to a dedicated evaluation flow.

[0233] Step 8:

[0234] The server executes a dedicated evaluation flow for each format. For example, for image works, it evaluates color balance using a color detection algorithm and composition using face detection technology. For music works, it evaluates melody, rhythm, creativity, and sound quality. For manga works, it evaluates story, character quality, art style, and creativity.

[0235] Step 9:

[0236] The server tally the generated evaluation scores and calculate an overall evaluation score. This is done by adding up or averaging the scores for each evaluation item. For example, for an image work, the evaluation scores for "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Technique: 6 / 10" are combined to calculate an overall evaluation score of "30 / 40."

[0237] Step 10:

[0238] The server compares the overall scores of all works and ranks them, which are recorded in a database in the form of a ranking, and each work is given a rank.

[0239] Step 11:

[0240] The server publishes the evaluation and ranking results to the user. A dedicated web interface or application screen is generated and made accessible to the user. The display of the evaluation result page can be customized based on the user's emotional data analyzed by the emotion engine.

[0241] Step 12:

[0242] Users can check the evaluation results on their own devices. Users can access the evaluation results page via the notification they receive and check how their work was evaluated and how it was ranked.

[0243] Step 13:

[0244] The server sends a notification of the evaluation result to the user. The emotion engine analyzes the user's psychological state and optimizes the notification method, for example, sending a gentle tone notification message if the user is feeling depressed. The notification is delivered to the user via email or in-app notification.

[0245] Example 2

[0246] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0247] When evaluating works generated by AI, it is difficult to obtain fair and accurate evaluations. Furthermore, the lack of personalized evaluations and notifications that take user emotions into account results in a poor user experience. Conventional systems are unable to provide comprehensive evaluations that include emotional information, and lack an appropriate feedback process that utilizes user emotion analysis. As a result, it remains difficult for users to receive evaluations that they are satisfied with.

[0248] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0249] In this invention, the server includes: a means for a user to submit an AI-generated work to a database; a means for the server to classify the submitted work based on its format; a means for the server to analyze the user's emotions using an emotion recognition engine and store the information as metadata; a means for the server to execute a dedicated evaluation flow for each format; a means for the server to compile and rank the evaluation results; and a means for publishing the evaluation results and rankings to the user. This enables personalized evaluations that reflect the user's emotions, providing fair and convincing evaluations. Furthermore, publishing the evaluation results and providing appropriate notification methods can improve the user experience.

[0250] "User" means a person or entity that uses the system to upload AI-generated works and receive evaluation results.

[0251] "Artificial intelligence-generated works" are creative works such as images, music, and comics that are generated using artificial intelligence.

[0252] "Means for sending to the database" refers to a function that allows a user to use their own terminal to send AI-generated works and related metadata to the server.

[0253] The "means for classifying based on format" is an algorithm that the server uses to classify the received works according to their format, such as images, music, comics, etc.

[0254] An "emotion recognition engine" is a software program that analyzes emotions from a user's facial expressions and voice and saves the results as metadata.

[0255] "Metadata" is additional information associated with an AI-generated work, such as the work's name, description, category, and analyzed emotional information.

[0256] The "means for executing the evaluation flow" is a process in which the server evaluates each classified work based on specific evaluation items (for example, color, composition, creativity, technique, etc.).

[0257] The "means for aggregating evaluation results and ranking" is a function that allows the server to aggregate the scores of each evaluation item, calculate a total evaluation score, and rank the works.

[0258] The "means for disclosing to users" refers to a web interface or application that displays the aggregated evaluation results and rankings so that users can check them.

[0259] The system of the present invention allows users to fairly and accurately evaluate works generated by artificial intelligence. The system combines an emotion recognition engine to provide a personalized experience.

[0260] As an example of the system, a program that operates based on the following procedure will be described.

[0261] 1. Upload your work

[0262] Users access the system's upload screen using their own device (e.g., a PC or smartphone). They select an AI-generated work, such as an image, music, or manga, and enter metadata such as the work's name, description, and category. When the user clicks the "Upload" button, the device sends this data to the server. At the same time, the device's camera and microphone are used to capture the user's facial expressions and voice, and an emotion recognition engine (e.g., Microsoft® Azure® Emotion API or IBM Watson® Tone Analyzer) analyzes the user's emotions. The results of this analysis are also sent to the server as metadata.

[0263] 2. Classification of works

[0264] The server receives the artwork data and metadata from the user. Then, using a deep learning model (for example, a model using TensorFlow or PyTorch), the server determines whether the artwork is AI-generated. Once this determination is complete, the server classifies the artwork by type (image, music, manga, etc.) and assigns it to a dedicated evaluation flow for each type.

[0265] 3. Dedicated evaluation flow

[0266] The server will rate each type of work based on the following criteria:

[0267] Image work: color, composition, creativity, technique

[0268] Musical composition: melody, rhythm, creativity, sound quality

[0269] Manga works: Story, character quality, art style, creativity

[0270] For example, the server evaluates the color and composition of the image using color analysis algorithms (e.g., OpenCV), and the creativity and technique are evaluated using pre-trained generative AI models, while the emotion recognition engine continuously acquires real-time emotional data from the user and incorporates this information into the evaluation.

[0271] 4. Calculation and ranking of evaluation results

[0272] The server aggregates the evaluation results for each work. For example, an image may receive scores of "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Technique: 6 / 10." The server then calculates an overall evaluation score of "30 / 40" based on these scores. Based on this, the server ranks all works. The server also takes into account the user's emotional data to adjust the extent to which emotional bias affects the evaluation score.

[0273] 5. Publication and notification of evaluation results

[0274] The server stores the final evaluation results in a database and makes them available through a viewable web interface or application. Users can access and check the evaluation results from their own devices. The server also determines the optimal notification method based on the analysis results of the emotion recognition engine. For example, if the evaluation result is unexpectedly low, the server will send a notification in a way that will not surprise the user.

[0275] Examples and prompts

[0276] For example, suppose User A uploads an image titled "Spring Landscape." At the time of upload, the emotion recognition engine analyzes User A's current emotion (e.g., joy or excitement) and sends the results to the server as metadata. The server then confirms that the image was generated by artificial intelligence and then evaluates it according to an evaluation flow dedicated to images. The evaluation results are "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Technique: 6 / 10," resulting in an overall evaluation score of "30 / 40." These evaluation results are ranked, and User A can check the rank of "Spring Landscape" on his or her own device. In addition, the notification method is optimized based on User A's emotional information, so that, for example, User A is not surprised when he or she receives the evaluation results.

[0277] Prompt Sentence Examples

[0278] 1. "What was the sentiment analysis result when I uploaded an AI-generated image of a spring landscape?"

[0279] 2. Please rate the uploaded image and calculate the overall score.

[0280] 3. "Please explain the optimized notification method based on the evaluation results and user sentiment."

[0281] In this way, the system of the present invention accurately and fairly evaluates AI-generated works uploaded by users and appropriately discloses the evaluation results to users. By combining it with an emotion recognition engine, it is possible to improve the user experience and provide a personalized evaluation process.

[0282] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0283] Step 1:

[0284] Users access the system's upload screen using their own devices, select an AI-generated work such as an image, music, or manga, and enter metadata such as the work's name, description, and category.

[0285] Input: User-selected artwork file, artwork name, description, category, and other metadata

[0286] Output: A data packet containing the input work file and metadata.

[0287] Specific operation: When the user clicks the "Upload" button, the device sends this data to the server. At the same time, the device's camera and microphone are used to capture the user's facial expressions and voice, and the emotion recognition engine analyzes the user's emotions in real time. The analysis results are also sent to the server as metadata.

[0288] Step 2:

[0289] The server receives the work data and metadata received from the user and then uses a deep learning model to determine whether the work is artificial intelligence-generated.

[0290] Input: Submitted work data and metadata

[0291] Output: Work judgment and classification results

[0292] How it works: The server uses a deep learning framework (such as TensorFlow or PyTorch) to check whether the submitted work is AI-generated, then categorizes it by format (e.g., image, music, comics, etc.) and stores it in a directory for each format.

[0293] Step 3:

[0294] The server executes a dedicated evaluation flow for the classified works.

[0295] Input: Classified artwork data

[0296] Output: Score for each evaluation item

[0297] Specific operation: Evaluation is performed for each category using color analysis algorithms (e.g., OpenCV), audio analysis algorithms, story analysis algorithms, etc. Scores are calculated for evaluation items such as color, composition, creativity, and technique. In addition, an emotion recognition engine analyzes the user's real-time emotions during the evaluation, and this emotional information is also reflected in the evaluation.

[0298] Step 4:

[0299] The server compiles the evaluation results for each work and ranks them.

[0300] Input: Scores for each evaluation item, user's emotional information

[0301] Output: Overall evaluation score and ranking results

[0302] Specific operation: The server stores the scores for each evaluation item in a database and calculates an overall evaluation score by aggregating the scores. Each work is ranked based on this overall evaluation score. The server also takes into account the user's emotional information, adjusting the evaluation to avoid bias, especially in subjective evaluation items such as creativity.

[0303] Step 5:

[0304] The server stores the evaluation results in a database, makes them available to users, and notifies them.

[0305] Input: Overall evaluation score and ranking results

[0306] Output: Publishing the evaluation results and rankings, and notifying the user

[0307] Specific operation: The server publishes the evaluation results through a web interface or application. Users can check the evaluation results on their own devices. In addition, the notification method is optimized based on the analysis results of the emotion recognition engine. For example, if the evaluation result is unexpectedly low, a notification message will be sent to avoid surprise.

[0308] In this way, the system of the present invention can accurately and fairly evaluate AI-generated works uploaded by users and appropriately disclose the evaluation results to users. By combining it with an emotion recognition engine, it is possible to improve the user experience and provide a personalized evaluation process.

[0309] (Application example 2)

[0310] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0311] Conventional AI-generated artwork evaluation systems have struggled to provide fair evaluations and a personalized experience. Furthermore, they have been unable to effectively utilize user emotional data, resulting in incomplete subjective evaluations of creative works. The present invention aims to provide a system that improves the user experience by analyzing user emotions and incorporating that data into the evaluation process.

[0312] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a means for a user to upload AI-generated works, a means for the server to classify the uploaded works based on their format, a means for the server to execute a dedicated evaluation flow for each format, a means for acquiring and analyzing user emotional data during the evaluation, a means for complementing the evaluation score based on the acquired emotional data, a means for the server to aggregate and rank the evaluation results, and a means for disclosing the evaluation results and rankings to the user. By reflecting user emotional information in the evaluation process, this enables subjective evaluation of advertising creatives and the like to be performed in a more accurate and personalized manner.

[0313] "User" refers to the individual or entity that uploads and evaluates AI-generated works.

[0314] "AI-generated works" refers to content such as images, music, videos, and comics generated by artificial intelligence or machine learning models.

[0315] "Uploading" refers to the act of sending digital data from a user's device to a server.

[0316] "Server" refers to a computer system that stores, processes, and delivers data.

[0317] "Format" refers to the type or category of work uploaded (e.g., image, music, video, etc.).

[0318] "Evaluation flow" refers to the series of evaluation steps or processes that are carried out on uploaded works.

[0319] "Emotional data" refers to data that measures a user's emotional state (e.g., joy, excitement, surprise, etc.) and expresses it as a numerical value or text.

[0320] "Analysis" is the process of examining collected data and extracting specific information.

[0321] An "evaluation score" is a numerical indicator of the quality of a work, calculated based on multiple evaluation criteria.

[0322] "Aggregation" refers to the act of compiling multiple evaluation results and calculating statistical values ​​such as totals and averages.

[0323] "Ranking" refers to arranging works in order of merit based on their evaluation scores.

[0324] "Publication" refers to the act of providing evaluation results and rankings in a form that is accessible to users.

[0325] "Personalization" refers to optimizing experiences and information based on the individual characteristics and preferences of each user.

[0326] This invention is a system that uses emotional data to provide a more personalized experience when users rate AI-generated works. The system consists of a user terminal, an emotion analysis engine, a server, a rating flow, and a publishing means.

[0327] Hardware and Software Configuration

[0328] 1. On the user's device:

[0329] This includes devices such as smartphones and smart glasses, which allow users to upload AI-generated creations and view evaluation results.

[0330] 2. Sentiment Analysis Engine:

[0331] This software is used for emotion analysis, such as Affectiva and Microsoft Azure Face API, and collects emotion data when users upload and rate.

[0332] 3. Server:

[0333] This is a computer system that manages the evaluation process, stores and processes data, classifies works to be evaluated, generates scores based on each evaluation item, tallying and ranking the results, and publishes the final results.

[0334] Data processing and calculation methods

[0335] 1. Upload:

[0336] AI-generated works (images, videos, music, etc.) are uploaded from the user's device to the server. Metadata includes the work's name, description, and emotional data.

[0337] 2. Classification:

[0338] The server automatically classifies the uploaded works and assigns them to the appropriate evaluation flow depending on their format (images, videos, music, etc.).

[0339] 3. Emotion analysis:

[0340] When users upload their work or receive ratings, a sentiment analysis engine is used to collect real-time emotional data, which directly influences the rating process and is particularly used to complement subjective rating items.

[0341] 4. Evaluation and Scoring:

[0342] The server evaluates each work in each format based on technical criteria (e.g., color, composition, technical ability) and subjective criteria (e.g., creativity, engagement). It also performs a supplementary evaluation based on emotional data, and calculates an overall score by combining the scores for each evaluation item.

[0343] 5. Counting and ranking:

[0344] The evaluation results are compiled and ranked, which determines the ranking of the work compared to other works.

[0345] 6. Publication of evaluation results:

[0346] The final evaluation results are published in an optimal format based on the user's emotional data. Users can view the evaluation results on their own devices, and the notification method is also adjusted based on the emotional data.

[0347] Examples and prompts

[0348] For example, when an ad creator uploads an advertising video for a new fashion brand, the video is classified and evaluated on the server. Emotional data is collected using a smartphone or smart glasses camera while the video is being viewed, and an engagement score and overall evaluation score are calculated based on that data. The ad creator who uploaded the video can check the evaluation results and find out which parts of the ad particularly engaged users.

[0349] Example prompt sentence:

[0350] "Please watch an advertisement video for a new fashion brand and calculate an engagement score based on the user's sentiment analysis data while watching. Store the results in a rating database and return an overall score."

[0351] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0352] Step 1:

[0353] A user uploads an AI-generated work to the system using a terminal. The input is the work file and its metadata (work name, description, emotional data), and the output is the uploaded data sent to the server. This data includes the file itself as well as the metadata entered by the user.

[0354] Step 2:

[0355] The server receives the uploaded work data. The input is the uploaded data sent from the user's device, the server saves the work file and analyzes the metadata. The output is the work's storage and metadata classification information.

[0356] Step 3:

[0357] The server classifies uploaded works based on their format. The input is the work file and its metadata, and the output is the work's category information (e.g., image, video, music). The server determines that the work is AI-generated and assigns it to a dedicated evaluation flow based on its format.

[0358] Step 4:

[0359] When a user uploads a work, the emotion analysis engine acquires and analyzes the user's emotional data. The input is the user's emotional data (real-time facial expression data and voice data), and the output is the emotion analysis result (e.g., joy, excitement, surprise). This value is sent to the server as metadata.

[0360] Step 5:

[0361] The server executes a dedicated evaluation flow for each type of work. The input is the work file and metadata (including emotional data), and the output is a score for each evaluation item (technical and subjective). The server uses a deep learning model to perform technical evaluations (e.g., color, composition) and complements subjective evaluations (e.g., creativity, engagement) with emotional data.

[0362] Step 6:

[0363] The server aggregates the evaluation results and ranks them. The input is the score for each evaluation item, and the output is the overall evaluation score and ranking information. The server statistically aggregates the evaluation results and generates a ranking.

[0364] Step 7:

[0365] The server publishes the evaluation results and rankings to users. The input is the overall evaluation score and ranking information, and the output is the evaluation results published in a form that users can access. Furthermore, the notification method is optimized based on the emotion engine, and users can check the evaluation results on their own devices.

[0366] Step 8:

[0367] Users can check the published evaluation results on their devices and receive feedback. The input is the evaluation results sent from the server, and the output is a visualization of the evaluation content and feedback information. For example, users can see which evaluation items they received high scores for and what kind of feedback they received based on emotional data.

[0368] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0369] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0370] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0371] [Second embodiment]

[0372] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0373] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0374] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0375] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0376] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0377] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0378] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0379] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0380] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0381] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0382] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0383] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0384] The system of this invention allows users to fairly evaluate AI-generated works. The system begins with the user uploading the work, and then the server classifies the work, executes the appropriate evaluation flow, and compiles and publishes the results.

[0385] 1. Upload your work

[0386] Users use their devices to upload AI-generated images, music, comics, and other works to the system. On the upload screen, users enter metadata such as the work's name, description, and category. The device then sends the uploaded data to the server.

[0387] 2. Classification of works

[0388] The server receives the uploaded work and verifies that it is AI-generated. This verification is done using a deep learning model. This model analyzes the characteristics of the work and determines the likelihood that it was generated by AI. This prevents non-AI-generated works from proceeding to the next step.

[0389] Works that are confirmed to be AI-generated are classified into their format (images, music, manga, etc.) and assigned to the appropriate evaluation flow.

[0390] 3. Dedicated evaluation flow

[0391] The server then applies the appropriate evaluation flow to the classified works. For images, it evaluates color, composition, creativity, and technical aspects. For music, it evaluates melody, rhythm, creativity, and sound quality. For manga, it evaluates story, character quality, art style, and creativity.

[0392] For example, when an image is uploaded, the server uses a color detection algorithm to evaluate color balance and facial detection technology to evaluate composition, generating a separate score based on each evaluation factor.

[0393] 4. Calculation and ranking of evaluation results

[0394] The server aggregates the evaluation results for each work. For example, for an image work, it aggregates each score such as "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Technique: 6 / 10," and calculates an overall evaluation score. Each work is ranked based on the calculated overall score.

[0395] 5. Publication of evaluation results

[0396] The aggregated evaluation results are stored in a database, and the server makes these results available for users to view. Users can check the evaluation results from their own devices using a web interface or application.

[0397] As a concrete example, consider the case where User A uploads an image titled "Spring Scenery." The server confirms that this image is AI-generated and evaluates it according to an evaluation flow specifically for images. The evaluation results are "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Technology: 6 / 10," resulting in an overall evaluation score of "30 / 40." These evaluation results are ranked, and User A can check from his or her device how "Spring Scenery" is ranked.

[0398] In this way, the system of the present invention accurately and fairly evaluates AI-generated works uploaded by users and appropriately discloses the evaluation results to users, thereby improving the quality of AI-generated works and ensuring transparency and fairness in the evaluation process.

[0399] The processing flow will be explained below.

[0400] Step 1:

[0401] Users upload AI-generated artworks using their devices. They select artworks such as images, music, and manga from a file selection screen via a web form or dedicated application. They also enter metadata such as the artwork's name, description, and category.

[0402] Step 2:

[0403] The device sends the entered work data and metadata to the server via HTTP requests or API calls.

[0404] Step 3:

[0405] The server receives the work data. After receiving it, the server checks the data size and file format, checking whether it is in a standard format, such as JPG or PNG for images, or MP3 or WAV for music.

[0406] Step 4:

[0407] The server records the received work data and metadata in a database, along with additional information such as the work ID and timestamp.

[0408] Step 5:

[0409] The server analyzes the stored artwork data and uses a deep learning model to determine whether the artwork is AI-generated. The model analyzes the artwork's characteristics and outputs a score indicating the likelihood of AI generation.

[0410] Step 6:

[0411] The server automatically classifies the work by format, such as image, music, or manga, and then assigns it to the corresponding evaluation flow based on the classification results.

[0412] Step 7:

[0413] The server executes the evaluation flow for each method. For example, in the case of an image, it evaluates color balance using a color detection algorithm and composition using face detection technology. A score is generated based on each evaluation item.

[0414] Step 8:

[0415] The server aggregates the scores for each evaluation item and calculates an overall evaluation score. The final score is calculated by summing or averaging the scores for each evaluation item.

[0416] Step 9:

[0417] The server compares the overall scores of all works and ranks them. The ranking results are updated in the database, and each work is given a rank.

[0418] Step 10:

[0419] The server publishes the evaluation results and rankings to users by generating a web page for publication, and users can view the evaluation results by accessing that page.

[0420] Step 11:

[0421] The server will notify the user of the evaluation results via email or the app's notification function.

[0422] Step 12:

[0423] Users can check the evaluation results on their own devices. Users will receive a notification and can access the detailed evaluation result page via a specified link or in-app menu to check the evaluation content and ranking.

[0424] Example 1

[0425] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0426] In recent years, advances in generative AI technology have led to an increase in the number of AI-generated works in a variety of formats. However, due to the lack of a standard system for fairly and objectively evaluating these works, quality evaluations and rankings of works often lack transparency and fairness. As a result, it is difficult for users to accurately grasp the quality of their own works. In addition, the lack of consistency in the evaluation process makes it difficult to compare works of different formats.

[0427] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0428] In this invention, the server includes: a means for users to upload AI-generated works; a means for a terminal to send metadata of the uploaded works to the server; a means for the server to verify that the uploaded works are AI-generated using a deep learning model; a means for the server to classify the works based on their format; a means for the server to execute a dedicated evaluation flow for each format; a means for the server to generate scores based on evaluation criteria such as color, composition, creativity, and technical aspects; a means for the server to aggregate and rank the evaluation results; and a means for the server to disclose the evaluation results and rankings to users. This enables transparent and consistent evaluation of AI-generated works, allowing users to accurately determine the merits of their own works. Furthermore, fair ranking based on the scores generated during the evaluation process makes it easier to compare works of different formats.

[0429] "User" means an individual or entity that accesses the System and uploads AI-generated Works.

[0430] A "terminal" is a device (computer, smartphone, tablet, etc.) that a user uses to input a work and send metadata to a server.

[0431] A "server" is a computer system that receives, categorizes, evaluates, and aggregates uploaded works, and then makes the evaluation results available to users.

[0432] "AI-generated works" are images, music, comics, and other creative works that are automatically or semi-automatically generated using artificial intelligence technology.

[0433] "Metadata" is additional information related to a work, such as the work's name, description, and category.

[0434] A "deep learning model" is an algorithm or network based on deep learning, a technology used to analyze and recognize AI-generated works.

[0435] "Classification" is the process of dividing uploaded works into categories based on their format (e.g., images, music, comics, etc.).

[0436] An "evaluation flow" is a series of procedures or algorithms that evaluate the quality and characteristics of a work based on evaluation criteria defined for each format.

[0437] A "score" is a score or evaluation value for a specific evaluation item that is generated through an evaluation flow.

[0438] The "color detection algorithm" is an algorithm for analyzing and evaluating the color balance and color placement of a work.

[0439] "Face detection technology" is a technology for identifying the position and number of faces in an image.

[0440] "Tallying" is the process of adding up the scores for each evaluation item to calculate an overall evaluation score.

[0441] "Ranking" is the process of determining the relative order of works based on their overall evaluation scores.

[0442] "Public" means to display and provide evaluation results and ranking information so that users can view them.

[0443] The system of this invention allows users to fairly evaluate AI-generated works. The system begins with the user uploading the work, and then the server classifies the work, executes the appropriate evaluation flow, and compiles and publishes the evaluation results.

[0444] First, a user uses a device to upload AI-generated images, music, manga, or other works to the system. Specifically, the user enters metadata such as the "work name," "work description," and "work category" on the upload screen, and the device then sends the work file along with this data to the server.

[0445] The server receives the uploaded data, analyzes the raw artwork file and metadata, and uses a deep learning model to confirm whether the artwork is AI-generated. Typical deep learning models are TensorFlow or PyTorch. This model analyzes the artwork's feature vector and calculates the probability of AI generation. Based on this result, the server will not proceed to the next step if the artwork is determined not to be AI-generated, and will notify the user.

[0446] The server categorizes works confirmed to be AI-generated based on their format, such as images, music, or comics. A dedicated evaluation process is applied to each classified work. For images, the server evaluates color balance using a color detection algorithm (e.g., OpenCV) and composition using face detection technology. It also evaluates creativity and technical aspects using machine learning models.

[0447] The server then calculates an overall score by adding up the scores generated for each evaluation item. For example, for an image work, the server would add up scores such as "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Technique: 6 / 10" to give an overall score of "30 / 40."

[0448] Finally, the server ranks the works based on these evaluation results and stores the information in a database. The evaluation results and rankings are made publicly accessible to users. Specifically, when a user accesses the system using a terminal and clicks the "View Evaluation Results" button, a screen will appear displaying the aggregated scores and ranks.

[0449] As a concrete example, consider the case where User A uploads an image titled "Spring Landscape." The server confirms that the image is AI-generated and performs color detection, face detection, and creativity and technical evaluation according to an evaluation flow specifically for images. The evaluation results are "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Technology: 6 / 10," resulting in an overall evaluation score of "30 / 40." The rankings are updated based on these scores, and User A can check from his or her device where "Spring Landscape" ranks.

[0450] As described above, the system of the present invention can accurately and fairly evaluate AI-generated works uploaded by users and quickly make the evaluation results available to users, thereby improving the quality of AI-generated works and ensuring transparency and fairness in the evaluation process.

[0451] Example prompt sentence:

[0452] "Run this image evaluation flow to generate and rank scores based on color, composition, creativity, and technique."

[0453] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0454] Step 1:

[0455] The user uses the device to access the upload screen. On the upload screen, they enter metadata such as the "work name," "work description," and "work category." After completing the entry, the user selects the work file and clicks the upload button. This sends the work file and metadata from the device to the server.

[0456] Input: User-entered work name, work description, work category, work file

[0457] Output: Upload data sent to the server

[0458] Step 2:

[0459] The server receives the uploaded data sent by the user. The server first checks the integrity of the data and analyzes the received metadata and the format of the work file. Next, it uses a deep learning model (e.g., TensorFlow or PyTorch) to confirm whether the work is AI-generated. Works that are confirmed to be AI-generated proceed to the next step.

[0460] Input: Upload data sent by the user

[0461] Output: AI generation confirmation result (True / False), work format classification

[0462] Step 3:

[0463] The server classifies works that are confirmed to be AI-generated based on their format (images, music, manga, etc.) using pre-defined rules and algorithms. Works of each type are then assigned to their own evaluation flow.

[0464] Input: AI generation confirmation result, work format

[0465] Output: Classification results (images, music, manga, etc.)

[0466] Step 4:

[0467] The server applies a dedicated evaluation flow to each classified work. For example, for image works, it evaluates color balance using a color detection algorithm (using OpenCV) and composition using face detection technology. Other creative and technical aspects are also analyzed and evaluated using machine learning models.

[0468] Input: Classified works

[0469] Output: Score for each evaluation item (color, composition, creativity, technique, etc.)

[0470] Step 5:

[0471] The server aggregates the scores generated for each evaluation category. For example, for an image, the scores might be "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Technique: 6 / 10." These scores are then added together to calculate an overall evaluation score.

[0472] Input: Score for each evaluation item

[0473] Output: Overall evaluation score

[0474] Step 6:

[0475] The server automatically ranks the works based on the total score, and the ranking information is stored in a database.

[0476] Input: Overall evaluation score

[0477] Output: Ranked work information

[0478] Step 7:

[0479] The server stores the evaluation results and rankings in a database and makes them available for viewing by users. Users can access the system using their devices and click the "View Evaluation Results" button to check the evaluation results and rankings of their own works.

[0480] Input: Saved evaluation results and ranking information

[0481] Output: Evaluation results and ranking information displayed on the user screen

[0482] (Application example 1)

[0483] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0484] Food delivery services are required to improve the efficiency of new menu development and promotional activities by fairly evaluating and ranking the quality and appeal of AI-generated food images and menus. In current systems, such evaluations are often done manually, which lacks fairness and transparency. Furthermore, there is a possibility that images that are not AI-generated may be mixed in, making it difficult to ensure reliability.

[0485] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0486] In this invention, the server includes a means for users to upload AI-generated creations, a means for the server to classify the uploaded creations based on their format, and a means for the server to execute a dedicated evaluation flow for each format, thereby enabling a food delivery service to fairly and efficiently evaluate the color, composition, creativity, and delicious appearance of AI-generated food images and menus, and to aggregate and rank the evaluation results.

[0487] "User" means an individual or legal entity that uses the system to upload AI-generated works.

[0488] A "server" is a computer device that receives uploaded works, categorizes them, executes an evaluation flow, and aggregates and ranks the evaluation results.

[0489] "Works" are creative works such as AI-generated images, music, and comics uploaded by users.

[0490] "Classification" is the process by which the server identifies works received based on their format and places them into appropriate categories.

[0491] The "evaluation flow" is a series of evaluation processes that the server carries out on classified works, with different evaluation items set for each format.

[0492] "Evaluation results" refer to the aggregated scores for each evaluation item generated by the evaluation flow.

[0493] "Ranking" refers to ranking works based on the evaluation results.

[0494] "Food delivery service" refers to a service business that delivers food to customers who order it.

[0495] "Food images" are images of the appearance of food provided by food delivery services, and are important for stimulating the user's appetite.

[0496] A "menu" is a list of food and drinks offered by a food delivery service, showing the items that a customer can choose from.

[0497] "Color" is an item that evaluates the arrangement and balance of colors in a work.

[0498] "Composition" is an item that evaluates how the elements of a work are arranged.

[0499] "Creativity" is an item that evaluates how original and innovative a work is.

[0500] "Appetizing appearance" is an item that evaluates how visually appetizing a food image is.

[0501] This invention is a system for impartially evaluating AI-generated food images and menus for food delivery services. This system involves the steps of a user uploading AI-generated food images and menus, a server classifying, evaluating, and ranking the images, and publishing the results.

[0502] System Configuration

[0503] The system mainly consists of a user device, a server, and software that runs the evaluation flow. User devices are smartphones or PCs, while the server is a high-performance computer. The software used is a deep learning framework such as TensorFlow or a web framework such as Flask.

[0504] Processing steps

[0505] 1. Upload an image

[0506] Users upload AI-generated food images and menus to the system from their own devices, along with metadata such as the dish name, description, and category (e.g., appetizer, main dish, dessert, etc.).

[0507] 2. AI-generated judgment

[0508] The server uses a deep learning model (for example, a model built with TensorFlow) to determine whether the uploaded image is AI-generated. Only images that are recognized as AI-generated are allowed to proceed to the next step.

[0509] 3. Image Classification

[0510] Images that are confirmed to be AI-generated are then sorted into categories according to their format, which is based on the type of food (appetizer, main dish, dessert, etc.).

[0511] 4. Execute the evaluation flow

[0512] The server then runs an evaluation flow on the classified images, using algorithms to evaluate criteria such as color, composition, creativity, and appetizing appearance.

[0513] 5. Calculation and ranking of evaluation results

[0514] A score is generated for each item, and these scores are then aggregated to calculate an overall score. Based on the overall score, food images and menus are ranked.

[0515] 6. Publication of evaluation results

[0516] The evaluation results are stored on a server in a form that can be viewed by food delivery service administrators and users, and are made public through a web interface or application.

[0517] Specific examples

[0518] For example, consider a new menu item, "Spring Salad," generated using AI. A user uploads this image to the system as "Spring Salad." The server uses a TensorFlow model to verify that the image is AI-generated, and then evaluates it based on factors such as color balance, composition, creativity, and appetizing appearance. Finally, the server assigns ratings such as "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Appetizing: 9 / 10," resulting in an overall score of "33 / 40." These scores are reflected in the rankings, allowing administrators and users to see which menu items received the highest ratings.

[0519] Prompt Sentence Examples

[0520] "We used AI to generate food images for a new food delivery menu. Please rate these images on color, composition, creativity, and whether they look delicious."

[0521] This system will enable food delivery services to fairly and efficiently evaluate the appeal of new menu items, helping them with promotional activities and menu development.

[0522] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0523] Step 1:

[0524] Users upload AI-generated food images and menus to the system from their own devices. On the upload screen, users also enter metadata such as the dish name, description, and category (e.g., appetizer, main dish, dessert, etc.). The entered data and images are sent to the server.

[0525] Step 2:

[0526] The server uses a deep learning model (TensorFlow model) to determine whether an uploaded image is AI-generated. Specifically, the server inputs the image into the model and outputs a probability of whether it is AI-generated. If the result exceeds a threshold, the image is recognized as AI-generated. The input data is the image and its metadata, and the output data is the result of the AI-generated determination.

[0527] Step 3:

[0528] The server classifies images that are certified as AI-generated based on their format (category). Specifically, they are sorted according to food category (appetizer, main dish, dessert, etc.). The input data is the image and metadata, and the output data is the classification result, which is category information.

[0529] Step 4:

[0530] The server then runs an evaluation flow on the classified images, using algorithms to evaluate color, composition, creativity, and delicious appearance. The evaluation process analyzes color balance, evaluates the placement of elements, judges creativity, and evaluates how appetizing the food looks. The input data is the classified image, and the output data is the score for each evaluation item.

[0531] Step 5:

[0532] The server aggregates the scores for each evaluation item and calculates an overall score. For example, adding up evaluation scores such as "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Appetizing: 9 / 10," the overall score is "33 / 40." The input data is the score for each evaluation item, and the output data is the overall score.

[0533] Step 6:

[0534] The server ranks each food image and menu item based on the evaluation results (total score). Specifically, it lists all evaluation results and sorts them in ascending or descending order based on the score. The input data is the total score, and the output data is the ranked list.

[0535] Step 7:

[0536] The server publishes the evaluation results and rankings in a form that can be viewed by food delivery service administrators and users. Specifically, it makes them accessible through a web interface or application. Administrators and users can check the evaluation results from their own devices and use them to develop new menu items and promote their activities. The input data is a ranked list, and the output data is the evaluation results that can be viewed by users.

[0537] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0538] The system of this invention allows users to fairly evaluate AI-generated works, and by combining it with an emotion engine that recognizes the user's emotions, it provides a more personalized experience. The system flow is as follows:

[0539] 1. Upload your work

[0540] Users use their devices to upload AI-generated works such as images, music, and comics to the system. On the upload screen, users enter metadata such as the work's name, description, and category. When uploading, the emotion engine analyzes the user's emotions and sends the analysis results to the server as metadata. For example, emotional information such as whether the user is excited or happy is included in the metadata.

[0541] 2. Classification of works

[0542] The server receives the uploaded work and uses a deep learning model to determine whether the work is AI-generated. Once confirmed, the work is classified into its format and sent through a dedicated evaluation flow.

[0543] 3. Dedicated evaluation flow

[0544] The server then applies an appropriate evaluation process to each classified work. For example, for image works, it evaluates color, composition, creativity, and technical aspects. For music works, it evaluates melody, rhythm, creativity, and sound quality. For manga works, it evaluates story, character quality, art style, and creativity.

[0545] The emotion engine analyzes the user's emotions in real time during the evaluation and records changes in their emotions. This emotional information influences the evaluation results, and is an important factor, especially for subjective evaluation items such as creativity.

[0546] 4. Calculation and ranking of evaluation results

[0547] The server aggregates the evaluation results for each work. For example, for an image work, it aggregates the individual scores, such as "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Technique: 6 / 10," and calculates an overall evaluation score. Each work is ranked based on the calculated overall score. The user's emotional information may also be taken into account.

[0548] 5. Publication and notification of evaluation results

[0549] The server stores the evaluation results in a database and makes them available for users to view. Users can use a web interface or application to check the evaluation results from their own devices. Furthermore, the emotion engine optimizes the notification method based on the user's emotional state and sends notifications in a more appropriate format.

[0550] Specific examples

[0551] For example, consider the case where User A uploads an image titled "Spring Scenery." At the time of uploading, the emotion engine analyzes User A's current emotion (e.g., joy or excitement) and sends this as metadata to the server. The server confirms that the image is AI-generated and evaluates it according to an evaluation flow specifically for images. The evaluation results are "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Technique: 6 / 10," resulting in an overall evaluation score of "30 / 40." These evaluation results are ranked, and User A can check how "Spring Scenery" is ranked from his or her own device.

[0552] Furthermore, the notification method is optimized based on User A's emotional information, so that, for example, User A will receive a notification that is designed to avoid surprise when receiving the evaluation result. In this way, the system of the present invention accurately and fairly evaluates the AI-generated works uploaded by users and appropriately discloses the evaluation results to the users. By combining the emotion engine, it is possible to improve the user experience and provide a personalized evaluation process.

[0553] The processing flow will be explained below.

[0554] Step 1:

[0555] Users upload AI-generated artworks using their devices. They then select images, music, manga, etc. from a file selection screen via an application or web form. They also enter metadata such as the artwork's name, description, and category.

[0556] Step 2:

[0557] The device sends the uploaded content data and metadata to the server, typically via an HTTP request or API call.

[0558] Step 3:

[0559] The server receives the work data. After receiving it, the server checks the data size and file format (JPEG, PNG, MP3, WAV, etc.) to see if the format is within the allowed range, and generates an error message if the format is invalid.

[0560] Step 4:

[0561] The server stores the received artwork data and metadata in a database, along with additional information such as artwork ID, timestamp, and user information.

[0562] Step 5:

[0563] The server uses an emotion engine to analyze the user's emotions during and after uploading, and records the results as metadata. For example, the emotion engine analyzes the user's facial expressions and tone of voice to determine whether the user is currently "happy" or "nervous."

[0564] Step 6:

[0565] The server analyzes the artwork data and determines whether the artwork is AI-generated. It uses a deep learning model to analyze the artwork's characteristics and outputs a score indicating the likelihood of AI generation.

[0566] Step 7:

[0567] The server automatically classifies the work by format (image, music, manga, etc.), identifies which category the work belongs to, and assigns it to a dedicated evaluation flow.

[0568] Step 8:

[0569] The server executes a dedicated evaluation flow for each format. For example, for image works, it evaluates color balance using a color detection algorithm and composition using face detection technology. For music works, it evaluates melody, rhythm, creativity, and sound quality. For manga works, it evaluates story, character quality, art style, and creativity.

[0570] Step 9:

[0571] The server tally the generated evaluation scores and calculate an overall evaluation score. This is done by adding up or averaging the scores for each evaluation item. For example, for an image work, the evaluation scores for "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Technique: 6 / 10" are combined to calculate an overall evaluation score of "30 / 40."

[0572] Step 10:

[0573] The server compares the overall scores of all works and ranks them, which are recorded in a database in the form of a ranking, and each work is given a rank.

[0574] Step 11:

[0575] The server publishes the evaluation and ranking results to the user. A dedicated web interface or application screen is generated and made accessible to the user. The display of the evaluation result page can be customized based on the user's emotional data analyzed by the emotion engine.

[0576] Step 12:

[0577] Users can check the evaluation results on their own devices. Users can access the evaluation results page via the notification they receive and check how their work was evaluated and how it was ranked.

[0578] Step 13:

[0579] The server sends a notification of the evaluation result to the user. The emotion engine analyzes the user's psychological state and optimizes the notification method, for example, sending a gentle tone notification message if the user is feeling depressed. The notification is delivered to the user via email or in-app notification.

[0580] Example 2

[0581] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0582] When evaluating works generated by AI, it is difficult to obtain fair and accurate evaluations. Furthermore, the lack of personalized evaluations and notifications that take user emotions into account results in a poor user experience. Conventional systems are unable to provide comprehensive evaluations that include emotional information, and lack an appropriate feedback process that utilizes user emotion analysis. As a result, it remains difficult for users to receive evaluations that they are satisfied with.

[0583] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0584] In this invention, the server includes: a means for a user to submit an AI-generated work to a database; a means for the server to classify the submitted work based on its format; a means for the server to analyze the user's emotions using an emotion recognition engine and store the information as metadata; a means for the server to execute a dedicated evaluation flow for each format; a means for the server to compile and rank the evaluation results; and a means for publishing the evaluation results and rankings to the user. This enables personalized evaluations that reflect the user's emotions, providing fair and convincing evaluations. Furthermore, publishing the evaluation results and providing appropriate notification methods can improve the user experience.

[0585] "User" means a person or entity that uses the system to upload AI-generated works and receive evaluation results.

[0586] "Artificial intelligence-generated works" are creative works such as images, music, and comics that are generated using artificial intelligence.

[0587] "Means for sending to the database" refers to a function that allows a user to use their own terminal to send AI-generated works and related metadata to the server.

[0588] The "means for classifying based on format" is an algorithm that the server uses to classify the received works according to their format, such as images, music, comics, etc.

[0589] An "emotion recognition engine" is a software program that analyzes emotions from a user's facial expressions and voice and saves the results as metadata.

[0590] "Metadata" is additional information associated with an AI-generated work, such as the work's name, description, category, and analyzed emotional information.

[0591] The "means for executing the evaluation flow" is a process in which the server evaluates each classified work based on specific evaluation items (for example, color, composition, creativity, technique, etc.).

[0592] The "means for aggregating evaluation results and ranking" is a function that allows the server to aggregate the scores of each evaluation item, calculate a total evaluation score, and rank the works.

[0593] The "means for disclosing to users" refers to a web interface or application that displays the aggregated evaluation results and rankings so that users can check them.

[0594] The system of the present invention allows users to fairly and accurately evaluate works generated by artificial intelligence. The system combines an emotion recognition engine to provide a personalized experience.

[0595] As an example of the system, a program that operates based on the following procedure will be described.

[0596] 1. Upload your work

[0597] Users access the system's upload screen using their own device (e.g., a PC or smartphone). They select an AI-generated work, such as an image, music, or manga, and enter metadata such as the work's name, description, and category. When the user clicks the "Upload" button, the device sends this data to the server. At the same time, the device's camera and microphone are used to capture the user's facial expressions and voice, and an emotion recognition engine (e.g., Microsoft Azure Emotion API or IBM Watson Tone Analyzer) analyzes the user's emotions. The results of this analysis are also sent to the server as metadata.

[0598] 2. Classification of works

[0599] The server receives the artwork data and metadata from the user. Then, using a deep learning model (for example, a model using TensorFlow or PyTorch), the server determines whether the artwork is AI-generated. Once this determination is complete, the server classifies the artwork by type (image, music, manga, etc.) and assigns it to a dedicated evaluation flow for each type.

[0600] 3. Dedicated evaluation flow

[0601] The server will rate each type of work based on the following criteria:

[0602] Image work: color, composition, creativity, technique

[0603] Musical composition: melody, rhythm, creativity, sound quality

[0604] Manga works: Story, character quality, art style, creativity

[0605] For example, the server evaluates the color and composition of the image using color analysis algorithms (e.g., OpenCV), and the creativity and technique are evaluated using pre-trained generative AI models, while the emotion recognition engine continuously acquires real-time emotional data from the user and incorporates this information into the evaluation.

[0606] 4. Calculation and ranking of evaluation results

[0607] The server aggregates the evaluation results for each work. For example, an image may receive scores of "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Technique: 6 / 10." The server then calculates an overall evaluation score of "30 / 40" based on these scores. Based on this, the server ranks all works. The server also takes into account the user's emotional data to adjust the extent to which emotional bias affects the evaluation score.

[0608] 5. Publication and notification of evaluation results

[0609] The server stores the final evaluation results in a database and makes them available through a viewable web interface or application. Users can access and check the evaluation results from their own devices. The server also determines the optimal notification method based on the analysis results of the emotion recognition engine. For example, if the evaluation result is unexpectedly low, the server will send a notification in a way that will not surprise the user.

[0610] Examples and prompts

[0611] For example, suppose User A uploads an image titled "Spring Landscape." At the time of upload, the emotion recognition engine analyzes User A's current emotion (e.g., joy or excitement) and sends the results to the server as metadata. The server then confirms that the image was generated by artificial intelligence and then evaluates it according to an evaluation flow dedicated to images. The evaluation results are "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Technique: 6 / 10," resulting in an overall evaluation score of "30 / 40." These evaluation results are ranked, and User A can check the rank of "Spring Landscape" on his or her own device. In addition, the notification method is optimized based on User A's emotional information, so that, for example, User A is not surprised when he or she receives the evaluation results.

[0612] Prompt Sentence Examples

[0613] 1. "What was the sentiment analysis result when I uploaded an AI-generated image of a spring landscape?"

[0614] 2. Please rate the uploaded image and calculate the overall score.

[0615] 3. "Please explain the optimized notification method based on the evaluation results and user sentiment."

[0616] In this way, the system of the present invention accurately and fairly evaluates AI-generated works uploaded by users and appropriately discloses the evaluation results to users. By combining it with an emotion recognition engine, it is possible to improve the user experience and provide a personalized evaluation process.

[0617] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0618] Step 1:

[0619] Users access the system's upload screen using their own devices, select an AI-generated work such as an image, music, or manga, and enter metadata such as the work's name, description, and category.

[0620] Input: User-selected artwork file, artwork name, description, category, and other metadata

[0621] Output: A data packet containing the input work file and metadata.

[0622] Specific operation: When the user clicks the "Upload" button, the device sends this data to the server. At the same time, the device's camera and microphone are used to capture the user's facial expressions and voice, and the emotion recognition engine analyzes the user's emotions in real time. The analysis results are also sent to the server as metadata.

[0623] Step 2:

[0624] The server receives the work data and metadata received from the user and then uses a deep learning model to determine whether the work is artificial intelligence-generated.

[0625] Input: Submitted work data and metadata

[0626] Output: Work judgment and classification results

[0627] How it works: The server uses a deep learning framework (such as TensorFlow or PyTorch) to check whether the submitted work is AI-generated, then categorizes it by format (e.g., image, music, comics, etc.) and stores it in a directory for each format.

[0628] Step 3:

[0629] The server executes a dedicated evaluation flow for the classified works.

[0630] Input: Classified artwork data

[0631] Output: Score for each evaluation item

[0632] Specific operation: Evaluation is performed for each category using color analysis algorithms (e.g., OpenCV), audio analysis algorithms, story analysis algorithms, etc. Scores are calculated for evaluation items such as color, composition, creativity, and technique. In addition, an emotion recognition engine analyzes the user's real-time emotions during the evaluation, and this emotional information is also reflected in the evaluation.

[0633] Step 4:

[0634] The server compiles the evaluation results for each work and ranks them.

[0635] Input: Scores for each evaluation item, user's emotional information

[0636] Output: Overall evaluation score and ranking results

[0637] Specific operation: The server stores the scores for each evaluation item in a database and calculates an overall evaluation score by aggregating the scores. Each work is ranked based on this overall evaluation score. The server also takes into account the user's emotional information, adjusting the evaluation to avoid bias, especially in subjective evaluation items such as creativity.

[0638] Step 5:

[0639] The server stores the evaluation results in a database, makes them available to users, and notifies them.

[0640] Input: Overall evaluation score and ranking results

[0641] Output: Publishing the evaluation results and rankings, and notifying the user

[0642] Specific operation: The server publishes the evaluation results through a web interface or application. Users can check the evaluation results on their own devices. In addition, the notification method is optimized based on the analysis results of the emotion recognition engine. For example, if the evaluation result is unexpectedly low, a notification message will be sent to avoid surprise.

[0643] In this way, the system of the present invention can accurately and fairly evaluate AI-generated works uploaded by users and appropriately disclose the evaluation results to users. By combining it with an emotion recognition engine, it is possible to improve the user experience and provide a personalized evaluation process.

[0644] (Application example 2)

[0645] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0646] Conventional AI-generated artwork evaluation systems have struggled to provide fair evaluations and a personalized experience. Furthermore, they have been unable to effectively utilize user emotional data, resulting in incomplete subjective evaluations of creative works. The present invention aims to provide a system that improves the user experience by analyzing user emotions and incorporating that data into the evaluation process.

[0647] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a means for a user to upload AI-generated works, a means for the server to classify the uploaded works based on their format, a means for the server to execute a dedicated evaluation flow for each format, a means for acquiring and analyzing user emotional data during the evaluation, a means for complementing the evaluation score based on the acquired emotional data, a means for the server to aggregate and rank the evaluation results, and a means for disclosing the evaluation results and rankings to the user. By reflecting user emotional information in the evaluation process, this enables subjective evaluation of advertising creatives and the like to be performed in a more accurate and personalized manner.

[0648] "User" refers to the individual or entity that uploads and evaluates AI-generated works.

[0649] "AI-generated works" refers to content such as images, music, videos, and comics generated by artificial intelligence or machine learning models.

[0650] "Uploading" refers to the act of sending digital data from a user's device to a server.

[0651] "Server" refers to a computer system that stores, processes, and delivers data.

[0652] "Format" refers to the type or category of work uploaded (e.g., image, music, video, etc.).

[0653] "Evaluation flow" refers to the series of evaluation steps or processes that are carried out on uploaded works.

[0654] "Emotional data" refers to data that measures a user's emotional state (e.g., joy, excitement, surprise, etc.) and expresses it as a numerical value or text.

[0655] "Analysis" is the process of examining collected data and extracting specific information.

[0656] An "evaluation score" is a numerical indicator of the quality of a work, calculated based on multiple evaluation criteria.

[0657] "Aggregation" refers to the act of compiling multiple evaluation results and calculating statistical values ​​such as totals and averages.

[0658] "Ranking" refers to arranging works in order of merit based on their evaluation scores.

[0659] "Publication" refers to the act of providing evaluation results and rankings in a form that is accessible to users.

[0660] "Personalization" refers to optimizing experiences and information based on the individual characteristics and preferences of each user.

[0661] This invention is a system that uses emotional data to provide a more personalized experience when users rate AI-generated works. The system consists of a user terminal, an emotion analysis engine, a server, a rating flow, and a publishing means.

[0662] Hardware and Software Configuration

[0663] 1. On the user's device:

[0664] This includes devices such as smartphones and smart glasses, which allow users to upload AI-generated creations and view evaluation results.

[0665] 2. Sentiment Analysis Engine:

[0666] This software is used for emotion analysis, such as Affectiva and Microsoft Azure Face API, and collects emotion data when users upload and rate.

[0667] 3. Server:

[0668] This is a computer system that manages the evaluation process, stores and processes data, classifies works to be evaluated, generates scores based on each evaluation item, tallying and ranking the results, and publishes the final results.

[0669] Data processing and calculation methods

[0670] 1. Upload:

[0671] AI-generated works (images, videos, music, etc.) are uploaded from the user's device to the server. Metadata includes the work's name, description, and emotional data.

[0672] 2. Classification:

[0673] The server automatically classifies the uploaded works and assigns them to the appropriate evaluation flow depending on their format (images, videos, music, etc.).

[0674] 3. Emotion analysis:

[0675] When users upload their work or receive ratings, a sentiment analysis engine is used to collect real-time emotional data, which directly influences the rating process and is particularly used to complement subjective rating items.

[0676] 4. Evaluation and Scoring:

[0677] The server evaluates each work in each format based on technical criteria (e.g., color, composition, technical ability) and subjective criteria (e.g., creativity, engagement). It also performs a supplementary evaluation based on emotional data, and calculates an overall score by combining the scores for each evaluation item.

[0678] 5. Counting and ranking:

[0679] The evaluation results are compiled and ranked, which determines the ranking of the work compared to other works.

[0680] 6. Publication of evaluation results:

[0681] The final evaluation results are published in an optimal format based on the user's emotional data. Users can view the evaluation results on their own devices, and the notification method is also adjusted based on the emotional data.

[0682] Examples and prompts

[0683] For example, when an ad creator uploads an advertising video for a new fashion brand, the video is classified and evaluated on the server. Emotional data is collected using a smartphone or smart glasses camera while the video is being viewed, and an engagement score and overall evaluation score are calculated based on that data. The ad creator who uploaded the video can check the evaluation results and find out which parts of the ad particularly engaged users.

[0684] Example prompt sentence:

[0685] "Please watch an advertisement video for a new fashion brand and calculate an engagement score based on the user's sentiment analysis data while watching. Store the results in a rating database and return an overall score."

[0686] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0687] Step 1:

[0688] A user uploads an AI-generated work to the system using a terminal. The input is the work file and its metadata (work name, description, emotional data), and the output is the uploaded data sent to the server. This data includes the file itself as well as the metadata entered by the user.

[0689] Step 2:

[0690] The server receives the uploaded work data. The input is the uploaded data sent from the user's device, the server saves the work file and analyzes the metadata. The output is the work's storage and metadata classification information.

[0691] Step 3:

[0692] The server classifies uploaded works based on their format. The input is the work file and its metadata, and the output is the work's category information (e.g., image, video, music). The server determines that the work is AI-generated and assigns it to a dedicated evaluation flow based on its format.

[0693] Step 4:

[0694] When a user uploads a work, the emotion analysis engine acquires and analyzes the user's emotional data. The input is the user's emotional data (real-time facial expression data and voice data), and the output is the emotion analysis result (e.g., joy, excitement, surprise). This value is sent to the server as metadata.

[0695] Step 5:

[0696] The server executes a dedicated evaluation flow for each type of work. The input is the work file and metadata (including emotional data), and the output is a score for each evaluation item (technical and subjective). The server uses a deep learning model to perform technical evaluations (e.g., color, composition) and complements subjective evaluations (e.g., creativity, engagement) with emotional data.

[0697] Step 6:

[0698] The server aggregates the evaluation results and ranks them. The input is the score for each evaluation item, and the output is the overall evaluation score and ranking information. The server statistically aggregates the evaluation results and generates a ranking.

[0699] Step 7:

[0700] The server publishes the evaluation results and rankings to users. The input is the overall evaluation score and ranking information, and the output is the evaluation results published in a form that users can access. Furthermore, the notification method is optimized based on the emotion engine, and users can check the evaluation results on their own devices.

[0701] Step 8:

[0702] Users can check the published evaluation results on their devices and receive feedback. The input is the evaluation results sent from the server, and the output is a visualization of the evaluation content and feedback information. For example, users can see which evaluation items they received high scores for and what kind of feedback they received based on emotional data.

[0703] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0704] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0705] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0706] [Third embodiment]

[0707] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0708] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0709] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0710] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0711] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0712] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0713] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0714] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0715] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0716] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0717] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0718] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0719] The system of this invention allows users to fairly evaluate AI-generated works. The system begins with the user uploading the work, and then the server classifies the work, executes the appropriate evaluation flow, and compiles and publishes the results.

[0720] 1. Upload your work

[0721] Users use their devices to upload AI-generated images, music, comics, and other works to the system. On the upload screen, users enter metadata such as the work's name, description, and category. The device then sends the uploaded data to the server.

[0722] 2. Classification of works

[0723] The server receives the uploaded work and verifies that it is AI-generated. This verification is done using a deep learning model. This model analyzes the characteristics of the work and determines the likelihood that it was generated by AI. This prevents non-AI-generated works from proceeding to the next step.

[0724] Works that are confirmed to be AI-generated are classified into their format (images, music, manga, etc.) and assigned to the appropriate evaluation flow.

[0725] 3. Dedicated evaluation flow

[0726] The server then applies the appropriate evaluation flow to the classified works. For images, it evaluates color, composition, creativity, and technical aspects. For music, it evaluates melody, rhythm, creativity, and sound quality. For manga, it evaluates story, character quality, art style, and creativity.

[0727] For example, when an image is uploaded, the server uses a color detection algorithm to evaluate color balance and facial detection technology to evaluate composition, generating a separate score based on each evaluation factor.

[0728] 4. Calculation and ranking of evaluation results

[0729] The server aggregates the evaluation results for each work. For example, for an image work, it aggregates each score such as "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Technique: 6 / 10," and calculates an overall evaluation score. Each work is ranked based on the calculated overall score.

[0730] 5. Publication of evaluation results

[0731] The aggregated evaluation results are stored in a database, and the server makes these results available for users to view. Users can check the evaluation results from their own devices using a web interface or application.

[0732] As a concrete example, consider the case where User A uploads an image titled "Spring Scenery." The server confirms that this image is AI-generated and evaluates it according to an evaluation flow specifically for images. The evaluation results are "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Technology: 6 / 10," resulting in an overall evaluation score of "30 / 40." These evaluation results are ranked, and User A can check from his or her device how "Spring Scenery" is ranked.

[0733] In this way, the system of the present invention accurately and fairly evaluates AI-generated works uploaded by users and appropriately discloses the evaluation results to users, thereby improving the quality of AI-generated works and ensuring transparency and fairness in the evaluation process.

[0734] The processing flow will be explained below.

[0735] Step 1:

[0736] Users upload AI-generated artworks using their devices. They select artworks such as images, music, and manga from a file selection screen via a web form or dedicated application. They also enter metadata such as the artwork's name, description, and category.

[0737] Step 2:

[0738] The device sends the entered work data and metadata to the server via HTTP requests or API calls.

[0739] Step 3:

[0740] The server receives the work data. After receiving it, the server checks the data size and file format, checking whether it is in a standard format, such as JPG or PNG for images, or MP3 or WAV for music.

[0741] Step 4:

[0742] The server records the received work data and metadata in a database, along with additional information such as the work ID and timestamp.

[0743] Step 5:

[0744] The server analyzes the stored artwork data and uses a deep learning model to determine whether the artwork is AI-generated. The model analyzes the artwork's characteristics and outputs a score indicating the likelihood of AI generation.

[0745] Step 6:

[0746] The server automatically classifies the work by format, such as image, music, or manga, and then assigns it to the corresponding evaluation flow based on the classification results.

[0747] Step 7:

[0748] The server executes the evaluation flow for each method. For example, in the case of an image, it evaluates color balance using a color detection algorithm and composition using face detection technology. A score is generated based on each evaluation item.

[0749] Step 8:

[0750] The server aggregates the scores for each evaluation item and calculates an overall evaluation score. The final score is calculated by summing or averaging the scores for each evaluation item.

[0751] Step 9:

[0752] The server compares the overall scores of all works and ranks them. The ranking results are updated in the database, and each work is given a rank.

[0753] Step 10:

[0754] The server publishes the evaluation results and rankings to users by generating a web page for publication, and users can view the evaluation results by accessing that page.

[0755] Step 11:

[0756] The server will notify the user of the evaluation results via email or the app's notification function.

[0757] Step 12:

[0758] Users can check the evaluation results on their own devices. Users will receive a notification and can access the detailed evaluation result page via a specified link or in-app menu to check the evaluation content and ranking.

[0759] Example 1

[0760] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0761] In recent years, advances in generative AI technology have led to an increase in the number of AI-generated works in a variety of formats. However, due to the lack of a standard system for fairly and objectively evaluating these works, quality evaluations and rankings of works often lack transparency and fairness. As a result, it is difficult for users to accurately grasp the quality of their own works. In addition, the lack of consistency in the evaluation process makes it difficult to compare works of different formats.

[0762] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0763] In this invention, the server includes: a means for users to upload AI-generated works; a means for a terminal to send metadata of the uploaded works to the server; a means for the server to verify that the uploaded works are AI-generated using a deep learning model; a means for the server to classify the works based on their format; a means for the server to execute a dedicated evaluation flow for each format; a means for the server to generate scores based on evaluation criteria such as color, composition, creativity, and technical aspects; a means for the server to aggregate and rank the evaluation results; and a means for the server to disclose the evaluation results and rankings to users. This enables transparent and consistent evaluation of AI-generated works, allowing users to accurately determine the merits of their own works. Furthermore, fair ranking based on the scores generated during the evaluation process makes it easier to compare works of different formats.

[0764] "User" means an individual or entity that accesses the System and uploads AI-generated Works.

[0765] A "terminal" is a device (computer, smartphone, tablet, etc.) that a user uses to input a work and send metadata to a server.

[0766] A "server" is a computer system that receives, categorizes, evaluates, and aggregates uploaded works, and then makes the evaluation results available to users.

[0767] "AI-generated works" are images, music, comics, and other creative works that are automatically or semi-automatically generated using artificial intelligence technology.

[0768] "Metadata" is additional information related to a work, such as the work's name, description, and category.

[0769] A "deep learning model" is an algorithm or network based on deep learning, a technology used to analyze and recognize AI-generated works.

[0770] "Classification" is the process of dividing uploaded works into categories based on their format (e.g., images, music, comics, etc.).

[0771] An "evaluation flow" is a series of procedures or algorithms that evaluate the quality and characteristics of a work based on evaluation criteria defined for each format.

[0772] A "score" is a score or evaluation value for a specific evaluation item that is generated through an evaluation flow.

[0773] The "color detection algorithm" is an algorithm for analyzing and evaluating the color balance and color placement of a work.

[0774] "Face detection technology" is a technology for identifying the position and number of faces in an image.

[0775] "Tallying" is the process of adding up the scores for each evaluation item to calculate an overall evaluation score.

[0776] "Ranking" is the process of determining the relative order of works based on their overall evaluation scores.

[0777] "Public" means to display and provide evaluation results and ranking information so that users can view them.

[0778] The system of this invention allows users to fairly evaluate AI-generated works. The system begins with the user uploading the work, and then the server classifies the work, executes the appropriate evaluation flow, and compiles and publishes the evaluation results.

[0779] First, a user uses a device to upload AI-generated images, music, manga, or other works to the system. Specifically, the user enters metadata such as the "work name," "work description," and "work category" on the upload screen, and the device then sends the work file along with this data to the server.

[0780] The server receives the uploaded data, analyzes the raw artwork file and metadata, and uses a deep learning model to confirm whether the artwork is AI-generated. Typical deep learning models are TensorFlow or PyTorch. This model analyzes the artwork's feature vector and calculates the probability of AI generation. Based on this result, the server will not proceed to the next step if the artwork is determined not to be AI-generated, and will notify the user.

[0781] The server categorizes works confirmed to be AI-generated based on their format, such as images, music, or comics. A dedicated evaluation process is applied to each classified work. For images, the server evaluates color balance using a color detection algorithm (e.g., OpenCV) and composition using face detection technology. It also evaluates creativity and technical aspects using machine learning models.

[0782] The server then calculates an overall score by adding up the scores generated for each evaluation item. For example, for an image work, the server would add up scores such as "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Technique: 6 / 10" to give an overall score of "30 / 40."

[0783] Finally, the server ranks the works based on these evaluation results and stores the information in a database. The evaluation results and rankings are made publicly accessible to users. Specifically, when a user accesses the system using a terminal and clicks the "View Evaluation Results" button, a screen will appear displaying the aggregated scores and ranks.

[0784] As a concrete example, consider the case where User A uploads an image titled "Spring Landscape." The server confirms that the image is AI-generated and performs color detection, face detection, and creativity and technical evaluation according to an evaluation flow specifically for images. The evaluation results are "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Technology: 6 / 10," resulting in an overall evaluation score of "30 / 40." The rankings are updated based on these scores, and User A can check from his or her device where "Spring Landscape" ranks.

[0785] As described above, the system of the present invention can accurately and fairly evaluate AI-generated works uploaded by users and quickly make the evaluation results available to users, thereby improving the quality of AI-generated works and ensuring transparency and fairness in the evaluation process.

[0786] Example prompt sentence:

[0787] "Run this image evaluation flow to generate and rank scores based on color, composition, creativity, and technique."

[0788] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0789] Step 1:

[0790] The user uses the device to access the upload screen. On the upload screen, they enter metadata such as the "work name," "work description," and "work category." After completing the entry, the user selects the work file and clicks the upload button. This sends the work file and metadata from the device to the server.

[0791] Input: User-entered work name, work description, work category, work file

[0792] Output: Upload data sent to the server

[0793] Step 2:

[0794] The server receives the uploaded data sent by the user. The server first checks the integrity of the data and analyzes the received metadata and the format of the work file. Next, it uses a deep learning model (e.g., TensorFlow or PyTorch) to confirm whether the work is AI-generated. Works that are confirmed to be AI-generated proceed to the next step.

[0795] Input: Upload data sent by the user

[0796] Output: AI generation confirmation result (True / False), work format classification

[0797] Step 3:

[0798] The server classifies works that are confirmed to be AI-generated based on their format (images, music, manga, etc.) using pre-defined rules and algorithms. Works of each type are then assigned to their own evaluation flow.

[0799] Input: AI generation confirmation result, work format

[0800] Output: Classification results (images, music, manga, etc.)

[0801] Step 4:

[0802] The server applies a dedicated evaluation flow to each classified work. For example, for image works, it evaluates color balance using a color detection algorithm (using OpenCV) and composition using face detection technology. Other creative and technical aspects are also analyzed and evaluated using machine learning models.

[0803] Input: Classified works

[0804] Output: Score for each evaluation item (color, composition, creativity, technique, etc.)

[0805] Step 5:

[0806] The server aggregates the scores generated for each evaluation category. For example, for an image, the scores might be "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Technique: 6 / 10." These scores are then added together to calculate an overall evaluation score.

[0807] Input: Score for each evaluation item

[0808] Output: Overall evaluation score

[0809] Step 6:

[0810] The server automatically ranks the works based on the total score, and the ranking information is stored in a database.

[0811] Input: Overall evaluation score

[0812] Output: Ranked work information

[0813] Step 7:

[0814] The server stores the evaluation results and rankings in a database and makes them available for viewing by users. Users can access the system using their devices and click the "View Evaluation Results" button to check the evaluation results and rankings of their own works.

[0815] Input: Saved evaluation results and ranking information

[0816] Output: Evaluation results and ranking information displayed on the user screen

[0817] (Application example 1)

[0818] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0819] Food delivery services are required to improve the efficiency of new menu development and promotional activities by fairly evaluating and ranking the quality and appeal of AI-generated food images and menus. In current systems, such evaluations are often done manually, which lacks fairness and transparency. Furthermore, there is a possibility that images that are not AI-generated may be mixed in, making it difficult to ensure reliability.

[0820] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0821] In this invention, the server includes a means for users to upload AI-generated creations, a means for the server to classify the uploaded creations based on their format, and a means for the server to execute a dedicated evaluation flow for each format, thereby enabling a food delivery service to fairly and efficiently evaluate the color, composition, creativity, and delicious appearance of AI-generated food images and menus, and to aggregate and rank the evaluation results.

[0822] "User" means an individual or legal entity that uses the system to upload AI-generated works.

[0823] A "server" is a computer device that receives uploaded works, categorizes them, executes an evaluation flow, and aggregates and ranks the evaluation results.

[0824] "Works" are creative works such as AI-generated images, music, and comics uploaded by users.

[0825] "Classification" is the process by which the server identifies works received based on their format and places them into appropriate categories.

[0826] The "evaluation flow" is a series of evaluation processes that the server carries out on classified works, with different evaluation items set for each format.

[0827] "Evaluation results" refer to the aggregated scores for each evaluation item generated by the evaluation flow.

[0828] "Ranking" refers to ranking works based on the evaluation results.

[0829] "Food delivery service" refers to a service business that delivers food to customers who order it.

[0830] "Food images" are images of the appearance of food provided by food delivery services, and are important for stimulating the user's appetite.

[0831] A "menu" is a list of food and drinks offered by a food delivery service, showing the items that a customer can choose from.

[0832] "Color" is an item that evaluates the arrangement and balance of colors in a work.

[0833] "Composition" is an item that evaluates how the elements of a work are arranged.

[0834] "Creativity" is an item that evaluates how original and innovative a work is.

[0835] "Appetizing appearance" is an item that evaluates how visually appetizing a food image is.

[0836] This invention is a system for impartially evaluating AI-generated food images and menus for food delivery services. This system involves the steps of a user uploading AI-generated food images and menus, a server classifying, evaluating, and ranking the images, and publishing the results.

[0837] System Configuration

[0838] The system mainly consists of a user device, a server, and software that runs the evaluation flow. User devices are smartphones or PCs, while the server is a high-performance computer. The software used is a deep learning framework such as TensorFlow or a web framework such as Flask.

[0839] Processing steps

[0840] 1. Upload an image

[0841] Users upload AI-generated food images and menus to the system from their own devices, along with metadata such as the dish name, description, and category (e.g., appetizer, main dish, dessert, etc.).

[0842] 2. AI-generated judgment

[0843] The server uses a deep learning model (for example, a model built with TensorFlow) to determine whether the uploaded image is AI-generated. Only images that are recognized as AI-generated are allowed to proceed to the next step.

[0844] 3. Image Classification

[0845] Images that are confirmed to be AI-generated are then sorted into categories according to their format, which is based on the type of food (appetizer, main dish, dessert, etc.).

[0846] 4. Execute the evaluation flow

[0847] The server then runs an evaluation flow on the classified images, using algorithms to evaluate criteria such as color, composition, creativity, and appetizing appearance.

[0848] 5. Calculation and ranking of evaluation results

[0849] A score is generated for each item, and these scores are then aggregated to calculate an overall score. Based on the overall score, food images and menus are ranked.

[0850] 6. Publication of evaluation results

[0851] The evaluation results are stored on a server in a form that can be viewed by food delivery service administrators and users, and are made public through a web interface or application.

[0852] Specific examples

[0853] For example, consider a new menu item, "Spring Salad," generated using AI. A user uploads this image to the system as "Spring Salad." The server uses a TensorFlow model to verify that the image is AI-generated, and then evaluates it based on factors such as color balance, composition, creativity, and appetizing appearance. Finally, the server assigns ratings such as "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Appetizing: 9 / 10," resulting in an overall score of "33 / 40." These scores are reflected in the rankings, allowing administrators and users to see which menu items received the highest ratings.

[0854] Prompt Sentence Examples

[0855] "We used AI to generate food images for a new food delivery menu. Please rate these images on color, composition, creativity, and whether they look delicious."

[0856] This system will enable food delivery services to fairly and efficiently evaluate the appeal of new menu items, helping them with promotional activities and menu development.

[0857] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0858] Step 1:

[0859] Users upload AI-generated food images and menus to the system from their own devices. On the upload screen, users also enter metadata such as the dish name, description, and category (e.g., appetizer, main dish, dessert, etc.). The entered data and images are sent to the server.

[0860] Step 2:

[0861] The server uses a deep learning model (TensorFlow model) to determine whether an uploaded image is AI-generated. Specifically, the server inputs the image into the model and outputs a probability of whether it is AI-generated. If the result exceeds a threshold, the image is recognized as AI-generated. The input data is the image and its metadata, and the output data is the result of the AI-generated determination.

[0862] Step 3:

[0863] The server classifies images that are certified as AI-generated based on their format (category). Specifically, they are sorted according to food category (appetizer, main dish, dessert, etc.). The input data is the image and metadata, and the output data is the classification result, which is category information.

[0864] Step 4:

[0865] The server then runs an evaluation flow on the classified images, using algorithms to evaluate color, composition, creativity, and delicious appearance. The evaluation process analyzes color balance, evaluates the placement of elements, judges creativity, and evaluates how appetizing the food looks. The input data is the classified image, and the output data is the score for each evaluation item.

[0866] Step 5:

[0867] The server aggregates the scores for each evaluation item and calculates an overall score. For example, adding up evaluation scores such as "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Appetizing: 9 / 10," the overall score is "33 / 40." The input data is the score for each evaluation item, and the output data is the overall score.

[0868] Step 6:

[0869] The server ranks each food image and menu item based on the evaluation results (total score). Specifically, it lists all evaluation results and sorts them in ascending or descending order based on the score. The input data is the total score, and the output data is the ranked list.

[0870] Step 7:

[0871] The server publishes the evaluation results and rankings in a form that can be viewed by food delivery service administrators and users. Specifically, it makes them accessible through a web interface or application. Administrators and users can check the evaluation results from their own devices and use them to develop new menu items and promote their activities. The input data is a ranked list, and the output data is the evaluation results that can be viewed by users.

[0872] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0873] The system of this invention allows users to fairly evaluate AI-generated works, and by combining it with an emotion engine that recognizes the user's emotions, it provides a more personalized experience. The system flow is as follows:

[0874] 1. Upload your work

[0875] Users use their devices to upload AI-generated works such as images, music, and comics to the system. On the upload screen, users enter metadata such as the work's name, description, and category. When uploading, the emotion engine analyzes the user's emotions and sends the analysis results to the server as metadata. For example, emotional information such as whether the user is excited or happy is included in the metadata.

[0876] 2. Classification of works

[0877] The server receives the uploaded work and uses a deep learning model to determine whether the work is AI-generated. Once confirmed, the work is classified into its format and sent through a dedicated evaluation flow.

[0878] 3. Dedicated evaluation flow

[0879] The server then applies an appropriate evaluation process to each classified work. For example, for image works, it evaluates color, composition, creativity, and technical aspects. For music works, it evaluates melody, rhythm, creativity, and sound quality. For manga works, it evaluates story, character quality, art style, and creativity.

[0880] The emotion engine analyzes the user's emotions in real time during the evaluation and records changes in their emotions. This emotional information influences the evaluation results, and is an important factor, especially for subjective evaluation items such as creativity.

[0881] 4. Calculation and ranking of evaluation results

[0882] The server aggregates the evaluation results for each work. For example, for an image work, it aggregates the individual scores, such as "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Technique: 6 / 10," and calculates an overall evaluation score. Each work is ranked based on the calculated overall score. The user's emotional information may also be taken into account.

[0883] 5. Publication and notification of evaluation results

[0884] The server stores the evaluation results in a database and makes them available for users to view. Users can use a web interface or application to check the evaluation results from their own devices. Furthermore, the emotion engine optimizes the notification method based on the user's emotional state and sends notifications in a more appropriate format.

[0885] Specific examples

[0886] For example, consider the case where User A uploads an image titled "Spring Scenery." At the time of uploading, the emotion engine analyzes User A's current emotion (e.g., joy or excitement) and sends this as metadata to the server. The server confirms that the image is AI-generated and evaluates it according to an evaluation flow specifically for images. The evaluation results are "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Technique: 6 / 10," resulting in an overall evaluation score of "30 / 40." These evaluation results are ranked, and User A can check how "Spring Scenery" is ranked from his or her own device.

[0887] Furthermore, the notification method is optimized based on User A's emotional information, so that, for example, User A will receive a notification that is designed to avoid surprise when receiving the evaluation result. In this way, the system of the present invention accurately and fairly evaluates the AI-generated works uploaded by users and appropriately discloses the evaluation results to the users. By combining the emotion engine, it is possible to improve the user experience and provide a personalized evaluation process.

[0888] The processing flow will be explained below.

[0889] Step 1:

[0890] Users upload AI-generated artworks using their devices. They then select images, music, manga, etc. from a file selection screen via an application or web form. They also enter metadata such as the artwork's name, description, and category.

[0891] Step 2:

[0892] The device sends the uploaded content data and metadata to the server, typically via an HTTP request or API call.

[0893] Step 3:

[0894] The server receives the work data. After receiving it, the server checks the data size and file format (JPEG, PNG, MP3, WAV, etc.) to see if the format is within the allowed range, and generates an error message if the format is invalid.

[0895] Step 4:

[0896] The server stores the received artwork data and metadata in a database, along with additional information such as artwork ID, timestamp, and user information.

[0897] Step 5:

[0898] The server uses an emotion engine to analyze the user's emotions during and after uploading, and records the results as metadata. For example, the emotion engine analyzes the user's facial expressions and tone of voice to determine whether the user is currently "happy" or "nervous."

[0899] Step 6:

[0900] The server analyzes the artwork data and determines whether the artwork is AI-generated. It uses a deep learning model to analyze the artwork's characteristics and outputs a score indicating the likelihood of AI generation.

[0901] Step 7:

[0902] The server automatically classifies the work by format (image, music, manga, etc.), identifies which category the work belongs to, and assigns it to a dedicated evaluation flow.

[0903] Step 8:

[0904] The server executes a dedicated evaluation flow for each format. For example, for image works, it evaluates color balance using a color detection algorithm and composition using face detection technology. For music works, it evaluates melody, rhythm, creativity, and sound quality. For manga works, it evaluates story, character quality, art style, and creativity.

[0905] Step 9:

[0906] The server tally the generated evaluation scores and calculate an overall evaluation score. This is done by adding up or averaging the scores for each evaluation item. For example, for an image work, the evaluation scores for "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Technique: 6 / 10" are combined to calculate an overall evaluation score of "30 / 40."

[0907] Step 10:

[0908] The server compares the overall scores of all works and ranks them, which are recorded in a database in the form of a ranking, and each work is given a rank.

[0909] Step 11:

[0910] The server publishes the evaluation and ranking results to the user. A dedicated web interface or application screen is generated and made accessible to the user. The display of the evaluation result page can be customized based on the user's emotional data analyzed by the emotion engine.

[0911] Step 12:

[0912] Users can check the evaluation results on their own devices. Users can access the evaluation results page via the notification they receive and check how their work was evaluated and how it was ranked.

[0913] Step 13:

[0914] The server sends a notification of the evaluation result to the user. The emotion engine analyzes the user's psychological state and optimizes the notification method, for example, sending a gentle tone notification message if the user is feeling depressed. The notification is delivered to the user via email or in-app notification.

[0915] Example 2

[0916] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0917] When evaluating works generated by AI, it is difficult to obtain fair and accurate evaluations. Furthermore, the lack of personalized evaluations and notifications that take user emotions into account results in a poor user experience. Conventional systems are unable to provide comprehensive evaluations that include emotional information, and lack an appropriate feedback process that utilizes user emotion analysis. As a result, it remains difficult for users to receive evaluations that they are satisfied with.

[0918] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0919] In this invention, the server includes: a means for a user to submit an AI-generated work to a database; a means for the server to classify the submitted work based on its format; a means for the server to analyze the user's emotions using an emotion recognition engine and store the information as metadata; a means for the server to execute a dedicated evaluation flow for each format; a means for the server to compile and rank the evaluation results; and a means for publishing the evaluation results and rankings to the user. This enables personalized evaluations that reflect the user's emotions, providing fair and convincing evaluations. Furthermore, publishing the evaluation results and providing appropriate notification methods can improve the user experience.

[0920] "User" means a person or entity that uses the system to upload AI-generated works and receive evaluation results.

[0921] "Artificial intelligence-generated works" are creative works such as images, music, and comics that are generated using artificial intelligence.

[0922] "Means for sending to the database" refers to a function that allows a user to use their own terminal to send AI-generated works and related metadata to the server.

[0923] The "means for classifying based on format" is an algorithm that the server uses to classify the received works according to their format, such as images, music, comics, etc.

[0924] An "emotion recognition engine" is a software program that analyzes emotions from a user's facial expressions and voice and saves the results as metadata.

[0925] "Metadata" is additional information associated with an AI-generated work, such as the work's name, description, category, and analyzed emotional information.

[0926] The "means for executing the evaluation flow" is a process in which the server evaluates each classified work based on specific evaluation items (for example, color, composition, creativity, technique, etc.).

[0927] The "means for aggregating evaluation results and ranking" is a function that allows the server to aggregate the scores of each evaluation item, calculate a total evaluation score, and rank the works.

[0928] The "means for disclosing to users" refers to a web interface or application that displays the aggregated evaluation results and rankings so that users can check them.

[0929] The system of the present invention allows users to fairly and accurately evaluate works generated by artificial intelligence. The system combines an emotion recognition engine to provide a personalized experience.

[0930] As an example of the system, a program that operates based on the following procedure will be described.

[0931] 1. Upload your work

[0932] Users access the system's upload screen using their own device (e.g., a PC or smartphone). They select an AI-generated work, such as an image, music, or manga, and enter metadata such as the work's name, description, and category. When the user clicks the "Upload" button, the device sends this data to the server. At the same time, the device's camera and microphone are used to capture the user's facial expressions and voice, and an emotion recognition engine (e.g., Microsoft Azure Emotion API or IBM Watson Tone Analyzer) analyzes the user's emotions. The results of this analysis are also sent to the server as metadata.

[0933] 2. Classification of works

[0934] The server receives the artwork data and metadata from the user. Then, using a deep learning model (for example, a model using TensorFlow or PyTorch), the server determines whether the artwork is AI-generated. Once this determination is complete, the server classifies the artwork by type (image, music, manga, etc.) and assigns it to a dedicated evaluation flow for each type.

[0935] 3. Dedicated evaluation flow

[0936] The server will rate each type of work based on the following criteria:

[0937] Image work: color, composition, creativity, technique

[0938] Musical composition: melody, rhythm, creativity, sound quality

[0939] Manga works: Story, character quality, art style, creativity

[0940] For example, the server evaluates the color and composition of the image using color analysis algorithms (e.g., OpenCV), and the creativity and technique are evaluated using pre-trained generative AI models, while the emotion recognition engine continuously acquires real-time emotional data from the user and incorporates this information into the evaluation.

[0941] 4. Calculation and ranking of evaluation results

[0942] The server aggregates the evaluation results for each work. For example, an image may receive scores of "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Technique: 6 / 10." The server then calculates an overall evaluation score of "30 / 40" based on these scores. Based on this, the server ranks all works. The server also takes into account the user's emotional data to adjust the extent to which emotional bias affects the evaluation score.

[0943] 5. Publication and notification of evaluation results

[0944] The server stores the final evaluation results in a database and makes them available through a viewable web interface or application. Users can access and check the evaluation results from their own devices. The server also determines the optimal notification method based on the analysis results of the emotion recognition engine. For example, if the evaluation result is unexpectedly low, the server will send a notification in a way that will not surprise the user.

[0945] Examples and prompts

[0946] For example, suppose User A uploads an image titled "Spring Landscape." At the time of upload, the emotion recognition engine analyzes User A's current emotion (e.g., joy or excitement) and sends the results to the server as metadata. The server then confirms that the image was generated by artificial intelligence and then evaluates it according to an evaluation flow dedicated to images. The evaluation results are "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Technique: 6 / 10," resulting in an overall evaluation score of "30 / 40." These evaluation results are ranked, and User A can check the rank of "Spring Landscape" on his or her own device. In addition, the notification method is optimized based on User A's emotional information, so that, for example, User A is not surprised when he or she receives the evaluation results.

[0947] Prompt Sentence Examples

[0948] 1. "What was the sentiment analysis result when I uploaded an AI-generated image of a spring landscape?"

[0949] 2. Please rate the uploaded image and calculate the overall score.

[0950] 3. "Please explain the optimized notification method based on the evaluation results and user sentiment."

[0951] In this way, the system of the present invention accurately and fairly evaluates AI-generated works uploaded by users and appropriately discloses the evaluation results to users. By combining it with an emotion recognition engine, it is possible to improve the user experience and provide a personalized evaluation process.

[0952] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0953] Step 1:

[0954] Users access the system's upload screen using their own devices, select an AI-generated work such as an image, music, or manga, and enter metadata such as the work's name, description, and category.

[0955] Input: User-selected artwork file, artwork name, description, category, and other metadata

[0956] Output: A data packet containing the input work file and metadata.

[0957] Specific operation: When the user clicks the "Upload" button, the device sends this data to the server. At the same time, the device's camera and microphone are used to capture the user's facial expressions and voice, and the emotion recognition engine analyzes the user's emotions in real time. The analysis results are also sent to the server as metadata.

[0958] Step 2:

[0959] The server receives the work data and metadata received from the user and then uses a deep learning model to determine whether the work is artificial intelligence-generated.

[0960] Input: Submitted work data and metadata

[0961] Output: Work judgment and classification results

[0962] How it works: The server uses a deep learning framework (such as TensorFlow or PyTorch) to check whether the submitted work is AI-generated, then categorizes it by format (e.g., image, music, comics, etc.) and stores it in a directory for each format.

[0963] Step 3:

[0964] The server executes a dedicated evaluation flow for the classified works.

[0965] Input: Classified artwork data

[0966] Output: Score for each evaluation item

[0967] Specific operation: Evaluation is performed for each category using color analysis algorithms (e.g., OpenCV), audio analysis algorithms, story analysis algorithms, etc. Scores are calculated for evaluation items such as color, composition, creativity, and technique. In addition, an emotion recognition engine analyzes the user's real-time emotions during the evaluation, and this emotional information is also reflected in the evaluation.

[0968] Step 4:

[0969] The server compiles the evaluation results for each work and ranks them.

[0970] Input: Scores for each evaluation item, user's emotional information

[0971] Output: Overall evaluation score and ranking results

[0972] Specific operation: The server stores the scores for each evaluation item in a database and calculates an overall evaluation score by aggregating the scores. Each work is ranked based on this overall evaluation score. The server also takes into account the user's emotional information, adjusting the evaluation to avoid bias, especially in subjective evaluation items such as creativity.

[0973] Step 5:

[0974] The server stores the evaluation results in a database, makes them available to users, and notifies them.

[0975] Input: Overall evaluation score and ranking results

[0976] Output: Publishing the evaluation results and rankings, and notifying the user

[0977] Specific operation: The server publishes the evaluation results through a web interface or application. Users can check the evaluation results on their own devices. In addition, the notification method is optimized based on the analysis results of the emotion recognition engine. For example, if the evaluation result is unexpectedly low, a notification message will be sent to avoid surprise.

[0978] In this way, the system of the present invention can accurately and fairly evaluate AI-generated works uploaded by users and appropriately disclose the evaluation results to users. By combining it with an emotion recognition engine, it is possible to improve the user experience and provide a personalized evaluation process.

[0979] (Application example 2)

[0980] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0981] Conventional AI-generated artwork evaluation systems have struggled to provide fair evaluations and a personalized experience. Furthermore, they have been unable to effectively utilize user emotional data, resulting in incomplete subjective evaluations of creative works. The present invention aims to provide a system that improves the user experience by analyzing user emotions and incorporating that data into the evaluation process.

[0982] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a means for a user to upload AI-generated works, a means for the server to classify the uploaded works based on their format, a means for the server to execute a dedicated evaluation flow for each format, a means for acquiring and analyzing user emotional data during the evaluation, a means for complementing the evaluation score based on the acquired emotional data, a means for the server to aggregate and rank the evaluation results, and a means for disclosing the evaluation results and rankings to the user. By reflecting user emotional information in the evaluation process, this enables subjective evaluation of advertising creatives and the like to be performed in a more accurate and personalized manner.

[0983] "User" refers to the individual or entity that uploads and evaluates AI-generated works.

[0984] "AI-generated works" refers to content such as images, music, videos, and comics generated by artificial intelligence or machine learning models.

[0985] "Uploading" refers to the act of sending digital data from a user's device to a server.

[0986] "Server" refers to a computer system that stores, processes, and delivers data.

[0987] "Format" refers to the type or category of work uploaded (e.g., image, music, video, etc.).

[0988] "Evaluation flow" refers to the series of evaluation steps or processes that are carried out on uploaded works.

[0989] "Emotional data" refers to data that measures a user's emotional state (e.g., joy, excitement, surprise, etc.) and expresses it as a numerical value or text.

[0990] "Analysis" is the process of examining collected data and extracting specific information.

[0991] An "evaluation score" is a numerical indicator of the quality of a work, calculated based on multiple evaluation criteria.

[0992] "Aggregation" refers to the act of compiling multiple evaluation results and calculating statistical values ​​such as totals and averages.

[0993] "Ranking" refers to arranging works in order of merit based on their evaluation scores.

[0994] "Publication" refers to the act of providing evaluation results and rankings in a form that is accessible to users.

[0995] "Personalization" refers to optimizing experiences and information based on the individual characteristics and preferences of each user.

[0996] This invention is a system that uses emotional data to provide a more personalized experience when users rate AI-generated works. The system consists of a user terminal, an emotion analysis engine, a server, a rating flow, and a publishing means.

[0997] Hardware and Software Configuration

[0998] 1. On the user's device:

[0999] This includes devices such as smartphones and smart glasses, which allow users to upload AI-generated creations and view evaluation results.

[1000] 2. Sentiment Analysis Engine:

[1001] This software is used for emotion analysis, such as Affectiva and Microsoft Azure Face API, and collects emotion data when users upload and rate.

[1002] 3. Server:

[1003] This is a computer system that manages the evaluation process, stores and processes data, classifies works to be evaluated, generates scores based on each evaluation item, tallying and ranking the results, and publishes the final results.

[1004] Data processing and calculation methods

[1005] 1. Upload:

[1006] AI-generated works (images, videos, music, etc.) are uploaded from the user's device to the server. Metadata includes the work's name, description, and emotional data.

[1007] 2. Classification:

[1008] The server automatically classifies the uploaded works and assigns them to the appropriate evaluation flow depending on their format (images, videos, music, etc.).

[1009] 3. Emotion analysis:

[1010] When users upload their work or receive ratings, a sentiment analysis engine is used to collect real-time emotional data, which directly influences the rating process and is particularly used to complement subjective rating items.

[1011] 4. Evaluation and Scoring:

[1012] The server evaluates each work in each format based on technical criteria (e.g., color, composition, technical ability) and subjective criteria (e.g., creativity, engagement). It also performs a supplementary evaluation based on emotional data, and calculates an overall score by combining the scores for each evaluation item.

[1013] 5. Counting and ranking:

[1014] The evaluation results are compiled and ranked, which determines the ranking of the work compared to other works.

[1015] 6. Publication of evaluation results:

[1016] The final evaluation results are published in an optimal format based on the user's emotional data. Users can view the evaluation results on their own devices, and the notification method is also adjusted based on the emotional data.

[1017] Examples and prompts

[1018] For example, when an ad creator uploads an advertising video for a new fashion brand, the video is classified and evaluated on the server. Emotional data is collected using a smartphone or smart glasses camera while the video is being viewed, and an engagement score and overall evaluation score are calculated based on that data. The ad creator who uploaded the video can check the evaluation results and find out which parts of the ad particularly engaged users.

[1019] Example prompt sentence:

[1020] "Please watch an advertisement video for a new fashion brand and calculate an engagement score based on the user's sentiment analysis data while watching. Store the results in a rating database and return an overall score."

[1021] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1022] Step 1:

[1023] A user uploads an AI-generated work to the system using a terminal. The input is the work file and its metadata (work name, description, emotional data), and the output is the uploaded data sent to the server. This data includes the file itself as well as the metadata entered by the user.

[1024] Step 2:

[1025] The server receives the uploaded work data. The input is the uploaded data sent from the user's device, the server saves the work file and analyzes the metadata. The output is the work's storage and metadata classification information.

[1026] Step 3:

[1027] The server classifies uploaded works based on their format. The input is the work file and its metadata, and the output is the work's category information (e.g., image, video, music). The server determines that the work is AI-generated and assigns it to a dedicated evaluation flow based on its format.

[1028] Step 4:

[1029] When a user uploads a work, the emotion analysis engine acquires and analyzes the user's emotional data. The input is the user's emotional data (real-time facial expression data and voice data), and the output is the emotion analysis result (e.g., joy, excitement, surprise). This value is sent to the server as metadata.

[1030] Step 5:

[1031] The server executes a dedicated evaluation flow for each type of work. The input is the work file and metadata (including emotional data), and the output is a score for each evaluation item (technical and subjective). The server uses a deep learning model to perform technical evaluations (e.g., color, composition) and complements subjective evaluations (e.g., creativity, engagement) with emotional data.

[1032] Step 6:

[1033] The server aggregates the evaluation results and ranks them. The input is the score for each evaluation item, and the output is the overall evaluation score and ranking information. The server statistically aggregates the evaluation results and generates a ranking.

[1034] Step 7:

[1035] The server publishes the evaluation results and rankings to users. The input is the overall evaluation score and ranking information, and the output is the evaluation results published in a form that users can access. Furthermore, the notification method is optimized based on the emotion engine, and users can check the evaluation results on their own devices.

[1036] Step 8:

[1037] Users can check the published evaluation results on their devices and receive feedback. The input is the evaluation results sent from the server, and the output is a visualization of the evaluation content and feedback information. For example, users can see which evaluation items they received high scores for and what kind of feedback they received based on emotional data.

[1038] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1039] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1040] 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 the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1041] [Fourth embodiment]

[1042] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1043] 7, a 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.

[1044] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1045] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1046] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1047] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1048] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1049] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1050] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1051] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1052] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1053] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1054] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1055] The system of this invention allows users to fairly evaluate AI-generated works. The system begins with the user uploading the work, and then the server classifies the work, executes the appropriate evaluation flow, and compiles and publishes the results.

[1056] 1. Upload your work

[1057] Users use their devices to upload AI-generated images, music, comics, and other works to the system. On the upload screen, users enter metadata such as the work's name, description, and category. The device then sends the uploaded data to the server.

[1058] 2. Classification of works

[1059] The server receives the uploaded work and verifies that it is AI-generated. This verification is done using a deep learning model. This model analyzes the characteristics of the work and determines the likelihood that it was generated by AI. This prevents non-AI-generated works from proceeding to the next step.

[1060] Works that are confirmed to be AI-generated are classified into their format (images, music, manga, etc.) and assigned to the appropriate evaluation flow.

[1061] 3. Dedicated evaluation flow

[1062] The server then applies the appropriate evaluation flow to the classified works. For images, it evaluates color, composition, creativity, and technical aspects. For music, it evaluates melody, rhythm, creativity, and sound quality. For manga, it evaluates story, character quality, art style, and creativity.

[1063] For example, when an image is uploaded, the server uses a color detection algorithm to evaluate color balance and facial detection technology to evaluate composition, generating a separate score based on each evaluation factor.

[1064] 4. Calculation and ranking of evaluation results

[1065] The server aggregates the evaluation results for each work. For example, for an image work, it aggregates each score such as "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Technique: 6 / 10," and calculates an overall evaluation score. Each work is ranked based on the calculated overall score.

[1066] 5. Publication of evaluation results

[1067] The aggregated evaluation results are stored in a database, and the server makes these results available for users to view. Users can check the evaluation results from their own devices using a web interface or application.

[1068] As a concrete example, consider the case where User A uploads an image titled "Spring Scenery." The server confirms that this image is AI-generated and evaluates it according to an evaluation flow specifically for images. The evaluation results are "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Technology: 6 / 10," resulting in an overall evaluation score of "30 / 40." These evaluation results are ranked, and User A can check from his or her device how "Spring Scenery" is ranked.

[1069] In this way, the system of the present invention accurately and fairly evaluates AI-generated works uploaded by users and appropriately discloses the evaluation results to users, thereby improving the quality of AI-generated works and ensuring transparency and fairness in the evaluation process.

[1070] The processing flow will be explained below.

[1071] Step 1:

[1072] Users upload AI-generated artworks using their devices. They select artworks such as images, music, and manga from a file selection screen via a web form or dedicated application. They also enter metadata such as the artwork's name, description, and category.

[1073] Step 2:

[1074] The device sends the entered work data and metadata to the server via HTTP requests or API calls.

[1075] Step 3:

[1076] The server receives the work data. After receiving it, the server checks the data size and file format, checking whether it is in a standard format, such as JPG or PNG for images, or MP3 or WAV for music.

[1077] Step 4:

[1078] The server records the received work data and metadata in a database, along with additional information such as the work ID and timestamp.

[1079] Step 5:

[1080] The server analyzes the stored artwork data and uses a deep learning model to determine whether the artwork is AI-generated. The model analyzes the artwork's characteristics and outputs a score indicating the likelihood of AI generation.

[1081] Step 6:

[1082] The server automatically classifies the work by format, such as image, music, or manga, and then assigns it to the corresponding evaluation flow based on the classification results.

[1083] Step 7:

[1084] The server executes the evaluation flow for each method. For example, in the case of an image, it evaluates color balance using a color detection algorithm and composition using face detection technology. A score is generated based on each evaluation item.

[1085] Step 8:

[1086] The server aggregates the scores for each evaluation item and calculates an overall evaluation score. The final score is calculated by summing or averaging the scores for each evaluation item.

[1087] Step 9:

[1088] The server compares the overall scores of all works and ranks them. The ranking results are updated in the database, and each work is given a rank.

[1089] Step 10:

[1090] The server publishes the evaluation results and rankings to users by generating a web page for publication, and users can view the evaluation results by accessing that page.

[1091] Step 11:

[1092] The server will notify the user of the evaluation results via email or the app's notification function.

[1093] Step 12:

[1094] Users can check the evaluation results on their own devices. Users will receive a notification and can access the detailed evaluation result page via a specified link or in-app menu to check the evaluation content and ranking.

[1095] Example 1

[1096] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1097] In recent years, advances in generative AI technology have led to an increase in the number of AI-generated works in a variety of formats. However, due to the lack of a standard system for fairly and objectively evaluating these works, quality evaluations and rankings of works often lack transparency and fairness. As a result, it is difficult for users to accurately grasp the quality of their own works. In addition, the lack of consistency in the evaluation process makes it difficult to compare works of different formats.

[1098] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1099] In this invention, the server includes: a means for users to upload AI-generated works; a means for a terminal to send metadata of the uploaded works to the server; a means for the server to verify that the uploaded works are AI-generated using a deep learning model; a means for the server to classify the works based on their format; a means for the server to execute a dedicated evaluation flow for each format; a means for the server to generate scores based on evaluation criteria such as color, composition, creativity, and technical aspects; a means for the server to aggregate and rank the evaluation results; and a means for the server to disclose the evaluation results and rankings to users. This enables transparent and consistent evaluation of AI-generated works, allowing users to accurately determine the merits of their own works. Furthermore, fair ranking based on the scores generated during the evaluation process makes it easier to compare works of different formats.

[1100] "User" means an individual or entity that accesses the System and uploads AI-generated Works.

[1101] A "terminal" is a device (computer, smartphone, tablet, etc.) that a user uses to input a work and send metadata to a server.

[1102] A "server" is a computer system that receives, categorizes, evaluates, and aggregates uploaded works, and then makes the evaluation results available to users.

[1103] "AI-generated works" are images, music, comics, and other creative works that are automatically or semi-automatically generated using artificial intelligence technology.

[1104] "Metadata" is additional information related to a work, such as the work's name, description, and category.

[1105] A "deep learning model" is an algorithm or network based on deep learning, a technology used to analyze and recognize AI-generated works.

[1106] "Classification" is the process of dividing uploaded works into categories based on their format (e.g., images, music, comics, etc.).

[1107] An "evaluation flow" is a series of procedures or algorithms that evaluate the quality and characteristics of a work based on evaluation criteria defined for each format.

[1108] A "score" is a score or evaluation value for a specific evaluation item that is generated through an evaluation flow.

[1109] The "color detection algorithm" is an algorithm for analyzing and evaluating the color balance and color placement of a work.

[1110] "Face detection technology" is a technology for identifying the position and number of faces in an image.

[1111] "Tallying" is the process of adding up the scores for each evaluation item to calculate an overall evaluation score.

[1112] "Ranking" is the process of determining the relative order of works based on their overall evaluation scores.

[1113] "Public" means to display and provide evaluation results and ranking information so that users can view them.

[1114] The system of this invention allows users to fairly evaluate AI-generated works. The system begins with the user uploading the work, and then the server classifies the work, executes the appropriate evaluation flow, and compiles and publishes the evaluation results.

[1115] First, a user uses a device to upload AI-generated images, music, manga, or other works to the system. Specifically, the user enters metadata such as the "work name," "work description," and "work category" on the upload screen, and the device then sends the work file along with this data to the server.

[1116] The server receives the uploaded data, analyzes the raw artwork file and metadata, and uses a deep learning model to confirm whether the artwork is AI-generated. Typical deep learning models are TensorFlow or PyTorch. This model analyzes the artwork's feature vector and calculates the probability of AI generation. Based on this result, the server will not proceed to the next step if the artwork is determined not to be AI-generated, and will notify the user.

[1117] The server categorizes works confirmed to be AI-generated based on their format, such as images, music, or comics. A dedicated evaluation process is applied to each classified work. For images, the server evaluates color balance using a color detection algorithm (e.g., OpenCV) and composition using face detection technology. It also evaluates creativity and technical aspects using machine learning models.

[1118] The server then calculates an overall score by adding up the scores generated for each evaluation item. For example, for an image work, the server would add up scores such as "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Technique: 6 / 10" to give an overall score of "30 / 40."

[1119] Finally, the server ranks the works based on these evaluation results and stores the information in a database. The evaluation results and rankings are made publicly accessible to users. Specifically, when a user accesses the system using a terminal and clicks the "View Evaluation Results" button, a screen will appear displaying the aggregated scores and ranks.

[1120] As a concrete example, consider the case where User A uploads an image titled "Spring Landscape." The server confirms that the image is AI-generated and performs color detection, face detection, and creativity and technical evaluation according to an evaluation flow specifically for images. The evaluation results are "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Technology: 6 / 10," resulting in an overall evaluation score of "30 / 40." The rankings are updated based on these scores, and User A can check from his or her device where "Spring Landscape" ranks.

[1121] As described above, the system of the present invention can accurately and fairly evaluate AI-generated works uploaded by users and quickly make the evaluation results available to users, thereby improving the quality of AI-generated works and ensuring transparency and fairness in the evaluation process.

[1122] Example prompt sentence:

[1123] "Run this image evaluation flow to generate and rank scores based on color, composition, creativity, and technique."

[1124] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1125] Step 1:

[1126] The user uses the device to access the upload screen. On the upload screen, they enter metadata such as the "work name," "work description," and "work category." After completing the entry, the user selects the work file and clicks the upload button. This sends the work file and metadata from the device to the server.

[1127] Input: User-entered work name, work description, work category, work file

[1128] Output: Upload data sent to the server

[1129] Step 2:

[1130] The server receives the uploaded data sent by the user. The server first checks the integrity of the data and analyzes the received metadata and the format of the work file. Next, it uses a deep learning model (e.g., TensorFlow or PyTorch) to confirm whether the work is AI-generated. Works that are confirmed to be AI-generated proceed to the next step.

[1131] Input: Upload data sent by the user

[1132] Output: AI generation confirmation result (True / False), work format classification

[1133] Step 3:

[1134] The server classifies works that are confirmed to be AI-generated based on their format (images, music, manga, etc.) using pre-defined rules and algorithms. Works of each type are then assigned to their own evaluation flow.

[1135] Input: AI generation confirmation result, work format

[1136] Output: Classification results (images, music, manga, etc.)

[1137] Step 4:

[1138] The server applies a dedicated evaluation flow to each classified work. For example, for image works, it evaluates color balance using a color detection algorithm (using OpenCV) and composition using face detection technology. Other creative and technical aspects are also analyzed and evaluated using machine learning models.

[1139] Input: Classified works

[1140] Output: Score for each evaluation item (color, composition, creativity, technique, etc.)

[1141] Step 5:

[1142] The server aggregates the scores generated for each evaluation category. For example, for an image, the scores might be "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Technique: 6 / 10." These scores are then added together to calculate an overall evaluation score.

[1143] Input: Score for each evaluation item

[1144] Output: Overall evaluation score

[1145] Step 6:

[1146] The server automatically ranks the works based on the total score, and the ranking information is stored in a database.

[1147] Input: Overall evaluation score

[1148] Output: Ranked work information

[1149] Step 7:

[1150] The server stores the evaluation results and rankings in a database and makes them available for viewing by users. Users can access the system using their devices and click the "View Evaluation Results" button to check the evaluation results and rankings of their own works.

[1151] Input: Saved evaluation results and ranking information

[1152] Output: Evaluation results and ranking information displayed on the user screen

[1153] (Application example 1)

[1154] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1155] Food delivery services are required to improve the efficiency of new menu development and promotional activities by fairly evaluating and ranking the quality and appeal of AI-generated food images and menus. In current systems, such evaluations are often done manually, which lacks fairness and transparency. Furthermore, there is a possibility that images that are not AI-generated may be mixed in, making it difficult to ensure reliability.

[1156] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1157] In this invention, the server includes a means for users to upload AI-generated creations, a means for the server to classify the uploaded creations based on their format, and a means for the server to execute a dedicated evaluation flow for each format, thereby enabling a food delivery service to fairly and efficiently evaluate the color, composition, creativity, and delicious appearance of AI-generated food images and menus, and to aggregate and rank the evaluation results.

[1158] "User" means an individual or legal entity that uses the system to upload AI-generated works.

[1159] A "server" is a computer device that receives uploaded works, categorizes them, executes an evaluation flow, and aggregates and ranks the evaluation results.

[1160] "Works" are creative works such as AI-generated images, music, and comics uploaded by users.

[1161] "Classification" is the process by which the server identifies works received based on their format and places them into appropriate categories.

[1162] The "evaluation flow" is a series of evaluation processes that the server carries out on classified works, with different evaluation items set for each format.

[1163] "Evaluation results" refer to the aggregated scores for each evaluation item generated by the evaluation flow.

[1164] "Ranking" refers to ranking works based on the evaluation results.

[1165] "Food delivery service" refers to a service business that delivers food to customers who order it.

[1166] "Food images" are images of the appearance of food provided by food delivery services, and are important for stimulating the user's appetite.

[1167] A "menu" is a list of food and drinks offered by a food delivery service, showing the items that a customer can choose from.

[1168] "Color" is an item that evaluates the arrangement and balance of colors in a work.

[1169] "Composition" is an item that evaluates how the elements of a work are arranged.

[1170] "Creativity" is an item that evaluates how original and innovative a work is.

[1171] "Appetizing appearance" is an item that evaluates how visually appetizing a food image is.

[1172] This invention is a system for impartially evaluating AI-generated food images and menus for food delivery services. This system involves the steps of a user uploading AI-generated food images and menus, a server classifying, evaluating, and ranking the images, and publishing the results.

[1173] System Configuration

[1174] The system mainly consists of a user device, a server, and software that runs the evaluation flow. User devices are smartphones or PCs, while the server is a high-performance computer. The software used is a deep learning framework such as TensorFlow or a web framework such as Flask.

[1175] Processing steps

[1176] 1. Upload an image

[1177] Users upload AI-generated food images and menus to the system from their own devices, along with metadata such as the dish name, description, and category (e.g., appetizer, main dish, dessert, etc.).

[1178] 2. AI-generated judgment

[1179] The server uses a deep learning model (for example, a model built with TensorFlow) to determine whether the uploaded image is AI-generated. Only images that are recognized as AI-generated are allowed to proceed to the next step.

[1180] 3. Image Classification

[1181] Images that are confirmed to be AI-generated are then sorted into categories according to their format, which is based on the type of food (appetizer, main dish, dessert, etc.).

[1182] 4. Execute the evaluation flow

[1183] The server then runs an evaluation flow on the classified images, using algorithms to evaluate criteria such as color, composition, creativity, and appetizing appearance.

[1184] 5. Calculation and ranking of evaluation results

[1185] A score is generated for each item, and these scores are then aggregated to calculate an overall score. Based on the overall score, food images and menus are ranked.

[1186] 6. Publication of evaluation results

[1187] The evaluation results are stored on a server in a form that can be viewed by food delivery service administrators and users, and are made public through a web interface or application.

[1188] Specific examples

[1189] For example, consider a new menu item, "Spring Salad," generated using AI. A user uploads this image to the system as "Spring Salad." The server uses a TensorFlow model to verify that the image is AI-generated, and then evaluates it based on factors such as color balance, composition, creativity, and appetizing appearance. Finally, the server assigns ratings such as "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Appetizing: 9 / 10," resulting in an overall score of "33 / 40." These scores are reflected in the rankings, allowing administrators and users to see which menu items received the highest ratings.

[1190] Prompt Sentence Examples

[1191] "We used AI to generate food images for a new food delivery menu. Please rate these images on color, composition, creativity, and whether they look delicious."

[1192] This system will enable food delivery services to fairly and efficiently evaluate the appeal of new menu items, helping them with promotional activities and menu development.

[1193] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1194] Step 1:

[1195] Users upload AI-generated food images and menus to the system from their own devices. On the upload screen, users also enter metadata such as the dish name, description, and category (e.g., appetizer, main dish, dessert, etc.). The entered data and images are sent to the server.

[1196] Step 2:

[1197] The server uses a deep learning model (TensorFlow model) to determine whether an uploaded image is AI-generated. Specifically, the server inputs the image into the model and outputs a probability of whether it is AI-generated. If the result exceeds a threshold, the image is recognized as AI-generated. The input data is the image and its metadata, and the output data is the result of the AI-generated determination.

[1198] Step 3:

[1199] The server classifies images that are certified as AI-generated based on their format (category). Specifically, they are sorted according to food category (appetizer, main dish, dessert, etc.). The input data is the image and metadata, and the output data is the classification result, which is category information.

[1200] Step 4:

[1201] The server then runs an evaluation flow on the classified images, using algorithms to evaluate color, composition, creativity, and delicious appearance. The evaluation process analyzes color balance, evaluates the placement of elements, judges creativity, and evaluates how appetizing the food looks. The input data is the classified image, and the output data is the score for each evaluation item.

[1202] Step 5:

[1203] The server aggregates the scores for each evaluation item and calculates an overall score. For example, adding up evaluation scores such as "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Appetizing: 9 / 10," the overall score is "33 / 40." The input data is the score for each evaluation item, and the output data is the overall score.

[1204] Step 6:

[1205] The server ranks each food image and menu item based on the evaluation results (total score). Specifically, it lists all evaluation results and sorts them in ascending or descending order based on the score. The input data is the total score, and the output data is the ranked list.

[1206] Step 7:

[1207] The server publishes the evaluation results and rankings in a form that can be viewed by food delivery service administrators and users. Specifically, it makes them accessible through a web interface or application. Administrators and users can check the evaluation results from their own devices and use them to develop new menu items and promote their activities. The input data is a ranked list, and the output data is the evaluation results that can be viewed by users.

[1208] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1209] The system of this invention allows users to fairly evaluate AI-generated works, and by combining it with an emotion engine that recognizes the user's emotions, it provides a more personalized experience. The system flow is as follows:

[1210] 1. Upload your work

[1211] Users use their devices to upload AI-generated works such as images, music, and comics to the system. On the upload screen, users enter metadata such as the work's name, description, and category. When uploading, the emotion engine analyzes the user's emotions and sends the analysis results to the server as metadata. For example, emotional information such as whether the user is excited or happy is included in the metadata.

[1212] 2. Classification of works

[1213] The server receives the uploaded work and uses a deep learning model to determine whether the work is AI-generated. Once confirmed, the work is classified into its format and sent through a dedicated evaluation flow.

[1214] 3. Dedicated evaluation flow

[1215] The server then applies an appropriate evaluation process to each classified work. For example, for image works, it evaluates color, composition, creativity, and technical aspects. For music works, it evaluates melody, rhythm, creativity, and sound quality. For manga works, it evaluates story, character quality, art style, and creativity.

[1216] The emotion engine analyzes the user's emotions in real time during the evaluation and records changes in their emotions. This emotional information influences the evaluation results, and is an important factor, especially for subjective evaluation items such as creativity.

[1217] 4. Calculation and ranking of evaluation results

[1218] The server aggregates the evaluation results for each work. For example, for an image work, it aggregates the individual scores, such as "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Technique: 6 / 10," and calculates an overall evaluation score. Each work is ranked based on the calculated overall score. The user's emotional information may also be taken into account.

[1219] 5. Publication and notification of evaluation results

[1220] The server stores the evaluation results in a database and makes them available for users to view. Users can use a web interface or application to check the evaluation results from their own devices. Furthermore, the emotion engine optimizes the notification method based on the user's emotional state and sends notifications in a more appropriate format.

[1221] Specific examples

[1222] For example, consider the case where User A uploads an image titled "Spring Scenery." At the time of uploading, the emotion engine analyzes User A's current emotion (e.g., joy or excitement) and sends this as metadata to the server. The server confirms that the image is AI-generated and evaluates it according to an evaluation flow specifically for images. The evaluation results are "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Technique: 6 / 10," resulting in an overall evaluation score of "30 / 40." These evaluation results are ranked, and User A can check how "Spring Scenery" is ranked from his or her own device.

[1223] Furthermore, the notification method is optimized based on User A's emotional information, so that, for example, User A will receive a notification that is designed to avoid surprise when receiving the evaluation result. In this way, the system of the present invention accurately and fairly evaluates the AI-generated works uploaded by users and appropriately discloses the evaluation results to the users. By combining the emotion engine, it is possible to improve the user experience and provide a personalized evaluation process.

[1224] The processing flow will be explained below.

[1225] Step 1:

[1226] Users upload AI-generated artworks using their devices. They then select images, music, manga, etc. from a file selection screen via an application or web form. They also enter metadata such as the artwork's name, description, and category.

[1227] Step 2:

[1228] The device sends the uploaded content data and metadata to the server, typically via an HTTP request or API call.

[1229] Step 3:

[1230] The server receives the work data. After receiving it, the server checks the data size and file format (JPEG, PNG, MP3, WAV, etc.) to see if the format is within the allowed range, and generates an error message if the format is invalid.

[1231] Step 4:

[1232] The server stores the received artwork data and metadata in a database, along with additional information such as artwork ID, timestamp, and user information.

[1233] Step 5:

[1234] The server uses an emotion engine to analyze the user's emotions during and after uploading, and records the results as metadata. For example, the emotion engine analyzes the user's facial expressions and tone of voice to determine whether the user is currently "happy" or "nervous."

[1235] Step 6:

[1236] The server analyzes the artwork data and determines whether the artwork is AI-generated. It uses a deep learning model to analyze the artwork's characteristics and outputs a score indicating the likelihood of AI generation.

[1237] Step 7:

[1238] The server automatically classifies the work by format (image, music, manga, etc.), identifies which category the work belongs to, and assigns it to a dedicated evaluation flow.

[1239] Step 8:

[1240] The server executes a dedicated evaluation flow for each format. For example, for image works, it evaluates color balance using a color detection algorithm and composition using face detection technology. For music works, it evaluates melody, rhythm, creativity, and sound quality. For manga works, it evaluates story, character quality, art style, and creativity.

[1241] Step 9:

[1242] The server tally the generated evaluation scores and calculate an overall evaluation score. This is done by adding up or averaging the scores for each evaluation item. For example, for an image work, the evaluation scores for "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Technique: 6 / 10" are combined to calculate an overall evaluation score of "30 / 40."

[1243] Step 10:

[1244] The server compares the overall scores of all works and ranks them, which are recorded in a database in the form of a ranking, and each work is given a rank.

[1245] Step 11:

[1246] The server publishes the evaluation and ranking results to the user. A dedicated web interface or application screen is generated and made accessible to the user. The display of the evaluation result page can be customized based on the user's emotional data analyzed by the emotion engine.

[1247] Step 12:

[1248] Users can check the evaluation results on their own devices. Users can access the evaluation results page via the notification they receive and check how their work was evaluated and how it was ranked.

[1249] Step 13:

[1250] The server sends a notification of the evaluation result to the user. The emotion engine analyzes the user's psychological state and optimizes the notification method, for example, sending a gentle tone notification message if the user is feeling depressed. The notification is delivered to the user via email or in-app notification.

[1251] Example 2

[1252] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1253] When evaluating works generated by AI, it is difficult to obtain fair and accurate evaluations. Furthermore, the lack of personalized evaluations and notifications that take user emotions into account results in a poor user experience. Conventional systems are unable to provide comprehensive evaluations that include emotional information, and lack an appropriate feedback process that utilizes user emotion analysis. As a result, it remains difficult for users to receive evaluations that they are satisfied with.

[1254] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1255] In this invention, the server includes: a means for a user to submit an AI-generated work to a database; a means for the server to classify the submitted work based on its format; a means for the server to analyze the user's emotions using an emotion recognition engine and store the information as metadata; a means for the server to execute a dedicated evaluation flow for each format; a means for the server to compile and rank the evaluation results; and a means for publishing the evaluation results and rankings to the user. This enables personalized evaluations that reflect the user's emotions, providing fair and convincing evaluations. Furthermore, publishing the evaluation results and providing appropriate notification methods can improve the user experience.

[1256] "User" means a person or entity that uses the system to upload AI-generated works and receive evaluation results.

[1257] "Artificial intelligence-generated works" are creative works such as images, music, and comics that are generated using artificial intelligence.

[1258] "Means for sending to the database" refers to a function that allows a user to use their own terminal to send AI-generated works and related metadata to the server.

[1259] The "means for classifying based on format" is an algorithm that the server uses to classify the received works according to their format, such as images, music, comics, etc.

[1260] An "emotion recognition engine" is a software program that analyzes emotions from a user's facial expressions and voice and saves the results as metadata.

[1261] "Metadata" is additional information associated with an AI-generated work, such as the work's name, description, category, and analyzed emotional information.

[1262] The "means for executing the evaluation flow" is a process in which the server evaluates each classified work based on specific evaluation items (for example, color, composition, creativity, technique, etc.).

[1263] The "means for aggregating evaluation results and ranking" is a function that allows the server to aggregate the scores of each evaluation item, calculate a total evaluation score, and rank the works.

[1264] The "means for disclosing to users" refers to a web interface or application that displays the aggregated evaluation results and rankings so that users can check them.

[1265] The system of the present invention allows users to fairly and accurately evaluate works generated by artificial intelligence. The system combines an emotion recognition engine to provide a personalized experience.

[1266] As an example of the system, a program that operates based on the following procedure will be described.

[1267] 1. Upload your work

[1268] Users access the system's upload screen using their own device (e.g., a PC or smartphone). They select an AI-generated work, such as an image, music, or manga, and enter metadata such as the work's name, description, and category. When the user clicks the "Upload" button, the device sends this data to the server. At the same time, the device's camera and microphone are used to capture the user's facial expressions and voice, and an emotion recognition engine (e.g., Microsoft Azure Emotion API or IBM Watson Tone Analyzer) analyzes the user's emotions. The results of this analysis are also sent to the server as metadata.

[1269] 2. Classification of works

[1270] The server receives the artwork data and metadata from the user. Then, using a deep learning model (for example, a model using TensorFlow or PyTorch), the server determines whether the artwork is AI-generated. Once this determination is complete, the server classifies the artwork by type (image, music, manga, etc.) and assigns it to a dedicated evaluation flow for each type.

[1271] 3. Dedicated evaluation flow

[1272] The server will rate each type of work based on the following criteria:

[1273] Image work: color, composition, creativity, technique

[1274] Musical composition: melody, rhythm, creativity, sound quality

[1275] Manga works: Story, character quality, art style, creativity

[1276] For example, the server evaluates the color and composition of the image using color analysis algorithms (e.g., OpenCV), and the creativity and technique are evaluated using pre-trained generative AI models, while the emotion recognition engine continuously acquires real-time emotional data from the user and incorporates this information into the evaluation.

[1277] 4. Calculation and ranking of evaluation results

[1278] The server aggregates the evaluation results for each work. For example, an image may receive scores of "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Technique: 6 / 10." The server then calculates an overall evaluation score of "30 / 40" based on these scores. Based on this, the server ranks all works. The server also takes into account the user's emotional data to adjust the extent to which emotional bias affects the evaluation score.

[1279] 5. Publication and notification of evaluation results

[1280] The server stores the final evaluation results in a database and makes them available through a viewable web interface or application. Users can access and check the evaluation results from their own devices. The server also determines the optimal notification method based on the analysis results of the emotion recognition engine. For example, if the evaluation result is unexpectedly low, the server will send a notification in a way that will not surprise the user.

[1281] Examples and prompts

[1282] For example, suppose User A uploads an image titled "Spring Landscape." At the time of upload, the emotion recognition engine analyzes User A's current emotion (e.g., joy or excitement) and sends the results to the server as metadata. The server then confirms that the image was generated by artificial intelligence and then evaluates it according to an evaluation flow dedicated to images. The evaluation results are "Color: 8 / 10," "Composition: 7 / 10," "Creativity: 9 / 10," and "Technique: 6 / 10," resulting in an overall evaluation score of "30 / 40." These evaluation results are ranked, and User A can check the rank of "Spring Landscape" on his or her own device. In addition, the notification method is optimized based on User A's emotional information, so that, for example, User A is not surprised when he or she receives the evaluation results.

[1283] Prompt Sentence Examples

[1284] 1. "What was the sentiment analysis result when I uploaded an AI-generated image of a spring landscape?"

[1285] 2. Please rate the uploaded image and calculate the overall score.

[1286] 3. "Please explain the optimized notification method based on the evaluation results and user sentiment."

[1287] In this way, the system of the present invention accurately and fairly evaluates AI-generated works uploaded by users and appropriately discloses the evaluation results to users. By combining it with an emotion recognition engine, it is possible to improve the user experience and provide a personalized evaluation process.

[1288] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1289] Step 1:

[1290] Users access the system's upload screen using their own devices, select an AI-generated work such as an image, music, or manga, and enter metadata such as the work's name, description, and category.

[1291] Input: User-selected artwork file, artwork name, description, category, and other metadata

[1292] Output: A data packet containing the input work file and metadata.

[1293] Specific operation: When the user clicks the "Upload" button, the device sends this data to the server. At the same time, the device's camera and microphone are used to capture the user's facial expressions and voice, and the emotion recognition engine analyzes the user's emotions in real time. The analysis results are also sent to the server as metadata.

[1294] Step 2:

[1295] The server receives the work data and metadata received from the user and then uses a deep learning model to determine whether the work is artificial intelligence-generated.

[1296] Input: Submitted work data and metadata

[1297] Output: Work judgment and classification results

[1298] How it works: The server uses a deep learning framework (such as TensorFlow or PyTorch) to check whether the submitted work is AI-generated, then categorizes it by format (e.g., image, music, comics, etc.) and stores it in a directory for each format.

[1299] Step 3:

[1300] The server executes a dedicated evaluation flow for the classified works.

[1301] Input: Classified artwork data

[1302] Output: Score for each evaluation item

[1303] Specific operation: Evaluation is performed for each category using color analysis algorithms (e.g., OpenCV), audio analysis algorithms, story analysis algorithms, etc. Scores are calculated for evaluation items such as color, composition, creativity, and technique. In addition, an emotion recognition engine analyzes the user's real-time emotions during the evaluation, and this emotional information is also reflected in the evaluation.

[1304] Step 4:

[1305] The server compiles the evaluation results for each work and ranks them.

[1306] Input: Scores for each evaluation item, user's emotional information

[1307] Output: Overall evaluation score and ranking results

[1308] Specific operation: The server stores the scores for each evaluation item in a database and calculates an overall evaluation score by aggregating the scores. Each work is ranked based on this overall evaluation score. The server also takes into account the user's emotional information, adjusting the evaluation to avoid bias, especially in subjective evaluation items such as creativity.

[1309] Step 5:

[1310] The server stores the evaluation results in a database, makes them available to users, and notifies them.

[1311] Input: Overall evaluation score and ranking results

[1312] Output: Publishing the evaluation results and rankings, and notifying the user

[1313] Specific operation: The server publishes the evaluation results through a web interface or application. Users can check the evaluation results on their own devices. In addition, the notification method is optimized based on the analysis results of the emotion recognition engine. For example, if the evaluation result is unexpectedly low, a notification message will be sent to avoid surprise.

[1314] In this way, the system of the present invention can accurately and fairly evaluate AI-generated works uploaded by users and appropriately disclose the evaluation results to users. By combining it with an emotion recognition engine, it is possible to improve the user experience and provide a personalized evaluation process.

[1315] (Application example 2)

[1316] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1317] Conventional AI-generated artwork evaluation systems have struggled to provide fair evaluations and a personalized experience. Furthermore, they have been unable to effectively utilize user emotional data, resulting in incomplete subjective evaluations of creative works. The present invention aims to provide a system that improves the user experience by analyzing user emotions and incorporating that data into the evaluation process.

[1318] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a means for a user to upload AI-generated works, a means for the server to classify the uploaded works based on their format, a means for the server to execute a dedicated evaluation flow for each format, a means for acquiring and analyzing user emotional data during the evaluation, a means for complementing the evaluation score based on the acquired emotional data, a means for the server to aggregate and rank the evaluation results, and a means for disclosing the evaluation results and rankings to the user. By reflecting user emotional information in the evaluation process, this enables subjective evaluation of advertising creatives and the like to be performed in a more accurate and personalized manner.

[1319] "User" refers to the individual or entity that uploads and evaluates AI-generated works.

[1320] "AI-generated works" refers to content such as images, music, videos, and comics generated by artificial intelligence or machine learning models.

[1321] "Uploading" refers to the act of sending digital data from a user's device to a server.

[1322] "Server" refers to a computer system that stores, processes, and delivers data.

[1323] "Format" refers to the type or category of work uploaded (e.g., image, music, video, etc.).

[1324] "Evaluation flow" refers to the series of evaluation steps or processes that are carried out on uploaded works.

[1325] "Emotional data" refers to data that measures a user's emotional state (e.g., joy, excitement, surprise, etc.) and expresses it as a numerical value or text.

[1326] "Analysis" is the process of examining collected data and extracting specific information.

[1327] An "evaluation score" is a numerical indicator of the quality of a work, calculated based on multiple evaluation criteria.

[1328] "Aggregation" refers to the act of compiling multiple evaluation results and calculating statistical values ​​such as totals and averages.

[1329] "Ranking" refers to arranging works in order of merit based on their evaluation scores.

[1330] "Publication" refers to the act of providing evaluation results and rankings in a form that is accessible to users.

[1331] "Personalization" refers to optimizing experiences and information based on the individual characteristics and preferences of each user.

[1332] This invention is a system that uses emotional data to provide a more personalized experience when users rate AI-generated works. The system consists of a user terminal, an emotion analysis engine, a server, a rating flow, and a publishing means.

[1333] Hardware and Software Configuration

[1334] 1. On the user's device:

[1335] This includes devices such as smartphones and smart glasses, which allow users to upload AI-generated creations and view evaluation results.

[1336] 2. Sentiment Analysis Engine:

[1337] This software is used for emotion analysis, such as Affectiva and Microsoft Azure Face API, and collects emotion data when users upload and rate.

[1338] 3. Server:

[1339] This is a computer system that manages the evaluation process, stores and processes data, classifies works to be evaluated, generates scores based on each evaluation item, tallying and ranking the results, and publishes the final results.

[1340] Data processing and calculation methods

[1341] 1. Upload:

[1342] AI-generated works (images, videos, music, etc.) are uploaded from the user's device to the server. Metadata includes the work's name, description, and emotional data.

[1343] 2. Classification:

[1344] The server automatically classifies the uploaded works and assigns them to the appropriate evaluation flow depending on their format (images, videos, music, etc.).

[1345] 3. Emotion analysis:

[1346] When users upload their work or receive ratings, a sentiment analysis engine is used to collect real-time emotional data, which directly influences the rating process and is particularly used to complement subjective rating items.

[1347] 4. Evaluation and Scoring:

[1348] The server evaluates each work in each format based on technical criteria (e.g., color, composition, technical ability) and subjective criteria (e.g., creativity, engagement). It also performs a supplementary evaluation based on emotional data, and calculates an overall score by combining the scores for each evaluation item.

[1349] 5. Counting and ranking:

[1350] The evaluation results are compiled and ranked, which determines the ranking of the work compared to other works.

[1351] 6. Publication of evaluation results:

[1352] The final evaluation results are published in an optimal format based on the user's emotional data. Users can view the evaluation results on their own devices, and the notification method is also adjusted based on the emotional data.

[1353] Examples and prompts

[1354] For example, when an ad creator uploads an advertising video for a new fashion brand, the video is classified and evaluated on the server. Emotional data is collected using a smartphone or smart glasses camera while the video is being viewed, and an engagement score and overall evaluation score are calculated based on that data. The ad creator who uploaded the video can check the evaluation results and find out which parts of the ad particularly engaged users.

[1355] Example prompt sentence:

[1356] "Please watch an advertisement video for a new fashion brand and calculate an engagement score based on the user's sentiment analysis data while watching. Store the results in a rating database and return an overall score."

[1357] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1358] Step 1:

[1359] A user uploads an AI-generated work to the system using a terminal. The input is the work file and its metadata (work name, description, emotional data), and the output is the uploaded data sent to the server. This data includes the file itself as well as the metadata entered by the user.

[1360] Step 2:

[1361] The server receives the uploaded work data. The input is the uploaded data sent from the user's device, the server saves the work file and analyzes the metadata. The output is the work's storage and metadata classification information.

[1362] Step 3:

[1363] The server classifies uploaded works based on their format. The input is the work file and its metadata, and the output is the work's category information (e.g., image, video, music). The server determines that the work is AI-generated and assigns it to a dedicated evaluation flow based on its format.

[1364] Step 4:

[1365] When a user uploads a work, the emotion analysis engine acquires and analyzes the user's emotional data. The input is the user's emotional data (real-time facial expression data and voice data), and the output is the emotion analysis result (e.g., joy, excitement, surprise). This value is sent to the server as metadata.

[1366] Step 5:

[1367] The server executes a dedicated evaluation flow for each type of work. The input is the work file and metadata (including emotional data), and the output is a score for each evaluation item (technical and subjective). The server uses a deep learning model to perform technical evaluations (e.g., color, composition) and complements subjective evaluations (e.g., creativity, engagement) with emotional data.

[1368] Step 6:

[1369] The server aggregates the evaluation results and ranks them. The input is the score for each evaluation item, and the output is the overall evaluation score and ranking information. The server statistically aggregates the evaluation results and generates a ranking.

[1370] Step 7:

[1371] The server publishes the evaluation results and rankings to users. The input is the overall evaluation score and ranking information, and the output is the evaluation results published in a form that users can access. Furthermore, the notification method is optimized based on the emotion engine, and users can check the evaluation results on their own devices.

[1372] Step 8:

[1373] Users can check the published evaluation results on their devices and receive feedback. The input is the evaluation results sent from the server, and the output is a visualization of the evaluation content and feedback information. For example, users can see which evaluation items they received high scores for and what kind of feedback they received based on emotional data.

[1374] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1375] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1376] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1377] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1378] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1379] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1380] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1381] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1382] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1383] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1384] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1385] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1386] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1387] 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.

[1388] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1389] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1390] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific processing may be a single processor.

[1391] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1392] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1393] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1394] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1395] The following is further disclosed regarding the above embodiment.

[1396] (Claim 1)

[1397] A means for users to upload AI-generated creations;

[1398] means for the server to classify uploaded works based on format;

[1399] A means for the server to execute a dedicated evaluation flow for each format;

[1400] A means for the server to aggregate and rank the evaluation results;

[1401] a means for disclosing the evaluation results and rankings to users;

[1402] A system including:

[1403] (Claim 2)

[1404] 10. The system of claim 1, wherein the server further comprises means for determining that the uploaded work is AI-generated.

[1405] (Claim 3)

[1406] The system according to claim 1, wherein the server further comprises means for generating a score including evaluation items of color, composition, creativity, and technical aspects in the evaluation flow.

[1407] (Claim 4)

[1408] The system of claim 1, wherein the server further comprises means for generating a score including evaluation items of rhythm, melody, creativity, and sound quality in the evaluation flow.

[1409] (Claim 5)

[1410] The system of claim 1, wherein the server further comprises means for generating a score including each evaluation item of story quality, character quality, art style, and creativity in the evaluation flow.

[1411] (Claim 6)

[1412] 10. The system of claim 1, wherein the server further comprises means for recording the evaluation results in a database.

[1413] (Claim 7)

[1414] 10. The system of claim 1, further comprising means for a user to notify the evaluation result.

[1415] "Example 1"

[1416] (Claim 1)

[1417] A means for users to upload AI-generated creations;

[1418] means for the terminal to transmit metadata of the uploaded work to the server;

[1419] The server uses a deep learning model to verify that the uploaded work is AI-generated; and

[1420] a means for the server to classify works based on format;

[1421] A means for the server to execute a dedicated evaluation flow for each format;

[1422] a means for the server to generate a score based on color, composition, creativity, and technical evaluation criteria;

[1423] A means for the server to aggregate and rank the evaluation results;

[1424] a means for disclosing the evaluation results and rankings to users;

[1425] A system including:

[1426] (Claim 2)

[1427] 10. The system of claim 1, wherein the server further comprises means for determining that the uploaded work is AI-generated.

[1428] (Claim 3)

[1429] 10. The system of claim 1, wherein the server further comprises means for executing the evaluation flow using a color detection algorithm and a face detection technique.

[1430] "Application Example 1"

[1431] (Claim 1)

[1432] A means for users to upload AI-generated creations;

[1433] means for the server to classify uploaded works based on format;

[1434] A means for the server to execute a dedicated evaluation flow for each format;

[1435] A means for the server to aggregate and rank the evaluation results;

[1436] a means for disclosing the evaluation results and rankings to users;

[1437] A means for the server to evaluate AI-generated food images and menus in a food delivery service;

[1438] A means to evaluate AI-generated food images and menus for color, composition, creativity, and delicious appearance;

[1439] A system including:

[1440] (Claim 2)

[1441] 10. The system of claim 1, wherein the server further comprises means for determining that the uploaded work is AI-generated.

[1442] (Claim 3)

[1443] The system according to claim 1, wherein the server further comprises means for generating a score including evaluation items of color, composition, creativity, and technical aspects in the evaluation flow.

[1444] "Example 2: Combining Emotion Engines"

[1445] (Claim 1)

[1446] a means for a user to submit an AI-generated work to the database;

[1447] means for the server to classify the submitted works based on their format;

[1448] A means for the server to analyze the user's emotions using an emotion recognition engine and store the information as metadata;

[1449] A means for the server to execute a dedicated evaluation flow for each format;

[1450] A means for the server to aggregate and rank the evaluation results;

[1451] a means for disclosing the evaluation results and rankings to users;

[1452] A system including:

[1453] (Claim 2)

[1454] 10. The system of claim 1, wherein the server further comprises means for determining that the submitted work is artificial intelligence generated.

[1455] (Claim 3)

[1456] a means for the server to generate a score including evaluation items of color, composition, creativity, and technique in the evaluation flow;

[1457] 2. The system according to claim 1, further comprising means for influencing the evaluation result based on the user's emotional information analyzed using the emotion recognition engine.

[1458] "Application example 2 when combining emotion engines"

[1459] (Claim 1)

[1460] A means for users to upload AI-generated creations;

[1461] means for the server to classify uploaded works based on format;

[1462] A means for the server to execute a dedicated evaluation flow for each format;

[1463] means for acquiring and analyzing user emotion data during the evaluation;

[1464] A means for complementing the evaluation score based on the acquired emotion data;

[1465] A means for the server to aggregate and rank the evaluation results;

[1466] a means for disclosing the evaluation results and rankings to users;

[1467] A system including:

[1468] (Claim 2)

[1469] 10. The system of claim 1, wherein the server further comprises means for determining that the uploaded work is AI-generated.

[1470] (Claim 3)

[1471] The system according to claim 1, wherein the server further comprises means for generating a score including evaluation items of color, composition, creativity, and technical aspects in the evaluation flow. [Explanation of symbols]

[1472] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for users to upload AI-generated creations; means for the server to classify uploaded works based on format; A means for the server to execute a dedicated evaluation flow for each format; A means for the server to aggregate and rank the evaluation results; a means for disclosing the evaluation results and rankings to users; A system including:

2. The system of claim 1 , wherein the server further comprises means for determining that the uploaded work is AI-generated.

3. The system according to claim 1 , wherein the server further comprises means for generating a score including evaluation items of color, composition, creativity, and technical aspects in the evaluation flow.

4. The system according to claim 1 , wherein the server further comprises means for generating a score including evaluation items of rhythm, melody, creativity, and sound quality in the evaluation flow.

5. The system according to claim 1, wherein the server further comprises means for generating a score including evaluation items of story quality, character quality, art style, and creativity in the evaluation flow.

6. The system of claim 1, wherein the server further comprises means for recording the evaluation results in a database.

7. The system of claim 1 further comprising means for a user to notify the evaluation result.

Images