system

Abstract

We provide the system. [Solution] Image acquisition method, Scene analysis means, Composition calculation means, Guideline display means and A means for controlling the shooting, Individual habit-based learning methods, A photography assistance system including...

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern times when everyone takes photos daily, there is a need for a method that allows beginners and amateur photographers to easily take photos with a composition as beautiful as that of professionals. However, it is difficult to easily acquire advanced photography techniques such as artistic composition of photos, exclusion of unnecessary elements, and emphasis of important subjects. Therefore, it is an object to provide an effective system for easily improving the sense of composition.

Means for Solving the Problems

[0005] To solve this problem, a photography assistance system is provided that includes an image acquisition means, a scene analysis means, a composition calculation means, a guideline display means, a shooting control means, and an individual habit learning means. The image acquisition means acquires an image through a camera, and the scene analysis means analyzes the image to identify the landscape and subject. The composition calculation means generates optimal composition candidates based on the analysis results, and these are displayed in the user's camera view using the guideline display means. Furthermore, the shooting control means activates an automatic shutter function, and the individual habit learning means learns the user's preferences, enabling the user to easily take professional-quality photographs.

[0006] "Image acquisition means" refers to technology for capturing images in real time using a camera.

[0007] "Scene analysis means" refers to a technique for analyzing acquired images and identifying elements such as landscapes, people, and objects contained within them.

[0008] A "composition calculation method" is a technique for generating optimal composition candidates by applying artistic rules such as the rule of thirds, the golden ratio, and diagonal composition based on analyzed elements.

[0009] A "guideline display means" is a technology that displays guidelines on the camera view based on the generated composition candidates, providing users with a reference point for adjusting their composition.

[0010] "Shooting control means" refers to technology that detects when the user has aligned the camera to the optimal composition and automatically activates the shutter.

[0011] "Individualized habit learning methods" are technologies that learn a user's behavior and preferences and provide personalized layout suggestions based on that information for subsequent visits. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, the numbered 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.

[0016] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the numbered 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.

[0018] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

[0019] 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."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] 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.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] As shown in Figure 2, in the data processing device 12, 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.

[0030] 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.

[0031] 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.

[0032] 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".

[0033] This photography assistance system primarily consists of terminals and servers, providing users with a professional photography experience with great composition.

[0034] First, the device captures images in real time through its camera function, serving as an image acquisition tool. The captured images are immediately sent to a scene analysis tool, where elements such as landscapes, people, and objects are identified. This analysis utilizes a machine learning model.

[0035] After analysis, the terminal sends the analysis data to the server, which uses a composition calculation tool to generate optimal composition candidates. These compositions are based on various artistic rules of photography, such as the rule of thirds, the golden ratio, and diagonal composition.

[0036] Composition candidates are sent to the terminal using a guideline display mechanism. The terminal overlays these on the camera view in real time, supporting the user in easily adjusting the camera angle.

[0037] Users can adjust the camera position and subject while viewing guidelines displayed on their device. Once the optimal composition is achieved, the automatic shutter control system activates. This allows users to take high-quality photos without consciously thinking about it.

[0038] Furthermore, the server is equipped with individual habit learning capabilities that learn from the user's choices and shooting history. This information is used to create composition suggestions for future shoots, providing personalized shooting guides tailored to the user's preferences.

[0039] A concrete example of its use is when a user wants to take a special photo at a tourist destination. Simply activating the camera will automatically analyze the landscape and people, suggesting the optimal composition. The user only needs to operate the camera according to the guidelines to obtain professional-looking photos. In this way, anyone can take high-quality photos without any technical knowledge.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The device activates the camera and prepares to capture the scene the user wants to photograph in real time. Video data from the camera is acquired sequentially and stored in memory in an analyzable format.

[0043] Step 2:

[0044] The terminal sends the acquired image to a scene analysis system. This system uses a dedicated machine learning model to recognize landscapes, people, and objects in the image. The analysis results include the position and identification information of each element.

[0045] Step 3:

[0046] The terminal sends the analysis results to the server. The server activates the composition calculation mechanism based on the received data. The composition calculation mechanism generates optimal composition candidates using the rule of thirds or the golden ratio based on the analyzed image elements.

[0047] Step 4:

[0048] The server sends the calculated composition candidates to the terminal. Each composition candidate includes guideline information indicating how the camera should be positioned and the subject laid out.

[0049] Step 5:

[0050] When the device receives a composition suggestion, it overlays AR guidelines onto the camera view. The user can then adjust the camera angle and subject position according to the guidelines.

[0051] Step 6:

[0052] When the user has adjusted the composition according to the guidelines, the device detects that the composition is properly positioned. Subsequently, the shooting control means automatically activates the shutter and takes a photograph.

[0053] Step 7:

[0054] The server learns the user's composition choices and shooting style based on the captured data. Using individual habit learning methods, it provides personalized composition suggestions based on the user's preferences for future shoots.

[0055] (Example 1)

[0056] 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."

[0057] In recent years, advancements in photography technology have created a demand for anyone to take high-quality photographs. However, it remains difficult for users lacking experience and expertise to capture professional-quality images. In particular, effectively judging composition and shooting conditions is challenging, often resulting in unsatisfactory results. Therefore, there is a need to develop support systems that allow users to easily utilize professional photography techniques.

[0058] 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.

[0059] In this invention, the server includes an image acquisition means, a scene analysis means, and a composition calculation means. This allows users to easily take high-quality photographs with excellent image composition, regardless of their shooting experience or technical knowledge.

[0060] "Image acquisition means" refers to a function that allows the user to capture images in real time using a camera and record those images.

[0061] "Scene analysis means" refers to a function that uses a machine learning model to identify landscapes, people, and objects in acquired images.

[0062] The "analysis data transmission means" is a communication function for sending analysis results generated based on scene analysis to a server.

[0063] The "composition calculation method" is a function that generates optimal composition candidates by applying artistic rules in photography based on the received analysis data.

[0064] The "guideline generation method" is a function that creates guidelines for visually presenting the generated composition candidates to the user.

[0065] The "guideline display means" is a function that overlays guidelines onto the camera view on the device, supporting users in making adjustments in real time.

[0066] "Shooting control means" refers to a function that automatically activates the shutter when the user adjusts the camera according to the optimal composition.

[0067] The "individual habit learning method" is a function that learns the user's shooting history and selected composition information, and provides a personalized shooting guide tailored to the user's preferences in subsequent shoots.

[0068] This photography assistance system is designed to allow users to easily take professional-quality photographs. The system primarily consists of terminals and a server.

[0069] When a user activates the device's camera, the device captures an image in real time using image acquisition equipment. The hardware used in this process is a typical smartphone or camera device. The captured image is immediately processed by scene analysis equipment. Here, machine learning models (e.g., YOLO or ResNet) are used to identify landscapes, people, objects, etc., in the image. This analysis extracts important image elements.

[0070] The analyzed data is sent from the terminal to the server. The server uses a composition calculation method to generate optimal composition candidates based on the received data. Artistic rules such as the rule of thirds, the golden ratio, and diagonal composition are integrated into the composition calculation, providing users with high-quality visual representation.

[0071] Subsequently, the server uses a guideline generation mechanism to create guidelines that visually communicate composition options to the user. These guidelines are sent to the terminal and overlaid on the camera view by a guideline display mechanism. The user can then adjust the camera position and angle according to these guidelines.

[0072] Furthermore, the system includes a shooting control mechanism that automatically activates the shutter once the user has adjusted the camera according to the guidelines. This ensures that high-quality, well-balanced photographs are taken.

[0073] Furthermore, the server uses individual habit learning methods to learn the user's shooting history and preferences, and improves the user experience by suggesting personalized composition options for subsequent shoots.

[0074] For example, if a user wants to capture a special memory in a photograph at a tourist destination, simply launching the camera will automatically analyze the environment and suggest the optimal composition. By inputting example prompts such as "Please suggest guidelines for taking professionally composed landscape photographs at a tourist destination" into the AI ​​model, users can easily obtain professionally composed photos.

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

[0076] Step 1:

[0077] The device activates its camera function and captures images in real time using an image acquisition method. In this step, each time the user presses the camera's shutter button, light information is acquired from the camera sensor and saved as a digital image. The input is light information from the camera sensor, and the output is digitized image data.

[0078] Step 2:

[0079] The terminal transmits the captured image to a scene analysis system. The scene analysis system utilizes a machine learning model to identify different elements (landscape, people, objects) contained in the image. The input is digital image data, and the output is analysis result data after each element has been identified. Models such as YOLO and ResNet are used for this analysis.

[0080] Step 3:

[0081] The terminal sends the analysis results to the server using an analysis data transmission method. Here, data is sent to the server via the network using protocols such as HTTP. The input is the analysis result data, and the output is a notification of successful transmission to the server.

[0082] Step 4:

[0083] The server generates optimal composition candidates using a composition calculation method based on the received analysis data. The input is analysis data, and the output is data of composition candidates derived from the rule of thirds, the golden ratio, diagonal composition, etc. A generation AI model is used to evaluate multiple composition patterns and select the most appropriate one.

[0084] Step 5:

[0085] The server uses a guideline generation mechanism to create guidelines for communicating composition candidates to the user. The input is data of composition candidates, and the output is guideline data that can be displayed on the terminal. These guidelines must be in a visually interpretable format.

[0086] Step 6:

[0087] The device uses a guideline display mechanism to overlay the received composition guidelines onto the camera view. The input is guideline data, and the output is a real-time display of the guidelines on the camera view. The user checks the grids, circles, lines, and other guides displayed on the screen and adjusts the camera position and angle.

[0088] Step 7:

[0089] When the user aligns the camera position and angle with the guidelines, the device's shooting control system activates the automatic shutter. The input is the adjusted camera settings and position information, and the output is the final image captured by the shutter activation. This allows the user to take photos with optimal composition without consciously thinking about it.

[0090] Step 8:

[0091] The server uses individual habit learning methods to analyze the user's shooting history and preferences, preparing to suggest a personalized shooting guide for the next shoot. The input is shooting history data, and the output is an updated user profile based on that history. This ensures that compositions that better suit the user's preferences are more accurately reflected in the next shoot.

[0092] (Application Example 1)

[0093] 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."

[0094] In autonomous vehicles, there is a lack of means to automatically record beautiful scenery and travel events in the optimal composition, leading to the challenge of users missing recording opportunities while driving. Therefore, there is a need for a system that can easily acquire professional-quality images or videos while driving without compromising the scenery.

[0095] 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.

[0096] In this invention, the server includes a scene analysis means, a composition calculation means, and a driving support means that automatically calculates a composition suitable for the driving environment. This makes it possible for the user to record images and videos with the optimal composition automatically, without missing any beautiful scenery while driving.

[0097] An "image acquisition means" is a device that has the function of acquiring images of the environment or subject in real time using a camera or sensor.

[0098] A "scene analysis device" is a device that utilizes computer vision technology to analyze acquired images and identify features such as landscapes, people, and objects.

[0099] A "composition calculation device" is a device that generates optimal composition candidates based on the results of scene analysis, following artistic rules such as the rule of thirds, the golden ratio, and diagonal composition.

[0100] A "guideline display device" is a display device that visually presents the calculated optimal composition to the user and assists in adjusting the camera's composition.

[0101] A "shooting control means" is a device that automatically controls the shutter when the optimal composition is obtained, and records images or videos.

[0102] A "personalized habit learning tool" is a device that learns a user's shooting history and preferences, and uses that information to personalize future shooting guides.

[0103] A "driving support system" is a device that calculates the optimal composition in real time within the driving environment of an autonomous vehicle and automatically records the scenery.

[0104] A "recording device" is a device that has the function of saving acquired images and videos as digital data.

[0105] To realize this invention, the system uses image acquisition means, scene analysis means, composition calculation means, guideline display means, shooting control means, individual habit learning means, driving support means, and recording means.

[0106] The server receives image data acquired in real time using cameras and analyzes it using scene analysis tools. The analysis uses computer vision technology and machine learning models (e.g., a subject recognition model using TENSORFLOW®) to identify landscapes and objects.

[0107] Based on the scene analysis results, the composition calculation system calculates the optimal composition according to rules such as the rule of thirds, the golden ratio, and diagonal composition. This composition information is adjusted to the user's preferences and presented to the device via a guideline display system.

[0108] On the device, these guidelines are overlaid on display media such as smart head-mounted displays, making it easier for users to grasp the optimal composition. Furthermore, driving assistance systems automatically perform these processes while the autonomous vehicle is in motion, helping to ensure that the scenery is not missed.

[0109] After the user confirms the optimal composition, the shutter is automatically activated by the shooting control means, and the image or video is saved to the recording means in high quality. Furthermore, the individual habit learning means learns the user's shooting data and builds a database to suggest personalized compositions.

[0110] For example, if you want to take a picture of a beautiful sunset while driving an autonomous vehicle, this system allows you to take a photo with the optimal composition without getting out of the car, and save the record to the vehicle's system.

[0111] An example of a prompt message for a generating AI model might be: "Based on the image captured by the in-car camera, perform real-time scene analysis, calculate the optimal photographic composition, and display it as an overlay."

[0112] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0113] Step 1:

[0114] The device uses its camera to acquire images in real time. These images are processed as input data. Image data from the camera is acquired in streaming format and sent to the system.

[0115] Step 2:

[0116] The server analyzes the received image data using scene analysis tools. Here, it utilizes generative AI models and machine learning models to recognize subjects and backgrounds. This data processing outputs information identifying landscapes and objects.

[0117] Step 3:

[0118] The server calculates the optimal composition using a composition calculation method based on the analysis results. Using the specific information obtained as input, it calculates the optimal composition based on the rule of thirds, the golden ratio, and diagonal composition. A composition guide calculated through this process is then output.

[0119] Step 4:

[0120] The device uses a guideline display mechanism to visualize the calculated composition guide to the user. Using composition guide information as input, the guidelines are overlaid and displayed on a smart head-mounted display.

[0121] Step 5:

[0122] The user adjusts the camera position according to the guidelines. After the user has properly aligned the camera, a confirmation signal is output from the device, and the process proceeds to the next step.

[0123] Step 6:

[0124] The device's shooting control mechanism activates, automatically pressing the shutter when the composition is complete. This allows the acquired image to be output to the recording device and saved in high quality.

[0125] Step 7:

[0126] The server's individual habit learning mechanism collects the user's shooting data and prepares personalized advice for the next shoot. This learning process generates guides as output data tailored to the user's preferences.

[0127] 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.

[0128] This photo-taking assistance system, which incorporates an emotion engine, works in conjunction with a terminal and server to recognize the user's emotional state in real time and provide a photo-taking experience that takes that into account.

[0129] First, the device activates its camera and captures images in real time. During this process, the image acquisition mechanism works to collect image data from the camera view, and at the same time, it receives the user's facial expressions as input data for the emotion engine. The emotion engine uses facial expression analysis technology to analyze the user's emotional state.

[0130] The analyzed emotion data is sent to the server along with scene information acquired by the scene analysis means. Based on this, the server uses a composition calculation means to generate a composition suitable for the user's emotional state. For example, when the user is expressing feelings of joy, a composition that emphasizes a bright background or a wide sky is recommended.

[0131] The generated composition candidates are transmitted to the terminal in real time via a guideline display mechanism. The terminal overlays these on the camera view, and the user adjusts the camera angle according to the guide. During this process, the emotion engine continuously monitors the user's facial expressions and can dynamically adjust the composition in response to changes in emotion.

[0132] Once the user positions themselves according to the guidelines, the camera control system automatically activates the shutter, capturing a professional photograph that resonates with their emotions. During this process, a personalized learning system learns the user's composition choices and emotional responses, providing more accurate and personalized suggestions for future use.

[0133] As a concrete example of its use, when a user takes photos at a birthday party, the emotion engine recognizes the user's smile, and the composition calculation means provides a composition that recommends a bright color tone and wide-angle lens effect that matches it. In this way, the user can capture special moments in photographs that are optimized for the atmosphere of the moment. This system allows users to easily take emotionally appealing photos without having to consciously think about technology or environmental judgments.

[0134] The following describes the processing flow.

[0135] Step 1:

[0136] The device begins acquiring real-time image data as soon as the user launches the camera app. The image data is converted to a format suitable for system processing and stored in memory.

[0137] Step 2:

[0138] The device also captures the user's facial expressions through its camera and inputs them into the emotion engine. The emotion engine uses a facial expression analysis algorithm to recognize the user's current emotional state in real time.

[0139] Step 3:

[0140] The device's scene analysis mechanism identifies scene elements within the captured image, such as landscapes and people. This clarifies areas of interest within the image.

[0141] Step 4:

[0142] The terminal sends the scene analysis results and the emotion engine analysis results to the server. The server analyzes this data and generates composition candidates that take into account the user's emotions and the characteristics of the scene.

[0143] Step 5:

[0144] The server's composition calculation method uses the rule of thirds and the golden ratio to calculate compositions that are appropriate for the user's emotions. For example, if the user is enjoying themselves, a bright and open composition will be prioritized.

[0145] Step 6:

[0146] The terminal receives composition candidates sent from the server and overlays them on the camera view using a guideline display mechanism. This allows the user to easily match the ideal composition with real-time guidance.

[0147] Step 7:

[0148] The user adjusts the camera and subject according to the guidelines, and is guided to achieve the desired composition. During this time, the emotion engine continuously monitors the user's facial expressions.

[0149] Step 8:

[0150] The device activates its shooting control mechanism and automatically takes a picture when the user's actions match the guidelines. This ensures that the optimal moment is accurately recorded as a photograph.

[0151] Step 9:

[0152] The server analyzes the captured data and stores the user's emotional state and composition selection history as training data. This enables more personalized suggestions in subsequent shooting sessions.

[0153] (Example 2)

[0154] 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".

[0155] Conventional photo-taking assistance systems have difficulty taking into account the user's emotional state, making it challenging to capture emotional moments in photographs. Furthermore, they lacked sufficient functionality to learn individual user shooting habits and apply that knowledge to future shoots.

[0156] 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.

[0157] In this invention, the server includes a facial expression analysis means, an emotional state analysis means, and an individual habit learning means. This enables the automatic generation of compositions based on the user's emotional state and personalized shooting support based on the learning of shooting habits.

[0158] "Image acquisition means" refers to a function that acquires image data in real time using a camera or other image sensor.

[0159] "Facial expression analysis means" refers to analysis technology for identifying a user's facial expressions and estimating their emotions.

[0160] "Emotional state analysis means" is a technology that identifies a user's emotional state based on analyzed facial expression data.

[0161] A "scene analysis tool" is a function that analyzes scene information within an image, and is used to recognize the subject and determine the surrounding environment.

[0162] The "composition calculation means" is a function that calculates the optimal composition for a photograph based on the user's emotional state and scene information.

[0163] A "guideline display mechanism" is a function that visually presents the calculated composition to the user and supports them in taking photos.

[0164] "Shooting control means" refers to a function that automatically operates the camera's shutter based on user instructions or system commands.

[0165] "Individualized habit learning method" is a technology that learns the user's past shooting data and preferences and makes optimal suggestions for future shooting sessions.

[0166] The photographic assistance system of this invention includes an image acquisition means, a facial expression analysis means, an emotional state analysis means, a scene analysis means, a composition calculation means, a guideline display means, a shooting control means, and an individual habit learning means.

[0167] The device first activates its camera and captures images in real time using an image acquisition device. The device can be an imaging device such as a smartphone or digital camera. During this process, a facial expression analysis device analyzes the user's facial expressions using data obtained from the camera, and an emotional state analysis device identifies the user's emotional state. A generative AI model is used for this analysis to recognize emotions, such as when the user's facial expression is smiling.

[0168] The server uses a composition calculation tool to generate the optimal composition for shooting, based on the analyzed emotion data and scene information acquired by the scene analysis tool. For example, when the user is expressing joy, a bright and open composition is selected. The AI ​​model used by the server can perform calculations utilizing the high processing power of the cloud.

[0169] The device then overlays composition information sent from the server onto the camera view using a guideline display mechanism, guiding the user to the optimal angle and framing. Based on these guidelines, the user can adjust the camera position and angle to capture emotionally resonant and appealing photos. Once adjustments are complete, the shooting control mechanism automatically activates the shutter.

[0170] Furthermore, the individual habit learning mechanism learns from the user's shooting data and accumulates data to provide more personalized suggestions for subsequent shoots. A generative AI model is also used in this learning process.

[0171] As a concrete example, consider a scenario where a user takes a photo during a birthday party. After the emotion engine analyzes the user's smile, the server suggests a wide-angle composition with bright colors. This photo-taking experience is made possible by a prompt message that says, "Detect the user's smile and suggest a composition based on bright colors." This system allows users to capture special moments emotionally in photographs, even without technical knowledge.

[0172] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0173] Step 1:

[0174] The device activates its camera and captures image data in real time. The input is image information from the camera, and the image acquisition means processes this information to output a series of image data. Specifically, the smartphone's camera sensor works to capture images in real time in accordance with the user's movements.

[0175] Step 2:

[0176] A facial expression analysis system, which receives image data as input, analyzes the user's facial expressions using a generative AI model. This analysis outputs data indicating the user's emotional state. Specifically, the AI ​​model analyzes facial patterns within the image and generates emotion labels such as smiles or surprises.

[0177] Step 3:

[0178] The server receives emotional data from the facial expression analysis means as input, analyzes it with the emotional state analysis means, and evaluates the user's overall emotional state. Furthermore, the scene analysis means processes the image data and obtains scene information. Using this data, the server calculates the optimal composition and outputs composition data with the composition calculation means. Specifically, the server utilizes cloud-based processes to propose a composition based on scene characteristics and emotional state.

[0179] Step 4:

[0180] Using composition data transmitted from the server as input, the terminal overlays a composition guide onto the camera view using a guideline display mechanism. The user adjusts the camera position and angle based on this guide and prepares to shoot. Specifically, a transparent composition guide is displayed on the terminal's screen, and the user moves the camera accordingly.

[0181] Step 5:

[0182] After the user completes the camera settings according to the composition guide, the shooting control system activates and the shutter is automatically released. This operation automatically takes photos that reflect the user's emotions without any user input. Specifically, the camera saves the image based on pre-set timings and conditions.

[0183] Step 6:

[0184] Using the captured data as input, a personalized habit learning system analyzes the user's shooting habits and learns from the data to optimize future shots. During this process, a generative AI model is used, accumulating past preference data to update the learning model. This is then reflected in the composition suggestions provided to the user for the next shoot.

[0185] (Application Example 2)

[0186] 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".

[0187] Conventional photo-taking systems have the drawback of making it difficult to adjust the timing and composition of shots based on the user's emotions, and also failing to allow for immediate sharing of captured photos on social media. Therefore, it is difficult to efficiently capture moments that emotionally satisfy the user.

[0188] 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.

[0189] In this invention, the server includes emotion analysis means, video display means, composition adjustment means based on emotional state, and automatic sharing means. This makes it possible to perform optimal shooting according to the user's emotions and to quickly share the results.

[0190] An "image acquisition means" is a mechanism for capturing video data in real time using a camera or sensor.

[0191] "Scene analysis means" refers to a technology that analyzes acquired image data to identify landscapes, people, objects, etc.

[0192] The "composition calculation method" is a method for calculating the appropriate screen layout for shooting based on the analysis results.

[0193] A "guideline display device" is a device that provides real-time visual instructions to help users choose the optimal shooting composition.

[0194] "Shooting control means" refers to a function that controls the camera's shutter based on user instructions or system judgment.

[0195] "Individualized habit learning methods" are algorithms that learn the user's preferences and behaviors and provide optimal advice for future shooting opportunities.

[0196] "Emotional analysis methods" refer to technologies that recognize a user's facial expressions and analyze their emotional state.

[0197] A "video display means" is a display device that visually presents images captured by a camera or guidelines to the user.

[0198] "Emotional state-based composition adjustment means" refers to a function that dynamically adjusts the shooting composition according to the user's emotions.

[0199] An "automatic sharing method" is a system that automatically uploads photos taken to social media and other platforms based on user instructions.

[0200] This invention is a system that enables optimal photography and automatic sharing in response to the user's emotions. The system operates with a server and a terminal working in cooperation. Specifically, it uses the camera and display installed in the terminal to analyze the user's facial expressions in real time and adjust the shooting composition based on their emotional state.

[0201] The server uses image processing-based software (e.g., OpenCV) for sentiment analysis. Images captured by the camera are first captured on the terminal, and the image data is processed by a cloud-based sentiment recognition AI engine (e.g., AWS® Rekognition). Once the user's emotions are analyzed, the data is used by a composition calculation means to optimize the shooting. The composition is displayed in real time through a video display means and provided as a guide.

[0202] If the user positions themselves according to this guide, the camera control system will automatically activate the shutter and capture the perfect moment. After the photo is taken, the server uses an automatic sharing system to quickly upload the captured photo to the selected social media platform. This makes it easy for users to share the photo that best fits their emotions.

[0203] As a concrete example, when a user tries on new clothes in a fitting room, the system captures the moment they smile at themselves in the mirror and automatically takes a photo. This photo is immediately displayed on the device, and the user can choose to post it to social media right then and there. This automated process allows users to instantly share wonderful moments, saving them time and effort.

[0204] An example of a prompt using a generative AI model is: "We want to develop a smart mirror application that captures photos of moments when the user is filled with joy and confidence. Please propose a system that uses facial expression analysis technology to provide real-time instructions for the optimal timing to take a photo."

[0205] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0206] Step 1: The device activates the camera and captures images, including the user's face, in real time. The input is the camera video, and the output is face image data. This image data is secured using the acquisition means.

[0207] Step 2: The device transmits the acquired image data to the emotion analysis system. The input is facial image data, and the output is emotional state. The device uses an emotion recognition AI engine to analyze facial expressions and identify the user's emotions.

[0208] Step 3: The server uses emotional state and image data to calculate the optimal composition for the photograph using a composition calculation tool. The input is emotional state and facial image data, and the output is composition data. Based on this, the server formulates a visually effective composition.

[0209] Step 4: The server sends composition data to the terminal, and the terminal overlays the guides onto the video display via the guideline display means. The input is composition data, and the output is a visual display of the guidelines. The user adjusts the camera angle and position based on this.

[0210] Step 5: Once the user follows the guidelines and finds a good position, the device automatically takes a picture using the shooting control mechanism. The input is the optimized position information, and the output is the captured photo data.

[0211] Step 6: The server uses individual habit learning methods to analyze the captured photo data and its emotional correspondence, and learns the user's preferences for future use. The input is photo data and emotional state, and the output is the learned user model.

[0212] Step 7: The server processes the captured photo data using an automated sharing mechanism and uploads it to social media platforms. The input is the photo data, and the output is the content shared online. Through this process, users can instantly share photos that match their emotions.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] [Second Embodiment]

[0217] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0218] 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.

[0219] 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).

[0220] 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.

[0221] 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.

[0222] 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).

[0223] 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.

[0224] 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.

[0225] 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.

[0226] 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.

[0227] 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.

[0228] 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".

[0229] This photography assistance system primarily consists of terminals and servers, providing users with a professional photography experience with great composition.

[0230] First, the device captures images in real time through its camera function, serving as an image acquisition tool. The captured images are immediately sent to a scene analysis tool, where elements such as landscapes, people, and objects are identified. This analysis utilizes a machine learning model.

[0231] After analysis, the terminal sends the analysis data to the server, which uses a composition calculation tool to generate optimal composition candidates. These compositions are based on various artistic rules of photography, such as the rule of thirds, the golden ratio, and diagonal composition.

[0232] Composition candidates are sent to the terminal using a guideline display mechanism. The terminal overlays these on the camera view in real time, supporting the user in easily adjusting the camera angle.

[0233] Users can adjust the camera position and subject while viewing guidelines displayed on their device. Once the optimal composition is achieved, the automatic shutter control system activates. This allows users to take high-quality photos without consciously thinking about it.

[0234] Furthermore, the server is equipped with individual habit learning capabilities that learn from the user's choices and shooting history. This information is used to create composition suggestions for future shoots, providing personalized shooting guides tailored to the user's preferences.

[0235] A concrete example of its use is when a user wants to take a special photo at a tourist destination. Simply activating the camera will automatically analyze the landscape and people, suggesting the optimal composition. The user only needs to operate the camera according to the guidelines to obtain professional-looking photos. In this way, anyone can take high-quality photos without any technical knowledge.

[0236] The following describes the processing flow.

[0237] Step 1:

[0238] The device activates the camera and prepares to capture the scene the user wants to photograph in real time. Video data from the camera is acquired sequentially and stored in memory in an analyzable format.

[0239] Step 2:

[0240] The terminal sends the acquired image to a scene analysis system. This system uses a dedicated machine learning model to recognize landscapes, people, and objects in the image. The analysis results include the position and identification information of each element.

[0241] Step 3:

[0242] The terminal sends the analysis results to the server. The server activates the composition calculation mechanism based on the received data. The composition calculation mechanism generates optimal composition candidates using the rule of thirds or the golden ratio based on the analyzed image elements.

[0243] Step 4:

[0244] The server sends the calculated composition candidates to the terminal. Each composition candidate includes guideline information indicating how the camera should be positioned and the subject laid out.

[0245] Step 5:

[0246] When the device receives a composition suggestion, it overlays AR guidelines onto the camera view. The user can then adjust the camera angle and subject position according to the guidelines.

[0247] Step 6:

[0248] When the user has adjusted the composition according to the guidelines, the device detects that the composition is properly positioned. Subsequently, the shooting control means automatically activates the shutter and takes a photograph.

[0249] Step 7:

[0250] The server learns the user's composition choices and shooting style based on the captured data. Using individual habit learning methods, it provides personalized composition suggestions based on the user's preferences for future shoots.

[0251] (Example 1)

[0252] 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."

[0253] In recent years, advancements in photography technology have created a demand for anyone to take high-quality photographs. However, it remains difficult for users lacking experience and expertise to capture professional-quality images. In particular, effectively judging composition and shooting conditions is challenging, often resulting in unsatisfactory results. Therefore, there is a need to develop support systems that allow users to easily utilize professional photography techniques.

[0254] 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.

[0255] In this invention, the server includes an image acquisition means, a scene analysis means, and a composition calculation means. This allows users to easily take high-quality photographs with excellent image composition, regardless of their shooting experience or technical knowledge.

[0256] "Image acquisition means" refers to a function that allows the user to capture images in real time using a camera and record those images.

[0257] "Scene analysis means" refers to a function that uses a machine learning model to identify landscapes, people, and objects in acquired images.

[0258] The "analysis data transmission means" is a communication function for sending analysis results generated based on scene analysis to a server.

[0259] The "composition calculation method" is a function that generates optimal composition candidates by applying artistic rules in photography based on the received analysis data.

[0260] The "guideline generation method" is a function that creates guidelines for visually presenting the generated composition candidates to the user.

[0261] The "guideline display means" is a function that overlays guidelines onto the camera view on the device, supporting users in making adjustments in real time.

[0262] "Shooting control means" refers to a function that automatically activates the shutter when the user adjusts the camera according to the optimal composition.

[0263] The "individual habit learning method" is a function that learns the user's shooting history and selected composition information, and provides a personalized shooting guide tailored to the user's preferences in subsequent shoots.

[0264] This photography assistance system is designed to allow users to easily take professional-quality photographs. The system primarily consists of terminals and a server.

[0265] When a user activates the device's camera, the device captures an image in real time using image acquisition equipment. The hardware used in this process is a typical smartphone or camera device. The captured image is immediately processed by scene analysis equipment. Here, machine learning models (e.g., YOLO or ResNet) are used to identify landscapes, people, objects, etc., in the image. This analysis extracts important image elements.

[0266] The analyzed data is sent from the terminal to the server. The server uses a composition calculation method to generate optimal composition candidates based on the received data. Artistic rules such as the rule of thirds, the golden ratio, and diagonal composition are integrated into the composition calculation, providing users with high-quality visual representation.

[0267] Subsequently, the server uses a guideline generation mechanism to create guidelines that visually communicate composition options to the user. These guidelines are sent to the terminal and overlaid on the camera view by a guideline display mechanism. The user can then adjust the camera position and angle according to these guidelines.

[0268] Furthermore, the system includes a shooting control mechanism that automatically activates the shutter once the user has adjusted the camera according to the guidelines. This ensures that high-quality, well-balanced photographs are taken.

[0269] Furthermore, the server uses individual habit learning methods to learn the user's shooting history and preferences, and improves the user experience by suggesting personalized composition options for subsequent shoots.

[0270] For example, if a user wants to capture a special memory in a photograph at a tourist destination, simply launching the camera will automatically analyze the environment and suggest the optimal composition. By inputting example prompts such as "Please suggest guidelines for taking professionally composed landscape photographs at a tourist destination" into the AI ​​model, users can easily obtain professionally composed photos.

[0271] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0272] Step 1:

[0273] The device activates its camera function and captures images in real time using an image acquisition method. In this step, each time the user presses the camera's shutter button, light information is acquired from the camera sensor and saved as a digital image. The input is light information from the camera sensor, and the output is digitized image data.

[0274] Step 2:

[0275] The terminal transmits the captured image to a scene analysis system. The scene analysis system utilizes a machine learning model to identify different elements (landscape, people, objects) contained in the image. The input is digital image data, and the output is analysis result data after each element has been identified. Models such as YOLO and ResNet are used for this analysis.

[0276] Step 3:

[0277] The terminal sends the analysis results to the server using an analysis data transmission method. Here, data is sent to the server via the network using protocols such as HTTP. The input is the analysis result data, and the output is a notification of successful transmission to the server.

[0278] Step 4:

[0279] The server generates optimal composition candidates using a composition calculation method based on the received analysis data. The input is analysis data, and the output is data of composition candidates derived from the rule of thirds, the golden ratio, diagonal composition, etc. A generation AI model is used to evaluate multiple composition patterns and select the most appropriate one.

[0280] Step 5:

[0281] The server uses a guideline generation mechanism to create guidelines for communicating composition candidates to the user. The input is data of composition candidates, and the output is guideline data that can be displayed on the terminal. These guidelines must be in a visually interpretable format.

[0282] Step 6:

[0283] The device uses a guideline display mechanism to overlay the received composition guidelines onto the camera view. The input is guideline data, and the output is a real-time display of the guidelines on the camera view. The user checks the grids, circles, lines, and other guides displayed on the screen and adjusts the camera position and angle.

[0284] Step 7:

[0285] When the user aligns the position and angle of the camera with the guidelines, the shooting control means of the terminal activates the automatic shutter. The input is the adjusted camera settings and position information, and the output is the final captured image by the shutter activation. As a result, the user can take pictures with an optimal composition without being aware of it.

[0286] Step 8:

[0287] The server uses the individual habit learning means to analyze the user's shooting history and preferences, and prepares to propose a personalized shooting guide for the next shooting. The input is the shooting history data, and the output is the updated user profile based on that history. As a result, the composition that suits the user's preferences is more accurately reflected at the next shooting.

[0288] (Application Example 1)

[0289] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0290] In an autonomous vehicle, there is a problem that the user may miss recording because there is a lack of means to automatically record beautiful scenery or events during the trip with an optimal composition. Therefore, there is a need for a system that can easily acquire professional-quality images or videos without impairing the landscape during driving.

[0291] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0292] In this invention, the server includes a scene analysis means, a composition calculation means, and a driving support means that automatically calculates a composition suitable for the driving environment. This makes it possible for the user to record images and videos with the optimal composition automatically, without missing any beautiful scenery while driving.

[0293] An "image acquisition means" is a device that has the function of acquiring images of the environment or subject in real time using a camera or sensor.

[0294] A "scene analysis device" is a device that utilizes computer vision technology to analyze acquired images and identify features such as landscapes, people, and objects.

[0295] A "composition calculation device" is a device that generates optimal composition candidates based on the results of scene analysis, following artistic rules such as the rule of thirds, the golden ratio, and diagonal composition.

[0296] A "guideline display device" is a display device that visually presents the calculated optimal composition to the user and assists in adjusting the camera's composition.

[0297] A "shooting control means" is a device that automatically controls the shutter when the optimal composition is obtained, and records images or videos.

[0298] A "personalized habit learning tool" is a device that learns a user's shooting history and preferences, and uses that information to personalize future shooting guides.

[0299] A "driving support system" is a device that calculates the optimal composition in real time within the driving environment of an autonomous vehicle and automatically records the scenery.

[0300] A "recording device" is a device that has the function of saving acquired images and videos as digital data.

[0301] To realize this invention, the system uses image acquisition means, scene analysis means, composition calculation means, guideline display means, shooting control means, individual habit learning means, driving support means, and recording means.

[0302] The server receives image data acquired in real time using the camera and analyzes it using scene analysis tools. The analysis uses computer vision technology and machine learning models (e.g., a subject recognition model using TensorFlow) to identify landscapes and objects.

[0303] Based on the scene analysis results, the composition calculation system calculates the optimal composition according to rules such as the rule of thirds, the golden ratio, and diagonal composition. This composition information is adjusted to the user's preferences and presented to the device via a guideline display system.

[0304] On the device, these guidelines are overlaid on display media such as smart head-mounted displays, making it easier for users to grasp the optimal composition. Furthermore, driving assistance systems automatically perform these processes while the autonomous vehicle is in motion, helping to ensure that the scenery is not missed.

[0305] After the user confirms the optimal composition, the shutter is automatically activated by the shooting control means, and the image or video is saved to the recording means in high quality. Furthermore, the individual habit learning means learns the user's shooting data and builds a database to suggest personalized compositions.

[0306] For example, if you want to take a picture of a beautiful sunset while driving an autonomous vehicle, this system allows you to take a photo with the optimal composition without getting out of the car, and save the record to the in-vehicle system.

[0307] Examples of prompt texts for the generative AI model may include forms such as "Based on the images captured by the in-vehicle camera, perform real-time scene analysis, calculate the optimal photo composition, and display it as an overlay."

[0308] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0309] Step 1:

[0310] The terminal acquires images in real time using the camera. This image is processed as input data. The image data from the camera is acquired in streaming format and transmitted to the system.

[0311] Step 2:

[0312] The server analyzes the received image data using scene analysis means. Here, the generative AI model and machine learning models are utilized to recognize the subject and background. Through this data processing, specific information about the scenery and objects is output.

[0313] Step 3:

[0314] The server calculates the optimal composition using the composition calculation means based on the analysis results. Utilizing the specific information obtained as input, the optimal composition based on the三分法, the golden ratio, or the diagonal composition is calculated. The composition guide calculated through this process is output.

[0315] Step 4:

[0316] The terminal visualizes the calculated composition guide for the user using the guideline display means. Using the composition guide information as input, the guidelines are overlaid and displayed on the smart head-mounted display.

[0317] Step 5:

[0318] The user adjusts the camera position according to the guidelines. After the user has properly aligned the camera, a confirmation signal is output from the device, and the process proceeds to the next step.

[0319] Step 6:

[0320] The device's shooting control mechanism activates, automatically pressing the shutter when the composition is complete. This allows the acquired image to be output to the recording device and saved in high quality.

[0321] Step 7:

[0322] The server's individual habit learning mechanism collects the user's shooting data and prepares personalized advice for the next shoot. This learning process generates guides as output data tailored to the user's preferences.

[0323] 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.

[0324] This photo-taking assistance system, which incorporates an emotion engine, works in conjunction with a terminal and server to recognize the user's emotional state in real time and provide a photo-taking experience that takes that into account.

[0325] First, the device activates its camera and captures images in real time. During this process, the image acquisition mechanism works to collect image data from the camera view, and at the same time, it receives the user's facial expressions as input data for the emotion engine. The emotion engine uses facial expression analysis technology to analyze the user's emotional state.

[0326] The analyzed emotion data is sent to the server along with scene information acquired by the scene analysis means. Based on this, the server uses a composition calculation means to generate a composition suitable for the user's emotional state. For example, when the user is expressing feelings of joy, a composition that emphasizes a bright background or a wide sky is recommended.

[0327] The generated composition candidates are transmitted to the terminal in real time via a guideline display mechanism. The terminal overlays these on the camera view, and the user adjusts the camera angle according to the guide. During this process, the emotion engine continuously monitors the user's facial expressions and can dynamically adjust the composition in response to changes in emotion.

[0328] Once the user positions themselves according to the guidelines, the camera control system automatically activates the shutter, capturing a professional photograph that resonates with their emotions. During this process, a personalized learning system learns the user's composition choices and emotional responses, providing more accurate and personalized suggestions for future use.

[0329] As a concrete example of its use, when a user takes photos at a birthday party, the emotion engine recognizes the user's smile, and the composition calculation means provides a composition that recommends a bright color tone and wide-angle lens effect that matches it. In this way, the user can capture special moments in photographs that are optimized for the atmosphere of the moment. This system allows users to easily take emotionally appealing photos without having to consciously think about technology or environmental judgments.

[0330] The following describes the processing flow.

[0331] Step 1:

[0332] The device begins acquiring real-time image data as soon as the user launches the camera app. The image data is converted to a format suitable for system processing and stored in memory.

[0333] Step 2:

[0334] The device also captures the user's facial expressions through its camera and inputs them into the emotion engine. The emotion engine uses a facial expression analysis algorithm to recognize the user's current emotional state in real time.

[0335] Step 3:

[0336] The device's scene analysis mechanism identifies scene elements within the captured image, such as landscapes and people. This clarifies areas of interest within the image.

[0337] Step 4:

[0338] The terminal sends the scene analysis results and the emotion engine analysis results to the server. The server analyzes this data and generates composition candidates that take into account the user's emotions and the characteristics of the scene.

[0339] Step 5:

[0340] The server's composition calculation method uses the rule of thirds and the golden ratio to calculate compositions that are appropriate for the user's emotions. For example, if the user is enjoying themselves, a bright and open composition will be prioritized.

[0341] Step 6:

[0342] The terminal receives composition candidates sent from the server and overlays them on the camera view using a guideline display mechanism. This allows the user to easily match the ideal composition with real-time guidance.

[0343] Step 7:

[0344] The user adjusts the camera and subject according to the guidelines, and is guided to achieve the desired composition. During this time, the emotion engine continuously monitors the user's facial expressions.

[0345] Step 8:

[0346] The device activates its shooting control mechanism and automatically takes a picture when the user's actions match the guidelines. This ensures that the optimal moment is accurately recorded as a photograph.

[0347] Step 9:

[0348] The server analyzes the captured data and stores the user's emotional state and composition selection history as training data. This enables more personalized suggestions in subsequent shooting sessions.

[0349] (Example 2)

[0350] 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".

[0351] Conventional photo-taking assistance systems have difficulty taking into account the user's emotional state, making it challenging to capture emotional moments in photographs. Furthermore, they lacked sufficient functionality to learn individual user shooting habits and apply that knowledge to future shoots.

[0352] 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.

[0353] In this invention, the server includes a facial expression analysis means, an emotional state analysis means, and an individual habit learning means. This enables the automatic generation of compositions based on the user's emotional state and personalized shooting support based on the learning of shooting habits.

[0354] "Image acquisition means" refers to a function that acquires image data in real time using a camera or other image sensor.

[0355] "Facial expression analysis means" refers to analysis technology for identifying a user's facial expressions and estimating their emotions.

[0356] "Emotional state analysis means" is a technology that identifies a user's emotional state based on analyzed facial expression data.

[0357] A "scene analysis tool" is a function that analyzes scene information within an image, and is used to recognize the subject and determine the surrounding environment.

[0358] The "composition calculation means" is a function that calculates the optimal composition for a photograph based on the user's emotional state and scene information.

[0359] A "guideline display mechanism" is a function that visually presents the calculated composition to the user and supports them in taking photos.

[0360] "Shooting control means" refers to a function that automatically operates the camera's shutter based on user instructions or system commands.

[0361] "Individualized habit learning method" is a technology that learns the user's past shooting data and preferences and makes optimal suggestions for future shooting sessions.

[0362] The photographic assistance system of this invention includes an image acquisition means, a facial expression analysis means, an emotional state analysis means, a scene analysis means, a composition calculation means, a guideline display means, a shooting control means, and an individual habit learning means.

[0363] The device first activates its camera and captures images in real time using an image acquisition device. The device can be an imaging device such as a smartphone or digital camera. During this process, a facial expression analysis device analyzes the user's facial expressions using data obtained from the camera, and an emotional state analysis device identifies the user's emotional state. A generative AI model is used for this analysis to recognize emotions, such as when the user's facial expression is smiling.

[0364] The server uses a composition calculation tool to generate the optimal composition for shooting, based on the analyzed emotion data and scene information acquired by the scene analysis tool. For example, when the user is expressing joy, a bright and open composition is selected. The AI ​​model used by the server can perform calculations utilizing the high processing power of the cloud.

[0365] The device then overlays composition information sent from the server onto the camera view using a guideline display mechanism, guiding the user to the optimal angle and framing. Based on these guidelines, the user can adjust the camera position and angle to capture emotionally resonant and appealing photos. Once adjustments are complete, the shooting control mechanism automatically activates the shutter.

[0366] Furthermore, the individual habit learning mechanism learns from the user's shooting data and accumulates data to provide more personalized suggestions for subsequent shoots. A generative AI model is also used in this learning process.

[0367] As a concrete example, consider a scenario where a user takes a photo during a birthday party. After the emotion engine analyzes the user's smile, the server suggests a wide-angle composition with bright colors. This photo-taking experience is made possible by a prompt message that says, "Detect the user's smile and suggest a composition based on bright colors." This system allows users to capture special moments emotionally in photographs, even without technical knowledge.

[0368] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0369] Step 1:

[0370] The device activates its camera and captures image data in real time. The input is image information from the camera, and the image acquisition means processes this information to output a series of image data. Specifically, the smartphone's camera sensor works to capture images in real time in accordance with the user's movements.

[0371] Step 2:

[0372] A facial expression analysis system, which receives image data as input, analyzes the user's facial expressions using a generative AI model. This analysis outputs data indicating the user's emotional state. Specifically, the AI ​​model analyzes facial patterns within the image and generates emotion labels such as smiles or surprises.

[0373] Step 3:

[0374] The server receives emotional data from the facial expression analysis means as input, analyzes it with the emotional state analysis means, and evaluates the user's overall emotional state. Furthermore, the scene analysis means processes the image data and obtains scene information. Using this data, the server calculates the optimal composition and outputs composition data with the composition calculation means. Specifically, the server utilizes cloud-based processes to propose a composition based on scene characteristics and emotional state.

[0375] Step 4:

[0376] Using composition data transmitted from the server as input, the terminal overlays a composition guide onto the camera view using a guideline display mechanism. The user adjusts the camera position and angle based on this guide and prepares to shoot. Specifically, a transparent composition guide is displayed on the terminal's screen, and the user moves the camera accordingly.

[0377] Step 5:

[0378] After the user completes the camera settings according to the composition guide, the shooting control system activates and the shutter is automatically released. This operation automatically takes photos that reflect the user's emotions without any user input. Specifically, the camera saves the image based on pre-set timings and conditions.

[0379] Step 6:

[0380] Using the captured data as input, a personalized habit learning system analyzes the user's shooting habits and learns from the data to optimize future shots. During this process, a generative AI model is used, accumulating past preference data to update the learning model. This is then reflected in the composition suggestions provided to the user for the next shoot.

[0381] (Application Example 2)

[0382] 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."

[0383] Conventional photo-taking systems have the drawback of making it difficult to adjust the timing and composition of shots based on the user's emotions, and also failing to allow for immediate sharing of captured photos on social media. Therefore, it is difficult to efficiently capture moments that emotionally satisfy the user.

[0384] 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.

[0385] In this invention, the server includes emotion analysis means, video display means, composition adjustment means based on emotional state, and automatic sharing means. This makes it possible to perform optimal shooting according to the user's emotions and to quickly share the results.

[0386] An "image acquisition means" is a mechanism for capturing video data in real time using a camera or sensor.

[0387] "Scene analysis means" refers to a technology that analyzes acquired image data to identify landscapes, people, objects, etc.

[0388] The "composition calculation method" is a method for calculating the appropriate screen layout for shooting based on the analysis results.

[0389] A "guideline display device" is a device that provides real-time visual instructions to help users choose the optimal shooting composition.

[0390] "Shooting control means" refers to a function that controls the camera's shutter based on user instructions or system judgment.

[0391] "Individualized habit learning methods" are algorithms that learn the user's preferences and behaviors and provide optimal advice for future shooting opportunities.

[0392] "Emotional analysis methods" refer to technologies that recognize a user's facial expressions and analyze their emotional state.

[0393] A "video display means" is a display device that visually presents images captured by a camera or guidelines to the user.

[0394] "Emotional state-based composition adjustment means" refers to a function that dynamically adjusts the shooting composition according to the user's emotions.

[0395] An "automatic sharing method" is a system that automatically uploads photos taken to social media and other platforms based on user instructions.

[0396] This invention is a system that enables optimal photography and automatic sharing in response to the user's emotions. The system operates with a server and a terminal working in cooperation. Specifically, it uses the camera and display installed in the terminal to analyze the user's facial expressions in real time and adjust the shooting composition based on their emotional state.

[0397] The server uses image processing-based software (e.g., OpenCV) for sentiment analysis. Images captured by the camera are first captured on the terminal, and this image data is processed by a cloud-based sentiment recognition AI engine (e.g., AWS Rekognition). Once the user's emotions are analyzed, the data is used by a composition calculation system to optimize the shooting. The composition is displayed in real time through a video display system and provided as a guide.

[0398] If the user positions themselves according to this guide, the camera control system will automatically activate the shutter and capture the perfect moment. After the photo is taken, the server uses an automatic sharing system to quickly upload the captured photo to the selected social media platform. This makes it easy for users to share the photo that best fits their emotions.

[0399] As a concrete example, when a user tries on new clothes in a fitting room, the system captures the moment they smile at themselves in the mirror and automatically takes a photo. This photo is immediately displayed on the device, and the user can choose to post it to social media right then and there. This automated process allows users to instantly share wonderful moments, saving them time and effort.

[0400] An example of a prompt using a generative AI model is: "We want to develop a smart mirror application that captures photos of moments when the user is filled with joy and confidence. Please propose a system that uses facial expression analysis technology to provide real-time instructions for the optimal timing to take a photo."

[0401] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0402] Step 1: The device activates the camera and captures images, including the user's face, in real time. The input is the camera video, and the output is face image data. This image data is secured using the acquisition means.

[0403] Step 2: The device transmits the acquired image data to the emotion analysis system. The input is facial image data, and the output is emotional state. The device uses an emotion recognition AI engine to analyze facial expressions and identify the user's emotions.

[0404] Step 3: The server uses emotional state and image data to calculate the optimal composition for the photograph using a composition calculation tool. The input is emotional state and facial image data, and the output is composition data. Based on this, the server formulates a visually effective composition.

[0405] Step 4: The server sends composition data to the terminal, and the terminal overlays the guides onto the video display via the guideline display means. The input is composition data, and the output is a visual display of the guidelines. The user adjusts the camera angle and position based on this.

[0406] Step 5: Once the user follows the guidelines and finds a good position, the device automatically takes a picture using the shooting control mechanism. The input is the optimized position information, and the output is the captured photo data.

[0407] Step 6: The server uses individual habit learning methods to analyze the captured photo data and its emotional correspondence, and learns the user's preferences for future use. The input is photo data and emotional state, and the output is the learned user model.

[0408] Step 7: The server processes the captured photo data using an automated sharing mechanism and uploads it to social media platforms. The input is the photo data, and the output is the content shared online. Through this process, users can instantly share photos that match their emotions.

[0409] 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.

[0410] 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.

[0411] 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.

[0412] [Third Embodiment]

[0413] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0414] 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.

[0415] 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).

[0416] 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.

[0417] 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.

[0418] 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).

[0419] 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.

[0420] 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.

[0421] 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.

[0422] 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.

[0423] 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.

[0424] 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".

[0425] This photography assistance system primarily consists of terminals and servers, providing users with a professional photography experience with great composition.

[0426] First, the device captures images in real time through its camera function, serving as an image acquisition tool. The captured images are immediately sent to a scene analysis tool, where elements such as landscapes, people, and objects are identified. This analysis utilizes a machine learning model.

[0427] After analysis, the terminal sends the analysis data to the server, which uses a composition calculation tool to generate optimal composition candidates. These compositions are based on various artistic rules of photography, such as the rule of thirds, the golden ratio, and diagonal composition.

[0428] Composition candidates are sent to the terminal using a guideline display mechanism. The terminal overlays these on the camera view in real time, supporting the user in easily adjusting the camera angle.

[0429] Users can adjust the camera position and subject while viewing guidelines displayed on their device. Once the optimal composition is achieved, the automatic shutter control system activates. This allows users to take high-quality photos without consciously thinking about it.

[0430] Furthermore, the server is equipped with individual habit learning capabilities that learn from the user's choices and shooting history. This information is used to create composition suggestions for future shoots, providing personalized shooting guides tailored to the user's preferences.

[0431] A concrete example of its use is when a user wants to take a special photo at a tourist destination. Simply activating the camera will automatically analyze the landscape and people, suggesting the optimal composition. The user only needs to operate the camera according to the guidelines to obtain professional-looking photos. In this way, anyone can take high-quality photos without any technical knowledge.

[0432] The following describes the processing flow.

[0433] Step 1:

[0434] The device activates the camera and prepares to capture the scene the user wants to photograph in real time. Video data from the camera is acquired sequentially and stored in memory in an analyzable format.

[0435] Step 2:

[0436] The terminal sends the acquired image to a scene analysis system. This system uses a dedicated machine learning model to recognize landscapes, people, and objects in the image. The analysis results include the position and identification information of each element.

[0437] Step 3:

[0438] The terminal sends the analysis results to the server. The server activates the composition calculation mechanism based on the received data. The composition calculation mechanism generates optimal composition candidates using the rule of thirds or the golden ratio based on the analyzed image elements.

[0439] Step 4:

[0440] The server sends the calculated composition candidates to the terminal. Each composition candidate includes guideline information indicating how the camera should be positioned and the subject laid out.

[0441] Step 5:

[0442] When the device receives a composition suggestion, it overlays AR guidelines onto the camera view. The user can then adjust the camera angle and subject position according to the guidelines.

[0443] Step 6:

[0444] When the user has adjusted the composition according to the guidelines, the device detects that the composition is properly positioned. Subsequently, the shooting control means automatically activates the shutter and takes a photograph.

[0445] Step 7:

[0446] The server learns the user's composition choices and shooting style based on the captured data. Using individual habit learning methods, it provides personalized composition suggestions based on the user's preferences for future shoots.

[0447] (Example 1)

[0448] 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."

[0449] In recent years, advancements in photography technology have created a demand for anyone to take high-quality photographs. However, it remains difficult for users lacking experience and expertise to capture professional-quality images. In particular, effectively judging composition and shooting conditions is challenging, often resulting in unsatisfactory results. Therefore, there is a need to develop support systems that allow users to easily utilize professional photography techniques.

[0450] 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.

[0451] In this invention, the server includes an image acquisition means, a scene analysis means, and a composition calculation means. This allows users to easily take high-quality photographs with excellent image composition, regardless of their shooting experience or technical knowledge.

[0452] "Image acquisition means" refers to a function that allows the user to capture images in real time using a camera and record those images.

[0453] "Scene analysis means" refers to a function that uses a machine learning model to identify landscapes, people, and objects in acquired images.

[0454] The "analysis data transmission means" is a communication function for sending analysis results generated based on scene analysis to a server.

[0455] The "composition calculation method" is a function that generates optimal composition candidates by applying artistic rules in photography based on the received analysis data.

[0456] The "guideline generation method" is a function that creates guidelines for visually presenting the generated composition candidates to the user.

[0457] The "guideline display means" is a function that overlays guidelines onto the camera view on the device, supporting users in making adjustments in real time.

[0458] "Shooting control means" refers to a function that automatically activates the shutter when the user adjusts the camera according to the optimal composition.

[0459] The "individual habit learning method" is a function that learns the user's shooting history and selected composition information, and provides a personalized shooting guide tailored to the user's preferences in subsequent shoots.

[0460] This photography assistance system is designed to allow users to easily take professional-quality photographs. The system primarily consists of terminals and a server.

[0461] When a user activates the device's camera, the device captures an image in real time using image acquisition equipment. The hardware used in this process is a typical smartphone or camera device. The captured image is immediately processed by scene analysis equipment. Here, machine learning models (e.g., YOLO or ResNet) are used to identify landscapes, people, objects, etc., in the image. This analysis extracts important image elements.

[0462] The analyzed data is sent from the terminal to the server. The server uses a composition calculation method to generate optimal composition candidates based on the received data. Artistic rules such as the rule of thirds, the golden ratio, and diagonal composition are integrated into the composition calculation, providing users with high-quality visual representation.

[0463] Subsequently, the server uses a guideline generation mechanism to create guidelines that visually communicate composition options to the user. These guidelines are sent to the terminal and overlaid on the camera view by a guideline display mechanism. The user can then adjust the camera position and angle according to these guidelines.

[0464] Furthermore, the system includes a shooting control mechanism that automatically activates the shutter once the user has adjusted the camera according to the guidelines. This ensures that high-quality, well-balanced photographs are taken.

[0465] Furthermore, the server uses individual habit learning methods to learn the user's shooting history and preferences, and improves the user experience by suggesting personalized composition options for subsequent shoots.

[0466] For example, if a user wants to capture a special memory in a photograph at a tourist destination, simply launching the camera will automatically analyze the environment and suggest the optimal composition. By inputting example prompts such as "Please suggest guidelines for taking professionally composed landscape photographs at a tourist destination" into the AI ​​model, users can easily obtain professionally composed photos.

[0467] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0468] Step 1:

[0469] The device activates its camera function and captures images in real time using an image acquisition method. In this step, each time the user presses the camera's shutter button, light information is acquired from the camera sensor and saved as a digital image. The input is light information from the camera sensor, and the output is digitized image data.

[0470] Step 2:

[0471] The terminal transmits the captured image to a scene analysis system. The scene analysis system utilizes a machine learning model to identify different elements (landscape, people, objects) contained in the image. The input is digital image data, and the output is analysis result data after each element has been identified. Models such as YOLO and ResNet are used for this analysis.

[0472] Step 3:

[0473] The terminal sends the analysis results to the server using an analysis data transmission method. Here, data is sent to the server via the network using protocols such as HTTP. The input is the analysis result data, and the output is a notification of successful transmission to the server.

[0474] Step 4:

[0475] The server generates optimal composition candidates using a composition calculation method based on the received analysis data. The input is analysis data, and the output is data of composition candidates derived from the rule of thirds, the golden ratio, diagonal composition, etc. A generation AI model is used to evaluate multiple composition patterns and select the most appropriate one.

[0476] Step 5:

[0477] The server uses a guideline generation mechanism to create guidelines for communicating composition candidates to the user. The input is data of composition candidates, and the output is guideline data that can be displayed on the terminal. These guidelines must be in a visually interpretable format.

[0478] Step 6:

[0479] The device uses a guideline display mechanism to overlay the received composition guidelines onto the camera view. The input is guideline data, and the output is a real-time display of the guidelines on the camera view. The user checks the grids, circles, lines, and other guides displayed on the screen and adjusts the camera position and angle.

[0480] Step 7:

[0481] When the user aligns the camera position and angle with the guidelines, the device's shooting control system activates the automatic shutter. The input is the adjusted camera settings and position information, and the output is the final image captured by the shutter activation. This allows the user to take photos with optimal composition without consciously thinking about it.

[0482] Step 8:

[0483] The server uses individual habit learning methods to analyze the user's shooting history and preferences, preparing to suggest a personalized shooting guide for the next shoot. The input is shooting history data, and the output is an updated user profile based on that history. This ensures that compositions that better suit the user's preferences are more accurately reflected in the next shoot.

[0484] (Application Example 1)

[0485] 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."

[0486] In autonomous vehicles, there is a lack of means to automatically record beautiful scenery and travel events in the optimal composition, leading to the challenge of users missing recording opportunities while driving. Therefore, there is a need for a system that can easily acquire professional-quality images or videos while driving without compromising the scenery.

[0487] 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.

[0488] In this invention, the server includes a scene analysis means, a composition calculation means, and a driving support means that automatically calculates a composition suitable for the driving environment. This makes it possible for the user to record images and videos with the optimal composition automatically, without missing any beautiful scenery while driving.

[0489] An "image acquisition means" is a device that has the function of acquiring images of the environment or subject in real time using a camera or sensor.

[0490] A "scene analysis device" is a device that utilizes computer vision technology to analyze acquired images and identify features such as landscapes, people, and objects.

[0491] A "composition calculation device" is a device that generates optimal composition candidates based on the results of scene analysis, following artistic rules such as the rule of thirds, the golden ratio, and diagonal composition.

[0492] A "guideline display device" is a display device that visually presents the calculated optimal composition to the user and assists in adjusting the camera's composition.

[0493] A "shooting control means" is a device that automatically controls the shutter when the optimal composition is obtained, and records images or videos.

[0494] A "personalized habit learning tool" is a device that learns a user's shooting history and preferences, and uses that information to personalize future shooting guides.

[0495] A "driving support system" is a device that calculates the optimal composition in real time within the driving environment of an autonomous vehicle and automatically records the scenery.

[0496] A "recording device" is a device that has the function of saving acquired images and videos as digital data.

[0497] To realize this invention, the system uses image acquisition means, scene analysis means, composition calculation means, guideline display means, shooting control means, individual habit learning means, driving support means, and recording means.

[0498] The server receives image data acquired in real time using the camera and analyzes it using scene analysis tools. The analysis uses computer vision technology and machine learning models (e.g., a subject recognition model using TensorFlow) to identify landscapes and objects.

[0499] Based on the scene analysis results, the composition calculation system calculates the optimal composition according to rules such as the rule of thirds, the golden ratio, and diagonal composition. This composition information is adjusted to the user's preferences and presented to the device via a guideline display system.

[0500] On the device, these guidelines are overlaid on display media such as smart head-mounted displays, making it easier for users to grasp the optimal composition. Furthermore, driving assistance systems automatically perform these processes while the autonomous vehicle is in motion, helping to ensure that the scenery is not missed.

[0501] After the user confirms the optimal composition, the shutter is automatically activated by the shooting control means, and the image or video is saved to the recording means in high quality. Furthermore, the individual habit learning means learns the user's shooting data and builds a database to suggest personalized compositions.

[0502] For example, if you want to take a picture of a beautiful sunset while driving an autonomous vehicle, this system allows you to take a photo with the optimal composition without getting out of the car, and save the record to the in-vehicle system.

[0503] An example of a prompt message for a generating AI model might be: "Based on the image captured by the in-car camera, perform real-time scene analysis, calculate the optimal photographic composition, and display it as an overlay."

[0504] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0505] Step 1:

[0506] The device uses its camera to acquire images in real time. These images are processed as input data. Image data from the camera is acquired in streaming format and sent to the system.

[0507] Step 2:

[0508] The server analyzes the received image data using scene analysis tools. Here, it uses generative AI models and machine learning models to recognize subjects and backgrounds. This data processing outputs information identifying landscapes and objects.

[0509] Step 3:

[0510] The server calculates the optimal composition using a composition calculation method based on the analysis results. Using the specific information obtained as input, it calculates the optimal composition based on the rule of thirds, the golden ratio, and diagonal composition. A composition guide calculated through this process is then output.

[0511] Step 4:

[0512] The device uses a guideline display mechanism to visualize the calculated composition guide to the user. Using composition guide information as input, the guidelines are overlaid and displayed on a smart head-mounted display.

[0513] Step 5:

[0514] The user adjusts the camera position according to the guidelines. After the user has properly aligned the camera, a confirmation signal is output from the device, and the process proceeds to the next step.

[0515] Step 6:

[0516] The device's shooting control mechanism activates, automatically pressing the shutter when the composition is complete. This allows the acquired image to be output to the recording device and saved in high quality.

[0517] Step 7:

[0518] The server's individual habit learning mechanism collects the user's shooting data and prepares personalized advice for the next shoot. This learning process generates guides as output data tailored to the user's preferences.

[0519] 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.

[0520] This photo-taking assistance system, which incorporates an emotion engine, works in conjunction with a terminal and server to recognize the user's emotional state in real time and provide a photo-taking experience that takes that into account.

[0521] First, the device activates its camera and captures images in real time. During this process, the image acquisition mechanism works to collect image data from the camera view, and at the same time, it receives the user's facial expressions as input data for the emotion engine. The emotion engine uses facial expression analysis technology to analyze the user's emotional state.

[0522] The analyzed emotion data is sent to the server along with scene information acquired by the scene analysis means. Based on this, the server uses a composition calculation means to generate a composition suitable for the user's emotional state. For example, when the user is expressing feelings of joy, a composition that emphasizes a bright background or a wide sky is recommended.

[0523] The generated composition candidates are transmitted to the terminal in real time via a guideline display mechanism. The terminal overlays these on the camera view, and the user adjusts the camera angle according to the guide. During this process, the emotion engine continuously monitors the user's facial expressions and can dynamically adjust the composition in response to changes in emotion.

[0524] Once the user positions themselves according to the guidelines, the camera control system automatically activates the shutter, capturing a professional photograph that resonates with their emotions. During this process, a personalized learning system learns the user's composition choices and emotional responses, providing more accurate and personalized suggestions for future use.

[0525] As a concrete example of its use, when a user takes photos at a birthday party, the emotion engine recognizes the user's smile, and the composition calculation means provides a composition that recommends a bright color tone and wide-angle lens effect that matches it. In this way, the user can capture special moments in photographs that are optimized for the atmosphere of the moment. This system allows users to easily take emotionally appealing photos without having to consciously think about technology or environmental judgments.

[0526] The following describes the processing flow.

[0527] Step 1:

[0528] The device begins acquiring real-time image data as soon as the user launches the camera app. The image data is converted to a format suitable for system processing and stored in memory.

[0529] Step 2:

[0530] The device also captures the user's facial expressions through its camera and inputs them into the emotion engine. The emotion engine uses a facial expression analysis algorithm to recognize the user's current emotional state in real time.

[0531] Step 3:

[0532] The device's scene analysis mechanism identifies scene elements within the captured image, such as landscapes and people. This clarifies areas of interest within the image.

[0533] Step 4:

[0534] The terminal sends the scene analysis results and the emotion engine analysis results to the server. The server analyzes this data and generates composition candidates that take into account the user's emotions and the characteristics of the scene.

[0535] Step 5:

[0536] The server's composition calculation method uses the rule of thirds and the golden ratio to calculate compositions that are appropriate for the user's emotions. For example, if the user is enjoying themselves, a bright and open composition will be prioritized.

[0537] Step 6:

[0538] The terminal receives composition candidates sent from the server and overlays them on the camera view using a guideline display mechanism. This allows the user to easily match the ideal composition with real-time guidance.

[0539] Step 7:

[0540] The user adjusts the camera and subject according to the guidelines, and is guided to achieve the desired composition. During this time, the emotion engine continuously monitors the user's facial expressions.

[0541] Step 8:

[0542] The device activates its shooting control mechanism and automatically takes a picture when the user's actions match the guidelines. This ensures that the optimal moment is accurately recorded as a photograph.

[0543] Step 9:

[0544] The server analyzes the captured data and stores the user's emotional state and composition selection history as training data. This enables more personalized suggestions in subsequent shooting sessions.

[0545] (Example 2)

[0546] 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."

[0547] Conventional photo-taking assistance systems have difficulty taking into account the user's emotional state, making it challenging to capture emotional moments in photographs. Furthermore, they lacked sufficient functionality to learn individual user shooting habits and apply that knowledge to future shoots.

[0548] 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.

[0549] In this invention, the server includes a facial expression analysis means, an emotional state analysis means, and an individual habit learning means. This enables the automatic generation of compositions based on the user's emotional state and personalized shooting support based on the learning of shooting habits.

[0550] "Image acquisition means" refers to a function that acquires image data in real time using a camera or other image sensor.

[0551] "Facial expression analysis means" refers to analysis technology for identifying a user's facial expressions and estimating their emotions.

[0552] "Emotional state analysis means" is a technology that identifies a user's emotional state based on analyzed facial expression data.

[0553] A "scene analysis tool" is a function that analyzes scene information within an image, and is used to recognize the subject and determine the surrounding environment.

[0554] The "composition calculation means" is a function that calculates the optimal composition for a photograph based on the user's emotional state and scene information.

[0555] A "guideline display mechanism" is a function that visually presents the calculated composition to the user and supports them in taking photos.

[0556] "Shooting control means" refers to a function that automatically operates the camera's shutter based on user instructions or system commands.

[0557] "Individualized habit learning method" is a technology that learns the user's past shooting data and preferences and makes optimal suggestions for future shooting sessions.

[0558] The photographic assistance system of this invention includes an image acquisition means, a facial expression analysis means, an emotional state analysis means, a scene analysis means, a composition calculation means, a guideline display means, a shooting control means, and an individual habit learning means.

[0559] The device first activates its camera and captures images in real time using an image acquisition device. The device can be an imaging device such as a smartphone or digital camera. During this process, a facial expression analysis device analyzes the user's facial expressions using data obtained from the camera, and an emotional state analysis device identifies the user's emotional state. A generative AI model is used for this analysis to recognize emotions, such as when the user's facial expression is smiling.

[0560] The server uses a composition calculation tool to generate the optimal composition for shooting, based on the analyzed emotion data and scene information acquired by the scene analysis tool. For example, when the user is expressing joy, a bright and open composition is selected. The AI ​​model used by the server can perform calculations utilizing the high processing power of the cloud.

[0561] The device then overlays composition information sent from the server onto the camera view using a guideline display mechanism, guiding the user to the optimal angle and framing. Based on these guidelines, the user can adjust the camera position and angle to capture emotionally resonant and appealing photos. Once adjustments are complete, the shooting control mechanism automatically activates the shutter.

[0562] Furthermore, the individual habit learning mechanism learns from the user's shooting data and accumulates data to provide more personalized suggestions for subsequent shoots. A generative AI model is also used in this learning process.

[0563] As a concrete example, consider a scenario where a user takes a photo during a birthday party. After the emotion engine analyzes the user's smile, the server suggests a wide-angle composition with bright colors. This photo-taking experience is made possible by a prompt message that says, "Detect the user's smile and suggest a composition based on bright colors." This system allows users to capture special moments emotionally in photographs, even without technical knowledge.

[0564] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0565] Step 1:

[0566] The device activates its camera and captures image data in real time. The input is image information from the camera, and the image acquisition means processes this information to output a series of image data. Specifically, the smartphone's camera sensor works to capture images in real time in accordance with the user's movements.

[0567] Step 2:

[0568] A facial expression analysis system, which receives image data as input, analyzes the user's facial expressions using a generative AI model. This analysis outputs data indicating the user's emotional state. Specifically, the AI ​​model analyzes facial patterns within the image and generates emotion labels such as smiles or surprises.

[0569] Step 3:

[0570] The server receives emotional data from the facial expression analysis means as input, analyzes it with the emotional state analysis means, and evaluates the user's overall emotional state. Furthermore, the scene analysis means processes the image data and obtains scene information. Using this data, the server calculates the optimal composition and outputs composition data with the composition calculation means. Specifically, the server utilizes cloud-based processes to propose a composition based on scene characteristics and emotional state.

[0571] Step 4:

[0572] Using composition data transmitted from the server as input, the terminal overlays a composition guide onto the camera view using a guideline display mechanism. The user adjusts the camera position and angle based on this guide and prepares to shoot. Specifically, a transparent composition guide is displayed on the terminal's screen, and the user moves the camera accordingly.

[0573] Step 5:

[0574] After the user completes the camera settings according to the composition guide, the shooting control system activates and the shutter is automatically released. This operation automatically takes photos that reflect the user's emotions without any user input. Specifically, the camera saves the image based on pre-set timings and conditions.

[0575] Step 6:

[0576] Using the captured data as input, a personalized habit learning system analyzes the user's shooting habits and learns from the data to optimize future shots. During this process, a generative AI model is used, accumulating past preference data to update the learning model. This is then reflected in the composition suggestions provided to the user for the next shoot.

[0577] (Application Example 2)

[0578] 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."

[0579] Conventional photo-taking systems have the drawback of making it difficult to adjust the timing and composition of shots based on the user's emotions, and also failing to allow for immediate sharing of captured photos on social media. Therefore, it is difficult to efficiently capture moments that emotionally satisfy the user.

[0580] 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.

[0581] In this invention, the server includes emotion analysis means, video display means, composition adjustment means based on emotional state, and automatic sharing means. This makes it possible to perform optimal shooting according to the user's emotions and to quickly share the results.

[0582] An "image acquisition means" is a mechanism for capturing video data in real time using a camera or sensor.

[0583] "Scene analysis means" refers to a technology that analyzes acquired image data to identify landscapes, people, objects, etc.

[0584] The "composition calculation method" is a method for calculating the appropriate screen layout for shooting based on the analysis results.

[0585] A "guideline display device" is a device that provides real-time visual instructions to help users choose the optimal shooting composition.

[0586] "Shooting control means" refers to a function that controls the camera's shutter based on user instructions or system judgment.

[0587] "Individualized habit learning methods" are algorithms that learn the user's preferences and behaviors and provide optimal advice for future shooting opportunities.

[0588] "Emotional analysis methods" refer to technologies that recognize a user's facial expressions and analyze their emotional state.

[0589] A "video display means" is a display device that visually presents images captured by a camera or guidelines to the user.

[0590] "Emotional state-based composition adjustment means" refers to a function that dynamically adjusts the shooting composition according to the user's emotions.

[0591] An "automatic sharing method" is a system that automatically uploads photos taken to social media and other platforms based on user instructions.

[0592] This invention is a system that enables optimal photography and automatic sharing in response to the user's emotions. The system operates with a server and a terminal working in cooperation. Specifically, it uses the camera and display installed in the terminal to analyze the user's facial expressions in real time and adjust the shooting composition based on their emotional state.

[0593] The server uses image processing-based software (e.g., OpenCV) for sentiment analysis. Images captured by the camera are first captured on the terminal, and this image data is processed by a cloud-based sentiment recognition AI engine (e.g., AWS Rekognition). Once the user's emotions are analyzed, the data is used by a composition calculation system to optimize the shooting. The composition is displayed in real time through a video display system and provided as a guide.

[0594] If the user positions themselves according to this guide, the camera control system will automatically activate the shutter and capture the perfect moment. After the photo is taken, the server uses an automatic sharing system to quickly upload the captured photo to the selected social media platform. This makes it easy for users to share the photo that best fits their emotions.

[0595] As a concrete example, when a user tries on new clothes in a fitting room, the system captures the moment they smile at themselves in the mirror and automatically takes a photo. This photo is immediately displayed on the device, and the user can choose to post it to social media right then and there. This automated process allows users to instantly share wonderful moments, saving them time and effort.

[0596] An example of a prompt using a generative AI model is: "We want to develop a smart mirror application that captures photos of moments when the user is filled with joy and confidence. Please propose a system that uses facial expression analysis technology to provide real-time instructions for the optimal timing to take a photo."

[0597] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0598] Step 1: The device activates the camera and captures images, including the user's face, in real time. The input is the camera video, and the output is face image data. This image data is secured using the acquisition means.

[0599] Step 2: The device transmits the acquired image data to the emotion analysis system. The input is facial image data, and the output is emotional state. The device uses an emotion recognition AI engine to analyze facial expressions and identify the user's emotions.

[0600] Step 3: The server uses emotional state and image data to calculate the optimal composition for the photograph using a composition calculation tool. The input is emotional state and facial image data, and the output is composition data. Based on this, the server formulates a visually effective composition.

[0601] Step 4: The server sends composition data to the terminal, and the terminal overlays the guides onto the video display via the guideline display means. The input is composition data, and the output is a visual display of the guidelines. The user adjusts the camera angle and position based on this.

[0602] Step 5: Once the user follows the guidelines and finds a good position, the device automatically takes a picture using the shooting control mechanism. The input is the optimized position information, and the output is the captured photo data.

[0603] Step 6: The server uses individual habit learning methods to analyze the captured photo data and its emotional correspondence, and learns the user's preferences for future use. The input is photo data and emotional state, and the output is the learned user model.

[0604] Step 7: The server processes the captured photo data using an automated sharing mechanism and uploads it to social media platforms. The input is the photo data, and the output is the content shared online. Through this process, users can instantly share photos that match their emotions.

[0605] 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.

[0606] 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.

[0607] 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.

[0608] [Fourth Embodiment]

[0609] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0610] 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.

[0611] 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).

[0612] 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.

[0613] 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.

[0614] 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).

[0615] 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.

[0616] 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.

[0617] 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.

[0618] 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.

[0619] 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.

[0620] 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.

[0621] 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".

[0622] This photography assistance system primarily consists of terminals and servers, providing users with a professional photography experience with great composition.

[0623] First, the device captures images in real time through its camera function, serving as an image acquisition tool. The captured images are immediately sent to a scene analysis tool, where elements such as landscapes, people, and objects are identified. This analysis utilizes a machine learning model.

[0624] After analysis, the terminal sends the analysis data to the server, which uses a composition calculation tool to generate optimal composition candidates. These compositions are based on various artistic rules of photography, such as the rule of thirds, the golden ratio, and diagonal composition.

[0625] Composition candidates are sent to the terminal using a guideline display mechanism. The terminal overlays these on the camera view in real time, supporting the user in easily adjusting the camera angle.

[0626] Users can adjust the camera position and subject while viewing guidelines displayed on their device. Once the optimal composition is achieved, the automatic shutter control system activates. This allows users to take high-quality photos without consciously thinking about it.

[0627] Furthermore, the server is equipped with individual habit learning capabilities that learn from the user's choices and shooting history. This information is used to create composition suggestions for future shoots, providing personalized shooting guides tailored to the user's preferences.

[0628] A concrete example of its use is when a user wants to take a special photo at a tourist destination. Simply activating the camera will automatically analyze the landscape and people, suggesting the optimal composition. The user only needs to operate the camera according to the guidelines to obtain professional-looking photos. In this way, anyone can take high-quality photos without any technical knowledge.

[0629] The following describes the processing flow.

[0630] Step 1:

[0631] The device activates the camera and prepares to capture the scene the user wants to photograph in real time. Video data from the camera is acquired sequentially and stored in memory in an analyzable format.

[0632] Step 2:

[0633] The terminal sends the acquired image to a scene analysis system. This system uses a dedicated machine learning model to recognize landscapes, people, and objects in the image. The analysis results include the position and identification information of each element.

[0634] Step 3:

[0635] The terminal sends the analysis results to the server. The server activates the composition calculation mechanism based on the received data. The composition calculation mechanism generates optimal composition candidates using the rule of thirds or the golden ratio based on the analyzed image elements.

[0636] Step 4:

[0637] The server sends the calculated composition candidates to the terminal. Each composition candidate includes guideline information indicating how the camera should be positioned and the subject laid out.

[0638] Step 5:

[0639] When the device receives a composition suggestion, it overlays AR guidelines onto the camera view. The user can then adjust the camera angle and subject position according to the guidelines.

[0640] Step 6:

[0641] When the user has adjusted the composition according to the guidelines, the device detects that the composition is properly positioned. Subsequently, the shooting control means automatically activates the shutter and takes a photograph.

[0642] Step 7:

[0643] The server learns the user's composition choices and shooting style based on the captured data. Using individual habit learning methods, it provides personalized composition suggestions based on the user's preferences for future shoots.

[0644] (Example 1)

[0645] 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".

[0646] In recent years, advancements in photography technology have created a demand for anyone to take high-quality photographs. However, it remains difficult for users lacking experience and expertise to capture professional-quality images. In particular, effectively judging composition and shooting conditions is challenging, often resulting in unsatisfactory results. Therefore, there is a need to develop support systems that allow users to easily utilize professional photography techniques.

[0647] 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.

[0648] In this invention, the server includes an image acquisition means, a scene analysis means, and a composition calculation means. This allows users to easily take high-quality photographs with excellent image composition, regardless of their shooting experience or technical knowledge.

[0649] "Image acquisition means" refers to a function that allows the user to capture images in real time using a camera and record those images.

[0650] "Scene analysis means" refers to a function that uses a machine learning model to identify landscapes, people, and objects in acquired images.

[0651] The "analysis data transmission means" is a communication function for sending analysis results generated based on scene analysis to a server.

[0652] The "composition calculation method" is a function that generates optimal composition candidates by applying artistic rules in photography based on the received analysis data.

[0653] The "guideline generation method" is a function that creates guidelines for visually presenting the generated composition candidates to the user.

[0654] The "guideline display means" is a function that overlays guidelines onto the camera view on the device, supporting users in making adjustments in real time.

[0655] "Shooting control means" refers to a function that automatically activates the shutter when the user adjusts the camera according to the optimal composition.

[0656] The "individual habit learning method" is a function that learns the user's shooting history and selected composition information, and provides a personalized shooting guide tailored to the user's preferences in subsequent shoots.

[0657] This photography assistance system is designed to allow users to easily take professional-quality photographs. The system primarily consists of terminals and a server.

[0658] When a user activates the device's camera, the device captures an image in real time using image acquisition equipment. The hardware used in this process is a typical smartphone or camera device. The captured image is immediately processed by scene analysis equipment. Here, machine learning models (e.g., YOLO or ResNet) are used to identify landscapes, people, objects, etc., in the image. This analysis extracts important image elements.

[0659] The analyzed data is sent from the terminal to the server. The server uses a composition calculation method to generate optimal composition candidates based on the received data. Artistic rules such as the rule of thirds, the golden ratio, and diagonal composition are integrated into the composition calculation, providing users with high-quality visual representation.

[0660] Subsequently, the server uses a guideline generation mechanism to create guidelines that visually communicate composition options to the user. These guidelines are sent to the terminal and overlaid on the camera view by a guideline display mechanism. The user can then adjust the camera position and angle according to these guidelines.

[0661] Furthermore, the system includes a shooting control mechanism that automatically activates the shutter once the user has adjusted the camera according to the guidelines. This ensures that high-quality, well-balanced photographs are taken.

[0662] Furthermore, the server uses individual habit learning methods to learn the user's shooting history and preferences, and improves the user experience by suggesting personalized composition options for subsequent shoots.

[0663] For example, if a user wants to capture a special memory in a photograph at a tourist destination, simply launching the camera will automatically analyze the environment and suggest the optimal composition. By inputting example prompts such as "Please suggest guidelines for taking professionally composed landscape photographs at a tourist destination" into the AI ​​model, users can easily obtain professionally composed photos.

[0664] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0665] Step 1:

[0666] The device activates its camera function and captures images in real time using an image acquisition method. In this step, each time the user presses the camera's shutter button, light information is acquired from the camera sensor and saved as a digital image. The input is light information from the camera sensor, and the output is digitized image data.

[0667] Step 2:

[0668] The terminal transmits the captured image to a scene analysis system. The scene analysis system utilizes a machine learning model to identify different elements (landscape, people, objects) contained in the image. The input is digital image data, and the output is analysis result data after each element has been identified. Models such as YOLO and ResNet are used for this analysis.

[0669] Step 3:

[0670] The terminal sends the analysis results to the server using an analysis data transmission method. Here, data is sent to the server via the network using protocols such as HTTP. The input is the analysis result data, and the output is a notification of successful transmission to the server.

[0671] Step 4:

[0672] The server generates optimal composition candidates using a composition calculation method based on the received analysis data. The input is analysis data, and the output is data of composition candidates derived from the rule of thirds, the golden ratio, diagonal composition, etc. A generation AI model is used to evaluate multiple composition patterns and select the most appropriate one.

[0673] Step 5:

[0674] The server uses a guideline generation mechanism to create guidelines for communicating composition candidates to the user. The input is data of composition candidates, and the output is guideline data that can be displayed on the terminal. These guidelines must be in a visually interpretable format.

[0675] Step 6:

[0676] The device uses a guideline display mechanism to overlay the received composition guidelines onto the camera view. The input is guideline data, and the output is a real-time display of the guidelines on the camera view. The user checks the grids, circles, lines, and other guides displayed on the screen and adjusts the camera position and angle.

[0677] Step 7:

[0678] When the user aligns the camera position and angle with the guidelines, the device's shooting control system activates the automatic shutter. The input is the adjusted camera settings and position information, and the output is the final image captured by the shutter activation. This allows the user to take photos with optimal composition without consciously thinking about it.

[0679] Step 8:

[0680] The server uses individual habit learning methods to analyze the user's shooting history and preferences, preparing to suggest a personalized shooting guide for the next shoot. The input is shooting history data, and the output is an updated user profile based on that history. This ensures that compositions that better suit the user's preferences are more accurately reflected in the next shoot.

[0681] (Application Example 1)

[0682] 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".

[0683] In autonomous vehicles, there is a lack of means to automatically record beautiful scenery and travel events in the optimal composition, leading to the challenge of users missing recording opportunities while driving. Therefore, there is a need for a system that can easily acquire professional-quality images or videos while driving without compromising the scenery.

[0684] 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.

[0685] In this invention, the server includes a scene analysis means, a composition calculation means, and a driving support means that automatically calculates a composition suitable for the driving environment. This makes it possible for the user to record images and videos with the optimal composition automatically, without missing any beautiful scenery while driving.

[0686] An "image acquisition means" is a device that has the function of acquiring images of the environment or subject in real time using a camera or sensor.

[0687] A "scene analysis device" is a device that utilizes computer vision technology to analyze acquired images and identify features such as landscapes, people, and objects.

[0688] A "composition calculation device" is a device that generates optimal composition candidates based on the results of scene analysis, following artistic rules such as the rule of thirds, the golden ratio, and diagonal composition.

[0689] A "guideline display device" is a display device that visually presents the calculated optimal composition to the user and assists in adjusting the camera's composition.

[0690] A "shooting control means" is a device that automatically controls the shutter when the optimal composition is obtained, and records images or videos.

[0691] A "personalized habit learning tool" is a device that learns a user's shooting history and preferences, and uses that information to personalize future shooting guides.

[0692] A "driving support system" is a device that calculates the optimal composition in real time within the driving environment of an autonomous vehicle and automatically records the scenery.

[0693] A "recording device" is a device that has the function of saving acquired images and videos as digital data.

[0694] To realize this invention, the system uses image acquisition means, scene analysis means, composition calculation means, guideline display means, shooting control means, individual habit learning means, driving support means, and recording means.

[0695] The server receives image data acquired in real time using the camera and analyzes it using scene analysis tools. The analysis uses computer vision technology and machine learning models (e.g., a subject recognition model using TensorFlow) to identify landscapes and objects.

[0696] Based on the scene analysis results, the composition calculation system calculates the optimal composition according to rules such as the rule of thirds, the golden ratio, and diagonal composition. This composition information is adjusted to the user's preferences and presented to the device via a guideline display system.

[0697] On the device, these guidelines are overlaid on display media such as smart head-mounted displays, making it easier for users to grasp the optimal composition. Furthermore, driving assistance systems automatically perform these processes while the autonomous vehicle is in motion, helping to ensure that the scenery is not missed.

[0698] After the user confirms the optimal composition, the shutter is automatically activated by the shooting control means, and the image or video is saved to the recording means in high quality. Furthermore, the individual habit learning means learns the user's shooting data and builds a database to suggest personalized compositions.

[0699] For example, if you want to take a picture of a beautiful sunset while driving an autonomous vehicle, this system allows you to take a photo with the optimal composition without getting out of the car, and save the record to the in-vehicle system.

[0700] An example of a prompt message for a generating AI model might be: "Based on the image captured by the in-car camera, perform real-time scene analysis, calculate the optimal photographic composition, and display it as an overlay."

[0701] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0702] Step 1:

[0703] The device uses its camera to acquire images in real time. These images are processed as input data. Image data from the camera is acquired in streaming format and sent to the system.

[0704] Step 2:

[0705] The server analyzes the received image data using scene analysis tools. Here, it uses generative AI models and machine learning models to recognize subjects and backgrounds. This data processing outputs information identifying landscapes and objects.

[0706] Step 3:

[0707] The server calculates the optimal composition using a composition calculation method based on the analysis results. Using the specific information obtained as input, it calculates the optimal composition based on the rule of thirds, the golden ratio, and diagonal composition. A composition guide calculated through this process is then output.

[0708] Step 4:

[0709] The device uses a guideline display mechanism to visualize the calculated composition guide to the user. Using composition guide information as input, the guidelines are overlaid and displayed on a smart head-mounted display.

[0710] Step 5:

[0711] The user adjusts the camera position according to the guidelines. After the user has properly aligned the camera, a confirmation signal is output from the device, and the process proceeds to the next step.

[0712] Step 6:

[0713] The device's shooting control mechanism activates, automatically pressing the shutter when the composition is complete. This allows the acquired image to be output to the recording device and saved in high quality.

[0714] Step 7:

[0715] The server's individual habit learning mechanism collects the user's shooting data and prepares personalized advice for the next shoot. This learning process generates guides as output data tailored to the user's preferences.

[0716] 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.

[0717] This photo-taking assistance system, which incorporates an emotion engine, works in conjunction with a terminal and server to recognize the user's emotional state in real time and provide a photo-taking experience that takes that into account.

[0718] First, the device activates its camera and captures images in real time. During this process, the image acquisition mechanism works to collect image data from the camera view, and at the same time, it receives the user's facial expressions as input data for the emotion engine. The emotion engine uses facial expression analysis technology to analyze the user's emotional state.

[0719] The analyzed emotion data is sent to the server along with scene information acquired by the scene analysis means. Based on this, the server uses a composition calculation means to generate a composition suitable for the user's emotional state. For example, when the user is expressing feelings of joy, a composition that emphasizes a bright background or a wide sky is recommended.

[0720] The generated composition candidates are transmitted to the terminal in real time via a guideline display mechanism. The terminal overlays these on the camera view, and the user adjusts the camera angle according to the guide. During this process, the emotion engine continuously monitors the user's facial expressions and can dynamically adjust the composition in response to changes in emotion.

[0721] Once the user positions themselves according to the guidelines, the camera control system automatically activates the shutter, capturing a professional photograph that resonates with their emotions. During this process, a personalized learning system learns the user's composition choices and emotional responses, providing more accurate and personalized suggestions for future use.

[0722] As a concrete example of its use, when a user takes photos at a birthday party, the emotion engine recognizes the user's smile, and the composition calculation means provides a composition that recommends a bright color tone and wide-angle lens effect that matches it. In this way, the user can capture special moments in photographs that are optimized for the atmosphere of the moment. This system allows users to easily take emotionally appealing photos without having to consciously think about technology or environmental judgments.

[0723] The following describes the processing flow.

[0724] Step 1:

[0725] The device begins acquiring real-time image data as soon as the user launches the camera app. The image data is converted to a format suitable for system processing and stored in memory.

[0726] Step 2:

[0727] The device also captures the user's facial expressions through its camera and inputs them into the emotion engine. The emotion engine uses a facial expression analysis algorithm to recognize the user's current emotional state in real time.

[0728] Step 3:

[0729] The device's scene analysis mechanism identifies scene elements within the captured image, such as landscapes and people. This clarifies areas of interest within the image.

[0730] Step 4:

[0731] The terminal sends the scene analysis results and the emotion engine analysis results to the server. The server analyzes this data and generates composition candidates that take into account the user's emotions and the characteristics of the scene.

[0732] Step 5:

[0733] The server's composition calculation method uses the rule of thirds and the golden ratio to calculate compositions that are appropriate for the user's emotions. For example, if the user is enjoying themselves, a bright and open composition will be prioritized.

[0734] Step 6:

[0735] The terminal receives composition candidates sent from the server and overlays them on the camera view using a guideline display mechanism. This allows the user to easily match the ideal composition with real-time guidance.

[0736] Step 7:

[0737] The user adjusts the camera and subject according to the guidelines, and is guided to achieve the desired composition. During this time, the emotion engine continuously monitors the user's facial expressions.

[0738] Step 8:

[0739] The device activates its shooting control mechanism and automatically takes a picture when the user's actions match the guidelines. This ensures that the optimal moment is accurately recorded as a photograph.

[0740] Step 9:

[0741] The server analyzes the captured data and stores the user's emotional state and composition selection history as training data. This enables more personalized suggestions in subsequent shooting sessions.

[0742] (Example 2)

[0743] 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".

[0744] Conventional photo-taking assistance systems have difficulty taking into account the user's emotional state, making it challenging to capture emotional moments in photographs. Furthermore, they lacked sufficient functionality to learn individual user shooting habits and apply that knowledge to future shoots.

[0745] 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.

[0746] In this invention, the server includes a facial expression analysis means, an emotional state analysis means, and an individual habit learning means. This enables the automatic generation of compositions based on the user's emotional state and personalized shooting support based on the learning of shooting habits.

[0747] "Image acquisition means" refers to a function that acquires image data in real time using a camera or other image sensor.

[0748] "Facial expression analysis means" refers to analysis technology for identifying a user's facial expressions and estimating their emotions.

[0749] "Emotional state analysis means" is a technology that identifies a user's emotional state based on analyzed facial expression data.

[0750] A "scene analysis tool" is a function that analyzes scene information within an image, and is used to recognize the subject and determine the surrounding environment.

[0751] The "composition calculation means" is a function that calculates the optimal composition for a photograph based on the user's emotional state and scene information.

[0752] A "guideline display mechanism" is a function that visually presents the calculated composition to the user and supports them in taking photos.

[0753] "Shooting control means" refers to a function that automatically operates the camera's shutter based on user instructions or system commands.

[0754] "Individualized habit learning method" is a technology that learns the user's past shooting data and preferences and makes optimal suggestions for future shooting sessions.

[0755] The photographic assistance system of this invention includes an image acquisition means, a facial expression analysis means, an emotional state analysis means, a scene analysis means, a composition calculation means, a guideline display means, a shooting control means, and an individual habit learning means.

[0756] The device first activates its camera and captures images in real time using an image acquisition device. The device can be an imaging device such as a smartphone or digital camera. During this process, a facial expression analysis device analyzes the user's facial expressions using data obtained from the camera, and an emotional state analysis device identifies the user's emotional state. A generative AI model is used for this analysis to recognize emotions, such as when the user's facial expression is smiling.

[0757] The server uses a composition calculation tool to generate the optimal composition for shooting, based on the analyzed emotion data and scene information acquired by the scene analysis tool. For example, when the user is expressing joy, a bright and open composition is selected. The AI ​​model used by the server can perform calculations utilizing the high processing power of the cloud.

[0758] The device then overlays composition information sent from the server onto the camera view using a guideline display mechanism, guiding the user to the optimal angle and framing. Based on these guidelines, the user can adjust the camera position and angle to capture emotionally resonant and appealing photos. Once adjustments are complete, the shooting control mechanism automatically activates the shutter.

[0759] Furthermore, the individual habit learning mechanism learns from the user's shooting data and accumulates data to provide more personalized suggestions for subsequent shoots. A generative AI model is also used in this learning process.

[0760] As a concrete example, consider a scenario where a user takes a photo during a birthday party. After the emotion engine analyzes the user's smile, the server suggests a wide-angle composition with bright colors. This photo-taking experience is made possible by a prompt message that says, "Detect the user's smile and suggest a composition based on bright colors." This system allows users to capture special moments emotionally in photographs, even without technical knowledge.

[0761] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0762] Step 1:

[0763] The device activates its camera and captures image data in real time. The input is image information from the camera, and the image acquisition means processes this information to output a series of image data. Specifically, the smartphone's camera sensor works to capture images in real time in accordance with the user's movements.

[0764] Step 2:

[0765] A facial expression analysis system, which receives image data as input, analyzes the user's facial expressions using a generative AI model. This analysis outputs data indicating the user's emotional state. Specifically, the AI ​​model analyzes facial patterns within the image and generates emotion labels such as smiles or surprises.

[0766] Step 3:

[0767] The server receives emotional data from the facial expression analysis means as input, analyzes it with the emotional state analysis means, and evaluates the user's overall emotional state. Furthermore, the scene analysis means processes the image data and obtains scene information. Using this data, the server calculates the optimal composition and outputs composition data with the composition calculation means. Specifically, the server utilizes cloud-based processes to propose a composition based on scene characteristics and emotional state.

[0768] Step 4:

[0769] Using composition data transmitted from the server as input, the terminal overlays a composition guide onto the camera view using a guideline display mechanism. The user adjusts the camera position and angle based on this guide and prepares to shoot. Specifically, a transparent composition guide is displayed on the terminal's screen, and the user moves the camera accordingly.

[0770] Step 5:

[0771] After the user completes the camera settings according to the composition guide, the shooting control system activates and the shutter is automatically released. This operation automatically takes photos that reflect the user's emotions without any user input. Specifically, the camera saves the image based on pre-set timings and conditions.

[0772] Step 6:

[0773] Using the captured data as input, a personalized habit learning system analyzes the user's shooting habits and learns from the data to optimize future shots. During this process, a generative AI model is used, accumulating past preference data to update the learning model. This is then reflected in the composition suggestions provided to the user for the next shoot.

[0774] (Application Example 2)

[0775] 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".

[0776] Conventional photo-taking systems have the drawback of making it difficult to adjust the timing and composition of shots based on the user's emotions, and also failing to allow for immediate sharing of captured photos on social media. Therefore, it is difficult to efficiently capture moments that emotionally satisfy the user.

[0777] 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.

[0778] In this invention, the server includes emotion analysis means, video display means, composition adjustment means based on emotional state, and automatic sharing means. This makes it possible to perform optimal shooting according to the user's emotions and to quickly share the results.

[0779] An "image acquisition means" is a mechanism for capturing video data in real time using a camera or sensor.

[0780] "Scene analysis means" refers to a technology that analyzes acquired image data to identify landscapes, people, objects, etc.

[0781] The "composition calculation method" is a method for calculating the appropriate screen layout for shooting based on the analysis results.

[0782] A "guideline display device" is a device that provides real-time visual instructions to help users choose the optimal shooting composition.

[0783] "Shooting control means" refers to a function that controls the camera's shutter based on user instructions or system judgment.

[0784] "Individualized habit learning methods" are algorithms that learn the user's preferences and behaviors and provide optimal advice for future shooting opportunities.

[0785] "Emotional analysis methods" refer to technologies that recognize a user's facial expressions and analyze their emotional state.

[0786] A "video display means" is a display device that visually presents images captured by a camera or guidelines to the user.

[0787] "Emotional state-based composition adjustment means" refers to a function that dynamically adjusts the shooting composition according to the user's emotions.

[0788] An "automatic sharing method" is a system that automatically uploads photos taken to social media and other platforms based on user instructions.

[0789] This invention is a system that enables optimal photography and automatic sharing in response to the user's emotions. The system operates with a server and a terminal working in cooperation. Specifically, it uses the camera and display installed in the terminal to analyze the user's facial expressions in real time and adjust the shooting composition based on their emotional state.

[0790] The server uses image processing-based software (e.g., OpenCV) for sentiment analysis. Images captured by the camera are first captured on the terminal, and this image data is processed by a cloud-based sentiment recognition AI engine (e.g., AWS Rekognition). Once the user's emotions are analyzed, the data is used by a composition calculation system to optimize the shooting. The composition is displayed in real time through a video display system and provided as a guide.

[0791] If the user positions themselves according to this guide, the camera control system will automatically activate the shutter and capture the perfect moment. After the photo is taken, the server uses an automatic sharing system to quickly upload the captured photo to the selected social media platform. This makes it easy for users to share the photo that best fits their emotions.

[0792] As a concrete example, when a user tries on new clothes in a fitting room, the system captures the moment they smile at themselves in the mirror and automatically takes a photo. This photo is immediately displayed on the device, and the user can choose to post it to social media right then and there. This automated process allows users to instantly share wonderful moments, saving them time and effort.

[0793] An example of a prompt using a generative AI model is: "We want to develop a smart mirror application that captures photos of moments when the user is filled with joy and confidence. Please propose a system that uses facial expression analysis technology to provide real-time instructions for the optimal timing to take a photo."

[0794] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0795] Step 1: The device activates the camera and captures images, including the user's face, in real time. The input is the camera video, and the output is face image data. This image data is secured using the acquisition means.

[0796] Step 2: The device transmits the acquired image data to the emotion analysis system. The input is facial image data, and the output is emotional state. The device uses an emotion recognition AI engine to analyze facial expressions and identify the user's emotions.

[0797] Step 3: The server uses emotional state and image data to calculate the optimal composition for the photograph using a composition calculation tool. The input is emotional state and facial image data, and the output is composition data. Based on this, the server formulates a visually effective composition.

[0798] Step 4: The server sends composition data to the terminal, and the terminal overlays the guides onto the video display via the guideline display means. The input is composition data, and the output is a visual display of the guidelines. The user adjusts the camera angle and position based on this.

[0799] Step 5: Once the user follows the guidelines and finds a good position, the device automatically takes a picture using the shooting control mechanism. The input is the optimized position information, and the output is the captured photo data.

[0800] Step 6: The server uses individual habit learning methods to analyze the captured photo data and its emotional correspondence, and learns the user's preferences for future use. The input is photo data and emotional state, and the output is the learned user model.

[0801] Step 7: The server processes the captured photo data using an automated sharing mechanism and uploads it to social media platforms. The input is the photo data, and the output is the content shared online. Through this process, users can instantly share photos that match their emotions.

[0802] 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.

[0803] 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.

[0804] 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.

[0805] 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.

[0806] 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.

[0807] 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.

[0808] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0809] 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.

[0810] 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."

[0811] 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.

[0812] 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.

[0813] 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.

[0814] 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.

[0815] 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.

[0816] 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.

[0817] 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.

[0818] 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.

[0819] 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.

[0820] 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.

[0821] 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.

[0822] 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 as being incorporated by reference.

[0823] The following is further disclosed regarding the embodiments described above.

[0824] (Claim 1)

[0825] Image acquisition method,

[0826] Scene analysis means,

[0827] Composition calculation means,

[0828] Guideline display means and

[0829] A means for controlling the shooting,

[0830] Individual habit-based learning methods,

[0831] A photography assistance system including...

[0832] (Claim 2)

[0833] The photography assistance system according to claim 1, characterized in that the scene analysis means uses a subject recognition model to identify landscapes, people, and objects.

[0834] (Claim 3)

[0835] The photography assistance system according to claim 1, characterized in that the composition calculation means generates composition candidates based on the rule of thirds, the golden ratio, and diagonal composition.

[0836] "Example 1"

[0837] (Claim 1)

[0838] Image acquisition method,

[0839] Scene analysis means,

[0840] means for transmitting analysis data,

[0841] Composition calculation means,

[0842] Guideline generation method,

[0843] Guideline display means and

[0844] A means for controlling the shooting,

[0845] Individual habit-based learning methods,

[0846] A system that includes this.

[0847] (Claim 2)

[0848] The system according to claim 1, characterized in that the scene analysis means uses a machine learning model to identify landscapes, people, and objects.

[0849] (Claim 3)

[0850] The system according to claim 1, characterized in that the composition calculation means generates composition candidates based on artistic rules in photography.

[0851] "Application Example 1"

[0852] (Claim 1)

[0853] Image acquisition method,

[0854] Scene analysis means,

[0855] Composition calculation means,

[0856] Guideline display means and

[0857] A means for controlling the shooting,

[0858] Individual habit-based learning methods,

[0859] A driving support system that automatically calculates a composition suitable for the driving environment,

[0860] A means of recording the acquired scenery,

[0861] A system that includes this.

[0862] (Claim 2)

[0863] The system according to claim 1, characterized in that the scene analysis means uses a subject recognition model to identify landscapes, people, and objects.

[0864] (Claim 3)

[0865] The system according to claim 1, characterized in that the composition calculation means generates composition candidates based on the rule of thirds, the golden ratio, and diagonal composition, and the driving support means obtains the optimal scenery while driving.

[0866] "Example 2 of combining an emotion engine"

[0867] (Claim 1)

[0868] Image acquisition method,

[0869] A means for analyzing facial expressions,

[0870] Methods for analyzing emotional states,

[0871] Scene analysis means,

[0872] Composition calculation method,

[0873] Guideline display means and

[0874] A means for controlling the shooting,

[0875] Individual habit learning methods,

[0876] A system that includes this.

[0877] (Claim 2)

[0878] The system according to claim 1, characterized in that the facial expression analysis means analyzes the user's emotions using a generative AI model.

[0879] (Claim 3)

[0880] The system according to claim 1, characterized in that the composition calculation means generates composition candidates based on the user's emotional state.

[0881] "Application example 2 when combining with an emotional engine"

[0882] (Claim 1)

[0883] Image acquisition method,

[0884] Scene analysis means,

[0885] Composition calculation means,

[0886] Guideline display means and

[0887] A means for controlling the shooting,

[0888] Individual habit-based learning methods,

[0889] Emotional analysis methods,

[0890] A means of displaying images,

[0891] A means of adjusting composition based on emotional state,

[0892] Automatic sharing methods,

[0893] A system that includes this.

[0894] (Claim 2)

[0895] The system according to claim 1, characterized in that the scene analysis means uses a subject recognition model to identify landscapes, people, and objects.

[0896] (Claim 3)

[0897] The system according to claim 1, characterized in that the composition calculation means generates composition candidates based on the rule of thirds, the golden ratio, and diagonal composition. [Explanation of Symbols]

[0898] 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. An image acquisition method that captures images in real time using a camera, A scene analysis means that analyzes acquired images and identifies elements such as landscapes, people, and objects contained within them, A composition calculation means that generates optimal composition candidates based on the analyzed elements, A guideline display means that displays guidelines in the camera view based on the generated composition candidates, A shooting control means that detects when the user has positioned the camera to the optimal composition and automatically activates the shutter, A personalized habit learning method that learns user behavior and preferences, A photography assistance system including...

2. The photography assistance system according to claim 1, characterized in that the scene analysis means uses a subject recognition model to identify landscapes, people, and objects.

3. The photography assistance system according to claim 1, characterized in that the composition calculation means generates composition candidates based on the rule of thirds, the golden ratio, and diagonal composition.

Images