system

Abstract

We provide the system. [Solution] A means by which a user transmits a handwritten representation via a presenting device, A means for generating feature data using a machine learning model that analyzes the transmitted handwritten representation and absorbs its features, A method for selecting characters using eye-tracking technology, A means for generating handwritten-like representations by reflecting feature data on selected characters, A means for returning the generated handwritten-like representation to the presentation device, 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 method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance 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] There is a need to provide communication means that allows people with difficulty in handwriting due to muscle weakness, especially patients with muscle diseases, to easily and flexibly use their own handwritten characters without being restricted by conventional handwriting input. The lack of such means hinders the free information transmission in the daily lives of these patients, and there is a demand for the development of a system that reduces the resulting psychological burden.

Means for Solving the Problems

[0005] This invention provides a system that transmits handwritten expression samples via a display device and absorbs the features of the handwriting using a machine learning model that analyzes the received samples. Furthermore, it enables user character selection using eye-tracking technology, generates a handwritten-like representation by reflecting the previously analyzed features in the selected character, and transmits it to the display device. Through this series of processes, a handwritten-like representation is obtained, reducing the burden on users who have difficulty writing by hand while maintaining individual expressiveness.

[0006] A "presentation device" is a device or apparatus used by a user to input or receive information.

[0007] "Handwritten expression" refers to the shapes of letters and figures created by an individual using a pen, stylus, or other writing instrument.

[0008] A "machine learning model" is an algorithm or system that automatically learns specific patterns and features using large amounts of data, and performs predictions and analyses based on future data.

[0009] "Feature data" refers to information that extracts, describes, or records the unique stylistic and geometric features contained in handwritten representations.

[0010] "Eye-tracking technology" is a technology that detects the user's gaze direction and eye movements, and uses that information to control device operations and interfaces.

[0011] "Handwriting-like representations" are characters or figures generated by imitating the characteristics of existing handwriting representations, and which retain the features of the original handwriting style. [Brief explanation of the drawing]

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

Embodiments for Carrying Out the Invention

[0013] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0015] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

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

[0017] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

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

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

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

[0022] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

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

[0030] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] This invention provides a system that allows users with muscle weakness who have difficulty with handwriting input to select characters using eye-tracking technology and generate character representations that are faithful to their own handwriting style. This system mainly consists of a display device and a server, and utilizes machine learning models to learn the user's handwriting characteristics and provide handwriting-like representations.

[0034] As an example of how it works, the user first scans a sample of their handwriting using a presentation device and sends it to the server. The server analyzes the received handwriting and generates feature data such as character shape and style using a machine learning model. In particular, it captures and stores data on each individual's pen pressure, character curves, and style attributes.

[0035] Next, the user uses a display device equipped with eye-tracking technology to select the desired character on the screen using their eyes. Once the eye-tracking position information is sent to the server, a handwritten-like representation is generated based on the accumulated handwriting feature data according to the selected character. The generated representation is displayed on the display device in real time, allowing the user to instantly obtain a character that looks as if they wrote it themselves.

[0036] For example, if a user selects "thank you" using eye-tracking input, the server uses pre-learned handwriting data to generate the string "thank you" in the user's handwriting style and sends it to the display device. This process allows users to create documents while preserving the unique characteristics of their individual handwriting, without physically writing the characters.

[0037] This system not only digitally reproduces the user's handwriting style but can also accommodate new combinations of characters and expressions, enabling more natural and personalized digital communication.

[0038] The following describes the processing flow.

[0039] Step 1:

[0040] The user prepares a digital sample of their handwritten expression using a display device, scans or photographs it, and saves it to the device. Then, they upload that data from the device to the server.

[0041] Step 2:

[0042] The server analyzes the received handwritten expression samples and uses a machine learning model to identify features such as character shape, curves, pen pressure, and style data. The identified features are stored in a feature database for each user.

[0043] Step 3:

[0044] The user uses a device to select a character on the screen using eye-tracking technology to choose from the displayed characters. The eye-tracking data is acquired in real time by the device.

[0045] Step 4:

[0046] The device transfers the eye-tracking data it acquires to the server, which then generates handwritten-like characters based on previously accumulated feature data for the selected characters. These characters are generated by mimicking the user's handwriting style.

[0047] Step 5:

[0048] The server generates handwritten-like character data and sends it to the terminal. The terminal receives this data and immediately displays it to the user on the screen. The user can then see the result and feel as if they have written it themselves.

[0049] (Example 1)

[0050] 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."

[0051] For users who have difficulty with handwriting input due to reasons such as muscle weakness, the challenge is to enable natural digital text input while preserving their individual handwriting style. Furthermore, improving the accuracy of eye-tracking input and providing diverse and natural expressions that reflect individual styles are also required.

[0052] 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.

[0053] In this invention, the server includes means for scanning an individual's handwriting style and transmitting it to an integrator, means for analyzing feature information from image data and deriving feature information using a generative model, and means for selecting characters using eye-tracking technology. This makes it possible to quickly and accurately generate digital representations while maintaining the individual's style, just like handwriting.

[0054] "Personal handwriting style" refers to elements such as the shape of letters, pen pressure, and curve of lines that are unique to a particular user when they handwrite letters or symbols.

[0055] A "data integrator" refers to a computer system used for receiving, processing, and transmitting digital data. It typically functions as a server.

[0056] "Image data" refers to data that represents handwritten characters and symbols in a digital format so that they can be processed by other systems.

[0057] "Feature information" refers to data extracted to describe an individual's handwriting pattern, such as pen pressure, line length, and style.

[0058] A "generative model" refers to a machine learning model or algorithm used to generate characters by mimicking handwriting styles.

[0059] "Eye-tracking technology" refers to technology that tracks the user's eye movements and uses that information to input data.

[0060] "Handwriting-like representation" refers to the representation of characters and shapes generated in a digital environment to resemble the user's handwriting style.

[0061] "Resending" refers to the process of sending data or information that has already been sent. It is typically used to return data to the user's device.

[0062] This invention is a system for users who have difficulty with handwriting input due to muscle weakness or other reasons, enabling them to digitally reproduce their own handwriting style. It mainly consists of an integrator (server), terminals, and a display device, and utilizes a generative AI model.

[0063] The user first uses a presentation device to digitally scan handwritten text on paper or a display. A scanner or high-resolution camera can be used for this purpose. For example, the user can scan a piece of paper with the word "thank you" written on it. The terminal then transmits the digitized image data to a data collection unit.

[0064] The server analyzes the received image data and extracts feature information unique to each handwritten character. This analysis uses machine learning frameworks such as TENSORFLOW® and PyTorch. As a result, features of individual handwriting styles, such as character shape, pressure, and curves, are accumulated as data.

[0065] Next, the user uses their gaze to select characters on the screen using a display device equipped with eye-tracking technology. The eye-tracking technology identifies the user's gaze position, and this information is sent to the server. The server identifies the selected character and generates a handwritten-like representation based on the already constructed feature information.

[0066] The generated handwritten-like representation is sent back to the terminal and displayed on the display device in real time. The user can see the characters displayed in a style that looks as if they were handwritten by them.

[0067] For example, if a user selects the word "hello" using eye-tracking input, the server can generate the word "hello" according to the prompt "Generate the word 'hello' in the user's unique handwriting style" and send it to the terminal.

[0068] This format allows users to input and display digital characters without physically writing, while maintaining their own handwriting style. It also enables natural and diverse digital communication that reflects individual handwriting styles.

[0069] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0070] Step 1:

[0071] The user scans handwritten content on paper or a screen using a display device. The input consists of handwritten letters and shapes, for example, a piece of paper with "Thank you" written on it. The terminal converts this handwritten sample into a high-resolution digital image format. This results in image capture, which becomes the input data for the server.

[0072] Step 2:

[0073] The server receives digital images transmitted from the terminal. Using the received image data as input, image processing techniques are applied to analyze the shape data of characters and figures. Specifically, image edge detection and feature extraction algorithms are used to generate handwritten-style feature information. This feature information is the output data used in the next step.

[0074] Step 3:

[0075] The user operates a display device with eye-tracking capabilities and selects characters displayed on the screen using their gaze. The input is the user's gaze position data, which is acquired by the display device's camera sensor. Based on the gaze information, the terminal transmits the selected character to the server.

[0076] Step 4:

[0077] The server identifies selected characters from eye-tracking data and generates handwritten-like digital characters based on previously generated feature information. This process utilizes a generative AI model and applies the input prompt "Generate the selected characters in the user's unique handwriting style." The output is a digital character representation similar to the user's handwriting style.

[0078] Step 5:

[0079] The terminal receives handwritten-like digital characters transmitted from the server and displays them on the display device. This allows the user to see characters generated in their own handwriting style displayed on the screen in real time. The output is the displayed handwritten-style characters.

[0080] (Application Example 1)

[0081] 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."

[0082] The challenge is to generate digital signatures that faithfully reflect individual handwriting styles, even when users have difficulty with handwriting input due to muscle weakness or other reasons, and to enable their use in electronic transaction approval processes. Furthermore, the aim is to provide a system that utilizes eye-tracking technology to allow users to create digital signatures with natural operation.

[0083] 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.

[0084] In this invention, the server includes means for a user to transmit a handwritten representation via a display device, means for generating feature data using a machine learning model that analyzes the transmitted handwritten representation and absorbs its features, means for selecting characters using eye-tracking technology, and means for utilizing the generated handwritten-like representation in the electronic transaction approval process. This enables users to generate digital signatures in their own handwriting style and approve electronic transactions using only eye movements.

[0085] A "user" refers to a person who uses the system to digitize their handwriting style and participate in the approval process for electronic transactions.

[0086] A "display device" is a device that allows a user to select characters using their gaze and to check the generated, manually-like representations.

[0087] "Handwritten representation" refers to samples of characters and shapes based on actual handwriting styles provided by users.

[0088] A "machine learning model" refers to an artificial intelligence-based algorithm that analyzes a user's handwritten representation, learns its features, and extracts them.

[0089] "Eye-tracking technology" refers to a technology that detects the movement of a user's eyes and allows them to select items on a digital interface using their gaze.

[0090] "Handwritten-like representations" refer to handwritten-style signatures and letters expressed in a digital environment, reflecting user characteristic data.

[0091] The "electronic transaction approval process" is a procedure that uses digital signatures to verify and authenticate transactions in e-commerce.

[0092] This invention provides a novel method for users to reproduce their own handwriting style in a digital environment. The system consists of an eye-tracking display device, a server running a machine learning model, and an interface for receiving user input.

[0093] The user first imports their handwritten representation into the system via a display device. This is done by capturing samples written on paper or a digital pad using a digital scanner or camera. The imported handwritten representation is sent to a server and analyzed by a machine learning model. The machine learning model uses a platform such as "AWS® Machine Learning Services" to extract feature data such as pen pressure and stroke patterns.

[0094] When a user selects a character on a display device using eye-tracking technology, that selection information is transmitted to a server. Based on the accumulated feature data, the server generates a manually analogous representation of the selected character and returns it to the display device. Tobii Eye Tracking technology is used for eye tracking.

[0095] As a concrete example, in a supermarket self-checkout system, a user might use a display device to select "Tanaka" via eye-tracking input and authorize the electronic payment with the generated digital signature. This process uses the following prompt: "Generate a digital signature based on the handwriting sample provided by the user, using the character selected via eye-tracking. This signature must be faithful to the user's handwriting style. The area of ​​application is electronic transaction authorization."

[0096] This allows users to perform natural digital operations while preserving their individual handwriting characteristics, without the need for physical writing.

[0097] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0098] Step 1:

[0099] The user inputs handwritten representations using a display device. The device captures this as digital data, and the terminal uses its scanning function to generate image data of the handwritten characters and shapes. This image data is the input. The generated image data is transferred to the server as output.

[0100] Step 2:

[0101] The server analyzes the received image data. Using a machine learning model, it extracts features such as pen pressure and strokes from the handwritten image data and generates a feature dataset. This process employs image processing algorithms, with image data as input and a feature dataset as output.

[0102] Step 3:

[0103] The user selects characters on the screen using the eye-tracking function of their display device. The terminal acquires the user's eye-tracking data and sends the selected character information to the server. The input is eye-tracking data, and the output is the selected character information.

[0104] Step 4:

[0105] The server uses selected character information and pre-generated feature data to generate a handwritten-like representation using a generative AI model. In this process, the feature data is modified to replicate the user's handwriting style, creating a new digital signature. The input is character information and feature data, and the output is a handwritten-like representation.

[0106] Step 5:

[0107] The generated manual analogue is sent to a display device and displayed in real time by the terminal. The user can instantly verify the digital signature. The input is the manual analogue, and the output is the displayed data.

[0108] Step 6:

[0109] The user uses this digital signature to complete the electronic transaction approval process. The server transfers the generated digital signature along with the transaction data to the electronic approval system. The inputs are a similar manual representation and transaction data, and the output is the transaction approval result.

[0110] 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.

[0111] This invention provides a system that enables users with impaired handwriting abilities to generate characters in their own handwriting style, incorporating an emotion engine into the process to allow for character expression that responds to the user's emotions. This system is constructed using a presentation device, a server, and an emotion engine.

[0112] To use the system, the user first prepares a handwritten representation sample using a presentation device, scans or captures the sample into the device, and sends it to the server. The server accepts this information, analyzes the handwritten features using a machine learning model, and generates feature data.

[0113] Next, the user selects characters using their gaze through the display device. The emotion engine analyzes the user's emotional state in real time from their facial expressions, voice, and other actions, and emotional data is transmitted to the terminal along with the gaze input. The server responds to the received gaze data and generates handwritten-like representations, taking into account the obtained handwriting feature data and the emotional data acquired from the emotion engine.

[0114] The handwritten approximations are styled and decorated according to the user's emotions. For example, if the user is happy, the letters may be given brighter colors and softer curves. The generated handwritten approximations are sent to the display device and displayed instantly, allowing the user to obtain a beautiful handwriting representation that reflects their emotions.

[0115] For example, if a user selects "thank you" and the emotion engine simultaneously detects a feeling of happiness, the server will implement a subtle smile emoji and bright colors into the text, generate the phrase "thank you," and visualize it on the user's device. This method enables even more personalized communication.

[0116] The following describes the processing flow.

[0117] Step 1:

[0118] The user uses a presentation device to scan or photograph their own handwritten sample and saves the data to the device. Then, the saved data is sent from the device to the server.

[0119] Step 2:

[0120] The server analyzes the received handwritten sample data and uses a machine learning model to extract handwriting features. Feature data such as character shape and pen pressure are recorded and stored in a database.

[0121] Step 3:

[0122] The display device tracks the user's gaze, allowing the user to select the desired character on the screen using their eyes. The device then acquires the location information of the user's gaze.

[0123] Step 4:

[0124] The device sends eye-tracking data to the server. At the same time, the emotion engine analyzes the user's emotions from their facial expressions and voice, and also transfers the resulting emotion data to the server.

[0125] Step 5:

[0126] The server generates handwritten-like representations of selected characters based on accumulated handwriting feature data and sentiment data. The style and decoration of the characters are applied according to the user's emotions.

[0127] Step 6:

[0128] The server generates a handwritten-like expression and sends it to the terminal. The terminal immediately displays this data on the display device, allowing the user to visually confirm the written expression that reflects their emotions.

[0129] (Example 2)

[0130] 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".

[0131] Traditionally, generating handwritten-style text for users with impaired handwriting abilities has been difficult, limiting the range of expression. Furthermore, it has been challenging to accurately reflect individual emotional states through personalized text representation that reflects user emotions. Additionally, combining eye-tracking selection with real-time emotion analysis to provide a personalized communication tool for users has been difficult.

[0132] 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.

[0133] In this invention, the server includes means for transmitting input expressions via a presentation device, means for generating feature information using machine learning means for analyzing the transmitted input expressions and extracting features, means for selecting information using gaze detection technology, means for acquiring the user's emotional state using a real-time emotion analysis engine, means for generating similar expressions by reflecting the feature information and emotion information on the selected information, and means for returning the generated similar expressions to the presentation device. This makes it possible for users to easily generate individual character expressions that match their emotions and handwriting style, thereby realizing personalized communication.

[0134] A "display device" is a display device that allows users to input handwritten expressions or visually confirm similar expressions that have been generated.

[0135] "Input representation" refers to data that represents the handwriting style provided by the user through a display device.

[0136] "Machine learning methods" refer to algorithms and models used to analyze a user's handwritten representation and extract feature information.

[0137] "Eye-tracking technology" is a technology that tracks the direction of a user's gaze and enables selections on the screen based on that.

[0138] An "emotion analysis engine" is a device or software that analyzes a user's facial expressions and voice in real time to detect and acquire their emotional state.

[0139] "Feature information" refers to a collection of data obtained as a result of analyzing the user's handwriting style.

[0140] "Similar representation" refers to the visual representation of generated characters that reflects the user's handwriting style and emotional information.

[0141] A "generative AI model" is an artificial intelligence algorithm that generates a specified output based on user input expressions and acquired data.

[0142] This invention is a system that allows users to generate textual representations based on their own handwriting style, while compensating for a decline in their handwriting ability, and to apply emotionally appropriate embellishments. This system consists of multiple elements, including a presentation device, a server, and an emotion analysis engine.

[0143] User

[0144] The user scans or directly inputs an input representation that reflects their own handwriting style using a display device. The user can then select a character from those displayed on the device using their gaze. Eye-tracking technology transmits the selected character to the server.

[0145] server

[0146] The server receives handwritten expressions transmitted from the presentation device. After receiving the data, it analyzes it using machine learning to generate feature information. Furthermore, the server combines gaze data obtained from the presentation device with the user's emotional state obtained using an emotion analysis engine to generate similar expressions. This uses an existing generative AI model, and prompts such as "Generate personalized characters according to the user's emotions" are used.

[0147] terminal

[0148] The device is equipped with an emotion analysis engine that uses a camera and microphone to acquire emotional data from the user. This allows for real-time analysis of changes in facial expressions and voice, and the emotional state is transmitted to a server. Based on this information, the server generates similar expressions, which are then immediately displayed on the display device.

[0149] Specific example

[0150] For example, if a user selects the expression "thank you," the emotion analysis engine detects a feeling of happiness, and the server generates a similar expression characterized by bright colors and soft curves, which is then displayed on the presentation device. This method allows the user to visually confirm customized text that reflects their own emotions.

[0151] In this way, users can easily and effectively generate text to express emotions, thereby improving the quality of communication.

[0152] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0153] Step 1:

[0154] User

[0155] The user creates handwritten-style input on the display device, generating digital data from it. Specifically, the user writes characters or symbols on the screen using a stylus pen. This data becomes the input, is scanned by the display device, and sent to the server.

[0156] Step 2:

[0157] server

[0158] The server receives handwritten input data sent by the user. Using machine learning techniques, it analyzes this data and extracts feature information such as character shape, pen pressure, and line thickness. The feature information generated by this analysis process becomes the output.

[0159] Step 3:

[0160] terminal

[0161] The device tracks the user's gaze and detects the selected character from those displayed on the input device. Specifically, it uses an eye-tracking sensor to determine where the user's gaze is pointing on the screen and sends this information to a server. This gaze data becomes the output.

[0162] Step 4:

[0163] terminal

[0164] The emotion analysis engine measures the user's facial expressions and voice in real time and analyzes their emotional state. Specifically, it performs facial analysis using a camera and voice analysis using a microphone, and sends the results to the server as emotion data.

[0165] Step 5:

[0166] server

[0167] The server integrates eye-tracking data, feature information, and emotion data, and uses a generative AI model to generate similar expressions. Based on the input information, it is given a prompt message such as "Create a handwritten expression corresponding to the detected emotion," and the generative AI model outputs a similar expression that matches the emotion and handwriting style.

[0168] Step 6:

[0169] terminal

[0170] The terminal receives similar expression data returned from the server and displays it on the display device. Specifically, it draws the data on the display, allowing the user to see characters that reflect their emotions.

[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 a "server" and the smart device 14 as a "terminal".

[0173] Users with diminished handwriting abilities find it difficult to generate written expressions that reflect their individuality and emotions. Furthermore, there is a lack of readily available means to easily generate written expressions that visually convey emotions and to effectively use them in visual media such as advertising. This results in a problem of the lack of emotional elements in visual expression.

[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 means for generating feature data using a machine learning model that analyzes handwritten representations and absorbs features, means for using an emotion analysis engine that analyzes emotions and generates emotion data, and means for generating handwritten-like representations by reflecting the feature data and emotion data on selected characters. This makes it possible to generate handwritten-like representations with styles and decorations that correspond to the user's emotions, and to express emotional elements in a visual medium.

[0176] A "display device" is an electronic device used by users to input handwritten expressions or to display handwritten-like expressions that have been generated.

[0177] "Handwritten representation" refers to information that a user inputs into a display device as handwritten characters or shapes.

[0178] A "machine learning model" is an algorithmic model that analyzes the features of handwritten representations and generates feature data.

[0179] "Feature data" refers to analytical information related to handwritten representations generated by machine learning models, including data on character style and individuality.

[0180] "Eye-tracking technology" is a technology that detects and tracks a user's gaze to assist in selecting text on a display device.

[0181] An "emotion analysis engine" is software that analyzes a user's facial expressions and voice to analyze their emotional state in real time.

[0182] "Emotional data" refers to data that indicates a user's emotional state, obtained using an emotion analysis engine.

[0183] "Handwriting-like representations" are character and graphic representations generated by reflecting handwriting feature data and sentiment data for selected characters.

[0184] The system for carrying out this invention aims to compensate for a user's declining handwriting ability and generate emotionally resonant handwritten expressions. This system utilizes a presentation device (e.g., a smartphone or tablet), through which the user inputs samples of handwritten expressions. The input information is sent to a server for processing.

[0185] The server uses a machine learning model to analyze handwritten representations submitted by users and generate handwriting feature data. This model utilizes widely adopted machine learning frameworks such as TensorFlow and PyTorch. This feature data is crucial as fundamental information for reproducing the user's handwriting style.

[0186] Furthermore, to understand the user's emotional state, an emotion analysis engine (e.g., Microsoft® Azure® Emotion API) is incorporated. It analyzes the user's facial expressions and voice obtained using the device's camera and microphone, generating emotion data in real time. This allows for an accurate capture of the user's current emotions.

[0187] The device utilizes eye-tracking technology to detect the character selected by the user. This technology analyzes the user's gaze using a camera and then makes a specific character selection on the display device.

[0188] The server combines the received gaze data, feature data, and emotion data to generate handwritten analogues. The generated analogues are styled and decorated according to the user's emotional state, and are returned to the presentation device for immediate display.

[0189] For example, if the emotion analysis engine detects that a user is feeling happy, the generated handwritten representation will use bright colors and curves. In this way, it becomes possible to visually express the emotions that the user intends to express.

[0190] Furthermore, examples of prompt statements for the generative AI model in this system are as follows:

[0191] "What kind of emotional style of ad do you generate? Users are excited."

[0192] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0193] Step 1:

[0194] The user uses a presentation device to input a sample of handwritten representation. The input sample is captured using the device's scanning function or touch interface. Digital data of the sample is created and sent to the server.

[0195] Step 2:

[0196] The server analyzes the digital data of the received handwritten sample. It runs a machine learning model (e.g., using TensorFlow or PyTorch) to analyze the handwriting style and other features and generate feature data. As a result of the analysis, vector data representing the handwriting style is obtained.

[0197] Step 3:

[0198] The device uses a camera to monitor the user's face, expressions, and voice, and acquires emotional data using an emotion analysis engine. For example, it uses the Microsoft Azure Emotion API to determine what emotion the user is experiencing and outputs the result as an emotion vector.

[0199] Step 4:

[0200] The device uses eye-tracking technology to identify the character selected by the user on the presented device. The identified character information is collected as input data and sent to the server.

[0201] Step 5:

[0202] The server integrates eye-tracking data, handwriting feature data, and emotion data to generate handwriting-like representations. Utilizing a generative AI model, it calculates new character styles based on the input data and outputs handwriting-like representations that reflect emotion.

[0203] Step 6:

[0204] The generated handwritten analogy data is immediately sent to the presenting device and displayed to the user. This allows the user to see a visual representation of their own emotions reflected in their handwritten text. This process can then be immediately used to create advertisements and personalized messages.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] [Second Embodiment]

[0209] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0210] 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.

[0211] 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).

[0212] 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.

[0213] 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.

[0214] 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).

[0215] 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.

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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.

[0220] 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".

[0221] This invention provides a system that allows users with muscle weakness who have difficulty with handwriting input to select characters using eye-tracking technology and generate character representations that are faithful to their own handwriting style. This system mainly consists of a display device and a server, and utilizes machine learning models to learn the user's handwriting characteristics and provide handwriting-like representations.

[0222] As an example of how it works, the user first scans a sample of their handwriting using a presentation device and sends it to the server. The server analyzes the received handwriting and generates feature data such as character shape and style using a machine learning model. In particular, it captures and stores data on each individual's pen pressure, character curves, and style attributes.

[0223] Next, the user uses a display device equipped with eye-tracking technology to select the desired character on the screen using their eyes. Once the eye-tracking position information is sent to the server, a handwritten-like representation is generated based on the accumulated handwriting feature data according to the selected character. The generated representation is displayed on the display device in real time, allowing the user to instantly obtain a character that looks as if they wrote it themselves.

[0224] For example, if a user selects "thank you" using eye-tracking input, the server uses pre-learned handwriting data to generate the string "thank you" in the user's handwriting style and sends it to the display device. This process allows users to create documents while preserving the unique characteristics of their individual handwriting, without physically writing the characters.

[0225] This system not only digitally reproduces the user's handwriting style but can also accommodate new combinations of characters and expressions, enabling more natural and personalized digital communication.

[0226] The following describes the processing flow.

[0227] Step 1:

[0228] The user prepares a digital sample of their handwritten expression using a display device, scans or photographs it, and saves it to the device. Then, they upload that data from the device to the server.

[0229] Step 2:

[0230] The server analyzes the received handwritten expression samples and uses a machine learning model to identify features such as character shape, curves, pen pressure, and style data. The identified features are stored in a feature database for each user.

[0231] Step 3:

[0232] The user uses a device to select a character on the screen using eye-tracking technology to choose from the displayed characters. The eye-tracking data is acquired in real time by the device.

[0233] Step 4:

[0234] The device transfers the eye-tracking data it acquires to the server, which then generates handwritten-like characters based on previously accumulated feature data for the selected characters. These characters are generated by mimicking the user's handwriting style.

[0235] Step 5:

[0236] The server generates handwritten-like character data and sends it to the terminal. The terminal receives this data and immediately displays it to the user on the screen. The user can then see the result and feel as if they have written it themselves.

[0237] (Example 1)

[0238] 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."

[0239] For users who have difficulty with handwriting input due to reasons such as muscle weakness, the challenge is to enable natural digital text input while preserving their individual handwriting style. Furthermore, improving the accuracy of eye-tracking input and providing diverse and natural expressions that reflect individual styles are also required.

[0240] 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.

[0241] In this invention, the server includes means for scanning an individual's handwriting style and transmitting it to an integrator, means for analyzing feature information from image data and deriving feature information using a generative model, and means for selecting characters using eye-tracking technology. This makes it possible to quickly and accurately generate digital representations while maintaining the individual's style, just like handwriting.

[0242] "Personal handwriting style" refers to elements such as the shape of letters, pen pressure, and curve of lines that are unique to a particular user when they handwrite letters or symbols.

[0243] A "data integrator" refers to a computer system used for receiving, processing, and transmitting digital data. It typically functions as a server.

[0244] "Image data" refers to data that represents handwritten characters and symbols in a digital format so that they can be processed by other systems.

[0245] "Feature information" refers to data extracted to describe an individual's handwriting pattern, such as pen pressure, line length, and style.

[0246] A "generative model" refers to a machine learning model or algorithm used to generate characters by mimicking handwriting styles.

[0247] "Eye-tracking technology" refers to technology that tracks the user's eye movements and uses that information to input data.

[0248] "Handwriting-like representation" refers to the representation of characters and shapes generated in a digital environment to resemble the user's handwriting style.

[0249] "Resending" refers to the process of sending data or information that has already been sent. It is typically used to return data to the user's device.

[0250] This invention is a system for users who have difficulty with handwriting input due to muscle weakness or other reasons, enabling them to digitally reproduce their own handwriting style. It mainly consists of an integrator (server), terminals, and a display device, and utilizes a generative AI model.

[0251] The user first uses a presentation device to digitally scan handwritten text on paper or a display. A scanner or high-resolution camera can be used for this purpose. For example, the user can scan a piece of paper with the word "thank you" written on it. The terminal then transmits the digitized image data to a data collection unit.

[0252] The server analyzes the received image data and extracts feature information unique to each handwritten character. This analysis uses machine learning frameworks such as TensorFlow and PyTorch. As a result, features of individual handwriting styles, such as character shape, pressure, and curves, are accumulated as data.

[0253] Next, the user uses their gaze to select characters on the screen using a display device equipped with eye-tracking technology. The eye-tracking technology identifies the user's gaze position, and this information is sent to the server. The server identifies the selected character and generates a handwritten-like representation based on the already constructed feature information.

[0254] The generated handwritten-like representation is sent back to the terminal and displayed on the display device in real time. The user can see the characters displayed in a style that looks as if they were handwritten by them.

[0255] For example, if a user selects the word "hello" using eye-tracking input, the server can generate the word "hello" according to the prompt "Generate the word 'hello' in the user's unique handwriting style" and send it to the terminal.

[0256] This format allows users to input and display digital characters without physically writing, while maintaining their own handwriting style. It also enables natural and diverse digital communication that reflects individual handwriting styles.

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

[0258] Step 1:

[0259] The user scans handwritten content on paper or a screen using a display device. The input consists of handwritten letters and shapes, for example, a piece of paper with "Thank you" written on it. The terminal converts this handwritten sample into a high-resolution digital image format. This results in image capture, which becomes the input data for the server.

[0260] Step 2:

[0261] The server receives digital images transmitted from the terminal. Using the received image data as input, image processing techniques are applied to analyze the shape data of characters and figures. Specifically, image edge detection and feature extraction algorithms are used to generate handwritten-style feature information. This feature information is the output data used in the next step.

[0262] Step 3:

[0263] The user operates a display device with eye-tracking capabilities and selects characters displayed on the screen using their gaze. The input is the user's gaze position data, which is acquired by the display device's camera sensor. Based on the gaze information, the terminal transmits the selected character to the server.

[0264] Step 4:

[0265] The server identifies selected characters from eye-tracking data and generates handwritten-like digital characters based on previously generated feature information. This process utilizes a generative AI model and applies the input prompt "Generate the selected characters in the user's unique handwriting style." The output is a digital character representation similar to the user's handwriting style.

[0266] Step 5:

[0267] The terminal receives handwritten-like digital characters transmitted from the server and displays them on the display device. This allows the user to see characters generated in their own handwriting style displayed on the screen in real time. The output is the displayed handwritten-style characters.

[0268] (Application Example 1)

[0269] 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."

[0270] The challenge is to generate digital signatures that faithfully reflect individual handwriting styles, even when users have difficulty with handwriting input due to muscle weakness or other reasons, and to enable their use in electronic transaction approval processes. Furthermore, the aim is to provide a system that utilizes eye-tracking technology to allow users to create digital signatures with natural operation.

[0271] 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.

[0272] In this invention, the server includes means for a user to transmit a handwritten representation via a display device, means for generating feature data using a machine learning model that analyzes the transmitted handwritten representation and absorbs its features, means for selecting characters using eye-tracking technology, and means for utilizing the generated handwritten-like representation in the electronic transaction approval process. This enables users to generate digital signatures in their own handwriting style and approve electronic transactions using only eye movements.

[0273] A "user" refers to a person who uses the system to digitize their handwriting style and participate in the approval process for electronic transactions.

[0274] A "display device" is a device that allows a user to select characters using their gaze and to check the generated, manually-like representations.

[0275] "Handwritten representation" refers to samples of characters and shapes based on actual handwriting styles provided by users.

[0276] A "machine learning model" refers to an artificial intelligence-based algorithm that analyzes a user's handwritten representation, learns its features, and extracts them.

[0277] "Eye-tracking technology" refers to a technology that detects the movement of a user's eyes and allows them to select items on a digital interface using their gaze.

[0278] "Handwritten-like representations" refer to handwritten-style signatures and letters expressed in a digital environment, reflecting user characteristic data.

[0279] The "electronic transaction approval process" is a procedure that uses digital signatures to verify and authenticate transactions in e-commerce.

[0280] This invention provides a new method for users to reproduce their own handwriting style in a digital environment. The system consists of a display device capable of eye tracking, a server that executes a machine learning model, and an interface that receives user input.

[0281] First, the user captures their own handwriting expression into the system via the display device. This is done by using a digital scanner or camera to capture samples written on paper or a digital pad. The captured handwriting expression is sent to the server and analyzed by the machine learning model. The machine learning model extracts feature data such as pen pressure and stroke patterns using a platform like "AWS Machine Learning Service".

[0282] When the user selects a character on the display device using eye tracking technology, the selection information is transferred to the server. Based on the accumulated feature data, the server generates a manually crafted similar expression of the selected character and returns it to the display device. "Tobii Eye Tracking" technology is used for eye tracking.

[0283] As a specific example, at the self-checkout in a supermarket, the user may use the display device to select "Tanaka" by eye input and approve the electronic payment with the generated digital signature. In this process, the prompt text "Please generate the characters selected by eye tracking as a digital signature based on the handwriting samples provided by the user. This signature must be faithful to the user's handwriting style. The applicable area is the approval of electronic transactions." is used.

[0284] This enables the user to perform digital and natural operations while maintaining individual handwriting characteristics without physically writing.

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

[0286] Step 1:

[0287] The user inputs handwritten representations using a display device. The device captures this as digital data, and the terminal uses its scanning function to generate image data of the handwritten characters and shapes. This image data is the input. The generated image data is transferred to the server as output.

[0288] Step 2:

[0289] The server analyzes the received image data. Using a machine learning model, it extracts features such as pen pressure and strokes from the handwritten image data and generates a feature dataset. This process employs image processing algorithms, with image data as input and a feature dataset as output.

[0290] Step 3:

[0291] The user selects characters on the screen using the eye-tracking function of their display device. The terminal acquires the user's eye-tracking data and sends the selected character information to the server. The input is eye-tracking data, and the output is the selected character information.

[0292] Step 4:

[0293] The server uses selected character information and pre-generated feature data to generate a handwritten-like representation using a generative AI model. In this process, the feature data is modified to replicate the user's handwriting style, creating a new digital signature. The input is character information and feature data, and the output is a handwritten-like representation.

[0294] Step 5:

[0295] The generated manual analogue is sent to a display device and displayed in real time by the terminal. The user can instantly verify the digital signature. The input is the manual analogue, and the output is the displayed data.

[0296] Step 6:

[0297] The user uses this digital signature to complete the electronic transaction approval process. The server transfers the generated digital signature along with the transaction data to the electronic approval system. The inputs are a similar manual representation and transaction data, and the output is the transaction approval result.

[0298] 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.

[0299] This invention provides a system that enables users with impaired handwriting abilities to generate characters in their own handwriting style, incorporating an emotion engine into the process to allow for character expression that responds to the user's emotions. This system is constructed using a presentation device, a server, and an emotion engine.

[0300] To use the system, the user first prepares a handwritten representation sample using a presentation device, scans or captures the sample into the device, and sends it to the server. The server accepts this information, analyzes the handwritten features using a machine learning model, and generates feature data.

[0301] Next, the user selects characters using their gaze through the display device. The emotion engine analyzes the user's emotional state in real time from their facial expressions, voice, and other actions, and emotional data is transmitted to the terminal along with the gaze input. The server responds to the received gaze data and generates handwritten-like representations, taking into account the obtained handwriting feature data and the emotional data acquired from the emotion engine.

[0302] The handwritten approximations are styled and decorated according to the user's emotions. For example, if the user is happy, the letters may be given brighter colors and softer curves. The generated handwritten approximations are sent to the display device and displayed instantly, allowing the user to obtain a beautiful handwriting representation that reflects their emotions.

[0303] As a specific example, when the user selects "Thank you" and at the same time the happiness is detected by the emotion engine, the server implements a slightly smiling emoji or a bright color tone into the text, generates the phrase "Thank you", and visualizes it on the presentation device. By this method, further personalized communication becomes possible.

[0304] The following describes the process flow.

[0305] Step 1:

[0306] The user uses the presentation device to scan or photograph their own handwritten sample and saves the data on the terminal. Next, the saved data is transmitted from the terminal to the server.

[0307] Step 2:

[0308] The server analyzes the received handwritten sample data and extracts the characteristics of the handwriting using a machine learning model. Record the character shape, pen pressure, etc. as feature data and accumulate this information in the database.

[0309] Step 3:

[0310] The presentation device tracks the user's line of sight, and the user selects the characters to be selected on the screen with their line of sight. The position information of the line of sight is obtained by the terminal.

[0311] Step 4:

[0312] The terminal transmits the line-of-sight data to the server. At that time, the emotion engine analyzes the emotion from the user's expression and voice, and the obtained emotion data is also transferred to the server.

[0313] Step 5:

[0314] Based on the accumulated handwriting feature data and emotion data for the selected characters, the server generates a handwritten-like expression. The style and decoration of the characters are applied according to the user's emotion.

[0315] Step 6:

[0316] The server generates a handwritten-like expression and sends it to the terminal. The terminal immediately displays this data on the display device, allowing the user to visually confirm the written expression that reflects their emotions.

[0317] (Example 2)

[0318] 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".

[0319] Traditionally, generating handwritten-style text for users with impaired handwriting abilities has been difficult, limiting the range of expression. Furthermore, it has been challenging to accurately reflect individual emotional states through personalized text representation that reflects user emotions. Additionally, combining eye-tracking selection with real-time emotion analysis to provide a personalized communication tool for users has been difficult.

[0320] 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.

[0321] In this invention, the server includes means for transmitting input expressions via a presentation device, means for generating feature information using machine learning means for analyzing the transmitted input expressions and extracting features, means for selecting information using gaze detection technology, means for acquiring the user's emotional state using a real-time emotion analysis engine, means for generating similar expressions by reflecting the feature information and emotion information on the selected information, and means for returning the generated similar expressions to the presentation device. This makes it possible for users to easily generate individual character expressions that match their emotions and handwriting style, thereby realizing personalized communication.

[0322] A "display device" is a display device that allows users to input handwritten expressions or visually confirm similar expressions that have been generated.

[0323] "Input representation" refers to data that represents the handwriting style provided by the user through a display device.

[0324] "Machine learning methods" refer to algorithms and models used to analyze a user's handwritten representation and extract feature information.

[0325] "Eye-tracking technology" is a technology that tracks the direction of a user's gaze and enables selections on the screen based on that.

[0326] An "emotion analysis engine" is a device or software that analyzes a user's facial expressions and voice in real time to detect and acquire their emotional state.

[0327] "Feature information" refers to a collection of data obtained as a result of analyzing the user's handwriting style.

[0328] "Similar representation" refers to the visual representation of generated characters that reflects the user's handwriting style and emotional information.

[0329] A "generative AI model" is an artificial intelligence algorithm that generates a specified output based on user input expressions and acquired data.

[0330] This invention is a system that allows users to generate textual representations based on their own handwriting style, while compensating for a decline in their handwriting ability, and to apply emotionally appropriate embellishments. This system consists of multiple elements, including a presentation device, a server, and an emotion analysis engine.

[0331] User

[0332] The user scans or directly inputs an input representation that reflects their own handwriting style using a display device. The user can then select a character from those displayed on the device using their gaze. Eye-tracking technology transmits the selected character to the server.

[0333] server

[0334] The server receives handwritten expressions transmitted from the presentation device. After receiving the data, it analyzes it using machine learning to generate feature information. Furthermore, the server combines gaze data obtained from the presentation device with the user's emotional state obtained using an emotion analysis engine to generate similar expressions. This uses an existing generative AI model, and prompts such as "Generate personalized characters according to the user's emotions" are used.

[0335] terminal

[0336] The device is equipped with an emotion analysis engine that uses a camera and microphone to acquire emotional data from the user. This allows for real-time analysis of changes in facial expressions and voice, and the emotional state is transmitted to a server. Based on this information, the server generates similar expressions, which are then immediately displayed on the display device.

[0337] Specific example

[0338] For example, if a user selects the expression "thank you," the emotion analysis engine detects a feeling of happiness, and the server generates a similar expression characterized by bright colors and soft curves, which is then displayed on the presentation device. This method allows the user to visually confirm customized text that reflects their own emotions.

[0339] In this way, users can easily and effectively generate text to express emotions, thereby improving the quality of communication.

[0340] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0341] Step 1:

[0342] User

[0343] The user creates handwritten-style input on the display device, generating digital data from it. Specifically, the user writes characters or symbols on the screen using a stylus pen. This data becomes the input, is scanned by the display device, and sent to the server.

[0344] Step 2:

[0345] server

[0346] The server receives handwritten input data sent by the user. Using machine learning techniques, it analyzes this data and extracts feature information such as character shape, pen pressure, and line thickness. The feature information generated by this analysis process becomes the output.

[0347] Step 3:

[0348] terminal

[0349] The device tracks the user's gaze and detects the selected character from those displayed on the input device. Specifically, it uses an eye-tracking sensor to determine where the user's gaze is pointing on the screen and sends this information to a server. This gaze data becomes the output.

[0350] Step 4:

[0351] terminal

[0352] The emotion analysis engine measures the user's facial expressions and voice in real time and analyzes their emotional state. Specifically, it performs facial analysis using a camera and voice analysis using a microphone, and sends the results to the server as emotion data.

[0353] Step 5:

[0354] server

[0355] The server integrates eye-tracking data, feature information, and emotion data, and uses a generative AI model to generate similar expressions. Based on the input information, it is given a prompt message such as "Create a handwritten expression corresponding to the detected emotion," and the generative AI model outputs a similar expression that matches the emotion and handwriting style.

[0356] Step 6:

[0357] terminal

[0358] The terminal receives similar expression data returned from the server and displays it on the display device. Specifically, it draws the data on the display, allowing the user to see characters that reflect their emotions.

[0359] (Application Example 2)

[0360] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0361] Users with diminished handwriting abilities find it difficult to generate written expressions that reflect their individuality and emotions. Furthermore, there is a lack of readily available means to easily generate written expressions that visually convey emotions and to effectively use them in visual media such as advertising. This results in a problem of the lack of emotional elements in visual expression.

[0362] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0363] In this invention, the server includes means for generating feature data using a machine learning model that analyzes handwritten representations and absorbs features, means for using an emotion analysis engine that analyzes emotions and generates emotion data, and means for generating handwritten-like representations by reflecting the feature data and emotion data on selected characters. This makes it possible to generate handwritten-like representations with styles and decorations that correspond to the user's emotions, and to express emotional elements in a visual medium.

[0364] A "display device" is an electronic device used by users to input handwritten expressions or to display handwritten-like expressions that have been generated.

[0365] "Handwritten representation" refers to information that a user inputs into a display device as handwritten characters or shapes.

[0366] A "machine learning model" is an algorithmic model that analyzes the features of handwritten representations and generates feature data.

[0367] "Feature data" refers to analytical information related to handwritten representations generated by machine learning models, including data on character style and individuality.

[0368] "Eye-tracking technology" is a technology that detects and tracks a user's gaze to assist in selecting text on a display device.

[0369] An "emotion analysis engine" is software that analyzes a user's facial expressions and voice to analyze their emotional state in real time.

[0370] "Emotional data" refers to data that indicates a user's emotional state, obtained using an emotion analysis engine.

[0371] "Handwriting-like representations" are character and graphic representations generated by reflecting handwriting feature data and sentiment data for selected characters.

[0372] The system for carrying out this invention aims to compensate for a user's declining handwriting ability and generate emotionally resonant handwritten expressions. This system utilizes a presentation device (e.g., a smartphone or tablet), through which the user inputs samples of handwritten expressions. The input information is sent to a server for processing.

[0373] The server uses a machine learning model to analyze handwritten representations submitted by users and generate handwriting feature data. This model utilizes widely adopted machine learning frameworks such as TensorFlow and PyTorch. This feature data is crucial as fundamental information for reproducing the user's handwriting style.

[0374] Furthermore, to understand the user's emotional state, an emotion analysis engine (e.g., Microsoft Azure's Emotion API) is integrated. It analyzes the user's facial expressions and voice obtained using the device's camera and microphone, generating emotion data in real time. This allows for an accurate capture of the user's current emotions.

[0375] The device utilizes eye-tracking technology to detect the character selected by the user. This technology analyzes the user's gaze using a camera and then makes a specific character selection on the display device.

[0376] The server combines the received gaze data, feature data, and emotion data to generate handwritten analogues. The generated analogues are styled and decorated according to the user's emotional state, and are returned to the presentation device for immediate display.

[0377] For example, if the emotion analysis engine detects that a user is feeling happy, the generated handwritten representation will use bright colors and curves. In this way, it becomes possible to visually express the emotions that the user intends to express.

[0378] Furthermore, examples of prompt statements for the generative AI model in this system are as follows:

[0379] "What kind of emotional style of ad do you generate? Users are excited."

[0380] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0381] Step 1:

[0382] The user uses a presentation device to input a sample of handwritten representation. The input sample is captured using the device's scanning function or touch interface. Digital data of the sample is created and sent to the server.

[0383] Step 2:

[0384] The server analyzes the digital data of the received handwritten sample. It runs a machine learning model (e.g., using TensorFlow or PyTorch) to analyze the handwriting style and other features and generate feature data. As a result of the analysis, vector data representing the handwriting style is obtained.

[0385] Step 3:

[0386] The device uses a camera to monitor the user's face, expressions, and voice, and acquires emotional data using an emotion analysis engine. For example, it uses the Microsoft Azure Emotion API to determine what emotion the user is experiencing and outputs the result as an emotion vector.

[0387] Step 4:

[0388] The device uses eye-tracking technology to identify the character selected by the user on the presented device. The identified character information is collected as input data and sent to the server.

[0389] Step 5:

[0390] The server integrates eye-tracking data, handwriting feature data, and emotion data to generate handwriting-like representations. Utilizing a generative AI model, it calculates new character styles based on the input data and outputs handwriting-like representations that reflect emotion.

[0391] Step 6:

[0392] The generated handwritten analogy data is immediately sent to the presenting device and displayed to the user. This allows the user to see a visual representation of their own emotions reflected in their handwritten text. This process can then be immediately used to create advertisements and personalized messages.

[0393] 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.

[0394] 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.

[0395] 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.

[0396] [Third Embodiment]

[0397] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0398] 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.

[0399] 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).

[0400] 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.

[0401] 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.

[0402] 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).

[0403] 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.

[0404] 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.

[0405] 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.

[0406] 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.

[0407] 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.

[0408] 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".

[0409] This invention provides a system that allows users with muscle weakness who have difficulty with handwriting input to select characters using eye-tracking technology and generate character representations that are faithful to their own handwriting style. This system mainly consists of a display device and a server, and utilizes machine learning models to learn the user's handwriting characteristics and provide handwriting-like representations.

[0410] As an example of how it works, the user first scans a sample of their handwriting using a presentation device and sends it to the server. The server analyzes the received handwriting and generates feature data such as character shape and style using a machine learning model. In particular, it captures and stores data on each individual's pen pressure, character curves, and style attributes.

[0411] Next, the user uses a display device equipped with eye-tracking technology to select the desired character on the screen using their eyes. Once the eye-tracking position information is sent to the server, a handwritten-like representation is generated based on the accumulated handwriting feature data according to the selected character. The generated representation is displayed on the display device in real time, allowing the user to instantly obtain a character that looks as if they wrote it themselves.

[0412] For example, if a user selects "thank you" using eye-tracking input, the server uses pre-learned handwriting data to generate the string "thank you" in the user's handwriting style and sends it to the display device. This process allows users to create documents while preserving the unique characteristics of their individual handwriting, without physically writing the characters.

[0413] This system not only digitally reproduces the user's handwriting style but can also accommodate new combinations of characters and expressions, enabling more natural and personalized digital communication.

[0414] The following describes the processing flow.

[0415] Step 1:

[0416] The user prepares a digital sample of their handwritten expression using a display device, scans or photographs it, and saves it to the device. Then, they upload that data from the device to the server.

[0417] Step 2:

[0418] The server analyzes the received handwritten expression samples and uses a machine learning model to identify features such as character shape, curves, pen pressure, and style data. The identified features are stored in a feature database for each user.

[0419] Step 3:

[0420] The user uses a device to select a character on the screen using eye-tracking technology to choose from the displayed characters. The eye-tracking data is acquired in real time by the device.

[0421] Step 4:

[0422] The device transfers the eye-tracking data it acquires to the server, which then generates handwritten-like characters based on previously accumulated feature data for the selected characters. These characters are generated by mimicking the user's handwriting style.

[0423] Step 5:

[0424] The server generates handwritten-like character data and sends it to the terminal. The terminal receives this data and immediately displays it to the user on the screen. The user can then see the result and feel as if they have written it themselves.

[0425] (Example 1)

[0426] 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."

[0427] For users who have difficulty with handwriting input due to reasons such as muscle weakness, the challenge is to enable natural digital text input while preserving their individual handwriting style. Furthermore, improving the accuracy of eye-tracking input and providing diverse and natural expressions that reflect individual styles are also required.

[0428] 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.

[0429] In this invention, the server includes means for scanning an individual's handwriting style and transmitting it to an integrator, means for analyzing feature information from image data and deriving feature information using a generative model, and means for selecting characters using eye-tracking technology. This makes it possible to quickly and accurately generate digital representations while maintaining the individual's style, just like handwriting.

[0430] "Personal handwriting style" refers to elements such as the shape of letters, pen pressure, and curve of lines that are unique to a particular user when they handwrite letters or symbols.

[0431] A "data integrator" refers to a computer system used for receiving, processing, and transmitting digital data. It typically functions as a server.

[0432] "Image data" refers to data that represents handwritten characters and symbols in a digital format so that they can be processed by other systems.

[0433] "Feature information" refers to data extracted to describe an individual's handwriting pattern, such as pen pressure, line length, and style.

[0434] A "generative model" refers to a machine learning model or algorithm used to generate characters by mimicking handwriting styles.

[0435] "Eye-tracking technology" refers to technology that tracks the user's eye movements and uses that information to input data.

[0436] "Handwriting-like representation" refers to the representation of characters and shapes generated in a digital environment to resemble the user's handwriting style.

[0437] "Resending" refers to the process of sending data or information that has already been sent. It is typically used to return data to the user's device.

[0438] This invention is a system for users who have difficulty with handwriting input due to muscle weakness or other reasons, enabling them to digitally reproduce their own handwriting style. It mainly consists of an integrator (server), terminals, and a display device, and utilizes a generative AI model.

[0439] The user first uses a presentation device to digitally scan handwritten text on paper or a display. A scanner or high-resolution camera can be used for this purpose. For example, the user can scan a piece of paper with the word "thank you" written on it. The terminal then transmits the digitized image data to a data collection unit.

[0440] The server analyzes the received image data and extracts feature information unique to each handwritten character. This analysis uses machine learning frameworks such as TensorFlow and PyTorch. As a result, features of individual handwriting styles, such as character shape, pressure, and curves, are accumulated as data.

[0441] Next, the user uses their gaze to select characters on the screen using a display device equipped with eye-tracking technology. The eye-tracking technology identifies the user's gaze position, and this information is sent to the server. The server identifies the selected character and generates a handwritten-like representation based on the already constructed feature information.

[0442] The generated handwritten-like representation is sent back to the terminal and displayed on the display device in real time. The user can see the characters displayed in a style that looks as if they were handwritten by them.

[0443] For example, if a user selects the word "hello" using eye-tracking input, the server can generate the word "hello" according to the prompt "Generate the word 'hello' in the user's unique handwriting style" and send it to the terminal.

[0444] This format allows users to input and display digital characters without physically writing, while maintaining their own handwriting style. It also enables natural and diverse digital communication that reflects individual handwriting styles.

[0445] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0446] Step 1:

[0447] The user scans handwritten content on paper or a screen using a display device. The input consists of handwritten letters and shapes, for example, a piece of paper with "Thank you" written on it. The terminal converts this handwritten sample into a high-resolution digital image format. This results in image capture, which becomes the input data for the server.

[0448] Step 2:

[0449] The server receives digital images transmitted from the terminal. Using the received image data as input, image processing techniques are applied to analyze the shape data of characters and figures. Specifically, image edge detection and feature extraction algorithms are used to generate handwritten-style feature information. This feature information is the output data used in the next step.

[0450] Step 3:

[0451] The user operates a display device with eye-tracking capabilities and selects characters displayed on the screen using their gaze. The input is the user's gaze position data, which is acquired by the display device's camera sensor. Based on the gaze information, the terminal transmits the selected character to the server.

[0452] Step 4:

[0453] The server identifies selected characters from eye-tracking data and generates handwritten-like digital characters based on previously generated feature information. This process utilizes a generative AI model and applies the input prompt "Generate the selected characters in the user's unique handwriting style." The output is a digital character representation similar to the user's handwriting style.

[0454] Step 5:

[0455] The terminal receives handwritten-like digital characters transmitted from the server and displays them on the display device. This allows the user to see characters generated in their own handwriting style displayed on the screen in real time. The output is the displayed handwritten-style characters.

[0456] (Application Example 1)

[0457] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0458] The challenge is to generate digital signatures that faithfully reflect individual handwriting styles, even when users have difficulty with handwriting input due to muscle weakness or other reasons, and to enable their use in electronic transaction approval processes. Furthermore, the aim is to provide a system that utilizes eye-tracking technology to allow users to create digital signatures with natural operation.

[0459] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0460] In this invention, the server includes means for a user to transmit a handwritten representation via a display device, means for generating feature data using a machine learning model that analyzes the transmitted handwritten representation and absorbs its features, means for selecting characters using eye-tracking technology, and means for utilizing the generated handwritten-like representation in the electronic transaction approval process. This enables users to generate digital signatures in their own handwriting style and approve electronic transactions using only eye movements.

[0461] A "user" refers to a person who uses the system to digitize their handwriting style and participate in the approval process for electronic transactions.

[0462] A "display device" is a device that allows a user to select characters using their gaze and to check the generated, manually-like representations.

[0463] "Handwritten representation" refers to samples of characters and shapes based on actual handwriting styles provided by users.

[0464] A "machine learning model" refers to an artificial intelligence-based algorithm that analyzes a user's handwritten representation, learns its features, and extracts them.

[0465] "Eye-tracking technology" refers to a technology that detects the movement of a user's eyes and allows them to select items on a digital interface using their gaze.

[0466] "Handwritten-like representations" refer to handwritten-style signatures and letters expressed in a digital environment, reflecting user characteristic data.

[0467] The "electronic transaction approval process" is a procedure that uses digital signatures to verify and authenticate transactions in e-commerce.

[0468] This invention provides a novel method for users to reproduce their own handwriting style in a digital environment. The system consists of an eye-tracking display device, a server running a machine learning model, and an interface for receiving user input.

[0469] The user first imports their handwritten representation into the system via a display device. This is done by capturing samples written on paper or a digital pad using a digital scanner or camera. The imported handwritten representation is sent to a server and analyzed by a machine learning model. The machine learning model uses a platform such as "AWS Machine Learning Services" to extract feature data such as pen pressure and stroke patterns.

[0470] When a user selects a character on a display device using eye-tracking technology, that selection information is transmitted to a server. Based on the accumulated feature data, the server generates a manually analogous representation of the selected character and returns it to the display device. Tobii Eye Tracking technology is used for eye tracking.

[0471] As a concrete example, in a supermarket self-checkout system, a user might use a display device to select "Tanaka" via eye-tracking input and authorize the electronic payment with the generated digital signature. This process uses the following prompt: "Generate a digital signature based on the handwriting sample provided by the user, using the character selected via eye-tracking. This signature must be faithful to the user's handwriting style. The area of ​​application is electronic transaction authorization."

[0472] This allows users to perform natural digital operations while preserving their individual handwriting characteristics, without the need for physical writing.

[0473] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0474] Step 1:

[0475] The user inputs handwritten representations using a display device. The device captures this as digital data, and the terminal uses its scanning function to generate image data of the handwritten characters and shapes. This image data is the input. The generated image data is transferred to the server as output.

[0476] Step 2:

[0477] The server analyzes the received image data. Using a machine learning model, it extracts features such as pen pressure and strokes from the handwritten image data and generates a feature dataset. This process employs image processing algorithms, with image data as input and a feature dataset as output.

[0478] Step 3:

[0479] The user selects characters on the screen using the eye-tracking function of their display device. The terminal acquires the user's eye-tracking data and sends the selected character information to the server. The input is eye-tracking data, and the output is the selected character information.

[0480] Step 4:

[0481] The server uses selected character information and pre-generated feature data to generate a handwritten-like representation using a generative AI model. In this process, the feature data is modified to replicate the user's handwriting style, creating a new digital signature. The input is character information and feature data, and the output is a handwritten-like representation.

[0482] Step 5:

[0483] The generated manual analogue is sent to a display device and displayed in real time by the terminal. The user can instantly verify the digital signature. The input is the manual analogue, and the output is the displayed data.

[0484] Step 6:

[0485] The user uses this digital signature to complete the electronic transaction approval process. The server transfers the generated digital signature along with the transaction data to the electronic approval system. The inputs are a similar manual representation and transaction data, and the output is the transaction approval result.

[0486] 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.

[0487] This invention provides a system that enables users with impaired handwriting abilities to generate characters in their own handwriting style, incorporating an emotion engine into the process to allow for character expression that responds to the user's emotions. This system is constructed using a presentation device, a server, and an emotion engine.

[0488] To use the system, the user first prepares a handwritten representation sample using a presentation device, scans or captures the sample into the device, and sends it to the server. The server accepts this information, analyzes the handwritten features using a machine learning model, and generates feature data.

[0489] Next, the user selects characters using their gaze through the display device. The emotion engine analyzes the user's emotional state in real time from their facial expressions, voice, and other actions, and emotional data is transmitted to the terminal along with the gaze input. The server responds to the received gaze data and generates handwritten-like representations, taking into account the obtained handwriting feature data and the emotional data acquired from the emotion engine.

[0490] The handwritten approximations are styled and decorated according to the user's emotions. For example, if the user is happy, the letters may be given brighter colors and softer curves. The generated handwritten approximations are sent to the display device and displayed instantly, allowing the user to obtain a beautiful handwriting representation that reflects their emotions.

[0491] For example, if a user selects "thank you" and the emotion engine simultaneously detects a feeling of happiness, the server will implement a subtle smile emoji and bright colors into the text, generate the phrase "thank you," and visualize it on the user's device. This method enables even more personalized communication.

[0492] The following describes the processing flow.

[0493] Step 1:

[0494] The user uses a presentation device to scan or photograph their own handwritten sample and saves the data to the device. Then, the saved data is sent from the device to the server.

[0495] Step 2:

[0496] The server analyzes the received handwritten sample data and uses a machine learning model to extract handwriting features. Feature data such as character shape and pen pressure are recorded and stored in a database.

[0497] Step 3:

[0498] The display device tracks the user's gaze, allowing the user to select the desired character on the screen using their eyes. The device then acquires the location information of the user's gaze.

[0499] Step 4:

[0500] The device sends eye-tracking data to the server. At the same time, the emotion engine analyzes the user's emotions from their facial expressions and voice, and also transfers the resulting emotion data to the server.

[0501] Step 5:

[0502] The server generates handwritten-like representations of selected characters based on accumulated handwriting feature data and sentiment data. The style and decoration of the characters are applied according to the user's emotions.

[0503] Step 6:

[0504] The server generates a handwritten-like expression and sends it to the terminal. The terminal immediately displays this data on the display device, allowing the user to visually confirm the written expression that reflects their emotions.

[0505] (Example 2)

[0506] 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."

[0507] Traditionally, generating handwritten-style text for users with impaired handwriting abilities has been difficult, limiting the range of expression. Furthermore, it has been challenging to accurately reflect individual emotional states through personalized text representation that reflects user emotions. Additionally, combining eye-tracking selection with real-time emotion analysis to provide a personalized communication tool for users has been difficult.

[0508] 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.

[0509] In this invention, the server includes means for transmitting input expressions via a presentation device, means for generating feature information using machine learning means for analyzing the transmitted input expressions and extracting features, means for selecting information using gaze detection technology, means for acquiring the user's emotional state using a real-time emotion analysis engine, means for generating similar expressions by reflecting the feature information and emotion information on the selected information, and means for returning the generated similar expressions to the presentation device. This makes it possible for users to easily generate individual character expressions that match their emotions and handwriting style, thereby realizing personalized communication.

[0510] A "display device" is a display device that allows users to input handwritten expressions or visually confirm similar expressions that have been generated.

[0511] "Input representation" refers to data that represents the handwriting style provided by the user through a display device.

[0512] "Machine learning methods" refer to algorithms and models used to analyze a user's handwritten representation and extract feature information.

[0513] "Eye-tracking technology" is a technology that tracks the direction of a user's gaze and enables selections on the screen based on that.

[0514] An "emotion analysis engine" is a device or software that analyzes a user's facial expressions and voice in real time to detect and acquire their emotional state.

[0515] "Feature information" refers to a collection of data obtained as a result of analyzing the user's handwriting style.

[0516] "Similar representation" refers to the visual representation of generated characters that reflects the user's handwriting style and emotional information.

[0517] A "generative AI model" is an artificial intelligence algorithm that generates a specified output based on user input expressions and acquired data.

[0518] This invention is a system that allows users to generate textual representations based on their own handwriting style, while compensating for a decline in their handwriting ability, and to apply emotionally appropriate embellishments. This system consists of multiple elements, including a presentation device, a server, and an emotion analysis engine.

[0519] User

[0520] The user scans or directly inputs an input representation that reflects their own handwriting style using a display device. The user can then select a character from those displayed on the device using their gaze. Eye-tracking technology transmits the selected character to the server.

[0521] server

[0522] The server receives handwritten expressions transmitted from the presentation device. After receiving the data, it analyzes it using machine learning to generate feature information. Furthermore, the server combines gaze data obtained from the presentation device with the user's emotional state obtained using an emotion analysis engine to generate similar expressions. This uses an existing generative AI model, and prompts such as "Generate personalized characters according to the user's emotions" are used.

[0523] terminal

[0524] The device is equipped with an emotion analysis engine that uses a camera and microphone to acquire emotional data from the user. This allows for real-time analysis of changes in facial expressions and voice, and the emotional state is transmitted to a server. Based on this information, the server generates similar expressions, which are then immediately displayed on the display device.

[0525] Specific example

[0526] For example, if a user selects the expression "thank you," the emotion analysis engine detects a feeling of happiness, and the server generates a similar expression characterized by bright colors and soft curves, which is then displayed on the presentation device. This method allows the user to visually confirm customized text that reflects their own emotions.

[0527] In this way, users can easily and effectively generate text to express emotions, thereby improving the quality of communication.

[0528] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0529] Step 1:

[0530] User

[0531] The user creates handwritten-style input on the display device, generating digital data from it. Specifically, the user writes characters or symbols on the screen using a stylus pen. This data becomes the input, is scanned by the display device, and sent to the server.

[0532] Step 2:

[0533] server

[0534] The server receives handwritten input data sent by the user. Using machine learning techniques, it analyzes this data and extracts feature information such as character shape, pen pressure, and line thickness. The feature information generated by this analysis process becomes the output.

[0535] Step 3:

[0536] terminal

[0537] The device tracks the user's gaze and detects the selected character from those displayed on the input device. Specifically, it uses an eye-tracking sensor to determine where the user's gaze is pointing on the screen and sends this information to a server. This gaze data becomes the output.

[0538] Step 4:

[0539] terminal

[0540] The emotion analysis engine measures the user's facial expressions and voice in real time and analyzes their emotional state. Specifically, it performs facial analysis using a camera and voice analysis using a microphone, and sends the results to the server as emotion data.

[0541] Step 5:

[0542] server

[0543] The server integrates eye-tracking data, feature information, and emotion data, and uses a generative AI model to generate similar expressions. Based on the input information, it is given a prompt message such as "Create a handwritten expression corresponding to the detected emotion," and the generative AI model outputs a similar expression that matches the emotion and handwriting style.

[0544] Step 6:

[0545] terminal

[0546] The terminal receives similar expression data returned from the server and displays it on the display device. Specifically, it draws the data on the display, allowing the user to see characters that reflect their emotions.

[0547] (Application Example 2)

[0548] 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."

[0549] Users with diminished handwriting abilities find it difficult to generate written expressions that reflect their individuality and emotions. Furthermore, there is a lack of readily available means to easily generate written expressions that visually convey emotions and to effectively use them in visual media such as advertising. This results in a problem of the lack of emotional elements in visual expression.

[0550] 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.

[0551] In this invention, the server includes means for generating feature data using a machine learning model that analyzes handwritten representations and absorbs features, means for using an emotion analysis engine that analyzes emotions and generates emotion data, and means for generating handwritten-like representations by reflecting the feature data and emotion data on selected characters. This makes it possible to generate handwritten-like representations with styles and decorations that correspond to the user's emotions, and to express emotional elements in a visual medium.

[0552] A "display device" is an electronic device used by users to input handwritten expressions or to display handwritten-like expressions that have been generated.

[0553] "Handwritten representation" refers to information that a user inputs into a display device as handwritten characters or shapes.

[0554] A "machine learning model" is an algorithmic model that analyzes the features of handwritten representations and generates feature data.

[0555] "Feature data" refers to analytical information related to handwritten representations generated by machine learning models, including data on character style and individuality.

[0556] "Eye-tracking technology" is a technology that detects and tracks a user's gaze to assist in selecting text on a display device.

[0557] An "emotion analysis engine" is software that analyzes a user's facial expressions and voice to analyze their emotional state in real time.

[0558] "Emotional data" refers to data that indicates a user's emotional state, obtained using an emotion analysis engine.

[0559] "Handwriting-like representations" are character and graphic representations generated by reflecting handwriting feature data and sentiment data for selected characters.

[0560] The system for carrying out this invention aims to compensate for a user's declining handwriting ability and generate emotionally resonant handwritten expressions. This system utilizes a presentation device (e.g., a smartphone or tablet), through which the user inputs samples of handwritten expressions. The input information is sent to a server for processing.

[0561] The server uses a machine learning model to analyze handwritten representations submitted by users and generate handwriting feature data. This model utilizes widely adopted machine learning frameworks such as TensorFlow and PyTorch. This feature data is crucial as fundamental information for reproducing the user's handwriting style.

[0562] Furthermore, to understand the user's emotional state, an emotion analysis engine (e.g., Microsoft Azure's Emotion API) is integrated. It analyzes the user's facial expressions and voice obtained using the device's camera and microphone, generating emotion data in real time. This allows for an accurate capture of the user's current emotions.

[0563] The device utilizes eye-tracking technology to detect the character selected by the user. This technology analyzes the user's gaze using a camera and then makes a specific character selection on the display device.

[0564] The server combines the received gaze data, feature data, and emotion data to generate handwritten analogues. The generated analogues are styled and decorated according to the user's emotional state, and are returned to the presentation device for immediate display.

[0565] For example, if the emotion analysis engine detects that a user is feeling happy, the generated handwritten representation will use bright colors and curves. In this way, it becomes possible to visually express the emotions that the user intends to express.

[0566] Furthermore, examples of prompt statements for the generative AI model in this system are as follows:

[0567] "What kind of emotional style of ad do you generate? Users are excited."

[0568] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0569] Step 1:

[0570] The user uses a presentation device to input a sample of handwritten representation. The input sample is captured using the device's scanning function or touch interface. Digital data of the sample is created and sent to the server.

[0571] Step 2:

[0572] The server analyzes the digital data of the received handwritten sample. It runs a machine learning model (e.g., using TensorFlow or PyTorch) to analyze the handwriting style and other features and generate feature data. As a result of the analysis, vector data representing the handwriting style is obtained.

[0573] Step 3:

[0574] The device uses a camera to monitor the user's face, expressions, and voice, and acquires emotional data using an emotion analysis engine. For example, it uses the Microsoft Azure Emotion API to determine what emotion the user is experiencing and outputs the result as an emotion vector.

[0575] Step 4:

[0576] The device uses eye-tracking technology to identify the character selected by the user on the presented device. The identified character information is collected as input data and sent to the server.

[0577] Step 5:

[0578] The server integrates eye-tracking data, handwriting feature data, and emotion data to generate handwriting-like representations. Utilizing a generative AI model, it calculates new character styles based on the input data and outputs handwriting-like representations that reflect emotion.

[0579] Step 6:

[0580] The generated handwritten analogy data is immediately sent to the presenting device and displayed to the user. This allows the user to see a visual representation of their own emotions reflected in their handwritten text. This process can then be immediately used to create advertisements and personalized messages.

[0581] 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.

[0582] 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.

[0583] 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.

[0584] [Fourth Embodiment]

[0585] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0586] 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.

[0587] 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).

[0588] 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.

[0589] 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.

[0590] 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).

[0591] 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.

[0592] 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.

[0593] 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.

[0594] 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.

[0595] 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.

[0596] 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.

[0597] 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".

[0598] This invention provides a system that allows users with muscle weakness who have difficulty with handwriting input to select characters using eye-tracking technology and generate character representations that are faithful to their own handwriting style. This system mainly consists of a display device and a server, and utilizes machine learning models to learn the user's handwriting characteristics and provide handwriting-like representations.

[0599] As an example of how it works, the user first scans a sample of their handwriting using a presentation device and sends it to the server. The server analyzes the received handwriting and generates feature data such as character shape and style using a machine learning model. In particular, it captures and stores data on each individual's pen pressure, character curves, and style attributes.

[0600] Next, the user uses a display device equipped with eye-tracking technology to select the desired character on the screen using their eyes. Once the eye-tracking position information is sent to the server, a handwritten-like representation is generated based on the accumulated handwriting feature data according to the selected character. The generated representation is displayed on the display device in real time, allowing the user to instantly obtain a character that looks as if they wrote it themselves.

[0601] For example, if a user selects "thank you" using eye-tracking input, the server uses pre-learned handwriting data to generate the string "thank you" in the user's handwriting style and sends it to the display device. This process allows users to create documents while preserving the unique characteristics of their individual handwriting, without physically writing the characters.

[0602] This system not only digitally reproduces the user's handwriting style but can also accommodate new combinations of characters and expressions, enabling more natural and personalized digital communication.

[0603] The following describes the processing flow.

[0604] Step 1:

[0605] The user prepares a digital sample of their handwritten expression using a display device, scans or photographs it, and saves it to the device. Then, they upload that data from the device to the server.

[0606] Step 2:

[0607] The server analyzes the received handwritten expression samples and uses a machine learning model to identify features such as character shape, curves, pen pressure, and style data. The identified features are stored in a feature database for each user.

[0608] Step 3:

[0609] The user uses a device to select a character on the screen using eye-tracking technology to choose from the displayed characters. The eye-tracking data is acquired in real time by the device.

[0610] Step 4:

[0611] The device transfers the eye-tracking data it acquires to the server, which then generates handwritten-like characters based on previously accumulated feature data for the selected characters. These characters are generated by mimicking the user's handwriting style.

[0612] Step 5:

[0613] The server generates handwritten-like character data and sends it to the terminal. The terminal receives this data and immediately displays it to the user on the screen. The user can then see the result and feel as if they have written it themselves.

[0614] (Example 1)

[0615] 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".

[0616] For users who have difficulty with handwriting input due to reasons such as muscle weakness, the challenge is to enable natural digital text input while preserving their individual handwriting style. Furthermore, improving the accuracy of eye-tracking input and providing diverse and natural expressions that reflect individual styles are also required.

[0617] 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.

[0618] In this invention, the server includes means for scanning an individual's handwriting style and transmitting it to an integrator, means for analyzing feature information from image data and deriving feature information using a generative model, and means for selecting characters using eye-tracking technology. This makes it possible to quickly and accurately generate digital representations while maintaining the individual's style, just like handwriting.

[0619] "Personal handwriting style" refers to elements such as the shape of letters, pen pressure, and curve of lines that are unique to a particular user when they handwrite letters or symbols.

[0620] A "data integrator" refers to a computer system used for receiving, processing, and transmitting digital data. It typically functions as a server.

[0621] "Image data" refers to data that represents handwritten characters and symbols in a digital format so that they can be processed by other systems.

[0622] "Feature information" refers to data extracted to describe an individual's handwriting pattern, such as pen pressure, line length, and style.

[0623] A "generative model" refers to a machine learning model or algorithm used to generate characters by mimicking handwriting styles.

[0624] "Eye-tracking technology" refers to technology that tracks the user's eye movements and uses that information to input data.

[0625] "Handwriting-like representation" refers to the representation of characters and shapes generated in a digital environment to resemble the user's handwriting style.

[0626] "Resending" refers to the process of sending data or information that has already been sent. It is typically used to return data to the user's device.

[0627] This invention is a system for users who have difficulty with handwriting input due to muscle weakness or other reasons, enabling them to digitally reproduce their own handwriting style. It mainly consists of an integrator (server), terminals, and a display device, and utilizes a generative AI model.

[0628] The user first uses a presentation device to digitally scan handwritten text on paper or a display. A scanner or high-resolution camera can be used for this purpose. For example, the user can scan a piece of paper with the word "thank you" written on it. The terminal then transmits the digitized image data to a data collection unit.

[0629] The server analyzes the received image data and extracts feature information unique to each handwritten character. This analysis uses machine learning frameworks such as TensorFlow and PyTorch. As a result, features of individual handwriting styles, such as character shape, pressure, and curves, are accumulated as data.

[0630] Next, the user uses their gaze to select characters on the screen using a display device equipped with eye-tracking technology. The eye-tracking technology identifies the user's gaze position, and this information is sent to the server. The server identifies the selected character and generates a handwritten-like representation based on the already constructed feature information.

[0631] The generated handwritten-like representation is sent back to the terminal and displayed on the display device in real time. The user can see the characters displayed in a style that looks as if they were handwritten by them.

[0632] For example, if a user selects the word "hello" using eye-tracking input, the server can generate the word "hello" according to the prompt "Generate the word 'hello' in the user's unique handwriting style" and send it to the terminal.

[0633] This format allows users to input and display digital characters without physically writing, while maintaining their own handwriting style. It also enables natural and diverse digital communication that reflects individual handwriting styles.

[0634] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0635] Step 1:

[0636] The user scans handwritten content on paper or a screen using a display device. The input consists of handwritten letters and shapes, for example, a piece of paper with "Thank you" written on it. The terminal converts this handwritten sample into a high-resolution digital image format. This results in image capture, which becomes the input data for the server.

[0637] Step 2:

[0638] The server receives digital images transmitted from the terminal. Using the received image data as input, image processing techniques are applied to analyze the shape data of characters and figures. Specifically, image edge detection and feature extraction algorithms are used to generate handwritten-style feature information. This feature information is the output data used in the next step.

[0639] Step 3:

[0640] The user operates a display device with eye-tracking capabilities and selects characters displayed on the screen using their gaze. The input is the user's gaze position data, which is acquired by the display device's camera sensor. Based on the gaze information, the terminal transmits the selected character to the server.

[0641] Step 4:

[0642] The server identifies selected characters from eye-tracking data and generates handwritten-like digital characters based on previously generated feature information. This process utilizes a generative AI model and applies the input prompt "Generate the selected characters in the user's unique handwriting style." The output is a digital character representation similar to the user's handwriting style.

[0643] Step 5:

[0644] The terminal receives handwritten-like digital characters transmitted from the server and displays them on the display device. This allows the user to see characters generated in their own handwriting style displayed on the screen in real time. The output is the displayed handwritten-style characters.

[0645] (Application Example 1)

[0646] 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".

[0647] The challenge is to generate digital signatures that faithfully reflect individual handwriting styles, even when users have difficulty with handwriting input due to muscle weakness or other reasons, and to enable their use in electronic transaction approval processes. Furthermore, the aim is to provide a system that utilizes eye-tracking technology to allow users to create digital signatures with natural operation.

[0648] 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.

[0649] In this invention, the server includes means for a user to transmit a handwritten representation via a display device, means for generating feature data using a machine learning model that analyzes the transmitted handwritten representation and absorbs its features, means for selecting characters using eye-tracking technology, and means for utilizing the generated handwritten-like representation in the electronic transaction approval process. This enables users to generate digital signatures in their own handwriting style and approve electronic transactions using only eye movements.

[0650] A "user" refers to a person who uses the system to digitize their handwriting style and participate in the approval process for electronic transactions.

[0651] A "display device" is a device that allows a user to select characters using their gaze and to check the generated, manually-like representations.

[0652] "Handwritten representation" refers to samples of characters and shapes based on actual handwriting styles provided by users.

[0653] A "machine learning model" refers to an artificial intelligence-based algorithm that analyzes a user's handwritten representation, learns its features, and extracts them.

[0654] "Eye-tracking technology" refers to a technology that detects the movement of a user's eyes and allows them to select items on a digital interface using their gaze.

[0655] "Handwritten-like representations" refer to handwritten-style signatures and letters expressed in a digital environment, reflecting user characteristic data.

[0656] The "electronic transaction approval process" is a procedure that uses digital signatures to verify and authenticate transactions in e-commerce.

[0657] This invention provides a novel method for users to reproduce their own handwriting style in a digital environment. The system consists of an eye-tracking display device, a server running a machine learning model, and an interface for receiving user input.

[0658] The user first imports their handwritten representation into the system via a display device. This is done by capturing samples written on paper or a digital pad using a digital scanner or camera. The imported handwritten representation is sent to a server and analyzed by a machine learning model. The machine learning model uses a platform such as "AWS Machine Learning Services" to extract feature data such as pen pressure and stroke patterns.

[0659] When a user selects a character on a display device using eye-tracking technology, that selection information is transmitted to a server. Based on the accumulated feature data, the server generates a manually analogous representation of the selected character and returns it to the display device. Tobii Eye Tracking technology is used for eye tracking.

[0660] As a concrete example, in a supermarket self-checkout system, a user might use a display device to select "Tanaka" via eye-tracking input and authorize the electronic payment with the generated digital signature. This process uses the following prompt: "Generate a digital signature based on the handwriting sample provided by the user, using the character selected via eye-tracking. This signature must be faithful to the user's handwriting style. The area of ​​application is electronic transaction authorization."

[0661] This allows users to perform natural digital operations while preserving their individual handwriting characteristics, without the need for physical writing.

[0662] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0663] Step 1:

[0664] The user inputs handwritten representations using a display device. The device captures this as digital data, and the terminal uses its scanning function to generate image data of the handwritten characters and shapes. This image data is the input. The generated image data is transferred to the server as output.

[0665] Step 2:

[0666] The server analyzes the received image data. Using a machine learning model, it extracts features such as pen pressure and strokes from the handwritten image data and generates a feature dataset. This process employs image processing algorithms, with image data as input and a feature dataset as output.

[0667] Step 3:

[0668] The user selects characters on the screen using the eye-tracking function of their display device. The terminal acquires the user's eye-tracking data and sends the selected character information to the server. The input is eye-tracking data, and the output is the selected character information.

[0669] Step 4:

[0670] The server uses selected character information and pre-generated feature data to generate a handwritten-like representation using a generative AI model. In this process, the feature data is modified to replicate the user's handwriting style, creating a new digital signature. The input is character information and feature data, and the output is a handwritten-like representation.

[0671] Step 5:

[0672] The generated manual analogue is sent to a display device and displayed in real time by the terminal. The user can instantly verify the digital signature. The input is the manual analogue, and the output is the displayed data.

[0673] Step 6:

[0674] The user uses this digital signature to complete the electronic transaction approval process. The server transfers the generated digital signature along with the transaction data to the electronic approval system. The inputs are a similar manual representation and transaction data, and the output is the transaction approval result.

[0675] 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.

[0676] This invention provides a system that enables users with impaired handwriting abilities to generate characters in their own handwriting style, incorporating an emotion engine into the process to allow for character expression that responds to the user's emotions. This system is constructed using a presentation device, a server, and an emotion engine.

[0677] To use the system, the user first prepares a handwritten representation sample using a presentation device, scans or captures the sample into the device, and sends it to the server. The server accepts this information, analyzes the handwritten features using a machine learning model, and generates feature data.

[0678] Next, the user selects characters using their gaze through the display device. The emotion engine analyzes the user's emotional state in real time from their facial expressions, voice, and other actions, and emotional data is transmitted to the terminal along with the gaze input. The server responds to the received gaze data and generates handwritten-like representations, taking into account the obtained handwriting feature data and the emotional data acquired from the emotion engine.

[0679] The handwritten approximations are styled and decorated according to the user's emotions. For example, if the user is happy, the letters may be given brighter colors and softer curves. The generated handwritten approximations are sent to the display device and displayed instantly, allowing the user to obtain a beautiful handwriting representation that reflects their emotions.

[0680] For example, if a user selects "thank you" and the emotion engine simultaneously detects a feeling of happiness, the server will implement a subtle smile emoji and bright colors into the text, generate the phrase "thank you," and visualize it on the user's device. This method enables even more personalized communication.

[0681] The following describes the processing flow.

[0682] Step 1:

[0683] The user uses a presentation device to scan or photograph their own handwritten sample and saves the data to the device. Then, the saved data is sent from the device to the server.

[0684] Step 2:

[0685] The server analyzes the received handwritten sample data and uses a machine learning model to extract handwriting features. Feature data such as character shape and pen pressure are recorded and stored in a database.

[0686] Step 3:

[0687] The display device tracks the user's gaze, allowing the user to select the desired character on the screen using their eyes. The device then acquires the location information of the user's gaze.

[0688] Step 4:

[0689] The device sends eye-tracking data to the server. At the same time, the emotion engine analyzes the user's emotions from their facial expressions and voice, and also transfers the resulting emotion data to the server.

[0690] Step 5:

[0691] The server generates handwritten-like representations of selected characters based on accumulated handwriting feature data and sentiment data. The style and decoration of the characters are applied according to the user's emotions.

[0692] Step 6:

[0693] The server generates a handwritten-like expression and sends it to the terminal. The terminal immediately displays this data on the display device, allowing the user to visually confirm the written expression that reflects their emotions.

[0694] (Example 2)

[0695] 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".

[0696] Traditionally, generating handwritten-style text for users with impaired handwriting abilities has been difficult, limiting the range of expression. Furthermore, it has been challenging to accurately reflect individual emotional states through personalized text representation that reflects user emotions. Additionally, combining eye-tracking selection with real-time emotion analysis to provide a personalized communication tool for users has been difficult.

[0697] 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.

[0698] In this invention, the server includes means for transmitting input expressions via a presentation device, means for generating feature information using machine learning means for analyzing the transmitted input expressions and extracting features, means for selecting information using gaze detection technology, means for acquiring the user's emotional state using a real-time emotion analysis engine, means for generating similar expressions by reflecting the feature information and emotion information on the selected information, and means for returning the generated similar expressions to the presentation device. This makes it possible for users to easily generate individual character expressions that match their emotions and handwriting style, thereby realizing personalized communication.

[0699] A "display device" is a display device that allows users to input handwritten expressions or visually confirm similar expressions that have been generated.

[0700] "Input representation" refers to data that represents the handwriting style provided by the user through a display device.

[0701] "Machine learning methods" refer to algorithms and models used to analyze a user's handwritten representation and extract feature information.

[0702] "Eye-tracking technology" is a technology that tracks the direction of a user's gaze and enables selections on the screen based on that.

[0703] An "emotion analysis engine" is a device or software that analyzes a user's facial expressions and voice in real time to detect and acquire their emotional state.

[0704] "Feature information" refers to a collection of data obtained as a result of analyzing the user's handwriting style.

[0705] "Similar representation" refers to the visual representation of generated characters that reflects the user's handwriting style and emotional information.

[0706] A "generative AI model" is an artificial intelligence algorithm that generates a specified output based on user input expressions and acquired data.

[0707] This invention is a system that allows users to generate textual representations based on their own handwriting style, while compensating for a decline in their handwriting ability, and to apply emotionally appropriate embellishments. This system consists of multiple elements, including a presentation device, a server, and an emotion analysis engine.

[0708] User

[0709] The user scans or directly inputs an input representation that reflects their own handwriting style using a display device. The user can then select a character from those displayed on the device using their gaze. Eye-tracking technology transmits the selected character to the server.

[0710] server

[0711] The server receives handwritten expressions transmitted from the presentation device. After receiving the data, it analyzes it using machine learning to generate feature information. Furthermore, the server combines gaze data obtained from the presentation device with the user's emotional state obtained using an emotion analysis engine to generate similar expressions. This uses an existing generative AI model, and prompts such as "Generate personalized characters according to the user's emotions" are used.

[0712] terminal

[0713] The device is equipped with an emotion analysis engine that uses a camera and microphone to acquire emotional data from the user. This allows for real-time analysis of changes in facial expressions and voice, and the emotional state is transmitted to a server. Based on this information, the server generates similar expressions, which are then immediately displayed on the display device.

[0714] Specific example

[0715] For example, if a user selects the expression "thank you," the emotion analysis engine detects a feeling of happiness, and the server generates a similar expression characterized by bright colors and soft curves, which is then displayed on the presentation device. This method allows the user to visually confirm customized text that reflects their own emotions.

[0716] In this way, users can easily and effectively generate text to express emotions, thereby improving the quality of communication.

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

[0718] Step 1:

[0719] User

[0720] The user creates handwritten-style input on the display device, generating digital data from it. Specifically, the user writes characters or symbols on the screen using a stylus pen. This data becomes the input, is scanned by the display device, and sent to the server.

[0721] Step 2:

[0722] server

[0723] The server receives handwritten input data sent by the user. Using machine learning techniques, it analyzes this data and extracts feature information such as character shape, pen pressure, and line thickness. The feature information generated by this analysis process becomes the output.

[0724] Step 3:

[0725] terminal

[0726] The device tracks the user's gaze and detects the selected character from those displayed on the input device. Specifically, it uses an eye-tracking sensor to determine where the user's gaze is pointing on the screen and sends this information to a server. This gaze data becomes the output.

[0727] Step 4:

[0728] terminal

[0729] The emotion analysis engine measures the user's facial expressions and voice in real time and analyzes their emotional state. Specifically, it performs facial analysis using a camera and voice analysis using a microphone, and sends the results to the server as emotion data.

[0730] Step 5:

[0731] server

[0732] The server integrates eye-tracking data, feature information, and emotion data, and uses a generative AI model to generate similar expressions. Based on the input information, it is given a prompt message such as "Create a handwritten expression corresponding to the detected emotion," and the generative AI model outputs a similar expression that matches the emotion and handwriting style.

[0733] Step 6:

[0734] terminal

[0735] The terminal receives similar expression data returned from the server and displays it on the display device. Specifically, it draws the data on the display, allowing the user to see characters that reflect their emotions.

[0736] (Application Example 2)

[0737] 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".

[0738] Users with diminished handwriting abilities find it difficult to generate written expressions that reflect their individuality and emotions. Furthermore, there is a lack of readily available means to easily generate written expressions that visually convey emotions and to effectively use them in visual media such as advertising. This results in a problem of the lack of emotional elements in visual expression.

[0739] 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.

[0740] In this invention, the server includes means for generating feature data using a machine learning model that analyzes handwritten representations and absorbs features, means for using an emotion analysis engine that analyzes emotions and generates emotion data, and means for generating handwritten-like representations by reflecting the feature data and emotion data on selected characters. This makes it possible to generate handwritten-like representations with styles and decorations that correspond to the user's emotions, and to express emotional elements in a visual medium.

[0741] A "display device" is an electronic device used by users to input handwritten expressions or to display handwritten-like expressions that have been generated.

[0742] "Handwritten representation" refers to information that a user inputs into a display device as handwritten characters or shapes.

[0743] A "machine learning model" is an algorithmic model that analyzes the features of handwritten representations and generates feature data.

[0744] "Feature data" refers to analytical information related to handwritten representations generated by machine learning models, including data on character style and individuality.

[0745] "Eye-tracking technology" is a technology that detects and tracks a user's gaze to assist in selecting text on a display device.

[0746] An "emotion analysis engine" is software that analyzes a user's facial expressions and voice to analyze their emotional state in real time.

[0747] "Emotional data" refers to data that indicates a user's emotional state, obtained using an emotion analysis engine.

[0748] "Handwriting-like representations" are character and graphic representations generated by reflecting handwriting feature data and sentiment data for selected characters.

[0749] The system for carrying out this invention aims to compensate for a user's declining handwriting ability and generate emotionally resonant handwritten expressions. This system utilizes a presentation device (e.g., a smartphone or tablet), through which the user inputs samples of handwritten expressions. The input information is sent to a server for processing.

[0750] The server uses a machine learning model to analyze handwritten representations submitted by users and generate handwriting feature data. This model utilizes widely adopted machine learning frameworks such as TensorFlow and PyTorch. This feature data is crucial as fundamental information for reproducing the user's handwriting style.

[0751] Furthermore, to understand the user's emotional state, an emotion analysis engine (e.g., Microsoft Azure's Emotion API) is integrated. It analyzes the user's facial expressions and voice obtained using the device's camera and microphone, generating emotion data in real time. This allows for an accurate capture of the user's current emotions.

[0752] The device utilizes eye-tracking technology to detect the character selected by the user. This technology analyzes the user's gaze using a camera and then makes a specific character selection on the display device.

[0753] The server combines the received gaze data, feature data, and emotion data to generate handwritten analogues. The generated analogues are styled and decorated according to the user's emotional state, and are returned to the presentation device for immediate display.

[0754] For example, if the emotion analysis engine detects that a user is feeling happy, the generated handwritten representation will use bright colors and curves. In this way, it becomes possible to visually express the emotions that the user intends to express.

[0755] Furthermore, examples of prompt statements for the generative AI model in this system are as follows:

[0756] "What kind of emotional style of ad do you generate? Users are excited."

[0757] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0758] Step 1:

[0759] The user uses a presentation device to input a sample of handwritten representation. The input sample is captured using the device's scanning function or touch interface. Digital data of the sample is created and sent to the server.

[0760] Step 2:

[0761] The server analyzes the digital data of the received handwritten sample. It runs a machine learning model (e.g., using TensorFlow or PyTorch) to analyze the handwriting style and other features and generate feature data. As a result of the analysis, vector data representing the handwriting style is obtained.

[0762] Step 3:

[0763] The device uses a camera to monitor the user's face, expressions, and voice, and acquires emotional data using an emotion analysis engine. For example, it uses the Microsoft Azure Emotion API to determine what emotion the user is experiencing and outputs the result as an emotion vector.

[0764] Step 4:

[0765] The device uses eye-tracking technology to identify the character selected by the user on the presented device. The identified character information is collected as input data and sent to the server.

[0766] Step 5:

[0767] The server integrates eye-tracking data, handwriting feature data, and emotion data to generate handwriting-like representations. Utilizing a generative AI model, it calculates new character styles based on the input data and outputs handwriting-like representations that reflect emotion.

[0768] Step 6:

[0769] The generated handwritten analogy data is immediately sent to the presenting device and displayed to the user. This allows the user to see a visual representation of their own emotions reflected in their handwritten text. This process can then be immediately used to create advertisements and personalized messages.

[0770] 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.

[0771] 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.

[0772] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0773] 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.

[0774] 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. In the upper and lower directions of the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. Also, the upper side of the concentric circles is where "pleasant" emotions are located, and the lower side is where "unpleasant" emotions are located. In this way, 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.

[0775] 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.

[0776] 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.

[0777] 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.

[0778] 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."

[0779] 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.

[0780] 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.

[0781] 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.

[0782] 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.

[0783] 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.

[0784] 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.

[0785] 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.

[0786] 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.

[0787] 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.

[0788] 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.

[0789] 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.

[0790] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0791] The following is further disclosed regarding the embodiments described above.

[0792] (Claim 1)

[0793] A means by which a user transmits a handwritten representation via a presenting device,

[0794] A means for generating feature data using a machine learning model that analyzes the transmitted handwritten representation and absorbs its features,

[0795] A method for selecting characters using eye-tracking technology,

[0796] A means for generating handwritten-like representations by reflecting feature data on selected characters,

[0797] A means for returning the generated handwritten-like representation to the presentation device,

[0798] A system that includes this.

[0799] (Claim 2)

[0800] The system according to claim 1, characterized by adding random elements to preserve individual features.

[0801] (Claim 3)

[0802] The system according to claim 1, which enables the generation of a series of handwritten representations, including figures, in a specific manner.

[0803] "Example 1"

[0804] (Claim 1)

[0805] A means of scanning an individual's handwritten style and sending it to a digitizer,

[0806] A means of analyzing feature information from image data and deriving feature information using a generative model,

[0807] A method for selecting characters using eye-tracking technology,

[0808] A means for creating a handwritten-like representation by applying characteristic information formed to selected characters,

[0809] A means for resending the created handwritten-like display to the accumulator,

[0810] A system that includes this.

[0811] (Claim 2)

[0812] The system according to claim 1, characterized in that each characteristic is maintained by adding a probabilistic element.

[0813] (Claim 3)

[0814] The system according to claim 1, which enables the creation of handwritten representations, including geometric shapes, in a specified manner.

[0815] "Application Example 1"

[0816] (Claim 1)

[0817] A means by which a user transmits a handwritten representation via a display device,

[0818] A means for generating feature data using a machine learning model that analyzes the transmitted handwritten representation and absorbs its features,

[0819] A method for selecting characters using eye-tracking technology,

[0820] A means for generating manually similar representations by reflecting feature data on selected characters,

[0821] A means for returning the generated manually generated similar expression to the display device,

[0822] A means of using manually generated similar expressions in the approval process of electronic transactions,

[0823] A system that includes this.

[0824] (Claim 2)

[0825] The system according to claim 1, characterized by adding random elements to preserve individual features.

[0826] (Claim 3)

[0827] The system according to claim 1, which enables the generation of a series of manual representations, including geometric shapes, in a specific manner and their use in approving electronic transactions.

[0828] "Example 2 of combining an emotion engine"

[0829] (Claim 1)

[0830] Means by which the user transmits an input representation via a presentation device,

[0831] A means for generating feature information using machine learning methods that analyze the transmitted input representation and extract features,

[0832] A means of selecting information using eye-tracking technology,

[0833] A means of acquiring a user's emotional state using a real-time emotion analysis engine,

[0834] A means for generating similar expressions by reflecting feature information and sentiment information on selected information,

[0835] Means for returning the generated similar expression to the presentation device,

[0836] A system that includes this.

[0837] (Claim 2)

[0838] The system according to claim 1, characterized in that it incorporates random elements and emotional elements to maintain individual characteristics.

[0839] (Claim 3)

[0840] The system according to claim 1, which enables the generation of a series of representations including actions by a specific algorithm.

[0841] "Application example 2 when combining with an emotional engine"

[0842] (Claim 1)

[0843] A means by which a user transmits a handwritten representation via a presenting device,

[0844] A means for generating feature data using a machine learning model that analyzes the transmitted handwritten representation and absorbs its features,

[0845] A method for selecting characters using eye-tracking technology,

[0846] A method using an emotion analysis engine that analyzes emotions and generates emotion data,

[0847] A means for generating handwritten-like representations by reflecting feature data and sentiment data on selected characters,

[0848] A means for returning the generated handwritten-like representation to the presentation device,

[0849] A system that includes this.

[0850] (Claim 2)

[0851] The system according to claim 1, characterized by adding random elements to preserve individual characteristics and applying emotion-based styles and decorations.

[0852] (Claim 3)

[0853] The system according to claim 1, which enables the generation of a series of handwritten representations, including figures, in a specific manner, accompanied by visual changes corresponding to emotions. [Explanation of Symbols]

[0854] 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 by which a user transmits a handwritten representation via a presenting device, A means for generating feature data using a machine learning model that analyzes the transmitted handwritten representation and absorbs its features, A method for selecting characters using eye-tracking technology, A means for generating handwritten-like representations by reflecting feature data on selected characters, A means for returning the generated handwritten-like representation to the presentation device, A system that includes this.

2. The system according to claim 1, characterized in that it retains individual characteristics by adding random elements.

3. The system according to claim 1, which enables the generation of a series of handwritten representations, including figures, by a specific method.

Images