System

Abstract

A system is provided.SOLUTION: A system for assessing the risk of copyright infringement of an image for commercial use, comprising: means for a user to upload an image to be assessed; means for receiving and initially processing the uploaded image; means for feature extraction using an artificial intelligence model to extract visual features from the image; means for matching the extracted features with an existing database and assessing the match or similarity; means for determining the copyright risk of the image based on the assessment; and means for notifying the user of the determination.SELECTED DRAWING: Figure 1

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] With the spread of the Internet and advances in artificial intelligence technology, the risk of unauthorized use of images is increasing. In particular, the risk of copyright infringement when using images for commercial purposes is becoming a serious problem for corporations and individual businesses. Conventional methods require time and effort to assess the risk of copyright infringement of commercial images, and the accuracy of the assessment is limited. There is a need for a system that can solve this problem and enable users to easily and quickly assess the copyright risk of images. [Means for solving the problem]

[0005] The present invention is a system for assessing the risk of copyright infringement of images for commercial use. The system includes the following means: a means for a user to upload images to be assessed; a means for receiving the uploaded images and performing initial processing; a means for extracting visual features from the images using an artificial intelligence model; a means for comparing the extracted features with an existing database and evaluating the degree of match or similarity; a means for determining the copyright risk of the images based on the assessment results; and a means for notifying the user of the assessment results. This system allows users to quickly and accurately assess the copyright risk of commercial images, thereby reducing business risk.

[0006] "Commercial Use" means the use of an Image for a commercial purpose.

[0007] "User" means any person or entity that uses the System to assess the copyright risk of Images.

[0008] "Image to be evaluated" refers to the image file for which you wish to diagnose the risk of copyright infringement.

[0009] "Means of uploading" refers to the method or process by which a user submits images to the system for evaluation.

[0010] "Initial processing" refers to preprocessing such as checking the format and resizing of image files received by the system.

[0011] "Artificial intelligence model" refers to an algorithm or system that uses machine learning or deep learning techniques to analyze and extract visual features.

[0012] "Feature extraction method" refers to a method of analyzing visual features such as color, shape, and texture from an image using an AI model and extracting them as data in a specific format.

[0013] "Database" refers to the collection of information in a system in which non-commercially available images and copyright-related information are stored.

[0014] "Matching" refers to the process of comparing extracted features with existing data in a database to identify matching or similar items.

[0015] "Copyright risk" refers to the possibility that concerns about copyright infringement may arise when using an image commercially.

[0016] "Means of determination" refers to the process of evaluating whether or not an image can be used commercially based on the results of database matching and making a final decision.

[0017] "Means of notification" refers to the method or process by which the system communicates the evaluation results to the user. [Brief explanation of the drawings]

[0018] [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

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] 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).

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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."

[0039] The present invention provides a system for assessing the risk of copyright infringement of images for commercial use, which includes a means for allowing a user to upload images to be assessed, a means for receiving the uploaded images and performing initial processing, a means for extracting visual features from the images using an artificial intelligence model, a means for comparing the extracted features with an existing database and assessing the degree of match or similarity, a means for determining the copyright risk of the images based on the assessment results, and a means for notifying the user of the assessment results.

[0040] A specific embodiment of this system is described below.

[0041] System Operation Overview

[0042] 1. User image upload

[0043] The user accesses the interface provided through a web browser, selects and uploads an image to be evaluated, and the user's device acquires the path of this image file and sends it to the system.

[0044] 2. Server Reception and Initial Processing

[0045] The server receives the image file sent from the user's device. During this process, the server checks the format of the image file and compresses or converts the image if necessary. For example, if the image is too large, it is compressed and converted into a usable format (e.g., JPEG).

[0046] 3. Feature extraction using AI models

[0047] The server inputs the received image into an AI model to extract visual features. The AI ​​model uses deep learning techniques to analyze visual information such as color, shape, and texture in the image. The resulting feature vector is used for subsequent database matching.

[0048] 4. Checking existing databases

[0049] The server compares the extracted feature vector with an existing image database, which stores images that are prohibited for commercial use and copyright information. The server performs a search using the feature vector as a key to identify matching or similar images.

[0050] 5. Copyright Risk Assessment

[0051] The server determines the copyright risk of the image being evaluated based on the results of the database match. If an identical or highly similar image is found, the image is deemed unsuitable for commercial use. If there is no match or high similarity, the image is deemed suitable for commercial use.

[0052] 6. Output and notification of results

[0053] The server generates the copyright risk assessment results and notifies the user's device. The user can then check the results on their device's web browser. For example, the results may include messages such as "This image may be used for commercial purposes" or "This image may infringe copyright, so please avoid using it for commercial purposes."

[0054] Specific examples

[0055] Example 1: Rating images for non-commercial use

[0056] Users upload images for inclusion on their websites.

[0057] Images received by the server undergo feature extraction through an artificial intelligence model.

[0058] The extracted features are found to have a high degree of similarity to known non-commercial images in the database.

[0059] The server determines that "this image poses a risk of copyright infringement, so please avoid using it for commercial purposes," and notifies the user of the result.

[0060] Example 2: Rating images for commercial use

[0061] Users upload images for use in marketing materials.

[0062] The server extracts features from the received image and compares them with an existing database.

[0063] It is determined that there are no images in the database that have a match or a high degree of similarity.

[0064] The server determines that "this image can be used commercially" and notifies the user of the result.

[0065] In this way, by using the system of the present invention, users can easily and quickly evaluate the copyright risk of images and determine whether or not they can be used commercially.

[0066] The processing flow will be explained below.

[0067] Step 1:

[0068] A user accesses the application and clicks the "Upload Image" button. The user selects an image file to be evaluated and starts uploading. The user's device obtains the path of the selected image file and inserts the file into the upload stream.

[0069] Step 2:

[0070] The server receives the image file sent from the user's device. The server checks the format of the image file and compresses or converts the image as necessary. For example, images that are too large will be compressed, and images in an unsupported format (such as BMP or GIF) will be converted to JPEG format.

[0071] Step 3:

[0072] The server inputs the received image into an artificial intelligence model to extract visual features. The server uses a deep learning model (e.g., CNN) to analyze visual information such as the image's color, shape, and texture. As a result of the analysis, a feature vector is generated and used for subsequent processing.

[0073] Step 4:

[0074] The server compares the extracted feature vector with an existing image database, which stores images that are not for commercial use and copyright-related information. The server then searches the database using the feature vector as a key to identify images that match or have a high degree of similarity.

[0075] Step 5:

[0076] The server determines the copyright risk of the image being evaluated based on the results of the database comparison. If the server finds a match or a high degree of similarity, it determines that the image cannot be used commercially. Conversely, if the server finds no match or high degree of similarity, it determines that the image can be used commercially.

[0077] Step 6:

[0078] The server notifies the user's device of the risk assessment results it has generated. The server then sends the assessment results to the user's device as an HTTP response, sending the results in JSON format or similar. The user can then check the assessment results on their own device's web browser.

[0079] Step 7:

[0080] The user checks the evaluation results sent from the server on the web application interface. The user's device receives the response from the server and displays it to the user in an appropriate format. For example, it displays specific content such as "This image can be used for commercial purposes" or "Please avoid using this image for commercial purposes as there is a risk of copyright infringement."

[0081] Example 1

[0082] 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."

[0083] Previous image copyright risk assessment systems had problems with low assessment accuracy and lacked reliability for commercial use. Furthermore, they lacked sufficient use of AI models to extract visual features and compare them with databases, resulting in a high likelihood of false positives. This made it difficult for companies and individuals to make appropriate decisions to avoid the risk of copyright infringement.

[0084] 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.

[0085] In this invention, the server includes means for users to upload images to be evaluated, means for receiving the uploaded images and performing initial processing, means for extracting visual features from the images using an artificial intelligence model, means for comparing the extracted features with an existing database and evaluating the degree of match or similarity, means for determining the copyright risk of the images based on the evaluation results, and means for notifying the user of the determination results. This makes it possible to evaluate the copyright risk of images with high accuracy and quickly and accurately determine whether or not they can be used commercially.

[0086] "User" means any person or entity that uses the System to assess the copyright risk of Images.

[0087] "Upload" refers to the act of a user sending an image file to be evaluated to the system.

[0088] "Receiving" refers to the act of the server receiving the image file sent by the user.

[0089] "Initial processing" refers to the process of performing preprocessing such as format confirmation, compression, and format conversion of received images.

[0090] "Visual features" refers to the characteristic information of an image, such as color, shape, or texture, extracted through a deep learning model.

[0091] "Artificial intelligence model" refers to a mathematical and computational structure for extracting visual features using deep learning techniques.

[0092] A "feature vector" refers to data that numerically represents visual features extracted by an artificial intelligence model.

[0093] "Matching" refers to the process of comparing the extracted feature vectors with those in an existing database.

[0094] "Database" means a data storage facility for storing uncommercially protected images and associated copyright information.

[0095] "Match" refers to the state where the extracted feature vector is exactly the same as the feature vector in the database.

[0096] "Similarity" refers to a measure that numerically indicates how similar the extracted feature vector is to the feature vector in the database.

[0097] "Evaluation Results" refers to the results report for determining the copyright risk of an image.

[0098] "Notification" refers to the act of informing the user of the evaluation results.

[0099] This invention is a system for assessing the risk of copyright infringement of images for commercial use. This system allows users to upload images to be assessed, and then goes through a series of processes to extract, match, and assess visual features from the images, and finally notifies users of the assessment results.

[0100] System Configuration

[0101] 1. User image upload

[0102] The user accesses the interface provided through a web browser, selects an image to be evaluated, and uploads the image along with the prompt, "Please evaluate the risk of commercial use." At this time, the user's device obtains the path to the image file and sends the image data to the server.

[0103] 2. Server Reception and Initial Processing

[0104] The server receives the image file sent from the user's device. After receiving it, the server checks the image format and converts it to the appropriate format. Specifically, it uses an image processing library such as OpenCV to convert it to JPEG format and compress the size.

[0105] 3. Feature extraction using AI models

[0106] The server then inputs the received images into an AI model to extract visual features. This AI model uses deep learning frameworks such as TensorFlow and PyTorch to analyze features such as color, shape, and texture in the image. The resulting feature vector is used in the next stage of the matching process.

[0107] 4. Matching with existing databases

[0108] The server then matches the extracted feature vectors with an existing image database. Using similarity measures such as Cosine Similarity and Euclidean Distance, the server compares the extracted feature vectors with known non-commercial images and copyright-related information in the database. The database contains feature vectors of non-commercial images, and images with high similarity are identified.

[0109] 5. Copyright Risk Assessment

[0110] The server determines the copyright risk of the image being evaluated based on the results of the database comparison. If a match or high similarity is confirmed, the image is deemed not suitable for commercial use. Conversely, if no match or high similarity is confirmed, the image is deemed suitable for commercial use. As a criterion for evaluation, a threshold is considered, such as a similarity of 0.9 or higher being considered a high risk.

[0111] 6. Notification of Results

[0112] The server generates the results of the copyright risk assessment and notifies the user with specific messages such as "This image can be used for commercial purposes" or "This image may infringe copyright, so please avoid using it for commercial purposes." The user can then check the results on their own device.

[0113] Specific examples

[0114] Example 1: Rating images for non-commercial use

[0115] Users upload images for use on their websites, along with a prompt to "assess the risk of commercial use."

[0116] The server converts the format of the received images and performs feature extraction through an artificial intelligence model.

[0117] The server compares the extracted feature vectors with an existing database, and non-commercial images with high similarity are identified.

[0118] The server generates an evaluation result saying, "This image may infringe copyright, so please avoid using it for commercial purposes," and notifies the user.

[0119] Example 2: Evaluating images for commercial use

[0120] Users upload images for use in ads, along with a prompt to "assess the risk of commercial use."

[0121] The server converts the format of the received image and then extracts features using an artificial intelligence model.

[0122] The match does not identify a match or a highly similar image in the database.

[0123] The server generates an evaluation result that says "This image can be used commercially," and notifies the user.

[0124] In this way, by implementing this system, users can easily evaluate the copyright risk of images and quickly and accurately determine whether or not they can be used commercially.

[0125] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0126] Step 1: User uploads an image

[0127] A user accesses the system interface using a web browser and selects an image file to be evaluated. The user can also enter a prompt such as "Please evaluate the risk of commercial use." The user's device obtains the path of the selected image file and sends a request containing the image data to the server. The input is the image file, and the output is a request to the server.

[0128] Step 2: The server receives the image and performs some initial processing.

[0129] The server receives image files sent from the user's device. After receiving the image, the server checks the image format and converts it to the appropriate format if necessary. Specifically, it uses the OpenCV library to convert the image format to JPEG and compresses it if the size is too large. The input is the received image file, and the output is the processed and converted image file.

[0130] Step 3: The server uses the AI ​​model to extract features

[0131] The server inputs the initially processed image into a deep learning model to extract visual features. This artificial intelligence model uses TensorFlow and PyTorch to analyze features such as color, shape, and texture in the image. Specifically, the image is input into the model and a feature vector is obtained as the output. The input is the initially processed image file, and the output is the feature vector.

[0132] Step 4: The server checks against the existing database

[0133] The server compares the feature vector with an existing image database. In this step, it uses Cosine Similarity or Euclidean Distance to measure the similarity with the feature vector in the database. The database contains non-commercial images and copyright information, and it determines whether the feature vector matches or has a high similarity with them. The input is the extracted feature vector, and the output is a result indicating a match or a high similarity in the database.

[0134] Step 5: Server assesses copyright risk

[0135] The server determines the copyright risk of the image based on the matching results. For example, if the similarity is 0.9 or higher, it is considered a high risk, and if it is below that, it is considered a low risk. The input is the result of matching with the database, and the output is the copyright risk assessment result. A judgment is made as to whether the image is "commercially usable" or "not for commercial use."

[0136] Step 6: The server notifies the user of the evaluation results

[0137] The server generates the evaluation result and notifies the user's device. The notification is made via a web browser interface, displaying a message such as "This image can be used for commercial purposes" or "This image may infringe copyright, so please avoid using it for commercial purposes." The input is the copyright risk evaluation result, and the output is the notification message displayed to the user.

[0138] (Application example 1)

[0139] 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."

[0140] In recent years, the use of images on the Internet has increased, and the risk of copyright infringement in commercial use of images has become a serious issue. Advertising agencies and marketers, in particular, must quickly evaluate a large number of image materials, and in doing so, they are required to quickly and accurately determine the copyright risk of images. However, current manual checking methods are time-consuming, labor-intensive, and inefficient. To address this issue, the present invention aims to provide a system for evaluating the copyright risk of images used for advertising management in real time.

[0141] 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.

[0142] In this invention, the server includes means for users to upload images to be evaluated, means for receiving the uploaded images and performing initial processing, feature extraction means using an artificial intelligence model to extract visual features from the images, means for comparing the extracted features with an existing database and evaluating the degree of match or similarity, means for determining the copyright risk of the images based on the evaluation results, means for notifying the user of the determination results, and means for uploading images via a smartphone for advertising management and evaluating the copyright risk in real time. This enables users to quickly evaluate the copyright risk of images to be used as advertising material and immediately determine whether or not they can be used commercially.

[0143] "User" means a person or entity that uploads images to the system and receives the results of a copyright risk assessment.

[0144] An "image to be evaluated" is an image file uploaded by a user for commercial use.

[0145] "Upload" refers to the act of a user sending an image to be evaluated to the online system.

[0146] "Initial processing" is a series of processes that check the format of the received image and compress and convert it.

[0147] "Visual features" refer to information such as color, shape, and texture within an image, and are extracted using artificial intelligence.

[0148] An "artificial intelligence model" is an algorithm or system that uses deep learning technology to analyze visual features.

[0149] "Feature extraction means" refers to technical means or tools for extracting visual features from an image.

[0150] An "existing database" is an information collection that stores image data collected in the past and its copyright information.

[0151] "Matching" is the act of comparing extracted visual features with an existing database to evaluate the degree of match or similarity.

[0152] "Similarity" is a measure of the visual match between an image and an existing image in a database.

[0153] The "evaluation result" is the copyright risk assessment result derived based on the matching of visual features.

[0154] "Copyright risk" refers to the degree of likelihood that the image being evaluated constitutes copyright infringement.

[0155] "Notification" refers to the act of informing the user of the evaluation results.

[0156] "For advertising management" refers to the purpose of managing and evaluating images used as advertising materials.

[0157] A "smartphone" is a portable communication device that can connect to the Internet and use multi-function applications.

[0158] "Real-time" means that the time from when a user uploads an image to when the evaluation result is notified is extremely short, and processing is immediate.

[0159] The present invention provides a system for evaluating the copyright risk of images in real time, specially designed for advertising management, which mainly uses a server, a smartphone terminal, and an artificial intelligence (AI) model.

[0160] Overall system configuration

[0161] The system includes the following main components:

[0162] 1. User terminal: A smartphone is used, providing a means for users to upload images as advertising materials.

[0163] 2. Server: Receives uploaded images, performs initial processing, extracts visual features, matches them with databases, assesses copyright risk, and notifies the results.

[0164] 3. Artificial intelligence model: Deep learning techniques are used to analyze visual features in images.

[0165] Program processing overview

[0166] 1. User image upload

[0167] The user uses a dedicated smartphone application to select an image to be evaluated and upload it to the system, which obtains the image's file path and sends it to the server.

[0168] 2. Server Reception and Initial Processing

[0169] The server receives the image file sent from the user terminal. It checks the format of the received image file and performs image compression or format conversion as necessary. For example, it converts the image to JPEG format or compresses the image size.

[0170] 3. Feature extraction using AI models

[0171] The server inputs the processed image into an artificial intelligence model to extract visual features. This model uses ResNet50, built using TensorFlow, which extracts visual features such as color, shape, and texture from the image as vectors.

[0172] 4. Matching with existing databases

[0173] The server compares the extracted feature vector with an existing image database. For comparison, it uses the cosine_similarity function from the scikit-learn library to calculate the similarity to images in the database. If the highest similarity exceeds a predetermined threshold, it is determined to have a high copyright risk.

[0174] 5. Copyright Risk Assessment and Notification of Results

[0175] The server evaluates the copyright risk of the image based on the results of the database comparison. The evaluation results are sent to the user's smartphone in real time. The user can then check the results, such as "There is a risk of copyright infringement" or "Commercial use is permitted," via a dedicated application.

[0176] Hardware and software used

[0177] Hardware: Smartphones, servers

[0178] software:

[0179] TensorFlow: Used to implement the artificial intelligence model (ResNet50) and extract features

[0180] Pillow: Used for initial image processing (format conversion and resizing)

[0181] scikit-learn: Used to compare similarity between feature vectors (cosine_similarity)

[0182] Specific examples

[0183] Example 1: Marketer use case

[0184] Marketers upload images to be used as advertising materials for new products from their smartphones, and the images are evaluated through an AI model, which immediately informs them that they are "suitable for commercial use."

[0185] Example 2: Advertising agency use case

[0186] Advertising agencies use a smartphone application to simultaneously evaluate multiple advertising materials. The application allows users to upload images in bulk, and the server evaluates the copyright risk of each image and notifies users of the results individually.

[0187] Prompt Sentence Examples

[0188] Upload a new image "example.jpg" as advertising material and assess its copyright risk.

[0189] Run the assessment and view the results.

[0190] Specify the file path:

[0191] file_path = "example.jpg"

[0192] main(file_path)

[0193] In this way, by using the system of the present invention, users can easily evaluate the copyright risk of advertising materials and quickly determine whether or not they can be used commercially.

[0194] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0195] Step 1:

[0196] The user selects an image to be evaluated as advertising material and uploads it to the system through a smartphone application. Specifically, the user uses the app's interface to select an image from the device's storage and clicks the upload button. This step inputs the selected image file. The app then sends this image file to the server.

[0197] Step 2:

[0198] The server receives image files sent from the user device and performs initial processing. It checks the format of the received image file, converts it to JPEG format if necessary, and compresses the image size. Specifically, it uses the Pillow library to convert the image format and resize it. The input is the image data sent from the smartphone, and the output is the image data after initial processing has been completed.

[0199] Step 3:

[0200] The server inputs the pre-processed image into an artificial intelligence model to extract visual features. Specifically, it uses a ResNet50 model built using TensorFlow to extract visual information such as the image's color, shape, and texture as a feature vector. The input at this stage is the pre-processed image data, and the output is the extracted visual feature vector.

[0201] Step 4:

[0202] The server compares the extracted feature vector with an existing database. Specifically, it calculates the similarity between the extracted feature vector and an existing image in the database using the cosine_similarity function in the scikit-learn library. The input is the visual feature vector and the feature vector in the database, and the output is a similarity score.

[0203] Step 5:

[0204] The server evaluates copyright risk based on the results of database matching. If the similarity score exceeds a predetermined threshold, the image is deemed to have a high risk of copyright infringement. The input is the similarity score, and the output is the copyright risk assessment result. Specifically, it generates an assessment result such as "There is a risk of copyright infringement" or "Commercial use is permitted."

[0205] Step 6:

[0206] The server notifies the user of the results of the copyright risk assessment via their smartphone. Specifically, the assessment results are sent to a dedicated application and displayed to the user as a notification message. The input is the copyright risk assessment result, and the output is a notification message sent to the user's device. The user can then check the results to determine whether or not the advertising material can be used commercially.

[0207] In this way, users can easily use their smartphones to evaluate the copyright risks of advertising materials and make appropriate usage decisions.

[0208] 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.

[0209] The present invention combines a system for assessing the risk of copyright infringement of images for commercial use with an emotion engine that recognizes user emotions. This system includes the following means: a means for a user to upload images to be assessed, a means for receiving the uploaded images and performing initial processing, a feature extraction means using an artificial intelligence model to extract visual features from the images, a means for comparing the extracted features with an existing database and assessing their match or similarity, a means for determining the copyright risk of the images based on the assessment results, a means for notifying the user of the assessment results, and an emotion engine that recognizes user emotions.

[0210] A specific embodiment of this system is described below.

[0211] System Operation Overview

[0212] 1. User image upload

[0213] The user accesses the interface provided through a web browser, selects and uploads the image file to be evaluated, and the user's device acquires the path of this image file and sends it to the system.

[0214] 2. Server Reception and Initial Processing

[0215] The server receives the image file sent from the user's device. The server checks the format of the image file and compresses or converts the image as necessary. For example, images that are too large will be compressed, and images in an unsupported format (such as BMP or GIF) will be converted to JPEG format.

[0216] 3. Feature extraction using AI models

[0217] The server inputs the received image into an artificial intelligence model to extract visual features. The server uses a deep learning model (e.g., CNN) to analyze visual information such as the image's color, shape, and texture. As a result of the analysis, a feature vector is generated and used for subsequent processing.

[0218] 4. Checking existing databases

[0219] The server compares the extracted feature vector with an existing image database, which stores images that are not for commercial use and copyright-related information. The server performs a database search using the feature vector as a key to identify images that match or have a high degree of similarity.

[0220] 5. Copyright Risk Assessment

[0221] The server determines the copyright risk of the image being evaluated based on the results of the database comparison. If the server finds a match or a high degree of similarity, it determines that the image cannot be used commercially. Conversely, if the server finds no match or high degree of similarity, it determines that the image can be used commercially.

[0222] 6. Recognition of user emotions by emotion engine

[0223] The device uses the user's camera and microphone to enable the emotion engine to recognize the user's emotions in real time. The emotion engine uses facial expression analysis and tone of voice analysis to determine whether the user is in an emotional state such as excitement, joy, or anger.

[0224] 7. Result output and emotional notifications

[0225] When the server notifies the user of the generated evaluation results, it changes the notification method based on the recognition results of the emotion engine. For example, if the user is feeling stressed, it will notify the result in gentler terms, and conversely, if the user is excited, it will notify them in a more concise manner.

[0226] Users can check the evaluation results on their own devices in a web browser, which may display a message such as "This image can be used for commercial purposes" or "Please avoid using this image for commercial purposes as there is a risk of copyright infringement."

[0227] Specific examples

[0228] Example 1: Rating and responding to sentiment for images that are not suitable for commercial use

[0229] Users upload images for inclusion on their websites.

[0230] Images received by the server undergo feature extraction through an artificial intelligence model.

[0231] The extracted features are found to have a high degree of similarity to known non-commercial images in the database.

[0232] The server determines that "this image poses a risk of copyright infringement, so please avoid using it for commercial purposes," and notifies the user of the result.

[0233] The user's device uses a camera and microphone to allow the emotion engine to recognize the user's emotions and determine whether they are feeling stressed.

[0234] The server notifies the user of the evaluation results in gentle language designed to reduce stress.

[0235] Example 2: Ratings and positive emotional responses for commercially available images

[0236] Users upload images for use in marketing materials.

[0237] The server extracts features from the received image and compares them with an existing database.

[0238] It is determined that there are no images in the database that have a match or a high degree of similarity.

[0239] The server determines that "this image can be used commercially" and notifies the user of the result.

[0240] The user's device recognizes the user's emotions through an emotion engine and detects the emotion of joy.

[0241] The server notifies the user of the evaluation results in simple and positive terms.

[0242] In this way, by using the system of the present invention, it is possible to efficiently evaluate the copyright risk of commercial images and to provide notifications that take into consideration the user's feelings.

[0243] The processing flow will be explained below.

[0244] Step 1:

[0245] A user accesses the application and clicks the "Upload Image" button. The user selects an image file to be evaluated and starts uploading. The user's device obtains the path of the selected image file and inserts the file into the upload stream.

[0246] Step 2:

[0247] The server receives the image file sent from the user's device. The server checks the format of the image file and compresses or converts the image as necessary. For example, an image that is too large will be compressed, or if the format is not supported, it will be converted to JPEG format.

[0248] Step 3:

[0249] The server inputs the received image into an artificial intelligence model to extract visual features. The server uses a deep learning model to analyze the image's visual information, such as color, shape, and texture. As a result of the analysis, a feature vector is generated.

[0250] Step 4:

[0251] The server compares the extracted feature vector with an existing image database, which stores images that are not for commercial use and copyright-related information. The server then searches the database using the feature vector as a key to identify images that match or have a high degree of similarity.

[0252] Step 5:

[0253] The server determines the copyright risk of the image being evaluated based on the results of the database comparison. If the server finds a match or a high degree of similarity, it determines that the image cannot be used commercially. Conversely, if the server finds no match or high degree of similarity, it determines that the image can be used commercially.

[0254] Step 6:

[0255] The device uses the user's camera and microphone to enable the emotion engine to recognize the user's emotions in real time. The emotion engine uses facial expression analysis and tone of voice analysis to determine whether the user is in an emotional state such as excitement, joy, or anger.

[0256] Step 7:

[0257] The server changes the notification method based on the recognition results of the emotion engine. For example, if the user is feeling stressed, the server notifies the user in a gentle manner, whereas if the user is excited, the server notifies the user in a concise manner.

[0258] Step 8:

[0259] The server notifies the user's device of the evaluation results it has generated. The server then sends the results to the user's device as an HTTP response in JSON format or similar. The user can then check the evaluation results on their device's web browser.

[0260] Step 9:

[0261] The user checks the evaluation results sent from the server on the web application interface. The user's device receives the response from the server and displays it to the user in an appropriate format. For example, it displays specific content such as "This image can be used for commercial purposes" or "Please avoid using this image for commercial purposes as there is a risk of copyright infringement."

[0262] Example 2

[0263] 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."

[0264] In assessing the copyright risk of images intended for commercial use, existing systems have the problem of being unable to accurately assess the copyright risk of images and not giving consideration to the user's feelings when notifying them. In particular, not taking the user's feelings into consideration when notifying them of the copyright risk assessment results can cause unnecessary stress and confusion for the user.

[0265] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving uploaded images and performing initial processing, feature extraction means using an artificial intelligence model to extract visual features from the images, means for comparing the extracted features with an existing database and evaluating the degree of match or similarity, means for determining the copyright risk of the images based on the evaluation results, means for notifying the user of the evaluation results, and an emotion engine for recognizing the user's emotions and adjusting the method of notifying the evaluation results. This not only enables efficient and accurate evaluation of the copyright risk of images, but also enables appropriate notification that takes the user's emotions into consideration.

[0266] "User" refers to a user who uses the system to upload images and have them assessed for copyright risk.

[0267] "Server" refers to a computer system that receives images sent from a user's terminal and is responsible for all processing, including initial processing, feature extraction, database matching, and notification of evaluation results.

[0268] "Terminal" refers to a device accessed by a user, including a web browser and related hardware devices for uploading images and checking evaluation results.

[0269] "Image" refers to the visual data to be evaluated that users upload to the system, and includes common image formats such as JPEG and PNG.

[0270] "Visual features" are information extracted from an image, including color, shape, texture, and other attributes necessary for image recognition and feature vector generation.

[0271] "Artificial intelligence model" refers to an algorithm or network model used to extract visual features using deep learning techniques, including convolutional neural networks (CNNs).

[0272] "Database" refers to an information system that stores existing image data and associated copyright information against which extracted feature vectors can be matched.

[0273] A "feature vector" is a data set that quantifies the visual features of an image, and is used for matching with a database and evaluating similarity.

[0274] "Emotion engine" refers to the algorithms and software modules used to recognize a user's emotions, analyzing data acquired through the camera and microphone.

[0275] The "evaluation result" is a conclusion generated based on the copyright risk assessment, and is notified to the user in the form of "Commercial use is permitted" or "Commercial use should be avoided."

[0276] The "notification method" refers to the means or format for notifying the user of the evaluation results, and is adjusted according to the user's emotional state.

[0277] The present invention is a system for assessing the risk of copyright infringement of images intended for commercial use, which is combined with an emotion engine that recognizes user emotions. This system includes the following means: a means for a user to upload an image to be assessed, a means for receiving the uploaded image and performing initial processing, a feature extraction means using an artificial intelligence model to extract visual features from the image, a means for comparing the extracted features with an existing database and evaluating the degree of match or similarity, a means for determining the copyright risk of the image based on the assessment result, a means for notifying the user of the assessment result, and an emotion engine that recognizes user emotions.

[0278] System Operation Overview

[0279] 1. User image upload

[0280] The user accesses the interface provided through a web browser, selects and uploads the image file to be evaluated, and the user's device obtains the path of this image file and sends it to the system.

[0281] 2. Server Reception and Initial Processing

[0282] The server receives the image file sent from the terminal. After receiving it, it checks the format of the image file and compresses or converts the image as necessary. For example, large images are compressed, and images in unsupported formats (such as BMP or GIF) are converted to JPEG format.

[0283] 3. Feature extraction using AI models

[0284] The server inputs the received image into an artificial intelligence model (e.g., CNN) using deep learning technology to extract visual features. The analyzed feature vectors are used for database matching.

[0285] 4. Checking existing databases

[0286] The server uses the feature vector as a key to match existing image data and associated copyright information in a database that stores images and copyright information that are not for commercial use.

[0287] 5. Copyright Risk Assessment

[0288] The server determines the copyright risk of the image being evaluated based on the results of the database comparison. If a high degree of similarity is found, the image is deemed "unsuitable for commercial use," but if the match or similarity is low, it is deemed "available for commercial use."

[0289] 6. Recognition of user emotions by emotion engine

[0290] The device uses a camera and microphone to capture the user's facial expressions and tone of voice in real time, and analyzes the captured data with an emotion engine (e.g., Microsoft Azure's Emotion API) to determine the user's emotional state (e.g., excitement, joy, anger, stress).

[0291] 7. Result output and emotional notifications

[0292] The server generates an evaluation result and sends it to the device in a format that corresponds to the user's emotional state based on the judgment of the emotion engine. For example, if the user is feeling stressed, the server will notify them in gentle words, and if the user is excited, the server will notify them in a concise manner.

[0293] Users can check the evaluation results on their device in a web browser, which will display messages such as "Commercial use is permitted" or "Please avoid commercial use due to the risk of copyright infringement."

[0294] Specific examples

[0295] Example 1: Rating and responding to sentiment for images that are not suitable for commercial use

[0296] Users upload images for inclusion on their websites.

[0297] The image received by the server undergoes feature extraction through an artificial intelligence model.

[0298] The extracted features are found to have a high degree of similarity to known non-commercial images in the database.

[0299] The server determines that "This image poses a risk of copyright infringement, so please avoid using it for commercial purposes," and notifies the user of the result.

[0300] The user's device uses a camera and microphone to allow the emotion engine to recognize the user's emotions and determine whether they are feeling stressed.

[0301] The server will notify you of the evaluation results in gentle language.

[0302] Example 2: Ratings and positive emotional responses for commercially available images

[0303] Users upload images for use in marketing materials.

[0304] The server extracts features from the received image and compares them with an existing database.

[0305] It is determined that there are no images in the database that have a match or a high degree of similarity.

[0306] The server determines that "this image can be used commercially" and notifies the user of the result.

[0307] The user's device recognizes the user's emotions through an emotion engine and detects the emotion of joy.

[0308] The server will notify you of the evaluation results in simple and positive terms.

[0309] Prompt Sentence Examples

[0310] Example 1: A user who uploads a non-commercial image experiences frustration

[0311] "Please rate whether this image is safe for commercial use."

[0312] Example 2: A user expresses joy by uploading an image that can be used commercially.

[0313] "Can I use this image in my marketing materials?"

[0314] In this way, by using the system of the present invention, it is possible to efficiently evaluate the copyright risk of commercial images and provide notifications that take into consideration the user's feelings.

[0315] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0316] Processing steps of this system's program

[0317] Step 1: Upload user image

[0318] The user accesses a web browser, selects the image file to be evaluated, and clicks the upload button. The image file path selected by the user is obtained as input. Based on this path, the terminal sends the image file to the system. Specifically, the image file is sent to the server via an HTTP POST request.

[0319] Step 2: Server reception and initial processing

[0320] The server receives image files sent from the terminal. As input, the image file data arrives at the server. The server checks the format of the image file and compresses or converts the image as necessary. For example, files in a format other than JPEG are converted to JPEG, and files that are too large are compressed. As output, the image file data after initial processing is obtained.

[0321] Step 3: Feature extraction using an AI model

[0322] The server inputs the received image into an artificial intelligence model (such as CNN) that uses deep learning technology. An initially processed image file is obtained as input. The server analyzes this image and extracts visual features (color, shape, texture, etc.) as a feature vector. Specific examples include using TensorFlow or PyTorch. The feature vector is obtained as output.

[0323] Step 4: Check the existing database

[0324] The server compares the feature vector with an existing image database. The input is the feature vector. The server searches the database using an SQL query to identify image data that matches or has a high degree of similarity. The output is the matching result.

[0325] Step 5: Copyright Risk Assessment

[0326] The server determines the copyright risk of the image being evaluated based on the database match results. The database match results are received as input. The server determines the risk level using a rule-based or machine learning model. The copyright risk assessment result is received as output.

[0327] Step 6: Recognizing user emotions with the emotion engine

[0328] The device uses a camera and microphone to capture the user's facial expressions and voice in real time. Video and audio data are obtained as input. This data is analyzed by an emotion engine (e.g., Emotion API) to determine the user's emotional state (joy, anger, stress, etc.). The emotional state is obtained as output.

[0329] Step 7: Output the results and notify based on the emotion

[0330] The server generates an evaluation result and transmits it to the device in a format that corresponds to the user's emotional state based on the emotion engine's judgment. The copyright risk evaluation result and the user's emotional state are received as input. The server selects an appropriate way to express the result and transmits it to the device via an HTTP response. The output is the evaluation result that is displayed on the user's device.

[0331] Users can check the evaluation results on their device via a web browser, which allows them to understand the copyright risks of commercial images and make appropriate decisions based on that information.

[0332] Specific prompt examples

[0333] Example 1: A user who uploads a non-commercial image experiences frustration

[0334] "Please rate whether this image is safe for commercial use."

[0335] Example 2: A user expresses joy by uploading an image that can be used commercially.

[0336] "Can I use this image in my marketing materials?"

[0337] In this way, by using the system of the present invention, it is possible to efficiently and accurately evaluate the copyright risk of an image and to provide a notification that takes into consideration the user's feelings.

[0338] (Application example 2)

[0339] 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."

[0340] Currently, there is a demand for a system that can efficiently evaluate the copyright risk of images intended for commercial use. However, existing systems have the problem of conveying results in a uniform manner without taking the user's emotional state into consideration, resulting in a poor user experience. It is necessary to develop a system that solves this problem and supports smoother commercial use by providing notifications that take the user's emotions into consideration.

[0341] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0342] In this invention, the server includes means for a user to upload an image to be evaluated, means for receiving the uploaded image and performing initial processing, means for extracting visual features from the image using an artificial intelligence model, means for comparing the image with an existing database and evaluating the degree of match or similarity, means for determining the copyright risk of the image based on the evaluation result, means for notifying the user of the determination result, means for recognizing the user's emotional state, and means for optimizing the notification method based on the user's emotional state. This makes it possible to efficiently evaluate the copyright risk of images intended for commercial use and to provide notification that takes the user's emotions into consideration.

[0343] "User" means any individual or legal entity that wishes to use the system to assess the copyright risk of an image.

[0344] An "image to be evaluated" is an image file uploaded by a user for commercial use.

[0345] "Means for uploading" refers to an interface or program that allows a user to send images to be evaluated to the system.

[0346] The "means for performing initial processing" is a function for performing processing such as compression, format conversion, and resizing of received images.

[0347] "Visual features" are feature information extracted by image analysis, such as the color, shape, and texture of an image.

[0348] An "artificial intelligence model" is a model that uses deep learning technology and is used to extract visual features from images.

[0349] "Feature extraction means" is a function that extracts visual features of an image using an artificial intelligence model.

[0350] A "database" is a searchable repository of existing, non-commercially available images and copyright-related information.

[0351] The "means for matching and evaluating the degree of match or similarity" is a function for comparing the extracted features with image features in a database and calculating the degree of match or similarity.

[0352] The "evaluation result" is information used to determine whether there is a copyright risk.

[0353] The "means for determining copyright risk" is a function that determines whether an image can be used commercially based on the evaluation results.

[0354] "Means of notification" refers to means for communicating the judgment results to the user, and includes web browser, email, in-app notification, etc.

[0355] "Emotional state" is the result of a real-time analysis of a user's emotions, including excitement, joy, anger, stress, etc.

[0356] The "means for recognizing emotional state" is a function that analyzes the user's emotions in real time using the user's camera and microphone.

[0357] The "means for optimizing the notification method" is a function for adjusting the notification method and content of the judgment result based on the emotional state of the user.

[0358] The system according to the present invention evaluates the copyright risk of images for commercial use and provides optimal notification according to the user's emotional state. This system is configured and operates as follows.

[0359] The system includes a means for users to upload images to be evaluated. The user selects an image file through a web browser or a dedicated application and uploads it to the system. At this point, the user's device obtains the path to the image file and sends it to the server. The uploaded image is received by the server and undergoes initial processing, which may include image compression, resizing, and format conversion.

[0360] The server then inputs the received image into an artificial intelligence model to extract visual features. This AI model uses deep learning technology, specifically a convolutional neural network (CNN) model. It analyzes visual information such as the image's color, shape, and texture to generate a feature vector.

[0361] The generated feature vector is compared with an existing database stored on the server. The database contains images that are not for commercial use and copyright-related information, and a database search is performed using the feature vector as a key. The server evaluates the degree of match and similarity based on the search results and derives an evaluation result.

[0362] Based on the evaluation results, the server determines the copyright risk of the image. If the image being evaluated is determined to be unsuitable for commercial use, the server notifies the user. A similar notification is also given if the image is determined to be suitable for commercial use. However, what is unique about this system is that the notification is given taking into account the user's emotional state.

[0363] The server uses the device's camera and microphone to recognize the user's emotional state. Emotion Engine is used for emotion recognition. Facial expressions are analyzed from the camera and tone of voice is analyzed from the microphone to determine whether the user is in an emotional state such as excitement, joy, anger, or stress. Based on this determination, the server optimizes the method of notifying the evaluation result. For example, if the user is feeling stressed, the server will notify them in soft language, and conversely, if the user is excited, the server will notify them in a concise manner.

[0364] Specific examples of prompts are as follows:

[0365] Your custom script will use the smartphone's camera and microphone to recognize user emotions and assess the copyright risk of uploaded images. The deep learning model will extract image features and compare them with a database to assess risk. Emotion Engine will be used for emotion recognition, and the results will be fed back to the user in the form of a notification message based on the emotion.

[0366] In this way, the system can efficiently assess the copyright risk of images intended for commercial use and further improve the user experience by providing notifications that take into account the user's emotional state.

[0367] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0368] Step 1:

[0369] User image upload

[0370] The user uploads the image to be evaluated from their own device. The input is an image file (e.g., JPEG or PNG), and the output is the transmission of the image file to the server. The user selects an image through a web browser or a dedicated application and clicks the upload button to obtain the path of the image file and send it to the server.

[0371] Step 2:

[0372] Server reception and initial processing

[0373] The server receives the image file sent by the user and performs initial processing. The input is the received image file, and the output is the processed image file. At this stage, the server checks the image format and performs compression or format conversion (e.g., from BMP to JPEG) as necessary. The image may also be resized.

[0374] Step 3:

[0375] Feature extraction using AI models

[0376] The server inputs the image after initial processing into an artificial intelligence model to extract visual features. The input is the processed image file, and the output is a feature vector. The server uses deep learning technology (e.g., CNN) to analyze visual information such as the color, shape, and texture of the image and generate a feature vector.

[0377] Step 4:

[0378] Checking an existing database

[0379] The server compares the extracted feature vector with an existing database. The input is the feature vector and database information, and the output is the evaluation result of the degree of match or similarity. The server performs a database search using the feature vector as a key to identify images that match or have a high degree of similarity.

[0380] Step 5:

[0381] Copyright Risk Assessment

[0382] The server determines the copyright risk of the image being evaluated based on the results of the database match. The input is the evaluation result of the database match, and the output is the copyright risk judgment result. If the server finds a match or a high similarity, it determines that the image is not commercially available; otherwise, it determines that the image is commercially available.

[0383] Step 6:

[0384] Recognizing user emotions with an emotion engine

[0385] The emotion engine on the user's device uses a camera and microphone to recognize the user's emotions in real time. The input is camera footage and audio data, and the output is the user's emotional state (excitement, joy, anger, stress, etc.). The emotion engine analyzes facial expressions and tone of voice to determine the user's emotional state.

[0386] Step 7:

[0387] Result output and emotional notifications

[0388] When the server notifies the user's device of the generated evaluation results, it changes the notification method based on the recognition results of the emotion engine. The input is the copyright risk assessment result and the user's emotional state, and the output is a notification message that takes the emotion into consideration. For example, if the user is feeling stressed, the result will be notified in soft language, and conversely, if the user is excited, the notification will be concise.

[0389] Through these processing steps, the system can efficiently assess the copyright risk of images intended for commercial use and provide notifications that take into account the user's emotional state.

[0390] 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.

[0391] 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.

[0392] 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.

[0393] [Second embodiment]

[0394] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0395] 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.

[0396] 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).

[0397] 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.

[0398] 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.

[0399] 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).

[0400] 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.

[0401] 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.

[0402] 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.

[0403] 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.

[0404] In the smart glasses 214, the 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.

[0405] 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."

[0406] The present invention provides a system for assessing the risk of copyright infringement of images for commercial use, which includes a means for allowing a user to upload images to be assessed, a means for receiving the uploaded images and performing initial processing, a means for extracting visual features from the images using an artificial intelligence model, a means for comparing the extracted features with an existing database and assessing the degree of match or similarity, a means for determining the copyright risk of the images based on the assessment results, and a means for notifying the user of the assessment results.

[0407] A specific embodiment of this system is described below.

[0408] System Operation Overview

[0409] 1. User image upload

[0410] The user accesses the interface provided through a web browser, selects and uploads an image to be evaluated, and the user's device acquires the path of this image file and sends it to the system.

[0411] 2. Server Reception and Initial Processing

[0412] The server receives the image file sent from the user's device. During this process, the server checks the format of the image file and compresses or converts the image if necessary. For example, if the image is too large, it is compressed and converted into a usable format (e.g., JPEG).

[0413] 3. Feature extraction using AI models

[0414] The server inputs the received image into an AI model to extract visual features. The AI ​​model uses deep learning techniques to analyze visual information such as color, shape, and texture in the image. The resulting feature vector is used for subsequent database matching.

[0415] 4. Checking existing databases

[0416] The server compares the extracted feature vector with an existing image database, which stores images that are prohibited for commercial use and copyright information. The server performs a search using the feature vector as a key to identify matching or similar images.

[0417] 5. Copyright Risk Assessment

[0418] The server determines the copyright risk of the image being evaluated based on the results of the database match. If an identical or highly similar image is found, the image is deemed unsuitable for commercial use. If there is no match or high similarity, the image is deemed suitable for commercial use.

[0419] 6. Output and notification of results

[0420] The server generates the copyright risk assessment results and notifies the user's device. The user can then check the results on their device's web browser. For example, the results may include messages such as "This image may be used for commercial purposes" or "This image may infringe copyright, so please avoid using it for commercial purposes."

[0421] Specific examples

[0422] Example 1: Rating images for non-commercial use

[0423] Users upload images for inclusion on their websites.

[0424] Images received by the server undergo feature extraction through an artificial intelligence model.

[0425] The extracted features are found to have a high degree of similarity to known non-commercial images in the database.

[0426] The server determines that "this image poses a risk of copyright infringement, so please avoid using it for commercial purposes," and notifies the user of the result.

[0427] Example 2: Rating images for commercial use

[0428] Users upload images for use in marketing materials.

[0429] The server extracts features from the received image and compares them with an existing database.

[0430] It is determined that there are no images in the database that have a match or a high degree of similarity.

[0431] The server determines that "this image can be used commercially" and notifies the user of the result.

[0432] In this way, by using the system of the present invention, users can easily and quickly evaluate the copyright risk of images and determine whether or not they can be used commercially.

[0433] The processing flow will be explained below.

[0434] Step 1:

[0435] A user accesses the application and clicks the "Upload Image" button. The user selects an image file to be evaluated and starts uploading. The user's device obtains the path of the selected image file and inserts the file into the upload stream.

[0436] Step 2:

[0437] The server receives the image file sent from the user's device. The server checks the format of the image file and compresses or converts the image as necessary. For example, images that are too large will be compressed, and images in an unsupported format (such as BMP or GIF) will be converted to JPEG format.

[0438] Step 3:

[0439] The server inputs the received image into an artificial intelligence model to extract visual features. The server uses a deep learning model (e.g., CNN) to analyze visual information such as the image's color, shape, and texture. As a result of the analysis, a feature vector is generated and used for subsequent processing.

[0440] Step 4:

[0441] The server compares the extracted feature vector with an existing image database, which stores images that are not for commercial use and copyright-related information. The server then searches the database using the feature vector as a key to identify images that match or have a high degree of similarity.

[0442] Step 5:

[0443] The server determines the copyright risk of the image being evaluated based on the results of the database comparison. If the server finds a match or a high degree of similarity, it determines that the image cannot be used commercially. Conversely, if the server finds no match or high degree of similarity, it determines that the image can be used commercially.

[0444] Step 6:

[0445] The server notifies the user's device of the risk assessment results it has generated. The server then sends the assessment results to the user's device as an HTTP response, sending the results in JSON format or similar. The user can then check the assessment results on their own device's web browser.

[0446] Step 7:

[0447] The user checks the evaluation results sent from the server on the web application interface. The user's device receives the response from the server and displays it to the user in an appropriate format. For example, it displays specific content such as "This image can be used for commercial purposes" or "Please avoid using this image for commercial purposes as there is a risk of copyright infringement."

[0448] Example 1

[0449] 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."

[0450] Previous image copyright risk assessment systems had problems with low assessment accuracy and lacked reliability for commercial use. Furthermore, they lacked sufficient use of AI models to extract visual features and compare them with databases, resulting in a high likelihood of false positives. This made it difficult for companies and individuals to make appropriate decisions to avoid the risk of copyright infringement.

[0451] 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.

[0452] In this invention, the server includes means for users to upload images to be evaluated, means for receiving the uploaded images and performing initial processing, means for extracting visual features from the images using an artificial intelligence model, means for comparing the extracted features with an existing database and evaluating the degree of match or similarity, means for determining the copyright risk of the images based on the evaluation results, and means for notifying the user of the determination results. This makes it possible to evaluate the copyright risk of images with high accuracy and quickly and accurately determine whether or not they can be used commercially.

[0453] "User" means any person or entity that uses the System to assess the copyright risk of Images.

[0454] "Upload" refers to the act of a user sending an image file to be evaluated to the system.

[0455] "Receiving" refers to the act of the server receiving the image file sent by the user.

[0456] "Initial processing" refers to the process of performing preprocessing such as format confirmation, compression, and format conversion of received images.

[0457] "Visual features" refers to the characteristic information of an image, such as color, shape, or texture, extracted through a deep learning model.

[0458] "Artificial intelligence model" refers to a mathematical and computational structure for extracting visual features using deep learning techniques.

[0459] A "feature vector" refers to data that numerically represents visual features extracted by an artificial intelligence model.

[0460] "Matching" refers to the process of comparing the extracted feature vectors with those in an existing database.

[0461] "Database" means a data storage facility for storing uncommercially protected images and associated copyright information.

[0462] "Match" refers to the state where the extracted feature vector is exactly the same as the feature vector in the database.

[0463] "Similarity" refers to a measure that numerically indicates how similar the extracted feature vector is to the feature vector in the database.

[0464] "Evaluation Results" refers to the results report for determining the copyright risk of an image.

[0465] "Notification" refers to the act of informing the user of the evaluation results.

[0466] This invention is a system for assessing the risk of copyright infringement of images for commercial use. This system allows users to upload images to be assessed, and then goes through a series of processes to extract, match, and assess visual features from the images, and finally notifies users of the assessment results.

[0467] System Configuration

[0468] 1. User image upload

[0469] The user accesses the interface provided through a web browser, selects an image to be evaluated, and uploads the image along with the prompt, "Please evaluate the risk of commercial use." At this time, the user's device obtains the path to the image file and sends the image data to the server.

[0470] 2. Server Reception and Initial Processing

[0471] The server receives the image file sent from the user's device. After receiving it, the server checks the image format and converts it to the appropriate format. Specifically, it uses an image processing library such as OpenCV to convert it to JPEG format and compress the size.

[0472] 3. Feature extraction using AI models

[0473] The server then inputs the received images into an AI model to extract visual features. This AI model uses deep learning frameworks such as TensorFlow and PyTorch to analyze features such as color, shape, and texture in the image. The resulting feature vector is used in the next stage of the matching process.

[0474] 4. Matching with existing databases

[0475] The server then matches the extracted feature vectors with an existing image database. Using similarity measures such as Cosine Similarity and Euclidean Distance, the server compares the extracted feature vectors with known non-commercial images and copyright-related information in the database. The database contains feature vectors of non-commercial images, and images with high similarity are identified.

[0476] 5. Copyright Risk Assessment

[0477] The server determines the copyright risk of the image being evaluated based on the results of the database comparison. If a match or high similarity is confirmed, the image is deemed not suitable for commercial use. Conversely, if no match or high similarity is confirmed, the image is deemed suitable for commercial use. As a criterion for evaluation, a threshold is considered, such as a similarity of 0.9 or higher being considered a high risk.

[0478] 6. Notification of Results

[0479] The server generates the results of the copyright risk assessment and notifies the user with specific messages such as "This image can be used for commercial purposes" or "This image may infringe copyright, so please avoid using it for commercial purposes." The user can then check the results on their own device.

[0480] Specific examples

[0481] Example 1: Rating images for non-commercial use

[0482] Users upload images for use on their websites, along with a prompt to "assess the risk of commercial use."

[0483] The server converts the format of the received images and performs feature extraction through an artificial intelligence model.

[0484] The server compares the extracted feature vectors with an existing database, and non-commercial images with high similarity are identified.

[0485] The server generates an evaluation result saying, "This image may infringe copyright, so please avoid using it for commercial purposes," and notifies the user.

[0486] Example 2: Evaluating images for commercial use

[0487] Users upload images for use in ads, along with a prompt to "assess the risk of commercial use."

[0488] The server converts the format of the received image and then extracts features using an artificial intelligence model.

[0489] The match does not identify a match or a highly similar image in the database.

[0490] The server generates an evaluation result that says "This image can be used commercially," and notifies the user.

[0491] In this way, by implementing this system, users can easily evaluate the copyright risk of images and quickly and accurately determine whether or not they can be used commercially.

[0492] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0493] Step 1: User uploads an image

[0494] A user accesses the system interface using a web browser and selects an image file to be evaluated. The user can also enter a prompt such as "Please evaluate the risk of commercial use." The user's device obtains the path of the selected image file and sends a request containing the image data to the server. The input is the image file, and the output is a request to the server.

[0495] Step 2: The server receives the image and performs some initial processing.

[0496] The server receives image files sent from the user's device. After receiving the image, the server checks the image format and converts it to the appropriate format if necessary. Specifically, it uses the OpenCV library to convert the image format to JPEG and compresses it if the size is too large. The input is the received image file, and the output is the processed and converted image file.

[0497] Step 3: The server uses the AI ​​model to extract features

[0498] The server inputs the initially processed image into a deep learning model to extract visual features. This artificial intelligence model uses TensorFlow and PyTorch to analyze features such as color, shape, and texture in the image. Specifically, the image is input into the model and a feature vector is obtained as the output. The input is the initially processed image file, and the output is the feature vector.

[0499] Step 4: The server checks against the existing database

[0500] The server compares the feature vector with an existing image database. In this step, it uses Cosine Similarity or Euclidean Distance to measure the similarity with the feature vector in the database. The database contains non-commercial images and copyright information, and it determines whether the feature vector matches or has a high similarity with them. The input is the extracted feature vector, and the output is a result indicating a match or a high similarity in the database.

[0501] Step 5: Server assesses copyright risk

[0502] The server determines the copyright risk of the image based on the matching results. For example, if the similarity is 0.9 or higher, it is considered a high risk, and if it is below that, it is considered a low risk. The input is the result of matching with the database, and the output is the copyright risk assessment result. A judgment is made as to whether the image is "commercially usable" or "not for commercial use."

[0503] Step 6: The server notifies the user of the evaluation results

[0504] The server generates the evaluation result and notifies the user's device. The notification is made via a web browser interface, displaying a message such as "This image can be used for commercial purposes" or "This image may infringe copyright, so please avoid using it for commercial purposes." The input is the copyright risk evaluation result, and the output is the notification message displayed to the user.

[0505] (Application example 1)

[0506] 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."

[0507] In recent years, the use of images on the Internet has increased, and the risk of copyright infringement in commercial use of images has become a serious issue. Advertising agencies and marketers, in particular, must quickly evaluate a large number of image materials, and in doing so, they are required to quickly and accurately determine the copyright risk of images. However, current manual checking methods are time-consuming, labor-intensive, and inefficient. To address this issue, the present invention aims to provide a system for evaluating the copyright risk of images used for advertising management in real time.

[0508] 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.

[0509] In this invention, the server includes means for users to upload images to be evaluated, means for receiving the uploaded images and performing initial processing, feature extraction means using an artificial intelligence model to extract visual features from the images, means for comparing the extracted features with an existing database and evaluating the degree of match or similarity, means for determining the copyright risk of the images based on the evaluation results, means for notifying the user of the determination results, and means for uploading images via a smartphone for advertising management and evaluating the copyright risk in real time. This enables users to quickly evaluate the copyright risk of images to be used as advertising material and immediately determine whether or not they can be used commercially.

[0510] "User" means a person or entity that uploads images to the system and receives the results of a copyright risk assessment.

[0511] An "image to be evaluated" is an image file uploaded by a user for commercial use.

[0512] "Upload" refers to the act of a user sending an image to be evaluated to the online system.

[0513] "Initial processing" is a series of processes that check the format of the received image and compress and convert it.

[0514] "Visual features" refer to information such as color, shape, and texture within an image, and are extracted using artificial intelligence.

[0515] An "artificial intelligence model" is an algorithm or system that uses deep learning technology to analyze visual features.

[0516] "Feature extraction means" refers to technical means or tools for extracting visual features from an image.

[0517] An "existing database" is an information collection that stores image data collected in the past and its copyright information.

[0518] "Matching" is the act of comparing extracted visual features with an existing database to evaluate the degree of match or similarity.

[0519] "Similarity" is a measure of the visual match between an image and an existing image in a database.

[0520] The "evaluation result" is the copyright risk assessment result derived based on the matching of visual features.

[0521] "Copyright risk" refers to the degree of likelihood that the image being evaluated constitutes copyright infringement.

[0522] "Notification" refers to the act of informing the user of the evaluation results.

[0523] "For advertising management" refers to the purpose of managing and evaluating images used as advertising materials.

[0524] A "smartphone" is a portable communication device that can connect to the Internet and use multi-function applications.

[0525] "Real-time" means that the time from when a user uploads an image to when the evaluation result is notified is extremely short, and processing is immediate.

[0526] The present invention provides a system for evaluating the copyright risk of images in real time, specially designed for advertising management, which mainly uses a server, a smartphone terminal, and an artificial intelligence (AI) model.

[0527] Overall system configuration

[0528] The system includes the following main components:

[0529] 1. User terminal: A smartphone is used, providing a means for users to upload images as advertising materials.

[0530] 2. Server: Receives uploaded images, performs initial processing, extracts visual features, matches them with databases, assesses copyright risk, and notifies the results.

[0531] 3. Artificial intelligence model: Deep learning techniques are used to analyze visual features in images.

[0532] Program processing overview

[0533] 1. User image upload

[0534] The user uses a dedicated smartphone application to select an image to be evaluated and upload it to the system, which obtains the image's file path and sends it to the server.

[0535] 2. Server Reception and Initial Processing

[0536] The server receives the image file sent from the user terminal. It checks the format of the received image file and performs image compression or format conversion as necessary. For example, it converts the image to JPEG format or compresses the image size.

[0537] 3. Feature extraction using AI models

[0538] The server inputs the processed image into an artificial intelligence model to extract visual features. This model uses ResNet50, built using TensorFlow, which extracts visual features such as color, shape, and texture from the image as vectors.

[0539] 4. Matching with existing databases

[0540] The server compares the extracted feature vector with an existing image database. For comparison, it uses the cosine_similarity function from the scikit-learn library to calculate the similarity to images in the database. If the highest similarity exceeds a predetermined threshold, it is determined to have a high copyright risk.

[0541] 5. Copyright Risk Assessment and Notification of Results

[0542] The server evaluates the copyright risk of the image based on the results of the database comparison. The evaluation results are sent to the user's smartphone in real time. The user can then check the results, such as "There is a risk of copyright infringement" or "Commercial use is permitted," via a dedicated application.

[0543] Hardware and software used

[0544] Hardware: Smartphones, servers

[0545] software:

[0546] TensorFlow: Used to implement the artificial intelligence model (ResNet50) and extract features

[0547] Pillow: Used for initial image processing (format conversion and resizing)

[0548] scikit-learn: Used to compare similarity between feature vectors (cosine_similarity)

[0549] Specific examples

[0550] Example 1: Marketer use case

[0551] Marketers upload images to be used as advertising materials for new products from their smartphones, and the images are evaluated through an AI model, which immediately informs them that they are "suitable for commercial use."

[0552] Example 2: Advertising agency use case

[0553] Advertising agencies use a smartphone application to simultaneously evaluate multiple advertising materials. The application allows users to upload images in bulk, and the server evaluates the copyright risk of each image and notifies users of the results individually.

[0554] Prompt Sentence Examples

[0555] Upload a new image "example.jpg" as advertising material and assess its copyright risk.

[0556] Run the assessment and view the results.

[0557] Specify the file path:

[0558] file_path = "example.jpg"

[0559] main(file_path)

[0560] In this way, by using the system of the present invention, users can easily evaluate the copyright risk of advertising materials and quickly determine whether or not they can be used commercially.

[0561] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0562] Step 1:

[0563] The user selects an image to be evaluated as advertising material and uploads it to the system through a smartphone application. Specifically, the user uses the app's interface to select an image from the device's storage and clicks the upload button. This step inputs the selected image file. The app then sends this image file to the server.

[0564] Step 2:

[0565] The server receives image files sent from the user device and performs initial processing. It checks the format of the received image file, converts it to JPEG format if necessary, and compresses the image size. Specifically, it uses the Pillow library to convert the image format and resize it. The input is the image data sent from the smartphone, and the output is the image data after initial processing has been completed.

[0566] Step 3:

[0567] The server inputs the pre-processed image into an artificial intelligence model to extract visual features. Specifically, it uses a ResNet50 model built using TensorFlow to extract visual information such as the image's color, shape, and texture as a feature vector. The input at this stage is the pre-processed image data, and the output is the extracted visual feature vector.

[0568] Step 4:

[0569] The server compares the extracted feature vector with an existing database. Specifically, it calculates the similarity between the extracted feature vector and an existing image in the database using the cosine_similarity function in the scikit-learn library. The input is the visual feature vector and the feature vector in the database, and the output is a similarity score.

[0570] Step 5:

[0571] The server evaluates copyright risk based on the results of database matching. If the similarity score exceeds a predetermined threshold, the image is deemed to have a high risk of copyright infringement. The input is the similarity score, and the output is the copyright risk assessment result. Specifically, it generates an assessment result such as "There is a risk of copyright infringement" or "Commercial use is permitted."

[0572] Step 6:

[0573] The server notifies the user of the results of the copyright risk assessment via their smartphone. Specifically, the assessment results are sent to a dedicated application and displayed to the user as a notification message. The input is the copyright risk assessment result, and the output is a notification message sent to the user's device. The user can then check the results to determine whether or not the advertising material can be used commercially.

[0574] In this way, users can easily use their smartphones to evaluate the copyright risks of advertising materials and make appropriate usage decisions.

[0575] 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.

[0576] The present invention combines a system for assessing the risk of copyright infringement of images for commercial use with an emotion engine that recognizes user emotions. This system includes the following means: a means for a user to upload images to be assessed, a means for receiving the uploaded images and performing initial processing, a feature extraction means using an artificial intelligence model to extract visual features from the images, a means for comparing the extracted features with an existing database and assessing their match or similarity, a means for determining the copyright risk of the images based on the assessment results, a means for notifying the user of the assessment results, and an emotion engine that recognizes user emotions.

[0577] A specific embodiment of this system is described below.

[0578] System Operation Overview

[0579] 1. User image upload

[0580] The user accesses the interface provided through a web browser, selects and uploads the image file to be evaluated, and the user's device acquires the path of this image file and sends it to the system.

[0581] 2. Server Reception and Initial Processing

[0582] The server receives the image file sent from the user's device. The server checks the format of the image file and compresses or converts the image as necessary. For example, images that are too large will be compressed, and images in an unsupported format (such as BMP or GIF) will be converted to JPEG format.

[0583] 3. Feature extraction using AI models

[0584] The server inputs the received image into an artificial intelligence model to extract visual features. The server uses a deep learning model (e.g., CNN) to analyze visual information such as the image's color, shape, and texture. As a result of the analysis, a feature vector is generated and used for subsequent processing.

[0585] 4. Checking existing databases

[0586] The server compares the extracted feature vector with an existing image database, which stores images that are not for commercial use and copyright-related information. The server performs a database search using the feature vector as a key to identify images that match or have a high degree of similarity.

[0587] 5. Copyright Risk Assessment

[0588] The server determines the copyright risk of the image being evaluated based on the results of the database comparison. If the server finds a match or a high degree of similarity, it determines that the image cannot be used commercially. Conversely, if the server finds no match or high degree of similarity, it determines that the image can be used commercially.

[0589] 6. Recognition of user emotions by emotion engine

[0590] The device uses the user's camera and microphone to enable the emotion engine to recognize the user's emotions in real time. The emotion engine uses facial expression analysis and tone of voice analysis to determine whether the user is in an emotional state such as excitement, joy, or anger.

[0591] 7. Result output and emotional notifications

[0592] When the server notifies the user of the generated evaluation results, it changes the notification method based on the recognition results of the emotion engine. For example, if the user is feeling stressed, it will notify the result in gentler terms, and conversely, if the user is excited, it will notify them in a more concise manner.

[0593] Users can check the evaluation results on their own devices in a web browser, which may display a message such as "This image can be used for commercial purposes" or "Please avoid using this image for commercial purposes as there is a risk of copyright infringement."

[0594] Specific examples

[0595] Example 1: Rating and responding to sentiment for images that are not suitable for commercial use

[0596] Users upload images for inclusion on their websites.

[0597] Images received by the server undergo feature extraction through an artificial intelligence model.

[0598] The extracted features are found to have a high degree of similarity to known non-commercial images in the database.

[0599] The server determines that "this image poses a risk of copyright infringement, so please avoid using it for commercial purposes," and notifies the user of the result.

[0600] The user's device uses a camera and microphone to allow the emotion engine to recognize the user's emotions and determine whether they are feeling stressed.

[0601] The server notifies the user of the evaluation results in gentle language designed to reduce stress.

[0602] Example 2: Ratings and positive emotional responses for commercially available images

[0603] Users upload images for use in marketing materials.

[0604] The server extracts features from the received image and compares them with an existing database.

[0605] It is determined that there are no images in the database that have a match or a high degree of similarity.

[0606] The server determines that "this image can be used commercially" and notifies the user of the result.

[0607] The user's device recognizes the user's emotions through an emotion engine and detects the emotion of joy.

[0608] The server notifies the user of the evaluation results in simple and positive terms.

[0609] In this way, by using the system of the present invention, it is possible to efficiently evaluate the copyright risk of commercial images and to provide notifications that take into consideration the user's feelings.

[0610] The processing flow will be explained below.

[0611] Step 1:

[0612] A user accesses the application and clicks the "Upload Image" button. The user selects an image file to be evaluated and starts uploading. The user's device obtains the path of the selected image file and inserts the file into the upload stream.

[0613] Step 2:

[0614] The server receives the image file sent from the user's device. The server checks the format of the image file and compresses or converts the image as necessary. For example, an image that is too large will be compressed, or if the format is not supported, it will be converted to JPEG format.

[0615] Step 3:

[0616] The server inputs the received image into an artificial intelligence model to extract visual features. The server uses a deep learning model to analyze the image's visual information, such as color, shape, and texture. As a result of the analysis, a feature vector is generated.

[0617] Step 4:

[0618] The server compares the extracted feature vector with an existing image database, which stores images that are not for commercial use and copyright-related information. The server then searches the database using the feature vector as a key to identify images that match or have a high degree of similarity.

[0619] Step 5:

[0620] The server determines the copyright risk of the image being evaluated based on the results of the database comparison. If the server finds a match or a high degree of similarity, it determines that the image cannot be used commercially. Conversely, if the server finds no match or high degree of similarity, it determines that the image can be used commercially.

[0621] Step 6:

[0622] The device uses the user's camera and microphone to enable the emotion engine to recognize the user's emotions in real time. The emotion engine uses facial expression analysis and tone of voice analysis to determine whether the user is in an emotional state such as excitement, joy, or anger.

[0623] Step 7:

[0624] The server changes the notification method based on the recognition results of the emotion engine. For example, if the user is feeling stressed, the server notifies the user in a gentle manner, whereas if the user is excited, the server notifies the user in a concise manner.

[0625] Step 8:

[0626] The server notifies the user's device of the evaluation results it has generated. The server then sends the results to the user's device as an HTTP response in JSON format or similar. The user can then check the evaluation results on their device's web browser.

[0627] Step 9:

[0628] The user checks the evaluation results sent from the server on the web application interface. The user's device receives the response from the server and displays it to the user in an appropriate format. For example, it displays specific content such as "This image can be used for commercial purposes" or "Please avoid using this image for commercial purposes as there is a risk of copyright infringement."

[0629] Example 2

[0630] 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."

[0631] In assessing the copyright risk of images intended for commercial use, existing systems have the problem of being unable to accurately assess the copyright risk of images and not giving consideration to the user's feelings when notifying them. In particular, not taking the user's feelings into consideration when notifying them of the copyright risk assessment results can cause unnecessary stress and confusion for the user.

[0632] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving uploaded images and performing initial processing, feature extraction means using an artificial intelligence model to extract visual features from the images, means for comparing the extracted features with an existing database and evaluating the degree of match or similarity, means for determining the copyright risk of the images based on the evaluation results, means for notifying the user of the evaluation results, and an emotion engine for recognizing the user's emotions and adjusting the method of notifying the evaluation results. This not only enables efficient and accurate evaluation of the copyright risk of images, but also enables appropriate notification that takes the user's emotions into consideration.

[0633] "User" refers to a user who uses the system to upload images and have them assessed for copyright risk.

[0634] "Server" refers to a computer system that receives images sent from a user's terminal and is responsible for all processing, including initial processing, feature extraction, database matching, and notification of evaluation results.

[0635] "Terminal" refers to a device accessed by a user, including a web browser and related hardware devices for uploading images and checking evaluation results.

[0636] "Image" refers to the visual data to be evaluated that users upload to the system, and includes common image formats such as JPEG and PNG.

[0637] "Visual features" are information extracted from an image, including color, shape, texture, and other attributes necessary for image recognition and feature vector generation.

[0638] "Artificial intelligence model" refers to an algorithm or network model used to extract visual features using deep learning techniques, including convolutional neural networks (CNNs).

[0639] "Database" refers to an information system that stores existing image data and associated copyright information against which extracted feature vectors can be matched.

[0640] A "feature vector" is a data set that quantifies the visual features of an image, and is used for matching with a database and evaluating similarity.

[0641] "Emotion engine" refers to the algorithms and software modules used to recognize a user's emotions, analyzing data acquired through the camera and microphone.

[0642] The "evaluation result" is a conclusion generated based on the copyright risk assessment, and is notified to the user in the form of "Commercial use is permitted" or "Commercial use should be avoided."

[0643] The "notification method" refers to the means or format for notifying the user of the evaluation results, and is adjusted according to the user's emotional state.

[0644] The present invention is a system for assessing the risk of copyright infringement of images intended for commercial use, which is combined with an emotion engine that recognizes user emotions. This system includes the following means: a means for a user to upload an image to be assessed, a means for receiving the uploaded image and performing initial processing, a feature extraction means using an artificial intelligence model to extract visual features from the image, a means for comparing the extracted features with an existing database and evaluating the degree of match or similarity, a means for determining the copyright risk of the image based on the assessment result, a means for notifying the user of the assessment result, and an emotion engine that recognizes user emotions.

[0645] System Operation Overview

[0646] 1. User image upload

[0647] The user accesses the interface provided through a web browser, selects and uploads the image file to be evaluated, and the user's device obtains the path of this image file and sends it to the system.

[0648] 2. Server Reception and Initial Processing

[0649] The server receives the image file sent from the terminal. After receiving it, it checks the format of the image file and compresses or converts the image as necessary. For example, large images are compressed, and images in unsupported formats (such as BMP or GIF) are converted to JPEG format.

[0650] 3. Feature extraction using AI models

[0651] The server inputs the received image into an artificial intelligence model (e.g., CNN) using deep learning technology to extract visual features. The analyzed feature vectors are used for database matching.

[0652] 4. Checking existing databases

[0653] The server uses the feature vector as a key to match existing image data and associated copyright information in a database that stores images and copyright information that are not for commercial use.

[0654] 5. Copyright Risk Assessment

[0655] The server determines the copyright risk of the image being evaluated based on the results of the database comparison. If a high degree of similarity is found, the image is deemed "unsuitable for commercial use," but if the match or similarity is low, it is deemed "available for commercial use."

[0656] 6. Recognition of user emotions by emotion engine

[0657] The device uses a camera and microphone to capture the user's facial expressions and tone of voice in real time, and analyzes the captured data with an emotion engine (e.g., Microsoft Azure's Emotion API) to determine the user's emotional state (e.g., excitement, joy, anger, stress).

[0658] 7. Result output and emotional notifications

[0659] The server generates an evaluation result and sends it to the device in a format that corresponds to the user's emotional state based on the judgment of the emotion engine. For example, if the user is feeling stressed, the server will notify them in gentle words, and if the user is excited, the server will notify them in a concise manner.

[0660] Users can check the evaluation results on their device in a web browser, which will display messages such as "Commercial use is permitted" or "Please avoid commercial use due to the risk of copyright infringement."

[0661] Specific examples

[0662] Example 1: Rating and responding to sentiment for images that are not suitable for commercial use

[0663] Users upload images for inclusion on their websites.

[0664] The image received by the server undergoes feature extraction through an artificial intelligence model.

[0665] The extracted features are found to have a high degree of similarity to known non-commercial images in the database.

[0666] The server determines that "This image poses a risk of copyright infringement, so please avoid using it for commercial purposes," and notifies the user of the result.

[0667] The user's device uses a camera and microphone to allow the emotion engine to recognize the user's emotions and determine whether they are feeling stressed.

[0668] The server will notify you of the evaluation results in gentle language.

[0669] Example 2: Ratings and positive emotional responses for commercially available images

[0670] Users upload images for use in marketing materials.

[0671] The server extracts features from the received image and compares them with an existing database.

[0672] It is determined that there are no images in the database that have a match or a high degree of similarity.

[0673] The server determines that "this image can be used commercially" and notifies the user of the result.

[0674] The user's device recognizes the user's emotions through an emotion engine and detects the emotion of joy.

[0675] The server will notify you of the evaluation results in simple and positive terms.

[0676] Prompt Sentence Examples

[0677] Example 1: A user who uploads a non-commercial image experiences frustration

[0678] "Please rate whether this image is safe for commercial use."

[0679] Example 2: A user expresses joy by uploading an image that can be used commercially.

[0680] "Can I use this image in my marketing materials?"

[0681] In this way, by using the system of the present invention, it is possible to efficiently evaluate the copyright risk of commercial images and provide notifications that take into consideration the user's feelings.

[0682] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0683] Processing steps of this system's program

[0684] Step 1: Upload user image

[0685] The user accesses a web browser, selects the image file to be evaluated, and clicks the upload button. The image file path selected by the user is obtained as input. Based on this path, the terminal sends the image file to the system. Specifically, the image file is sent to the server via an HTTP POST request.

[0686] Step 2: Server reception and initial processing

[0687] The server receives image files sent from the terminal. As input, the image file data arrives at the server. The server checks the format of the image file and compresses or converts the image as necessary. For example, files in a format other than JPEG are converted to JPEG, and files that are too large are compressed. As output, the image file data after initial processing is obtained.

[0688] Step 3: Feature extraction using an AI model

[0689] The server inputs the received image into an artificial intelligence model (such as CNN) that uses deep learning technology. An initially processed image file is obtained as input. The server analyzes this image and extracts visual features (color, shape, texture, etc.) as a feature vector. Specific examples include using TensorFlow or PyTorch. The feature vector is obtained as output.

[0690] Step 4: Check the existing database

[0691] The server compares the feature vector with an existing image database. The input is the feature vector. The server searches the database using an SQL query to identify image data that matches or has a high degree of similarity. The output is the matching result.

[0692] Step 5: Copyright Risk Assessment

[0693] The server determines the copyright risk of the image being evaluated based on the database match results. The database match results are received as input. The server determines the risk level using a rule-based or machine learning model. The copyright risk assessment result is received as output.

[0694] Step 6: Recognizing user emotions with the emotion engine

[0695] The device uses a camera and microphone to capture the user's facial expressions and voice in real time. Video and audio data are obtained as input. This data is analyzed by an emotion engine (e.g., Emotion API) to determine the user's emotional state (joy, anger, stress, etc.). The emotional state is obtained as output.

[0696] Step 7: Output the results and notify based on the emotion

[0697] The server generates an evaluation result and transmits it to the device in a format that corresponds to the user's emotional state based on the emotion engine's judgment. The copyright risk evaluation result and the user's emotional state are received as input. The server selects an appropriate way to express the result and transmits it to the device via an HTTP response. The output is the evaluation result that is displayed on the user's device.

[0698] Users can check the evaluation results on their device via a web browser, which allows them to understand the copyright risks of commercial images and make appropriate decisions based on that information.

[0699] Specific prompt examples

[0700] Example 1: A user who uploads a non-commercial image experiences frustration

[0701] "Please rate whether this image is safe for commercial use."

[0702] Example 2: A user expresses joy by uploading an image that can be used commercially.

[0703] "Can I use this image in my marketing materials?"

[0704] In this way, by using the system of the present invention, it is possible to efficiently and accurately evaluate the copyright risk of an image and to provide a notification that takes into consideration the user's feelings.

[0705] (Application example 2)

[0706] 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."

[0707] Currently, there is a demand for a system that can efficiently evaluate the copyright risk of images intended for commercial use. However, existing systems have the problem of conveying results in a uniform manner without taking the user's emotional state into consideration, resulting in a poor user experience. It is necessary to develop a system that solves this problem and supports smoother commercial use by providing notifications that take the user's emotions into consideration.

[0708] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0709] In this invention, the server includes means for a user to upload an image to be evaluated, means for receiving the uploaded image and performing initial processing, means for extracting visual features from the image using an artificial intelligence model, means for comparing the image with an existing database and evaluating the degree of match or similarity, means for determining the copyright risk of the image based on the evaluation result, means for notifying the user of the determination result, means for recognizing the user's emotional state, and means for optimizing the notification method based on the user's emotional state. This makes it possible to efficiently evaluate the copyright risk of images intended for commercial use and to provide notification that takes the user's emotions into consideration.

[0710] "User" means any individual or legal entity that wishes to use the system to assess the copyright risk of an image.

[0711] An "image to be evaluated" is an image file uploaded by a user for commercial use.

[0712] "Means for uploading" refers to an interface or program that allows a user to send images to be evaluated to the system.

[0713] The "means for performing initial processing" is a function for performing processing such as compression, format conversion, and resizing of received images.

[0714] "Visual features" are feature information extracted by image analysis, such as the color, shape, and texture of an image.

[0715] An "artificial intelligence model" is a model that uses deep learning technology and is used to extract visual features from images.

[0716] "Feature extraction means" is a function that extracts visual features of an image using an artificial intelligence model.

[0717] A "database" is a searchable repository of existing, non-commercially available images and copyright-related information.

[0718] The "means for matching and evaluating the degree of match or similarity" is a function for comparing the extracted features with image features in a database and calculating the degree of match or similarity.

[0719] The "evaluation result" is information used to determine whether there is a copyright risk.

[0720] The "means for determining copyright risk" is a function that determines whether an image can be used commercially based on the evaluation results.

[0721] "Means of notification" refers to means for communicating the judgment results to the user, and includes web browser, email, in-app notification, etc.

[0722] "Emotional state" is the result of a real-time analysis of a user's emotions, including excitement, joy, anger, stress, etc.

[0723] The "means for recognizing emotional state" is a function that analyzes the user's emotions in real time using the user's camera and microphone.

[0724] The "means for optimizing the notification method" is a function for adjusting the notification method and content of the judgment result based on the emotional state of the user.

[0725] The system according to the present invention evaluates the copyright risk of images for commercial use and provides optimal notification according to the user's emotional state. This system is configured and operates as follows.

[0726] The system includes a means for users to upload images to be evaluated. The user selects an image file through a web browser or a dedicated application and uploads it to the system. At this point, the user's device obtains the path to the image file and sends it to the server. The uploaded image is received by the server and undergoes initial processing, which may include image compression, resizing, and format conversion.

[0727] The server then inputs the received image into an artificial intelligence model to extract visual features. This AI model uses deep learning technology, specifically a convolutional neural network (CNN) model. It analyzes visual information such as the image's color, shape, and texture to generate a feature vector.

[0728] The generated feature vector is compared with an existing database stored on the server. The database contains images that are not for commercial use and copyright-related information, and a database search is performed using the feature vector as a key. The server evaluates the degree of match and similarity based on the search results and derives an evaluation result.

[0729] Based on the evaluation results, the server determines the copyright risk of the image. If the image being evaluated is determined to be unsuitable for commercial use, the server notifies the user. A similar notification is also given if the image is determined to be suitable for commercial use. However, what is unique about this system is that the notification is given taking into account the user's emotional state.

[0730] The server uses the device's camera and microphone to recognize the user's emotional state. Emotion Engine is used for emotion recognition. Facial expressions are analyzed from the camera and tone of voice is analyzed from the microphone to determine whether the user is in an emotional state such as excitement, joy, anger, or stress. Based on this determination, the server optimizes the method of notifying the evaluation result. For example, if the user is feeling stressed, the server will notify them in soft language, and conversely, if the user is excited, the server will notify them in a concise manner.

[0731] Specific examples of prompts are as follows:

[0732] Your custom script will use the smartphone's camera and microphone to recognize user emotions and assess the copyright risk of uploaded images. The deep learning model will extract image features and compare them with a database to assess risk. Emotion Engine will be used for emotion recognition, and the results will be fed back to the user in the form of a notification message based on the emotion.

[0733] In this way, the system can efficiently assess the copyright risk of images intended for commercial use and further improve the user experience by providing notifications that take into account the user's emotional state.

[0734] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0735] Step 1:

[0736] User image upload

[0737] The user uploads the image to be evaluated from their own device. The input is an image file (e.g., JPEG or PNG), and the output is the transmission of the image file to the server. The user selects an image through a web browser or a dedicated application and clicks the upload button to obtain the path of the image file and send it to the server.

[0738] Step 2:

[0739] Server reception and initial processing

[0740] The server receives the image file sent by the user and performs initial processing. The input is the received image file, and the output is the processed image file. At this stage, the server checks the image format and performs compression or format conversion (e.g., from BMP to JPEG) as necessary. The image may also be resized.

[0741] Step 3:

[0742] Feature extraction using AI models

[0743] The server inputs the image after initial processing into an artificial intelligence model to extract visual features. The input is the processed image file, and the output is a feature vector. The server uses deep learning technology (e.g., CNN) to analyze visual information such as the color, shape, and texture of the image and generate a feature vector.

[0744] Step 4:

[0745] Checking an existing database

[0746] The server compares the extracted feature vector with an existing database. The input is the feature vector and database information, and the output is the evaluation result of the degree of match or similarity. The server performs a database search using the feature vector as a key to identify images that match or have a high degree of similarity.

[0747] Step 5:

[0748] Copyright Risk Assessment

[0749] The server determines the copyright risk of the image being evaluated based on the results of the database match. The input is the evaluation result of the database match, and the output is the copyright risk judgment result. If the server finds a match or a high similarity, it determines that the image is not commercially available; otherwise, it determines that the image is commercially available.

[0750] Step 6:

[0751] Recognizing user emotions with an emotion engine

[0752] The emotion engine on the user's device uses a camera and microphone to recognize the user's emotions in real time. The input is camera footage and audio data, and the output is the user's emotional state (excitement, joy, anger, stress, etc.). The emotion engine analyzes facial expressions and tone of voice to determine the user's emotional state.

[0753] Step 7:

[0754] Result output and emotional notifications

[0755] When the server notifies the user's device of the generated evaluation results, it changes the notification method based on the recognition results of the emotion engine. The input is the copyright risk assessment result and the user's emotional state, and the output is a notification message that takes the emotion into consideration. For example, if the user is feeling stressed, the result will be notified in soft language, and conversely, if the user is excited, the notification will be concise.

[0756] Through these processing steps, the system can efficiently assess the copyright risk of images intended for commercial use and provide notifications that take into account the user's emotional state.

[0757] 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.

[0758] 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.

[0759] 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.

[0760] [Third embodiment]

[0761] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0762] 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.

[0763] 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).

[0764] 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.

[0765] 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.

[0766] 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).

[0767] 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.

[0768] 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.

[0769] 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.

[0770] 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.

[0771] 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.

[0772] 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."

[0773] The present invention provides a system for assessing the risk of copyright infringement of images for commercial use, which includes a means for allowing a user to upload images to be assessed, a means for receiving the uploaded images and performing initial processing, a means for extracting visual features from the images using an artificial intelligence model, a means for comparing the extracted features with an existing database and assessing the degree of match or similarity, a means for determining the copyright risk of the images based on the assessment results, and a means for notifying the user of the assessment results.

[0774] A specific embodiment of this system is described below.

[0775] System Operation Overview

[0776] 1. User image upload

[0777] The user accesses the interface provided through a web browser, selects and uploads an image to be evaluated, and the user's device acquires the path of this image file and sends it to the system.

[0778] 2. Server Reception and Initial Processing

[0779] The server receives the image file sent from the user's device. During this process, the server checks the format of the image file and compresses or converts the image if necessary. For example, if the image is too large, it is compressed and converted into a usable format (e.g., JPEG).

[0780] 3. Feature extraction using AI models

[0781] The server inputs the received image into an AI model to extract visual features. The AI ​​model uses deep learning techniques to analyze visual information such as color, shape, and texture in the image. The resulting feature vector is used for subsequent database matching.

[0782] 4. Checking existing databases

[0783] The server compares the extracted feature vector with an existing image database, which stores images that are prohibited for commercial use and copyright information. The server performs a search using the feature vector as a key to identify matching or similar images.

[0784] 5. Copyright Risk Assessment

[0785] The server determines the copyright risk of the image being evaluated based on the results of the database match. If an identical or highly similar image is found, the image is deemed unsuitable for commercial use. If there is no match or high similarity, the image is deemed suitable for commercial use.

[0786] 6. Output and notification of results

[0787] The server generates the copyright risk assessment results and notifies the user's device. The user can then check the results on their device's web browser. For example, the results may include messages such as "This image may be used for commercial purposes" or "This image may infringe copyright, so please avoid using it for commercial purposes."

[0788] Specific examples

[0789] Example 1: Rating images for non-commercial use

[0790] Users upload images for inclusion on their websites.

[0791] Images received by the server undergo feature extraction through an artificial intelligence model.

[0792] The extracted features are found to have a high degree of similarity to known non-commercial images in the database.

[0793] The server determines that "this image poses a risk of copyright infringement, so please avoid using it for commercial purposes," and notifies the user of the result.

[0794] Example 2: Rating images for commercial use

[0795] Users upload images for use in marketing materials.

[0796] The server extracts features from the received image and compares them with an existing database.

[0797] It is determined that there are no images in the database that have a match or a high degree of similarity.

[0798] The server determines that "this image can be used commercially" and notifies the user of the result.

[0799] In this way, by using the system of the present invention, users can easily and quickly evaluate the copyright risk of images and determine whether or not they can be used commercially.

[0800] The processing flow will be explained below.

[0801] Step 1:

[0802] A user accesses the application and clicks the "Upload Image" button. The user selects an image file to be evaluated and starts uploading. The user's device obtains the path of the selected image file and inserts the file into the upload stream.

[0803] Step 2:

[0804] The server receives the image file sent from the user's device. The server checks the format of the image file and compresses or converts the image as necessary. For example, images that are too large will be compressed, and images in an unsupported format (such as BMP or GIF) will be converted to JPEG format.

[0805] Step 3:

[0806] The server inputs the received image into an artificial intelligence model to extract visual features. The server uses a deep learning model (e.g., CNN) to analyze visual information such as the image's color, shape, and texture. As a result of the analysis, a feature vector is generated and used for subsequent processing.

[0807] Step 4:

[0808] The server compares the extracted feature vector with an existing image database, which stores images that are not for commercial use and copyright-related information. The server then searches the database using the feature vector as a key to identify images that match or have a high degree of similarity.

[0809] Step 5:

[0810] The server determines the copyright risk of the image being evaluated based on the results of the database comparison. If the server finds a match or a high degree of similarity, it determines that the image cannot be used commercially. Conversely, if the server finds no match or high degree of similarity, it determines that the image can be used commercially.

[0811] Step 6:

[0812] The server notifies the user's device of the risk assessment results it has generated. The server then sends the assessment results to the user's device as an HTTP response, sending the results in JSON format or similar. The user can then check the assessment results on their own device's web browser.

[0813] Step 7:

[0814] The user checks the evaluation results sent from the server on the web application interface. The user's device receives the response from the server and displays it to the user in an appropriate format. For example, it displays specific content such as "This image can be used for commercial purposes" or "Please avoid using this image for commercial purposes as there is a risk of copyright infringement."

[0815] Example 1

[0816] 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."

[0817] Previous image copyright risk assessment systems had problems with low assessment accuracy and lacked reliability for commercial use. Furthermore, they lacked sufficient use of AI models to extract visual features and compare them with databases, resulting in a high likelihood of false positives. This made it difficult for companies and individuals to make appropriate decisions to avoid the risk of copyright infringement.

[0818] 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.

[0819] In this invention, the server includes means for users to upload images to be evaluated, means for receiving the uploaded images and performing initial processing, means for extracting visual features from the images using an artificial intelligence model, means for comparing the extracted features with an existing database and evaluating the degree of match or similarity, means for determining the copyright risk of the images based on the evaluation results, and means for notifying the user of the determination results. This makes it possible to evaluate the copyright risk of images with high accuracy and quickly and accurately determine whether or not they can be used commercially.

[0820] "User" means any person or entity that uses the System to assess the copyright risk of Images.

[0821] "Upload" refers to the act of a user sending an image file to be evaluated to the system.

[0822] "Receiving" refers to the act of the server receiving the image file sent by the user.

[0823] "Initial processing" refers to the process of performing preprocessing such as format confirmation, compression, and format conversion of received images.

[0824] "Visual features" refers to the characteristic information of an image, such as color, shape, or texture, extracted through a deep learning model.

[0825] "Artificial intelligence model" refers to a mathematical and computational structure for extracting visual features using deep learning techniques.

[0826] A "feature vector" refers to data that numerically represents visual features extracted by an artificial intelligence model.

[0827] "Matching" refers to the process of comparing the extracted feature vectors with those in an existing database.

[0828] "Database" means a data storage facility for storing uncommercially protected images and associated copyright information.

[0829] "Match" refers to the state where the extracted feature vector is exactly the same as the feature vector in the database.

[0830] "Similarity" refers to a measure that numerically indicates how similar the extracted feature vector is to the feature vector in the database.

[0831] "Evaluation Results" refers to the results report for determining the copyright risk of an image.

[0832] "Notification" refers to the act of informing the user of the evaluation results.

[0833] This invention is a system for assessing the risk of copyright infringement of images for commercial use. This system allows users to upload images to be assessed, and then goes through a series of processes to extract, match, and assess visual features from the images, and finally notifies users of the assessment results.

[0834] System Configuration

[0835] 1. User image upload

[0836] The user accesses the interface provided through a web browser, selects an image to be evaluated, and uploads the image along with the prompt, "Please evaluate the risk of commercial use." At this time, the user's device obtains the path to the image file and sends the image data to the server.

[0837] 2. Server Reception and Initial Processing

[0838] The server receives the image file sent from the user's device. After receiving it, the server checks the image format and converts it to the appropriate format. Specifically, it uses an image processing library such as OpenCV to convert it to JPEG format and compress the size.

[0839] 3. Feature extraction using AI models

[0840] The server then inputs the received images into an AI model to extract visual features. This AI model uses deep learning frameworks such as TensorFlow and PyTorch to analyze features such as color, shape, and texture in the image. The resulting feature vector is used in the next stage of the matching process.

[0841] 4. Matching with existing databases

[0842] The server then matches the extracted feature vectors with an existing image database. Using similarity measures such as Cosine Similarity and Euclidean Distance, the server compares the extracted feature vectors with known non-commercial images and copyright-related information in the database. The database contains feature vectors of non-commercial images, and images with high similarity are identified.

[0843] 5. Copyright Risk Assessment

[0844] The server determines the copyright risk of the image being evaluated based on the results of the database comparison. If a match or high similarity is confirmed, the image is deemed not suitable for commercial use. Conversely, if no match or high similarity is confirmed, the image is deemed suitable for commercial use. As a criterion for evaluation, a threshold is considered, such as a similarity of 0.9 or higher being considered a high risk.

[0845] 6. Notification of Results

[0846] The server generates the results of the copyright risk assessment and notifies the user with specific messages such as "This image can be used for commercial purposes" or "This image may infringe copyright, so please avoid using it for commercial purposes." The user can then check the results on their own device.

[0847] Specific examples

[0848] Example 1: Rating images for non-commercial use

[0849] Users upload images for use on their websites, along with a prompt to "assess the risk of commercial use."

[0850] The server converts the format of the received images and performs feature extraction through an artificial intelligence model.

[0851] The server compares the extracted feature vectors with an existing database, and non-commercial images with high similarity are identified.

[0852] The server generates an evaluation result saying, "This image may infringe copyright, so please avoid using it for commercial purposes," and notifies the user.

[0853] Example 2: Evaluating images for commercial use

[0854] Users upload images for use in ads, along with a prompt to "assess the risk of commercial use."

[0855] The server converts the format of the received image and then extracts features using an artificial intelligence model.

[0856] The match does not identify a match or a highly similar image in the database.

[0857] The server generates an evaluation result that says "This image can be used commercially," and notifies the user.

[0858] In this way, by implementing this system, users can easily evaluate the copyright risk of images and quickly and accurately determine whether or not they can be used commercially.

[0859] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0860] Step 1: User uploads an image

[0861] A user accesses the system interface using a web browser and selects an image file to be evaluated. The user can also enter a prompt such as "Please evaluate the risk of commercial use." The user's device obtains the path of the selected image file and sends a request containing the image data to the server. The input is the image file, and the output is a request to the server.

[0862] Step 2: The server receives the image and performs some initial processing.

[0863] The server receives image files sent from the user's device. After receiving the image, the server checks the image format and converts it to the appropriate format if necessary. Specifically, it uses the OpenCV library to convert the image format to JPEG and compresses it if the size is too large. The input is the received image file, and the output is the processed and converted image file.

[0864] Step 3: The server uses the AI ​​model to extract features

[0865] The server inputs the initially processed image into a deep learning model to extract visual features. This artificial intelligence model uses TensorFlow and PyTorch to analyze features such as color, shape, and texture in the image. Specifically, the image is input into the model and a feature vector is obtained as the output. The input is the initially processed image file, and the output is the feature vector.

[0866] Step 4: The server checks against the existing database

[0867] The server compares the feature vector with an existing image database. In this step, it uses Cosine Similarity or Euclidean Distance to measure the similarity with the feature vector in the database. The database contains non-commercial images and copyright information, and it determines whether the feature vector matches or has a high similarity with them. The input is the extracted feature vector, and the output is a result indicating a match or a high similarity in the database.

[0868] Step 5: Server assesses copyright risk

[0869] The server determines the copyright risk of the image based on the matching results. For example, if the similarity is 0.9 or higher, it is considered a high risk, and if it is below that, it is considered a low risk. The input is the result of matching with the database, and the output is the copyright risk assessment result. A judgment is made as to whether the image is "commercially usable" or "not for commercial use."

[0870] Step 6: The server notifies the user of the evaluation results

[0871] The server generates the evaluation result and notifies the user's device. The notification is made via a web browser interface, displaying a message such as "This image can be used for commercial purposes" or "This image may infringe copyright, so please avoid using it for commercial purposes." The input is the copyright risk evaluation result, and the output is the notification message displayed to the user.

[0872] (Application example 1)

[0873] 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."

[0874] In recent years, the use of images on the Internet has increased, and the risk of copyright infringement in commercial use of images has become a serious issue. Advertising agencies and marketers, in particular, must quickly evaluate a large number of image materials, and in doing so, they are required to quickly and accurately determine the copyright risk of images. However, current manual checking methods are time-consuming, labor-intensive, and inefficient. To address this issue, the present invention aims to provide a system for evaluating the copyright risk of images used for advertising management in real time.

[0875] 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.

[0876] In this invention, the server includes means for users to upload images to be evaluated, means for receiving the uploaded images and performing initial processing, feature extraction means using an artificial intelligence model to extract visual features from the images, means for comparing the extracted features with an existing database and evaluating the degree of match or similarity, means for determining the copyright risk of the images based on the evaluation results, means for notifying the user of the determination results, and means for uploading images via a smartphone for advertising management and evaluating the copyright risk in real time. This enables users to quickly evaluate the copyright risk of images to be used as advertising material and immediately determine whether or not they can be used commercially.

[0877] "User" means a person or entity that uploads images to the system and receives the results of a copyright risk assessment.

[0878] An "image to be evaluated" is an image file uploaded by a user for commercial use.

[0879] "Upload" refers to the act of a user sending an image to be evaluated to the online system.

[0880] "Initial processing" is a series of processes that check the format of the received image and compress and convert it.

[0881] "Visual features" refer to information such as color, shape, and texture within an image, and are extracted using artificial intelligence.

[0882] An "artificial intelligence model" is an algorithm or system that uses deep learning technology to analyze visual features.

[0883] "Feature extraction means" refers to technical means or tools for extracting visual features from an image.

[0884] An "existing database" is an information collection that stores image data collected in the past and its copyright information.

[0885] "Matching" is the act of comparing extracted visual features with an existing database to evaluate the degree of match or similarity.

[0886] "Similarity" is a measure of the visual match between an image and an existing image in a database.

[0887] The "evaluation result" is the copyright risk assessment result derived based on the matching of visual features.

[0888] "Copyright risk" refers to the degree of likelihood that the image being evaluated constitutes copyright infringement.

[0889] "Notification" refers to the act of informing the user of the evaluation results.

[0890] "For advertising management" refers to the purpose of managing and evaluating images used as advertising materials.

[0891] A "smartphone" is a portable communication device that can connect to the Internet and use multi-function applications.

[0892] "Real-time" means that the time from when a user uploads an image to when the evaluation result is notified is extremely short, and processing is immediate.

[0893] The present invention provides a system for evaluating the copyright risk of images in real time, specially designed for advertising management, which mainly uses a server, a smartphone terminal, and an artificial intelligence (AI) model.

[0894] Overall system configuration

[0895] The system includes the following main components:

[0896] 1. User terminal: A smartphone is used, providing a means for users to upload images as advertising materials.

[0897] 2. Server: Receives uploaded images, performs initial processing, extracts visual features, matches them with databases, assesses copyright risk, and notifies the results.

[0898] 3. Artificial intelligence model: Deep learning techniques are used to analyze visual features in images.

[0899] Program processing overview

[0900] 1. User image upload

[0901] The user uses a dedicated smartphone application to select an image to be evaluated and upload it to the system, which obtains the image's file path and sends it to the server.

[0902] 2. Server Reception and Initial Processing

[0903] The server receives the image file sent from the user terminal. It checks the format of the received image file and performs image compression or format conversion as necessary. For example, it converts the image to JPEG format or compresses the image size.

[0904] 3. Feature extraction using AI models

[0905] The server inputs the processed image into an artificial intelligence model to extract visual features. This model uses ResNet50, built using TensorFlow, which extracts visual features such as color, shape, and texture from the image as vectors.

[0906] 4. Matching with existing databases

[0907] The server compares the extracted feature vector with an existing image database. For comparison, it uses the cosine_similarity function from the scikit-learn library to calculate the similarity to images in the database. If the highest similarity exceeds a predetermined threshold, it is determined to have a high copyright risk.

[0908] 5. Copyright Risk Assessment and Notification of Results

[0909] The server evaluates the copyright risk of the image based on the results of the database comparison. The evaluation results are sent to the user's smartphone in real time. The user can then check the results, such as "There is a risk of copyright infringement" or "Commercial use is permitted," via a dedicated application.

[0910] Hardware and software used

[0911] Hardware: Smartphones, servers

[0912] software:

[0913] TensorFlow: Used to implement the artificial intelligence model (ResNet50) and extract features

[0914] Pillow: Used for initial image processing (format conversion and resizing)

[0915] scikit-learn: Used to compare similarity between feature vectors (cosine_similarity)

[0916] Specific examples

[0917] Example 1: Marketer use case

[0918] Marketers upload images to be used as advertising materials for new products from their smartphones, and the images are evaluated through an AI model, which immediately informs them that they are "suitable for commercial use."

[0919] Example 2: Advertising agency use case

[0920] Advertising agencies use a smartphone application to simultaneously evaluate multiple advertising materials. The application allows users to upload images in bulk, and the server evaluates the copyright risk of each image and notifies users of the results individually.

[0921] Prompt Sentence Examples

[0922] Upload a new image "example.jpg" as advertising material and assess its copyright risk.

[0923] Run the assessment and view the results.

[0924] Specify the file path:

[0925] file_path = "example.jpg"

[0926] main(file_path)

[0927] In this way, by using the system of the present invention, users can easily evaluate the copyright risk of advertising materials and quickly determine whether or not they can be used commercially.

[0928] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0929] Step 1:

[0930] The user selects an image to be evaluated as advertising material and uploads it to the system through a smartphone application. Specifically, the user uses the app's interface to select an image from the device's storage and clicks the upload button. This step inputs the selected image file. The app then sends this image file to the server.

[0931] Step 2:

[0932] The server receives image files sent from the user device and performs initial processing. It checks the format of the received image file, converts it to JPEG format if necessary, and compresses the image size. Specifically, it uses the Pillow library to convert the image format and resize it. The input is the image data sent from the smartphone, and the output is the image data after initial processing has been completed.

[0933] Step 3:

[0934] The server inputs the pre-processed image into an artificial intelligence model to extract visual features. Specifically, it uses a ResNet50 model built using TensorFlow to extract visual information such as the image's color, shape, and texture as a feature vector. The input at this stage is the pre-processed image data, and the output is the extracted visual feature vector.

[0935] Step 4:

[0936] The server compares the extracted feature vector with an existing database. Specifically, it calculates the similarity between the extracted feature vector and an existing image in the database using the cosine_similarity function in the scikit-learn library. The input is the visual feature vector and the feature vector in the database, and the output is a similarity score.

[0937] Step 5:

[0938] The server evaluates copyright risk based on the results of database matching. If the similarity score exceeds a predetermined threshold, the image is deemed to have a high risk of copyright infringement. The input is the similarity score, and the output is the copyright risk assessment result. Specifically, it generates an assessment result such as "There is a risk of copyright infringement" or "Commercial use is permitted."

[0939] Step 6:

[0940] The server notifies the user of the results of the copyright risk assessment via their smartphone. Specifically, the assessment results are sent to a dedicated application and displayed to the user as a notification message. The input is the copyright risk assessment result, and the output is a notification message sent to the user's device. The user can then check the results to determine whether or not the advertising material can be used commercially.

[0941] In this way, users can easily use their smartphones to evaluate the copyright risks of advertising materials and make appropriate usage decisions.

[0942] 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.

[0943] The present invention combines a system for assessing the risk of copyright infringement of images for commercial use with an emotion engine that recognizes user emotions. This system includes the following means: a means for a user to upload images to be assessed, a means for receiving the uploaded images and performing initial processing, a feature extraction means using an artificial intelligence model to extract visual features from the images, a means for comparing the extracted features with an existing database and assessing their match or similarity, a means for determining the copyright risk of the images based on the assessment results, a means for notifying the user of the assessment results, and an emotion engine that recognizes user emotions.

[0944] A specific embodiment of this system is described below.

[0945] System Operation Overview

[0946] 1. User image upload

[0947] The user accesses the interface provided through a web browser, selects and uploads the image file to be evaluated, and the user's device acquires the path of this image file and sends it to the system.

[0948] 2. Server Reception and Initial Processing

[0949] The server receives the image file sent from the user's device. The server checks the format of the image file and compresses or converts the image as necessary. For example, images that are too large will be compressed, and images in an unsupported format (such as BMP or GIF) will be converted to JPEG format.

[0950] 3. Feature extraction using AI models

[0951] The server inputs the received image into an artificial intelligence model to extract visual features. The server uses a deep learning model (e.g., CNN) to analyze visual information such as the image's color, shape, and texture. As a result of the analysis, a feature vector is generated and used for subsequent processing.

[0952] 4. Checking existing databases

[0953] The server compares the extracted feature vector with an existing image database, which stores images that are not for commercial use and copyright-related information. The server performs a database search using the feature vector as a key to identify images that match or have a high degree of similarity.

[0954] 5. Copyright Risk Assessment

[0955] The server determines the copyright risk of the image being evaluated based on the results of the database comparison. If the server finds a match or a high degree of similarity, it determines that the image cannot be used commercially. Conversely, if the server finds no match or high degree of similarity, it determines that the image can be used commercially.

[0956] 6. Recognition of user emotions by emotion engine

[0957] The device uses the user's camera and microphone to enable the emotion engine to recognize the user's emotions in real time. The emotion engine uses facial expression analysis and tone of voice analysis to determine whether the user is in an emotional state such as excitement, joy, or anger.

[0958] 7. Result output and emotional notifications

[0959] When the server notifies the user of the generated evaluation results, it changes the notification method based on the recognition results of the emotion engine. For example, if the user is feeling stressed, it will notify the result in gentler terms, and conversely, if the user is excited, it will notify them in a more concise manner.

[0960] Users can check the evaluation results on their own devices in a web browser, which may display a message such as "This image can be used for commercial purposes" or "Please avoid using this image for commercial purposes as there is a risk of copyright infringement."

[0961] Specific examples

[0962] Example 1: Rating and responding to sentiment for images that are not suitable for commercial use

[0963] Users upload images for inclusion on their websites.

[0964] Images received by the server undergo feature extraction through an artificial intelligence model.

[0965] The extracted features are found to have a high degree of similarity to known non-commercial images in the database.

[0966] The server determines that "this image poses a risk of copyright infringement, so please avoid using it for commercial purposes," and notifies the user of the result.

[0967] The user's device uses a camera and microphone to allow the emotion engine to recognize the user's emotions and determine whether they are feeling stressed.

[0968] The server notifies the user of the evaluation results in gentle language designed to reduce stress.

[0969] Example 2: Ratings and positive emotional responses for commercially available images

[0970] Users upload images for use in marketing materials.

[0971] The server extracts features from the received image and compares them with an existing database.

[0972] It is determined that there are no images in the database that have a match or a high degree of similarity.

[0973] The server determines that "this image can be used commercially" and notifies the user of the result.

[0974] The user's device recognizes the user's emotions through an emotion engine and detects the emotion of joy.

[0975] The server notifies the user of the evaluation results in simple and positive terms.

[0976] In this way, by using the system of the present invention, it is possible to efficiently evaluate the copyright risk of commercial images and to provide notifications that take into consideration the user's feelings.

[0977] The processing flow will be explained below.

[0978] Step 1:

[0979] A user accesses the application and clicks the "Upload Image" button. The user selects an image file to be evaluated and starts uploading. The user's device obtains the path of the selected image file and inserts the file into the upload stream.

[0980] Step 2:

[0981] The server receives the image file sent from the user's device. The server checks the format of the image file and compresses or converts the image as necessary. For example, an image that is too large will be compressed, or if the format is not supported, it will be converted to JPEG format.

[0982] Step 3:

[0983] The server inputs the received image into an artificial intelligence model to extract visual features. The server uses a deep learning model to analyze the image's visual information, such as color, shape, and texture. As a result of the analysis, a feature vector is generated.

[0984] Step 4:

[0985] The server compares the extracted feature vector with an existing image database, which stores images that are not for commercial use and copyright-related information. The server then searches the database using the feature vector as a key to identify images that match or have a high degree of similarity.

[0986] Step 5:

[0987] The server determines the copyright risk of the image being evaluated based on the results of the database comparison. If the server finds a match or a high degree of similarity, it determines that the image cannot be used commercially. Conversely, if the server finds no match or high degree of similarity, it determines that the image can be used commercially.

[0988] Step 6:

[0989] The device uses the user's camera and microphone to enable the emotion engine to recognize the user's emotions in real time. The emotion engine uses facial expression analysis and tone of voice analysis to determine whether the user is in an emotional state such as excitement, joy, or anger.

[0990] Step 7:

[0991] The server changes the notification method based on the recognition results of the emotion engine. For example, if the user is feeling stressed, the server notifies the user in a gentle manner, whereas if the user is excited, the server notifies the user in a concise manner.

[0992] Step 8:

[0993] The server notifies the user's device of the evaluation results it has generated. The server then sends the results to the user's device as an HTTP response in JSON format or similar. The user can then check the evaluation results on their device's web browser.

[0994] Step 9:

[0995] The user checks the evaluation results sent from the server on the web application interface. The user's device receives the response from the server and displays it to the user in an appropriate format. For example, it displays specific content such as "This image can be used for commercial purposes" or "Please avoid using this image for commercial purposes as there is a risk of copyright infringement."

[0996] Example 2

[0997] 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."

[0998] In assessing the copyright risk of images intended for commercial use, existing systems have the problem of being unable to accurately assess the copyright risk of images and not giving consideration to the user's feelings when notifying them. In particular, not taking the user's feelings into consideration when notifying them of the copyright risk assessment results can cause unnecessary stress and confusion for the user.

[0999] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving uploaded images and performing initial processing, feature extraction means using an artificial intelligence model to extract visual features from the images, means for comparing the extracted features with an existing database and evaluating the degree of match or similarity, means for determining the copyright risk of the images based on the evaluation results, means for notifying the user of the evaluation results, and an emotion engine for recognizing the user's emotions and adjusting the method of notifying the evaluation results. This not only enables efficient and accurate evaluation of the copyright risk of images, but also enables appropriate notification that takes the user's emotions into consideration.

[1000] "User" refers to a user who uses the system to upload images and have them assessed for copyright risk.

[1001] "Server" refers to a computer system that receives images sent from a user's terminal and is responsible for all processing, including initial processing, feature extraction, database matching, and notification of evaluation results.

[1002] "Terminal" refers to a device accessed by a user, including a web browser and related hardware devices for uploading images and checking evaluation results.

[1003] "Image" refers to the visual data to be evaluated that users upload to the system, and includes common image formats such as JPEG and PNG.

[1004] "Visual features" are information extracted from an image, including color, shape, texture, and other attributes necessary for image recognition and feature vector generation.

[1005] "Artificial intelligence model" refers to an algorithm or network model used to extract visual features using deep learning techniques, including convolutional neural networks (CNNs).

[1006] "Database" refers to an information system that stores existing image data and associated copyright information against which extracted feature vectors can be matched.

[1007] A "feature vector" is a data set that quantifies the visual features of an image, and is used for matching with a database and evaluating similarity.

[1008] "Emotion engine" refers to the algorithms and software modules used to recognize a user's emotions, analyzing data acquired through the camera and microphone.

[1009] The "evaluation result" is a conclusion generated based on the copyright risk assessment, and is notified to the user in the form of "Commercial use is permitted" or "Commercial use should be avoided."

[1010] The "notification method" refers to the means or format for notifying the user of the evaluation results, and is adjusted according to the user's emotional state.

[1011] The present invention is a system for assessing the risk of copyright infringement of images intended for commercial use, which is combined with an emotion engine that recognizes user emotions. This system includes the following means: a means for a user to upload an image to be assessed, a means for receiving the uploaded image and performing initial processing, a feature extraction means using an artificial intelligence model to extract visual features from the image, a means for comparing the extracted features with an existing database and evaluating the degree of match or similarity, a means for determining the copyright risk of the image based on the assessment result, a means for notifying the user of the assessment result, and an emotion engine that recognizes user emotions.

[1012] System Operation Overview

[1013] 1. User image upload

[1014] The user accesses the interface provided through a web browser, selects and uploads the image file to be evaluated, and the user's device obtains the path of this image file and sends it to the system.

[1015] 2. Server Reception and Initial Processing

[1016] The server receives the image file sent from the terminal. After receiving it, it checks the format of the image file and compresses or converts the image as necessary. For example, large images are compressed, and images in unsupported formats (such as BMP or GIF) are converted to JPEG format.

[1017] 3. Feature extraction using AI models

[1018] The server inputs the received image into an artificial intelligence model (e.g., CNN) using deep learning technology to extract visual features. The analyzed feature vectors are used for database matching.

[1019] 4. Checking existing databases

[1020] The server uses the feature vector as a key to match existing image data and associated copyright information in a database that stores images and copyright information that are not for commercial use.

[1021] 5. Copyright Risk Assessment

[1022] The server determines the copyright risk of the image being evaluated based on the results of the database comparison. If a high degree of similarity is found, the image is deemed "unsuitable for commercial use," but if the match or similarity is low, it is deemed "available for commercial use."

[1023] 6. Recognition of user emotions by emotion engine

[1024] The device uses a camera and microphone to capture the user's facial expressions and tone of voice in real time, and analyzes the captured data with an emotion engine (e.g., Microsoft Azure's Emotion API) to determine the user's emotional state (e.g., excitement, joy, anger, stress).

[1025] 7. Result output and emotional notifications

[1026] The server generates an evaluation result and sends it to the device in a format that corresponds to the user's emotional state based on the judgment of the emotion engine. For example, if the user is feeling stressed, the server will notify them in gentle words, and if the user is excited, the server will notify them in a concise manner.

[1027] Users can check the evaluation results on their device in a web browser, which will display messages such as "Commercial use is permitted" or "Please avoid commercial use due to the risk of copyright infringement."

[1028] Specific examples

[1029] Example 1: Rating and responding to sentiment for images that are not suitable for commercial use

[1030] Users upload images for inclusion on their websites.

[1031] The image received by the server undergoes feature extraction through an artificial intelligence model.

[1032] The extracted features are found to have a high degree of similarity to known non-commercial images in the database.

[1033] The server determines that "This image poses a risk of copyright infringement, so please avoid using it for commercial purposes," and notifies the user of the result.

[1034] The user's device uses a camera and microphone to allow the emotion engine to recognize the user's emotions and determine whether they are feeling stressed.

[1035] The server will notify you of the evaluation results in gentle language.

[1036] Example 2: Ratings and positive emotional responses for commercially available images

[1037] Users upload images for use in marketing materials.

[1038] The server extracts features from the received image and compares them with an existing database.

[1039] It is determined that there are no images in the database that have a match or a high degree of similarity.

[1040] The server determines that "this image can be used commercially" and notifies the user of the result.

[1041] The user's device recognizes the user's emotions through an emotion engine and detects the emotion of joy.

[1042] The server will notify you of the evaluation results in simple and positive terms.

[1043] Prompt Sentence Examples

[1044] Example 1: A user who uploads a non-commercial image experiences frustration

[1045] "Please rate whether this image is safe for commercial use."

[1046] Example 2: A user expresses joy by uploading an image that can be used commercially.

[1047] "Can I use this image in my marketing materials?"

[1048] In this way, by using the system of the present invention, it is possible to efficiently evaluate the copyright risk of commercial images and provide notifications that take into consideration the user's feelings.

[1049] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1050] Processing steps of this system's program

[1051] Step 1: Upload user image

[1052] The user accesses a web browser, selects the image file to be evaluated, and clicks the upload button. The image file path selected by the user is obtained as input. Based on this path, the terminal sends the image file to the system. Specifically, the image file is sent to the server via an HTTP POST request.

[1053] Step 2: Server reception and initial processing

[1054] The server receives image files sent from the terminal. As input, the image file data arrives at the server. The server checks the format of the image file and compresses or converts the image as necessary. For example, files in a format other than JPEG are converted to JPEG, and files that are too large are compressed. As output, the image file data after initial processing is obtained.

[1055] Step 3: Feature extraction using an AI model

[1056] The server inputs the received image into an artificial intelligence model (such as CNN) that uses deep learning technology. An initially processed image file is obtained as input. The server analyzes this image and extracts visual features (color, shape, texture, etc.) as a feature vector. Specific examples include using TensorFlow or PyTorch. The feature vector is obtained as output.

[1057] Step 4: Check the existing database

[1058] The server compares the feature vector with an existing image database. The input is the feature vector. The server searches the database using an SQL query to identify image data that matches or has a high degree of similarity. The output is the matching result.

[1059] Step 5: Copyright Risk Assessment

[1060] The server determines the copyright risk of the image being evaluated based on the database match results. The database match results are received as input. The server determines the risk level using a rule-based or machine learning model. The copyright risk assessment result is received as output.

[1061] Step 6: Recognizing user emotions with the emotion engine

[1062] The device uses a camera and microphone to capture the user's facial expressions and voice in real time. Video and audio data are obtained as input. This data is analyzed by an emotion engine (e.g., Emotion API) to determine the user's emotional state (joy, anger, stress, etc.). The emotional state is obtained as output.

[1063] Step 7: Output the results and notify based on the emotion

[1064] The server generates an evaluation result and transmits it to the device in a format that corresponds to the user's emotional state based on the emotion engine's judgment. The copyright risk evaluation result and the user's emotional state are received as input. The server selects an appropriate way to express the result and transmits it to the device via an HTTP response. The output is the evaluation result that is displayed on the user's device.

[1065] Users can check the evaluation results on their device via a web browser, which allows them to understand the copyright risks of commercial images and make appropriate decisions based on that information.

[1066] Specific prompt examples

[1067] Example 1: A user who uploads a non-commercial image experiences frustration

[1068] "Please rate whether this image is safe for commercial use."

[1069] Example 2: A user expresses joy by uploading an image that can be used commercially.

[1070] "Can I use this image in my marketing materials?"

[1071] In this way, by using the system of the present invention, it is possible to efficiently and accurately evaluate the copyright risk of an image and to provide a notification that takes into consideration the user's feelings.

[1072] (Application example 2)

[1073] 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."

[1074] Currently, there is a demand for a system that can efficiently evaluate the copyright risk of images intended for commercial use. However, existing systems have the problem of conveying results in a uniform manner without taking the user's emotional state into consideration, resulting in a poor user experience. It is necessary to develop a system that solves this problem and supports smoother commercial use by providing notifications that take the user's emotions into consideration.

[1075] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1076] In this invention, the server includes means for a user to upload an image to be evaluated, means for receiving the uploaded image and performing initial processing, means for extracting visual features from the image using an artificial intelligence model, means for comparing the image with an existing database and evaluating the degree of match or similarity, means for determining the copyright risk of the image based on the evaluation result, means for notifying the user of the determination result, means for recognizing the user's emotional state, and means for optimizing the notification method based on the user's emotional state. This makes it possible to efficiently evaluate the copyright risk of images intended for commercial use and to provide notification that takes the user's emotions into consideration.

[1077] "User" means any individual or legal entity that wishes to use the system to assess the copyright risk of an image.

[1078] An "image to be evaluated" is an image file uploaded by a user for commercial use.

[1079] "Means for uploading" refers to an interface or program that allows a user to send images to be evaluated to the system.

[1080] The "means for performing initial processing" is a function for performing processing such as compression, format conversion, and resizing of received images.

[1081] "Visual features" are feature information extracted by image analysis, such as the color, shape, and texture of an image.

[1082] An "artificial intelligence model" is a model that uses deep learning technology and is used to extract visual features from images.

[1083] "Feature extraction means" is a function that extracts visual features of an image using an artificial intelligence model.

[1084] A "database" is a searchable repository of existing, non-commercially available images and copyright-related information.

[1085] The "means for matching and evaluating the degree of match or similarity" is a function for comparing the extracted features with image features in a database and calculating the degree of match or similarity.

[1086] The "evaluation result" is information used to determine whether there is a copyright risk.

[1087] The "means for determining copyright risk" is a function that determines whether an image can be used commercially based on the evaluation results.

[1088] "Means of notification" refers to means for communicating the judgment results to the user, and includes web browser, email, in-app notification, etc.

[1089] "Emotional state" is the result of a real-time analysis of a user's emotions, including excitement, joy, anger, stress, etc.

[1090] The "means for recognizing emotional state" is a function that analyzes the user's emotions in real time using the user's camera and microphone.

[1091] The "means for optimizing the notification method" is a function for adjusting the notification method and content of the judgment result based on the emotional state of the user.

[1092] The system according to the present invention evaluates the copyright risk of images for commercial use and provides optimal notification according to the user's emotional state. This system is configured and operates as follows.

[1093] The system includes a means for users to upload images to be evaluated. The user selects an image file through a web browser or a dedicated application and uploads it to the system. At this point, the user's device obtains the path to the image file and sends it to the server. The uploaded image is received by the server and undergoes initial processing, which may include image compression, resizing, and format conversion.

[1094] The server then inputs the received image into an artificial intelligence model to extract visual features. This AI model uses deep learning technology, specifically a convolutional neural network (CNN) model. It analyzes visual information such as the image's color, shape, and texture to generate a feature vector.

[1095] The generated feature vector is compared with an existing database stored on the server. The database contains images that are not for commercial use and copyright-related information, and a database search is performed using the feature vector as a key. The server evaluates the degree of match and similarity based on the search results and derives an evaluation result.

[1096] Based on the evaluation results, the server determines the copyright risk of the image. If the image being evaluated is determined to be unsuitable for commercial use, the server notifies the user. A similar notification is also given if the image is determined to be suitable for commercial use. However, what is unique about this system is that the notification is given taking into account the user's emotional state.

[1097] The server uses the device's camera and microphone to recognize the user's emotional state. Emotion Engine is used for emotion recognition. Facial expressions are analyzed from the camera and tone of voice is analyzed from the microphone to determine whether the user is in an emotional state such as excitement, joy, anger, or stress. Based on this determination, the server optimizes the method of notifying the evaluation result. For example, if the user is feeling stressed, the server will notify them in soft language, and conversely, if the user is excited, the server will notify them in a concise manner.

[1098] Specific examples of prompts are as follows:

[1099] Your custom script will use the smartphone's camera and microphone to recognize user emotions and assess the copyright risk of uploaded images. The deep learning model will extract image features and compare them with a database to assess risk. Emotion Engine will be used for emotion recognition, and the results will be fed back to the user in the form of a notification message based on the emotion.

[1100] In this way, the system can efficiently assess the copyright risk of images intended for commercial use and further improve the user experience by providing notifications that take into account the user's emotional state.

[1101] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1102] Step 1:

[1103] User image upload

[1104] The user uploads the image to be evaluated from their own device. The input is an image file (e.g., JPEG or PNG), and the output is the transmission of the image file to the server. The user selects an image through a web browser or a dedicated application and clicks the upload button to obtain the path of the image file and send it to the server.

[1105] Step 2:

[1106] Server reception and initial processing

[1107] The server receives the image file sent by the user and performs initial processing. The input is the received image file, and the output is the processed image file. At this stage, the server checks the image format and performs compression or format conversion (e.g., from BMP to JPEG) as necessary. The image may also be resized.

[1108] Step 3:

[1109] Feature extraction using AI models

[1110] The server inputs the image after initial processing into an artificial intelligence model to extract visual features. The input is the processed image file, and the output is a feature vector. The server uses deep learning technology (e.g., CNN) to analyze visual information such as the color, shape, and texture of the image and generate a feature vector.

[1111] Step 4:

[1112] Checking an existing database

[1113] The server compares the extracted feature vector with an existing database. The input is the feature vector and database information, and the output is the evaluation result of the degree of match or similarity. The server performs a database search using the feature vector as a key to identify images that match or have a high degree of similarity.

[1114] Step 5:

[1115] Copyright Risk Assessment

[1116] The server determines the copyright risk of the image being evaluated based on the results of the database match. The input is the evaluation result of the database match, and the output is the copyright risk judgment result. If the server finds a match or a high similarity, it determines that the image is not commercially available; otherwise, it determines that the image is commercially available.

[1117] Step 6:

[1118] Recognizing user emotions with an emotion engine

[1119] The emotion engine on the user's device uses a camera and microphone to recognize the user's emotions in real time. The input is camera footage and audio data, and the output is the user's emotional state (excitement, joy, anger, stress, etc.). The emotion engine analyzes facial expressions and tone of voice to determine the user's emotional state.

[1120] Step 7:

[1121] Result output and emotional notifications

[1122] When the server notifies the user's device of the generated evaluation results, it changes the notification method based on the recognition results of the emotion engine. The input is the copyright risk assessment result and the user's emotional state, and the output is a notification message that takes the emotion into consideration. For example, if the user is feeling stressed, the result will be notified in soft language, and conversely, if the user is excited, the notification will be concise.

[1123] Through these processing steps, the system can efficiently assess the copyright risk of images intended for commercial use and provide notifications that take into account the user's emotional state.

[1124] 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.

[1125] 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.

[1126] 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.

[1127] [Fourth embodiment]

[1128] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1129] 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.

[1130] 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).

[1131] 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.

[1132] 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.

[1133] 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).

[1134] 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.

[1135] 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.

[1136] 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.

[1137] 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.

[1138] 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.

[1139] 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.

[1140] 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."

[1141] The present invention provides a system for assessing the risk of copyright infringement of images for commercial use, which includes a means for allowing a user to upload images to be assessed, a means for receiving the uploaded images and performing initial processing, a means for extracting visual features from the images using an artificial intelligence model, a means for comparing the extracted features with an existing database and assessing the degree of match or similarity, a means for determining the copyright risk of the images based on the assessment results, and a means for notifying the user of the assessment results.

[1142] A specific embodiment of this system is described below.

[1143] System Operation Overview

[1144] 1. User image upload

[1145] The user accesses the interface provided through a web browser, selects and uploads an image to be evaluated, and the user's device acquires the path of this image file and sends it to the system.

[1146] 2. Server Reception and Initial Processing

[1147] The server receives the image file sent from the user's device. During this process, the server checks the format of the image file and compresses or converts the image if necessary. For example, if the image is too large, it is compressed and converted into a usable format (e.g., JPEG).

[1148] 3. Feature extraction using AI models

[1149] The server inputs the received image into an AI model to extract visual features. The AI ​​model uses deep learning techniques to analyze visual information such as color, shape, and texture in the image. The resulting feature vector is used for subsequent database matching.

[1150] 4. Checking existing databases

[1151] The server compares the extracted feature vector with an existing image database, which stores images that are prohibited for commercial use and copyright information. The server performs a search using the feature vector as a key to identify matching or similar images.

[1152] 5. Copyright Risk Assessment

[1153] The server determines the copyright risk of the image being evaluated based on the results of the database match. If an identical or highly similar image is found, the image is deemed unsuitable for commercial use. If there is no match or high similarity, the image is deemed suitable for commercial use.

[1154] 6. Output and notification of results

[1155] The server generates the copyright risk assessment results and notifies the user's device. The user can then check the results on their device's web browser. For example, the results may include messages such as "This image may be used for commercial purposes" or "This image may infringe copyright, so please avoid using it for commercial purposes."

[1156] Specific examples

[1157] Example 1: Rating images for non-commercial use

[1158] Users upload images for inclusion on their websites.

[1159] Images received by the server undergo feature extraction through an artificial intelligence model.

[1160] The extracted features are found to have a high degree of similarity to known non-commercial images in the database.

[1161] The server determines that "this image poses a risk of copyright infringement, so please avoid using it for commercial purposes," and notifies the user of the result.

[1162] Example 2: Rating images for commercial use

[1163] Users upload images for use in marketing materials.

[1164] The server extracts features from the received image and compares them with an existing database.

[1165] It is determined that there are no images in the database that have a match or a high degree of similarity.

[1166] The server determines that "this image can be used commercially" and notifies the user of the result.

[1167] In this way, by using the system of the present invention, users can easily and quickly evaluate the copyright risk of images and determine whether or not they can be used commercially.

[1168] The processing flow will be explained below.

[1169] Step 1:

[1170] A user accesses the application and clicks the "Upload Image" button. The user selects an image file to be evaluated and starts uploading. The user's device obtains the path of the selected image file and inserts the file into the upload stream.

[1171] Step 2:

[1172] The server receives the image file sent from the user's device. The server checks the format of the image file and compresses or converts the image as necessary. For example, images that are too large will be compressed, and images in an unsupported format (such as BMP or GIF) will be converted to JPEG format.

[1173] Step 3:

[1174] The server inputs the received image into an artificial intelligence model to extract visual features. The server uses a deep learning model (e.g., CNN) to analyze visual information such as the image's color, shape, and texture. As a result of the analysis, a feature vector is generated and used for subsequent processing.

[1175] Step 4:

[1176] The server compares the extracted feature vector with an existing image database, which stores images that are not for commercial use and copyright-related information. The server then searches the database using the feature vector as a key to identify images that match or have a high degree of similarity.

[1177] Step 5:

[1178] The server determines the copyright risk of the image being evaluated based on the results of the database comparison. If the server finds a match or a high degree of similarity, it determines that the image cannot be used commercially. Conversely, if the server finds no match or high degree of similarity, it determines that the image can be used commercially.

[1179] Step 6:

[1180] The server notifies the user's device of the risk assessment results it has generated. The server then sends the assessment results to the user's device as an HTTP response, sending the results in JSON format or similar. The user can then check the assessment results on their own device's web browser.

[1181] Step 7:

[1182] The user checks the evaluation results sent from the server on the web application interface. The user's device receives the response from the server and displays it to the user in an appropriate format. For example, it displays specific content such as "This image can be used for commercial purposes" or "Please avoid using this image for commercial purposes as there is a risk of copyright infringement."

[1183] Example 1

[1184] 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."

[1185] Previous image copyright risk assessment systems had problems with low assessment accuracy and lacked reliability for commercial use. Furthermore, they lacked sufficient use of AI models to extract visual features and compare them with databases, resulting in a high likelihood of false positives. This made it difficult for companies and individuals to make appropriate decisions to avoid the risk of copyright infringement.

[1186] 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.

[1187] In this invention, the server includes means for users to upload images to be evaluated, means for receiving the uploaded images and performing initial processing, means for extracting visual features from the images using an artificial intelligence model, means for comparing the extracted features with an existing database and evaluating the degree of match or similarity, means for determining the copyright risk of the images based on the evaluation results, and means for notifying the user of the determination results. This makes it possible to evaluate the copyright risk of images with high accuracy and quickly and accurately determine whether or not they can be used commercially.

[1188] "User" means any person or entity that uses the System to assess the copyright risk of Images.

[1189] "Upload" refers to the act of a user sending an image file to be evaluated to the system.

[1190] "Receiving" refers to the act of the server receiving the image file sent by the user.

[1191] "Initial processing" refers to the process of performing preprocessing such as format confirmation, compression, and format conversion of received images.

[1192] "Visual features" refers to the characteristic information of an image, such as color, shape, or texture, extracted through a deep learning model.

[1193] "Artificial intelligence model" refers to a mathematical and computational structure for extracting visual features using deep learning techniques.

[1194] A "feature vector" refers to data that numerically represents visual features extracted by an artificial intelligence model.

[1195] "Matching" refers to the process of comparing the extracted feature vectors with those in an existing database.

[1196] "Database" means a data storage facility for storing uncommercially protected images and associated copyright information.

[1197] "Match" refers to the state where the extracted feature vector is exactly the same as the feature vector in the database.

[1198] "Similarity" refers to a measure that numerically indicates how similar the extracted feature vector is to the feature vector in the database.

[1199] "Evaluation Results" refers to the results report for determining the copyright risk of an image.

[1200] "Notification" refers to the act of informing the user of the evaluation results.

[1201] This invention is a system for assessing the risk of copyright infringement of images for commercial use. This system allows users to upload images to be assessed, and then goes through a series of processes to extract, match, and assess visual features from the images, and finally notifies users of the assessment results.

[1202] System Configuration

[1203] 1. User image upload

[1204] The user accesses the interface provided through a web browser, selects an image to be evaluated, and uploads the image along with the prompt, "Please evaluate the risk of commercial use." At this time, the user's device obtains the path to the image file and sends the image data to the server.

[1205] 2. Server Reception and Initial Processing

[1206] The server receives the image file sent from the user's device. After receiving it, the server checks the image format and converts it to the appropriate format. Specifically, it uses an image processing library such as OpenCV to convert it to JPEG format and compress the size.

[1207] 3. Feature extraction using AI models

[1208] The server then inputs the received images into an AI model to extract visual features. This AI model uses deep learning frameworks such as TensorFlow and PyTorch to analyze features such as color, shape, and texture in the image. The resulting feature vector is used in the next stage of the matching process.

[1209] 4. Matching with existing databases

[1210] The server then matches the extracted feature vectors with an existing image database. Using similarity measures such as Cosine Similarity and Euclidean Distance, the server compares the extracted feature vectors with known non-commercial images and copyright-related information in the database. The database contains feature vectors of non-commercial images, and images with high similarity are identified.

[1211] 5. Copyright Risk Assessment

[1212] The server determines the copyright risk of the image being evaluated based on the results of the database comparison. If a match or high similarity is confirmed, the image is deemed not suitable for commercial use. Conversely, if no match or high similarity is confirmed, the image is deemed suitable for commercial use. As a criterion for evaluation, a threshold is considered, such as a similarity of 0.9 or higher being considered a high risk.

[1213] 6. Notification of Results

[1214] The server generates the results of the copyright risk assessment and notifies the user with specific messages such as "This image can be used for commercial purposes" or "This image may infringe copyright, so please avoid using it for commercial purposes." The user can then check the results on their own device.

[1215] Specific examples

[1216] Example 1: Rating images for non-commercial use

[1217] Users upload images for use on their websites, along with a prompt to "assess the risk of commercial use."

[1218] The server converts the format of the received images and performs feature extraction through an artificial intelligence model.

[1219] The server compares the extracted feature vectors with an existing database, and non-commercial images with high similarity are identified.

[1220] The server generates an evaluation result saying, "This image may infringe copyright, so please avoid using it for commercial purposes," and notifies the user.

[1221] Example 2: Evaluating images for commercial use

[1222] Users upload images for use in ads, along with a prompt to "assess the risk of commercial use."

[1223] The server converts the format of the received image and then extracts features using an artificial intelligence model.

[1224] The match does not identify a match or a highly similar image in the database.

[1225] The server generates an evaluation result that says "This image can be used commercially," and notifies the user.

[1226] In this way, by implementing this system, users can easily evaluate the copyright risk of images and quickly and accurately determine whether or not they can be used commercially.

[1227] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1228] Step 1: User uploads an image

[1229] A user accesses the system interface using a web browser and selects an image file to be evaluated. The user can also enter a prompt such as "Please evaluate the risk of commercial use." The user's device obtains the path of the selected image file and sends a request containing the image data to the server. The input is the image file, and the output is a request to the server.

[1230] Step 2: The server receives the image and performs some initial processing.

[1231] The server receives image files sent from the user's device. After receiving the image, the server checks the image format and converts it to the appropriate format if necessary. Specifically, it uses the OpenCV library to convert the image format to JPEG and compresses it if the size is too large. The input is the received image file, and the output is the processed and converted image file.

[1232] Step 3: The server uses the AI ​​model to extract features

[1233] The server inputs the initially processed image into a deep learning model to extract visual features. This artificial intelligence model uses TensorFlow and PyTorch to analyze features such as color, shape, and texture in the image. Specifically, the image is input into the model and a feature vector is obtained as the output. The input is the initially processed image file, and the output is the feature vector.

[1234] Step 4: The server checks against the existing database

[1235] The server compares the feature vector with an existing image database. In this step, it uses Cosine Similarity or Euclidean Distance to measure the similarity with the feature vector in the database. The database contains non-commercial images and copyright information, and it determines whether the feature vector matches or has a high similarity with them. The input is the extracted feature vector, and the output is a result indicating a match or a high similarity in the database.

[1236] Step 5: Server assesses copyright risk

[1237] The server determines the copyright risk of the image based on the matching results. For example, if the similarity is 0.9 or higher, it is considered a high risk, and if it is below that, it is considered a low risk. The input is the result of matching with the database, and the output is the copyright risk assessment result. A judgment is made as to whether the image is "commercially usable" or "not for commercial use."

[1238] Step 6: The server notifies the user of the evaluation results

[1239] The server generates the evaluation result and notifies the user's device. The notification is made via a web browser interface, displaying a message such as "This image can be used for commercial purposes" or "This image may infringe copyright, so please avoid using it for commercial purposes." The input is the copyright risk evaluation result, and the output is the notification message displayed to the user.

[1240] (Application example 1)

[1241] 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."

[1242] In recent years, the use of images on the Internet has increased, and the risk of copyright infringement in commercial use of images has become a serious issue. Advertising agencies and marketers, in particular, must quickly evaluate a large number of image materials, and in doing so, they are required to quickly and accurately determine the copyright risk of images. However, current manual checking methods are time-consuming, labor-intensive, and inefficient. To address this issue, the present invention aims to provide a system for evaluating the copyright risk of images used for advertising management in real time.

[1243] 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.

[1244] In this invention, the server includes means for users to upload images to be evaluated, means for receiving the uploaded images and performing initial processing, feature extraction means using an artificial intelligence model to extract visual features from the images, means for comparing the extracted features with an existing database and evaluating the degree of match or similarity, means for determining the copyright risk of the images based on the evaluation results, means for notifying the user of the determination results, and means for uploading images via a smartphone for advertising management and evaluating the copyright risk in real time. This enables users to quickly evaluate the copyright risk of images to be used as advertising material and immediately determine whether or not they can be used commercially.

[1245] "User" means a person or entity that uploads images to the system and receives the results of a copyright risk assessment.

[1246] An "image to be evaluated" is an image file uploaded by a user for commercial use.

[1247] "Upload" refers to the act of a user sending an image to be evaluated to the online system.

[1248] "Initial processing" is a series of processes that check the format of the received image and compress and convert it.

[1249] "Visual features" refer to information such as color, shape, and texture within an image, and are extracted using artificial intelligence.

[1250] An "artificial intelligence model" is an algorithm or system that uses deep learning technology to analyze visual features.

[1251] "Feature extraction means" refers to technical means or tools for extracting visual features from an image.

[1252] An "existing database" is an information collection that stores image data collected in the past and its copyright information.

[1253] "Matching" is the act of comparing extracted visual features with an existing database to evaluate the degree of match or similarity.

[1254] "Similarity" is a measure of the visual match between an image and an existing image in a database.

[1255] The "evaluation result" is the copyright risk assessment result derived based on the matching of visual features.

[1256] "Copyright risk" refers to the degree of likelihood that the image being evaluated constitutes copyright infringement.

[1257] "Notification" refers to the act of informing the user of the evaluation results.

[1258] "For advertising management" refers to the purpose of managing and evaluating images used as advertising materials.

[1259] A "smartphone" is a portable communication device that can connect to the Internet and use multi-function applications.

[1260] "Real-time" means that the time from when a user uploads an image to when the evaluation result is notified is extremely short, and processing is immediate.

[1261] The present invention provides a system for evaluating the copyright risk of images in real time, specially designed for advertising management, which mainly uses a server, a smartphone terminal, and an artificial intelligence (AI) model.

[1262] Overall system configuration

[1263] The system includes the following main components:

[1264] 1. User terminal: A smartphone is used, providing a means for users to upload images as advertising materials.

[1265] 2. Server: Receives uploaded images, performs initial processing, extracts visual features, matches them with databases, assesses copyright risk, and notifies the results.

[1266] 3. Artificial intelligence model: Deep learning techniques are used to analyze visual features in images.

[1267] Program processing overview

[1268] 1. User image upload

[1269] The user uses a dedicated smartphone application to select an image to be evaluated and upload it to the system, which obtains the image's file path and sends it to the server.

[1270] 2. Server Reception and Initial Processing

[1271] The server receives the image file sent from the user terminal. It checks the format of the received image file and performs image compression or format conversion as necessary. For example, it converts the image to JPEG format or compresses the image size.

[1272] 3. Feature extraction using AI models

[1273] The server inputs the processed image into an artificial intelligence model to extract visual features. This model uses ResNet50, built using TensorFlow, which extracts visual features such as color, shape, and texture from the image as vectors.

[1274] 4. Matching with existing databases

[1275] The server compares the extracted feature vector with an existing image database. For comparison, it uses the cosine_similarity function from the scikit-learn library to calculate the similarity to images in the database. If the highest similarity exceeds a predetermined threshold, it is determined to have a high copyright risk.

[1276] 5. Copyright Risk Assessment and Notification of Results

[1277] The server evaluates the copyright risk of the image based on the results of the database comparison. The evaluation results are sent to the user's smartphone in real time. The user can then check the results, such as "There is a risk of copyright infringement" or "Commercial use is permitted," via a dedicated application.

[1278] Hardware and software used

[1279] Hardware: Smartphones, servers

[1280] software:

[1281] TensorFlow: Used to implement the artificial intelligence model (ResNet50) and extract features

[1282] Pillow: Used for initial image processing (format conversion and resizing)

[1283] scikit-learn: Used to compare similarity between feature vectors (cosine_similarity)

[1284] Specific examples

[1285] Example 1: Marketer use case

[1286] Marketers upload images to be used as advertising materials for new products from their smartphones, and the images are evaluated through an AI model, which immediately informs them that they are "suitable for commercial use."

[1287] Example 2: Advertising agency use case

[1288] Advertising agencies use a smartphone application to simultaneously evaluate multiple advertising materials. The application allows users to upload images in bulk, and the server evaluates the copyright risk of each image and notifies users of the results individually.

[1289] Prompt Sentence Examples

[1290] Upload a new image "example.jpg" as advertising material and assess its copyright risk.

[1291] Run the assessment and view the results.

[1292] Specify the file path:

[1293] file_path = "example.jpg"

[1294] main(file_path)

[1295] In this way, by using the system of the present invention, users can easily evaluate the copyright risk of advertising materials and quickly determine whether or not they can be used commercially.

[1296] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1297] Step 1:

[1298] The user selects an image to be evaluated as advertising material and uploads it to the system through a smartphone application. Specifically, the user uses the app's interface to select an image from the device's storage and clicks the upload button. This step inputs the selected image file. The app then sends this image file to the server.

[1299] Step 2:

[1300] The server receives image files sent from the user device and performs initial processing. It checks the format of the received image file, converts it to JPEG format if necessary, and compresses the image size. Specifically, it uses the Pillow library to convert the image format and resize it. The input is the image data sent from the smartphone, and the output is the image data after initial processing has been completed.

[1301] Step 3:

[1302] The server inputs the pre-processed image into an artificial intelligence model to extract visual features. Specifically, it uses a ResNet50 model built using TensorFlow to extract visual information such as the image's color, shape, and texture as a feature vector. The input at this stage is the pre-processed image data, and the output is the extracted visual feature vector.

[1303] Step 4:

[1304] The server compares the extracted feature vector with an existing database. Specifically, it calculates the similarity between the extracted feature vector and an existing image in the database using the cosine_similarity function in the scikit-learn library. The input is the visual feature vector and the feature vector in the database, and the output is a similarity score.

[1305] Step 5:

[1306] The server evaluates copyright risk based on the results of database matching. If the similarity score exceeds a predetermined threshold, the image is deemed to have a high risk of copyright infringement. The input is the similarity score, and the output is the copyright risk assessment result. Specifically, it generates an assessment result such as "There is a risk of copyright infringement" or "Commercial use is permitted."

[1307] Step 6:

[1308] The server notifies the user of the results of the copyright risk assessment via their smartphone. Specifically, the assessment results are sent to a dedicated application and displayed to the user as a notification message. The input is the copyright risk assessment result, and the output is a notification message sent to the user's device. The user can then check the results to determine whether or not the advertising material can be used commercially.

[1309] In this way, users can easily use their smartphones to evaluate the copyright risks of advertising materials and make appropriate usage decisions.

[1310] 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.

[1311] The present invention combines a system for assessing the risk of copyright infringement of images for commercial use with an emotion engine that recognizes user emotions. This system includes the following means: a means for a user to upload images to be assessed, a means for receiving the uploaded images and performing initial processing, a feature extraction means using an artificial intelligence model to extract visual features from the images, a means for comparing the extracted features with an existing database and assessing their match or similarity, a means for determining the copyright risk of the images based on the assessment results, a means for notifying the user of the assessment results, and an emotion engine that recognizes user emotions.

[1312] A specific embodiment of this system is described below.

[1313] System Operation Overview

[1314] 1. User image upload

[1315] The user accesses the interface provided through a web browser, selects and uploads the image file to be evaluated, and the user's device acquires the path of this image file and sends it to the system.

[1316] 2. Server Reception and Initial Processing

[1317] The server receives the image file sent from the user's device. The server checks the format of the image file and compresses or converts the image as necessary. For example, images that are too large will be compressed, and images in an unsupported format (such as BMP or GIF) will be converted to JPEG format.

[1318] 3. Feature extraction using AI models

[1319] The server inputs the received image into an artificial intelligence model to extract visual features. The server uses a deep learning model (e.g., CNN) to analyze visual information such as the image's color, shape, and texture. As a result of the analysis, a feature vector is generated and used for subsequent processing.

[1320] 4. Checking existing databases

[1321] The server compares the extracted feature vector with an existing image database, which stores images that are not for commercial use and copyright-related information. The server performs a database search using the feature vector as a key to identify images that match or have a high degree of similarity.

[1322] 5. Copyright Risk Assessment

[1323] The server determines the copyright risk of the image being evaluated based on the results of the database comparison. If the server finds a match or a high degree of similarity, it determines that the image cannot be used commercially. Conversely, if the server finds no match or high degree of similarity, it determines that the image can be used commercially.

[1324] 6. Recognition of user emotions by emotion engine

[1325] The device uses the user's camera and microphone to enable the emotion engine to recognize the user's emotions in real time. The emotion engine uses facial expression analysis and tone of voice analysis to determine whether the user is in an emotional state such as excitement, joy, or anger.

[1326] 7. Result output and emotional notifications

[1327] When the server notifies the user of the generated evaluation results, it changes the notification method based on the recognition results of the emotion engine. For example, if the user is feeling stressed, it will notify the result in gentler terms, and conversely, if the user is excited, it will notify them in a more concise manner.

[1328] Users can check the evaluation results on their own devices in a web browser, which may display a message such as "This image can be used for commercial purposes" or "Please avoid using this image for commercial purposes as there is a risk of copyright infringement."

[1329] Specific examples

[1330] Example 1: Rating and responding to sentiment for images that are not suitable for commercial use

[1331] Users upload images for inclusion on their websites.

[1332] Images received by the server undergo feature extraction through an artificial intelligence model.

[1333] The extracted features are found to have a high degree of similarity to known non-commercial images in the database.

[1334] The server determines that "this image poses a risk of copyright infringement, so please avoid using it for commercial purposes," and notifies the user of the result.

[1335] The user's device uses a camera and microphone to allow the emotion engine to recognize the user's emotions and determine whether they are feeling stressed.

[1336] The server notifies the user of the evaluation results in gentle language designed to reduce stress.

[1337] Example 2: Ratings and positive emotional responses for commercially available images

[1338] Users upload images for use in marketing materials.

[1339] The server extracts features from the received image and compares them with an existing database.

[1340] It is determined that there are no images in the database that have a match or a high degree of similarity.

[1341] The server determines that "this image can be used commercially" and notifies the user of the result.

[1342] The user's device recognizes the user's emotions through an emotion engine and detects the emotion of joy.

[1343] The server notifies the user of the evaluation results in simple and positive terms.

[1344] In this way, by using the system of the present invention, it is possible to efficiently evaluate the copyright risk of commercial images and to provide notifications that take into consideration the user's feelings.

[1345] The processing flow will be explained below.

[1346] Step 1:

[1347] A user accesses the application and clicks the "Upload Image" button. The user selects an image file to be evaluated and starts uploading. The user's device obtains the path of the selected image file and inserts the file into the upload stream.

[1348] Step 2:

[1349] The server receives the image file sent from the user's device. The server checks the format of the image file and compresses or converts the image as necessary. For example, an image that is too large will be compressed, or if the format is not supported, it will be converted to JPEG format.

[1350] Step 3:

[1351] The server inputs the received image into an artificial intelligence model to extract visual features. The server uses a deep learning model to analyze the image's visual information, such as color, shape, and texture. As a result of the analysis, a feature vector is generated.

[1352] Step 4:

[1353] The server compares the extracted feature vector with an existing image database, which stores images that are not for commercial use and copyright-related information. The server then searches the database using the feature vector as a key to identify images that match or have a high degree of similarity.

[1354] Step 5:

[1355] The server determines the copyright risk of the image being evaluated based on the results of the database comparison. If the server finds a match or a high degree of similarity, it determines that the image cannot be used commercially. Conversely, if the server finds no match or high degree of similarity, it determines that the image can be used commercially.

[1356] Step 6:

[1357] The device uses the user's camera and microphone to enable the emotion engine to recognize the user's emotions in real time. The emotion engine uses facial expression analysis and tone of voice analysis to determine whether the user is in an emotional state such as excitement, joy, or anger.

[1358] Step 7:

[1359] The server changes the notification method based on the recognition results of the emotion engine. For example, if the user is feeling stressed, the server notifies the user in a gentle manner, whereas if the user is excited, the server notifies the user in a concise manner.

[1360] Step 8:

[1361] The server notifies the user's device of the evaluation results it has generated. The server then sends the results to the user's device as an HTTP response in JSON format or similar. The user can then check the evaluation results on their device's web browser.

[1362] Step 9:

[1363] The user checks the evaluation results sent from the server on the web application interface. The user's device receives the response from the server and displays it to the user in an appropriate format. For example, it displays specific content such as "This image can be used for commercial purposes" or "Please avoid using this image for commercial purposes as there is a risk of copyright infringement."

[1364] Example 2

[1365] 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."

[1366] In assessing the copyright risk of images intended for commercial use, existing systems have the problem of being unable to accurately assess the copyright risk of images and not giving consideration to the user's feelings when notifying them. In particular, not taking the user's feelings into consideration when notifying them of the copyright risk assessment results can cause unnecessary stress and confusion for the user.

[1367] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving uploaded images and performing initial processing, feature extraction means using an artificial intelligence model to extract visual features from the images, means for comparing the extracted features with an existing database and evaluating the degree of match or similarity, means for determining the copyright risk of the images based on the evaluation results, means for notifying the user of the evaluation results, and an emotion engine for recognizing the user's emotions and adjusting the method of notifying the evaluation results. This not only enables efficient and accurate evaluation of the copyright risk of images, but also enables appropriate notification that takes the user's emotions into consideration.

[1368] "User" refers to a user who uses the system to upload images and have them assessed for copyright risk.

[1369] "Server" refers to a computer system that receives images sent from a user's terminal and is responsible for all processing, including initial processing, feature extraction, database matching, and notification of evaluation results.

[1370] "Terminal" refers to a device accessed by a user, including a web browser and related hardware devices for uploading images and checking evaluation results.

[1371] "Image" refers to the visual data to be evaluated that users upload to the system, and includes common image formats such as JPEG and PNG.

[1372] "Visual features" are information extracted from an image, including color, shape, texture, and other attributes necessary for image recognition and feature vector generation.

[1373] "Artificial intelligence model" refers to an algorithm or network model used to extract visual features using deep learning techniques, including convolutional neural networks (CNNs).

[1374] "Database" refers to an information system that stores existing image data and associated copyright information against which extracted feature vectors can be matched.

[1375] A "feature vector" is a data set that quantifies the visual features of an image, and is used for matching with a database and evaluating similarity.

[1376] "Emotion engine" refers to the algorithms and software modules used to recognize a user's emotions, analyzing data acquired through the camera and microphone.

[1377] The "evaluation result" is a conclusion generated based on the copyright risk assessment, and is notified to the user in the form of "Commercial use is permitted" or "Commercial use should be avoided."

[1378] The "notification method" refers to the means or format for notifying the user of the evaluation results, and is adjusted according to the user's emotional state.

[1379] The present invention is a system for assessing the risk of copyright infringement of images intended for commercial use, which is combined with an emotion engine that recognizes user emotions. This system includes the following means: a means for a user to upload an image to be assessed, a means for receiving the uploaded image and performing initial processing, a feature extraction means using an artificial intelligence model to extract visual features from the image, a means for comparing the extracted features with an existing database and evaluating the degree of match or similarity, a means for determining the copyright risk of the image based on the assessment result, a means for notifying the user of the assessment result, and an emotion engine that recognizes user emotions.

[1380] System Operation Overview

[1381] 1. User image upload

[1382] The user accesses the interface provided through a web browser, selects and uploads the image file to be evaluated, and the user's device obtains the path of this image file and sends it to the system.

[1383] 2. Server Reception and Initial Processing

[1384] The server receives the image file sent from the terminal. After receiving it, it checks the format of the image file and compresses or converts the image as necessary. For example, large images are compressed, and images in unsupported formats (such as BMP or GIF) are converted to JPEG format.

[1385] 3. Feature extraction using AI models

[1386] The server inputs the received image into an artificial intelligence model (e.g., CNN) using deep learning technology to extract visual features. The analyzed feature vectors are used for database matching.

[1387] 4. Checking existing databases

[1388] The server uses the feature vector as a key to match existing image data and associated copyright information in a database that stores images and copyright information that are not for commercial use.

[1389] 5. Copyright Risk Assessment

[1390] The server determines the copyright risk of the image being evaluated based on the results of the database comparison. If a high degree of similarity is found, the image is deemed "unsuitable for commercial use," but if the match or similarity is low, it is deemed "available for commercial use."

[1391] 6. Recognition of user emotions by emotion engine

[1392] The device uses a camera and microphone to capture the user's facial expressions and tone of voice in real time, and analyzes the captured data with an emotion engine (e.g., Microsoft Azure's Emotion API) to determine the user's emotional state (e.g., excitement, joy, anger, stress).

[1393] 7. Result output and emotional notifications

[1394] The server generates an evaluation result and sends it to the device in a format that corresponds to the user's emotional state based on the judgment of the emotion engine. For example, if the user is feeling stressed, the server will notify them in gentle words, and if the user is excited, the server will notify them in a concise manner.

[1395] Users can check the evaluation results on their device in a web browser, which will display messages such as "Commercial use is permitted" or "Please avoid commercial use due to the risk of copyright infringement."

[1396] Specific examples

[1397] Example 1: Rating and responding to sentiment for images that are not suitable for commercial use

[1398] Users upload images for inclusion on their websites.

[1399] The image received by the server undergoes feature extraction through an artificial intelligence model.

[1400] The extracted features are found to have a high degree of similarity to known non-commercial images in the database.

[1401] The server determines that "This image poses a risk of copyright infringement, so please avoid using it for commercial purposes," and notifies the user of the result.

[1402] The user's device uses a camera and microphone to allow the emotion engine to recognize the user's emotions and determine whether they are feeling stressed.

[1403] The server will notify you of the evaluation results in gentle language.

[1404] Example 2: Ratings and positive emotional responses for commercially available images

[1405] Users upload images for use in marketing materials.

[1406] The server extracts features from the received image and compares them with an existing database.

[1407] It is determined that there are no images in the database that have a match or a high degree of similarity.

[1408] The server determines that "this image can be used commercially" and notifies the user of the result.

[1409] The user's device recognizes the user's emotions through an emotion engine and detects the emotion of joy.

[1410] The server will notify you of the evaluation results in simple and positive terms.

[1411] Prompt Sentence Examples

[1412] Example 1: A user who uploads a non-commercial image experiences frustration

[1413] "Please rate whether this image is safe for commercial use."

[1414] Example 2: A user expresses joy by uploading an image that can be used commercially.

[1415] "Can I use this image in my marketing materials?"

[1416] In this way, by using the system of the present invention, it is possible to efficiently evaluate the copyright risk of commercial images and provide notifications that take into consideration the user's feelings.

[1417] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1418] Processing steps of this system's program

[1419] Step 1: Upload user image

[1420] The user accesses a web browser, selects the image file to be evaluated, and clicks the upload button. The image file path selected by the user is obtained as input. Based on this path, the terminal sends the image file to the system. Specifically, the image file is sent to the server via an HTTP POST request.

[1421] Step 2: Server reception and initial processing

[1422] The server receives image files sent from the terminal. As input, the image file data arrives at the server. The server checks the format of the image file and compresses or converts the image as necessary. For example, files in a format other than JPEG are converted to JPEG, and files that are too large are compressed. As output, the image file data after initial processing is obtained.

[1423] Step 3: Feature extraction using an AI model

[1424] The server inputs the received image into an artificial intelligence model (such as CNN) that uses deep learning technology. An initially processed image file is obtained as input. The server analyzes this image and extracts visual features (color, shape, texture, etc.) as a feature vector. Specific examples include using TensorFlow or PyTorch. The feature vector is obtained as output.

[1425] Step 4: Check the existing database

[1426] The server compares the feature vector with an existing image database. The input is the feature vector. The server searches the database using an SQL query to identify image data that matches or has a high degree of similarity. The output is the matching result.

[1427] Step 5: Copyright Risk Assessment

[1428] The server determines the copyright risk of the image being evaluated based on the database match results. The database match results are received as input. The server determines the risk level using a rule-based or machine learning model. The copyright risk assessment result is received as output.

[1429] Step 6: Recognizing user emotions with the emotion engine

[1430] The device uses a camera and microphone to capture the user's facial expressions and voice in real time. Video and audio data are obtained as input. This data is analyzed by an emotion engine (e.g., Emotion API) to determine the user's emotional state (joy, anger, stress, etc.). The emotional state is obtained as output.

[1431] Step 7: Output the results and notify based on the emotion

[1432] The server generates an evaluation result and transmits it to the device in a format that corresponds to the user's emotional state based on the emotion engine's judgment. The copyright risk evaluation result and the user's emotional state are received as input. The server selects an appropriate way to express the result and transmits it to the device via an HTTP response. The output is the evaluation result that is displayed on the user's device.

[1433] Users can check the evaluation results on their device via a web browser, which allows them to understand the copyright risks of commercial images and make appropriate decisions based on that information.

[1434] Specific prompt examples

[1435] Example 1: A user who uploads a non-commercial image experiences frustration

[1436] "Please rate whether this image is safe for commercial use."

[1437] Example 2: A user expresses joy by uploading an image that can be used commercially.

[1438] "Can I use this image in my marketing materials?"

[1439] In this way, by using the system of the present invention, it is possible to efficiently and accurately evaluate the copyright risk of an image and to provide a notification that takes into consideration the user's feelings.

[1440] (Application example 2)

[1441] 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."

[1442] Currently, there is a demand for a system that can efficiently evaluate the copyright risk of images intended for commercial use. However, existing systems have the problem of conveying results in a uniform manner without taking the user's emotional state into consideration, resulting in a poor user experience. It is necessary to develop a system that solves this problem and supports smoother commercial use by providing notifications that take the user's emotions into consideration.

[1443] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1444] In this invention, the server includes means for a user to upload an image to be evaluated, means for receiving the uploaded image and performing initial processing, means for extracting visual features from the image using an artificial intelligence model, means for comparing the image with an existing database and evaluating the degree of match or similarity, means for determining the copyright risk of the image based on the evaluation result, means for notifying the user of the determination result, means for recognizing the user's emotional state, and means for optimizing the notification method based on the user's emotional state. This makes it possible to efficiently evaluate the copyright risk of images intended for commercial use and to provide notification that takes the user's emotions into consideration.

[1445] "User" means any individual or legal entity that wishes to use the system to assess the copyright risk of an image.

[1446] An "image to be evaluated" is an image file uploaded by a user for commercial use.

[1447] "Means for uploading" refers to an interface or program that allows a user to send images to be evaluated to the system.

[1448] The "means for performing initial processing" is a function for performing processing such as compression, format conversion, and resizing of received images.

[1449] "Visual features" are feature information extracted by image analysis, such as the color, shape, and texture of an image.

[1450] An "artificial intelligence model" is a model that uses deep learning technology and is used to extract visual features from images.

[1451] "Feature extraction means" is a function that extracts visual features of an image using an artificial intelligence model.

[1452] A "database" is a searchable repository of existing, non-commercially available images and copyright-related information.

[1453] The "means for matching and evaluating the degree of match or similarity" is a function for comparing the extracted features with image features in a database and calculating the degree of match or similarity.

[1454] The "evaluation result" is information used to determine whether there is a copyright risk.

[1455] The "means for determining copyright risk" is a function that determines whether an image can be used commercially based on the evaluation results.

[1456] "Means of notification" refers to means for communicating the judgment results to the user, and includes web browser, email, in-app notification, etc.

[1457] "Emotional state" is the result of a real-time analysis of a user's emotions, including excitement, joy, anger, stress, etc.

[1458] The "means for recognizing emotional state" is a function that analyzes the user's emotions in real time using the user's camera and microphone.

[1459] The "means for optimizing the notification method" is a function for adjusting the notification method and content of the judgment result based on the emotional state of the user.

[1460] The system according to the present invention evaluates the copyright risk of images for commercial use and provides optimal notification according to the user's emotional state. This system is configured and operates as follows.

[1461] The system includes a means for users to upload images to be evaluated. The user selects an image file through a web browser or a dedicated application and uploads it to the system. At this point, the user's device obtains the path to the image file and sends it to the server. The uploaded image is received by the server and undergoes initial processing, which may include image compression, resizing, and format conversion.

[1462] The server then inputs the received image into an artificial intelligence model to extract visual features. This AI model uses deep learning technology, specifically a convolutional neural network (CNN) model. It analyzes visual information such as the image's color, shape, and texture to generate a feature vector.

[1463] The generated feature vector is compared with an existing database stored on the server. The database contains images that are not for commercial use and copyright-related information, and a database search is performed using the feature vector as a key. The server evaluates the degree of match and similarity based on the search results and derives an evaluation result.

[1464] Based on the evaluation results, the server determines the copyright risk of the image. If the image being evaluated is determined to be unsuitable for commercial use, the server notifies the user. A similar notification is also given if the image is determined to be suitable for commercial use. However, what is unique about this system is that the notification is given taking into account the user's emotional state.

[1465] The server uses the device's camera and microphone to recognize the user's emotional state. Emotion Engine is used for emotion recognition. Facial expressions are analyzed from the camera and tone of voice is analyzed from the microphone to determine whether the user is in an emotional state such as excitement, joy, anger, or stress. Based on this determination, the server optimizes the method of notifying the evaluation result. For example, if the user is feeling stressed, the server will notify them in soft language, and conversely, if the user is excited, the server will notify them in a concise manner.

[1466] Specific examples of prompts are as follows:

[1467] Your custom script will use the smartphone's camera and microphone to recognize user emotions and assess the copyright risk of uploaded images. The deep learning model will extract image features and compare them with a database to assess risk. Emotion Engine will be used for emotion recognition, and the results will be fed back to the user in the form of a notification message based on the emotion.

[1468] In this way, the system can efficiently assess the copyright risk of images intended for commercial use and further improve the user experience by providing notifications that take into account the user's emotional state.

[1469] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1470] Step 1:

[1471] User image upload

[1472] The user uploads the image to be evaluated from their own device. The input is an image file (e.g., JPEG or PNG), and the output is the transmission of the image file to the server. The user selects an image through a web browser or a dedicated application and clicks the upload button to obtain the path of the image file and send it to the server.

[1473] Step 2:

[1474] Server reception and initial processing

[1475] The server receives the image file sent by the user and performs initial processing. The input is the received image file, and the output is the processed image file. At this stage, the server checks the image format and performs compression or format conversion (e.g., from BMP to JPEG) as necessary. The image may also be resized.

[1476] Step 3:

[1477] Feature extraction using AI models

[1478] The server inputs the image after initial processing into an artificial intelligence model to extract visual features. The input is the processed image file, and the output is a feature vector. The server uses deep learning technology (e.g., CNN) to analyze visual information such as the color, shape, and texture of the image and generate a feature vector.

[1479] Step 4:

[1480] Checking an existing database

[1481] The server compares the extracted feature vector with an existing database. The input is the feature vector and database information, and the output is the evaluation result of the degree of match or similarity. The server performs a database search using the feature vector as a key to identify images that match or have a high degree of similarity.

[1482] Step 5:

[1483] Copyright Risk Assessment

[1484] The server determines the copyright risk of the image being evaluated based on the results of the database match. The input is the evaluation result of the database match, and the output is the copyright risk judgment result. If the server finds a match or a high similarity, it determines that the image is not commercially available; otherwise, it determines that the image is commercially available.

[1485] Step 6:

[1486] Recognizing user emotions with an emotion engine

[1487] The emotion engine on the user's device uses a camera and microphone to recognize the user's emotions in real time. The input is camera footage and audio data, and the output is the user's emotional state (excitement, joy, anger, stress, etc.). The emotion engine analyzes facial expressions and tone of voice to determine the user's emotional state.

[1488] Step 7:

[1489] Result output and emotional notifications

[1490] When the server notifies the user's device of the generated evaluation results, it changes the notification method based on the recognition results of the emotion engine. The input is the copyright risk assessment result and the user's emotional state, and the output is a notification message that takes the emotion into consideration. For example, if the user is feeling stressed, the result will be notified in soft language, and conversely, if the user is excited, the notification will be concise.

[1491] Through these processing steps, the system can efficiently assess the copyright risk of images intended for commercial use and provide notifications that take into account the user's emotional state.

[1492] 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.

[1493] 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.

[1494] 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 robot 414.

[1495] 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.

[1496] FIG. 9 is a diagram illustrating 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 actions 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.

[1497] 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.

[1498] 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).

[1499] 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.

[1500] 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."

[1501] 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.

[1502] 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).

[1503] 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.

[1504] 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.

[1505] 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.

[1506] 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.

[1507] 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.

[1508] 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.

[1509] 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.

[1510] 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.

[1511] 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.

[1512] 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.

[1513] The following is further disclosed regarding the above embodiment.

[1514] (Claim 1)

[1515] 1. A system for assessing the risk of copyright infringement of images for commercial use, comprising:

[1516] a means for a user to upload an image to be evaluated;

[1517] means for receiving and initializing the uploaded images;

[1518] a feature extraction means using an artificial intelligence model to extract visual features from an image;

[1519] a means for matching the extracted features with an existing database and assessing the degree of match or similarity;

[1520] a means for determining copyright risk of the image based on the evaluation result;

[1521] means for notifying a user of the determination result;

[1522] A system including:

[1523] (Claim 2)

[1524] The system according to claim 1, wherein the extracted features are used to identify the original image when a composite of multiple original images is suspected.

[1525] (Claim 3)

[1526] The system of claim 1, further comprising a process for determining whether the image is commercially available based on the result of the copyright risk assessment.

[1527] "Example 1"

[1528] (Claim 1)

[1529] a means for a user to upload an image to be evaluated;

[1530] means for receiving and initializing the uploaded images;

[1531] a feature extraction means using an artificial intelligence model to extract visual features from an image;

[1532] a means for matching the extracted features with an existing database and assessing the degree of match or similarity;

[1533] a means for determining copyright risk of the image based on the evaluation result;

[1534] means for notifying a user of the determination result;

[1535] A system including:

[1536] (Claim 2)

[1537] The system of claim 1, wherein the artificial intelligence model uses deep learning technology and includes a process of analyzing visual information and extracting feature vectors.

[1538] (Claim 3)

[1539] 2. The system according to claim 1, further comprising means for performing comparison using cosine similarity or Euclidean distance when obtaining the evaluation result.

[1540] "Application Example 1"

[1541] (Claim 1)

[1542] a means for a user to upload an image to be evaluated;

[1543] means for receiving and initializing the uploaded images;

[1544] a feature extraction means using an artificial intelligence model to extract visual features from an image;

[1545] a means for matching the extracted features with an existing database and assessing the degree of match or similarity;

[1546] a means for determining copyright risk of the image based on the evaluation result;

[1547] means for notifying a user of the determination result;

[1548] A means to upload images via smartphone for ad management and assess copyright risk in real time;

[1549] A system including:

[1550] (Claim 2)

[1551] The system according to claim 1, wherein the extracted features are used to identify the original image when a composite of multiple original images is suspected.

[1552] (Claim 3)

[1553] The system of claim 1, further comprising a process for determining whether the image is commercially available based on the result of the copyright risk assessment.

[1554] "Example 2: Combining Emotion Engines"

[1555] (Claim 1)

[1556] a means for a user to upload an image to be evaluated;

[1557] means for receiving and initializing the uploaded images;

[1558] a feature extraction means using an artificial intelligence model to extract visual features from an image;

[1559] a means for matching the extracted features with an existing database and assessing the degree of match or similarity;

[1560] a means for determining copyright risk of the image based on the evaluation result;

[1561] means for notifying a user of the determination result;

[1562] A system including an emotion engine that recognizes a user's emotions and adjusts how the evaluation results are communicated.

[1563] (Claim 2)

[1564] The system according to claim 1, wherein the extracted features are used to identify the original image when a composite of multiple original images is suspected.

[1565] (Claim 3)

[1566] The system of claim 1, further comprising a process for determining whether the image is commercially available based on the result of the copyright risk assessment.

[1567] "Application example 2 when combining emotion engines"

[1568] (Claim 1)

[1569] a means for a user to upload an image to be evaluated;

[1570] means for receiving and initializing the uploaded images;

[1571] a feature extraction means using an artificial intelligence model to extract visual features from an image;

[1572] a means for matching the extracted features with an existing database and assessing the degree of match or similarity;

[1573] a means for determining copyright risk of the image based on the evaluation result;

[1574] means for notifying a user of the determination result;

[1575] means for recognizing the emotional state of a user;

[1576] means for optimizing the notification method based on the emotional state of the user;

[1577] A system including:

[1578] (Claim 2)

[1579] The system according to claim 1, wherein the extracted features are used to identify the original image when a composite of multiple original images is suspected.

[1580] (Claim 3)

[1581] The system of claim 1, further comprising a process for determining whether the image is commercially available based on the result of the copyright risk assessment. [Explanation of symbols]

[1582] 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. 1. A system for assessing the risk of copyright infringement of images for commercial use, comprising: a means for a user to upload an image to be evaluated; means for receiving and initializing the uploaded images; a feature extraction means using an artificial intelligence model to extract visual features from an image; a means for matching the extracted features with an existing database and assessing the degree of match or similarity; a means for determining copyright risk of the image based on the evaluation result; means for notifying a user of the determination result; A system including:

2. The system according to claim 1, wherein the extracted features are used to identify the original image when a composite of multiple original images is suspected.

3. The system of claim 1 , further comprising a process for determining whether the image is commercially available based on the result of the copyright risk assessment.

Images