system

Abstract

We provide the system. [Solution] A means of capturing the baby's visual data, An analysis means for analyzing the degree of gaze and facial expressions of a baby based on captured visual data, A means for generating videos for babies based on analysis, A means of presenting the generated video to the baby, A system that includes this.

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, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] When parents with a baby utilize videos in child-rearing, they cannot determine which video content is preferred by the baby and need to change the videos many times to find appropriate content. This problem places a heavy burden on the parents and causes the problem that effective utilization of videos cannot be achieved by continuously watching content that the baby is not interested in.

Means for Solving the Problems

[0005] To solve this problem, the present invention provides a system that captures a baby's visual data and uses that data to analyze the baby's gaze and facial expressions. Based on the analysis results, it generates and presents personalized videos for babies, thereby attracting the baby's interest while allowing parents to easily provide appropriate content. Furthermore, by identifying the frequency of the baby's smiles, it provides a means to perform more accurate analysis and continuously improve the video generation process using machine learning.

[0006] "Means of capture" refers to cameras and other sensor devices used to acquire visual data from a baby.

[0007] "Analysis means" refers to algorithms and software used to analyze the degree of gaze and facial expressions of a baby based on visual data acquired by the imaging means.

[0008] "Generation method" refers to generation algorithms and software that use analysis results to automatically create video content for babies.

[0009] "Presentation means" refers to output devices such as display devices or projectors used to show the generated video content to the baby.

[0010] "Visual data" refers to video information including the baby's face, expressions, and movements, and is the basic data used for analysis.

[0011] "Attention level" is an index that measures the amount of time a baby is focused on a video and the degree to which their gaze is fixed.

[0012] "Facial expressions" refer to the movements of the facial muscles and the overall look of a baby's face, which indicate their emotional state and reactions, and include expressions such as smiles and surprise.

[0013] "Smile frequency" is an indicator that refers to the number of times a baby smiles within a certain period of time, and the frequency of those smiles.

[0014] "Personalized videos" are video content customized to suit each baby's individual interests and preferences.

[0015] "Machine learning" is a technique that uses large amounts of data to enable computer systems to build pattern recognition and predictive models, and in this invention, it is used to improve the video generation process. [Brief explanation of the drawing]

[0016] [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] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Mode for Carrying Out the Invention

[0017] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be described.

[0019] 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.

[0020] 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.

[0021] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] 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."

[0024] [First Embodiment]

[0025] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0034] 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.

[0035] 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.

[0036] 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".

[0037] As an embodiment of the present invention, a system that analyzes a baby's video viewing reactions in real time and generates personalized video content will be described. This system mainly consists of three elements: a terminal, a server, and a user.

[0038] The device is equipped with a camera to acquire visual data from the baby, capturing the baby's facial expressions and attention span in real time while they watch videos. This visual data is used to extract indicators such as the frequency of the baby's smiles and the duration of their interest.

[0039] Next, the device sends this analyzed data to a server. The server uses machine learning algorithms to analyze the data and understand the baby's preferences and interests. Based on this, the server uses generative AI to generate customized video content for the baby. This video is based on the baby's past reaction data and contains content that is expected to elicit smiles and attention.

[0040] The generated videos are sent from the server to the device and played back by the device. In this way, the baby can watch video content that suits their preferences. The user (parent) performs the initial system setup and camera positioning, but the effort required for subsequent content selection is greatly reduced.

[0041] For example, if a baby responds well to images of animals, the server will generate a colorful video featuring many animals. Furthermore, if the baby shows interest in music, adding video content with musical elements can further engage them.

[0042] This system will provide a video experience optimized for babies, reducing the burden on parents.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The user places the baby in front of the TV and adjusts the camera angle and position to set it up so that the baby's face is properly visible.

[0046] Step 2:

[0047] The device activates its built-in camera and captures the baby's face in real time. It continuously acquires the baby's facial expressions and eye movements from the camera's video feed.

[0048] Step 3:

[0049] The device analyzes the video data it acquires and converts the frequency of the baby's smiles and the degree of their gaze into numerical data. This data serves as an indicator of the baby's level of concentration and interest.

[0050] Step 4:

[0051] The terminal packages the analyzed data at regular time intervals and sends the data to the server.

[0052] Step 5:

[0053] The server uses the received data to perform analysis using machine learning algorithms. To identify the baby's preferences, patterns such as the frequency of smiles and the duration of fixed gaze are analyzed.

[0054] Step 6:

[0055] The server uses AI generation to create personalized videos for babies based on analysis results. These videos are designed based on specific interests and preferences.

[0056] Step 7:

[0057] The server encodes the generated video and efficiently transmits it to the terminal in streaming format.

[0058] Step 8:

[0059] The device decodes and plays the received video, then presents it to the baby. The content displayed on the screen is optimized to capture the baby's attention.

[0060] Step 9:

[0061] The device recaptures the baby's reactions during playback, collecting new data on smiles and attention levels. This information is then reused in step 1.

[0062] (Example 1)

[0063] 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."

[0064] There is a challenge in optimizing the video content that babies watch, providing a personalized experience tailored to their preferences, and reducing the burden on parents in selecting content.

[0065] 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.

[0066] In this invention, the server includes a shooting means for capturing image information of a baby, an analysis means for analyzing the captured image information to identify the baby's facial expressions and degree of attention, and a generation means for generating a video including musical elements based on the analysis results. This makes it possible to automatically generate and provide high-quality video content while maintaining the baby's interest.

[0067] "Photography means" refers to the devices and technologies used to acquire image information of a baby.

[0068] "Analysis means" refers to devices and technologies that analyze a baby's facial expressions and gaze intensity from acquired image information, and use that data to identify their interests and preferences.

[0069] "Generation method" refers to a technology or system that automatically creates videos containing music elements optimized for babies, based on analyzed data.

[0070] "Presentation means" refers to devices or mechanisms used to show generated video content to babies.

[0071] "Learning methods" refer to technologies and methods that use past analysis data to reflect a baby's preferences and continuously improve the video generation process.

[0072] This invention relates to a system that personalizes a baby's video viewing experience and reduces the burden on parents. The system mainly consists of three elements: a server, a terminal, and a user.

[0073] First, the device is equipped with a camera that captures the baby's visual data in real time. This camera is used to capture the baby's facial expressions and attention span while they are watching videos. The visual data is quantified by image recognition software within the device, and indicators such as smiles and attention duration are extracted.

[0074] The extracted data is sent from the device to the server. The server analyzes this data using machine learning algorithms and generative AI models. As a result of the analysis, the baby's preferences and interests are identified.

[0075] Next, the server inputs prompt messages into an AI model based on the analysis results to create video content for babies. The generated content is individually optimized because it is based on the babies' reaction data. For example, prompt messages such as "Generate colorful animal videos to elicit smiles" or "Create a video that includes musical elements that babies will find interesting" are used.

[0076] The generated content is sent from the server to the device and played back by the baby. In this way, the baby can watch videos tailored to their individual interests. The parent, as the user, performs the initial setup of the system and adjusts the camera position, but during normal use, content is generated automatically, saving the parent the trouble of selecting content.

[0077] This makes it possible to provide babies with the best possible video viewing experience while reducing the burden on parents.

[0078] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0079] Step 1:

[0080] The device acquires the baby's visual data through its camera. Specifically, the device captures the baby's facial expressions and gaze points in real time. This input data, consisting of images and videos, is analyzed by image recognition software within the device and output as quantified facial expression and gaze intensity data.

[0081] Step 2:

[0082] The terminal transmits the quantified data obtained from the analysis to the server via a communication protocol. This transmitted data includes information such as the frequency of smiles and gaze duration. The server receives this output data as input for the next analysis stage.

[0083] Step 3:

[0084] The server uses the input numerical data to apply machine learning algorithms to identify the baby's preferences and interests. This data processing includes comparing it with a database of past viewing patterns and extracting elements that triggered specific reactions. This process outputs characteristic information tailored to the baby's interests.

[0085] Step 4:

[0086] The server uses a generative AI model based on the outputted characteristic information to create prompt statements and input them into the model. The generative AI model generates video content tailored to the baby according to these prompt statements. For example, it may include specific instructions such as, "Generate animal videos with bright colors." This generated content is then produced as output.

[0087] Step 5:

[0088] The server sends the generated video content to the device. This process utilizes communication technologies that ensure the security and speed of data transfer. The device then uses a media player to play the received video in high quality, providing the baby with a viewing experience. The output video is played in a way that is engaging and interesting to the baby.

[0089] Step 6:

[0090] The user (parent) performs the initial setup and camera positioning at the start of the system. This helps ensure that the baby's visual data is properly captured. In subsequent steps, the system automatically collects data and generates videos with minimal user intervention.

[0091] (Application Example 1)

[0092] 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."

[0093] When providing video content for babies, existing methods make it difficult to generate personalized content that accurately reflects the individual interests and reactions of each baby. To solve this problem, there is a need for a system that analyzes the baby's visual data in real time and provides the most suitable videos according to their interests and preferences.

[0094] 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.

[0095] In this invention, the server includes an acquisition means for acquiring visual data, an analysis means for analyzing gaze intensity and facial expressions based on the acquired visual data, and a generation means for identifying interest tendencies based on the analysis and generating personalized content. This makes it possible to provide video content based on the baby's interests.

[0096] "Visual data" refers to image information acquired by a camera, such as a baby's facial expressions and eye movements.

[0097] "Acquisition means" refers to the part that has the function of acquiring visual data using hardware such as a camera.

[0098] "Analysis means" refers to software or algorithms that process acquired visual data to identify the baby's gaze level, facial expressions, and interests.

[0099] The "generation method" refers to the part that has the functionality to create personalized video content based on the interest trends obtained through analysis.

[0100] "Presentation means" refers to a device or method for delivering generated video content to a user device and visually presenting it to a baby.

[0101] A "learning tool" is a machine learning model that utilizes past visual data and its analysis results to continuously optimize the video content generation process.

[0102] This invention relates to a system that acquires a baby's visual data in real time, analyzes it, and generates personalized videos. The system is mainly composed of three components: a terminal, a server, and a user.

[0103] The device is equipped with a camera that captures the baby's facial expressions and gaze as visual data. This data is then analyzed using software built into the device to extract the baby's gaze intensity and facial characteristics. The hardware used includes smart devices with cameras (e.g., smartphones and tablets), and the software utilizes the OpenCV image processing library.

[0104] The visual data is then sent to a server for more advanced analysis. On the server, machine learning algorithms are used to learn the baby's interests and preferences by comparing them with the baby's past response data. Tensorflow® and Scikit-learn are used for machine learning. Based on these analysis results, a generative AI model generates customized video content for babies. The generated videos emphasize features that babies are likely to be interested in. For example, if the baby likes animal videos or music, videos containing these elements will be created. An example of a specific prompt might be, "Generate an animal video for babies, adding elements that will make the baby smile. Please also consider music."

[0105] The generated video is returned from the server to the device and presented to the baby in the visual environment set by the user. The user performs initial setup and camera position adjustments, but subsequent operations are basically performed automatically between the server and the device, significantly reducing the effort required from the user.

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

[0107] Step 1:

[0108] The device uses a camera to acquire visual data of the baby's facial expressions and gaze in real time. The input is an image of the baby's face, and the output is the captured visual data. The operation involves the camera continuously capturing video and storing that data in internal memory.

[0109] Step 2:

[0110] The device analyzes the baby's gaze intensity and facial expressions from visual data acquired using OpenCV. The input to this process is the visual data obtained in step 1, and the output is an index of gaze intensity and facial expression features. In terms of operation, an image processing algorithm is executed to detect landmark points on the face and analyze the frequency of smiles, etc.

[0111] Step 3:

[0112] The terminal sends the analyzed data to the server. The input is the data analyzed in step 2, and the output is a data packet in a format that the server can use for processing. The operation involves uploading the data to the server using a network protocol (e.g., HTTP).

[0113] Step 4:

[0114] The server uses a machine learning model to analyze the baby's interests based on the received data. The input for this step is the analysis data sent from the terminal, and the output is data indicating the types and tendencies of the baby's interests. The process involves using TensorFlow to perform statistical data processing and identify interest patterns by comparing them with past data.

[0115] Step 5:

[0116] The server generates video content based on the identified interest preferences using a generative AI model and outputs it as a file. The input for this procedure is the analysis results from step 4, and the output is a video file of the content. In terms of operation, prompt text is provided to the model, and it automatically generates a video containing recommended video elements.

[0117] Step 6:

[0118] The server sends the generated video content to the terminal. The input is the video file generated in step 5, and the output is video data that the device can visualize. The operation involves delivering video data packets to the terminal over the network.

[0119] Step 7:

[0120] The device presents the received video content to the baby. The input is video data sent from the server, and the output is visual content played on the device. The operation includes playing the video file in a media player and displaying it on the screen.

[0121] 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.

[0122] As an embodiment of the present invention, a system that analyzes the emotions of both the baby and the user (parent) and provides personalized video content will be described. This system consists of three elements: a terminal, a server, and a user, and in particular incorporates an emotion engine to recognize and analyze emotions.

[0123] The device captures the baby's face with a camera and collects visual data in real time. This data includes the baby's facial expressions, eye movements, and frequency of smiles. The device also simultaneously captures the parent's facial expressions and acquires the parent's emotional data as needed. This emotional data is analyzed by an emotion engine, which includes a multi-layer neural network, to identify the parent's emotional state.

[0124] Next, the server uses an emotion engine to perform in-depth analysis on the received data. Based on the user's emotional data and the baby's visual data, it comprehensively evaluates the state of both the parent and the baby. Based on this evaluation, it generates content that is beneficial to both parent and child, including not only videos suitable for the baby but also videos that soothe (or uplift) the parent's emotions.

[0125] The generated videos are sent from the server to the device and presented in a way that is optimal for the baby. For example, if the baby responds well to videos of animals and the parent appears relaxed, the server will generate a video that includes scenes of animals acting happily, with background music designed to further relax the user. On the other hand, if the baby does not respond or the parent appears stressed, these elements will be adjusted and new content will be presented.

[0126] This system can provide an optimal video experience that simultaneously considers the baby's reactions and the user's emotional state, reducing the stress of choosing videos for childcare and enhancing the happiness of both parent and child.

[0127] The following describes the processing flow.

[0128] Step 1:

[0129] The user prepares the system. They position the baby in front of the television, ensuring the parent is also within the same field of view. This ensures that both faces are clearly visible to the camera, allowing for accurate data collection.

[0130] Step 2:

[0131] The device activates the camera and captures the baby's and user's faces in real time. The camera records facial expressions, gaze, and subtle movements as visual data.

[0132] Step 3:

[0133] The device instantly analyzes the visual data it captures, analyzing the baby's gaze intensity, facial expression data, and the user's emotions. The emotion engine identifies the emotional state from changes in facial expressions and determines indicators such as whether the user is excited or relaxed.

[0134] Step 4:

[0135] The device sends the analyzed data from both parties to the server. The data includes the baby's level of interest and the user's emotional state.

[0136] Step 5:

[0137] Based on the data received by the server, machine learning algorithms perform further in-depth analysis. This analyzes the characteristics of the video to optimize the baby's preferences and the parents' emotional state.

[0138] Step 6:

[0139] Based on the analysis results, the server uses a generation AI to create an ideal video for both the baby and the user. This is designed to help parents maintain positive emotions regarding their baby's reactions.

[0140] Step 7:

[0141] The server sends the newly generated video to the terminal in streaming format. This allows for real-time playback with minimal latency.

[0142] Step 8:

[0143] The device displays the transmitted video and continuously captures the baby's and user's reactions during playback to collect new data.

[0144] Step 9:

[0145] The device sends the collected data back to the server, creating a feedback loop that is used to generate the next video. By repeating this process, content tailored to the preferences of both parties can be continuously improved and provided.

[0146] (Example 2)

[0147] 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".

[0148] While systems have existed that provide video content based on a baby's emotions and reactions, there is a lack of systems that simultaneously consider the emotional states of both the baby and the parent to provide the optimal video experience for both parent and child. Considering the parent's emotional state can further enhance the happiness of both parent and child, but an effective method for achieving this is needed.

[0149] 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.

[0150] In this invention, the server includes a shooting means for capturing visual data of the baby and parent, an analysis means for analyzing the baby's gaze, facial expressions, and parent's emotions based on the captured visual data, and a generation means for generating videos for the baby and parent based on the analysis. This makes it possible to provide optimal video content that corresponds to the emotional state of both the baby and parent, reduce stress in childcare, and improve the happiness of both parent and child.

[0151] "Mechanisms of recording" refer to devices and technologies for capturing visual data of babies and their parents in real time.

[0152] "Analysis means" refers to devices and technologies used to evaluate the baby's gaze, facial expressions, and the parents' emotional state based on captured visual data.

[0153] "Generation means" refers to devices and technologies for creating optimal video content for babies and their parents based on analysis results.

[0154] "Presentation means" refers to devices or technologies for visually providing the generated video to the baby and its parents.

[0155] The system according to this invention is configured to simultaneously analyze the emotions of both the baby and the parent and provide optimal video content. The system mainly consists of two main components: a terminal and a server.

[0156] The device is equipped with a means of capturing real-time visual data of the baby and parent. Specifically, it uses a video camera or the camera function of a smartphone to capture the baby's facial expressions, eye movements, frequency of smiles, and the parent's facial expressions.

[0157] The server receives this visual data and analyzes it using an emotion engine. The emotion engine incorporates a multi-layer neural network and has the ability to identify the baby's gaze and facial expressions, as well as the parent's emotional state. Based on this analysis, a generative AI model is used to generate video content. The server then generates prompts based on the results and creates a customized video accordingly.

[0158] As a concrete example, if a baby is smiling and the parents are relaxed, the server will generate a prompt message such as, "We have detected a baby's smile and relaxed expression in the parents. Please generate a scene of animals happily performing with background music." This prompt is then input into the AI ​​generation model, which outputs the most suitable content.

[0159] The device receives the generated video sent from the server and presents it for the parent and child to watch. This allows for the provision of video content tailored to the emotional state of both parent and child, thereby reducing stress related to childcare and improving the happiness of both parent and child.

[0160] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0161] Step 1:

[0162] The device uses a camera to collect real-time visual data of the baby and parent. Specifically, it records the baby's facial expressions and eye movements, capturing the frequency of smiles and the direction of gaze. Simultaneously, it acquires facial expression data of the parent, collecting the characteristics of each face as data. The input for this step is real-time video footage, and the output is facial expression data of the baby and parent.

[0163] Step 2:

[0164] The server activates the emotion engine to analyze the received visual data. The emotion engine processes the input facial expression data using a multilayer neural network to identify the frequency and intensity of the baby's smiles, as well as the parents' emotional state. The input is the facial expression data obtained in step 1, and the output is the emotion data as a result of the analysis.

[0165] Step 3:

[0166] The server uses a generative AI model based on emotion data to create prompts for generating video content. Specifically, based on information such as "a baby's smile and a parent's relaxed expression were detected," it generates prompts containing appropriate video elements and inputs them into the AI ​​model. The input is emotion data, and the output is the generated prompts.

[0167] Step 4:

[0168] The server uses a generative AI model to generate optimal video content based on the prompt text. For example, it might create a video featuring animals performing playfully, set to relaxing music. The input is the prompt text, and the output is the generated video content.

[0169] Step 5:

[0170] The device receives video content sent from the server and provides it to the baby and parent. Specifically, it plays the received video on the device and displays it so that the parent and child can visually enjoy it. The input is the generated video content, and the output is the video played on the device.

[0171] (Application Example 2)

[0172] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0173] In modern childcare, there is a challenge in adapting to the emotional states of both parents and babies in real time and providing content that is optimal for both. In particular, providing content without considering the parents' emotional state can hinder parent-child interaction and potentially reduce the quality of childcare. Therefore, there is a need for a system that can appropriately analyze the parents' emotional state and simultaneously provide content based on the baby's reactions.

[0174] 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.

[0175] In this invention, the server includes a shooting means for simultaneously capturing the user's (parent's) visual data, an analysis means for analyzing the user's emotions based on the captured visual data, and a generation means for generating content suitable for both parent and child based on the analyzed user's emotional data and the baby's visual data. This makes it possible to provide appropriate content in response to the baby's reactions while taking into account the parent's emotional state.

[0176] "Users" refer to parents who use the system and are the ones who evaluate the content together with their babies.

[0177] "Visual data" refers to image information captured by cameras or other imaging devices, including information about the baby's and user's facial expressions and movements.

[0178] "Filming equipment" refers to a device or function for acquiring visual data, specifically for recording the facial expressions and movements of the baby and the user in real time.

[0179] "Analysis means" refers to technology for determining the emotional state of the baby and the user based on acquired visual data.

[0180] "Emotional data" refers to the emotional state of babies and users recognized through analytical methods, and serves as a guideline for content creation.

[0181] "Generation means" refers to a process and apparatus for generating content that is optimal for both parents and children based on analyzed emotional data.

[0182] "Content" refers to information such as videos presented to the user and the baby, and is characterized by being appropriate to the emotional state of the parent and child.

[0183] This system uses devices such as smartphones and tablets to provide content suitable for both parents and babies. The devices use their built-in cameras to acquire and evaluate visual data from both the baby and the parent. This includes the frequency of the baby's smiles, eye movements, and changes in the parent's facial expressions.

[0184] The server receives visual data transmitted from the terminal and analyzes the data using an emotion analysis engine that includes a multi-layer neural network. This analysis recognizes the emotional state of the baby and parent and generates emotion data. Based on this emotion data, the server uses a generative AI model to create video content that is optimal for both parent and child. For example, if the baby responds well to animal videos and the parent shows a relaxed expression, the server will generate a video that includes scenes of animals happily performing and will play relaxing music in the background.

[0185] The generated content is sent from the server to the device and immediately presented to the baby and parent. Through this process, we can provide an optimal video experience for parents and children, reduce the burden of content selection in childcare, and enhance the happiness of both parent and child.

[0186] As a concrete example, imagine a baby and parent using this system while playing in a park. Every time the baby smiles, the system generates a video of a cheerful animal, providing a reassuring space for the parent to watch over their child. For example, a prompt message could be sent to the generation AI model saying, "When the baby smiles, generate a fun animal video along with music that will help the parent relax." This allows the system to respond quickly and appropriately, enriching the time spent with the child.

[0187] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0188] Step 1:

[0189] The device uses its built-in camera to capture the baby's and user's facial expressions in real time. The input is the live video captured through the camera, and the output is a stream of this video data. The device sends this data to a server for use in the next step.

[0190] Step 2:

[0191] The server receives video data transmitted from the terminal. The input is a stream of video data, and the output is pre-processed data required by the emotion analysis engine. The server detects the baby's and the user's facial expressions in the video and converts the data into an appropriate format to pass to the emotion analysis engine.

[0192] Step 3:

[0193] The server's emotion analysis engine analyzes the emotional states of the baby and the user using pre-processed data. The input is pre-processed facial data, and the output is emotional data such as the baby's degree of smile and the user's degree of relaxation. The emotion analysis engine identifies emotions using techniques such as convolutional neural networks.

[0194] Step 4:

[0195] Based on the emotional data obtained, the server uses a generative AI model to generate content optimized for both the baby and the user. The input consists of emotional data and prompts for the generative AI model, while the output is video content appropriate to the state of each parent and child. The server sends data to the AI ​​model, including instructions such as "If the baby is smiling a lot, generate a video of fun animals" in the prompts.

[0196] Step 5:

[0197] The server sends the generated content to the terminal. The input is the generated video content, and the output is data in a format playable on the terminal. After performing data compression and data conversion to reduce latency, the server sends it back to the terminal.

[0198] Step 6:

[0199] The device receives video content transmitted from the server and presents it to the baby and user as visual and auditory information. The input is video data received from the server, and the output is the display and playback of the content through the display and speakers. The device adjusts the video content to play at the best possible quality, allowing parents and children to enjoy it immediately.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] [Second Embodiment]

[0204] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0205] 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.

[0206] 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).

[0207] 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.

[0208] 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.

[0209] 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).

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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".

[0216] As an embodiment of the present invention, a system that analyzes a baby's video viewing reactions in real time and generates personalized video content will be described. This system mainly consists of three elements: a terminal, a server, and a user.

[0217] The device is equipped with a camera to acquire visual data from the baby, capturing the baby's facial expressions and attention span in real time while they watch videos. This visual data is used to extract indicators such as the frequency of the baby's smiles and the duration of their interest.

[0218] Next, the device sends this analyzed data to a server. The server uses machine learning algorithms to analyze the data and understand the baby's preferences and interests. Based on this, the server uses generative AI to generate customized video content for the baby. This video is based on the baby's past reaction data and contains content that is expected to elicit smiles and attention.

[0219] The generated videos are sent from the server to the device and played back by the device. In this way, the baby can watch video content that suits their preferences. The user (parent) performs the initial system setup and camera positioning, but the effort required for subsequent content selection is greatly reduced.

[0220] For example, if a baby responds well to images of animals, the server will generate a colorful video featuring many animals. Furthermore, if the baby shows interest in music, adding video content with musical elements can further engage them.

[0221] This system will provide a video experience optimized for babies, reducing the burden on parents.

[0222] The following describes the processing flow.

[0223] Step 1:

[0224] The user places the baby in front of the TV and adjusts the camera angle and position to set it up so that the baby's face is properly visible.

[0225] Step 2:

[0226] The device activates its built-in camera and captures the baby's face in real time. It continuously acquires the baby's facial expressions and eye movements from the camera's video feed.

[0227] Step 3:

[0228] The device analyzes the video data it acquires and converts the frequency of the baby's smiles and the degree of their gaze into numerical data. This data serves as an indicator of the baby's level of concentration and interest.

[0229] Step 4:

[0230] The terminal packages the analyzed data at regular time intervals and sends the data to the server.

[0231] Step 5:

[0232] The server uses the received data to perform analysis using machine learning algorithms. To identify the baby's preferences, patterns such as the frequency of smiles and the duration of fixed gaze are analyzed.

[0233] Step 6:

[0234] The server uses AI generation to create personalized videos for babies based on analysis results. These videos are designed based on specific interests and preferences.

[0235] Step 7:

[0236] The server encodes the generated video and efficiently transmits it to the terminal in streaming format.

[0237] Step 8:

[0238] The device decodes and plays the received video, then presents it to the baby. The content displayed on the screen is optimized to capture the baby's attention.

[0239] Step 9:

[0240] The device recaptures the baby's reactions during playback, collecting new data on smiles and attention levels. This information is then reused in step 1.

[0241] (Example 1)

[0242] 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."

[0243] There is a challenge in optimizing the video content that babies watch, providing a personalized experience tailored to their preferences, and reducing the burden on parents in selecting content.

[0244] 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.

[0245] In this invention, the server includes a shooting means for capturing image information of a baby, an analysis means for analyzing the captured image information to identify the baby's facial expressions and degree of attention, and a generation means for generating a video including musical elements based on the analysis results. This makes it possible to automatically generate and provide high-quality video content while maintaining the baby's interest.

[0246] "Photography means" refers to the devices and technologies used to acquire image information of a baby.

[0247] "Analysis means" refers to devices and technologies that analyze a baby's facial expressions and gaze intensity from acquired image information, and use that data to identify their interests and preferences.

[0248] "Generation method" refers to a technology or system that automatically creates videos containing music elements optimized for babies, based on analyzed data.

[0249] "Presentation means" refers to devices or mechanisms used to show generated video content to babies.

[0250] "Learning methods" refer to technologies and methods that use past analysis data to reflect a baby's preferences and continuously improve the video generation process.

[0251] This invention relates to a system that personalizes a baby's video viewing experience and reduces the burden on parents. The system mainly consists of three elements: a server, a terminal, and a user.

[0252] First, the device is equipped with a camera that captures the baby's visual data in real time. This camera is used to capture the baby's facial expressions and attention span while they are watching videos. The visual data is quantified by image recognition software within the device, and indicators such as smiles and attention duration are extracted.

[0253] The extracted data is sent from the device to the server. The server analyzes this data using machine learning algorithms and generative AI models. As a result of the analysis, the baby's preferences and interests are identified.

[0254] Next, the server inputs prompt messages into an AI model based on the analysis results to create video content for babies. The generated content is individually optimized because it is based on the babies' reaction data. For example, prompt messages such as "Generate colorful animal videos to elicit smiles" or "Create a video that includes musical elements that babies will find interesting" are used.

[0255] The generated content is sent from the server to the device and played back by the baby. In this way, the baby can watch videos tailored to their individual interests. The parent, as the user, performs the initial setup of the system and adjusts the camera position, but during normal use, content is generated automatically, saving the parent the trouble of selecting content.

[0256] This makes it possible to provide babies with the best possible video viewing experience while reducing the burden on parents.

[0257] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0258] Step 1:

[0259] The device acquires the baby's visual data through its camera. Specifically, the device captures the baby's facial expressions and gaze points in real time. This input data, consisting of images and videos, is analyzed by image recognition software within the device and output as quantified facial expression and gaze intensity data.

[0260] Step 2:

[0261] The terminal transmits the quantified data obtained from the analysis to the server via a communication protocol. This transmitted data includes information such as the frequency of smiles and gaze duration. The server receives this output data as input for the next analysis stage.

[0262] Step 3:

[0263] The server uses the input numerical data to apply machine learning algorithms to identify the baby's preferences and interests. This data processing includes comparing it with a database of past viewing patterns and extracting elements that triggered specific reactions. This process outputs characteristic information tailored to the baby's interests.

[0264] Step 4:

[0265] The server uses a generative AI model based on the outputted characteristic information to create prompt statements and input them into the model. The generative AI model generates video content tailored to the baby according to these prompt statements. For example, it may include specific instructions such as, "Generate animal videos with bright colors." This generated content is then produced as output.

[0266] Step 5:

[0267] The server sends the generated video content to the device. This process utilizes communication technologies that ensure the security and speed of data transfer. The device then uses a media player to play the received video in high quality, providing the baby with a viewing experience. The output video is played in a way that is engaging and interesting to the baby.

[0268] Step 6:

[0269] The user (parent) performs the initial setup and camera positioning at the start of the system. This helps ensure that the baby's visual data is properly captured. In subsequent steps, the system automatically collects data and generates videos with minimal user intervention.

[0270] (Application Example 1)

[0271] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0272] When providing video content for babies, existing methods make it difficult to generate personalized content that accurately reflects the individual interests and reactions of each baby. To solve this problem, there is a need for a system that analyzes the baby's visual data in real time and provides the most suitable videos according to their interests and preferences.

[0273] 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.

[0274] In this invention, the server includes an acquisition means for acquiring visual data, an analysis means for analyzing gaze intensity and facial expressions based on the acquired visual data, and a generation means for identifying interest tendencies based on the analysis and generating personalized content. This makes it possible to provide video content based on the baby's interests.

[0275] "Visual data" refers to image information acquired by a camera, such as a baby's facial expressions and eye movements.

[0276] "Acquisition means" refers to the part that has the function of acquiring visual data using hardware such as a camera.

[0277] "Analysis means" refers to software or algorithms that process acquired visual data to identify the baby's gaze level, facial expressions, and interests.

[0278] The "generation method" refers to the part that has the functionality to create personalized video content based on the interest trends obtained through analysis.

[0279] "Presentation means" refers to a device or method for delivering generated video content to a user device and visually presenting it to a baby.

[0280] A "learning tool" is a machine learning model that utilizes past visual data and its analysis results to continuously optimize the video content generation process.

[0281] This invention relates to a system that acquires a baby's visual data in real time, analyzes it, and generates personalized videos. The system is mainly composed of three components: a terminal, a server, and a user.

[0282] The device is equipped with a camera that captures the baby's facial expressions and gaze as visual data. This data is then analyzed using software built into the device to extract the baby's gaze intensity and facial characteristics. The hardware used includes smart devices with cameras (e.g., smartphones and tablets), and the software utilizes the OpenCV image processing library.

[0283] After that, the visual data is sent to the server for more advanced analysis. On the server, using machine learning algorithms, while comparing with the baby's past reaction data, the server learns the baby's interest and preference trends. TensorFlow and Scikit-learn are used for machine learning. Based on this analysis result, a generative AI model generates customized video content for the baby. The generated video emphasizes more features that the baby is likely to be interested in. For example, if the baby prefers videos of animals or music elements, videos containing them are created. Specific examples of prompt texts include instructions such as "Please generate an animal video for the baby, adding elements that make the baby smile. Also consider music elements."

[0284] The video thus generated is sent back from the server to the terminal and presented to the baby in the visual environment set by the user. The user makes initial settings and adjusts the camera position, etc., but subsequent operations are basically automatically performed between the server and the terminal, so it is possible to greatly reduce the user's effort.

[0285] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0286] Step 1:

[0287] The terminal uses the camera to acquire in real time the visual data of the baby's expression and gaze. At this time, the input is the video of the baby's face, and the captured visual data is obtained as the output. As an operation, the camera continuously captures the video and holds the data in the internal memory.

[0288] Step 2:

[0289] The device analyzes the baby's gaze intensity and facial expressions from visual data acquired using OpenCV. The input to this process is the visual data obtained in step 1, and the output is an index of gaze intensity and facial expression features. In terms of operation, an image processing algorithm is executed to detect landmark points on the face and analyze the frequency of smiles, etc.

[0290] Step 3:

[0291] The terminal sends the analyzed data to the server. The input is the data analyzed in step 2, and the output is a data packet in a format that the server can use for processing. The operation involves uploading the data to the server using a network protocol (e.g., HTTP).

[0292] Step 4:

[0293] The server uses a machine learning model to analyze the baby's interests based on the received data. The input for this step is the analysis data sent from the terminal, and the output is data indicating the types and tendencies of the baby's interests. The process involves using TensorFlow to perform statistical data processing and identify interest patterns by comparing them with past data.

[0294] Step 5:

[0295] The server generates video content based on the identified interest preferences using a generative AI model and outputs it as a file. The input for this procedure is the analysis results from step 4, and the output is a video file of the content. In terms of operation, prompt text is provided to the model, and it automatically generates a video containing recommended video elements.

[0296] Step 6:

[0297] The server sends the generated video content to the terminal. The input is the video file generated in step 5, and the output is video data that the device can visualize. The operation involves delivering video data packets to the terminal over the network.

[0298] Step 7:

[0299] The device presents the received video content to the baby. The input is video data sent from the server, and the output is visual content played on the device. The operation includes playing the video file in a media player and displaying it on the screen.

[0300] 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.

[0301] As an embodiment of the present invention, a system that analyzes the emotions of both the baby and the user (parent) and provides personalized video content will be described. This system consists of three elements: a terminal, a server, and a user, and in particular incorporates an emotion engine to recognize and analyze emotions.

[0302] The device captures the baby's face with a camera and collects visual data in real time. This data includes the baby's facial expressions, eye movements, and frequency of smiles. The device also simultaneously captures the parent's facial expressions and acquires the parent's emotional data as needed. This emotional data is analyzed by an emotion engine, which includes a multi-layer neural network, to identify the parent's emotional state.

[0303] Next, the server deeply analyzes the data received using the emotion engine. Based on the user's emotion data and the baby's visual data, it comprehensively evaluates the state of the parent and the baby. Based on this evaluation, it generates beneficial content for both the parent and the baby, such as not only videos suitable for the baby but also videos that soothe (or elevate) the parent's emotions.

[0304] The generated video is sent from the server to the terminal and presented as the most suitable for the baby. As a specific example, when the baby shows a good reaction to an animal video and at the same time the parent shows a relaxed expression, the server generates a video containing scenes where the animal plays cheerfully and arranges music that allows the user to feel further relaxation in the background. On the other hand, when the baby shows no reaction or when the parent is feeling stressed, these elements are adjusted to present new content.

[0305] This system can provide an optimal video experience considering both the baby's reaction and the user's emotional state, reduce the stress of choosing videos in childcare, and enhance the happiness of the parent and child.

[0306] The following explains the processing flow.

[0307] Step 1:

[0308] [[ID=2​​​​​​​​​​​​​​ The device instantly analyzes the visual data it captures, analyzing the baby's gaze intensity, facial expression data, and the user's emotions. The emotion engine identifies the emotional state from changes in facial expressions and determines indicators such as whether the user is excited or relaxed.

[0313] Step 4:

[0314] The device sends the analyzed data from both parties to the server. The data includes the baby's level of interest and the user's emotional state.

[0315] Step 5:

[0316] Based on the data received by the server, machine learning algorithms perform further in-depth analysis. This analyzes the characteristics of the video to optimize the baby's preferences and the parents' emotional state.

[0317] Step 6:

[0318] Based on the analysis results, the server uses a generation AI to create an ideal video for both the baby and the user. This is designed to help parents maintain positive emotions regarding their baby's reactions.

[0319] Step 7:

[0320] The server sends the newly generated video to the terminal in streaming format. This allows for real-time playback with minimal latency.

[0321] Step 8:

[0322] The device displays the transmitted video and continuously captures the baby's and user's reactions during playback to collect new data.

[0323] Step 9:

[0324] The device sends the collected data back to the server, creating a feedback loop that is used to generate the next video. By repeating this process, content tailored to the preferences of both parties can be continuously improved and provided.

[0325] (Example 2)

[0326] 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".

[0327] While systems have existed that provide video content based on a baby's emotions and reactions, there is a lack of systems that simultaneously consider the emotional states of both the baby and the parent to provide the optimal video experience for both parent and child. Considering the parent's emotional state can further enhance the happiness of both parent and child, but an effective method for achieving this is needed.

[0328] 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.

[0329] In this invention, the server includes a shooting means for capturing visual data of the baby and parent, an analysis means for analyzing the baby's gaze, facial expressions, and parent's emotions based on the captured visual data, and a generation means for generating videos for the baby and parent based on the analysis. This makes it possible to provide optimal video content that corresponds to the emotional state of both the baby and parent, reduce stress in childcare, and improve the happiness of both parent and child.

[0330] "Mechanisms of recording" refer to devices and technologies for capturing visual data of babies and their parents in real time.

[0331] "Analysis means" refers to devices and technologies used to evaluate the baby's gaze, facial expressions, and the parents' emotional state based on captured visual data.

[0332] "Generation means" refers to devices and technologies for creating optimal video content for babies and their parents based on analysis results.

[0333] "Presentation means" refers to devices or technologies for visually providing the generated video to the baby and its parents.

[0334] The system according to this invention is configured to simultaneously analyze the emotions of both the baby and the parent and provide optimal video content. The system mainly consists of two main components: a terminal and a server.

[0335] The device is equipped with a means of capturing real-time visual data of the baby and parent. Specifically, it uses a video camera or the camera function of a smartphone to capture the baby's facial expressions, eye movements, frequency of smiles, and the parent's facial expressions.

[0336] The server receives this visual data and analyzes it using an emotion engine. The emotion engine incorporates a multi-layer neural network and has the ability to identify the baby's gaze and facial expressions, as well as the parent's emotional state. Based on this analysis, a generative AI model is used to generate video content. The server then generates prompts based on the results and creates a customized video accordingly.

[0337] As a concrete example, if a baby is smiling and the parents are relaxed, the server will generate a prompt message such as, "We have detected a baby's smile and relaxed expression in the parents. Please generate a scene of animals happily performing with background music." This prompt is then input into the AI ​​generation model, which outputs the most suitable content.

[0338] The device receives the generated video sent from the server and presents it for the parent and child to watch. This allows for the provision of video content tailored to the emotional state of both parent and child, thereby reducing stress related to childcare and improving the happiness of both parent and child.

[0339] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0340] Step 1:

[0341] The device uses a camera to collect real-time visual data of the baby and parent. Specifically, it records the baby's facial expressions and eye movements, capturing the frequency of smiles and the direction of gaze. Simultaneously, it acquires facial expression data of the parent, collecting the characteristics of each face as data. The input for this step is real-time video footage, and the output is facial expression data of the baby and parent.

[0342] Step 2:

[0343] The server activates the emotion engine to analyze the received visual data. The emotion engine processes the input facial expression data using a multilayer neural network to identify the frequency and intensity of the baby's smiles, as well as the parents' emotional state. The input is the facial expression data obtained in step 1, and the output is the emotion data as a result of the analysis.

[0344] Step 3:

[0345] The server uses a generative AI model based on emotion data to create prompts for generating video content. Specifically, based on information such as "a baby's smile and a parent's relaxed expression were detected," it generates prompts containing appropriate video elements and inputs them into the AI ​​model. The input is emotion data, and the output is the generated prompts.

[0346] Step 4:

[0347] The server uses a generative AI model to generate optimal video content based on the prompt text. For example, it might create a video featuring animals performing playfully, set to relaxing music. The input is the prompt text, and the output is the generated video content.

[0348] Step 5:

[0349] The device receives video content sent from the server and provides it to the baby and parent. Specifically, it plays the received video on the device and displays it so that the parent and child can visually enjoy it. The input is the generated video content, and the output is the video played on the device.

[0350] (Application Example 2)

[0351] 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 as the "terminal".

[0352] In modern childcare, there is a challenge in adapting to the emotional states of both parents and babies in real time and providing content that is optimal for both. In particular, providing content without considering the parents' emotional state can hinder parent-child interaction and potentially reduce the quality of childcare. Therefore, there is a need for a system that can appropriately analyze the parents' emotional state and simultaneously provide content based on the baby's reactions.

[0353] 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.

[0354] In this invention, the server includes a shooting means for simultaneously capturing the user's (parent's) visual data, an analysis means for analyzing the user's emotions based on the captured visual data, and a generation means for generating content suitable for both parent and child based on the analyzed user's emotional data and the baby's visual data. This makes it possible to provide appropriate content in response to the baby's reactions while taking into account the parent's emotional state.

[0355] "Users" refer to parents who use the system and are the ones who evaluate the content together with their babies.

[0356] "Visual data" refers to image information captured by cameras or other imaging devices, including information about the baby's and user's facial expressions and movements.

[0357] "Filming equipment" refers to a device or function for acquiring visual data, specifically for recording the facial expressions and movements of the baby and the user in real time.

[0358] "Analysis means" refers to technology for determining the emotional state of the baby and the user based on acquired visual data.

[0359] "Emotional data" refers to the emotional state of babies and users recognized through analytical methods, and serves as a guideline for content creation.

[0360] "Generation means" refers to a process and apparatus for generating content that is optimal for both parents and children based on analyzed emotional data.

[0361] "Content" refers to information such as videos presented to the user and the baby, and is characterized by being appropriate to the emotional state of the parent and child.

[0362] This system uses devices such as smartphones and tablets to provide content suitable for both parents and babies. The devices use their built-in cameras to acquire and evaluate visual data from both the baby and the parent. This includes the frequency of the baby's smiles, eye movements, and changes in the parent's facial expressions.

[0363] The server receives visual data transmitted from the terminal and analyzes the data using an emotion analysis engine that includes a multi-layer neural network. This analysis recognizes the emotional state of the baby and parent and generates emotion data. Based on this emotion data, the server uses a generative AI model to create video content that is optimal for both parent and child. For example, if the baby responds well to animal videos and the parent shows a relaxed expression, the server will generate a video that includes scenes of animals happily performing and will play relaxing music in the background.

[0364] The generated content is sent from the server to the device and immediately presented to the baby and parent. Through this process, we can provide an optimal video experience for parents and children, reduce the burden of content selection in childcare, and enhance the happiness of both parent and child.

[0365] As a concrete example, imagine a baby and parent using this system while playing in a park. Every time the baby smiles, the system generates a video of a cheerful animal, providing a reassuring space for the parent to watch over their child. For example, a prompt message could be sent to the generation AI model saying, "When the baby smiles, generate a fun animal video along with music that will help the parent relax." This allows the system to respond quickly and appropriately, enriching the time spent with the child.

[0366] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0367] Step 1:

[0368] The device uses its built-in camera to capture the baby's and user's facial expressions in real time. The input is the live video captured through the camera, and the output is a stream of this video data. The device sends this data to a server for use in the next step.

[0369] Step 2:

[0370] The server receives video data transmitted from the terminal. The input is a stream of video data, and the output is pre-processed data required by the emotion analysis engine. The server detects the baby's and the user's facial expressions in the video and converts the data into an appropriate format to pass to the emotion analysis engine.

[0371] Step 3:

[0372] The server's emotion analysis engine analyzes the emotional states of the baby and the user using pre-processed data. The input is pre-processed facial data, and the output is emotional data such as the baby's degree of smile and the user's degree of relaxation. The emotion analysis engine identifies emotions using techniques such as convolutional neural networks.

[0373] Step 4:

[0374] Based on the emotional data obtained, the server uses a generative AI model to generate content optimized for both the baby and the user. The input consists of emotional data and prompts for the generative AI model, while the output is video content appropriate to the state of each parent and child. The server sends data to the AI ​​model, including instructions such as "If the baby is smiling a lot, generate a video of fun animals" in the prompts.

[0375] Step 5:

[0376] The server sends the generated content to the terminal. The input is the generated video content, and the output is data in a format playable on the terminal. After performing data compression and data conversion to reduce latency, the server sends it back to the terminal.

[0377] Step 6:

[0378] The device receives video content transmitted from the server and presents it to the baby and user as visual and auditory information. The input is video data received from the server, and the output is the display and playback of the content through the display and speakers. The device adjusts the video content to play at the best possible quality, allowing parents and children to enjoy it immediately.

[0379] 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.

[0380] 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.

[0381] 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.

[0382] [Third Embodiment]

[0383] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0384] 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.

[0385] 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).

[0386] 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.

[0387] 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.

[0388] 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).

[0389] 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.

[0390] 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.

[0391] 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.

[0392] 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.

[0393] 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.

[0394] 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".

[0395] As an embodiment of the present invention, a system that analyzes a baby's video viewing reactions in real time and generates personalized video content will be described. This system mainly consists of three elements: a terminal, a server, and a user.

[0396] The device is equipped with a camera to acquire visual data from the baby, capturing the baby's facial expressions and attention span in real time while they watch videos. This visual data is used to extract indicators such as the frequency of the baby's smiles and the duration of their interest.

[0397] Next, the device sends this analyzed data to a server. The server uses machine learning algorithms to analyze the data and understand the baby's preferences and interests. Based on this, the server uses generative AI to generate customized video content for the baby. This video is based on the baby's past reaction data and contains content that is expected to elicit smiles and attention.

[0398] The generated videos are sent from the server to the device and played back by the device. In this way, the baby can watch video content that suits their preferences. The user (parent) performs the initial system setup and camera positioning, but the effort required for subsequent content selection is greatly reduced.

[0399] For example, if a baby responds well to images of animals, the server will generate a colorful video featuring many animals. Furthermore, if the baby shows interest in music, adding video content with musical elements can further engage them.

[0400] This system will provide a video experience optimized for babies, reducing the burden on parents.

[0401] The following describes the processing flow.

[0402] Step 1:

[0403] The user places the baby in front of the TV and adjusts the camera angle and position to set it up so that the baby's face is properly visible.

[0404] Step 2:

[0405] The device activates its built-in camera and captures the baby's face in real time. It continuously acquires the baby's facial expressions and eye movements from the camera's video feed.

[0406] Step 3:

[0407] The device analyzes the video data it acquires and converts the frequency of the baby's smiles and the degree of their gaze into numerical data. This data serves as an indicator of the baby's level of concentration and interest.

[0408] Step 4:

[0409] The terminal packages the analyzed data at regular time intervals and sends the data to the server.

[0410] Step 5:

[0411] The server uses the received data to perform analysis using machine learning algorithms. To identify the baby's preferences, patterns such as the frequency of smiles and the duration of fixed gaze are analyzed.

[0412] Step 6:

[0413] The server uses AI generation to create personalized videos for babies based on analysis results. These videos are designed based on specific interests and preferences.

[0414] Step 7:

[0415] The server encodes the generated video and efficiently transmits it to the terminal in streaming format.

[0416] Step 8:

[0417] The device decodes and plays the received video, then presents it to the baby. The content displayed on the screen is optimized to capture the baby's attention.

[0418] Step 9:

[0419] The device recaptures the baby's reactions during playback, collecting new data on smiles and attention levels. This information is then reused in step 1.

[0420] (Example 1)

[0421] 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."

[0422] There is a challenge in optimizing the video content that babies watch, providing a personalized experience tailored to their preferences, and reducing the burden on parents in selecting content.

[0423] 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.

[0424] In this invention, the server includes a shooting means for capturing image information of a baby, an analysis means for analyzing the captured image information to identify the baby's facial expressions and degree of attention, and a generation means for generating a video including musical elements based on the analysis results. This makes it possible to automatically generate and provide high-quality video content while maintaining the baby's interest.

[0425] "Photography means" refers to the devices and technologies used to acquire image information of a baby.

[0426] "Analysis means" refers to devices and technologies that analyze a baby's facial expressions and gaze intensity from acquired image information, and use that data to identify their interests and preferences.

[0427] "Generation method" refers to a technology or system that automatically creates videos containing music elements optimized for babies, based on analyzed data.

[0428] "Presentation means" refers to devices or mechanisms used to show generated video content to babies.

[0429] "Learning methods" refer to technologies and methods that use past analysis data to reflect a baby's preferences and continuously improve the video generation process.

[0430] This invention relates to a system that personalizes a baby's video viewing experience and reduces the burden on parents. The system mainly consists of three elements: a server, a terminal, and a user.

[0431] First, the device is equipped with a camera that captures the baby's visual data in real time. This camera is used to capture the baby's facial expressions and attention span while they are watching videos. The visual data is quantified by image recognition software within the device, and indicators such as smiles and attention duration are extracted.

[0432] The extracted data is sent from the device to the server. The server analyzes this data using machine learning algorithms and generative AI models. As a result of the analysis, the baby's preferences and interests are identified.

[0433] Next, the server inputs prompt messages into an AI model based on the analysis results to create video content for babies. The generated content is individually optimized because it is based on the babies' reaction data. For example, prompt messages such as "Generate colorful animal videos to elicit smiles" or "Create a video that includes musical elements that babies will find interesting" are used.

[0434] The generated content is sent from the server to the device and played back by the baby. In this way, the baby can watch videos tailored to their individual interests. The parent, as the user, performs the initial setup of the system and adjusts the camera position, but during normal use, content is generated automatically, saving the parent the trouble of selecting content.

[0435] This makes it possible to provide babies with the best possible video viewing experience while reducing the burden on parents.

[0436] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0437] Step 1:

[0438] The device acquires the baby's visual data through its camera. Specifically, the device captures the baby's facial expressions and gaze points in real time. This input data, consisting of images and videos, is analyzed by image recognition software within the device and output as quantified facial expression and gaze intensity data.

[0439] Step 2:

[0440] The terminal transmits the quantified data obtained from the analysis to the server via a communication protocol. This transmitted data includes information such as the frequency of smiles and gaze duration. The server receives this output data as input for the next analysis stage.

[0441] Step 3:

[0442] The server uses the input numerical data to apply machine learning algorithms to identify the baby's preferences and interests. This data processing includes comparing it with a database of past viewing patterns and extracting elements that triggered specific reactions. This process outputs characteristic information tailored to the baby's interests.

[0443] Step 4:

[0444] The server uses a generative AI model based on the outputted characteristic information to create prompt statements and input them into the model. The generative AI model generates video content tailored to the baby according to these prompt statements. For example, it may include specific instructions such as, "Generate animal videos with bright colors." This generated content is then produced as output.

[0445] Step 5:

[0446] The server sends the generated video content to the device. This process utilizes communication technologies that ensure the security and speed of data transfer. The device then uses a media player to play the received video in high quality, providing the baby with a viewing experience. The output video is played in a way that is engaging and interesting to the baby.

[0447] Step 6:

[0448] The user (parent) performs the initial setup and camera positioning at the start of the system. This helps ensure that the baby's visual data is properly captured. In subsequent steps, the system automatically collects data and generates videos with minimal user intervention.

[0449] (Application Example 1)

[0450] 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."

[0451] When providing video content for babies, existing methods make it difficult to generate personalized content that accurately reflects the individual interests and reactions of each baby. To solve this problem, there is a need for a system that analyzes the baby's visual data in real time and provides the most suitable videos according to their interests and preferences.

[0452] 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.

[0453] In this invention, the server includes an acquisition means for acquiring visual data, an analysis means for analyzing gaze intensity and facial expressions based on the acquired visual data, and a generation means for identifying interest tendencies based on the analysis and generating personalized content. This makes it possible to provide video content based on the baby's interests.

[0454] "Visual data" refers to image information acquired by a camera, such as a baby's facial expressions and eye movements.

[0455] "Acquisition means" refers to the part that has the function of acquiring visual data using hardware such as a camera.

[0456] "Analysis means" refers to software or algorithms that process acquired visual data to identify the baby's gaze level, facial expressions, and interests.

[0457] The "generation method" refers to the part that has the functionality to create personalized video content based on the interest trends obtained through analysis.

[0458] "Presentation means" refers to a device or method for delivering generated video content to a user device and visually presenting it to a baby.

[0459] A "learning tool" is a machine learning model that utilizes past visual data and its analysis results to continuously optimize the video content generation process.

[0460] This invention relates to a system that acquires a baby's visual data in real time, analyzes it, and generates personalized videos. The system is mainly composed of three components: a terminal, a server, and a user.

[0461] The device is equipped with a camera that captures the baby's facial expressions and gaze as visual data. This data is then analyzed using software built into the device to extract the baby's gaze intensity and facial characteristics. The hardware used includes smart devices with cameras (e.g., smartphones and tablets), and the software utilizes the OpenCV image processing library.

[0462] The visual data is then sent to a server for more advanced analysis. On the server, machine learning algorithms are used to learn the baby's interests and preferences by comparing them with the baby's past response data. TensorFlow and Scikit-learn are used for machine learning. Based on this analysis, a generative AI model generates customized video content for babies. The generated videos emphasize features that are likely to interest the baby. For example, if the baby likes animal videos or music, videos containing these elements will be created. An example of a specific prompt might be, "Generate an animal video for babies, adding elements that will make the baby smile. Please also consider music."

[0463] The generated video is returned from the server to the device and presented to the baby in the visual environment set by the user. The user performs initial setup and camera position adjustments, but subsequent operations are basically performed automatically between the server and the device, significantly reducing the effort required from the user.

[0464] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0465] Step 1:

[0466] The device uses a camera to acquire visual data of the baby's facial expressions and gaze in real time. The input is an image of the baby's face, and the output is the captured visual data. The operation involves the camera continuously capturing video and storing that data in internal memory.

[0467] Step 2:

[0468] The device analyzes the baby's gaze intensity and facial expressions from visual data acquired using OpenCV. The input to this process is the visual data obtained in step 1, and the output is an index of gaze intensity and facial expression features. In terms of operation, an image processing algorithm is executed to detect landmark points on the face and analyze the frequency of smiles, etc.

[0469] Step 3:

[0470] The terminal sends the analyzed data to the server. The input is the data analyzed in step 2, and the output is a data packet in a format that the server can use for processing. The operation involves uploading the data to the server using a network protocol (e.g., HTTP).

[0471] Step 4:

[0472] The server uses a machine learning model to analyze the baby's interests based on the received data. The input for this step is the analysis data sent from the terminal, and the output is data indicating the types and tendencies of the baby's interests. The process involves using TensorFlow to perform statistical data processing and identify interest patterns by comparing them with past data.

[0473] Step 5:

[0474] The server generates video content based on the identified interest preferences using a generative AI model and outputs it as a file. The input for this procedure is the analysis results from step 4, and the output is a video file of the content. In terms of operation, prompt text is provided to the model, and it automatically generates a video containing recommended video elements.

[0475] Step 6:

[0476] The server sends the generated video content to the terminal. The input is the video file generated in step 5, and the output is video data that the device can visualize. The operation involves delivering video data packets to the terminal over the network.

[0477] Step 7:

[0478] The device presents the received video content to the baby. The input is video data sent from the server, and the output is visual content played on the device. The operation includes playing the video file in a media player and displaying it on the screen.

[0479] 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.

[0480] As an embodiment of the present invention, a system that analyzes the emotions of both the baby and the user (parent) and provides personalized video content will be described. This system consists of three elements: a terminal, a server, and a user, and in particular incorporates an emotion engine to recognize and analyze emotions.

[0481] The device captures the baby's face with a camera and collects visual data in real time. This data includes the baby's facial expressions, eye movements, and frequency of smiles. The device also simultaneously captures the parent's facial expressions and acquires the parent's emotional data as needed. This emotional data is analyzed by an emotion engine, which includes a multi-layer neural network, to identify the parent's emotional state.

[0482] Next, the server uses an emotion engine to perform in-depth analysis on the received data. Based on the user's emotional data and the baby's visual data, it comprehensively evaluates the state of both the parent and the baby. Based on this evaluation, it generates content that is beneficial to both parent and child, including not only videos suitable for the baby but also videos that soothe (or uplift) the parent's emotions.

[0483] The generated videos are sent from the server to the device and presented in a way that is optimal for the baby. For example, if the baby responds well to videos of animals and the parent appears relaxed, the server will generate a video that includes scenes of animals acting happily, with background music designed to further relax the user. On the other hand, if the baby does not respond or the parent appears stressed, these elements will be adjusted and new content will be presented.

[0484] This system can provide an optimal video experience that simultaneously considers the baby's reactions and the user's emotional state, reducing the stress of choosing videos for childcare and enhancing the happiness of both parent and child.

[0485] The following describes the processing flow.

[0486] Step 1:

[0487] The user prepares the system. They position the baby in front of the television, ensuring the parent is also within the same field of view. This ensures that both faces are clearly visible to the camera, allowing for accurate data collection.

[0488] Step 2:

[0489] The device activates the camera and captures the baby's and user's faces in real time. The camera records facial expressions, gaze, and subtle movements as visual data.

[0490] Step 3:

[0491] The device instantly analyzes the visual data it captures, analyzing the baby's gaze intensity, facial expression data, and the user's emotions. The emotion engine identifies the emotional state from changes in facial expressions and determines indicators such as whether the user is excited or relaxed.

[0492] Step 4:

[0493] The device sends the analyzed data from both parties to the server. The data includes the baby's level of interest and the user's emotional state.

[0494] Step 5:

[0495] Based on the data received by the server, machine learning algorithms perform further in-depth analysis. This analyzes the characteristics of the video to optimize the baby's preferences and the parents' emotional state.

[0496] Step 6:

[0497] Based on the analysis results, the server uses a generation AI to create an ideal video for both the baby and the user. This is designed to help parents maintain positive emotions regarding their baby's reactions.

[0498] Step 7:

[0499] The server sends the newly generated video to the terminal in streaming format. This allows for real-time playback with minimal latency.

[0500] Step 8:

[0501] The device displays the transmitted video and continuously captures the baby's and user's reactions during playback to collect new data.

[0502] Step 9:

[0503] The device sends the collected data back to the server, creating a feedback loop that is used to generate the next video. By repeating this process, content tailored to the preferences of both parties can be continuously improved and provided.

[0504] (Example 2)

[0505] 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."

[0506] While systems have existed that provide video content based on a baby's emotions and reactions, there is a lack of systems that simultaneously consider the emotional states of both the baby and the parent to provide the optimal video experience for both parent and child. Considering the parent's emotional state can further enhance the happiness of both parent and child, but an effective method for achieving this is needed.

[0507] 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.

[0508] In this invention, the server includes a shooting means for capturing visual data of the baby and parent, an analysis means for analyzing the baby's gaze, facial expressions, and parent's emotions based on the captured visual data, and a generation means for generating videos for the baby and parent based on the analysis. This makes it possible to provide optimal video content that corresponds to the emotional state of both the baby and parent, reduce stress in childcare, and improve the happiness of both parent and child.

[0509] "Mechanisms of recording" refer to devices and technologies for capturing visual data of babies and their parents in real time.

[0510] "Analysis means" refers to devices and technologies used to evaluate the baby's gaze, facial expressions, and the parents' emotional state based on captured visual data.

[0511] "Generation means" refers to devices and technologies for creating optimal video content for babies and their parents based on analysis results.

[0512] "Presentation means" refers to devices or technologies for visually providing the generated video to the baby and its parents.

[0513] The system according to this invention is configured to simultaneously analyze the emotions of both the baby and the parent and provide optimal video content. The system mainly consists of two main components: a terminal and a server.

[0514] The device is equipped with a means of capturing real-time visual data of the baby and parent. Specifically, it uses a video camera or the camera function of a smartphone to capture the baby's facial expressions, eye movements, frequency of smiles, and the parent's facial expressions.

[0515] The server receives this visual data and analyzes it using an emotion engine. The emotion engine incorporates a multi-layer neural network and has the ability to identify the baby's gaze and facial expressions, as well as the parent's emotional state. Based on this analysis, a generative AI model is used to generate video content. The server then generates prompts based on the results and creates a customized video accordingly.

[0516] As a concrete example, if a baby is smiling and the parents are relaxed, the server will generate a prompt message such as, "We have detected a baby's smile and relaxed expression in the parents. Please generate a scene of animals happily performing with background music." This prompt is then input into the AI ​​generation model, which outputs the most suitable content.

[0517] The device receives the generated video sent from the server and presents it for the parent and child to watch. This allows for the provision of video content tailored to the emotional state of both parent and child, thereby reducing stress related to childcare and improving the happiness of both parent and child.

[0518] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0519] Step 1:

[0520] The device uses a camera to collect real-time visual data of the baby and parent. Specifically, it records the baby's facial expressions and eye movements, capturing the frequency of smiles and the direction of gaze. Simultaneously, it acquires facial expression data of the parent, collecting the characteristics of each face as data. The input for this step is real-time video footage, and the output is facial expression data of the baby and parent.

[0521] Step 2:

[0522] The server activates the emotion engine to analyze the received visual data. The emotion engine processes the input facial expression data using a multilayer neural network to identify the frequency and intensity of the baby's smiles, as well as the parents' emotional state. The input is the facial expression data obtained in step 1, and the output is the emotion data as a result of the analysis.

[0523] Step 3:

[0524] The server uses a generative AI model based on emotion data to create prompts for generating video content. Specifically, based on information such as "a baby's smile and a parent's relaxed expression were detected," it generates prompts containing appropriate video elements and inputs them into the AI ​​model. The input is emotion data, and the output is the generated prompts.

[0525] Step 4:

[0526] The server uses a generative AI model to generate optimal video content based on the prompt text. For example, it might create a video featuring animals performing playfully, set to relaxing music. The input is the prompt text, and the output is the generated video content.

[0527] Step 5:

[0528] The device receives video content sent from the server and provides it to the baby and parent. Specifically, it plays the received video on the device and displays it so that the parent and child can visually enjoy it. The input is the generated video content, and the output is the video played on the device.

[0529] (Application Example 2)

[0530] 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."

[0531] In modern childcare, there is a challenge in adapting to the emotional states of both parents and babies in real time and providing content that is optimal for both. In particular, providing content without considering the parents' emotional state can hinder parent-child interaction and potentially reduce the quality of childcare. Therefore, there is a need for a system that can appropriately analyze the parents' emotional state and simultaneously provide content based on the baby's reactions.

[0532] 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.

[0533] In this invention, the server includes a shooting means for simultaneously capturing the user's (parent's) visual data, an analysis means for analyzing the user's emotions based on the captured visual data, and a generation means for generating content suitable for both parent and child based on the analyzed user's emotional data and the baby's visual data. This makes it possible to provide appropriate content in response to the baby's reactions while taking into account the parent's emotional state.

[0534] "Users" refer to parents who use the system and are the ones who evaluate the content together with their babies.

[0535] "Visual data" refers to image information captured by cameras or other imaging devices, including information about the baby's and user's facial expressions and movements.

[0536] "Filming equipment" refers to a device or function for acquiring visual data, specifically for recording the facial expressions and movements of the baby and the user in real time.

[0537] "Analysis means" refers to technology for determining the emotional state of the baby and the user based on acquired visual data.

[0538] "Emotional data" refers to the emotional state of babies and users recognized through analytical methods, and serves as a guideline for content creation.

[0539] "Generation means" refers to a process and apparatus for generating content that is optimal for both parents and children based on analyzed emotional data.

[0540] "Content" refers to information such as videos presented to the user and the baby, and is characterized by being appropriate to the emotional state of the parent and child.

[0541] This system uses devices such as smartphones and tablets to provide content suitable for both parents and babies. The devices use their built-in cameras to acquire and evaluate visual data from both the baby and the parent. This includes the frequency of the baby's smiles, eye movements, and changes in the parent's facial expressions.

[0542] The server receives visual data transmitted from the terminal and analyzes the data using an emotion analysis engine that includes a multi-layer neural network. This analysis recognizes the emotional state of the baby and parent and generates emotion data. Based on this emotion data, the server uses a generative AI model to create video content that is optimal for both parent and child. For example, if the baby responds well to animal videos and the parent shows a relaxed expression, the server will generate a video that includes scenes of animals happily performing and will play relaxing music in the background.

[0543] The generated content is sent from the server to the device and immediately presented to the baby and parent. Through this process, we can provide an optimal video experience for parents and children, reduce the burden of content selection in childcare, and enhance the happiness of both parent and child.

[0544] As a concrete example, imagine a baby and parent using this system while playing in a park. Every time the baby smiles, the system generates a video of a cheerful animal, providing a reassuring space for the parent to watch over their child. For example, a prompt message could be sent to the generation AI model saying, "When the baby smiles, generate a fun animal video along with music that will help the parent relax." This allows the system to respond quickly and appropriately, enriching the time spent with the child.

[0545] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0546] Step 1:

[0547] The device uses its built-in camera to capture the baby's and user's facial expressions in real time. The input is the live video captured through the camera, and the output is a stream of this video data. The device sends this data to a server for use in the next step.

[0548] Step 2:

[0549] The server receives video data transmitted from the terminal. The input is a stream of video data, and the output is pre-processed data required by the emotion analysis engine. The server detects the baby's and the user's facial expressions in the video and converts the data into an appropriate format to pass to the emotion analysis engine.

[0550] Step 3:

[0551] The server's emotion analysis engine analyzes the emotional states of the baby and the user using pre-processed data. The input is pre-processed facial data, and the output is emotional data such as the baby's degree of smile and the user's degree of relaxation. The emotion analysis engine identifies emotions using techniques such as convolutional neural networks.

[0552] Step 4:

[0553] Based on the emotional data obtained, the server uses a generative AI model to generate content optimized for both the baby and the user. The input consists of emotional data and prompts for the generative AI model, while the output is video content appropriate to the state of each parent and child. The server sends data to the AI ​​model, including instructions such as "If the baby is smiling a lot, generate a video of fun animals" in the prompts.

[0554] Step 5:

[0555] The server sends the generated content to the terminal. The input is the generated video content, and the output is data in a format playable on the terminal. After performing data compression and data conversion to reduce latency, the server sends it back to the terminal.

[0556] Step 6:

[0557] The device receives video content transmitted from the server and presents it to the baby and user as visual and auditory information. The input is video data received from the server, and the output is the display and playback of the content through the display and speakers. The device adjusts the video content to play at the best possible quality, allowing parents and children to enjoy it immediately.

[0558] 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.

[0559] 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.

[0560] 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.

[0561] [Fourth Embodiment]

[0562] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0563] 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.

[0564] 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).

[0565] 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.

[0566] 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.

[0567] 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).

[0568] 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.

[0569] 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.

[0570] 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.

[0571] 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.

[0572] 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.

[0573] 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.

[0574] 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".

[0575] As an embodiment of the present invention, a system that analyzes a baby's video viewing reactions in real time and generates personalized video content will be described. This system mainly consists of three elements: a terminal, a server, and a user.

[0576] The device is equipped with a camera to acquire visual data from the baby, capturing the baby's facial expressions and attention span in real time while they watch videos. This visual data is used to extract indicators such as the frequency of the baby's smiles and the duration of their interest.

[0577] Next, the device sends this analyzed data to a server. The server uses machine learning algorithms to analyze the data and understand the baby's preferences and interests. Based on this, the server uses generative AI to generate customized video content for the baby. This video is based on the baby's past reaction data and contains content that is expected to elicit smiles and attention.

[0578] The generated videos are sent from the server to the device and played back by the device. In this way, the baby can watch video content that suits their preferences. The user (parent) performs the initial system setup and camera positioning, but the effort required for subsequent content selection is greatly reduced.

[0579] For example, if a baby responds well to images of animals, the server will generate a colorful video featuring many animals. Furthermore, if the baby shows interest in music, adding video content with musical elements can further engage them.

[0580] This system will provide a video experience optimized for babies, reducing the burden on parents.

[0581] The following describes the processing flow.

[0582] Step 1:

[0583] The user places the baby in front of the TV and adjusts the camera angle and position to set it up so that the baby's face is properly visible.

[0584] Step 2:

[0585] The device activates its built-in camera and captures the baby's face in real time. It continuously acquires the baby's facial expressions and eye movements from the camera's video feed.

[0586] Step 3:

[0587] The device analyzes the video data it acquires and converts the frequency of the baby's smiles and the degree of their gaze into numerical data. This data serves as an indicator of the baby's level of concentration and interest.

[0588] Step 4:

[0589] The terminal packages the analyzed data at regular time intervals and sends the data to the server.

[0590] Step 5:

[0591] The server uses the received data to perform analysis using machine learning algorithms. To identify the baby's preferences, patterns such as the frequency of smiles and the duration of fixed gaze are analyzed.

[0592] Step 6:

[0593] The server uses AI generation to create personalized videos for babies based on analysis results. These videos are designed based on specific interests and preferences.

[0594] Step 7:

[0595] The server encodes the generated video and efficiently transmits it to the terminal in streaming format.

[0596] Step 8:

[0597] The device decodes and plays the received video, then presents it to the baby. The content displayed on the screen is optimized to capture the baby's attention.

[0598] Step 9:

[0599] The device recaptures the baby's reactions during playback, collecting new data on smiles and attention levels. This information is then reused in step 1.

[0600] (Example 1)

[0601] 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".

[0602] There is a challenge in optimizing the video content that babies watch, providing a personalized experience tailored to their preferences, and reducing the burden on parents in selecting content.

[0603] 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.

[0604] In this invention, the server includes a shooting means for capturing image information of a baby, an analysis means for analyzing the captured image information to identify the baby's facial expressions and degree of attention, and a generation means for generating a video including musical elements based on the analysis results. This makes it possible to automatically generate and provide high-quality video content while maintaining the baby's interest.

[0605] "Photography means" refers to the devices and technologies used to acquire image information of a baby.

[0606] "Analysis means" refers to devices and technologies that analyze a baby's facial expressions and gaze intensity from acquired image information, and use that data to identify their interests and preferences.

[0607] "Generation method" refers to a technology or system that automatically creates videos containing music elements optimized for babies, based on analyzed data.

[0608] "Presentation means" refers to devices or mechanisms used to show generated video content to babies.

[0609] "Learning methods" refer to technologies and methods that use past analysis data to reflect a baby's preferences and continuously improve the video generation process.

[0610] This invention relates to a system that personalizes a baby's video viewing experience and reduces the burden on parents. The system mainly consists of three elements: a server, a terminal, and a user.

[0611] First, the device is equipped with a camera that captures the baby's visual data in real time. This camera is used to capture the baby's facial expressions and attention span while they are watching videos. The visual data is quantified by image recognition software within the device, and indicators such as smiles and attention duration are extracted.

[0612] The extracted data is sent from the device to the server. The server analyzes this data using machine learning algorithms and generative AI models. As a result of the analysis, the baby's preferences and interests are identified.

[0613] Next, the server inputs prompt messages into an AI model based on the analysis results to create video content for babies. The generated content is individually optimized because it is based on the babies' reaction data. For example, prompt messages such as "Generate colorful animal videos to elicit smiles" or "Create a video that includes musical elements that babies will find interesting" are used.

[0614] The generated content is sent from the server to the device and played back by the baby. In this way, the baby can watch videos tailored to their individual interests. The parent, as the user, performs the initial setup of the system and adjusts the camera position, but during normal use, content is generated automatically, saving the parent the trouble of selecting content.

[0615] This makes it possible to provide babies with the best possible video viewing experience while reducing the burden on parents.

[0616] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0617] Step 1:

[0618] The device acquires the baby's visual data through its camera. Specifically, the device captures the baby's facial expressions and gaze points in real time. This input data, consisting of images and videos, is analyzed by image recognition software within the device and output as quantified facial expression and gaze intensity data.

[0619] Step 2:

[0620] The terminal transmits the quantified data obtained from the analysis to the server via a communication protocol. This transmitted data includes information such as the frequency of smiles and gaze duration. The server receives this output data as input for the next analysis stage.

[0621] Step 3:

[0622] The server uses the input numerical data to apply machine learning algorithms to identify the baby's preferences and interests. This data processing includes comparing it with a database of past viewing patterns and extracting elements that triggered specific reactions. This process outputs characteristic information tailored to the baby's interests.

[0623] Step 4:

[0624] The server uses a generative AI model based on the outputted characteristic information to create prompt statements and input them into the model. The generative AI model generates video content tailored to the baby according to these prompt statements. For example, it may include specific instructions such as, "Generate animal videos with bright colors." This generated content is then produced as output.

[0625] Step 5:

[0626] The server sends the generated video content to the device. This process utilizes communication technologies that ensure the security and speed of data transfer. The device then uses a media player to play the received video in high quality, providing the baby with a viewing experience. The output video is played in a way that is engaging and interesting to the baby.

[0627] Step 6:

[0628] The user (parent) performs the initial setup and camera positioning at the start of the system. This helps ensure that the baby's visual data is properly captured. In subsequent steps, the system automatically collects data and generates videos with minimal user intervention.

[0629] (Application Example 1)

[0630] 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".

[0631] When providing video content for babies, existing methods make it difficult to generate personalized content that accurately reflects the individual interests and reactions of each baby. To solve this problem, there is a need for a system that analyzes the baby's visual data in real time and provides the most suitable videos according to their interests and preferences.

[0632] 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.

[0633] In this invention, the server includes an acquisition means for acquiring visual data, an analysis means for analyzing gaze intensity and facial expressions based on the acquired visual data, and a generation means for identifying interest tendencies based on the analysis and generating personalized content. This makes it possible to provide video content based on the baby's interests.

[0634] "Visual data" refers to image information acquired by a camera, such as a baby's facial expressions and eye movements.

[0635] "Acquisition means" refers to the part that has the function of acquiring visual data using hardware such as a camera.

[0636] "Analysis means" refers to software or algorithms that process acquired visual data to identify the baby's gaze level, facial expressions, and interests.

[0637] The "generation method" refers to the part that has the functionality to create personalized video content based on the interest trends obtained through analysis.

[0638] "Presentation means" refers to a device or method for delivering generated video content to a user device and visually presenting it to a baby.

[0639] A "learning tool" is a machine learning model that utilizes past visual data and its analysis results to continuously optimize the video content generation process.

[0640] This invention relates to a system that acquires a baby's visual data in real time, analyzes it, and generates personalized videos. The system is mainly composed of three components: a terminal, a server, and a user.

[0641] The device is equipped with a camera that captures the baby's facial expressions and gaze as visual data. This data is then analyzed using software built into the device to extract the baby's gaze intensity and facial characteristics. The hardware used includes smart devices with cameras (e.g., smartphones and tablets), and the software utilizes the OpenCV image processing library.

[0642] The visual data is then sent to a server for more advanced analysis. On the server, machine learning algorithms are used to learn the baby's interests and preferences by comparing them with the baby's past response data. TensorFlow and Scikit-learn are used for machine learning. Based on this analysis, a generative AI model generates customized video content for babies. The generated videos emphasize features that are likely to interest the baby. For example, if the baby likes animal videos or music, videos containing these elements will be created. An example of a specific prompt might be, "Generate an animal video for babies, adding elements that will make the baby smile. Please also consider music."

[0643] The generated video is returned from the server to the device and presented to the baby in the visual environment set by the user. The user performs initial setup and camera position adjustments, but subsequent operations are basically performed automatically between the server and the device, significantly reducing the effort required from the user.

[0644] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0645] Step 1:

[0646] The device uses a camera to acquire visual data of the baby's facial expressions and gaze in real time. The input is an image of the baby's face, and the output is the captured visual data. The operation involves the camera continuously capturing video and storing that data in internal memory.

[0647] Step 2:

[0648] The device analyzes the baby's gaze intensity and facial expressions from visual data acquired using OpenCV. The input to this process is the visual data obtained in step 1, and the output is an index of gaze intensity and facial expression features. In terms of operation, an image processing algorithm is executed to detect landmark points on the face and analyze the frequency of smiles, etc.

[0649] Step 3:

[0650] The terminal sends the analyzed data to the server. The input is the data analyzed in step 2, and the output is a data packet in a format that the server can use for processing. The operation involves uploading the data to the server using a network protocol (e.g., HTTP).

[0651] Step 4:

[0652] The server uses a machine learning model to analyze the baby's interests based on the received data. The input for this step is the analysis data sent from the terminal, and the output is data indicating the types and tendencies of the baby's interests. The process involves using TensorFlow to perform statistical data processing and identify interest patterns by comparing them with past data.

[0653] Step 5:

[0654] The server generates video content based on the identified interest preferences using a generative AI model and outputs it as a file. The input for this procedure is the analysis results from step 4, and the output is a video file of the content. In terms of operation, prompt text is provided to the model, and it automatically generates a video containing recommended video elements.

[0655] Step 6:

[0656] The server sends the generated video content to the terminal. The input is the video file generated in step 5, and the output is video data that the device can visualize. The operation involves delivering video data packets to the terminal over the network.

[0657] Step 7:

[0658] The device presents the received video content to the baby. The input is video data sent from the server, and the output is visual content played on the device. The operation includes playing the video file in a media player and displaying it on the screen.

[0659] 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.

[0660] As an embodiment of the present invention, a system that analyzes the emotions of both the baby and the user (parent) and provides personalized video content will be described. This system consists of three elements: a terminal, a server, and a user, and in particular incorporates an emotion engine to recognize and analyze emotions.

[0661] The device captures the baby's face with a camera and collects visual data in real time. This data includes the baby's facial expressions, eye movements, and frequency of smiles. The device also simultaneously captures the parent's facial expressions and acquires the parent's emotional data as needed. This emotional data is analyzed by an emotion engine, which includes a multi-layer neural network, to identify the parent's emotional state.

[0662] Next, the server uses an emotion engine to perform in-depth analysis on the received data. Based on the user's emotional data and the baby's visual data, it comprehensively evaluates the state of both the parent and the baby. Based on this evaluation, it generates content that is beneficial to both parent and child, including not only videos suitable for the baby but also videos that soothe (or uplift) the parent's emotions.

[0663] The generated videos are sent from the server to the device and presented in a way that is optimal for the baby. For example, if the baby responds well to videos of animals and the parent appears relaxed, the server will generate a video that includes scenes of animals acting happily, with background music designed to further relax the user. On the other hand, if the baby does not respond or the parent appears stressed, these elements will be adjusted and new content will be presented.

[0664] This system can provide an optimal video experience that simultaneously considers the baby's reactions and the user's emotional state, reducing the stress of choosing videos for childcare and enhancing the happiness of both parent and child.

[0665] The following describes the processing flow.

[0666] Step 1:

[0667] The user prepares the system. They position the baby in front of the television, ensuring the parent is also within the same field of view. This ensures that both faces are clearly visible to the camera, allowing for accurate data collection.

[0668] Step 2:

[0669] The device activates the camera and captures the baby's and user's faces in real time. The camera records facial expressions, gaze, and subtle movements as visual data.

[0670] Step 3:

[0671] The device instantly analyzes the visual data it captures, analyzing the baby's gaze intensity, facial expression data, and the user's emotions. The emotion engine identifies the emotional state from changes in facial expressions and determines indicators such as whether the user is excited or relaxed.

[0672] Step 4:

[0673] The device sends the analyzed data from both parties to the server. The data includes the baby's level of interest and the user's emotional state.

[0674] Step 5:

[0675] Based on the data received by the server, machine learning algorithms perform further in-depth analysis. This analyzes the characteristics of the video to optimize the baby's preferences and the parents' emotional state.

[0676] Step 6:

[0677] Based on the analysis results, the server uses a generation AI to create an ideal video for both the baby and the user. This is designed to help parents maintain positive emotions regarding their baby's reactions.

[0678] Step 7:

[0679] The server sends the newly generated video to the terminal in streaming format. This allows for real-time playback with minimal latency.

[0680] Step 8:

[0681] The device displays the transmitted video and continuously captures the baby's and user's reactions during playback to collect new data.

[0682] Step 9:

[0683] The device sends the collected data back to the server, creating a feedback loop that is used to generate the next video. By repeating this process, content tailored to the preferences of both parties can be continuously improved and provided.

[0684] (Example 2)

[0685] 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".

[0686] While systems have existed that provide video content based on a baby's emotions and reactions, there is a lack of systems that simultaneously consider the emotional states of both the baby and the parent to provide the optimal video experience for both parent and child. Considering the parent's emotional state can further enhance the happiness of both parent and child, but an effective method for achieving this is needed.

[0687] 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.

[0688] In this invention, the server includes a shooting means for capturing visual data of the baby and parent, an analysis means for analyzing the baby's gaze, facial expressions, and parent's emotions based on the captured visual data, and a generation means for generating videos for the baby and parent based on the analysis. This makes it possible to provide optimal video content that corresponds to the emotional state of both the baby and parent, reduce stress in childcare, and improve the happiness of both parent and child.

[0689] "Mechanisms of recording" refer to devices and technologies for capturing visual data of babies and their parents in real time.

[0690] "Analysis means" refers to devices and technologies used to evaluate the baby's gaze, facial expressions, and the parents' emotional state based on captured visual data.

[0691] "Generation means" refers to devices and technologies for creating optimal video content for babies and their parents based on analysis results.

[0692] "Presentation means" refers to devices or technologies for visually providing the generated video to the baby and its parents.

[0693] The system according to this invention is configured to simultaneously analyze the emotions of both the baby and the parent and provide optimal video content. The system mainly consists of two main components: a terminal and a server.

[0694] The device is equipped with a means of capturing real-time visual data of the baby and parent. Specifically, it uses a video camera or the camera function of a smartphone to capture the baby's facial expressions, eye movements, frequency of smiles, and the parent's facial expressions.

[0695] The server receives this visual data and analyzes it using an emotion engine. The emotion engine incorporates a multi-layer neural network and has the ability to identify the baby's gaze and facial expressions, as well as the parent's emotional state. Based on this analysis, a generative AI model is used to generate video content. The server then generates prompts based on the results and creates a customized video accordingly.

[0696] As a concrete example, if a baby is smiling and the parents are relaxed, the server will generate a prompt message such as, "We have detected a baby's smile and relaxed expression in the parents. Please generate a scene of animals happily performing with background music." This prompt is then input into the AI ​​generation model, which outputs the most suitable content.

[0697] The device receives the generated video sent from the server and presents it for the parent and child to watch. This allows for the provision of video content tailored to the emotional state of both parent and child, thereby reducing stress related to childcare and improving the happiness of both parent and child.

[0698] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0699] Step 1:

[0700] The device uses a camera to collect real-time visual data of the baby and parent. Specifically, it records the baby's facial expressions and eye movements, capturing the frequency of smiles and the direction of gaze. Simultaneously, it acquires facial expression data of the parent, collecting the characteristics of each face as data. The input for this step is real-time video footage, and the output is facial expression data of the baby and parent.

[0701] Step 2:

[0702] The server activates the emotion engine to analyze the received visual data. The emotion engine processes the input facial expression data using a multilayer neural network to identify the frequency and intensity of the baby's smiles, as well as the parents' emotional state. The input is the facial expression data obtained in step 1, and the output is the emotion data as a result of the analysis.

[0703] Step 3:

[0704] The server uses a generative AI model based on emotion data to create prompts for generating video content. Specifically, based on information such as "a baby's smile and a parent's relaxed expression were detected," it generates prompts containing appropriate video elements and inputs them into the AI ​​model. The input is emotion data, and the output is the generated prompts.

[0705] Step 4:

[0706] The server uses a generative AI model to generate optimal video content based on the prompt text. For example, it might create a video featuring animals performing playfully, set to relaxing music. The input is the prompt text, and the output is the generated video content.

[0707] Step 5:

[0708] The device receives video content sent from the server and provides it to the baby and parent. Specifically, it plays the received video on the device and displays it so that the parent and child can visually enjoy it. The input is the generated video content, and the output is the video played on the device.

[0709] (Application Example 2)

[0710] 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".

[0711] In modern childcare, there is a challenge in adapting to the emotional states of both parents and babies in real time and providing content that is optimal for both. In particular, providing content without considering the parents' emotional state can hinder parent-child interaction and potentially reduce the quality of childcare. Therefore, there is a need for a system that can appropriately analyze the parents' emotional state and simultaneously provide content based on the baby's reactions.

[0712] 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.

[0713] In this invention, the server includes a shooting means for simultaneously capturing the user's (parent's) visual data, an analysis means for analyzing the user's emotions based on the captured visual data, and a generation means for generating content suitable for both parent and child based on the analyzed user's emotional data and the baby's visual data. This makes it possible to provide appropriate content in response to the baby's reactions while taking into account the parent's emotional state.

[0714] "Users" refer to parents who use the system and are the ones who evaluate the content together with their babies.

[0715] "Visual data" refers to image information captured by cameras or other imaging devices, including information about the baby's and user's facial expressions and movements.

[0716] "Filming equipment" refers to a device or function for acquiring visual data, specifically for recording the facial expressions and movements of the baby and the user in real time.

[0717] "Analysis means" refers to technology for determining the emotional state of the baby and the user based on acquired visual data.

[0718] "Emotional data" refers to the emotional state of babies and users recognized through analytical methods, and serves as a guideline for content creation.

[0719] "Generation means" refers to a process and apparatus for generating content that is optimal for both parents and children based on analyzed emotional data.

[0720] "Content" refers to information such as videos presented to the user and the baby, and is characterized by being appropriate to the emotional state of the parent and child.

[0721] This system uses devices such as smartphones and tablets to provide content suitable for both parents and babies. The devices use their built-in cameras to acquire and evaluate visual data from both the baby and the parent. This includes the frequency of the baby's smiles, eye movements, and changes in the parent's facial expressions.

[0722] The server receives visual data transmitted from the terminal and analyzes the data using an emotion analysis engine that includes a multi-layer neural network. This analysis recognizes the emotional state of the baby and parent and generates emotion data. Based on this emotion data, the server uses a generative AI model to create video content that is optimal for both parent and child. For example, if the baby responds well to animal videos and the parent shows a relaxed expression, the server will generate a video that includes scenes of animals happily performing and will play relaxing music in the background.

[0723] The generated content is sent from the server to the device and immediately presented to the baby and parent. Through this process, we can provide an optimal video experience for parents and children, reduce the burden of content selection in childcare, and enhance the happiness of both parent and child.

[0724] As a concrete example, imagine a baby and parent using this system while playing in a park. Every time the baby smiles, the system generates a video of a cheerful animal, providing a reassuring space for the parent to watch over their child. For example, a prompt message could be sent to the generation AI model saying, "When the baby smiles, generate a fun animal video along with music that will help the parent relax." This allows the system to respond quickly and appropriately, enriching the time spent with the child.

[0725] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0726] Step 1:

[0727] The device uses its built-in camera to capture the baby's and user's facial expressions in real time. The input is the live video captured through the camera, and the output is a stream of this video data. The device sends this data to a server for use in the next step.

[0728] Step 2:

[0729] The server receives video data transmitted from the terminal. The input is a stream of video data, and the output is pre-processed data required by the emotion analysis engine. The server detects the baby's and the user's facial expressions in the video and converts the data into an appropriate format to pass to the emotion analysis engine.

[0730] Step 3:

[0731] The server's emotion analysis engine analyzes the emotional states of the baby and the user using pre-processed data. The input is pre-processed facial data, and the output is emotional data such as the baby's degree of smile and the user's degree of relaxation. The emotion analysis engine identifies emotions using techniques such as convolutional neural networks.

[0732] Step 4:

[0733] Based on the emotional data obtained, the server uses a generative AI model to generate content optimized for both the baby and the user. The input consists of emotional data and prompts for the generative AI model, while the output is video content appropriate to the state of each parent and child. The server sends data to the AI ​​model, including instructions such as "If the baby is smiling a lot, generate a video of fun animals" in the prompts.

[0734] Step 5:

[0735] The server sends the generated content to the terminal. The input is the generated video content, and the output is data in a format playable on the terminal. After performing data compression and data conversion to reduce latency, the server sends it back to the terminal.

[0736] Step 6:

[0737] The device receives video content transmitted from the server and presents it to the baby and user as visual and auditory information. The input is video data received from the server, and the output is the display and playback of the content through the display and speakers. The device adjusts the video content to play at the best possible quality, allowing parents and children to enjoy it immediately.

[0738] 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.

[0739] 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.

[0740] 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 robot 414.

[0741] 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.

[0742] 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.

[0743] 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.

[0744] 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.

[0745] 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.

[0746] 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."

[0747] 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.

[0748] 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.

[0749] 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.

[0750] 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.

[0751] 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.

[0752] 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.

[0753] 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.

[0754] 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.

[0755] 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.

[0756] 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.

[0757] 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.

[0758] 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.

[0759] The following is further disclosed regarding the embodiments described above.

[0760] (Claim 1)

[0761] A means of capturing the baby's visual data,

[0762] An analysis means for analyzing the degree of gaze and facial expressions of a baby based on captured visual data,

[0763] A means for generating videos for babies based on analysis,

[0764] A means of presenting the generated video to the baby,

[0765] A system that includes this.

[0766] (Claim 2)

[0767] The system according to claim 1, comprising an analytical means for determining the frequency of a baby's smiles from visual data.

[0768] (Claim 3)

[0769] The system according to claim 1, comprising a learning means for improving the video generation process using multiple visual data and analysis results.

[0770] "Example 1"

[0771] (Claim 1)

[0772] A means of capturing image information of a baby,

[0773] An analysis means for analyzing the degree of gaze and facial expression of a baby based on captured image information,

[0774] A generation means that generates a video containing musical elements based on the baby's preferences and interests obtained from the analysis means,

[0775] A means of presenting the generated video to the baby,

[0776] A system that includes this.

[0777] (Claim 2)

[0778] The system according to claim 1, comprising an analysis means for identifying the frequency of a baby's smiles and the duration of their interest from image information, and outputting the generated video content at high speed while maintaining its quality.

[0779] (Claim 3)

[0780] The system according to claim 1, comprising a learning means for improving the video generation process while reflecting the baby's preferences, using multiple image data and analysis results.

[0781] "Application Example 1"

[0782] (Claim 1)

[0783] A means of acquiring visual data,

[0784] An analysis means for analyzing gaze intensity and facial expressions based on acquired visual data,

[0785] A generation method that identifies interest trends based on analysis and generates personalized content,

[0786] A presentation means for delivering and presenting the generated content to a receiving device,

[0787] A system that includes this.

[0788] (Claim 2)

[0789] The system according to claim 1, comprising an analysis means for determining the frequency of smiles from acquired visual data.

[0790] (Claim 3)

[0791] The system according to claim 1, comprising a learning means for improving the content generation process based on multiple data analyses and results.

[0792] "Example 2 of combining an emotion engine"

[0793] (Claim 1)

[0794] A means of capturing visual data of the baby and parent,

[0795] An analytical means for analyzing the baby's gaze, facial expressions, and parental emotions based on captured visual data,

[0796] A means for generating videos for babies and parents based on analysis,

[0797] A presentation method for showing the generated video to the baby and parent,

[0798] A system that includes this.

[0799] (Claim 2)

[0800] The system according to claim 1, comprising analytical means for identifying the frequency of a baby's smiles and the emotional state of the parents from visual data.

[0801] (Claim 3)

[0802] The system according to claim 1, comprising a learning means for improving the video generation process using multiple visual data and analysis results.

[0803] "Application example 2 of combining emotional engines"

[0804] (Claim 1)

[0805] A shooting method that simultaneously captures the user's (parent's) visual data,

[0806] An analytical means for analyzing user emotions based on captured visual data,

[0807] A generation method that generates content suitable for both parent and child based on analyzed user emotional data and baby's visual data,

[0808] A means of presenting the generated content to the user and the baby,

[0809] A system that includes this.

[0810] (Claim 2)

[0811] The system according to claim 1, comprising analytical means for identifying the user's level of relaxation from visual data and reflecting this in the content generation process.

[0812] (Claim 3)

[0813] The system according to claim 1, comprising a learning means for improving the content generation process to suit the user and the baby using multiple visual data and analysis results. [Explanation of Symbols]

[0814] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of capturing the baby's visual data, An analysis means for analyzing the degree of gaze and facial expressions of a baby based on captured visual data, A means for generating videos for babies based on analysis, A means of presenting the generated video to the baby, A system that includes this.

2. The system according to claim 1, comprising an analytical means for determining the frequency of a baby's smiles from visual data.

3. The system according to claim 1, comprising a learning means for improving the video generation process using multiple visual data and analysis results.

Images