system

Abstract

Provide a system. 【Solution means】 Means for a user to input an image, Means for extracting features from the image, Means for selecting an optimal style by comparing with a past database based on the features, Means for synthesizing the selected style into the user's image using a generation engine to generate a visual proposal, Means for providing the visual proposal to the user, Means for presenting advice to the user by voice or display, Means for assisting the user's selection based on the proposed style, A system including the above.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern times, many individuals have difficulty finding the ideal style that best suits their face and body shape. This problem is due to the difficulty for users to judge the optimal choice for themselves from a vast number of options. Trial and error in style selection wastes time and costs and is a factor leading to a decrease in satisfaction. Therefore, there is a need to reduce the time and effort of users and support more appropriate choices by automatically proposing styles based on individual characteristics.

Means for Solving the Problems

[0005] This invention provides a system that takes an image as input by the user and extracts features from that image. The extracted features are compared with a past database to select the most suitable style for the user. Furthermore, by using a generation engine, the selected style can be combined with the user's image to generate concrete visual suggestions. This system allows the user to select the optimal style while visually confirming it, thereby improving the efficiency of style selection and increasing user satisfaction.

[0006] A "user" refers to an individual who uses this system to upload their own images and receive style suggestions.

[0007] "Image" refers to a photograph or digital image that includes the user's face and body shape.

[0008] "Features" refer to individual attributes such as facial shape and body shape that are extracted from an image.

[0009] A "database" refers to a collection of information that stores past style data and is used to match it with features.

[0010] "Style" refers to hairstyles and fashion designs selected based on facial features and body shape.

[0011] A "generative engine" refers to an algorithm or software that synthesizes selected styles onto a user's image to generate visual suggestions.

[0012] "Visual suggestions" refer to images created by a generation engine that reflect the selected style. [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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described according to the accompanying drawings.

[0015] First, the language 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, and the like.

[0019] In the following embodiments, the labeled communication I / F (Interface) is an interface that includes 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), and the like.

[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 in which a user uploads an image, and AI technology is used to suggest the most suitable style for that user. This system is realized by the user uploading an image on their device, and the server processing that image.

[0035] Specifically, users use their devices to take or select images of their face and body shape and upload them. The device first checks the image format and sends it to the server. The server uses an AI agent to extract facial and body shape features from the received images. This reveals the user's individual attributes.

[0036] The server compares the extracted features with a previously stored style database. This comparison selects the style best suited to the user's face and body shape. The selected style information is then passed to the generation engine, which performs style synthesis on the user's facial photograph.

[0037] The generation engine produces visual suggestions as concrete style images. The server sends these generated images back to the terminal along with the reasons for the suggestions and advice, allowing the user to view multiple styles on the screen. Based on the presented visual suggestions, the user can choose their preferred style.

[0038] This allows users to visually confirm and select the style that best suits them, significantly streamlining the traditional trial-and-error process of choosing a style. This invention is also applicable to other AI technologies and database systems, offering further expandability.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] The user uses their device to take or select images of their face and body shape. They then place these image files into the upload interface.

[0042] Step 2:

[0043] The device checks the format of the uploaded image, and if necessary, converts it to a standard format before sending the image to the server.

[0044] Step 3:

[0045] The server passes the image received from the terminal to the AI ​​agent and begins processing. The AI ​​agent recognizes facial landmarks from the image and extracts features such as facial shape and bone structure.

[0046] Step 4:

[0047] The server uses the extracted feature information to access a style database. Here, it searches for and matches the most suitable style based on the user's characteristics.

[0048] Step 5:

[0049] The server selects the style it deems most suitable for the user based on the matching results. It then passes the selected style information to the generation engine.

[0050] Step 6:

[0051] The generation engine synthesizes styles onto the user's facial image based on style information received from the server. This generates visual style suggestions.

[0052] Step 7:

[0053] The server sends the generated visual suggestions to the user's device, along with advice on the reasoning behind the suggestions and styling.

[0054] Step 8:

[0055] Users can view style images displayed on their device and choose their preferred style. The user's selection is then saved or sent for use in the next action.

[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] A problem exists in that users often need a lot of time and trial and error to find the style that best suits them. Furthermore, conventional technologies have limited means of automatically suggesting appropriate styles based on individual user attributes. This hinders improvements in the user experience.

[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 a device for the user to input image information, a device for extracting feature information from the image information, a device for making the optimal selection by comparing the feature information with a past information set, a device for synthesizing the selected style with the user's image information using a generation device to generate a visual suggestion, a device for providing the visual suggestion to the user, a device for checking the format of the image information and transmitting it securely using a communication procedure, and a device for ensuring security using data encryption technology. This makes it possible to quickly suggest styles tailored to the individual characteristics of each user and efficiently support the user's style selection.

[0061] A "user" refers to an individual who uses the system, inputs their own image information, and receives style suggestions.

[0062] "Image information" refers to digital data, including the user's face and body shape, which is what the system processes.

[0063] "Feature information" refers to unique information extracted from image data, such as the shape of a user's face and body shape.

[0064] An "information set" is a database accumulated over time, a collection of various styles and related information.

[0065] "Selection" refers to a judgment regarding the optimal style identified by matching feature information with a set of information.

[0066] A "generation device" refers to a device that generates visual suggestions by combining a selected style with the user's image information.

[0067] "Visual proposals" refer to specific style images created by a generation device and provided to the user.

[0068] "Communication protocol" refers to a protocol used to securely send and receive data between a terminal and a server.

[0069] "Encryption technology" is a technology used to ensure data security, and it plays a role in encrypting data and preventing unauthorized access.

[0070] This invention is a system that uses AI technology to suggest the optimal style based on the user's image information. First, the user takes or selects images of their face and body shape using their device and uploads them to the system. The device verifies that the image information format is appropriate and securely transmits it to the server via the HTTPS protocol. SSL / TLS encryption technology is used during communication to ensure security.

[0071] The server passes the received image information to an AI agent, which uses a deep learning framework (e.g., TENSORFLOW®) to extract feature information such as facial shape and body shape. This feature information is compared with a past data set (database) to select the optimal style. The data set contains data on various styles, and the attributes of each style are recorded.

[0072] The selected style is passed to a generation device, which uses an image processing library (e.g., OpenCV) to synthesize the style with the user's image information. The generated visual suggestions are sent back to the user's terminal, allowing them to visually check multiple styles on the screen. Specifically, several options are suggested, such as "casual short hairstyle" or "formal business style."

[0073] Based on these visual suggestions, users can select a style that suits their preferences. For example, by entering a prompt such as, "Please suggest a suitable casual style based on a photo of a woman in her 20s. Please suggest three examples of hairstyles and clothing, and explain the reasons for their selection," users can receive intuitive and efficient personalized style suggestions.

[0074] In this way, this system allows users to quickly find the style that best suits them, significantly streamlining the traditional trial-and-error process of choosing a style.

[0075] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0076] Step 1:

[0077] The user uses their device to capture or select image information of their face and body shape. The input here is image data containing the user's face and body shape. The device checks the format of this image data (JPEG or PNG). Once the correct format is confirmed, the image is sent to the server via the HTTPS protocol. As output, the confirmed image data is sent to the server.

[0078] Step 2:

[0079] The server passes the received image information to the AI ​​agent. The input for this is the user's image data. The AI ​​agent uses a deep learning framework such as TensorFlow to extract facial and body shape features from the image data. The output of this process is feature information, which includes identification information for facial and body shape.

[0080] Step 3:

[0081] The server uses the extracted feature information to match the features with those in the database. The input here is the feature information. The database contains information on various styles. The server searches the database based on the feature information and selects the optimal style. The output is the selected style information.

[0082] Step 4:

[0083] The server uses a generation device based on the selected style information to synthesize the style onto the user's image information. The input for this process is the selected style information and the original image data. An image processing library (e.g., OpenCV) is used to synthesize the selected style onto the user's image. The output is the generated visual suggestion.

[0084] Step 5:

[0085] The server sends the generated visual suggestions back to the user's terminal. The input here is the generated visual suggestions. The terminal receives this data and displays the visual suggestions on the user interface. This output allows the user to visually confirm each suggested style on the screen.

[0086] Step 6:

[0087] The user selects their preferred style based on visual suggestions displayed on the device. The input is the visual suggestions. The user intuitively compares and selects each style. As output, the user confirms their selected style and can receive additional feedback as needed.

[0088] (Application Example 1)

[0089] 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."

[0090] There is a need to provide users with an efficient way to select the style that best suits them without trial and error. Furthermore, there is a desire for a system that allows users to easily receive fashion advice at home and support them in making style choices in their daily lives.

[0091] 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.

[0092] In this invention, the server includes means for the user to input an image, means for extracting features from the image, means for selecting the optimal style by comparing it with a past database based on the features, means for synthesizing the selected style onto the user's image using a generation engine to generate a visual suggestion, means for providing the visual suggestion to the user, means for presenting advice to the user by voice or display, and means for supporting the user's selection based on the suggested style. This makes it possible for the user to efficiently select the optimal style at home and effectively support style selection in daily life.

[0093] A "user" is an individual or group that utilizes the system, inputting images and receiving style suggestions.

[0094] "Means of inputting images" refers to the devices and methods used by users to import their own photos and videos into the system.

[0095] "Methods for extracting features" refer to technical processes that analyze and extract important attributes such as facial shape and body shape from input images.

[0096] The "past database" is a collection of information about styles and fashion that has been gathered to date, and it serves as a source of information used to make suggestions to users.

[0097] "Means for selecting the optimal style" refers to an algorithm or process for finding the style that best suits the extracted characteristics by comparing them with the characteristics.

[0098] A "generative engine" is a software or hardware system for generating visual proposals based on a selected style.

[0099] "Means for generating visual suggestions" refers to a process or system for compositing styles onto a user's image and presenting them to the user in a visual form.

[0100] "Means of providing advice by voice or display" refers to technologies that convey style suggestions and opinions to users through voice or display.

[0101] "Means of supporting choice" refers to functions or interfaces that assist users in making judgments or taking actions regarding proposed styles.

[0102] In a system that implements an application example of this invention, a consumer robot and a server are combined and operated. When a user requests style suggestions from the robot, the robot takes an image of the user using its built-in camera. The image is converted to an appropriate format on the local terminal and sent to the server via the internet. On the server, an image processing library (e.g., OpenCV) is first used to extract features such as facial shape and body shape from the image.

[0103] Next, this feature information is compared with a previously accumulated style database. The server uses a machine learning model (e.g., a generative AI model using TensorFlow or PyTorch) to select the optimal style, and the generative engine synthesizes the style onto the user's image. This generates a visual style suggestion, which is then sent to the user's device. On the user's device, the visual suggestion is provided to the user via voice or screen display through the robot.

[0104] For example, if a user asks a robot to "give me advice on what to wear today" while getting ready in the morning, the robot will take a picture of the user and send it, and then provide voice feedback on styles suggested by the server. Specific advice such as "A red shirt and black pants would be perfect" will be offered.

[0105] An example of a prompt message for a generative AI model might be, "Based on the user's image, please suggest the best style."

[0106] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0107] Step 1:

[0108] The user requests style suggestions from a consumer robot. The robot uses its built-in camera to capture an image of the user and inputs it into a terminal. This image is converted to an appropriate format by an image processing library and sent to a server. The input is the user's image, and the output is a formatted image.

[0109] Step 2:

[0110] The server uses the received image to extract facial and body shape features using an image processing library (e.g., OpenCV). The input is a formatted image, and the output is the extracted feature information. In this step, edge detection and pattern recognition are performed to identify the contours of the face and important points.

[0111] Step 3:

[0112] The server compares the extracted feature information with a database of past styles. It utilizes machine learning models (e.g., TensorFlow or PyTorch). The input is feature information, and the output is the optimal style. Here, a generative AI model predicts the optimal style from past data.

[0113] Step 4:

[0114] The server's generation engine synthesizes the selected style onto the user's image to generate visual suggestions. The input is the user's image and the selected style, and the output is a visual style suggestion. This operation includes techniques for style texture synthesis and color correction.

[0115] Step 5:

[0116] The server sends the generated visual style suggestions to the terminal. The terminal, through the robot, provides these suggestions to the user via voice and screen display. The input is the visual style suggestions, and the output is visual and auditory feedback to the user. The robot gives the user specific clothing advice, such as "a red shirt and black pants would be best."

[0117] 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.

[0118] This invention is a system in which a user inputs an image, and AI technology combined with an emotion engine proposes the optimal style. This system works by having the user input an image on their device, and after the server recognizes the emotion and features, it proposes an appropriate style.

[0119] First, the user uses their device to take or select images of their face and body shape and uploads them to the system. The device collects the image data and sends it to the server. Upon receiving the images, the server activates an AI agent to analyze the user's facial features and body shape. Simultaneously, an emotion engine recognizes the user's emotional state from the images.

[0120] Characteristic and emotional information is cross-referenced with a database on the server and used in a process to select the most suitable style for the user based on past data. Style suggestions are then refined based on the emotional state, providing a style that matches the user's current emotions. For example, if the user is feeling calm, a style that conveys a gentle impression will be suggested.

[0121] The generation engine uses selected style data to synthesize styles onto the user's face. The generated visual suggestions provide the user with a concrete image of the style, along with emotion-based advice.

[0122] The styles provided by this system address both the user's characteristics and emotions, thereby improving user satisfaction. Furthermore, by capturing emotional changes in real time, flexible suggestions tailored to different situations become possible. Thus, this invention dramatically improves the efficiency and accuracy of style selection.

[0123] The following describes the processing flow.

[0124] Step 1:

[0125] The user uses their device to take or select images of their face and body shape. They then place the selected images into the upload interface.

[0126] Step 2:

[0127] The terminal uses format verification software to convert the image data to a standard format and prepares it for transmission to the server.

[0128] Step 3:

[0129] The server receives image data from the terminal. The received images are processed by an AI agent, which analyzes facial features and skeletal information.

[0130] Step 4:

[0131] The server also passes the image data to the emotion engine, which determines the user's emotional state based on their facial expressions and the degree of tension on their face, and generates emotion data.

[0132] Step 5:

[0133] The server compares the extracted feature data and sentiment data with the database and uses this as foundational information to select the optimal style.

[0134] Step 6:

[0135] The server selects a style that matches the user's current psychological state based on emotional data and sends the style information to the generation engine.

[0136] Step 7:

[0137] The generation engine uses the received style information to synthesize the style onto the user's face image. It then generates an image of the synthesized visual suggestion.

[0138] Step 8:

[0139] The server sends the terminal advice based on sentiment data, along with the generated visual style suggestions.

[0140] Step 9:

[0141] Users can view suggested images on their device and select their preferred style while referring to comments and advice regarding the visual suggestions.

[0142] (Example 2)

[0143] 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".

[0144] Conventional style suggestion systems often struggled to provide suggestions that adequately considered individual user characteristics and emotions, resulting in generic suggestions. Furthermore, they lacked the flexibility to adapt to changes in emotions, making it difficult to improve user satisfaction. In addition, the incomplete use of past data for effective style selection prevented them from providing personalized suggestions suitable for each user.

[0145] 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.

[0146] In this invention, the server includes means for analyzing facial features and emotional states from the image, means for comparing the analyzed features and emotional states with a database to select the optimal style, and means for synthesizing the selected style onto the user image using a generation algorithm to generate visual suggestions. This enables highly personalized style suggestions based on the user's features and emotions.

[0147] A "user" is an individual who uses the system to input their own image and receive style suggestions.

[0148] A "terminal" is an electronic device used by a user to take or select images, and a device used to transmit information to a server.

[0149] A "server" is a computer system that receives image data sent by users, analyzes it, and provides style suggestions.

[0150] "Image" refers to visual data that a user captures or selects using their device and inputs into the system.

[0151] "Data conversion" is the process of converting images provided by a user into an appropriate format, and is a procedure that enables transmission and processing.

[0152] "Facial features" refer to the specific physical characteristics of the user's face, including information about its shape and structure.

[0153] "Emotional state" refers to information that indicates the user's psychological or emotional state, and is inferred from facial features, etc.

[0154] A "database" is a record system that stores past user data and style information, and is used in the analysis process.

[0155] "Optimal style" refers to the most appropriate fashion and visual expression, selected based on the user's characteristics and emotional state.

[0156] A "generative algorithm" is a computational method used to perform visual synthesis on a user's image based on a selected style.

[0157] A "visual suggestion" is an image of a style proposed to the user, created by a generative algorithm.

[0158] This system allows users to input images of their face and body shape using a terminal, and the server then provides personalized style suggestions based on that input. The following describes a specific embodiment of this invention.

[0159] First, the user takes or selects an image using their device. The device is a smart device with a camera function, and this image is converted to JPEG or PNG format and sent to the server via the internet.

[0160] The server utilizes AI technology to analyze the received images. Specifically, it uses image processing libraries such as OpenCV to extract facial features and then uses emotion recognition software like EmotionAPI to identify emotional states. This information is then compared against a database on the server to select the optimal style.

[0161] The generated style suggestions utilize a learning model. By leveraging the generative AI model, styles based on user characteristics are synthesized onto user images, generating visual suggestions. Style transfer techniques, such as DeepArt, may be applied in this process.

[0162] Finally, visual suggestions and sentiment-based advice generated by the server are sent to the user's device. The user reviews these and decides whether the suggested style is suitable for them.

[0163] As a concrete example, suppose a user enters the prompt, "I'm attending a friend's wedding today. Please suggest an outfit that matches a festive and joyful mood." Based on this prompt, the system can recognize that the user is looking forward to a special day and suggest a style with vibrant colors and designs.

[0164] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0165] Step 1:

[0166] The user takes a picture of their face and body shape using the device's camera, or selects one from their photo library. This image is converted to JPEG or PNG format within the device and prepared for transmission to the server. The input is the image selected or taken by the user, and the output is the formatted image data sent to the server over the network.

[0167] Step 2:

[0168] The server receives image data sent from the user. The server uses an image processing library (e.g., OpenCV) to analyze this image and extract the user's facial features. Furthermore, it uses software such as EmotionAPI to identify the user's emotional state. In this step, the input is the user's image data, and the output is facial feature data and emotional state data.

[0169] Step 3:

[0170] The server uses the facial feature data and emotional state data obtained in the previous step to match it against its internal database. This process references historical data and trend information stored in the database to select the optimal style for the user. The input is feature data and emotional data, and the output is optimal style information.

[0171] Step 4:

[0172] The server runs a generative AI model using the selected style information. Style transfer techniques, such as DeepArt, are used in the process of compositing styles onto the user's image. The inputs here are the optimal style information and the user's image, and the output is a visually suggested image with the style composited.

[0173] Step 5:

[0174] The server sends emotion-based advice along with a generated visual suggestion image to the user's device. The user reviews the received suggestion on their device and considers whether it aligns with their preferences. The input is the suggestion image and advice, and the output is the visual confirmation and potential feedback on the user's device.

[0175] (Application Example 2)

[0176] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0177] In modern society, suggesting styles that match individual user characteristics and emotional states is essential for improving consumer satisfaction. However, many current style suggestion systems do not take into account users' real-time emotions, making it difficult to provide personalized and specific suggestions. Therefore, there is a growing demand for systems that enable dynamic and flexible style suggestions based on user characteristics and emotions.

[0178] 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.

[0179] In this invention, the server includes means for acquiring a user's image, means for analyzing features and emotions from the image, and means for selecting the optimal style by comparing the features and emotions with a past database. This makes it possible to suggest a style that corresponds to the user's current features and emotions.

[0180] "Means for acquiring user images" refers to devices or methods for collecting visual information of customers, thereby collecting data on the user's face and body shape.

[0181] "Means for analyzing characteristics and emotions" refers to technologies or functions for determining a user's physical characteristics and emotional state from collected visual information.

[0182] "A method for selecting the optimal style by comparing with past databases" refers to a process of referring to accumulated historical data to determine the style that best suits the user's characteristics and emotions.

[0183] "Means for generating visual suggestions by synthesizing the selected style onto the user's image using a generation engine" refers to a technology that visually represents the selected style by overlaying it onto the user's image, thereby providing the customer with a concrete image of the style.

[0184] "Means of providing on a display device" refers to a function that uses a screen or monitor to present images or videos in order to display the generated visual proposal.

[0185] The system for carrying out this invention provides a process for users to receive style suggestions via a display device installed in a fitting room. Its configuration and operation are described below.

[0186] When a user stands in front of a display device in a fitting room, a camera attached to the device captures the user's face and body shape. This image data is transmitted to a server via the terminal. The server uses image processing technology to analyze the user's features and emotions from the image. This analysis uses, for example, a "computer vision API" (e.g., Google® Cloud Vision) to extract facial and body shape information, and uses machine learning models to determine emotions.

[0187] The analysis results are compared with a database on the server to select the optimal style based on the user's characteristics and emotions. This selection process utilizes historical data, taking into account styles and trends the user has previously preferred.

[0188] The selected style is synthesized with the user's image by a generation engine. This generation process utilizes an artificial intelligence model (e.g., TensorFlow) that leverages machine learning. The generated visual style suggestions are displayed on a display device, allowing the user to visually confirm them.

[0189] For example, if a user expresses the sentiment of wanting to try a relaxed style before heading to work, the synthesis engine will generate a casual and calm style for the user's image. This suggestion is visually easy for the user to understand and allows for real-time suggestions that respond to their emotions.

[0190] Example prompt: "Analyze the customer image and suggest the most suitable casual style based on their current mood. Mood tag: Relaxed, Category: Work Style"

[0191] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0192] Step 1:

[0193] The terminal acquires the user's image through the display device's camera. The input in the image acquisition process is the user's visual information, and the output is digital image data of the user's face and body. The terminal then prepares to send this image data to the server.

[0194] Step 2:

[0195] The server receives image data transmitted from the terminal and uses a computer vision API to analyze the user's features and emotions. It processes the image data as input to extract the user's facial and body shape features, as well as their emotional state. The output consists of analyzed feature data and emotion data.

[0196] Step 3:

[0197] The server matches the analyzed feature and sentiment data against a database. The input includes feature and sentiment data, and the server selects the optimal style by performing a database search based on past history. The output is the data for the selected style.

[0198] Step 4:

[0199] The server uses a generation engine to synthesize selected styles onto the user's image. The input consists of the user's image data and style data, which are processed by a machine learning model to generate visually suggestible style images. The output is the image data of the synthesized style suggestions.

[0200] Step 5:

[0201] The terminal receives style suggestions synthesized from the server and displays them on the display device. The user can then review these visual style suggestions. It receives generated style image data as input and provides visual information to be displayed on the screen as output.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] [Second Embodiment]

[0206] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0207] 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.

[0208] 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).

[0209] 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.

[0210] 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.

[0211] 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).

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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".

[0218] This invention is a system in which a user uploads an image, and AI technology is used to suggest the most suitable style for that user. This system is realized by the user uploading an image on their device, and the server processing that image.

[0219] Specifically, users use their devices to take or select images of their face and body shape and upload them. The device first checks the image format and sends it to the server. The server uses an AI agent to extract facial and body shape features from the received images. This reveals the user's individual attributes.

[0220] The server compares the extracted features with a previously stored style database. This comparison selects the style best suited to the user's face and body shape. The selected style information is then passed to the generation engine, which performs style synthesis on the user's facial photograph.

[0221] The generation engine produces visual suggestions as concrete style images. The server sends these generated images back to the terminal along with the reasons for the suggestions and advice, allowing the user to view multiple styles on the screen. Based on the presented visual suggestions, the user can choose their preferred style.

[0222] This allows users to visually confirm and select the style that best suits them, significantly streamlining the traditional trial-and-error process of choosing a style. This invention is also applicable to other AI technologies and database systems, offering further expandability.

[0223] The following describes the processing flow.

[0224] Step 1:

[0225] The user uses their device to take or select images of their face and body shape. They then place these image files into the upload interface.

[0226] Step 2:

[0227] The device checks the format of the uploaded image, and if necessary, converts it to a standard format before sending the image to the server.

[0228] Step 3:

[0229] The server passes the image received from the terminal to the AI ​​agent and begins processing. The AI ​​agent recognizes facial landmarks from the image and extracts features such as facial shape and bone structure.

[0230] Step 4:

[0231] The server uses the extracted feature information to access a style database. Here, it searches for and matches the most suitable style based on the user's characteristics.

[0232] Step 5:

[0233] The server selects the style it deems most suitable for the user based on the matching results. It then passes the selected style information to the generation engine.

[0234] Step 6:

[0235] The generation engine synthesizes styles onto the user's facial image based on style information received from the server. This generates visual style suggestions.

[0236] Step 7:

[0237] The server sends the generated visual suggestions to the user's device, along with advice on the reasoning behind the suggestions and styling.

[0238] Step 8:

[0239] Users can view style images displayed on their device and choose their preferred style. The user's selection is then saved or sent for use in the next action.

[0240] (Example 1)

[0241] 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."

[0242] A problem exists in that users often need a lot of time and trial and error to find the style that best suits them. Furthermore, conventional technologies have limited means of automatically suggesting appropriate styles based on individual user attributes. This hinders improvements in the user experience.

[0243] 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.

[0244] In this invention, the server includes a device for the user to input image information, a device for extracting feature information from the image information, a device for making the optimal selection by comparing the feature information with a past information set, a device for synthesizing the selected style with the user's image information using a generation device to generate a visual suggestion, a device for providing the visual suggestion to the user, a device for checking the format of the image information and transmitting it securely using a communication procedure, and a device for ensuring security using data encryption technology. This makes it possible to quickly suggest styles tailored to the individual characteristics of each user and efficiently support the user's style selection.

[0245] A "user" refers to an individual who uses the system, inputs their own image information, and receives style suggestions.

[0246] "Image information" refers to digital data, including the user's face and body shape, which is what the system processes.

[0247] "Feature information" refers to unique information extracted from image data, such as the shape of a user's face and body shape.

[0248] An "information set" is a database accumulated over time, a collection of various styles and related information.

[0249] "Selection" refers to a judgment regarding the optimal style identified by matching feature information with a set of information.

[0250] A "generation device" refers to a device that generates visual suggestions by combining a selected style with the user's image information.

[0251] "Visual proposals" refer to specific style images created by a generation device and provided to the user.

[0252] "Communication protocol" refers to a protocol used to securely send and receive data between a terminal and a server.

[0253] "Encryption technology" is a technology used to ensure data security, and it plays a role in encrypting data and preventing unauthorized access.

[0254] This invention is a system that uses AI technology to suggest the optimal style based on the user's image information. First, the user takes or selects images of their face and body shape using their device and uploads them to the system. The device verifies that the image information format is appropriate and securely transmits it to the server via the HTTPS protocol. SSL / TLS encryption technology is used during communication to ensure security.

[0255] The server passes the received image information to an AI agent, which uses a deep learning framework (e.g., TensorFlow) to extract feature information such as facial shape and body shape. This feature information is compared with a past data set (database) to select the optimal style. The data set contains data on various styles, and the attributes of each style are recorded.

[0256] The selected style is passed to a generation device, which uses an image processing library (e.g., OpenCV) to synthesize the style with the user's image information. The generated visual suggestions are sent back to the user's terminal, allowing them to visually check multiple styles on the screen. Specifically, several options are suggested, such as "casual short hairstyle" or "formal business style."

[0257] Based on these visual suggestions, users can select a style that suits their preferences. For example, by entering a prompt such as, "Please suggest a suitable casual style based on a photo of a woman in her 20s. Please suggest three examples of hairstyles and clothing, and explain the reasons for their selection," users can receive intuitive and efficient personalized style suggestions.

[0258] In this way, this system allows users to quickly find the style that best suits them, significantly streamlining the traditional trial-and-error process of choosing a style.

[0259] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0260] Step 1:

[0261] The user uses their device to capture or select image information of their face and body shape. The input here is image data containing the user's face and body shape. The device checks the format of this image data (JPEG or PNG). Once the correct format is confirmed, the image is sent to the server via the HTTPS protocol. As output, the confirmed image data is sent to the server.

[0262] Step 2:

[0263] The server passes the received image information to the AI ​​agent. The input for this is the user's image data. The AI ​​agent uses a deep learning framework such as TensorFlow to extract facial and body shape features from the image data. The output of this process is feature information, which includes identification information for facial and body shape.

[0264] Step 3:

[0265] The server uses the extracted feature information to match the features with those in the database. The input here is the feature information. The database contains information on various styles. The server searches the database based on the feature information and selects the optimal style. The output is the selected style information.

[0266] Step 4:

[0267] The server uses a generation device based on the selected style information to synthesize the style onto the user's image information. The input for this process is the selected style information and the original image data. An image processing library (e.g., OpenCV) is used to synthesize the selected style onto the user's image. The output is the generated visual suggestion.

[0268] Step 5:

[0269] The server sends the generated visual suggestions back to the user's terminal. The input here is the generated visual suggestions. The terminal receives this data and displays the visual suggestions on the user interface. This output allows the user to visually confirm each suggested style on the screen.

[0270] Step 6:

[0271] The user selects their preferred style based on visual suggestions displayed on the device. The input is the visual suggestions. The user intuitively compares and selects each style. As output, the user confirms their selected style and can receive additional feedback as needed.

[0272] (Application Example 1)

[0273] 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."

[0274] There is a need to provide users with an efficient way to select the style that best suits them without trial and error. Furthermore, there is a desire for a system that allows users to easily receive fashion advice at home and support them in making style choices in their daily lives.

[0275] 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.

[0276] In this invention, the server includes means for the user to input an image, means for extracting features from the image, means for selecting the optimal style by comparing it with a past database based on the features, means for synthesizing the selected style onto the user's image using a generation engine to generate a visual suggestion, means for providing the visual suggestion to the user, means for presenting advice to the user by voice or display, and means for supporting the user's selection based on the suggested style. This makes it possible for the user to efficiently select the optimal style at home and effectively support style selection in daily life.

[0277] A "user" is an individual or group that utilizes the system, inputting images and receiving style suggestions.

[0278] "Means of inputting images" refers to the devices and methods used by users to import their own photos and videos into the system.

[0279] "Methods for extracting features" refer to technical processes that analyze and extract important attributes such as facial shape and body shape from input images.

[0280] The "past database" is a collection of information about styles and fashion that has been gathered to date, and it serves as a source of information used to make suggestions to users.

[0281] The "means for selecting the optimal style" is an algorithm or process for finding the style most suitable for the extracted features by matching them.

[0282] The "generation engine" is a software or hardware system for generating visual proposals based on the selected style.

[0283] The "means for generating visual proposals" is a process or system for synthesizing a style onto the user's image and presenting it to the user in a visual form.

[0284] The "means for presenting advice by voice or display" is a technology for conveying proposals and opinions regarding style to the user through voice or display.

[0285] The "means for assisting selection" is a function or interface for assisting the user's judgment and actions regarding the proposed style.

[0286] In a system that realizes an application example of this invention, a consumer robot and a server operate in combination. When the user requests a style proposal from the robot, the robot uses its built-in camera to take a picture of the user. The image is converted into an appropriate format at the local terminal and transmitted to the server via the Internet. At the server, first, features such as the shape of the face and body are extracted from the image using an image processing library (e.g., OpenCV).

[0287] Next, this feature information is compared with the style database accumulated in the past. The server uses a machine learning model (e.g., a generative AI model using TensorFlow or PyTorch) to select the optimal style and synthesizes the style onto the user's image with the generation engine. As a result, a visual style proposal is generated and transmitted to the user's terminal. At the user's terminal, the visual proposal is provided to the user through the robot by voice or on the screen.

[0288] For example, if a user asks a robot to "give me advice on what to wear today" while getting ready in the morning, the robot will take a picture of the user and send it, and then provide voice feedback on styles suggested by the server. Specific advice such as "A red shirt and black pants would be perfect" will be offered.

[0289] An example of a prompt message for a generative AI model might be, "Based on the user's image, please suggest the best style."

[0290] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0291] Step 1:

[0292] The user requests style suggestions from a consumer robot. The robot uses its built-in camera to capture an image of the user and inputs it into a terminal. This image is converted to an appropriate format by an image processing library and sent to a server. The input is the user's image, and the output is a formatted image.

[0293] Step 2:

[0294] The server uses the received image to extract facial and body shape features using an image processing library (e.g., OpenCV). The input is a formatted image, and the output is the extracted feature information. In this step, edge detection and pattern recognition are performed to identify the contours of the face and important points.

[0295] Step 3:

[0296] The server compares the extracted feature information with a database of past styles. It utilizes machine learning models (e.g., TensorFlow or PyTorch). The input is feature information, and the output is the optimal style. Here, a generative AI model predicts the optimal style from past data.

[0297] Step 4:

[0298] The server's generation engine synthesizes the selected style onto the user's image to generate visual suggestions. The input is the user's image and the selected style, and the output is a visual style suggestion. This operation includes techniques for style texture synthesis and color correction.

[0299] Step 5:

[0300] The server sends the generated visual style suggestions to the terminal. The terminal, through the robot, provides these suggestions to the user via voice and screen display. The input is the visual style suggestions, and the output is visual and auditory feedback to the user. The robot gives the user specific clothing advice, such as "a red shirt and black pants would be best."

[0301] 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.

[0302] This invention is a system in which a user inputs an image, and AI technology combined with an emotion engine proposes the optimal style. This system works by having the user input an image on their device, and after the server recognizes the emotion and features, it proposes an appropriate style.

[0303] First, the user uses their device to take or select images of their face and body shape and uploads them to the system. The device collects the image data and sends it to the server. Upon receiving the images, the server activates an AI agent to analyze the user's facial features and body shape. Simultaneously, an emotion engine recognizes the user's emotional state from the images.

[0304] The characteristics and emotional information are compared with the database in the server and used in the process of selecting the style that is optimal for the user from past data. By correcting the style proposal based on the emotional state, a style that matches the user's current emotion is provided. For example, when the user is in a calm emotion, a style that gives a gentle impression is proposed.

[0305] The generation engine uses the selected style data to synthesize the style on the user's face. The generated visual proposal provides the user with a specific style image and also gives advice based on emotion along with the proposal.

[0306] The style provided by this system corresponds to both the characteristics and emotions of the user, so it can improve the user's satisfaction. Furthermore, by capturing changes in emotion in real time, flexible proposals according to different situations become possible. Thus, the present invention dramatically improves the efficiency and accuracy of style selection.

[0307] The processing flow will be described below.

[0308] Step 1:

[0309] The user uses the terminal to take or select images of their face and body shape. The selected image is set to the interface for uploading.

[0310] Step 2:

[0311] The terminal uses format confirmation software to convert the image data into a standard format and prepares to send it to the server.

[0312] Step 3:

[0313] The server receives the image data from the terminal. The received image is processed by an AI agent to analyze facial features and skeletal information.

[0314] Step 4:

[0315] The server also passes the image data to the emotion engine, which determines the user's emotional state based on their facial expressions and the degree of tension on their face, and generates emotion data.

[0316] Step 5:

[0317] The server compares the extracted feature data and sentiment data with the database and uses this as foundational information to select the optimal style.

[0318] Step 6:

[0319] The server selects a style that matches the user's current psychological state based on emotional data and sends the style information to the generation engine.

[0320] Step 7:

[0321] The generation engine uses the received style information to synthesize the style onto the user's face image. It then generates an image of the synthesized visual suggestion.

[0322] Step 8:

[0323] The server sends the terminal advice based on sentiment data, along with the generated visual style suggestions.

[0324] Step 9:

[0325] Users can view suggested images on their device and select their preferred style while referring to comments and advice regarding the visual suggestions.

[0326] (Example 2)

[0327] 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".

[0328] Conventional style suggestion systems often struggled to provide suggestions that adequately considered individual user characteristics and emotions, resulting in generic suggestions. Furthermore, they lacked the flexibility to adapt to changes in emotions, making it difficult to improve user satisfaction. In addition, the incomplete use of past data for effective style selection prevented them from providing personalized suggestions suitable for each user.

[0329] 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.

[0330] In this invention, the server includes means for analyzing facial features and emotional states from the image, means for comparing the analyzed features and emotional states with a database to select the optimal style, and means for synthesizing the selected style onto the user image using a generation algorithm to generate visual suggestions. This enables highly personalized style suggestions based on the user's features and emotions.

[0331] A "user" is an individual who uses the system to input their own image and receive style suggestions.

[0332] A "terminal" is an electronic device used by a user to take or select images, and a device used to transmit information to a server.

[0333] A "server" is a computer system that receives image data sent by users, analyzes it, and provides style suggestions.

[0334] "Image" refers to visual data that a user captures or selects using their device and inputs into the system.

[0335] "Data conversion" is the process of converting images provided by a user into an appropriate format, and is a procedure that enables transmission and processing.

[0336] "Facial features" refer to the specific physical characteristics of the user's face, including information about its shape and structure.

[0337] "Emotional state" refers to information that indicates the user's psychological or emotional state, and is inferred from facial features, etc.

[0338] A "database" is a record system that stores past user data and style information, and is used in the analysis process.

[0339] "Optimal style" refers to the most appropriate fashion and visual expression, selected based on the user's characteristics and emotional state.

[0340] A "generative algorithm" is a computational method used to perform visual synthesis on a user's image based on a selected style.

[0341] A "visual suggestion" is an image of a style proposed to the user, created by a generative algorithm.

[0342] This system allows users to input images of their face and body shape using a terminal, and the server then provides personalized style suggestions based on that input. The following describes a specific embodiment of this invention.

[0343] First, the user takes or selects an image using their device. The device is a smart device with a camera function, and this image is converted to JPEG or PNG format and sent to the server via the internet.

[0344] The server utilizes AI technology to analyze the received images. Specifically, it uses image processing libraries such as OpenCV to extract facial features and then uses emotion recognition software like EmotionAPI to identify emotional states. This information is then compared against a database on the server to select the optimal style.

[0345] The generated style suggestions utilize a learning model. By leveraging the generative AI model, styles based on user characteristics are synthesized onto user images, generating visual suggestions. Style transfer techniques, such as DeepArt, may be applied in this process.

[0346] Finally, visual suggestions and sentiment-based advice generated by the server are sent to the user's device. The user reviews these and decides whether the suggested style is suitable for them.

[0347] As a concrete example, suppose a user enters the prompt, "I'm attending a friend's wedding today. Please suggest an outfit that matches a festive and joyful mood." Based on this prompt, the system can recognize that the user is looking forward to a special day and suggest a style with vibrant colors and designs.

[0348] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0349] Step 1:

[0350] The user takes a picture of their face and body shape using the device's camera, or selects one from their photo library. This image is converted to JPEG or PNG format within the device and prepared for transmission to the server. The input is the image selected or taken by the user, and the output is the formatted image data sent to the server over the network.

[0351] Step 2:

[0352] The server receives image data sent from the user. The server uses an image processing library (e.g., OpenCV) to analyze this image and extract the user's facial features. Furthermore, it uses software such as EmotionAPI to identify the user's emotional state. In this step, the input is the user's image data, and the output is facial feature data and emotional state data.

[0353] Step 3:

[0354] The server uses the facial feature data and emotional state data obtained in the previous step to match it against its internal database. This process references historical data and trend information stored in the database to select the optimal style for the user. The input is feature data and emotional data, and the output is optimal style information.

[0355] Step 4:

[0356] The server runs a generative AI model using the selected style information. Style transfer techniques, such as DeepArt, are used in the process of compositing styles onto the user's image. The inputs here are the optimal style information and the user's image, and the output is a visually suggested image with the style composited.

[0357] Step 5:

[0358] The server sends emotion-based advice along with a generated visual suggestion image to the user's device. The user reviews the received suggestion on their device and considers whether it aligns with their preferences. The input is the suggestion image and advice, and the output is the visual confirmation and potential feedback on the user's device.

[0359] (Application Example 2)

[0360] 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."

[0361] In modern society, suggesting styles that match individual user characteristics and emotional states is essential for improving consumer satisfaction. However, many current style suggestion systems do not take into account users' real-time emotions, making it difficult to provide personalized and specific suggestions. Therefore, there is a growing demand for systems that enable dynamic and flexible style suggestions based on user characteristics and emotions.

[0362] 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.

[0363] In this invention, the server includes means for acquiring a user's image, means for analyzing features and emotions from the image, and means for selecting the optimal style by comparing the features and emotions with a past database. This makes it possible to suggest a style that corresponds to the user's current features and emotions.

[0364] "Means for acquiring user images" refers to devices or methods for collecting visual information of customers, thereby collecting data on the user's face and body shape.

[0365] "Means for analyzing characteristics and emotions" refers to technologies or functions for determining a user's physical characteristics and emotional state from collected visual information.

[0366] "A method for selecting the optimal style by comparing with past databases" refers to a process of referring to accumulated historical data to determine the style that best suits the user's characteristics and emotions.

[0367] "Means for generating visual suggestions by synthesizing the selected style onto the user's image using a generation engine" refers to a technology that visually represents the selected style by overlaying it onto the user's image, thereby providing the customer with a concrete image of the style.

[0368] "Means of providing on a display device" refers to a function that uses a screen or monitor for presenting images or videos in order to display the generated visual proposal.

[0369] The system for carrying out this invention provides a process for users to receive style suggestions via a display device installed in a fitting room. Its configuration and operation are described below.

[0370] When a user stands in front of a display device in a fitting room, a camera attached to the device captures the user's face and body shape. This image data is sent to a server via the terminal. The server uses image processing technology to analyze the user's features and emotions from the image. This analysis uses, for example, a "computer vision API" (e.g., Google Cloud Vision) to extract facial and body shape information, and uses machine learning models to determine emotions.

[0371] The analysis results are compared with a database on the server to select the optimal style based on the user's characteristics and emotions. This selection process utilizes historical data, taking into account styles and trends the user has previously preferred.

[0372] The selected style is synthesized with the user's image by a generation engine. This generation process utilizes an artificial intelligence model (e.g., TensorFlow) that leverages machine learning. The generated visual style suggestions are displayed on a display device, allowing the user to visually confirm them.

[0373] For example, if a user expresses the sentiment of wanting to try a relaxed style before heading to work, the synthesis engine will generate a casual and calm style for the user's image. This suggestion is visually easy for the user to understand and allows for real-time suggestions that respond to their emotions.

[0374] Example prompt: "Analyze the customer image and suggest the most suitable casual style based on their current mood. Mood tag: Relaxed, Category: Work Style"

[0375] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0376] Step 1:

[0377] The terminal acquires the user's image through the display device's camera. The input in the image acquisition process is the user's visual information, and the output is digital image data of the user's face and body. The terminal then prepares to send this image data to the server.

[0378] Step 2:

[0379] The server receives image data transmitted from the terminal and uses a computer vision API to analyze the user's features and emotions. It processes the image data as input to extract the user's facial and body shape features, as well as their emotional state. The output consists of analyzed feature data and emotion data.

[0380] Step 3:

[0381] The server matches the analyzed feature and sentiment data against a database. The input includes feature and sentiment data, and the server selects the optimal style by performing a database search based on past history. The output is the data for the selected style.

[0382] Step 4:

[0383] The server uses a generation engine to synthesize selected styles onto the user's image. The input consists of the user's image data and style data, which are processed by a machine learning model to generate visually suggestible style images. The output is the image data of the synthesized style suggestions.

[0384] Step 5:

[0385] The terminal receives style suggestions synthesized from the server and displays them on the display device. The user can then review these visual style suggestions. It receives generated style image data as input and provides visual information to be displayed on the screen as output.

[0386] 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.

[0387] 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.

[0388] 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.

[0389] [Third Embodiment]

[0390] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0391] 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.

[0392] 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).

[0393] 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.

[0394] 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.

[0395] 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).

[0396] 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.

[0397] 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.

[0398] 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.

[0399] 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.

[0400] 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.

[0401] 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".

[0402] This invention is a system in which a user uploads an image, and AI technology is used to suggest the most suitable style for that user. This system is realized by the user uploading an image on their device, and the server processing that image.

[0403] Specifically, users use their devices to take or select images of their face and body shape and upload them. The device first checks the image format and sends it to the server. The server uses an AI agent to extract facial and body shape features from the received images. This reveals the user's individual attributes.

[0404] The server compares the extracted features with a previously stored style database. This comparison selects the style best suited to the user's face and body shape. The selected style information is then passed to the generation engine, which performs style synthesis on the user's facial photograph.

[0405] The generation engine produces visual suggestions as concrete style images. The server sends these generated images back to the terminal along with the reasons for the suggestions and advice, allowing the user to view multiple styles on the screen. Based on the presented visual suggestions, the user can choose their preferred style.

[0406] This allows users to visually confirm and select the style that best suits them, significantly streamlining the traditional trial-and-error process of choosing a style. This invention is also applicable to other AI technologies and database systems, offering further expandability.

[0407] The following describes the processing flow.

[0408] Step 1:

[0409] The user uses their device to take or select images of their face and body shape. They then place these image files into the upload interface.

[0410] Step 2:

[0411] The device checks the format of the uploaded image, and if necessary, converts it to a standard format before sending the image to the server.

[0412] Step 3:

[0413] The server passes the image received from the terminal to the AI ​​agent and begins processing. The AI ​​agent recognizes facial landmarks from the image and extracts features such as facial shape and bone structure.

[0414] Step 4:

[0415] The server uses the extracted feature information to access a style database. Here, it searches for and matches the most suitable style based on the user's characteristics.

[0416] Step 5:

[0417] The server selects the style it deems most suitable for the user based on the matching results. It then passes the selected style information to the generation engine.

[0418] Step 6:

[0419] The generation engine synthesizes styles onto the user's facial image based on style information received from the server. This generates visual style suggestions.

[0420] Step 7:

[0421] The server sends the generated visual suggestions to the user's device, along with advice on the reasoning behind the suggestions and styling.

[0422] Step 8:

[0423] Users can view style images displayed on their device and choose their preferred style. The user's selection is then saved or sent for use in the next action.

[0424] (Example 1)

[0425] 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."

[0426] A problem exists in that users often need a lot of time and trial and error to find the style that best suits them. Furthermore, conventional technologies have limited means of automatically suggesting appropriate styles based on individual user attributes. This hinders improvements in the user experience.

[0427] 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.

[0428] In this invention, the server includes a device for the user to input image information, a device for extracting feature information from the image information, a device for making the optimal selection by comparing the feature information with a past information set, a device for synthesizing the selected style with the user's image information using a generation device to generate a visual suggestion, a device for providing the visual suggestion to the user, a device for checking the format of the image information and transmitting it securely using a communication procedure, and a device for ensuring security using data encryption technology. This makes it possible to quickly suggest styles tailored to the individual characteristics of each user and efficiently support the user's style selection.

[0429] A "user" refers to an individual who uses the system, inputs their own image information, and receives style suggestions.

[0430] "Image information" refers to digital data, including the user's face and body shape, which is what the system processes.

[0431] "Feature information" refers to unique information extracted from image data, such as the shape of a user's face and body shape.

[0432] An "information set" is a database accumulated over time, a collection of various styles and related information.

[0433] "Selection" refers to a judgment regarding the optimal style identified by matching feature information with a set of information.

[0434] A "generation device" refers to a device that generates visual suggestions by combining a selected style with the user's image information.

[0435] "Visual proposals" refer to specific style images created by a generation device and provided to the user.

[0436] "Communication protocol" refers to a protocol used to securely send and receive data between a terminal and a server.

[0437] "Encryption technology" is a technology used to ensure data security, and it plays a role in encrypting data and preventing unauthorized access.

[0438] This invention is a system that uses AI technology to suggest the optimal style based on the user's image information. First, the user takes or selects images of their face and body shape using their device and uploads them to the system. The device verifies that the image information format is appropriate and securely transmits it to the server via the HTTPS protocol. SSL / TLS encryption technology is used during communication to ensure security.

[0439] The server passes the received image information to an AI agent, which uses a deep learning framework (e.g., TensorFlow) to extract feature information such as facial shape and body shape. This feature information is compared with a past data set (database) to select the optimal style. The data set contains data on various styles, and the attributes of each style are recorded.

[0440] The selected style is passed to a generation device, which uses an image processing library (e.g., OpenCV) to synthesize the style with the user's image information. The generated visual suggestions are sent back to the user's terminal, allowing them to visually check multiple styles on the screen. Specifically, several options are suggested, such as "casual short hairstyle" or "formal business style."

[0441] Based on these visual suggestions, users can select a style that suits their preferences. For example, by entering a prompt such as, "Please suggest a suitable casual style based on a photo of a woman in her 20s. Please suggest three examples of hairstyles and clothing, and explain the reasons for their selection," users can receive intuitive and efficient personalized style suggestions.

[0442] In this way, this system allows users to quickly find the style that best suits them, significantly streamlining the traditional trial-and-error process of choosing a style.

[0443] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0444] Step 1:

[0445] The user uses their device to capture or select image information of their face and body shape. The input here is image data containing the user's face and body shape. The device checks the format of this image data (JPEG or PNG). Once the correct format is confirmed, the image is sent to the server via the HTTPS protocol. As output, the confirmed image data is sent to the server.

[0446] Step 2:

[0447] The server passes the received image information to the AI ​​agent. The input for this is the user's image data. The AI ​​agent uses a deep learning framework such as TensorFlow to extract facial and body shape features from the image data. The output of this process is feature information, which includes identification information for facial and body shape.

[0448] Step 3:

[0449] The server uses the extracted feature information to match the features with those in the database. The input here is the feature information. The database contains information on various styles. The server searches the database based on the feature information and selects the optimal style. The output is the selected style information.

[0450] Step 4:

[0451] The server uses a generation device based on the selected style information to synthesize the style onto the user's image information. The input for this process is the selected style information and the original image data. An image processing library (e.g., OpenCV) is used to synthesize the selected style onto the user's image. The output is the generated visual suggestion.

[0452] Step 5:

[0453] The server sends the generated visual suggestions back to the user's terminal. The input here is the generated visual suggestions. The terminal receives this data and displays the visual suggestions on the user interface. This output allows the user to visually confirm each suggested style on the screen.

[0454] Step 6:

[0455] The user selects their preferred style based on visual suggestions displayed on the device. The input is the visual suggestions. The user intuitively compares and selects each style. As output, the user confirms their selected style and can receive additional feedback as needed.

[0456] (Application Example 1)

[0457] 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."

[0458] There is a need to provide users with an efficient way to select the style that best suits them without trial and error. Furthermore, there is a desire for a system that allows users to easily receive fashion advice at home and support them in making style choices in their daily lives.

[0459] 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.

[0460] In this invention, the server includes means for the user to input an image, means for extracting features from the image, means for selecting the optimal style by comparing it with a past database based on the features, means for synthesizing the selected style onto the user's image using a generation engine to generate a visual suggestion, means for providing the visual suggestion to the user, means for presenting advice to the user by voice or display, and means for supporting the user's selection based on the suggested style. This makes it possible for the user to efficiently select the optimal style at home and effectively support style selection in daily life.

[0461] A "user" is an individual or group that utilizes the system, inputting images and receiving style suggestions.

[0462] "Means of inputting images" refers to the devices and methods used by users to import their own photos and videos into the system.

[0463] "Methods for extracting features" refer to technical processes that analyze and extract important attributes such as facial shape and body shape from input images.

[0464] The "past database" is a collection of information about styles and fashion that has been gathered to date, and it serves as a source of information used to make suggestions to users.

[0465] "Means for selecting the optimal style" refers to an algorithm or process for finding the style that best suits the extracted characteristics by comparing them with the characteristics.

[0466] A "generative engine" is a software or hardware system for generating visual proposals based on a selected style.

[0467] "Means for generating visual suggestions" refers to a process or system for compositing styles onto a user's image and presenting them to the user in a visual form.

[0468] "Means of providing advice by voice or display" refers to technologies that convey style suggestions and opinions to users through voice or display.

[0469] "Means of supporting choice" refers to functions or interfaces that assist users in making judgments or taking actions regarding proposed styles.

[0470] In a system that implements an application example of this invention, a consumer robot and a server are combined and operated. When a user requests style suggestions from the robot, the robot takes an image of the user using its built-in camera. The image is converted to an appropriate format on the local terminal and sent to the server via the internet. On the server, an image processing library (e.g., OpenCV) is first used to extract features such as facial shape and body shape from the image.

[0471] Next, this feature information is compared with a previously accumulated style database. The server uses a machine learning model (e.g., a generative AI model using TensorFlow or PyTorch) to select the optimal style, and the generative engine synthesizes the style onto the user's image. This generates a visual style suggestion, which is then sent to the user's device. On the user's device, the visual suggestion is provided to the user via voice or screen display through the robot.

[0472] For example, if a user asks a robot to "give me advice on what to wear today" while getting ready in the morning, the robot will take a picture of the user and send it, and then provide voice feedback on styles suggested by the server. Specific advice such as "A red shirt and black pants would be perfect" will be offered.

[0473] An example of a prompt message for a generative AI model might be, "Based on the user's image, please suggest the best style."

[0474] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0475] Step 1:

[0476] The user requests style suggestions from a consumer robot. The robot uses its built-in camera to capture an image of the user and inputs it into a terminal. This image is converted to an appropriate format by an image processing library and sent to a server. The input is the user's image, and the output is a formatted image.

[0477] Step 2:

[0478] The server uses the received image to extract facial and body shape features using an image processing library (e.g., OpenCV). The input is a formatted image, and the output is the extracted feature information. In this step, edge detection and pattern recognition are performed to identify the contours of the face and important points.

[0479] Step 3:

[0480] The server compares the extracted feature information with a database of past styles. It utilizes machine learning models (e.g., TensorFlow or PyTorch). The input is feature information, and the output is the optimal style. Here, a generative AI model predicts the optimal style from past data.

[0481] Step 4:

[0482] The server's generation engine synthesizes the selected style onto the user's image to generate visual suggestions. The input is the user's image and the selected style, and the output is a visual style suggestion. This operation includes techniques for style texture synthesis and color correction.

[0483] Step 5:

[0484] The server sends the generated visual style suggestions to the terminal. The terminal, through the robot, provides these suggestions to the user via voice and screen display. The input is the visual style suggestions, and the output is visual and auditory feedback to the user. The robot gives the user specific clothing advice, such as "a red shirt and black pants would be best."

[0485] 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.

[0486] This invention is a system in which a user inputs an image, and AI technology combined with an emotion engine proposes the optimal style. This system works by having the user input an image on their device, and after the server recognizes the emotion and features, it proposes an appropriate style.

[0487] First, the user uses their device to take or select images of their face and body shape and uploads them to the system. The device collects the image data and sends it to the server. Upon receiving the images, the server activates an AI agent to analyze the user's facial features and body shape. Simultaneously, an emotion engine recognizes the user's emotional state from the images.

[0488] Characteristic and emotional information is cross-referenced with a database on the server and used in a process to select the most suitable style for the user based on past data. Style suggestions are then refined based on the emotional state, providing a style that matches the user's current emotions. For example, if the user is feeling calm, a style that conveys a gentle impression will be suggested.

[0489] The generation engine uses selected style data to synthesize styles onto the user's face. The generated visual suggestions provide the user with a concrete image of the style, along with emotion-based advice.

[0490] The styles provided by this system address both the user's characteristics and emotions, thereby improving user satisfaction. Furthermore, by capturing emotional changes in real time, flexible suggestions tailored to different situations become possible. Thus, this invention dramatically improves the efficiency and accuracy of style selection.

[0491] The following describes the processing flow.

[0492] Step 1:

[0493] The user uses their device to take or select images of their face and body shape. They then place the selected images into the upload interface.

[0494] Step 2:

[0495] The terminal uses format verification software to convert the image data to a standard format and prepares it for transmission to the server.

[0496] Step 3:

[0497] The server receives image data from the terminal. The received images are processed by an AI agent, which analyzes facial features and skeletal information.

[0498] Step 4:

[0499] The server also passes the image data to the emotion engine, which determines the user's emotional state based on their facial expressions and the degree of tension on their face, and generates emotion data.

[0500] Step 5:

[0501] The server compares the extracted feature data and sentiment data with the database and uses this as foundational information to select the optimal style.

[0502] Step 6:

[0503] The server selects a style that matches the user's current psychological state based on emotional data and sends the style information to the generation engine.

[0504] Step 7:

[0505] The generation engine uses the received style information to synthesize the style onto the user's face image. It then generates an image of the synthesized visual suggestion.

[0506] Step 8:

[0507] The server sends the terminal advice based on sentiment data, along with the generated visual style suggestions.

[0508] Step 9:

[0509] Users can view suggested images on their device and select their preferred style while referring to comments and advice regarding the visual suggestions.

[0510] (Example 2)

[0511] 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."

[0512] Conventional style suggestion systems often struggled to provide suggestions that adequately considered individual user characteristics and emotions, resulting in generic suggestions. Furthermore, they lacked the flexibility to adapt to changes in emotions, making it difficult to improve user satisfaction. In addition, the incomplete use of past data for effective style selection prevented them from providing personalized suggestions suitable for each user.

[0513] 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.

[0514] In this invention, the server includes means for analyzing facial features and emotional states from the image, means for comparing the analyzed features and emotional states with a database to select the optimal style, and means for synthesizing the selected style onto the user image using a generation algorithm to generate visual suggestions. This enables highly personalized style suggestions based on the user's features and emotions.

[0515] A "user" is an individual who uses the system to input their own image and receive style suggestions.

[0516] A "terminal" is an electronic device used by a user to take or select images, and a device used to transmit information to a server.

[0517] A "server" is a computer system that receives image data sent by users, analyzes it, and provides style suggestions.

[0518] "Image" refers to visual data that a user captures or selects using their device and inputs into the system.

[0519] "Data conversion" is the process of converting images provided by a user into an appropriate format, and is a procedure that enables transmission and processing.

[0520] "Facial features" refer to the specific physical characteristics of the user's face, including information about its shape and structure.

[0521] "Emotional state" refers to information that indicates the user's psychological or emotional state, and is inferred from facial features, etc.

[0522] A "database" is a record system that stores past user data and style information, and is used in the analysis process.

[0523] "Optimal style" refers to the most appropriate fashion and visual expression, selected based on the user's characteristics and emotional state.

[0524] A "generative algorithm" is a computational method used to perform visual synthesis on a user's image based on a selected style.

[0525] A "visual suggestion" is an image of a style proposed to the user, created by a generative algorithm.

[0526] This system allows users to input images of their face and body shape using a terminal, and the server then provides personalized style suggestions based on that input. The following describes a specific embodiment of this invention.

[0527] First, the user takes or selects an image using their device. The device is a smart device with a camera function, and this image is converted to JPEG or PNG format and sent to the server via the internet.

[0528] The server utilizes AI technology to analyze the received images. Specifically, it uses image processing libraries such as OpenCV to extract facial features and then uses emotion recognition software like EmotionAPI to identify emotional states. This information is then compared against a database on the server to select the optimal style.

[0529] The generated style suggestions utilize a learning model. By leveraging the generative AI model, styles based on user characteristics are synthesized onto user images, generating visual suggestions. Style transfer techniques, such as DeepArt, may be applied in this process.

[0530] Finally, visual suggestions and sentiment-based advice generated by the server are sent to the user's device. The user reviews these and decides whether the suggested style is suitable for them.

[0531] As a concrete example, suppose a user enters the prompt, "I'm attending a friend's wedding today. Please suggest an outfit that matches a festive and joyful mood." Based on this prompt, the system can recognize that the user is looking forward to a special day and suggest a style with vibrant colors and designs.

[0532] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0533] Step 1:

[0534] The user takes a picture of their face and body shape using the device's camera, or selects one from their photo library. This image is converted to JPEG or PNG format within the device and prepared for transmission to the server. The input is the image selected or taken by the user, and the output is the formatted image data sent to the server over the network.

[0535] Step 2:

[0536] The server receives image data sent from the user. The server uses an image processing library (e.g., OpenCV) to analyze this image and extract the user's facial features. Furthermore, it uses software such as EmotionAPI to identify the user's emotional state. In this step, the input is the user's image data, and the output is facial feature data and emotional state data.

[0537] Step 3:

[0538] The server uses the facial feature data and emotional state data obtained in the previous step to match it against its internal database. This process references historical data and trend information stored in the database to select the optimal style for the user. The input is feature data and emotional data, and the output is optimal style information.

[0539] Step 4:

[0540] The server runs a generative AI model using the selected style information. Style transfer techniques, such as DeepArt, are used in the process of compositing styles onto the user's image. The inputs here are the optimal style information and the user's image, and the output is a visually suggested image with the style composited.

[0541] Step 5:

[0542] The server sends emotion-based advice along with a generated visual suggestion image to the user's device. The user reviews the received suggestion on their device and considers whether it aligns with their preferences. The input is the suggestion image and advice, and the output is the visual confirmation and potential feedback on the user's device.

[0543] (Application Example 2)

[0544] 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."

[0545] In modern society, suggesting styles that match individual user characteristics and emotional states is essential for improving consumer satisfaction. However, many current style suggestion systems do not take into account users' real-time emotions, making it difficult to provide personalized and specific suggestions. Therefore, there is a growing demand for systems that enable dynamic and flexible style suggestions based on user characteristics and emotions.

[0546] 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.

[0547] In this invention, the server includes means for acquiring a user's image, means for analyzing features and emotions from the image, and means for selecting the optimal style by comparing the features and emotions with a past database. This makes it possible to suggest a style that corresponds to the user's current features and emotions.

[0548] "Means for acquiring user images" refers to devices or methods for collecting visual information of customers, thereby collecting data on the user's face and body shape.

[0549] "Means for analyzing characteristics and emotions" refers to technologies or functions for determining a user's physical characteristics and emotional state from collected visual information.

[0550] "A method for selecting the optimal style by comparing with past databases" refers to a process of referring to accumulated historical data to determine the style that best suits the user's characteristics and emotions.

[0551] "Means for generating visual suggestions by synthesizing the selected style onto the user's image using a generation engine" refers to a technology that visually represents the selected style by overlaying it onto the user's image, thereby providing the customer with a concrete image of the style.

[0552] "Means of providing on a display device" refers to a function that uses a screen or monitor to present images or videos in order to display the generated visual proposal.

[0553] The system for carrying out this invention provides a process for users to receive style suggestions via a display device installed in a fitting room. Its configuration and operation are described below.

[0554] When a user stands in front of a display device in a fitting room, a camera attached to the device captures the user's face and body shape. This image data is sent to a server via the terminal. The server uses image processing technology to analyze the user's features and emotions from the image. This analysis uses, for example, a "computer vision API" (e.g., Google Cloud Vision) to extract facial and body shape information, and uses machine learning models to determine emotions.

[0555] The analysis results are compared with a database on the server to select the optimal style based on the user's characteristics and emotions. This selection process utilizes historical data, taking into account styles and trends the user has previously preferred.

[0556] The selected style is synthesized with the user's image by a generation engine. This generation process utilizes an artificial intelligence model (e.g., TensorFlow) that leverages machine learning. The generated visual style suggestions are displayed on a display device, allowing the user to visually confirm them.

[0557] For example, if a user expresses the sentiment of wanting to try a relaxed style before heading to work, the synthesis engine will generate a casual and calm style for the user's image. This suggestion is visually easy for the user to understand and allows for real-time suggestions that respond to their emotions.

[0558] Example prompt: "Analyze the customer image and suggest the most suitable casual style based on their current mood. Mood tag: Relaxed, Category: Work Style"

[0559] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0560] Step 1:

[0561] The terminal acquires the user's image through the display device's camera. The input in the image acquisition process is the user's visual information, and the output is digital image data of the user's face and body. The terminal then prepares to send this image data to the server.

[0562] Step 2:

[0563] The server receives image data transmitted from the terminal and uses a computer vision API to analyze the user's features and emotions. It processes the image data as input to extract the user's facial and body shape features, as well as their emotional state. The output consists of analyzed feature data and emotion data.

[0564] Step 3:

[0565] The server matches the analyzed feature and sentiment data against a database. The input includes feature and sentiment data, and the server selects the optimal style by performing a database search based on past history. The output is the data for the selected style.

[0566] Step 4:

[0567] The server uses a generation engine to synthesize selected styles onto the user's image. The input consists of the user's image data and style data, which are processed by a machine learning model to generate visually suggestible style images. The output is the image data of the synthesized style suggestions.

[0568] Step 5:

[0569] The terminal receives style suggestions synthesized from the server and displays them on the display device. The user can then review these visual style suggestions. It receives generated style image data as input and provides visual information to be displayed on the screen as output.

[0570] 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.

[0571] 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.

[0572] 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.

[0573] [Fourth Embodiment]

[0574] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0575] 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.

[0576] 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).

[0577] 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.

[0578] 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.

[0579] 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).

[0580] 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.

[0581] 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.

[0582] 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.

[0583] 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.

[0584] 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.

[0585] 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.

[0586] 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".

[0587] This invention is a system in which a user uploads an image, and AI technology is used to suggest the most suitable style for that user. This system is realized by the user uploading an image on their device, and the server processing that image.

[0588] Specifically, users use their devices to take or select images of their face and body shape and upload them. The device first checks the image format and sends it to the server. The server uses an AI agent to extract facial and body shape features from the received images. This reveals the user's individual attributes.

[0589] The server compares the extracted features with a previously stored style database. This comparison selects the style best suited to the user's face and body shape. The selected style information is then passed to the generation engine, which performs style synthesis on the user's facial photograph.

[0590] The generation engine produces visual suggestions as concrete style images. The server sends these generated images back to the terminal along with the reasons for the suggestions and advice, allowing the user to view multiple styles on the screen. Based on the presented visual suggestions, the user can choose their preferred style.

[0591] This allows users to visually confirm and select the style that best suits them, significantly streamlining the traditional trial-and-error process of choosing a style. This invention is also applicable to other AI technologies and database systems, offering further expandability.

[0592] The following describes the processing flow.

[0593] Step 1:

[0594] The user uses their device to take or select images of their face and body shape. They then place these image files into the upload interface.

[0595] Step 2:

[0596] The device checks the format of the uploaded image, and if necessary, converts it to a standard format before sending the image to the server.

[0597] Step 3:

[0598] The server passes the image received from the terminal to the AI ​​agent and begins processing. The AI ​​agent recognizes facial landmarks from the image and extracts features such as facial shape and bone structure.

[0599] Step 4:

[0600] The server uses the extracted feature information to access a style database. Here, it searches for and matches the most suitable style based on the user's characteristics.

[0601] Step 5:

[0602] The server selects the style it deems most suitable for the user based on the matching results. It then passes the selected style information to the generation engine.

[0603] Step 6:

[0604] The generation engine synthesizes styles onto the user's facial image based on style information received from the server. This generates visual style suggestions.

[0605] Step 7:

[0606] The server sends the generated visual suggestions to the user's device, along with advice on the reasoning behind the suggestions and styling.

[0607] Step 8:

[0608] Users can view style images displayed on their device and choose their preferred style. The user's selection is then saved or sent for use in the next action.

[0609] (Example 1)

[0610] 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".

[0611] A problem exists in that users often need a lot of time and trial and error to find the style that best suits them. Furthermore, conventional technologies have limited means of automatically suggesting appropriate styles based on individual user attributes. This hinders improvements in the user experience.

[0612] 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.

[0613] In this invention, the server includes a device for the user to input image information, a device for extracting feature information from the image information, a device for making the optimal selection by comparing the feature information with a past information set, a device for synthesizing the selected style with the user's image information using a generation device to generate a visual suggestion, a device for providing the visual suggestion to the user, a device for checking the format of the image information and transmitting it securely using a communication procedure, and a device for ensuring security using data encryption technology. This makes it possible to quickly suggest styles tailored to the individual characteristics of each user and efficiently support the user's style selection.

[0614] A "user" refers to an individual who uses the system, inputs their own image information, and receives style suggestions.

[0615] "Image information" refers to digital data, including the user's face and body shape, which is what the system processes.

[0616] "Feature information" refers to unique information extracted from image data, such as the shape of a user's face and body shape.

[0617] An "information set" is a database accumulated over time, a collection of various styles and related information.

[0618] "Selection" refers to a judgment regarding the optimal style identified by matching feature information with a set of information.

[0619] A "generation device" refers to a device that generates visual suggestions by combining a selected style with the user's image information.

[0620] "Visual proposals" refer to specific style images created by a generation device and provided to the user.

[0621] "Communication protocol" refers to a protocol used to securely send and receive data between a terminal and a server.

[0622] "Encryption technology" is a technology used to ensure data security, and it plays a role in encrypting data and preventing unauthorized access.

[0623] This invention is a system that uses AI technology to suggest the optimal style based on the user's image information. First, the user takes or selects images of their face and body shape using their device and uploads them to the system. The device verifies that the image information format is appropriate and securely transmits it to the server via the HTTPS protocol. SSL / TLS encryption technology is used during communication to ensure security.

[0624] The server passes the received image information to an AI agent, which uses a deep learning framework (e.g., TensorFlow) to extract feature information such as facial shape and body shape. This feature information is compared with a past data set (database) to select the optimal style. The data set contains data on various styles, and the attributes of each style are recorded.

[0625] The selected style is passed to a generation device, which uses an image processing library (e.g., OpenCV) to synthesize the style with the user's image information. The generated visual suggestions are sent back to the user's terminal, allowing them to visually check multiple styles on the screen. Specifically, several options are suggested, such as "casual short hairstyle" or "formal business style."

[0626] Based on these visual suggestions, users can select a style that suits their preferences. For example, by entering a prompt such as, "Please suggest a suitable casual style based on a photo of a woman in her 20s. Please suggest three examples of hairstyles and clothing, and explain the reasons for their selection," users can receive intuitive and efficient personalized style suggestions.

[0627] In this way, this system allows users to quickly find the style that best suits them, significantly streamlining the traditional trial-and-error process of choosing a style.

[0628] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0629] Step 1:

[0630] The user uses their device to capture or select image information of their face and body shape. The input here is image data containing the user's face and body shape. The device checks the format of this image data (JPEG or PNG). Once the correct format is confirmed, the image is sent to the server via the HTTPS protocol. As output, the confirmed image data is sent to the server.

[0631] Step 2:

[0632] The server passes the received image information to the AI ​​agent. The input for this is the user's image data. The AI ​​agent uses a deep learning framework such as TensorFlow to extract facial and body shape features from the image data. The output of this process is feature information, which includes identification information for facial and body shape.

[0633] Step 3:

[0634] The server uses the extracted feature information to match the features with those in the database. The input here is the feature information. The database contains information on various styles. The server searches the database based on the feature information and selects the optimal style. The output is the selected style information.

[0635] Step 4:

[0636] The server uses a generation device based on the selected style information to synthesize the style onto the user's image information. The input for this process is the selected style information and the original image data. An image processing library (e.g., OpenCV) is used to synthesize the selected style onto the user's image. The output is the generated visual suggestion.

[0637] Step 5:

[0638] The server sends the generated visual suggestions back to the user's terminal. The input here is the generated visual suggestions. The terminal receives this data and displays the visual suggestions on the user interface. This output allows the user to visually confirm each suggested style on the screen.

[0639] Step 6:

[0640] The user selects their preferred style based on visual suggestions displayed on the device. The input is the visual suggestions. The user intuitively compares and selects each style. As output, the user confirms their selected style and can receive additional feedback as needed.

[0641] (Application Example 1)

[0642] 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".

[0643] There is a need to provide users with an efficient way to select the style that best suits them without trial and error. Furthermore, there is a desire for a system that allows users to easily receive fashion advice at home and support them in making style choices in their daily lives.

[0644] 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.

[0645] In this invention, the server includes means for the user to input an image, means for extracting features from the image, means for selecting the optimal style by comparing it with a past database based on the features, means for synthesizing the selected style onto the user's image using a generation engine to generate a visual suggestion, means for providing the visual suggestion to the user, means for presenting advice to the user by voice or display, and means for supporting the user's selection based on the suggested style. This makes it possible for the user to efficiently select the optimal style at home and effectively support style selection in daily life.

[0646] A "user" is an individual or group that utilizes the system, inputting images and receiving style suggestions.

[0647] "Means of inputting images" refers to the devices and methods used by users to import their own photos and videos into the system.

[0648] "Methods for extracting features" refer to technical processes that analyze and extract important attributes such as facial shape and body shape from input images.

[0649] The "past database" is a collection of information about styles and fashion that has been gathered to date, and it serves as a source of information used to make suggestions to users.

[0650] "Means for selecting the optimal style" refers to an algorithm or process for finding the style that best suits the extracted characteristics by comparing them with the characteristics.

[0651] A "generative engine" is a software or hardware system for generating visual proposals based on a selected style.

[0652] "Means for generating visual suggestions" refers to a process or system for compositing styles onto a user's image and presenting them to the user in a visual form.

[0653] "Means of providing advice by voice or display" refers to technologies that convey style suggestions and opinions to users through voice or display.

[0654] "Means of supporting choice" refers to functions or interfaces that assist users in making judgments or taking actions regarding proposed styles.

[0655] In a system that implements an application example of this invention, a consumer robot and a server are combined and operated. When a user requests style suggestions from the robot, the robot takes an image of the user using its built-in camera. The image is converted to an appropriate format on the local terminal and sent to the server via the internet. On the server, an image processing library (e.g., OpenCV) is first used to extract features such as facial shape and body shape from the image.

[0656] Next, this feature information is compared with a previously accumulated style database. The server uses a machine learning model (e.g., a generative AI model using TensorFlow or PyTorch) to select the optimal style, and the generative engine synthesizes the style onto the user's image. This generates a visual style suggestion, which is then sent to the user's device. On the user's device, the visual suggestion is provided to the user via voice or screen display through the robot.

[0657] For example, if a user asks a robot to "give me advice on what to wear today" while getting ready in the morning, the robot will take a picture of the user and send it, and then provide voice feedback on styles suggested by the server. Specific advice such as "A red shirt and black pants would be perfect" will be offered.

[0658] An example of a prompt message for a generative AI model might be, "Based on the user's image, please suggest the best style."

[0659] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0660] Step 1:

[0661] The user requests style suggestions from a consumer robot. The robot uses its built-in camera to capture an image of the user and inputs it into a terminal. This image is converted to an appropriate format by an image processing library and sent to a server. The input is the user's image, and the output is a formatted image.

[0662] Step 2:

[0663] The server uses the received image to extract facial and body shape features using an image processing library (e.g., OpenCV). The input is a formatted image, and the output is the extracted feature information. In this step, edge detection and pattern recognition are performed to identify the contours of the face and important points.

[0664] Step 3:

[0665] The server compares the extracted feature information with a database of past styles. It utilizes machine learning models (e.g., TensorFlow or PyTorch). The input is feature information, and the output is the optimal style. Here, a generative AI model predicts the optimal style from past data.

[0666] Step 4:

[0667] The server's generation engine synthesizes the selected style onto the user's image to generate visual suggestions. The input is the user's image and the selected style, and the output is a visual style suggestion. This operation includes techniques for style texture synthesis and color correction.

[0668] Step 5:

[0669] The server sends the generated visual style suggestions to the terminal. The terminal, through the robot, provides these suggestions to the user via voice and screen display. The input is the visual style suggestions, and the output is visual and auditory feedback to the user. The robot gives the user specific clothing advice, such as "a red shirt and black pants would be best."

[0670] 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.

[0671] This invention is a system in which a user inputs an image, and AI technology combined with an emotion engine proposes the optimal style. This system works by having the user input an image on their device, and after the server recognizes the emotion and features, it proposes an appropriate style.

[0672] First, the user uses their device to take or select images of their face and body shape and uploads them to the system. The device collects the image data and sends it to the server. Upon receiving the images, the server activates an AI agent to analyze the user's facial features and body shape. Simultaneously, an emotion engine recognizes the user's emotional state from the images.

[0673] Characteristic and emotional information is cross-referenced with a database on the server and used in a process to select the most suitable style for the user based on past data. Style suggestions are then refined based on the emotional state, providing a style that matches the user's current emotions. For example, if the user is feeling calm, a style that conveys a gentle impression will be suggested.

[0674] The generation engine uses selected style data to synthesize styles onto the user's face. The generated visual suggestions provide the user with a concrete image of the style, along with emotion-based advice.

[0675] The styles provided by this system address both the user's characteristics and emotions, thereby improving user satisfaction. Furthermore, by capturing emotional changes in real time, flexible suggestions tailored to different situations become possible. Thus, this invention dramatically improves the efficiency and accuracy of style selection.

[0676] The following describes the processing flow.

[0677] Step 1:

[0678] The user uses their device to take or select images of their face and body shape. They then place the selected images into the upload interface.

[0679] Step 2:

[0680] The terminal uses format verification software to convert the image data to a standard format and prepares it for transmission to the server.

[0681] Step 3:

[0682] The server receives image data from the terminal. The received images are processed by an AI agent, which analyzes facial features and skeletal information.

[0683] Step 4:

[0684] The server also passes the image data to the emotion engine, which determines the user's emotional state based on their facial expressions and the degree of tension on their face, and generates emotion data.

[0685] Step 5:

[0686] The server compares the extracted feature data and sentiment data with the database and uses this as foundational information to select the optimal style.

[0687] Step 6:

[0688] The server selects a style that matches the user's current psychological state based on emotional data and sends the style information to the generation engine.

[0689] Step 7:

[0690] The generation engine uses the received style information to synthesize the style onto the user's face image. It then generates an image of the synthesized visual suggestion.

[0691] Step 8:

[0692] The server sends the terminal advice based on sentiment data, along with the generated visual style suggestions.

[0693] Step 9:

[0694] Users can view suggested images on their device and select their preferred style while referring to comments and advice regarding the visual suggestions.

[0695] (Example 2)

[0696] 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".

[0697] Conventional style suggestion systems often struggled to provide suggestions that adequately considered individual user characteristics and emotions, resulting in generic suggestions. Furthermore, they lacked the flexibility to adapt to changes in emotions, making it difficult to improve user satisfaction. In addition, the incomplete use of past data for effective style selection prevented them from providing personalized suggestions suitable for each user.

[0698] 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.

[0699] In this invention, the server includes means for analyzing facial features and emotional states from the image, means for comparing the analyzed features and emotional states with a database to select the optimal style, and means for synthesizing the selected style onto the user image using a generation algorithm to generate visual suggestions. This enables highly personalized style suggestions based on the user's features and emotions.

[0700] A "user" is an individual who uses the system to input their own image and receive style suggestions.

[0701] A "terminal" is an electronic device used by a user to take or select images, and a device used to transmit information to a server.

[0702] A "server" is a computer system that receives image data sent by users, analyzes it, and provides style suggestions.

[0703] "Image" refers to visual data that a user captures or selects using their device and inputs into the system.

[0704] "Data conversion" is the process of converting images provided by a user into an appropriate format, and is a procedure that enables transmission and processing.

[0705] "Facial features" refer to the specific physical characteristics of the user's face, including information about its shape and structure.

[0706] "Emotional state" refers to information that indicates the user's psychological or emotional state, and is inferred from facial features, etc.

[0707] A "database" is a record system that stores past user data and style information, and is used in the analysis process.

[0708] "Optimal style" refers to the most appropriate fashion and visual expression, selected based on the user's characteristics and emotional state.

[0709] A "generative algorithm" is a computational method used to perform visual synthesis on a user's image based on a selected style.

[0710] A "visual suggestion" is an image of a style proposed to the user, created by a generative algorithm.

[0711] This system allows users to input images of their face and body shape using a terminal, and the server then provides personalized style suggestions based on that input. The following describes a specific embodiment of this invention.

[0712] First, the user takes or selects an image using their device. The device is a smart device with a camera function, and this image is converted to JPEG or PNG format and sent to the server via the internet.

[0713] The server utilizes AI technology to analyze the received images. Specifically, it uses image processing libraries such as OpenCV to extract facial features and then uses emotion recognition software like EmotionAPI to identify emotional states. This information is then compared against a database on the server to select the optimal style.

[0714] The generated style suggestions utilize a learning model. By leveraging the generative AI model, styles based on user characteristics are synthesized onto user images, generating visual suggestions. Style transfer techniques, such as DeepArt, may be applied in this process.

[0715] Finally, visual suggestions and sentiment-based advice generated by the server are sent to the user's device. The user reviews these and decides whether the suggested style is suitable for them.

[0716] As a concrete example, suppose a user enters the prompt, "I'm attending a friend's wedding today. Please suggest an outfit that matches a festive and joyful mood." Based on this prompt, the system can recognize that the user is looking forward to a special day and suggest a style with vibrant colors and designs.

[0717] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0718] Step 1:

[0719] The user takes a picture of their face and body shape using the device's camera, or selects one from their photo library. This image is converted to JPEG or PNG format within the device and prepared for transmission to the server. The input is the image selected or taken by the user, and the output is the formatted image data sent to the server over the network.

[0720] Step 2:

[0721] The server receives image data sent from the user. The server uses an image processing library (e.g., OpenCV) to analyze this image and extract the user's facial features. Furthermore, it uses software such as EmotionAPI to identify the user's emotional state. In this step, the input is the user's image data, and the output is facial feature data and emotional state data.

[0722] Step 3:

[0723] The server uses the facial feature data and emotional state data obtained in the previous step to match it against its internal database. This process references historical data and trend information stored in the database to select the optimal style for the user. The input is feature data and emotional data, and the output is optimal style information.

[0724] Step 4:

[0725] The server runs a generative AI model using the selected style information. Style transfer techniques, such as DeepArt, are used in the process of compositing styles onto the user's image. The inputs here are the optimal style information and the user's image, and the output is a visually suggested image with the style composited.

[0726] Step 5:

[0727] The server sends emotion-based advice along with a generated visual suggestion image to the user's device. The user reviews the received suggestion on their device and considers whether it aligns with their preferences. The input is the suggestion image and advice, and the output is the visual confirmation and potential feedback on the user's device.

[0728] (Application Example 2)

[0729] 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".

[0730] In modern society, suggesting styles that match individual user characteristics and emotional states is essential for improving consumer satisfaction. However, many current style suggestion systems do not take into account users' real-time emotions, making it difficult to provide personalized and specific suggestions. Therefore, there is a growing demand for systems that enable dynamic and flexible style suggestions based on user characteristics and emotions.

[0731] 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.

[0732] In this invention, the server includes means for acquiring a user's image, means for analyzing features and emotions from the image, and means for selecting the optimal style by comparing the features and emotions with a past database. This makes it possible to suggest a style that corresponds to the user's current features and emotions.

[0733] "Means for acquiring user images" refers to devices or methods for collecting visual information of customers, thereby collecting data on the user's face and body shape.

[0734] "Means for analyzing characteristics and emotions" refers to technologies or functions for determining a user's physical characteristics and emotional state from collected visual information.

[0735] "A method for selecting the optimal style by comparing with past databases" refers to a process of referring to accumulated historical data to determine the style that best suits the user's characteristics and emotions.

[0736] "Means for generating visual suggestions by synthesizing the selected style onto the user's image using a generation engine" refers to a technology that visually represents the selected style by overlaying it onto the user's image, thereby providing the customer with a concrete image of the style.

[0737] "Means of providing on a display device" refers to a function that uses a screen or monitor to present images or videos in order to display the generated visual proposal.

[0738] The system for carrying out this invention provides a process for users to receive style suggestions via a display device installed in a fitting room. Its configuration and operation are described below.

[0739] When a user stands in front of a display device in a fitting room, a camera attached to the device captures the user's face and body shape. This image data is sent to a server via the terminal. The server uses image processing technology to analyze the user's features and emotions from the image. This analysis uses, for example, a "computer vision API" (e.g., Google Cloud Vision) to extract facial and body shape information, and uses machine learning models to determine emotions.

[0740] The analysis results are compared with a database on the server to select the optimal style based on the user's characteristics and emotions. This selection process utilizes historical data, taking into account styles and trends the user has previously preferred.

[0741] The selected style is synthesized with the user's image by a generation engine. This generation process utilizes an artificial intelligence model (e.g., TensorFlow) that leverages machine learning. The generated visual style suggestions are displayed on a display device, allowing the user to visually confirm them.

[0742] For example, if a user expresses the sentiment of wanting to try a relaxed style before heading to work, the synthesis engine will generate a casual and calm style for the user's image. This suggestion is visually easy for the user to understand and allows for real-time suggestions that respond to their emotions.

[0743] Example prompt: "Analyze the customer image and suggest the most suitable casual style based on their current mood. Mood tag: Relaxed, Category: Work Style"

[0744] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0745] Step 1:

[0746] The terminal acquires the user's image through the display device's camera. The input in the image acquisition process is the user's visual information, and the output is digital image data of the user's face and body. The terminal then prepares to send this image data to the server.

[0747] Step 2:

[0748] The server receives image data transmitted from the terminal and uses a computer vision API to analyze the user's features and emotions. It processes the image data as input to extract the user's facial and body shape features, as well as their emotional state. The output consists of analyzed feature data and emotion data.

[0749] Step 3:

[0750] The server matches the analyzed feature and sentiment data against a database. The input includes feature and sentiment data, and the server selects the optimal style by performing a database search based on past history. The output is the data for the selected style.

[0751] Step 4:

[0752] The server uses a generation engine to synthesize selected styles onto the user's image. The input consists of the user's image data and style data, which are processed by a machine learning model to generate visually suggestible style images. The output is the image data of the synthesized style suggestions.

[0753] Step 5:

[0754] The terminal receives style suggestions synthesized from the server and displays them on the display device. The user can then review these visual style suggestions. It receives generated style image data as input and provides visual information to be displayed on the screen as output.

[0755] 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.

[0756] 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.

[0757] 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.

[0758] 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.

[0759] 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.

[0760] 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.

[0761] The inside of the Emotion Map 400 represents what's in your mind, while the outside represents what you're doing. Therefore, the further you go out the 400-coordinate scale, the more visible your emotions become (the more they manifest in your actions).

[0762] 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.

[0763] 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."

[0764] 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.

[0765] 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.

[0766] 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.

[0767] 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.

[0768] 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.

[0769] 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.

[0770] 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.

[0771] 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.

[0772] 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.

[0773] 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.

[0774] 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.

[0775] 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.

[0776] The following is further disclosed regarding the embodiments described above.

[0777] (Claim 1)

[0778] A means for the user to input an image,

[0779] A means for extracting features from the aforementioned image,

[0780] Based on the aforementioned characteristics, a means for selecting the optimal style by comparing it with past databases,

[0781] A means for generating visual suggestions by using a generation engine to synthesize the selection style onto the user's image,

[0782] Means for providing the aforementioned visual proposal to the user,

[0783] A system that includes this.

[0784] (Claim 2)

[0785] The system according to claim 1, characterized in that the aforementioned features include information on the shape of the face and the shape of the body.

[0786] (Claim 3)

[0787] The system according to claim 1, characterized in that the generation engine performs style synthesis using a machine learning model.

[0788] "Example 1"

[0789] (Claim 1)

[0790] A device in which the user inputs image information,

[0791] A device for extracting feature information from the aforementioned image information,

[0792] A device that makes the optimal selection by comparing the aforementioned characteristic information with a past set of information,

[0793] A device that uses a generation device to synthesize the selected style with the user's image information and generates a visual suggestion,

[0794] A device that provides the aforementioned visual proposal to the user,

[0795] A device that verifies the format of the aforementioned image information and transmits it securely using a communication protocol,

[0796] A device that ensures security using data encryption technology,

[0797] A system that includes this.

[0798] (Claim 2)

[0799] The system according to claim 1, characterized in that the characteristic information includes information on the shape of the face and the shape of the body.

[0800] (Claim 3)

[0801] The system according to claim 1, characterized in that the generation device synthesizes visual proposals using a trained model.

[0802] "Application Example 1"

[0803] (Claim 1)

[0804] A means for the user to input an image,

[0805] A means for extracting features from the aforementioned image,

[0806] Based on the aforementioned characteristics, a means for selecting the optimal style by comparing it with past databases,

[0807] A means for generating visual suggestions by using a generation engine to synthesize the selection style onto the user's image,

[0808] Means for providing the aforementioned visual proposal to the user,

[0809] A means of providing advice to the user via voice or display,

[0810] A means to support user selection based on the proposed style,

[0811] A system that includes this.

[0812] (Claim 2)

[0813] The system according to claim 1, characterized in that the aforementioned features include information on the shape of the face and the shape of the body.

[0814] (Claim 3)

[0815] The system according to claim 1, characterized in that the generation engine performs style synthesis using a machine learning model.

[0816] "Example 2 of combining an emotion engine"

[0817] (Claim 1)

[0818] A means for a user to input an image and convert that image into data,

[0819] Means for sending the converted image to a server,

[0820] The server includes means for analyzing facial features and emotional state from the image,

[0821] A means for selecting the optimal style by comparing the analyzed features and emotional states with a database,

[0822] A means for generating visual suggestions by synthesizing the selected style onto a user image using a generation algorithm,

[0823] The means of providing the user with the aforementioned visual suggestions and emotion-based advice,

[0824] A system that includes this.

[0825] (Claim 2)

[0826] The system according to claim 1, characterized in that the aforementioned features include facial contour information and body structure information.

[0827] (Claim 3)

[0828] The system according to claim 1, characterized in that the generation algorithm uses a learning model to synthesize styles.

[0829] "Application example 2 when combining with an emotional engine"

[0830] (Claim 1)

[0831] Means for obtaining user images,

[0832] A means for analyzing features and emotions from the aforementioned image,

[0833] A means for selecting the optimal style by comparing it with a past database based on the aforementioned characteristics and emotions,

[0834] A means for generating visual suggestions by using a generation engine to synthesize the selection style onto the user's image,

[0835] Means for providing the visual proposal on a display device,

[0836] A system that includes this.

[0837] (Claim 2)

[0838] The system according to claim 1, characterized in that the aforementioned features and emotions include information on facial shape, body shape, and emotional state.

[0839] (Claim 3)

[0840] The system according to claim 1, characterized in that the generation engine uses an artificial intelligence model to synthesize styles. [Explanation of symbols]

[0841] 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 for the user to input an image, A means for extracting features from the aforementioned image, Based on the aforementioned characteristics, a means for selecting the optimal style by comparing it with past databases, A means for generating visual suggestions by using a generation engine to synthesize the selection style onto the user's image, Means for providing the aforementioned visual proposal to the user, A means of providing advice to the user via voice or display, A means to support user selection based on the proposed style, A system that includes this.

2. The system according to claim 1, characterized in that the aforementioned features include information on the shape of the face and the shape of the body.

3. The system according to claim 1, characterized in that the generation engine uses a machine learning model to synthesize styles.

Images