system

Abstract

システムを提供する。【解決手段】画像を入力として受信する手段と、上記画像から特徴情報を抽出する手段と、上記特徴情報を用いて画像データベースを検索し、類似画像を特定する手段と、上記類似画像に基づいて著作権リスクを評価する手段と、上記評価に基づき、代替画像を生成する手段と、上記代替画像をユーザに提供する手段と、画像が広告媒体である場合に、その使用目的に適した代替画像を選択する手段と、を含むシステム。

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] When the generated image is similar to existing copyrighted content, there is a risk that the user may inadvertently infringe copyright. Such risks can cause legal problems when the image is used commercially or publicly, so a mechanism for users to use images with confidence is required.

Means for Solving the Problems

[0005] This invention includes means for receiving a generated image as input and extracting feature information from the image. It also includes means for searching an image database based on the extracted feature information to identify similar images. Furthermore, it includes means for evaluating copyright risk based on these similar images and provides means for generating alternative images based on the evaluation. Finally, by providing the generated alternative image to the user, it prevents the user from unintentionally infringing copyright and creates an environment in which images can be used safely.

[0006] An "image" is a representation of visual information in two or three dimensions, and can take the form of digital or analog data.

[0007] "Feature information" refers to the representation of an image's visual elements using numerical values ​​or patterns, which are then used for image recognition and comparison.

[0008] An "image database" is a platform that organizes and stores image data, making that data accessible as needed.

[0009] A "similar image" is another image that is identified as visually or structurally similar to the specified image.

[0010] "Copyright risk" refers to the possibility of legal issues arising from the similarity of an image to existing copyrighted content.

[0011] An "alternative image" is a new image that is generated based on specified criteria and designed to be used as a substitute for the original image.

[0012] A "machine learning model" is an algorithm or network structure built to learn and infer about a specific task using data. [Brief explanation of the drawing]

[0013] [Figure 1]This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0014] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0019] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), etc.

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] This invention is a system that automatically determines whether a user-generated image infringes copyright and provides an alternative image if necessary. The system is located in a cloud environment and is accessible to users through their own devices.

[0035] The system first receives an image generated by the user. The terminal sends the image to the server via an interface, and the image analysis process begins. After receiving the image, the server internally extracts feature information. This feature information is a collection of visual data points, which quantifies the unique features of the image.

[0036] The server uses the extracted feature information to search for similar images within a comprehensive database. This determines how similar a particular image is to a collection of copyrighted images worldwide. If similar images are found, the server evaluates them and determines the copyright risk. This evaluation includes calculating the similarity score and verifying copyright information.

[0037] If the server determines that there is a high risk of copyright infringement, it will generate an alternative image. The alternative image is newly created by a generation algorithm, has low similarity to the original image, and avoids the risk of copyright infringement. The server will send this generated alternative image to the user's device and send a notification.

[0038] As a concrete example, consider a case where a user generates a new logo using AI and requests a review through this system. The server analyzes the logo's characteristic information and searches the database for similar logos. If a highly similar existing logo is found, the system generates a new, unique logo, providing the user with a safe option to use. Through this process, the user can be protected from the risk of unexpected copyright infringement.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] The user selects an image generated using their device and uploads it to the system. The device then sends the selected image to the server.

[0042] Step 2:

[0043] The server analyzes the received images and performs image preprocessing. This includes converting image formats and adjusting their size so that they can proceed to the next processing step in a unified format.

[0044] Step 3:

[0045] The server extracts feature information from pre-processed images. This feature information is a numerical representation of the image's visual features and is used for subsequent searches. In particular, it is processed using techniques such as convolutional neural networks (CNNs).

[0046] Step 4:

[0047] The server uses the extracted feature information to search a copyright-aware database. The search uses a similarity calculation algorithm to measure the similarity to existing images and identify similar images.

[0048] Step 5:

[0049] The server evaluates whether there is a risk of copyright infringement between the image entered by the user and an existing image, based on the similarity calculation results. It refers to copyright information to determine whether or not there is a risk.

[0050] Step 6:

[0051] If the server determines that the image poses a high risk, it uses an AI algorithm to generate an alternative image. The generated alternative image will have a low degree of similarity to the original image while retaining its uniqueness.

[0052] Step 7:

[0053] The server sends the evaluation results and alternative images to the user's terminal. The terminal displays the results and the generated alternative images, and the user can select the image to use.

[0054] Step 8:

[0055] The user reviews the presented alternative images and makes a final decision on which image to use. The device can record the user's selection and send it to the server as feedback.

[0056] (Example 1)

[0057] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0058] In recent years, the risk of generated digital data infringing existing copyrights has increased. However, there is a lack of adequate means to automatically detect and avoid this at a feasible speed. This problem hinders creators from creating with peace of mind and can lead to legal issues related to copyright infringement.

[0059] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0060] In this invention, the server includes means for receiving digital data as input, means for extracting identification information, and means for searching a database and identifying corresponding digital data. This makes it possible to quickly detect the risk that the generated digital data infringes existing copyrights and to provide secure alternative digital data.

[0061] "Digital data" refers to information that is processed electronically, and includes data in various forms such as images, audio, and text.

[0062] "Identifying information" refers to a collection of characteristic data points extracted from digital data, used to identify or classify the relevant data.

[0063] A "database" refers to an organized collection of digital data, a collection of information that can be searched and updated.

[0064] A "similarity measurement" is a numerical representation of the degree of similarity between two or more digital data sets, and serves as an indicator for comparative evaluation.

[0065] A "machine learning algorithm" is a set of computational methods used by computers to automatically learn patterns and perform predictions and classifications.

[0066] This invention provides a system that receives digital data as input, extracts identification information, searches a database, and identifies corresponding digital data. The hardware used includes a high-performance server for data processing and a terminal for user data input. The software employs image processing algorithms and machine learning algorithms. Specifically, convolutional neural networks (CNNs) and deep learning models are operated on the server, contributing to the extraction of identification information from digital data.

[0067] The server automatically analyzes the input digital data and performs a database search based on the identification information. The database contains a vast amount of data collected from around the world, and similar digital data is identified from within it. This process is used to identify similar images, audio, and text, making it possible to quickly assess copyright risks.

[0068] As a concrete example, consider a scenario where a user generates a new digital logo using their own device and then checks whether that logo infringes on existing copyrights. In this case, the server analyzes the logo's identification information and searches its database. If a similar existing logo is found, the server can use a generation AI model to generate an alternative logo to mitigate the risk and provide it to the user. This allows users to confidently engage in new creative projects.

[0069] An example of a prompt message is, "Check if this image infringes copyright and generate a new alternative image if necessary." Through this prompt, users can quickly verify the safety and legality of the generated digital data.

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

[0071] Step 1:

[0072] The user's terminal inputs the generated digital data (e.g., images or logos) into the system. The input data is then sent from the user's terminal to the server. At this stage, the digital data is passed to the server in its original format.

[0073] Step 2:

[0074] The server analyzes the received digital data and extracts identification information. During this process, the server uses image processing algorithms such as convolutional neural networks (CNNs) to perform data calculations that quantify the features of the image. The extracted identification information represents characteristics such as color, shape, and pattern within the data.

[0075] Step 3:

[0076] The server searches the database based on the extracted identification information. In this process, the server uses a similarity calculation algorithm to identify similar digital data within the database. The database being searched contains a vast amount of copyrighted image data.

[0077] Step 4:

[0078] The server analyzes the search results and assesses copyright risk based on similarity scores. Here, similarity scoring is performed, and if a certain threshold is exceeded, it is determined to be high risk. Based on these results, a risk assessment is made.

[0079] Step 5:

[0080] If a high copyright risk is determined, the server uses a generative AI model to generate alternative digital data. In the generation process, the machine learning model generates new data with lower similarity, referencing the identification information of the input data. The output is new alternative digital data.

[0081] Step 6:

[0082] The generated alternative digital data is output from the server to the user's terminal. The terminal displays the received alternative data on the screen or in a designated location and notifies the user. This allows the user to use the alternative data with confidence.

[0083] (Application Example 1)

[0084] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0085] In advertising visual content, it is essential to proactively prevent copyright infringement risks and select images that can be used safely. In particular, the unintentional use of content similar to existing images can lead to legal problems. Furthermore, even in the process of creating new content using generation AI, it is necessary to provide users with a sense of security regarding copyright.

[0086] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0087] In this invention, the server includes means for selecting an alternative image suitable for the intended use when the image is an advertising medium, means for searching an image database using the above-mentioned characteristic information to identify similar images, and means for generating an alternative image based on the above-mentioned evaluation. This makes it possible to select images that are suitable for advertising while reducing the risk of copyright infringement.

[0088] "Means of receiving images as input" refers to a function that acquires image data provided by the user and incorporates it into the system.

[0089] "Means for extracting feature information" refers to a function that quantifies unique visual attributes from an input image and prepares that data as basic information for analysis.

[0090] "A means of searching an image database and identifying similar images" refers to a function that searches within an existing image database based on extracted feature information and identifies images with high similarity.

[0091] A "means for assessing copyright risk" is a function that determines legal risks and potential infringement related to copyright based on identified similar images.

[0092] "Methods for generating alternative images" refers to a function that uses a generation AI model to create new images with low similarity that avoid the risk of copyright infringement.

[0093] "Means of providing alternative images to users" refers to a function that sends the generated alternative images to the user's device, enabling them to view and use them.

[0094] "Means of selecting alternative images suitable for the purpose of use when it is an advertising medium" refers to a function that selects and provides images that are particularly suitable for advertising purposes from among the alternative images.

[0095] This invention is a system for reducing the risk of copyright infringement in visual content for advertising and providing safe images. The system consists of a server located in the cloud and a user's terminal such as a smartphone.

[0096] Users use their smartphones to select images to be used in advertisements and upload them to the system. At this stage, the images are sent to the server via the device's interface. The hardware used here consists of the user's smartphone and a cloud computing platform acting as the server.

[0097] The server extracts feature information from the received image. This extraction is performed using a machine learning algorithm, which generates data points that numerically represent the image. The server then searches an image database to identify similar images.

[0098] Next, the server assesses copyright risk based on similar images. This assessment includes calculating a similarity score with existing similar images. Based on this information, it determines whether there is a risk of copyright infringement.

[0099] If a copyright risk is deemed high, the server uses a generation AI model to generate an alternative image. This alternative image must be suitable for use in advertising media, and the server selects images with advertising objectives in mind.

[0100] Finally, the server sends the generated replacement image to the user's device. The user can then review the image and use it for advertising. This allows the user to safely use advertising images while avoiding copyright issues.

[0101] As a concrete example, suppose a user wants to create a banner for a new product campaign. In this situation, the user asks the system to check the image and evaluate whether there are any similar images. The server then provides the user with a uniquely designed alternative banner that can be used safely. This allows the user to use the image with confidence.

[0102] An example of a prompt to be input to the generation AI model would be: "Create a new illustration for a commercial poster. Since it may have a high degree of similarity to existing images in the database, please generate a unique design in a new style."

[0103] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0104] Step 1:

[0105] The user selects an image for advertising on their device and uploads it to the system. The input is image data stored on the user's device. The device sends the data to the server through an interface. This transmission prepares the image for processing on the server.

[0106] Step 2:

[0107] The server extracts feature information from the received image. The input is image data sent to the server. The server uses machine learning algorithms to convert the image into numerical information, obtaining a set of unique data points as output. This allows the image's structure and color features to be quantified and represented.

[0108] Step 3:

[0109] The server searches an image database based on feature information and identifies similar images. The input is numerically represented feature information. The server calculates the similarity to each image in the database and outputs a similarity score. The output is a list of similar images and their similarity scores.

[0110] Step 4:

[0111] The server assesses copyright risk based on identified similar images. The input consists of a list of similar images and their similarity scores. The server numerically evaluates the likelihood of copyright infringement based on these scores and outputs the risk level. This evaluation allows for the determination of high or low risk.

[0112] Step 5:

[0113] If a high copyright risk is determined, the server generates an alternative image using a generative AI model. The input is the result of the copyright risk assessment. The server uses a prompt to activate the generative AI model and outputs a new alternative image. The output is an alternative image that avoids the copyright risk associated with the original image.

[0114] Step 6:

[0115] The server sends the generated alternative image to the user's device. The input is the generated alternative image. The server transfers the alternative image to the user's device, and the user can receive a new, unique image as output. This allows the user to confidently use the image for advertising.

[0116] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0117] This invention combines emotion recognition with a system that automatically determines the risk of copyright infringement by comparing user-generated images with similar images and providing alternative images as needed. This system is cloud-based and easily accessible via the user's device. The user interface is designed for intuitive operation, allowing for quick image uploads and analysis.

[0118] First, the system begins processing when the user uploads the image they have generated to the server. After receiving the image, the server extracts its feature information and performs a comparative search using a similar image database. This process verifies whether the user's image is similar to an existing copyrighted image.

[0119] Once the copyright risk assessment is complete, the system then uses an emotion engine to recognize the user's emotional state. The device is equipped with a camera or other input device that can analyze emotions from the user's facial expressions, voice, or usage patterns.

[0120] After the emotion engine recognizes the user's emotional state, the server presents alternative images appropriate to that state. For example, if the system detects that the user is feeling anxious, it will generate an alternative image with a more friendly design. Conversely, if a positive emotion is detected, it can present an image with a more creative style.

[0121] As a concrete example, consider a case where a user generates a new advertising image using AI and requests a review through the system. In this case, the server first analyzes the image and searches for similar images. Simultaneously, the emotion engine analyzes the user's emotions. If the server recognizes a risk of copyright infringement and determines that the user is feeling uneasy, the system provides a reassuring alternative image to help the user make a comfortable final decision.

[0122] This system combines copyright risk management with emotion recognition features to enhance the user experience, providing flexible and comprehensive support for users to use images with confidence.

[0123] The following describes the processing flow.

[0124] Step 1:

[0125] The user generates a new image using an AI image generation tool and uploads that image to the system via their device. The device then sends the image data to the server.

[0126] Step 2:

[0127] The server analyzes the received image and extracts its feature information. This feature information represents the visual features as numerical data.

[0128] Step 3:

[0129] The server searches a database of similar images based on the feature information. It uses an algorithm to calculate similarity and determine how similar the image is to existing images.

[0130] Step 4:

[0131] The server assesses the risk of copyright infringement based on the results of identifying similar images. If a copyright risk is identified, it makes a determination to that effect.

[0132] Step 5:

[0133] The emotion engine operates through an input device connected to the terminal, detecting the user's emotional state. This is analyzed from the user's facial expressions, voice, and interaction style.

[0134] Step 6:

[0135] Based on the results analyzed by the emotion engine, the server adjusts the generation and presentation methods of alternative images according to the user's emotions.

[0136] Step 7:

[0137] The user reviews the risk assessment results. If the risk is high, the server displays alternative images on the user's device, and the user can select an image from the presented options.

[0138] Step 8:

[0139] The device sends this information to the server, taking into account the user's choices and emotional feedback. This data is used to improve the system and for future processing.

[0140] (Example 2)

[0141] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0142] The use of digital images carries the risk of copyright infringement, so users need ways to properly assess this risk and use images with peace of mind. Furthermore, there is a need to improve the user experience by providing images that are optimal according to the user's emotional state.

[0143] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0144] In this invention, the server includes means for receiving an image as input, means for extracting feature information from the image, means for identifying similar images and evaluating copyright risk, and means for recognizing the user's emotional state and generating an alternative image corresponding to that emotion. This reduces the risk of copyright infringement and provides an alternative image suitable for the user's emotional state, enabling the user to use images with peace of mind.

[0145] "Means for receiving images as input" refers to a function for importing user-generated or specified image data into a server or related system.

[0146] "Methods for extracting feature information" refer to the process of analyzing various attributes and patterns of an image to extract identifiable data.

[0147] "A means of searching an image database and identifying similar images" refers to a function that finds similar images from a large collection of images based on extracted feature information.

[0148] A "means of assessing copyright risk" is a method of calculating the likelihood that a subject image infringes on existing copyrights by comparing it with similar images.

[0149] "Means of recognizing a user's emotional state" refers to technologies that analyze a user's facial expressions, behavior, voice data, etc., to understand their current emotions.

[0150] "Means for generating alternative images according to emotional state" refers to the process of creating new images with designs and styles that best suit the user's emotions.

[0151] "Means of providing alternative images" refers to a mechanism that presents generated alternative images to the user, allowing them to select and use them.

[0152] This invention provides a system that evaluates the copyright risk of user-generated images and, taking into account the user's emotional state, offers the most suitable alternative image. This system is cloud-based and accessible from the user's own device. Specifically, the process begins when the user uploads the generated image to a server in the cloud.

[0153] When the server receives an image, it first uses an image analysis tool to extract feature information. Specifically, it uses image processing libraries such as TENSORFLOW® and OpenCV to analyze the image's patterns, color tones, and shapes. After that, it searches a similar image database using the Google® Cloud Vision API. This allows it to check how similar the image is to existing copyrighted images.

[0154] Next, the system uses the camera and microphone on the user's device to recognize the user's emotional state. The device sends the collected data to a server, which uses Microsoft® Azure® Emotion API to analyze the user's emotions. This allows the system to determine whether the user is feeling anxious or happy.

[0155] Based on this information, the server generates alternative images using a generative AI model (e.g., DALL-E). An example of a prompt might be, "Generate a relaxing ocean view." Based on this prompt, the system generates an image best suited to the user's emotional state and provides it to the user.

[0156] As a concrete example, consider a user who wants to create an advertising image for promotional purposes. The user uploads an image generated using AI to the system, and the server analyzes the image and searches for similar images. At the same time, the user's emotional state is analyzed, and if, for example, anxiety is detected, an alternative image that calms the user is generated and provided. In this way, the user can obtain an image that they can use with peace of mind.

[0157] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0158] Step 1:

[0159] The user uploads images generated using their device to the cloud system. The device sends and receives the image data from the server. The input is the image generated by the user, and the output is the image data stored on the server.

[0160] Step 2:

[0161] The server extracts feature information from the received image data. Specifically, it uses image analysis tools such as TensorFlow and OpenCV to analyze the patterns, shapes, and color tones of the images. In this step, the input is the image data stored on the server, and the output is the extracted feature information.

[0162] Step 3:

[0163] The server uses the extracted feature information to search an image database and identify similar images. It utilizes the Google Cloud Vision API to identify highly similar images. The input is feature information, and the output is a list of similar images and a similarity score for each image.

[0164] Step 4:

[0165] The server assesses copyright infringement risk based on similarity scores. Here, a high risk is determined if the similarity score exceeds a specified threshold. The input is a list of similar images and their similarity scores, and the output is the copyright risk assessment result.

[0166] Step 5:

[0167] The device uses its camera and microphone to collect the user's facial expressions and voice, and obtains data to identify their emotions. This data is then sent to a server. The input is the user's facial expressions and voice data, and the output is the unanalyzed emotion data transferred to the server.

[0168] Step 6:

[0169] The server uses the received emotion data to recognize the user's emotional state. It uses the Microsoft Azure Emotion API to analyze whether the user is feeling anxious or happy. The input is unanalyzed emotion data, and the output is the user's emotional state.

[0170] Step 7:

[0171] The server uses a generative AI model to generate alternative images that correspond to the user's emotional state. Prompts such as "Generate a relaxing ocean view" are used. The input is the user's emotional state, and the output is the generated alternative image.

[0172] Step 8:

[0173] The server provides the user with generated alternative images and prompts them to make a final selection. These are displayed on the terminal, allowing the user to review and use the suggested alternative images. The input is the generated alternative image, and the output is the alternative image reviewed by the user.

[0174] (Application Example 2)

[0175] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0176] Image generation requires the ability to quickly and effectively assess the risk of copyright infringement and provide feedback tailored to the image creator's emotional state. Conventional systems often fail to consider the user's emotional state, resulting in alternative solutions that don't align with the user's psychological condition. This leads to a lack of support for users in making optimal decisions.

[0177] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0178] In this invention, the server includes means for receiving an image as input, means for extracting feature information, and means for recognizing the emotional state of the image creator through an emotion analysis function. This makes it possible to combine emotion recognition with copyright risk assessment and present appropriate alternative images according to the user's psychological state.

[0179] "Means for receiving images as input" refers to a configuration that has the function of transferring user-generated image data to a server and inputting it for processing.

[0180] "Means for extracting feature information" refers to a function that analyzes the features of an image from received image data and obtains the information necessary for identification.

[0181] "A means of searching an image database and identifying similar images" refers to a function that uses extracted feature information to refer to an existing database and executes a process to identify similar images.

[0182] A "means for assessing copyright risk" is a function that determines the risk of whether an image is protected by copyright based on identified similar images.

[0183] "Means of recognizing the emotional state of the image creator through emotion analysis" refers to a function that uses the user's camera, microphone, or other devices to analyze the user's emotional state from their facial expressions and voice.

[0184] "Means for generating alternative images" refers to a function that creates appropriate alternative image suggestions for the user based on the results of copyright risk assessment and sentiment analysis.

[0185] "Means of providing the above alternative images to the user" refers to a function that presents the generated alternative images to the user in an easy-to-view manner and makes them available for use.

[0186] The system realized by this invention operates on a cloud-based system and consists of a program for receiving and processing images generated by image creators as input. Broadly speaking, this system operates based on the following main steps.

[0187] First, the image generator uploads the generated image to the cloud server via their device. This image is crucial as a starting point for processing on the server. The server analyzes the received image and extracts feature information. To do this, it uses image processing libraries such as Python and OpenCV to quickly obtain the necessary data from the image.

[0188] Next, the server uses the extracted feature information to search a pre-built database of similar images. This process uses a similarity algorithm to identify the similarity between the generated image and existing images. The Django framework is used for this data processing and computation, enabling efficient data management and backend operation.

[0189] Next, the server assesses the risk of copyright infringement based on similar images. In this process, a machine learning model is implemented using TensorFlow to perform automated decisions for risk assessment.

[0190] Furthermore, the system uses emotion analysis capabilities to understand the emotional state of the image creator. In this step, data is acquired from the camera and microphone on the user's device, and emotions are analyzed using TensorFlow and PyTorch.

[0191] Finally, based on the copyright risk assessment and emotional state analysis, alternative images are generated. The software used here combines Flask and a GAN model to assist in image generation using a generative AI model. These generated alternative images are provided to the user, offering a variety of choices.

[0192] For example, when an advertising creator generates a new image for an advertisement, this system checks the copyright risk of the image and simultaneously generates the most suitable alternative image based on the creator's emotional state. An example of a prompt message would be, "Please check the generated advertising image for copyright infringement of similar images and suggest an alternative image based on my emotional state."

[0193] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0194] Step 1:

[0195] The user uploads images generated using their device to a cloud server. The image data received as input is important for starting processing on the server. The output at this stage is the image data stored on the server.

[0196] Step 2:

[0197] The server extracts feature information from the input image. Using Python and image processing libraries such as OpenCV, it analyzes the main features of the image and quickly obtains the necessary data. This data processing yields the image feature information as output.

[0198] Step 3:

[0199] The server searches a similar image database using the extracted feature information. This process uses the Django framework to calculate the similarity between images and identify similar images from existing image data. The input is feature information, and the output is a list of identified similar images.

[0200] Step 4:

[0201] The server assesses the risk of copyright infringement based on identified similar images. A machine learning model using TensorFlow automatically determines the risk. The output of this process is the risk assessment result.

[0202] Step 5:

[0203] The server acquires facial expressions and voice data from the user to be analyzed for emotion from the terminal and analyzes their emotional state. The acquired data is analyzed using TensorFlow and PyTorch to identify the user's emotions. The output is the analyzed emotional state.

[0204] Step 6:

[0205] The server generates alternative images based on the results of risk assessment and sentiment analysis. Using Flask and a generative AI model (GAN model), it generates alternative images appropriate to the user's emotional state. The output is the generated alternative image.

[0206] Step 7:

[0207] The server provides the generated alternative image to the user's terminal. This final step allows the user to consider various options. The output at this stage is the alternative image presented to the user.

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

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

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

[0211] [Second Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0224] This invention is a system that automatically determines whether a user-generated image infringes copyright and provides an alternative image if necessary. The system is located in a cloud environment and is accessible to users through their own devices.

[0225] The system first receives an image generated by the user. The terminal sends the image to the server via an interface, and the image analysis process begins. After receiving the image, the server internally extracts feature information. This feature information is a collection of visual data points, which quantifies the unique features of the image.

[0226] The server uses the extracted feature information to search for similar images within a comprehensive database. This determines how similar a particular image is to a collection of copyrighted images worldwide. If similar images are found, the server evaluates them and determines the copyright risk. This evaluation includes calculating the similarity score and verifying copyright information.

[0227] If the server determines that there is a high risk of copyright infringement, it will generate an alternative image. The alternative image is newly created by a generation algorithm, has low similarity to the original image, and avoids the risk of copyright infringement. The server will send this generated alternative image to the user's device and send a notification.

[0228] As a concrete example, consider a case where a user generates a new logo using AI and requests a review through this system. The server analyzes the logo's characteristic information and searches the database for similar logos. If a highly similar existing logo is found, the system generates a new, unique logo, providing the user with a safe option to use. Through this process, the user can be protected from the risk of unexpected copyright infringement.

[0229] The following describes the processing flow.

[0230] Step 1:

[0231] The user selects an image generated using their device and uploads it to the system. The device then sends the selected image to the server.

[0232] Step 2:

[0233] The server analyzes the received images and performs image preprocessing. This includes converting image formats and adjusting their size so that they can proceed to the next processing step in a unified format.

[0234] Step 3:

[0235] The server extracts feature information from pre-processed images. This feature information is a numerical representation of the image's visual features and is used for subsequent searches. In particular, it is processed using techniques such as convolutional neural networks (CNNs).

[0236] Step 4:

[0237] The server uses the extracted feature information to search a copyright-aware database. The search uses a similarity calculation algorithm to measure the similarity to existing images and identify similar images.

[0238] Step 5:

[0239] The server evaluates whether there is a risk of copyright infringement between the image entered by the user and an existing image, based on the similarity calculation results. It refers to copyright information to determine whether or not there is a risk.

[0240] Step 6:

[0241] If the server determines that the image poses a high risk, it uses an AI algorithm to generate an alternative image. The generated alternative image will have a low degree of similarity to the original image while retaining its uniqueness.

[0242] Step 7:

[0243] The server sends the evaluation results and alternative images to the user's terminal. The terminal displays the results and the generated alternative images, and the user can select the image to use.

[0244] Step 8:

[0245] The user reviews the presented alternative images and makes a final decision on which image to use. The device can record the user's selection and send it to the server as feedback.

[0246] (Example 1)

[0247] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0248] In recent years, the risk of generated digital data infringing existing copyrights has increased. However, there is a lack of adequate means to automatically detect and avoid this at a feasible speed. This problem hinders creators from creating with peace of mind and can lead to legal issues related to copyright infringement.

[0249] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0250] In this invention, the server includes means for receiving digital data as input, means for extracting identification information, and means for searching a database and identifying corresponding digital data. This makes it possible to quickly detect the risk that the generated digital data infringes existing copyrights and to provide secure alternative digital data.

[0251] "Digital data" refers to information that is processed electronically, and includes data in various forms such as images, audio, and text.

[0252] "Identifying information" refers to a collection of characteristic data points extracted from digital data, used to identify or classify the relevant data.

[0253] A "database" refers to an organized collection of digital data, a collection of information that can be searched and updated.

[0254] A "similarity measurement" is a numerical representation of the degree of similarity between two or more digital data sets, and serves as an indicator for comparative evaluation.

[0255] A "machine learning algorithm" is a set of computational methods used by computers to automatically learn patterns and perform predictions and classifications.

[0256] This invention provides a system that receives digital data as input, extracts identification information, searches a database, and identifies corresponding digital data. The hardware used includes a high-performance server for data processing and a terminal for user data input. The software employs image processing algorithms and machine learning algorithms. Specifically, convolutional neural networks (CNNs) and deep learning models are operated on the server, contributing to the extraction of identification information from digital data.

[0257] The server automatically analyzes the input digital data and performs a database search based on the identification information. The database contains a vast amount of data collected from around the world, and similar digital data is identified from within it. This process is used to identify similar images, audio, and text, making it possible to quickly assess copyright risks.

[0258] As a concrete example, consider a scenario where a user generates a new digital logo using their own device and then checks whether that logo infringes on existing copyrights. In this case, the server analyzes the logo's identification information and searches its database. If a similar existing logo is found, the server can use a generation AI model to generate an alternative logo to mitigate the risk and provide it to the user. This allows users to confidently engage in new creative projects.

[0259] An example of a prompt message is, "Check if this image infringes copyright and generate a new alternative image if necessary." Through this prompt, users can quickly verify the safety and legality of the generated digital data.

[0260] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0261] Step 1:

[0262] The user's terminal inputs the generated digital data (e.g., images or logos) into the system. The input data is then sent from the user's terminal to the server. At this stage, the digital data is passed to the server in its original format.

[0263] Step 2:

[0264] The server analyzes the received digital data and extracts identification information. During this process, the server uses image processing algorithms such as convolutional neural networks (CNNs) to perform data calculations that quantify the features of the image. The extracted identification information represents characteristics such as color, shape, and pattern within the data.

[0265] Step 3:

[0266] The server searches the database based on the extracted identification information. In this process, the server uses a similarity calculation algorithm to identify similar digital data within the database. The database being searched contains a vast amount of copyrighted image data.

[0267] Step 4:

[0268] The server analyzes the search results and assesses copyright risk based on similarity scores. Here, similarity scoring is performed, and if a certain threshold is exceeded, it is determined to be high risk. Based on these results, a risk assessment is made.

[0269] Step 5:

[0270] If a high copyright risk is determined, the server uses a generative AI model to generate alternative digital data. In the generation process, the machine learning model generates new data with lower similarity, referencing the identification information of the input data. The output is new alternative digital data.

[0271] Step 6:

[0272] The generated alternative digital data is output from the server to the user's terminal. The terminal displays the received alternative data on the screen or in a designated location and notifies the user. This allows the user to use the alternative data with confidence.

[0273] (Application Example 1)

[0274] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0275] In advertising visual content, it is essential to proactively prevent copyright infringement risks and select images that can be used safely. In particular, the unintentional use of content similar to existing images can lead to legal problems. Furthermore, even in the process of creating new content using generation AI, it is necessary to provide users with a sense of security regarding copyright.

[0276] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0277] In this invention, the server includes means for selecting an alternative image suitable for the intended use when the image is an advertising medium, means for searching an image database using the above-mentioned characteristic information to identify similar images, and means for generating an alternative image based on the above-mentioned evaluation. This makes it possible to select images that are suitable for advertising while reducing the risk of copyright infringement.

[0278] "Means of receiving images as input" refers to a function that acquires image data provided by the user and incorporates it into the system.

[0279] The "means for extracting feature information" is a function that quantifies unique visual attributes from the input image and prepares the data as basic information for analysis.

[0280] The "means for searching an image database and identifying similar images" is a function that searches within an existing image database based on the extracted feature information and identifies images with high similarity.

[0281] The "means for evaluating copyright risk" is a function that determines legal risks and the possibility of infringement regarding copyright based on the identified similar images.

[0282] The "means for generating alternative images" is a function that creates new images with low similarity and the ability to avoid copyright infringement risks using a generative AI model.

[0283] The "means for providing alternative images to the user" is a function that sends the generated alternative images to the user's terminal to enable viewing and use.

[0284] The "means for selecting alternative images suitable for the purpose of use when it is an advertising medium" is a function that selects and provides the most optimal image for advertising purposes from among the alternative images.

[0285] This invention is a system for reducing the risk of copyright infringement and providing safe images in visual content for advertising. The system consists of a server placed on the cloud and a terminal such as the user's smartphone.

[0286] The user uses a smartphone to select an image for use in the advertisement on the terminal and uploads it to the system. At this stage, the image is sent to the server through the interface of the terminal. The hardware used here includes the user's smartphone and a cloud computing platform operating as a server.

[0287] The server extracts feature information from the received image. This extraction is performed using a machine learning algorithm, which generates data points that numerically represent the image. The server then searches an image database to identify similar images.

[0288] Next, the server assesses copyright risk based on similar images. This assessment includes calculating a similarity score with existing similar images. Based on this information, it determines whether there is a risk of copyright infringement.

[0289] If a copyright risk is deemed high, the server uses a generation AI model to generate an alternative image. This alternative image must be suitable for use in advertising media, and the server selects images with advertising objectives in mind.

[0290] Finally, the server sends the generated replacement image to the user's device. The user can then review the image and use it for advertising. This allows the user to safely use advertising images while avoiding copyright issues.

[0291] As a concrete example, suppose a user wants to create a banner for a new product campaign. In this situation, the user asks the system to check the image and evaluate whether there are any similar images. The server then provides the user with a uniquely designed alternative banner that can be used safely. This allows the user to use the image with confidence.

[0292] An example of a prompt to be input to the generation AI model would be: "Create a new illustration for a commercial poster. Since it may have a high degree of similarity to existing images in the database, please generate a unique design in a new style."

[0293] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0294] Step 1:

[0295] The user selects an image for advertising on their device and uploads it to the system. The input is image data stored on the user's device. The device sends the data to the server through an interface. This transmission prepares the image for processing on the server.

[0296] Step 2:

[0297] The server extracts feature information from the received image. The input is image data sent to the server. The server uses machine learning algorithms to convert the image into numerical information, obtaining a set of unique data points as output. This allows the image's structure and color features to be quantified and represented.

[0298] Step 3:

[0299] The server searches an image database based on feature information and identifies similar images. The input is quantified feature information. The server calculates the similarity to each image in the database and outputs a similarity score. The output is a list of similar images and their similarity scores.

[0300] Step 4:

[0301] The server assesses copyright risk based on identified similar images. The input consists of a list of similar images and their similarity scores. The server numerically evaluates the likelihood of copyright infringement based on these scores and outputs the risk level. This evaluation allows for the determination of high or low risk.

[0302] Step 5:

[0303] If a high copyright risk is determined, the server generates an alternative image using a generative AI model. The input is the result of the copyright risk assessment. The server uses a prompt to activate the generative AI model and outputs a new alternative image. The output is an alternative image that avoids the copyright risk associated with the original image.

[0304] Step 6:

[0305] The server transmits the generated alternative image to the user's terminal. The input is the generated alternative image. The server transfers the alternative image to the user's terminal, and as output, the user can receive a new unique image. This enables the user to use the image for advertising with confidence.

[0306] Furthermore, an emotion engine for estimating the user's emotions may be combined. That is, the specific processing unit 290 may estimate the user's emotions using the emotion recognition model 59 and perform specific processing using the user's emotions.

[0307] The present invention combines an emotion recognition function with a system that automatically determines the risk of copyright infringement for an image generated by a user compared to similar images and provides an alternative image as needed. This system is provided on a cloud basis and can be easily accessed via the user's terminal. The user interface is designed to be intuitively operable, and images can be quickly uploaded and analysis can be started.

[0308] First, the system starts processing by the user uploading the generated image to the server. After receiving the image, the server extracts the feature information of the image and performs a comparative search using the similar image database. This process confirms whether the user's image is similar to an image protected by an existing copyright.

[0309] When the evaluation of the copyright risk is completed, the system then uses the emotion engine to recognize the user's emotional state. The terminal is equipped with a camera or other input device, and emotions can be analyzed from the user's expression, voice, or usage pattern.

[0310] After the emotion engine recognizes the user's emotional state, the server presents alternative images appropriate to that state. For example, if the system detects that the user is feeling anxious, it will generate an alternative image with a more friendly design. Conversely, if a positive emotion is detected, it can present an image with a more creative style.

[0311] As a concrete example, consider a case where a user generates a new advertising image using AI and requests a review through the system. In this case, the server first analyzes the image and searches for similar images. Simultaneously, the emotion engine analyzes the user's emotions. If the server recognizes a risk of copyright infringement and determines that the user is feeling uneasy, the system provides a reassuring alternative image to help the user make a comfortable final decision.

[0312] This system combines copyright risk management with emotion recognition features to enhance the user experience, providing flexible and comprehensive support for users to use images with confidence.

[0313] The following describes the processing flow.

[0314] Step 1:

[0315] The user generates a new image using an AI image generation tool and uploads that image to the system via their device. The device then sends the image data to the server.

[0316] Step 2:

[0317] The server analyzes the received image and extracts its feature information. This feature information represents the visual features as numerical data.

[0318] Step 3:

[0319] The server searches a database of similar images based on the feature information. It uses an algorithm to calculate similarity and determine how similar the image is to existing images.

[0320] Step 4:

[0321] The server assesses the risk of copyright infringement based on the results of identifying similar images. If a copyright risk is identified, it makes a determination to that effect.

[0322] Step 5:

[0323] The emotion engine operates through an input device connected to the terminal, detecting the user's emotional state. This is analyzed from the user's facial expressions, voice, and interaction style.

[0324] Step 6:

[0325] Based on the results analyzed by the emotion engine, the server adjusts the generation and presentation methods of alternative images according to the user's emotions.

[0326] Step 7:

[0327] The user reviews the risk assessment results. If the risk is high, the server displays alternative images on the user's device, and the user can select an image from the presented options.

[0328] Step 8:

[0329] The device sends this information to the server, taking into account the user's choices and emotional feedback. This data is used to improve the system and for future processing.

[0330] (Example 2)

[0331] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0332] The use of digital images carries the risk of copyright infringement, so users need ways to properly assess this risk and use images with peace of mind. Furthermore, there is a need to improve the user experience by providing images that are optimal according to the user's emotional state.

[0333] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0334] In this invention, the server includes means for receiving an image as input, means for extracting feature information from the image, means for identifying similar images and evaluating copyright risk, and means for recognizing the user's emotional state and generating an alternative image corresponding to that emotion. This reduces the risk of copyright infringement and provides an alternative image suitable for the user's emotional state, enabling the user to use images with peace of mind.

[0335] "Means for receiving images as input" refers to a function for importing user-generated or specified image data into a server or related system.

[0336] "Methods for extracting feature information" refer to the process of analyzing various attributes and patterns of an image to extract identifiable data.

[0337] "A means of searching an image database and identifying similar images" refers to a function that finds similar images from a large collection of images based on extracted feature information.

[0338] A "means of assessing copyright risk" is a method of calculating the likelihood that a subject image infringes on existing copyrights by comparing it with similar images.

[0339] "Means for recognizing a user's emotional state" refers to technologies that analyze a user's facial expressions, behavior, voice data, etc., to understand their current emotions.

[0340] "Means for generating alternative images according to emotional state" refers to the process of creating new images with designs and styles that best suit the user's emotions.

[0341] "Means of providing alternative images" refers to a mechanism that presents generated alternative images to the user, allowing them to select and use them.

[0342] This invention provides a system that evaluates the copyright risk of user-generated images and, taking into account the user's emotional state, offers the most suitable alternative image. This system is cloud-based and accessible from the user's own device. Specifically, the process begins when the user uploads the generated image to a server in the cloud.

[0343] When the server receives an image, it first uses an image analysis tool to extract feature information. Specifically, it uses image processing libraries such as TensorFlow and OpenCV to analyze the image's patterns, color tones, and shapes. After that, it searches a similar image database using the Google Cloud Vision API. This allows it to check how similar the image is to existing copyrighted images.

[0344] Next, the system uses the camera and microphone on the user's device to recognize the user's emotional state. The device sends the collected data to a server, which uses Microsoft Azure's Emotion API to analyze the user's emotions. This allows the system to determine whether the user is feeling anxious or happy.

[0345] Based on this information, the server generates alternative images using a generative AI model (e.g., DALL-E). An example of a prompt might be, "Generate a relaxing ocean view." Based on this prompt, the system generates an image best suited to the user's emotional state and provides it to the user.

[0346] As a concrete example, consider a user who wants to create an advertising image for promotional purposes. The user uploads an image generated using AI to the system, and the server analyzes the image and searches for similar images. At the same time, the user's emotional state is analyzed, and if, for example, anxiety is detected, an alternative image that calms the user is generated and provided. In this way, the user can obtain an image that they can use with peace of mind.

[0347] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0348] Step 1:

[0349] The user uploads images generated using their device to the cloud system. The device sends and receives the image data from the server. The input is the image generated by the user, and the output is the image data stored on the server.

[0350] Step 2:

[0351] The server extracts feature information from the received image data. Specifically, it uses image analysis tools such as TensorFlow and OpenCV to analyze the patterns, shapes, and color tones of the images. In this step, the input is the image data stored on the server, and the output is the extracted feature information.

[0352] Step 3:

[0353] The server uses the extracted feature information to search an image database and identify similar images. It utilizes the Google Cloud Vision API to identify highly similar images. The input is feature information, and the output is a list of similar images and a similarity score for each image.

[0354] Step 4:

[0355] The server assesses copyright infringement risk based on similarity scores. Here, a high risk is determined if the similarity score exceeds a specified threshold. The input is a list of similar images and their similarity scores, and the output is the copyright risk assessment result.

[0356] Step 5:

[0357] The device uses its camera and microphone to collect the user's facial expressions and voice, and obtains data to identify their emotions. This data is then sent to a server. The input is the user's facial expressions and voice data, and the output is the unanalyzed emotion data transferred to the server.

[0358] Step 6:

[0359] The server uses the received emotion data to recognize the user's emotional state. It uses the Microsoft Azure Emotion API to analyze whether the user is feeling anxious or happy. The input is unanalyzed emotion data, and the output is the user's emotional state.

[0360] Step 7:

[0361] The server uses a generative AI model to generate alternative images that correspond to the user's emotional state. Prompts such as "Generate a relaxing ocean view" are used. The input is the user's emotional state, and the output is the generated alternative image.

[0362] Step 8:

[0363] The server provides the user with generated alternative images and prompts them to make a final selection. These are displayed on the terminal, allowing the user to review and use the suggested alternative images. The input is the generated alternative image, and the output is the alternative image reviewed by the user.

[0364] (Application Example 2)

[0365] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0366] Image generation requires the ability to quickly and effectively assess the risk of copyright infringement and provide feedback tailored to the image creator's emotional state. Conventional systems often fail to consider the user's emotional state, resulting in alternative solutions that don't align with the user's psychological condition. This leads to a lack of support for users in making optimal decisions.

[0367] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0368] In this invention, the server includes means for receiving an image as input, means for extracting feature information, and means for recognizing the emotional state of the image creator through an emotion analysis function. This makes it possible to combine emotion recognition with copyright risk assessment and present appropriate alternative images according to the user's psychological state.

[0369] "Means for receiving images as input" refers to a configuration that has the function of transferring user-generated image data to a server and inputting it for processing.

[0370] "Means for extracting feature information" refers to a function that analyzes the features of an image from received image data and obtains the information necessary for identification.

[0371] "A means of searching an image database and identifying similar images" refers to a function that uses extracted feature information to refer to an existing database and executes a process to identify similar images.

[0372] A "means for assessing copyright risk" is a function that determines the risk of whether an image is protected by copyright based on identified similar images.

[0373] "Means of recognizing the emotional state of the image creator through emotion analysis" refers to a function that uses the user's camera, microphone, or other devices to analyze the user's emotional state from their facial expressions and voice.

[0374] "Means for generating alternative images" refers to a function that creates appropriate alternative image suggestions for the user based on the results of copyright risk assessment and sentiment analysis.

[0375] "Means of providing the above alternative images to the user" refers to a function that presents the generated alternative images to the user in an easy-to-view manner and makes them available for use.

[0376] The system realized by this invention operates on a cloud-based system and consists of a program for receiving and processing images generated by image creators as input. Broadly speaking, this system operates based on the following main steps.

[0377] First, the image generator uploads the generated image to the cloud server via their device. This image is crucial as a starting point for processing on the server. The server analyzes the received image and extracts feature information. To do this, it uses image processing libraries such as Python and OpenCV to quickly obtain the necessary data from the image.

[0378] Next, the server uses the extracted feature information to search a pre-built database of similar images. This process uses a similarity algorithm to identify the similarity between the generated image and existing images. The Django framework is used for this data processing and computation, enabling efficient data management and backend operation.

[0379] Next, the server assesses the risk of copyright infringement based on similar images. In this process, a machine learning model is implemented using TensorFlow to perform automated decisions for risk assessment.

[0380] Furthermore, the system uses emotion analysis capabilities to understand the emotional state of the image creator. In this step, data is acquired from the camera and microphone on the user's device, and emotions are analyzed using TensorFlow and PyTorch.

[0381] Finally, based on the copyright risk assessment and emotional state analysis, alternative images are generated. The software used here combines Flask and a GAN model to assist in image generation using a generative AI model. These generated alternative images are provided to the user, offering a variety of choices.

[0382] For example, when an advertising creator generates a new image for an advertisement, this system checks the copyright risk of the image and simultaneously generates the most suitable alternative image based on the creator's emotional state. An example of a prompt message would be, "Please check the generated advertising image for copyright infringement of similar images and suggest an alternative image based on my emotional state."

[0383] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0384] Step 1:

[0385] The user uploads images generated using their device to a cloud server. The image data received as input is important for starting processing on the server. The output at this stage is the image data stored on the server.

[0386] Step 2:

[0387] The server extracts feature information from the input image. Using Python and image processing libraries such as OpenCV, it analyzes the main features of the image and quickly obtains the necessary data. This data processing yields the image feature information as output.

[0388] Step 3:

[0389] The server searches a similar image database using the extracted feature information. This process uses the Django framework to calculate the similarity between images and identify similar images from existing image data. The input is feature information, and the output is a list of identified similar images.

[0390] Step 4:

[0391] The server assesses the risk of copyright infringement based on identified similar images. A machine learning model using TensorFlow automatically determines the risk. The output of this process is the risk assessment result.

[0392] Step 5:

[0393] The server acquires facial expressions and voice data from the user to be analyzed for emotion from the terminal and analyzes their emotional state. The acquired data is analyzed using TensorFlow and PyTorch to identify the user's emotions. The output is the analyzed emotional state.

[0394] Step 6:

[0395] The server generates alternative images based on the results of risk assessment and sentiment analysis. Using Flask and a generative AI model (GAN model), it generates alternative images appropriate to the user's emotional state. The output is the generated alternative image.

[0396] Step 7:

[0397] The server provides the generated alternative image to the user's terminal. This final step allows the user to consider various options. The output at this stage is the alternative image presented to the user.

[0398] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0399] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0400] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0401] [Third Embodiment]

[0402] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0403] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0404] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0405] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0406] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0407] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0408] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0409] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0410] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0411] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0412] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0413] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0414] This invention is a system that automatically determines whether a user-generated image infringes copyright and provides an alternative image if necessary. The system is located in a cloud environment and is accessible to users through their own devices.

[0415] The system first receives an image generated by the user. The terminal sends the image to the server via an interface, and the image analysis process begins. After receiving the image, the server internally extracts feature information. This feature information is a collection of visual data points, which quantifies the unique features of the image.

[0416] The server uses the extracted feature information to search for similar images within a comprehensive database. This determines how similar a particular image is to a collection of copyrighted images worldwide. If similar images are found, the server evaluates them and determines the copyright risk. This evaluation includes calculating the similarity score and verifying copyright information.

[0417] If the server determines that there is a high risk of copyright infringement, it will generate an alternative image. The alternative image is newly created by a generation algorithm, has low similarity to the original image, and avoids the risk of copyright infringement. The server will send this generated alternative image to the user's device and send a notification.

[0418] As a concrete example, consider a case where a user generates a new logo using AI and requests a review through this system. The server analyzes the logo's characteristic information and searches the database for similar logos. If a highly similar existing logo is found, the system generates a new, unique logo, providing the user with a safe option to use. Through this process, the user can be protected from the risk of unexpected copyright infringement.

[0419] The following describes the processing flow.

[0420] Step 1:

[0421] The user selects an image generated using their device and uploads it to the system. The device then sends the selected image to the server.

[0422] Step 2:

[0423] The server analyzes the received images and performs image preprocessing. This includes converting image formats and adjusting their size so that they can proceed to the next processing step in a unified format.

[0424] Step 3:

[0425] The server extracts feature information from pre-processed images. This feature information is a numerical representation of the image's visual features and is used for subsequent searches. In particular, it is processed using techniques such as convolutional neural networks (CNNs).

[0426] Step 4:

[0427] The server uses the extracted feature information to search a copyright-aware database. The search uses a similarity calculation algorithm to measure the similarity to existing images and identify similar images.

[0428] Step 5:

[0429] The server evaluates whether there is a risk of copyright infringement between the image entered by the user and an existing image, based on the similarity calculation results. It refers to copyright information to determine whether or not there is a risk.

[0430] Step 6:

[0431] If the server determines that the image poses a high risk, it uses an AI algorithm to generate an alternative image. The generated alternative image will have a low degree of similarity to the original image while retaining its uniqueness.

[0432] Step 7:

[0433] The server sends the evaluation results and alternative images to the user's terminal. The terminal displays the results and the generated alternative images, and the user can select the image to use.

[0434] Step 8:

[0435] The user reviews the presented alternative images and makes a final decision on which image to use. The device can record the user's selection and send it to the server as feedback.

[0436] (Example 1)

[0437] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0438] In recent years, the risk of generated digital data infringing existing copyrights has increased. However, there is a lack of adequate means to automatically detect and avoid this at a feasible speed. This problem hinders creators from creating with peace of mind and can lead to legal issues related to copyright infringement.

[0439] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0440] In this invention, the server includes means for receiving digital data as input, means for extracting identification information, and means for searching a database and identifying corresponding digital data. This makes it possible to quickly detect the risk that the generated digital data infringes existing copyrights and to provide secure alternative digital data.

[0441] "Digital data" refers to information that is processed electronically, and includes data in various forms such as images, audio, and text.

[0442] "Identifying information" refers to a collection of characteristic data points extracted from digital data, used to identify or classify the relevant data.

[0443] A "database" refers to an organized collection of digital data, a collection of information that can be searched and updated.

[0444] A "similarity measurement" is a numerical representation of the degree of similarity between two or more digital data sets, and serves as an indicator for comparative evaluation.

[0445] A "machine learning algorithm" is a set of computational methods used by computers to automatically learn patterns and perform predictions and classifications.

[0446] This invention provides a system that receives digital data as input, extracts identification information, searches a database, and identifies corresponding digital data. The hardware used includes a high-performance server for data processing and a terminal for user data input. The software employs image processing algorithms and machine learning algorithms. Specifically, convolutional neural networks (CNNs) and deep learning models are operated on the server, contributing to the extraction of identification information from digital data.

[0447] The server automatically analyzes the input digital data and performs a database search based on the identification information. The database contains a vast amount of data collected from around the world, and similar digital data is identified from within it. This process is used to identify similar images, audio, and text, making it possible to quickly assess copyright risks.

[0448] As a concrete example, consider a scenario where a user generates a new digital logo using their own device and then checks whether that logo infringes on existing copyrights. In this case, the server analyzes the logo's identification information and searches its database. If a similar existing logo is found, the server can use a generation AI model to generate an alternative logo to mitigate the risk and provide it to the user. This allows users to confidently engage in new creative projects.

[0449] An example of a prompt message is, "Check if this image infringes copyright and generate a new alternative image if necessary." Through this prompt, users can quickly verify the safety and legality of the generated digital data.

[0450] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0451] Step 1:

[0452] The user's terminal inputs the generated digital data (e.g., images or logos) into the system. The input data is then sent from the user's terminal to the server. At this stage, the digital data is passed to the server in its original format.

[0453] Step 2:

[0454] The server analyzes the received digital data and extracts identification information. During this process, the server uses image processing algorithms such as convolutional neural networks (CNNs) to perform data calculations that quantify the features of the image. The extracted identification information represents characteristics such as color, shape, and pattern within the data.

[0455] Step 3:

[0456] The server searches the database based on the extracted identification information. In this process, the server uses a similarity calculation algorithm to identify similar digital data within the database. The database being searched contains a vast amount of copyrighted image data.

[0457] Step 4:

[0458] The server analyzes the search results and assesses copyright risk based on similarity scores. Here, similarity scoring is performed, and if a certain threshold is exceeded, it is determined to be high risk. Based on these results, a risk assessment is made.

[0459] Step 5:

[0460] If a high copyright risk is determined, the server uses a generative AI model to generate alternative digital data. In the generation process, the machine learning model generates new data with lower similarity, referencing the identification information of the input data. The output is new alternative digital data.

[0461] Step 6:

[0462] The generated alternative digital data is output from the server to the user's terminal. The terminal displays the received alternative data on the screen or in a designated location and notifies the user. This allows the user to use the alternative data with confidence.

[0463] (Application Example 1)

[0464] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0465] In advertising visual content, it is essential to proactively prevent copyright infringement risks and select images that can be used safely. In particular, the unintentional use of content similar to existing images can lead to legal problems. Furthermore, even in the process of creating new content using generation AI, it is necessary to provide users with a sense of security regarding copyright.

[0466] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0467] In this invention, the server includes means for selecting an alternative image suitable for the intended use when the image is an advertising medium, means for searching an image database using the above-mentioned characteristic information to identify similar images, and means for generating an alternative image based on the above-mentioned evaluation. This makes it possible to select images that are suitable for advertising while reducing the risk of copyright infringement.

[0468] "Means of receiving images as input" refers to a function that acquires image data provided by the user and incorporates it into the system.

[0469] "Means for extracting feature information" refers to a function that quantifies unique visual attributes from an input image and prepares that data as basic information for analysis.

[0470] "A means of searching an image database and identifying similar images" refers to a function that searches within an existing image database based on extracted feature information and identifies images with high similarity.

[0471] A "means for assessing copyright risk" is a function that determines legal risks and potential infringement related to copyright based on identified similar images.

[0472] "Methods for generating alternative images" refers to a function that uses a generation AI model to create new images with low similarity that avoid the risk of copyright infringement.

[0473] "Means of providing alternative images to users" refers to a function that sends the generated alternative images to the user's device, enabling them to view and use them.

[0474] "Means of selecting alternative images suitable for their intended use in the case of advertising media" refers to a function that selects and provides images that are particularly suitable for advertising purposes from among the alternative images.

[0475] This invention is a system for reducing the risk of copyright infringement in visual content for advertising and providing safe images. The system consists of a server located in the cloud and a user's terminal such as a smartphone.

[0476] Users use their smartphones to select images to be used in advertisements and upload them to the system. At this stage, the images are sent to the server via the device's interface. The hardware used here consists of the user's smartphone and a cloud computing platform acting as the server.

[0477] The server extracts feature information from the received image. This extraction is performed using a machine learning algorithm, which generates data points that numerically represent the image. The server then searches an image database to identify similar images.

[0478] Next, the server assesses copyright risk based on similar images. This assessment includes calculating a similarity score with existing similar images. Based on this information, it determines whether there is a risk of copyright infringement.

[0479] If a copyright risk is deemed high, the server uses a generation AI model to generate an alternative image. This alternative image must be suitable for use in advertising media, and the server selects images with advertising objectives in mind.

[0480] Finally, the server sends the generated replacement image to the user's device. The user can then review the image and use it for advertising. This allows the user to safely use advertising images while avoiding copyright issues.

[0481] As a concrete example, suppose a user wants to create a banner for a new product campaign. In this situation, the user asks the system to check the image and evaluate whether there are any similar images. The server then provides the user with a uniquely designed alternative banner that can be used safely. This allows the user to use the image with confidence.

[0482] An example of a prompt to be input to the generation AI model would be: "Create a new illustration for a commercial poster. Since it may have a high degree of similarity to existing images in the database, please generate a unique design in a new style."

[0483] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0484] Step 1:

[0485] The user selects an image for advertising on their device and uploads it to the system. The input is image data stored on the user's device. The device sends the data to the server through an interface. This transmission prepares the image for processing on the server.

[0486] Step 2:

[0487] The server extracts feature information from the received image. The input is image data sent to the server. The server uses machine learning algorithms to convert the image into numerical information, obtaining a set of unique data points as output. This allows the image's structure and color features to be quantified and represented.

[0488] Step 3:

[0489] The server searches an image database based on feature information and identifies similar images. The input is quantified feature information. The server calculates the similarity to each image in the database and outputs a similarity score. The output is a list of similar images and their similarity scores.

[0490] Step 4:

[0491] The server assesses copyright risk based on identified similar images. The input consists of a list of similar images and their similarity scores. The server numerically evaluates the likelihood of copyright infringement based on these scores and outputs the risk level. This evaluation allows for the determination of high or low risk.

[0492] Step 5:

[0493] If a high copyright risk is determined, the server generates an alternative image using a generative AI model. The input is the result of the copyright risk assessment. The server uses a prompt to activate the generative AI model and outputs a new alternative image. The output is an alternative image that avoids the copyright risk associated with the original image.

[0494] Step 6:

[0495] The server sends the generated alternative image to the user's device. The input is the generated alternative image. The server transfers the alternative image to the user's device, and the user can receive a new, unique image as output. This allows the user to confidently use the image for advertising.

[0496] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0497] This invention combines emotion recognition with a system that automatically determines the risk of copyright infringement by comparing user-generated images with similar images and providing alternative images as needed. This system is cloud-based and easily accessible via the user's device. The user interface is designed for intuitive operation, allowing for quick image uploads and analysis.

[0498] First, the system begins processing when the user uploads the image they have generated to the server. After receiving the image, the server extracts its feature information and performs a comparative search using a similar image database. This process verifies whether the user's image is similar to an existing copyrighted image.

[0499] Once the copyright risk assessment is complete, the system then uses an emotion engine to recognize the user's emotional state. The device is equipped with a camera or other input device that can analyze emotions from the user's facial expressions, voice, or usage patterns.

[0500] After the emotion engine recognizes the user's emotional state, the server presents alternative images appropriate to that state. For example, if the system detects that the user is feeling anxious, it will generate an alternative image with a more friendly design. Conversely, if a positive emotion is detected, it can present an image with a more creative style.

[0501] As a concrete example, consider a case where a user generates a new advertising image using AI and requests a review through the system. In this case, the server first analyzes the image and searches for similar images. Simultaneously, the emotion engine analyzes the user's emotions. If the server recognizes a risk of copyright infringement and determines that the user is feeling uneasy, the system provides a reassuring alternative image to help the user make a comfortable final decision.

[0502] This system combines copyright risk management with emotion recognition features to enhance the user experience, providing flexible and comprehensive support for users to use images with confidence.

[0503] The following describes the processing flow.

[0504] Step 1:

[0505] The user generates a new image using an AI image generation tool and uploads that image to the system via their device. The device then sends the image data to the server.

[0506] Step 2:

[0507] The server analyzes the received image and extracts its feature information. This feature information represents the visual features as numerical data.

[0508] Step 3:

[0509] The server searches a database of similar images based on the feature information. It uses an algorithm to calculate similarity and determine how similar the image is to existing images.

[0510] Step 4:

[0511] The server assesses the risk of copyright infringement based on the results of identifying similar images. If a copyright risk is identified, it makes a determination to that effect.

[0512] Step 5:

[0513] The emotion engine operates through an input device connected to the terminal, detecting the user's emotional state. This is analyzed from the user's facial expressions, voice, and interaction style.

[0514] Step 6:

[0515] Based on the results analyzed by the emotion engine, the server adjusts the generation and presentation methods of alternative images according to the user's emotions.

[0516] Step 7:

[0517] The user reviews the risk assessment results. If the risk is high, the server displays alternative images on the user's device, and the user can select an image from the presented options.

[0518] Step 8:

[0519] The device sends this information to the server, taking into account the user's choices and emotional feedback. This data is used to improve the system and for future processing.

[0520] (Example 2)

[0521] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0522] The use of digital images carries the risk of copyright infringement, so users need ways to properly assess this risk and use images with peace of mind. Furthermore, there is a need to improve the user experience by providing images that are optimal according to the user's emotional state.

[0523] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0524] In this invention, the server includes means for receiving an image as input, means for extracting feature information from the image, means for identifying similar images and evaluating copyright risk, and means for recognizing the user's emotional state and generating an alternative image corresponding to that emotion. This reduces the risk of copyright infringement and provides an alternative image suitable for the user's emotional state, enabling the user to use images with peace of mind.

[0525] "Means for receiving images as input" refers to a function for importing user-generated or specified image data into a server or related system.

[0526] "Methods for extracting feature information" refer to the process of analyzing various attributes and patterns of an image to extract identifiable data.

[0527] "A means of searching an image database and identifying similar images" refers to a function that finds similar images from a large collection of images based on extracted feature information.

[0528] A "means of assessing copyright risk" is a method of calculating the likelihood that a subject image infringes on existing copyrights by comparing it with similar images.

[0529] "Means for recognizing a user's emotional state" refers to technologies that analyze a user's facial expressions, behavior, voice data, etc., to understand their current emotions.

[0530] "Means for generating alternative images according to emotional state" refers to the process of creating new images with designs and styles that best suit the user's emotions.

[0531] "Means of providing alternative images" refers to a mechanism that presents generated alternative images to the user, allowing them to select and use them.

[0532] This invention provides a system that evaluates the copyright risk of user-generated images and, taking into account the user's emotional state, offers the most suitable alternative image. This system is cloud-based and accessible from the user's own device. Specifically, the process begins when the user uploads the generated image to a server in the cloud.

[0533] When the server receives an image, it first uses an image analysis tool to extract feature information. Specifically, it uses image processing libraries such as TensorFlow and OpenCV to analyze the image's patterns, color tones, and shapes. After that, it searches a similar image database using the Google Cloud Vision API. This allows it to check how similar the image is to existing copyrighted images.

[0534] Next, the system uses the camera and microphone on the user's device to recognize the user's emotional state. The device sends the collected data to a server, which uses Microsoft Azure's Emotion API to analyze the user's emotions. This allows the system to determine whether the user is feeling anxious or happy.

[0535] Based on this information, the server generates alternative images using a generative AI model (e.g., DALL-E). An example of a prompt might be, "Generate a relaxing ocean view." Based on this prompt, the system generates an image best suited to the user's emotional state and provides it to the user.

[0536] As a concrete example, consider a user who wants to create an advertising image for promotional purposes. The user uploads an image generated using AI to the system, and the server analyzes the image and searches for similar images. At the same time, the user's emotional state is analyzed, and if, for example, anxiety is detected, an alternative image that calms the user is generated and provided. In this way, the user can obtain an image that they can use with peace of mind.

[0537] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0538] Step 1:

[0539] The user uploads images generated using their device to the cloud system. The device sends and receives the image data from the server. The input is the image generated by the user, and the output is the image data stored on the server.

[0540] Step 2:

[0541] The server extracts feature information from the received image data. Specifically, it uses image analysis tools such as TensorFlow and OpenCV to analyze the patterns, shapes, and color tones of the images. In this step, the input is the image data stored on the server, and the output is the extracted feature information.

[0542] Step 3:

[0543] The server uses the extracted feature information to search an image database and identify similar images. It utilizes the Google Cloud Vision API to identify highly similar images. The input is feature information, and the output is a list of similar images and a similarity score for each image.

[0544] Step 4:

[0545] The server assesses copyright infringement risk based on similarity scores. Here, a high risk is determined if the similarity score exceeds a specified threshold. The input is a list of similar images and their similarity scores, and the output is the copyright risk assessment result.

[0546] Step 5:

[0547] The device uses its camera and microphone to collect the user's facial expressions and voice, and obtains data to identify their emotions. This data is then sent to a server. The input is the user's facial expressions and voice data, and the output is the unanalyzed emotion data transferred to the server.

[0548] Step 6:

[0549] The server uses the received emotion data to recognize the user's emotional state. It uses the Microsoft Azure Emotion API to analyze whether the user is feeling anxious or happy. The input is unanalyzed emotion data, and the output is the user's emotional state.

[0550] Step 7:

[0551] The server uses a generative AI model to generate alternative images that correspond to the user's emotional state. Prompts such as "Generate a relaxing ocean view" are used. The input is the user's emotional state, and the output is the generated alternative image.

[0552] Step 8:

[0553] The server provides the user with generated alternative images and prompts them to make a final selection. These are displayed on the terminal, allowing the user to review and use the suggested alternative images. The input is the generated alternative image, and the output is the alternative image reviewed by the user.

[0554] (Application Example 2)

[0555] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0556] Image generation requires the ability to quickly and effectively assess the risk of copyright infringement and provide feedback tailored to the image creator's emotional state. Conventional systems often fail to consider the user's emotional state, resulting in alternative solutions that don't align with the user's psychological condition. This leads to a lack of support for users in making optimal decisions.

[0557] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0558] In this invention, the server includes means for receiving an image as input, means for extracting feature information, and means for recognizing the emotional state of the image creator through an emotion analysis function. This makes it possible to combine emotion recognition with copyright risk assessment and present appropriate alternative images according to the user's psychological state.

[0559] "Means for receiving images as input" refers to a configuration that has the function of transferring user-generated image data to a server and inputting it for processing.

[0560] "Means for extracting feature information" refers to a function that analyzes the features of an image from received image data and obtains the information necessary for identification.

[0561] "A means of searching an image database and identifying similar images" refers to a function that uses extracted feature information to refer to an existing database and executes a process to identify similar images.

[0562] A "means for assessing copyright risk" is a function that determines the risk of whether an image is protected by copyright based on identified similar images.

[0563] "Means of recognizing the emotional state of the image creator through emotion analysis" refers to a function that uses the user's camera, microphone, or other devices to analyze the user's emotional state from their facial expressions and voice.

[0564] "Means for generating alternative images" refers to a function that creates appropriate alternative image suggestions for the user based on the results of copyright risk assessment and sentiment analysis.

[0565] "Means of providing the above alternative images to the user" refers to a function that presents the generated alternative images to the user in an easy-to-view manner and makes them available for use.

[0566] The system realized by this invention operates on a cloud-based system and consists of a program for receiving and processing images generated by image creators as input. Broadly speaking, this system operates based on the following main steps.

[0567] First, the image generator uploads the generated image to the cloud server via their device. This image is crucial as a starting point for processing on the server. The server analyzes the received image and extracts feature information. To do this, it uses image processing libraries such as Python and OpenCV to quickly obtain the necessary data from the image.

[0568] Next, the server uses the extracted feature information to search a pre-built database of similar images. This process uses a similarity algorithm to identify the similarity between the generated image and existing images. The Django framework is used for this data processing and computation, enabling efficient data management and backend operation.

[0569] Next, the server assesses the risk of copyright infringement based on similar images. In this process, a machine learning model is implemented using TensorFlow to perform automated decisions for risk assessment.

[0570] Furthermore, the system uses emotion analysis capabilities to understand the emotional state of the image creator. In this step, data is acquired from the camera and microphone on the user's device, and emotions are analyzed using TensorFlow and PyTorch.

[0571] Finally, based on the copyright risk assessment and emotional state analysis, alternative images are generated. The software used here combines Flask and a GAN model to assist in image generation using a generative AI model. These generated alternative images are provided to the user, offering a variety of choices.

[0572] For example, when an advertising creator generates a new image for an advertisement, this system checks the copyright risk of the image and simultaneously generates the most suitable alternative image based on the creator's emotional state. An example of a prompt message would be, "Please check the generated advertising image for copyright infringement of similar images and suggest an alternative image based on my emotional state."

[0573] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0574] Step 1:

[0575] The user uploads images generated using their device to a cloud server. The image data received as input is important for starting processing on the server. The output at this stage is the image data stored on the server.

[0576] Step 2:

[0577] The server extracts feature information from the input image. Using Python and image processing libraries such as OpenCV, it analyzes the main features of the image and quickly obtains the necessary data. This data processing yields the image feature information as output.

[0578] Step 3:

[0579] The server searches a similar image database using the extracted feature information. This process uses the Django framework to calculate the similarity between images and identify similar images from existing image data. The input is feature information, and the output is a list of identified similar images.

[0580] Step 4:

[0581] The server assesses the risk of copyright infringement based on identified similar images. A machine learning model using TensorFlow automatically determines the risk. The output of this process is the risk assessment result.

[0582] Step 5:

[0583] The server acquires facial expressions and voice data from the user to be analyzed for emotion from the terminal and analyzes their emotional state. The acquired data is analyzed using TensorFlow and PyTorch to identify the user's emotions. The output is the analyzed emotional state.

[0584] Step 6:

[0585] The server generates alternative images based on the results of risk assessment and sentiment analysis. Using Flask and a generative AI model (GAN model), it generates alternative images appropriate to the user's emotional state. The output is the generated alternative image.

[0586] Step 7:

[0587] The server provides the generated alternative image to the user's terminal. This final step allows the user to consider various options. The output at this stage is the alternative image presented to the user.

[0588] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0589] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0590] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0591] [Fourth Embodiment]

[0592] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0593] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0594] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0595] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0596] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0597] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0598] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0599] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0600] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0601] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0602] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0603] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0604] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0605] This invention is a system that automatically determines whether a user-generated image infringes copyright and provides an alternative image if necessary. The system is located in a cloud environment and is accessible to users through their own devices.

[0606] The system first receives an image generated by the user. The terminal sends the image to the server via an interface, and the image analysis process begins. After receiving the image, the server internally extracts feature information. This feature information is a collection of visual data points, which quantifies the unique features of the image.

[0607] The server uses the extracted feature information to search for similar images within a comprehensive database. This determines how similar a particular image is to a collection of copyrighted images worldwide. If similar images are found, the server evaluates them and determines the copyright risk. This evaluation includes calculating the similarity score and verifying copyright information.

[0608] If the server determines that there is a high risk of copyright infringement, it will generate an alternative image. The alternative image is newly created by a generation algorithm, has low similarity to the original image, and avoids the risk of copyright infringement. The server will send this generated alternative image to the user's device and send a notification.

[0609] As a concrete example, consider a case where a user generates a new logo using AI and requests a review through this system. The server analyzes the logo's characteristic information and searches the database for similar logos. If a highly similar existing logo is found, the system generates a new, unique logo, providing the user with a safe option to use. Through this process, the user can be protected from the risk of unexpected copyright infringement.

[0610] The following describes the processing flow.

[0611] Step 1:

[0612] The user selects an image generated using their device and uploads it to the system. The device then sends the selected image to the server.

[0613] Step 2:

[0614] The server analyzes the received images and performs image preprocessing. This includes converting image formats and adjusting their size so that they can proceed to the next processing step in a unified format.

[0615] Step 3:

[0616] The server extracts feature information from pre-processed images. This feature information is a numerical representation of the image's visual features and is used for subsequent searches. In particular, it is processed using techniques such as convolutional neural networks (CNNs).

[0617] Step 4:

[0618] The server uses the extracted feature information to search a copyright-aware database. The search uses a similarity calculation algorithm to measure the similarity to existing images and identify similar images.

[0619] Step 5:

[0620] The server evaluates whether there is a risk of copyright infringement between the image entered by the user and an existing image, based on the similarity calculation results. It refers to copyright information to determine whether or not there is a risk.

[0621] Step 6:

[0622] If the server determines that the image poses a high risk, it uses an AI algorithm to generate an alternative image. The generated alternative image will have a low degree of similarity to the original image while retaining its uniqueness.

[0623] Step 7:

[0624] The server sends the evaluation results and alternative images to the user's terminal. The terminal displays the results and the generated alternative images, and the user can select the image to use.

[0625] Step 8:

[0626] The user reviews the presented alternative images and makes a final decision on which image to use. The device can record the user's selection and send it to the server as feedback.

[0627] (Example 1)

[0628] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0629] In recent years, the risk of generated digital data infringing existing copyrights has increased. However, there is a lack of adequate means to automatically detect and avoid this at a feasible speed. This problem hinders creators from creating with peace of mind and can lead to legal issues related to copyright infringement.

[0630] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0631] In this invention, the server includes means for receiving digital data as input, means for extracting identification information, and means for searching a database and identifying corresponding digital data. This makes it possible to quickly detect the risk that the generated digital data infringes existing copyrights and to provide secure alternative digital data.

[0632] "Digital data" refers to information that is processed electronically, and includes data in various forms such as images, audio, and text.

[0633] "Identifying information" refers to a collection of characteristic data points extracted from digital data, used to identify or classify the relevant data.

[0634] A "database" refers to an organized collection of digital data, a collection of information that can be searched and updated.

[0635] A "similarity measurement" is a numerical representation of the degree of similarity between two or more digital data sets, and serves as an indicator for comparative evaluation.

[0636] A "machine learning algorithm" is a set of computational methods used by computers to automatically learn patterns and perform predictions and classifications.

[0637] This invention provides a system that receives digital data as input, extracts identification information, searches a database, and identifies corresponding digital data. The hardware used includes a high-performance server for data processing and a terminal for user data input. The software employs image processing algorithms and machine learning algorithms. Specifically, convolutional neural networks (CNNs) and deep learning models are operated on the server, contributing to the extraction of identification information from digital data.

[0638] The server automatically analyzes the input digital data and performs a database search based on the identification information. The database contains a vast amount of data collected from around the world, and similar digital data is identified from within it. This process is used to identify similar images, audio, and text, making it possible to quickly assess copyright risks.

[0639] As a concrete example, consider a scenario where a user generates a new digital logo using their own device and then checks whether that logo infringes on existing copyrights. In this case, the server analyzes the logo's identification information and searches its database. If a similar existing logo is found, the server can use a generation AI model to generate an alternative logo to mitigate the risk and provide it to the user. This allows users to confidently engage in new creative projects.

[0640] An example of a prompt message is, "Check if this image infringes copyright and generate a new alternative image if necessary." Through this prompt, users can quickly verify the safety and legality of the generated digital data.

[0641] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0642] Step 1:

[0643] The user's terminal inputs the generated digital data (e.g., images or logos) into the system. The input data is then sent from the user's terminal to the server. At this stage, the digital data is passed to the server in its original format.

[0644] Step 2:

[0645] The server analyzes the received digital data and extracts identification information. During this process, the server uses image processing algorithms such as convolutional neural networks (CNNs) to perform data calculations that quantify the features of the image. The extracted identification information represents characteristics such as color, shape, and pattern within the data.

[0646] Step 3:

[0647] The server searches the database based on the extracted identification information. In this process, the server uses a similarity calculation algorithm to identify similar digital data within the database. The database being searched contains a vast amount of copyrighted image data.

[0648] Step 4:

[0649] The server analyzes the search results and assesses copyright risk based on similarity scores. Here, similarity scoring is performed, and if a certain threshold is exceeded, it is determined to be high risk. Based on these results, a risk assessment is made.

[0650] Step 5:

[0651] If a high copyright risk is determined, the server uses a generative AI model to generate alternative digital data. In the generation process, the machine learning model generates new data with lower similarity, referencing the identification information of the input data. The output is new alternative digital data.

[0652] Step 6:

[0653] The generated alternative digital data is output from the server to the user's terminal. The terminal displays the received alternative data on the screen or in a designated location and notifies the user. This allows the user to use the alternative data with confidence.

[0654] (Application Example 1)

[0655] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0656] In advertising visual content, it is essential to proactively prevent copyright infringement risks and select images that can be used safely. In particular, the unintentional use of content similar to existing images can lead to legal problems. Furthermore, even in the process of creating new content using generation AI, it is necessary to provide users with a sense of security regarding copyright.

[0657] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0658] In this invention, the server includes means for selecting an alternative image suitable for the intended use when the image is an advertising medium, means for searching an image database using the above-mentioned characteristic information to identify similar images, and means for generating an alternative image based on the above-mentioned evaluation. This makes it possible to select images that are suitable for advertising while reducing the risk of copyright infringement.

[0659] "Means of receiving images as input" refers to a function that acquires image data provided by the user and incorporates it into the system.

[0660] "Means for extracting feature information" refers to a function that quantifies unique visual attributes from an input image and prepares that data as basic information for analysis.

[0661] "A means of searching an image database and identifying similar images" refers to a function that searches within an existing image database based on extracted feature information and identifies images with high similarity.

[0662] A "means for assessing copyright risk" is a function that determines legal risks and potential infringement related to copyright based on identified similar images.

[0663] "Methods for generating alternative images" refers to a function that uses a generation AI model to create new images with low similarity that avoid the risk of copyright infringement.

[0664] "Means of providing alternative images to users" refers to a function that sends the generated alternative images to the user's device, enabling them to view and use them.

[0665] "Means of selecting alternative images suitable for their intended use in the case of advertising media" refers to a function that selects and provides images that are particularly suitable for advertising purposes from among the alternative images.

[0666] This invention is a system for reducing the risk of copyright infringement in visual content for advertising and providing safe images. The system consists of a server located in the cloud and a user's terminal such as a smartphone.

[0667] Users use their smartphones to select images to be used in advertisements and upload them to the system. At this stage, the images are sent to the server via the device's interface. The hardware used here consists of the user's smartphone and a cloud computing platform acting as the server.

[0668] The server extracts feature information from the received image. This extraction is performed using a machine learning algorithm, which generates data points that numerically represent the image. The server then searches an image database to identify similar images.

[0669] Next, the server assesses copyright risk based on similar images. This assessment includes calculating a similarity score with existing similar images. Based on this information, it determines whether there is a risk of copyright infringement.

[0670] If a copyright risk is deemed high, the server uses a generation AI model to generate an alternative image. This alternative image must be suitable for use in advertising media, and the server selects images with advertising objectives in mind.

[0671] Finally, the server sends the generated replacement image to the user's device. The user can then review the image and use it for advertising. This allows the user to safely use advertising images while avoiding copyright issues.

[0672] As a concrete example, suppose a user wants to create a banner for a new product campaign. In this situation, the user asks the system to check the image and evaluate whether there are any similar images. The server then provides the user with a uniquely designed alternative banner that can be used safely. This allows the user to use the image with confidence.

[0673] An example of a prompt to be input to the generation AI model would be: "Create a new illustration for a commercial poster. Since it may have a high degree of similarity to existing images in the database, please generate a unique design in a new style."

[0674] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0675] Step 1:

[0676] The user selects an image for advertising on their device and uploads it to the system. The input is image data stored on the user's device. The device sends the data to the server through an interface. This transmission prepares the image for processing on the server.

[0677] Step 2:

[0678] The server extracts feature information from the received image. The input is image data sent to the server. The server uses machine learning algorithms to convert the image into numerical information, obtaining a set of unique data points as output. This allows the image's structure and color features to be quantified and represented.

[0679] Step 3:

[0680] The server searches an image database based on feature information and identifies similar images. The input is quantified feature information. The server calculates the similarity to each image in the database and outputs a similarity score. The output is a list of similar images and their similarity scores.

[0681] Step 4:

[0682] The server assesses copyright risk based on identified similar images. The input consists of a list of similar images and their similarity scores. The server numerically evaluates the likelihood of copyright infringement based on these scores and outputs the risk level. This evaluation allows for the determination of high or low risk.

[0683] Step 5:

[0684] If a high copyright risk is determined, the server generates an alternative image using a generative AI model. The input is the result of the copyright risk assessment. The server uses a prompt to activate the generative AI model and outputs a new alternative image. The output is an alternative image that avoids the copyright risk associated with the original image.

[0685] Step 6:

[0686] The server sends the generated alternative image to the user's device. The input is the generated alternative image. The server transfers the alternative image to the user's device, and the user can receive a new, unique image as output. This allows the user to confidently use the image for advertising.

[0687] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0688] This invention combines emotion recognition with a system that automatically determines the risk of copyright infringement by comparing user-generated images with similar images and providing alternative images as needed. This system is cloud-based and easily accessible via the user's device. The user interface is designed for intuitive operation, allowing for quick image uploads and analysis.

[0689] First, the system begins processing when the user uploads the image they have generated to the server. After receiving the image, the server extracts its feature information and performs a comparative search using a similar image database. This process verifies whether the user's image is similar to an existing copyrighted image.

[0690] Once the copyright risk assessment is complete, the system then uses an emotion engine to recognize the user's emotional state. The device is equipped with a camera or other input device that can analyze emotions from the user's facial expressions, voice, or usage patterns.

[0691] After the emotion engine recognizes the user's emotional state, the server presents alternative images appropriate to that state. For example, if the system detects that the user is feeling anxious, it will generate an alternative image with a more friendly design. Conversely, if a positive emotion is detected, it can present an image with a more creative style.

[0692] As a concrete example, consider a case where a user generates a new advertising image using AI and requests a review through the system. In this case, the server first analyzes the image and searches for similar images. Simultaneously, the emotion engine analyzes the user's emotions. If the server recognizes a risk of copyright infringement and determines that the user is feeling uneasy, the system provides a reassuring alternative image to help the user make a comfortable final decision.

[0693] This system combines copyright risk management with emotion recognition features to enhance the user experience, providing flexible and comprehensive support for users to use images with confidence.

[0694] The following describes the processing flow.

[0695] Step 1:

[0696] The user generates a new image using an AI image generation tool and uploads that image to the system via their device. The device then sends the image data to the server.

[0697] Step 2:

[0698] The server analyzes the received image and extracts its feature information. This feature information represents the visual features as numerical data.

[0699] Step 3:

[0700] The server searches a database of similar images based on the feature information. It uses an algorithm to calculate similarity and determine how similar the image is to existing images.

[0701] Step 4:

[0702] The server assesses the risk of copyright infringement based on the results of identifying similar images. If a copyright risk is identified, it makes a determination to that effect.

[0703] Step 5:

[0704] The emotion engine operates through an input device connected to the terminal, detecting the user's emotional state. This is analyzed from the user's facial expressions, voice, and interaction style.

[0705] Step 6:

[0706] Based on the results analyzed by the emotion engine, the server adjusts the generation and presentation methods of alternative images according to the user's emotions.

[0707] Step 7:

[0708] The user reviews the risk assessment results. If the risk is high, the server displays alternative images on the user's device, and the user can select an image from the presented options.

[0709] Step 8:

[0710] The device sends this information to the server, taking into account the user's choices and emotional feedback. This data is used to improve the system and for future processing.

[0711] (Example 2)

[0712] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0713] The use of digital images carries the risk of copyright infringement, so users need ways to properly assess this risk and use images with peace of mind. Furthermore, there is a need to improve the user experience by providing images that are optimal according to the user's emotional state.

[0714] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0715] In this invention, the server includes means for receiving an image as input, means for extracting feature information from the image, means for identifying similar images and evaluating copyright risk, and means for recognizing the user's emotional state and generating an alternative image corresponding to that emotion. This reduces the risk of copyright infringement and provides an alternative image suitable for the user's emotional state, enabling the user to use images with peace of mind.

[0716] "Means for receiving images as input" refers to a function for importing user-generated or specified image data into a server or related system.

[0717] "Methods for extracting feature information" refer to the process of analyzing various attributes and patterns of an image to extract identifiable data.

[0718] "A means of searching an image database and identifying similar images" refers to a function that finds similar images from a large collection of images based on extracted feature information.

[0719] A "means of assessing copyright risk" is a method of calculating the likelihood that a subject image infringes on existing copyrights by comparing it with similar images.

[0720] "Means for recognizing a user's emotional state" refers to technologies that analyze a user's facial expressions, behavior, voice data, etc., to understand their current emotions.

[0721] "Means for generating alternative images according to emotional state" refers to the process of creating new images with designs and styles that best suit the user's emotions.

[0722] "Means of providing alternative images" refers to a mechanism that presents generated alternative images to the user, allowing them to select and use them.

[0723] This invention provides a system that evaluates the copyright risk of user-generated images and, taking into account the user's emotional state, offers the most suitable alternative image. This system is cloud-based and accessible from the user's own device. Specifically, the process begins when the user uploads the generated image to a server in the cloud.

[0724] When the server receives an image, it first uses an image analysis tool to extract feature information. Specifically, it uses image processing libraries such as TensorFlow and OpenCV to analyze the image's patterns, color tones, and shapes. After that, it searches a similar image database using the Google Cloud Vision API. This allows it to check how similar the image is to existing copyrighted images.

[0725] Next, the system uses the camera and microphone on the user's device to recognize the user's emotional state. The device sends the collected data to a server, which uses Microsoft Azure's Emotion API to analyze the user's emotions. This allows the system to determine whether the user is feeling anxious or happy.

[0726] Based on this information, the server generates alternative images using a generative AI model (e.g., DALL-E). An example of a prompt might be, "Generate a relaxing ocean view." Based on this prompt, the system generates an image best suited to the user's emotional state and provides it to the user.

[0727] As a concrete example, consider a user who wants to create an advertising image for promotional purposes. The user uploads an image generated using AI to the system, and the server analyzes the image and searches for similar images. At the same time, the user's emotional state is analyzed, and if, for example, anxiety is detected, an alternative image that calms the user is generated and provided. In this way, the user can obtain an image that they can use with peace of mind.

[0728] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0729] Step 1:

[0730] The user uploads images generated using their device to the cloud system. The device sends and receives the image data from the server. The input is the image generated by the user, and the output is the image data stored on the server.

[0731] Step 2:

[0732] The server extracts feature information from the received image data. Specifically, it uses image analysis tools such as TensorFlow and OpenCV to analyze the patterns, shapes, and color tones of the images. In this step, the input is the image data stored on the server, and the output is the extracted feature information.

[0733] Step 3:

[0734] The server uses the extracted feature information to search an image database and identify similar images. It utilizes the Google Cloud Vision API to identify highly similar images. The input is feature information, and the output is a list of similar images and a similarity score for each image.

[0735] Step 4:

[0736] The server assesses copyright infringement risk based on similarity scores. Here, a high risk is determined if the similarity score exceeds a specified threshold. The input is a list of similar images and their similarity scores, and the output is the copyright risk assessment result.

[0737] Step 5:

[0738] The device uses its camera and microphone to collect the user's facial expressions and voice, and obtains data to identify their emotions. This data is then sent to a server. The input is the user's facial expressions and voice data, and the output is the unanalyzed emotion data transferred to the server.

[0739] Step 6:

[0740] The server uses the received emotion data to recognize the user's emotional state. It uses the Microsoft Azure Emotion API to analyze whether the user is feeling anxious or happy. The input is unanalyzed emotion data, and the output is the user's emotional state.

[0741] Step 7:

[0742] The server uses a generative AI model to generate alternative images that correspond to the user's emotional state. Prompts such as "Generate a relaxing ocean view" are used. The input is the user's emotional state, and the output is the generated alternative image.

[0743] Step 8:

[0744] The server provides the user with generated alternative images and prompts them to make a final selection. These are displayed on the terminal, allowing the user to review and use the suggested alternative images. The input is the generated alternative image, and the output is the alternative image reviewed by the user.

[0745] (Application Example 2)

[0746] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0747] Image generation requires the ability to quickly and effectively assess the risk of copyright infringement and provide feedback tailored to the image creator's emotional state. Conventional systems often fail to consider the user's emotional state, resulting in alternative solutions that don't align with the user's psychological condition. This leads to a lack of support for users in making optimal decisions.

[0748] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0749] In this invention, the server includes means for receiving an image as input, means for extracting feature information, and means for recognizing the emotional state of the image creator through an emotion analysis function. This makes it possible to combine emotion recognition with copyright risk assessment and present appropriate alternative images according to the user's psychological state.

[0750] "Means for receiving images as input" refers to a configuration that has the function of transferring user-generated image data to a server and inputting it for processing.

[0751] "Means for extracting feature information" refers to a function that analyzes the features of an image from received image data and obtains the information necessary for identification.

[0752] "A means of searching an image database and identifying similar images" refers to a function that uses extracted feature information to refer to an existing database and executes a process to identify similar images.

[0753] A "means for assessing copyright risk" is a function that determines the risk of whether an image is protected by copyright based on identified similar images.

[0754] "Means of recognizing the emotional state of the image creator through emotion analysis" refers to a function that uses the user's camera, microphone, or other devices to analyze the user's emotional state from their facial expressions and voice.

[0755] "Means for generating alternative images" refers to a function that creates appropriate alternative image suggestions for the user based on the results of copyright risk assessment and sentiment analysis.

[0756] "Means of providing the above alternative images to the user" refers to a function that presents the generated alternative images to the user in an easy-to-view manner and makes them available for use.

[0757] The system realized by this invention operates on a cloud-based system and consists of a program for receiving and processing images generated by image creators as input. Broadly speaking, this system operates based on the following main steps.

[0758] First, the image generator uploads the generated image to the cloud server via their device. This image is crucial as a starting point for processing on the server. The server analyzes the received image and extracts feature information. To do this, it uses image processing libraries such as Python and OpenCV to quickly obtain the necessary data from the image.

[0759] Next, the server uses the extracted feature information to search a pre-built database of similar images. This process uses a similarity algorithm to identify the similarity between the generated image and existing images. The Django framework is used for this data processing and computation, enabling efficient data management and backend operation.

[0760] Next, the server assesses the risk of copyright infringement based on similar images. In this process, a machine learning model is implemented using TensorFlow to perform automated decisions for risk assessment.

[0761] Furthermore, the system uses emotion analysis capabilities to understand the emotional state of the image creator. In this step, data is acquired from the camera and microphone on the user's device, and emotions are analyzed using TensorFlow and PyTorch.

[0762] Finally, based on the copyright risk assessment and emotional state analysis, alternative images are generated. The software used here combines Flask and a GAN model to assist in image generation using a generative AI model. These generated alternative images are provided to the user, offering a variety of choices.

[0763] For example, when an advertising creator generates a new image for an advertisement, this system checks the copyright risk of the image and simultaneously generates the most suitable alternative image based on the creator's emotional state. An example of a prompt message would be, "Please check the generated advertising image for copyright infringement of similar images and suggest an alternative image based on my emotional state."

[0764] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0765] Step 1:

[0766] The user uploads images generated using their device to a cloud server. The image data received as input is important for starting processing on the server. The output at this stage is the image data stored on the server.

[0767] Step 2:

[0768] The server extracts feature information from the input image. Using Python and image processing libraries such as OpenCV, it analyzes the main features of the image and quickly obtains the necessary data. This data processing yields the image feature information as output.

[0769] Step 3:

[0770] The server searches a similar image database using the extracted feature information. This process uses the Django framework to calculate the similarity between images and identify similar images from existing image data. The input is feature information, and the output is a list of identified similar images.

[0771] Step 4:

[0772] The server assesses the risk of copyright infringement based on identified similar images. A machine learning model using TensorFlow automatically determines the risk. The output of this process is the risk assessment result.

[0773] Step 5:

[0774] The server acquires facial expressions and voice data from the user to be analyzed for emotion from the terminal and analyzes their emotional state. The acquired data is analyzed using TensorFlow and PyTorch to identify the user's emotions. The output is the analyzed emotional state.

[0775] Step 6:

[0776] The server generates alternative images based on the results of risk assessment and sentiment analysis. Using Flask and a generative AI model (GAN model), it generates alternative images appropriate to the user's emotional state. The output is the generated alternative image.

[0777] Step 7:

[0778] The server provides the generated alternative image to the user's terminal. This final step allows the user to consider various options. The output at this stage is the alternative image presented to the user.

[0779] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0780] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0781] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0782] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0783] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0784] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0785] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0786] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0787] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0788] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0789] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0790] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0791] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0792] 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.

[0793] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0794] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0795] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0796] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0797] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0798] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0799] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0800] The following is further disclosed regarding the embodiments described above.

[0801] (Claim 1)

[0802] A means of receiving an image as input,

[0803] A method for extracting feature information from the above image,

[0804] A means of searching an image database using the above characteristic information and identifying similar images,

[0805] A means of evaluating copyright risk based on the above similar images,

[0806] Based on the above evaluation, means for generating an alternative image,

[0807] A means of providing the above alternative image to the user,

[0808] A system that includes this.

[0809] (Claim 2)

[0810] The system according to claim 1, characterized in that the evaluation means calculates a similarity score and evaluates risk based on the score.

[0811] (Claim 3)

[0812] The system according to claim 1, characterized in that the above-mentioned alternative image generation means generates images with low similarity using a machine learning model.

[0813] "Example 1"

[0814] (Claim 1)

[0815] A means of receiving digital data as input,

[0816] A means for extracting identification information from the above digital data,

[0817] A means of searching a database using the above identification information and identifying the corresponding digital data,

[0818] A means of evaluating rights risk based on the corresponding digital data described above,

[0819] Based on the above evaluation, a means for generating alternative digital data,

[0820] Means for providing the above alternative digital data to users,

[0821] A system that includes this.

[0822] (Claim 2)

[0823] The system according to claim 1, characterized in that the evaluation means calculates a similarity measurement and evaluates the risk based on the measurement.

[0824] (Claim 3)

[0825] The system according to claim 1, characterized in that the above-mentioned alternative digital data generation means generates digital data with low similarity using a machine learning algorithm.

[0826] "Application Example 1"

[0827] (Claim 1)

[0828] A means of receiving an image as input,

[0829] A method for extracting feature information from the above image,

[0830] A means of searching an image database using the above characteristic information and identifying similar images,

[0831] A means of evaluating copyright risk based on the above similar images,

[0832] Based on the above evaluation, means for generating an alternative image,

[0833] A means of providing the above alternative image to the user,

[0834] When an image is used as an advertising medium, a means of selecting an alternative image suitable for its intended use,

[0835] A system that includes this.

[0836] (Claim 2)

[0837] The system according to claim 1, characterized in that the evaluation means calculates a similarity score and evaluates risk based on the score.

[0838] (Claim 3)

[0839] The system according to claim 1, characterized in that the above-mentioned alternative image generation means generates images with low similarity using a machine learning model and makes those images suitable for use in advertising.

[0840] "Example 2 of combining an emotion engine"

[0841] (Claim 1)

[0842] A means of receiving an image as input,

[0843] A method for extracting feature information from the above image,

[0844] A means of searching an image database using the above characteristic information and identifying similar images,

[0845] A means of evaluating copyright risk based on the above similar images,

[0846] Based on the above evaluation, a means of recognizing the user's emotional state,

[0847] A means for generating alternative images corresponding to the above emotional state,

[0848] A means of providing the above alternative image to the user,

[0849] A system that includes this.

[0850] (Claim 2)

[0851] The system according to claim 1, characterized in that the evaluation means calculates a similarity score and evaluates risk and sentiment based on the score.

[0852] (Claim 3)

[0853] The system according to claim 1, characterized in that the above-mentioned alternative image generation means generates low-similarity images in a style that matches the emotional state using a machine learning model.

[0854] "Application example 2 when combining with an emotional engine"

[0855] (Claim 1)

[0856] A means of receiving an image as input,

[0857] A method for extracting feature information from the above image,

[0858] A means of searching an image database using the above characteristic information and identifying similar images,

[0859] A means of evaluating copyright risk based on the above similar images,

[0860] A means of recognizing the emotional state of the image creator through emotion analysis,

[0861] A means for generating an alternative image based on the above evaluation and emotion recognition,

[0862] A means of providing the above alternative image to the user,

[0863] A system that includes this.

[0864] (Claim 2)

[0865] The system according to claim 1, characterized in that the above-mentioned evaluation means and emotion recognition means adjust the similarity score according to the user's emotional state and evaluate the risk based on the score.

[0866] (Claim 3)

[0867] The system according to claim 1, characterized in that the above-mentioned alternative image generation means generates an image that reflects the user's emotional state using a machine learning model. [Explanation of Symbols]

[0868] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of receiving an image as input, A method for extracting feature information from the above image, A means of searching an image database using the above characteristic information and identifying similar images, A means of evaluating copyright risk based on the above similar images, Based on the above evaluation, means for generating an alternative image, A means of providing the above alternative image to the user, When an image is used as an advertising medium, a means of selecting an alternative image suitable for its intended use, A system that includes this.

2. The system according to claim 1, characterized in that the evaluation means calculates a similarity score and evaluates the risk based on the score.

3. The system according to claim 1, characterized in that the above-mentioned alternative image generation means generates images with low similarity using a machine learning model and makes those images suitable for use in advertising.

Images