system

Abstract

We provide the system. [Solution] Means for obtaining handwriting data, A means for modeling the acquired handwriting data as personal identification information, A means for performing identity verification by comparing the modeled handwriting data with the handwriting data entered during authentication, A means for outputting the results of the aforementioned identity verification, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the modern information security environment, the management of IDs and passwords is complicated and cumbersome, imposing a great burden on users. In addition, the introduction of a biometric authentication system involves high costs and technical complexities, presenting a problem that it is difficult for ordinary users to adopt. In response to these problems, there is a need to provide a more intuitive and reliable means of personal identification without the need for special equipment.

Means for Solving the Problems

[0005] The present invention solves the above problem by providing a handwriting authentication system that includes means for acquiring handwriting data, means for modeling the acquired handwriting data as personal identification information, means for performing identity authentication by comparing the modeled handwriting data with the handwriting data entered during authentication, and means for outputting the result of identity authentication. This makes it possible to easily perform identity verification using existing terminals without using special hardware.

[0006] "Handwriting data" refers to the digital recording of the shape information of handwritten letters and signatures by a specific individual.

[0007] "Means of acquisition" refers to hardware or software used to capture or record handwritten input by a user.

[0008] "Means for modeling as personally identifiable information" refers to a process or system that analyzes acquired handwriting data and generates a model for identifying individuals based on its characteristics.

[0009] "Means for verifying identity through comparison" refers to processes and algorithms that compare entered handwriting data with existing models to determine if the person entering the data is indeed the person in question.

[0010] "Means for outputting the results of identity verification" refers to functions or devices that display or notify the user of the results of handwriting comparison. [Brief explanation of the drawing]

[0011] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0012] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0013] First, let's explain the terminology used in the following explanation.

[0014] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0015] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0016] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0017] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

[0018] 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."

[0019] [First Embodiment]

[0020] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0021] 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.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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.

[0027] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] As shown in Figure 2, in the data processing device 12, specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0029] 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.

[0030] 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.

[0031] 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".

[0032] This invention relates to a handwriting authentication system that uses a user's handwriting as personal identification information to achieve highly reliable identity verification using common hardware. The embodiment of this system mainly consists of three main roles: server, terminal, and user.

[0033] First, the user handwrites their signature or a specific sentence onto the device. The device acquires this as handwriting data and converts it into a digital format. The converted data is then sent to a server via the network.

[0034] The server analyzes the received handwriting data and trains it as a user-specific personal identification model. This handwriting model reflects the user's characteristics and is used in the subsequent authentication process. The trained model is stored in a database and referenced in subsequent authentication requests.

[0035] When an authentication request occurs, the user re-enters handwriting data. The device collects this new data and sends it to the server in real time. The server compares the real-time handwriting data with a trained model and calculates a similarity score. If this score exceeds a pre-set threshold, the server determines that the user's identity has been successfully verified.

[0036] The authentication result is returned from the server to the terminal, which then displays the result to the user. If authentication is successful, the user can proceed to the next stage, for example, to complete logging into the system or to initiate a secure transaction.

[0037] In addition, this system also has a function to detect anomalies in handwriting data, preventing unauthorized access. Furthermore, to accommodate changes in handwriting over time, a mechanism has been introduced to periodically retrain the data and update the model.

[0038] Thus, this invention aims to enhance security and improve the user experience by utilizing user handwriting input. A specific example is its usefulness in secure, paperless identity verification during online banking. This configuration allows users to enjoy a high level of security using their everyday devices without any special preparation.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] The user uses the terminal's input interface to handwrite a signature or specific text. At this point, the terminal captures the handwriting data and formats it as digital data.

[0042] Step 2:

[0043] The device sends the captured handwriting data to the server. The transmission is performed using a secure network protocol to protect the confidentiality of the data.

[0044] Step 3:

[0045] The server analyzes the received handwriting data and generates a personal identification model for each user. This model learns the user's handwriting characteristics and stores that information in a database.

[0046] Step 4:

[0047] If an authentication request occurs, the user will again enter their signature by hand on the device. The device will capture this new handwriting data and send it to the server in real time.

[0048] Step 5:

[0049] The server compares the newly received handwriting data with existing personal identification models. Using a comparison algorithm, it calculates the similarity of the handwriting and determines whether it exceeds a threshold.

[0050] Step 6:

[0051] The server determines the success or failure of authentication based on the similarity score. If authentication is successful, it generates a success message; if it fails, it generates a message prompting the user to retry.

[0052] Step 7:

[0053] The server sends the authentication result to the terminal. The terminal displays this result to the user, and if authentication is successful, it grants the next action (e.g., access permission to the system).

[0054] Step 8:

[0055] If necessary, the server updates the handwriting model by relearning data at regular intervals. This compensates for the effects of time on handwriting and maintains authentication accuracy.

[0056] (Example 1)

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

[0058] There is a need to effectively utilize handwritten information from individuals as identification data and enable sophisticated individual verification. However, conventional technologies suffer from insufficient identification accuracy, and the complexity of data updates as the number of users increases. In particular, processing of information fluctuations and anomaly detection is inadequate, and there is a need to ensure user convenience while maintaining security.

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

[0060] In this invention, the server includes a device for receiving information input from a user, a device for converting the received information and transmitting it over a network, and a device for analyzing the received information, learning it as individual identification data, and storing it. This enables highly accurate identification and management of information.

[0061] A "device for receiving information input from the user" refers to an input device or interface that allows the user to input handwriting and other information as digital data.

[0062] "A device for converting the received information and transmitting it via a network" refers to a device that has the function of converting input digital data into a predetermined format and securely transmitting it to another device or system via a communication network.

[0063] A "device for analyzing received information, learning it as individual identification data, and storing it" is a device that analyzes data received via a network using a specific algorithm, creates an identification model that reflects the characteristics of an individual, and stores it in a memory device.

[0064] A "device for individual verification" is a device that compares a stored individual identification model with newly entered data to identify and verify an individual.

[0065] A "device for outputting results to a display device" is a device that displays the results of individual verification on a screen or other output means in order to inform the user or a specific system of the results in an easily understandable manner.

[0066] A "device for relearning information and updating individual identification data" is a device that relearns individual characteristics that change over time and due to information fluctuations, and maintains existing identification models in an up-to-date state.

[0067] A "device for detecting anomalies in information" is a device that inspects input or processed data for anomalies and issues a warning if a problem occurs.

[0068] The system provided in this invention is for individual verification using the user's handwritten information and mainly consists of three elements: a server, a terminal, and the user.

[0069] First, the user inputs information via a device. This device could be a tablet or a smartphone, for example. The device is equipped with a mechanism that converts handwritten information, such as a stylus pen or touchscreen, into digital data. This conversion to digital format is performed using a dedicated application installed on the device, which has a handwriting recognition function.

[0070] The converted data is securely encrypted by the terminal and sent to the server over the network. The terminal uses encryption technologies such as TLS (Transport Layer Security) to transmit the data and prevent it from being leaked to third parties.

[0071] The server is equipped with hardware and software to analyze received digital information and learn the user's unique characteristics as identification data. Examples of software used include machine learning frameworks such as TENSORFLOW® and PyTorch. These are used to construct a generative AI model that captures the characteristics of handwriting.

[0072] The generated model is stored in the database, and when a new individual verification request is received, the existing data is compared with the newly entered data. This comparison verifies the user's identity, and the result is returned to the terminal and displayed to the user.

[0073] This system includes a function to periodically retrain data, updating identification data to account for changes in user handwriting over time. It also features a function to detect anomalies in the information, playing a role in preventing unauthorized access. In this way, the system achieves highly reliable and secure individual verification while providing users with convenient access.

[0074] Specific examples of its use include online banking and secure electronic signatures. An example of a prompt message might be, "I would like to use your handwriting to securely access online services. Please enter your signature on the terminal."

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

[0076] Step 1:

[0077] The user uses a dedicated application on the device to input their signature or a designated text by hand. The input information is acquired as digital data, including pen pressure, speed, and angle. The device picks up this input data and measures various handwriting characteristics using its handwriting recognition function.

[0078] Step 2:

[0079] The device digitizes the acquired handwritten data and converts it into a data format. Specifically, it extracts features from the raw data and represents them as vectorized data. This digital data is encrypted and sent to the server using the TLS protocol to ensure security.

[0080] Step 3:

[0081] The server receives digitized handwriting data transmitted from the terminal. A pre-configured data cleaning algorithm is applied to the received data to remove noise and normalize the data. A clean dataset is then prepared.

[0082] Step 4:

[0083] The server trains a generative AI model using normalized data. In this step, machine learning libraries such as TensorFlow and PyTorch are used to learn the user's handwriting features. The model is then adjusted to recognize user-specific patterns, and the trained model is stored in a database.

[0084] Step 5:

[0085] If another individual verification request is made, the user re-enters the handwritten data on the device. The device acquires this new handwriting data in real time, encrypts it again, and sends it to the server.

[0086] Step 6:

[0087] The server compares the newly received handwriting data with the trained model. It calculates a similarity score and evaluates whether this score exceeds a pre-set threshold. If so, it determines that user verification was successful.

[0088] Step 7:

[0089] The server returns the authentication result to the terminal, which then displays this result to the user. If successful, access to the system and execution of transactions are permitted.

[0090] Step 8:

[0091] In addition to this process, the server can periodically retrain each user's handwriting model to improve and update its accuracy. This allows the system to take into account changes in handwriting over time.

[0092] (Application Example 1)

[0093] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0094] Traditional authentication methods have made it difficult to conduct secure electronic transactions while maintaining a balance between trustworthiness and convenience. Furthermore, these methods cannot completely prevent unauthorized access, and the transaction procedures are cumbersome.

[0095] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0096] In this invention, the server includes a device for acquiring handwriting data, a device for modeling the acquired handwriting data as personal identification information, a device for performing identity verification by comparing the modeled handwriting data with the handwriting data entered during authentication, and a device for executing transaction processing upon successful authentication. This enables users to conduct electronic transactions simply and securely.

[0097] A "device for acquiring handwriting data" is a device that electronically acquires information entered by a user in their handwriting and collects that data.

[0098] A "device for modeling as personal identification information" is a device that converts acquired handwriting data into a digital model while retaining individual characteristics, and structures it as data for identifying individuals.

[0099] A "device for verifying identity by comparing handwriting data with handwriting data entered during authentication" is a device that compares a registered digital model with newly entered handwriting data and authenticates whether the person is who they claim to be based on the degree of matching.

[0100] A "device for executing transaction processing upon successful authentication" is a device that automatically proceeds with a predetermined electronic transaction or procedure when the user's identity is successfully authenticated.

[0101] This invention is a handwriting authentication system for securely conducting electronic transactions using a smart device. In this system, the terminal acquires handwriting data and converts it into a digital format. When a user handwrites their signature into the smart device, the terminal recognizes it and converts it into the necessary digital data. By utilizing the latest drawing libraries (e.g., Draw2D) in this device, accurate handwriting information can be acquired.

[0102] The converted digital data is sent to the server via a secure communication protocol (e.g., HTTPS). The server receives this data and models it as personal identification information using a pre-trained generative AI model. This module utilizes advanced machine learning frameworks such as TensorFlow, which play a role in improving the accuracy of handwriting recognition. Cloud-based systems such as Amazon RDS are used for database management to ensure data consistency and availability.

[0103] When an authentication request is received, the server compares a trained personal model with real-time input handwriting data. This process calculates a similarity score and verifies the user's identity by evaluating whether it exceeds a certain threshold. If authentication is successful, the server immediately returns the result to the terminal, and the next stage, transaction processing, is executed. This transaction processing includes online shopping and electronic payments, allowing users to enjoy secure and fast services.

[0104] For example, when a user pays for coffee purchased at a cafe using this system, real-time authentication is performed, and the user is notified immediately upon completion of the payment, thus minimizing the use of cash or cards.

[0105] An example of a prompt might be: "Show a scenario where a user purchases coffee at a cafe, uses a smart device to digitally sign, and is successfully authenticated and securely completes the electronic payment."

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

[0107] Step 1:

[0108] The user inputs their signature by hand on a smart device. The device acquires the input signature as handwriting data and converts it into a digital format. The input is a handwritten signature, and the output is the digital data of that signature. A drawing library on the device (e.g., Draw2D) is used for this conversion.

[0109] Step 2:

[0110] The terminal transmits the handwriting data, converted into a digital format, to the server via a secure communication protocol. The input is the digital handwriting data, and the output is the result of the data transmission to the server. The HTTPS protocol is used for secure data transfer.

[0111] Step 3:

[0112] The server inputs the received handwriting data into a generating AI model to create a model that serves as personal identification information. The input is the received handwriting data, and the output is the personal model. An AI framework such as TensorFlow is used to perform the data modeling.

[0113] Step 4:

[0114] When a user requests authentication, the terminal converts the newly entered handwriting data back into a digital format and sends it to the server. The input is a signature entered in real time, and the output is the digitally converted real-time handwriting data.

[0115] Step 5:

[0116] The server compares a trained model with real-time handwriting data and calculates a similarity score. The input is the trained model and real-time data, and the output is the similarity score. An AI model is used to calculate the similarity score.

[0117] Step 6:

[0118] The server evaluates the similarity score and determines that authentication is successful if it exceeds the threshold. The input is the calculated similarity score, and the output is whether authentication was successful or not. The threshold value is pre-set and is determined here.

[0119] Step 7:

[0120] If authentication is successful, the server returns the result to the terminal, and the transaction process is executed. The input is the authentication result, and the output is the result of the transaction process execution. A specific transaction, such as online shopping or food delivery, is initiated.

[0121] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0122] This invention relates to a system that makes the authentication process secure and flexible by incorporating emotion recognition into a personal authentication system using handwriting data. This system mainly consists of three roles: server, terminal, and user, and by adding an emotion engine, it enables advanced authentication based on the user's emotional state.

[0123] First, the user inputs a signature or specific text by hand into the device. The device captures this as handwriting data, converts it into digital data, and uses an emotion engine to extract emotional data from the handwriting. The emotion engine analyzes elements such as pen pressure, speed, and changes in letter shape to evaluate the user's emotional state.

[0124] The device sends this data to the server. The server analyzes the received handwriting and sentiment data to train a user identification model. This model combines handwriting and sentiment characteristics to capture the user's personality in more detail. The model is then stored in a database and used for subsequent authentication requests.

[0125] When an authentication request arises, the user enters their handwritten signature again on the device. The device captures emotional data along with the handwriting and sends it to the server. The server uses a trained model to perform authentication based on the new data. Here, the emotional data plays a supporting role, allowing for additional processing, such as issuing a separate warning if a stressed or agitated state is detected.

[0126] The authentication result is returned from the server to the terminal, which then displays it to the user. If successful, the user is allowed to proceed to the next step (logging into the system or starting a transaction). If it fails, the user receives feedback about the error and is given the option to retry.

[0127] As a concrete example, it is used in corporate security systems when employees access confidential information. In addition to basic authentication using handwriting, it can prevent unauthorized access by checking the stress level and emotional stability at the time.

[0128] Thus, the present invention provides more comprehensive security and improves the user experience by combining emotion recognition with conventional identity verification methods.

[0129] The following describes the processing flow.

[0130] Step 1:

[0131] Users input signatures or specific sentences using the device's handwriting input interface. During this process, handwriting data, including pen pressure and writing speed, is recorded.

[0132] Step 2:

[0133] The device sends the input handwriting data to an emotion engine, which estimates the user's emotional state from the characteristics of the handwriting. The emotion engine analyzes pen pressure, speed, and changes in letter shape to extract emotional parameters such as the degree of relaxation or stress.

[0134] Step 3:

[0135] The device sends the acquired handwriting data and emotion parameters to the server. Encryption is applied to maintain data integrity and confidentiality.

[0136] Step 4:

[0137] The server analyzes the received data and creates or updates a user identification model. This model combines both handwriting and emotions to record the user's characteristics with high accuracy.

[0138] Step 5:

[0139] During the authentication request, the user re-enters their handwriting into the device. The device retrieves the handwriting data and sentiment information in real time and sends it to the server.

[0140] Step 6:

[0141] The server performs authentication by comparing the new handwriting data with a previously acquired handwriting model. If the similarity exceeds a certain threshold, it makes a final authentication decision after considering emotional information.

[0142] Step 7:

[0143] The server returns the authentication result to the terminal. The result includes information such as whether authentication was successful or failed, and whether or not there are any emotional abnormalities.

[0144] Step 8:

[0145] The device displays the received authentication result to the user. If authentication is successful, it grants permission for the next action (e.g., access to confidential information). If necessary, the user will also be notified of any emotional disturbances.

[0146] (Example 2)

[0147] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0148] Conventional identity verification systems rely solely on handwriting data for authentication, which presents security challenges. Furthermore, they fail to consider the user's emotional state, making them prone to unauthorized access and misidentification. Therefore, there is a need to establish a more secure and flexible identity verification method.

[0149] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0150] In this invention, the server includes a device for acquiring handwriting data, a device for modeling the acquired handwriting data as personal identification information, and an emotion analysis device for evaluating emotional states from the handwriting data. This makes it possible to authenticate users from multiple perspectives, considering both handwriting and emotions.

[0151] "Handwriting data" refers to information that includes characteristics such as the shape of characters and signatures entered by hand, as well as pen pressure and speed.

[0152] "Personal identification information" refers to data used to identify a specific individual, and is modeled based on handwriting characteristics and emotional states.

[0153] An "emotion analysis device" is a device that analyzes physical characteristics such as pen pressure and drawing speed from handwriting data to evaluate the user's emotional state.

[0154] "Identity verification" is the process of confirming and authenticating a specific individual based on entered handwriting data and emotional state data.

[0155] "Anomaly detection" is a process for identifying deviations from normal handwriting data and emotional states, and for identifying suspicious behavior or conditions.

[0156] This invention is a personal authentication system that combines handwriting data and emotional state. The system mainly consists of a server, a terminal, and a user interface.

[0157] Users input signatures or specific text using a stylus pen or a tablet's touchscreen. The device captures the handwriting data and saves it as digital data, including details such as speed and pressure. In addition, the device incorporates an emotion analyzer that analyzes the user's emotions based on changes in their handwriting and generates data accordingly.

[0158] The device sends this data to the server. The server uses a generative AI model to create a user identification model based on the handwriting data and sentiment data. This model accurately represents the user's unique handwriting and sentiment characteristics and is stored in a database.

[0159] A concrete example of its application is a company's security system. For instance, when an employee accesses confidential information, this authentication system can be used to perform authentication in two stages—by analyzing handwriting and emotions—contributing to the prevention of unauthorized access.

[0160] An example of a prompt to input into a generative AI model is: "Please describe the design of a system that performs user authentication based on data of a user's handwritten signature and its emotional state."

[0161] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0162] Step 1:

[0163] Users input handwritten signatures or specific text into the device. Input includes physical writing via a stylus pen or tablet touchscreen. Output is captured handwriting data of the handwritten letters and signatures. This data includes information such as pressure, speed, and letterform, and is converted into a digital format.

[0164] Step 2:

[0165] The terminal transmits the captured handwriting data to an emotion analysis device, which evaluates the emotional state from the handwriting. The input is the handwriting data obtained in step 1. The emotion analysis device analyzes changes in pen pressure and writing style to extract emotional characteristics. As output, emotion data indicating the user's emotional state is generated.

[0166] Step 3:

[0167] The terminal transmits handwriting data and sentiment data to the server. The input is handwriting data and sentiment data, and the output is secure data transmission to the server. Data security is crucial in this process, and encrypted communication is used.

[0168] Step 4:

[0169] The server uses the received data to train a personal identification model using a generative AI model. The input consists of handwriting data and sentiment data sent from the terminal. The server combines these to create a detailed personal authentication model, and the output is stored in a database. This model represents the user's handwriting characteristics and sentiment characteristics.

[0170] Step 5:

[0171] When an authentication request is received, the user enters their handwritten signature again on the device. The input is a newly recorded handwritten signature. The output is a capture of the latest handwriting and sentiment data.

[0172] Step 6:

[0173] The terminal sends new handwriting and emotion data to the server. The input is the data captured in step 5, and the output is the data transmission to the server.

[0174] Step 7:

[0175] The server uses a trained personal identification model to perform authentication based on new data. The input is data newly sent from the terminal. The server analyzes the input data based on the model and outputs a result indicating whether authentication was successful or failed.

[0176] Step 8:

[0177] The server returns the authentication result to the terminal, and the terminal displays the result to the user. The input is the authentication result received from the server, and the output is the notification of the result to the user. If authentication is successful, the user is allowed to proceed to the next step; if it fails, feedback is provided for retrying.

[0178] (Application Example 2)

[0179] 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".

[0180] Traditional authentication systems rely on static personal identification information, resulting in security vulnerabilities and making it difficult to prevent unauthorized access. Furthermore, by failing to consider the user's emotional state, opportunities for improving usability in the authentication process were lost.

[0181] 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.

[0182] In this invention, the server includes means for analyzing emotional information from handwriting data, means for generating a personal identification model incorporating the emotional information, and means for performing access control based on the user's mental state. This makes it possible to improve the accuracy of personal identification, more effectively prevent unauthorized access, and improve usability.

[0183] "Handwriting data" refers to information that digitally represents characters or signatures entered by a user through handwriting.

[0184] "Emotional information" refers to data that represents the user's emotional state, analyzed from handwriting data.

[0185] A "personal identification model" is a model constructed to identify individuals using handwriting data and sentiment information.

[0186] "Access control" is the process of managing users' access rights to specific information and allowing access only within the permitted scope.

[0187] A description of embodiments for carrying out the present invention will be provided.

[0188] This system primarily consists of three roles: server, terminal, and user. The user uses a dedicated input device to handwrite a signature or specific text into the terminal. The terminal captures the handwriting data and converts it into digital data. Furthermore, the terminal uses an emotion engine to analyze emotional information from the handwriting data and evaluate the user's emotional state. In this process, factors such as handwriting pressure, speed, and changes in letter shape are analyzed to extract the user's emotional characteristics.

[0189] The server receives handwriting data and emotional information transmitted from the terminal and generates a personal identification model based on this data. This model combines handwriting data and emotional information to capture the user's personality in detail. The generated personal identification model is stored in a database and used in subsequent authentication requests.

[0190] When an authentication request occurs, the user re-enters their handwritten signature into the terminal. The terminal captures the new handwriting data and emotional information and sends it to the server. The server uses a trained personal identification model to authenticate the user based on the new data. The authentication process considers both handwriting characteristics and emotional characteristics. Using emotional information allows for flexible responses, such as issuing warnings when the user is stressed or agitated.

[0191] For example, this system may be used when employees of large companies remotely access confidential files. The system automatically sends an alert to security personnel if an employee's stress level is unusual.

[0192] An example of a prompt for a generative AI model would be, "Explain the process of authenticating an individual using handwriting and sentiment data."

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

[0194] Step 1:

[0195] Users input signatures or specific text by hand on the device. The input handwriting data is captured in real time by the device and converted into a digital format. This input data includes detailed parameters such as pen pressure, speed, and letter shape.

[0196] Step 2:

[0197] The device passes the acquired handwriting data to the emotion engine. The emotion engine analyzes each element of the handwriting and extracts the user's emotional characteristics. Specifically, it evaluates stress levels, relaxation levels, etc., based on variations in speed and pressure. Emotional information is generated as a result of this analysis.

[0198] Step 3:

[0199] The handwriting data and emotional information generated on the device are sent to the server. The server receives this information and generates an individual identification model based on it. In model generation, a generative AI model is used to train a composite data combining handwriting characteristics and emotional characteristics. Big data analysis technology is utilized in this process.

[0200] Step 4:

[0201] The server stores the generated personal identification model in a database. This model is stored in a secure environment because it will be used in subsequent authentication processes.

[0202] Step 5:

[0203] If a new authentication request arises, the user enters their handwritten signature again on the device. The device then recaptures the latest handwriting data and sentiment information and sends it to the server.

[0204] Step 6:

[0205] The server compares the newly transmitted data with existing personal identification models. This comparison is used to authenticate the user's identity. If a discrepancy is detected between the handwriting and sentiment during this process, access will be restricted.

[0206] Step 7:

[0207] The authentication result is sent back from the server to the terminal. If authentication is successful, the user can access the system normally. If it fails, the user is shown an error message and prompted to try again. This feedback process improves the user experience.

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

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

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

[0211] [Second Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0224] This invention relates to a handwriting authentication system that uses a user's handwriting as personal identification information to achieve highly reliable identity verification using common hardware. The embodiment of this system mainly consists of three main roles: server, terminal, and user.

[0225] First, the user handwrites their signature or a specific sentence onto the device. The device acquires this as handwriting data and converts it into a digital format. The converted data is then sent to a server via the network.

[0226] The server analyzes the received handwriting data and trains it as a user-specific personal identification model. This handwriting model reflects the user's characteristics and is used in the subsequent authentication process. The trained model is stored in a database and referenced in subsequent authentication requests.

[0227] When an authentication request occurs, the user re-enters handwriting data. The device collects this new data and sends it to the server in real time. The server compares the real-time handwriting data with a trained model and calculates a similarity score. If this score exceeds a pre-set threshold, the server determines that the user's identity has been successfully verified.

[0228] The authentication result is returned from the server to the terminal, which then displays the result to the user. If authentication is successful, the user can proceed to the next stage, for example, to complete logging into the system or to initiate a secure transaction.

[0229] In addition, this system also has a function to detect anomalies in handwriting data, preventing unauthorized access. Furthermore, to accommodate changes in handwriting over time, a mechanism has been introduced to periodically retrain the data and update the model.

[0230] Thus, this invention aims to enhance security and improve the user experience by utilizing user handwriting input. A specific example is its usefulness in secure, paperless identity verification during online banking. This configuration allows users to enjoy a high level of security using their everyday devices without any special preparation.

[0231] The following describes the processing flow.

[0232] Step 1:

[0233] The user uses the terminal's input interface to handwrite a signature or specific text. At this point, the terminal captures the handwriting data and formats it as digital data.

[0234] Step 2:

[0235] The device sends the captured handwriting data to the server. The transmission is performed using a secure network protocol to protect the confidentiality of the data.

[0236] Step 3:

[0237] The server analyzes the received handwriting data and generates a user-specific personal identification model. This model learns the user's handwriting characteristics and stores that information in a database.

[0238] Step 4:

[0239] If an authentication request occurs, the user will again enter their signature by hand on the device. The device will capture this new handwriting data and send it to the server in real time.

[0240] Step 5:

[0241] The server compares the newly received handwriting data with existing personal identification models. Using a comparison algorithm, it calculates the similarity of the handwriting and determines whether it exceeds a threshold.

[0242] Step 6:

[0243] The server determines the success or failure of authentication based on the similarity score. If authentication is successful, it generates a success message; if it fails, it generates a message prompting the user to retry.

[0244] Step 7:

[0245] The server sends the authentication result to the terminal. The terminal displays this result to the user, and if authentication is successful, it grants the next action (e.g., access permission to the system).

[0246] Step 8:

[0247] If necessary, the server updates the handwriting model by relearning data at regular intervals. This compensates for the effects of time on handwriting and maintains authentication accuracy.

[0248] (Example 1)

[0249] 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."

[0250] There is a need to effectively utilize handwritten information from individuals as identification data and enable sophisticated individual verification. However, conventional technologies suffer from insufficient identification accuracy, and the complexity of data updates as the number of users increases. In particular, processing of information fluctuations and anomaly detection is inadequate, and there is a need to ensure user convenience while maintaining security.

[0251] 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.

[0252] In this invention, the server includes a device for receiving information input from a user, a device for converting the received information and transmitting it over a network, and a device for analyzing the received information, learning it as individual identification data, and storing it. This enables highly accurate identification and management of information.

[0253] A "device for receiving information input from the user" refers to an input device or interface that allows the user to input handwriting and other information as digital data.

[0254] "A device for converting the received information and transmitting it via a network" refers to a device that has the function of converting input digital data into a predetermined format and securely transmitting it to another device or system via a communication network.

[0255] A "device for analyzing received information, learning it as individual identification data, and storing it" is a device that analyzes data received via a network using a specific algorithm, creates an identification model that reflects the characteristics of an individual, and stores it in a memory device.

[0256] A "device for individual verification" is a device that compares a stored individual identification model with newly entered data to identify and verify an individual.

[0257] A "device for outputting results to a display device" is a device that displays the results of individual verification on a screen or other output means in order to inform the user or a specific system of the results in an easily understandable manner.

[0258] A "device for relearning information and updating individual identification data" is a device that relearns individual characteristics that change over time and due to information fluctuations, and maintains existing identification models in an up-to-date state.

[0259] A "device for detecting anomalies in information" is a device that inspects input or processed data for anomalies and issues a warning if a problem occurs.

[0260] The system provided in this invention is for individual verification using the user's handwritten information and mainly consists of three elements: a server, a terminal, and the user.

[0261] First, the user inputs information via a device. This device could be a tablet or a smartphone, for example. The device is equipped with a mechanism that converts handwritten information, such as a stylus pen or touchscreen, into digital data. This conversion to digital format is performed using a dedicated application installed on the device, which has a handwriting recognition function.

[0262] The converted data is securely encrypted by the terminal and sent to the server over the network. The terminal uses encryption technologies such as TLS (Transport Layer Security) to transmit the data and prevent it from being leaked to third parties.

[0263] The server is equipped with hardware and software to analyze the received digital information and learn the user's unique characteristics as identification data. Examples of software used include machine learning frameworks such as TensorFlow and PyTorch. These are used to build a generative AI model that captures the characteristics of handwriting.

[0264] The generated model is stored in the database, and when a new individual verification request is received, the existing data is compared with the newly entered data. This comparison verifies the user's identity, and the result is returned to the terminal and displayed to the user.

[0265] This system includes a function to periodically retrain data, updating identification data to account for changes in user handwriting over time. It also features a function to detect anomalies in the information, playing a role in preventing unauthorized access. In this way, the system achieves highly reliable and secure individual verification while providing users with convenient access.

[0266] Specific examples of its use include online banking and secure electronic signatures. An example of a prompt message might be, "I would like to use your handwriting to securely access online services. Please enter your signature on the terminal."

[0267] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0268] Step 1:

[0269] The user uses a dedicated application on the device to input their signature or a designated text by hand. The input information is acquired as digital data, including pen pressure, speed, and angle. The device picks up this input data and measures various handwriting characteristics using its handwriting recognition function.

[0270] Step 2:

[0271] The device digitizes the acquired handwritten data and converts it into a data format. Specifically, it extracts features from the raw data and represents them as vectorized data. This digital data is encrypted and sent to the server using the TLS protocol to ensure security.

[0272] Step 3:

[0273] The server receives digitized handwriting data transmitted from the terminal. A pre-configured data cleaning algorithm is applied to the received data to remove noise and normalize the data. A clean dataset is then prepared.

[0274] Step 4:

[0275] The server trains the generative AI model using the normalized data. In this step, machine learning libraries such as TensorFlow or PyTorch are utilized to learn the user's handwriting features. The model is adjusted so that it can recognize the user-specific patterns, and the trained model is saved in the database.

[0276] Step 5:

[0277] If there is a request for individual verification again, the user inputs the handwritten data on the terminal again. The terminal acquires this new handwriting data in real time, encrypts it again, and sends it to the server.

[0278] Step 6:

[0279] The server compares the trained model with the newly received handwriting data. It calculates a similarity score and evaluates whether this score exceeds a pre-set reference value. If so, it determines that the user's identity verification has been successful.

[0280] Step 7:

[0281] The server returns the authentication result to the terminal, and the terminal displays this result to the user. If successful, access to the system and execution of transactions are permitted.

[0282] [[ID=2,7]] Step 8:

[0283] In addition to this process, the server can periodically re-learn the handwriting model of each user to improve and update the accuracy of the model. This allows for taking into account changes in handwriting over time.

[0284] (Application Example 1)

[0285] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0286] In the conventional personal authentication method, it has been difficult to conduct secure electronic transactions while maintaining a balance between credibility and convenience. In addition, these methods have the problems that unauthorized access cannot be completely prevented, and the transaction procedures are complicated.

[0287] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0288] In this invention, the server includes a device for acquiring handwriting data, a device for modeling the acquired handwriting data as personal identification information, a device for comparing the modeled handwriting data with the handwriting data input at the time of authentication to perform personal authentication, and a device for executing transaction processing when authentication is successful. Thereby, the user can conduct electronic transactions simply and securely.

[0289] The "device for acquiring handwriting data" is a device for electronically acquiring information handwritten by a user and collecting the data.

[0290] The "device for modeling as personal identification information" is a device for converting the acquired handwriting data into a digital model while retaining individual features and structuring it as data for identifying an individual.

[0291] The "device for comparing the handwriting data with the handwriting data input at the time of authentication to perform personal authentication" is a device for comparing the registered digital model with the newly input handwriting data and authenticating whether the person is the same based on the degree of coincidence.

[0292] The "device for executing transaction processing when authentication is successful" is a device for automatically advancing the determined electronic transactions and procedures when personal authentication is successful.

[0293] This invention is a handwriting authentication system for securely conducting electronic transactions using a smart device. In this system, the terminal acquires handwriting data and converts it into a digital format. When a user handwrites their signature into the smart device, the terminal recognizes it and converts it into the necessary digital data. By utilizing the latest drawing libraries (e.g., Draw2D) in this device, accurate handwriting information can be acquired.

[0294] The converted digital data is sent to the server via a secure communication protocol (e.g., HTTPS). The server receives this data and models it as personal identification information using a pre-trained generative AI model. This module utilizes advanced machine learning frameworks such as TensorFlow, which play a role in improving the accuracy of handwriting recognition. Cloud-based systems such as Amazon RDS are used for database management to ensure data consistency and availability.

[0295] When an authentication request is received, the server compares a trained personal model with real-time input handwriting data. This process calculates a similarity score and verifies the user's identity by evaluating whether it exceeds a certain threshold. If authentication is successful, the server immediately returns the result to the terminal, and the next stage, transaction processing, is executed. This transaction processing includes online shopping and electronic payments, allowing users to enjoy secure and fast services.

[0296] For example, when a user pays for coffee purchased at a cafe using this system, real-time authentication is performed, and the user is notified immediately upon completion of the payment, thus minimizing the use of cash or cards.

[0297] An example of a prompt might be: "Show a scenario where a user purchases coffee at a cafe, uses a smart device to digitally sign, and is successfully authenticated and securely completes the electronic payment."

[0298] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0299] Step 1:

[0300] The user handwrites a signature on the smart device. The input signature is acquired by the terminal as handwriting data and converted into a digital format. The input is a handwritten signature, and the output is the digital data of that signature. For this conversion, a drawing library (e.g., Draw2D) on the device is used.

[0301] Step 2:

[0302] The terminal transmits the handwriting data converted into a digital format to the server through a secure communication protocol. The input is digital handwriting data, and the output is the data transmission result to the server. The HTTPS protocol is used to perform secure data transfer.

[0303] Step 3:

[0304] The server inputs the received handwriting data into a generative AI model to generate a model as personal identification information. The input is the received handwriting data, and the output is a personal model. An AI framework such as TensorFlow is used to perform data modeling.

[0305] Step 4:

[0306] When the user requests authentication, the terminal converts the newly input handwriting data into a digital format again and transmits it to the server. The input is the signature input in real time, and the output is the digitally converted real-time handwriting data.

[0307] Step 5:

[0308] The server compares a trained model with real-time handwriting data and calculates a similarity score. The input is the trained model and real-time data, and the output is the similarity score. An AI model is used to calculate the similarity score.

[0309] Step 6:

[0310] The server evaluates the similarity score and determines that authentication is successful if it exceeds the threshold. The input is the calculated similarity score, and the output is whether authentication was successful or not. The threshold value is pre-set and is determined here.

[0311] Step 7:

[0312] If authentication is successful, the server returns the result to the terminal, and the transaction process is executed. The input is the authentication result, and the output is the result of the transaction process execution. A specific transaction, such as online shopping or food delivery, is initiated.

[0313] 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.

[0314] This invention relates to a system that makes the authentication process secure and flexible by incorporating emotion recognition into a personal authentication system using handwriting data. This system mainly consists of three roles: server, terminal, and user, and by adding an emotion engine, it enables advanced authentication based on the user's emotional state.

[0315] First, the user inputs a signature or specific text by hand into the device. The device captures this as handwriting data, converts it into digital data, and uses an emotion engine to extract emotional data from the handwriting. The emotion engine analyzes elements such as pen pressure, speed, and changes in letter shape to evaluate the user's emotional state.

[0316] The device sends this data to the server. The server analyzes the received handwriting and sentiment data to train a user identification model. This model combines handwriting and sentiment characteristics to capture the user's personality in more detail. The model is then stored in a database and used for subsequent authentication requests.

[0317] When an authentication request arises, the user enters their handwritten signature again on the device. The device captures emotional data along with the handwriting and sends it to the server. The server uses a trained model to perform authentication based on the new data. Here, the emotional data plays a supporting role, allowing for additional processing, such as issuing a separate warning if a stressed or agitated state is detected.

[0318] The authentication result is returned from the server to the terminal, which then displays it to the user. If successful, the user is allowed to proceed to the next step (logging into the system or starting a transaction). If it fails, the user receives feedback about the error and is given the option to retry.

[0319] As a concrete example, it is used in corporate security systems when employees access confidential information. In addition to basic authentication using handwriting, it can prevent unauthorized access by checking the stress level and emotional stability at the time.

[0320] Thus, the present invention provides more comprehensive security and improves the user experience by combining emotion recognition with conventional identity verification methods.

[0321] The following describes the processing flow.

[0322] Step 1:

[0323] Users input signatures or specific sentences using the device's handwriting input interface. During this process, handwriting data, including pen pressure and writing speed, is recorded.

[0324] Step 2:

[0325] The device sends the input handwriting data to an emotion engine, which estimates the user's emotional state from the characteristics of the handwriting. The emotion engine analyzes pen pressure, speed, and changes in letter shape to extract emotional parameters such as the degree of relaxation or stress.

[0326] Step 3:

[0327] The device sends the acquired handwriting data and emotion parameters to the server. Encryption is applied to maintain data integrity and confidentiality.

[0328] Step 4:

[0329] The server analyzes the received data and creates or updates a user identification model. This model combines both handwriting and emotions to record the user's characteristics with high accuracy.

[0330] Step 5:

[0331] During the authentication request, the user re-enters their handwriting into the device. The device retrieves the handwriting data and sentiment information in real time and sends it to the server.

[0332] Step 6:

[0333] The server performs authentication by comparing the new handwriting data with a previously acquired handwriting model. If the similarity exceeds a certain threshold, it makes a final authentication decision after considering emotional information.

[0334] Step 7:

[0335] The server returns the authentication result to the terminal. The result includes information such as whether authentication was successful or failed, and whether or not there are any emotional abnormalities.

[0336] Step 8:

[0337] The device displays the received authentication result to the user. If authentication is successful, it grants permission for the next action (e.g., access to confidential information). If necessary, the user will also be notified of any emotional disturbances.

[0338] (Example 2)

[0339] 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".

[0340] Conventional identity verification systems rely solely on handwriting data for authentication, which presents security challenges. Furthermore, they fail to consider the user's emotional state, making them prone to unauthorized access and misidentification. Therefore, there is a need to establish a more secure and flexible identity verification method.

[0341] 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.

[0342] In this invention, the server includes a device for acquiring handwriting data, a device for modeling the acquired handwriting data as personal identification information, and an emotion analysis device for evaluating emotional states from the handwriting data. This makes it possible to authenticate users from multiple perspectives, considering both handwriting and emotions.

[0343] "Handwriting data" refers to information that includes characteristics such as the shape of characters and signatures entered by hand, as well as pen pressure and speed.

[0344] "Personal identification information" refers to data used to identify a specific individual, and is modeled based on handwriting characteristics and emotional states.

[0345] An "emotion analysis device" is a device that analyzes physical characteristics such as pen pressure and drawing speed from handwriting data to evaluate the user's emotional state.

[0346] "Identity verification" is the process of confirming and authenticating a specific individual based on entered handwriting data and emotional state data.

[0347] "Anomaly detection" is a process for identifying deviations from normal handwriting data and emotional states, and for identifying suspicious behavior or conditions.

[0348] This invention is a personal authentication system that combines handwriting data and emotional state. The system mainly consists of a server, a terminal, and a user interface.

[0349] Users input signatures or specific text using a stylus pen or a tablet's touchscreen. The device captures the handwriting data and saves it as digital data, including details such as speed and pressure. In addition, the device incorporates an emotion analyzer that analyzes the user's emotions based on changes in their handwriting and generates data accordingly.

[0350] The device sends this data to the server. The server uses a generative AI model to create a user identification model based on the handwriting data and sentiment data. This model accurately represents the user's unique handwriting and sentiment characteristics and is stored in a database.

[0351] A concrete example of its application is a company's security system. For instance, when an employee accesses confidential information, this authentication system can be used to perform authentication in two stages—by analyzing handwriting and emotions—contributing to the prevention of unauthorized access.

[0352] An example of a prompt to input into a generative AI model is: "Please describe the design of a system that performs user authentication based on data of a user's handwritten signature and its emotional state."

[0353] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0354] Step 1:

[0355] Users input handwritten signatures or specific text into the device. Input includes physical writing via a stylus pen or tablet touchscreen. Output is captured handwriting data of the handwritten letters and signatures. This data includes information such as pressure, speed, and letterform, and is converted into a digital format.

[0356] Step 2:

[0357] The terminal transmits the captured handwriting data to an emotion analysis device, which evaluates the emotional state from the handwriting. The input is the handwriting data obtained in step 1. The emotion analysis device analyzes changes in pen pressure and writing style to extract emotional characteristics. As output, emotion data indicating the user's emotional state is generated.

[0358] Step 3:

[0359] The terminal transmits handwriting data and sentiment data to the server. The input is handwriting data and sentiment data, and the output is secure data transmission to the server. Data security is crucial in this process, and encrypted communication is used.

[0360] Step 4:

[0361] The server uses the received data to train a personal identification model using a generative AI model. The input consists of handwriting data and sentiment data sent from the terminal. The server combines these to create a detailed personal authentication model, and the output is stored in a database. This model represents the user's handwriting characteristics and sentiment characteristics.

[0362] Step 5:

[0363] When an authentication request is received, the user enters their handwritten signature again on the device. The input is a newly recorded handwritten signature. The output is a capture of the latest handwriting and sentiment data.

[0364] Step 6:

[0365] The terminal sends new handwriting and emotion data to the server. The input is the data captured in step 5, and the output is the data transmission to the server.

[0366] Step 7:

[0367] The server uses a trained personal identification model to perform authentication based on new data. The input is data newly sent from the terminal. The server analyzes the input data based on the model and outputs a result indicating whether authentication was successful or failed.

[0368] Step 8:

[0369] The server returns the authentication result to the terminal, and the terminal displays the result to the user. The input is the authentication result received from the server, and the output is the notification of the result to the user. If authentication is successful, the user is allowed to proceed to the next step; if it fails, feedback is provided for retrying.

[0370] (Application Example 2)

[0371] 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."

[0372] Traditional authentication systems rely on static personal identification information, resulting in security vulnerabilities and making it difficult to prevent unauthorized access. Furthermore, by failing to consider the user's emotional state, opportunities for improving usability in the authentication process were lost.

[0373] 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.

[0374] In this invention, the server includes means for analyzing emotional information from handwriting data, means for generating a personal identification model incorporating the emotional information, and means for performing access control based on the user's mental state. This makes it possible to improve the accuracy of personal identification, more effectively prevent unauthorized access, and improve usability.

[0375] "Handwriting data" refers to information that digitally represents characters or signatures entered by a user through handwriting.

[0376] "Emotional information" refers to data that represents the user's emotional state, analyzed from handwriting data.

[0377] A "personal identification model" is a model constructed to identify individuals using handwriting data and sentiment information.

[0378] "Access control" is the process of managing users' access rights to specific information and allowing access only within the permitted scope.

[0379] A description of embodiments for carrying out the present invention will be provided.

[0380] This system primarily consists of three roles: server, terminal, and user. The user uses a dedicated input device to handwrite a signature or specific text into the terminal. The terminal captures the handwriting data and converts it into digital data. Furthermore, the terminal uses an emotion engine to analyze emotional information from the handwriting data and evaluate the user's emotional state. In this process, factors such as handwriting pressure, speed, and changes in letter shape are analyzed to extract the user's emotional characteristics.

[0381] The server receives handwriting data and emotional information transmitted from the terminal and generates a personal identification model based on this data. This model combines handwriting data and emotional information to capture the user's personality in detail. The generated personal identification model is stored in a database and used in subsequent authentication requests.

[0382] When an authentication request occurs, the user re-enters their handwritten signature into the terminal. The terminal captures the new handwriting data and emotional information and sends it to the server. The server uses a trained personal identification model to authenticate the user based on the new data. The authentication process considers both handwriting characteristics and emotional characteristics. Using emotional information allows for flexible responses, such as issuing warnings when the user is stressed or agitated.

[0383] For example, this system may be used when employees of large companies remotely access confidential files. The system automatically sends an alert to security personnel if an employee's stress level is unusual.

[0384] An example of a prompt for a generative AI model would be, "Explain the process of authenticating an individual using handwriting and sentiment data."

[0385] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0386] Step 1:

[0387] Users input signatures or specific text by hand on the device. The input handwriting data is captured in real time by the device and converted into a digital format. This input data includes detailed parameters such as pen pressure, speed, and letter shape.

[0388] Step 2:

[0389] The device passes the acquired handwriting data to the emotion engine. The emotion engine analyzes each element of the handwriting and extracts the user's emotional characteristics. Specifically, it evaluates stress levels, relaxation levels, etc., based on variations in speed and pressure. Emotional information is generated as a result of this analysis.

[0390] Step 3:

[0391] The handwriting data and emotional information generated on the device are sent to the server. The server receives this information and generates an individual identification model based on it. In model generation, a generative AI model is used to train a composite data combining handwriting characteristics and emotional characteristics. Big data analysis technology is utilized in this process.

[0392] Step 4:

[0393] The server stores the generated personal identification model in a database. This model is stored in a secure environment because it will be used in subsequent authentication processes.

[0394] Step 5:

[0395] If a new authentication request arises, the user enters their handwritten signature again on the device. The device then recaptures the latest handwriting data and sentiment information and sends it to the server.

[0396] Step 6:

[0397] The server compares the newly transmitted data with existing personal identification models. This comparison is used to authenticate the user's identity. If a discrepancy is detected between the handwriting and sentiment during this process, access will be restricted.

[0398] Step 7:

[0399] The authentication result is sent back from the server to the terminal. If authentication is successful, the user can access the system normally. If it fails, the user is shown an error message and prompted to try again. This feedback process improves the user experience.

[0400] 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.

[0401] 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.

[0402] 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.

[0403] [Third Embodiment]

[0404] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0405] 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.

[0406] 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).

[0407] 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.

[0408] 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.

[0409] 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).

[0410] 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.

[0411] 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.

[0412] 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.

[0413] 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.

[0414] 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.

[0415] 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".

[0416] This invention relates to a handwriting authentication system that uses a user's handwriting as personal identification information to achieve highly reliable identity verification using common hardware. The embodiment of this system mainly consists of three main roles: server, terminal, and user.

[0417] First, the user handwrites their signature or a specific sentence onto the device. The device acquires this as handwriting data and converts it into a digital format. The converted data is then sent to a server via the network.

[0418] The server analyzes the received handwriting data and trains it as a user-specific personal identification model. This handwriting model reflects the user's characteristics and is used in the subsequent authentication process. The trained model is stored in a database and referenced in subsequent authentication requests.

[0419] When an authentication request occurs, the user re-enters handwriting data. The device collects this new data and sends it to the server in real time. The server compares the real-time handwriting data with a trained model and calculates a similarity score. If this score exceeds a pre-set threshold, the server determines that the user's identity has been successfully verified.

[0420] The authentication result is returned from the server to the terminal, which then displays the result to the user. If authentication is successful, the user can proceed to the next stage, for example, to complete logging into the system or to initiate a secure transaction.

[0421] In addition, this system also has a function to detect anomalies in handwriting data, preventing unauthorized access. Furthermore, to accommodate changes in handwriting over time, a mechanism has been introduced to periodically retrain the data and update the model.

[0422] Thus, this invention aims to enhance security and improve the user experience by utilizing user handwriting input. A specific example is its usefulness in secure, paperless identity verification during online banking. This configuration allows users to enjoy a high level of security using their everyday devices without any special preparation.

[0423] The following describes the processing flow.

[0424] Step 1:

[0425] The user uses the terminal's input interface to handwrite a signature or specific text. At this point, the terminal captures the handwriting data and formats it as digital data.

[0426] Step 2:

[0427] The device sends the captured handwriting data to the server. The transmission is performed using a secure network protocol to protect the confidentiality of the data.

[0428] Step 3:

[0429] The server analyzes the received handwriting data and generates a user-specific personal identification model. This model learns the user's handwriting characteristics and stores that information in a database.

[0430] Step 4:

[0431] If an authentication request occurs, the user will again enter their signature by hand on the device. The device will capture this new handwriting data and send it to the server in real time.

[0432] Step 5:

[0433] The server compares the newly received handwriting data with existing personal identification models. Using a comparison algorithm, it calculates the similarity of the handwriting and determines whether it exceeds a threshold.

[0434] Step 6:

[0435] The server determines the success or failure of authentication based on the similarity score. If authentication is successful, it generates a success message; if it fails, it generates a message prompting the user to retry.

[0436] Step 7:

[0437] The server sends the authentication result to the terminal. The terminal displays this result to the user, and if authentication is successful, it grants the next action (e.g., access permission to the system).

[0438] Step 8:

[0439] If necessary, the server updates the handwriting model by relearning data at regular intervals. This compensates for the effects of time on handwriting and maintains authentication accuracy.

[0440] (Example 1)

[0441] 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."

[0442] There is a need to effectively utilize handwritten information from individuals as identification data and enable sophisticated individual verification. However, conventional technologies suffer from insufficient identification accuracy, and the complexity of data updates as the number of users increases. In particular, processing of information fluctuations and anomaly detection is inadequate, and there is a need to ensure user convenience while maintaining security.

[0443] 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.

[0444] In this invention, the server includes a device for receiving information input from a user, a device for converting the received information and transmitting it over a network, and a device for analyzing the received information, learning it as individual identification data, and storing it. This enables highly accurate identification and management of information.

[0445] A "device for receiving information input from the user" refers to an input device or interface that allows the user to input handwriting and other information as digital data.

[0446] "A device for converting the received information and transmitting it via a network" refers to a device that has the function of converting input digital data into a predetermined format and securely transmitting it to another device or system via a communication network.

[0447] A "device for analyzing received information, learning it as individual identification data, and storing it" is a device that analyzes data received via a network using a specific algorithm, creates an identification model that reflects the characteristics of an individual, and stores it in a memory device.

[0448] A "device for individual verification" is a device that compares a stored individual identification model with newly entered data to identify and verify an individual.

[0449] A "device for outputting results to a display device" is a device that displays the results of individual verification on a screen or other output means in order to inform the user or a specific system of the results in an easily understandable manner.

[0450] A "device for relearning information and updating individual identification data" is a device that relearns individual characteristics that change over time and due to information fluctuations, and maintains existing identification models in an up-to-date state.

[0451] A "device for detecting anomalies in information" is a device that inspects input or processed data for anomalies and issues a warning if a problem occurs.

[0452] The system provided in this invention is for individual verification using the user's handwritten information and mainly consists of three elements: a server, a terminal, and the user.

[0453] First, the user inputs information via a device. This device could be a tablet or a smartphone, for example. The device is equipped with a mechanism that converts handwritten information, such as a stylus pen or touchscreen, into digital data. This conversion to digital format is performed using a dedicated application installed on the device, which has a handwriting recognition function.

[0454] The converted data is securely encrypted by the terminal and sent to the server over the network. The terminal uses encryption technologies such as TLS (Transport Layer Security) to transmit the data and prevent it from being leaked to third parties.

[0455] The server is equipped with hardware and software to analyze the received digital information and learn the user's unique characteristics as identification data. Examples of software used include machine learning frameworks such as TensorFlow and PyTorch. These are used to build a generative AI model that captures the characteristics of handwriting.

[0456] The generated model is stored in the database, and when a new individual verification request is received, the existing data is compared with the newly entered data. This comparison verifies the user's identity, and the result is returned to the terminal and displayed to the user.

[0457] This system includes a function to periodically retrain data, updating identification data to account for changes in user handwriting over time. It also features a function to detect anomalies in the information, playing a role in preventing unauthorized access. In this way, the system achieves highly reliable and secure individual verification while providing users with convenient access.

[0458] Specific examples of its use include online banking and secure electronic signatures. An example of a prompt message might be, "I would like to use your handwriting to securely access online services. Please enter your signature on the terminal."

[0459] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0460] Step 1:

[0461] The user uses a dedicated application on the device to input their signature or a designated text by hand. The input information is acquired as digital data, including pen pressure, speed, and angle. The device picks up this input data and measures various handwriting characteristics using its handwriting recognition function.

[0462] Step 2:

[0463] The device digitizes the acquired handwritten data and converts it into a data format. Specifically, it extracts features from the raw data and represents them as vectorized data. This digital data is encrypted and sent to the server using the TLS protocol to ensure security.

[0464] Step 3:

[0465] The server receives digitized handwriting data transmitted from the terminal. A pre-configured data cleaning algorithm is applied to the received data to remove noise and normalize the data. A clean dataset is then prepared.

[0466] Step 4:

[0467] The server trains a generative AI model using normalized data. In this step, machine learning libraries such as TensorFlow and PyTorch are used to learn the user's handwriting features. The model is then adjusted to recognize user-specific patterns, and the trained model is stored in a database.

[0468] Step 5:

[0469] If another individual verification request is made, the user re-enters the handwritten data on the device. The device acquires this new handwriting data in real time, encrypts it again, and sends it to the server.

[0470] Step 6:

[0471] The server compares the newly received handwriting data with the trained model. It calculates a similarity score and evaluates whether this score exceeds a pre-set threshold. If so, it determines that user verification was successful.

[0472] Step 7:

[0473] The server returns the authentication result to the terminal, which then displays this result to the user. If successful, access to the system and execution of transactions are permitted.

[0474] Step 8:

[0475] In addition to this process, the server can periodically retrain each user's handwriting model to improve and update its accuracy. This allows the system to take into account changes in handwriting over time.

[0476] (Application Example 1)

[0477] 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."

[0478] Traditional authentication methods have made it difficult to conduct secure electronic transactions while maintaining a balance between trustworthiness and convenience. Furthermore, these methods cannot completely prevent unauthorized access, and the transaction procedures are cumbersome.

[0479] 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.

[0480] In this invention, the server includes a device for acquiring handwriting data, a device for modeling the acquired handwriting data as personal identification information, a device for performing identity verification by comparing the modeled handwriting data with the handwriting data entered during authentication, and a device for executing transaction processing upon successful authentication. This enables users to conduct electronic transactions simply and securely.

[0481] A "device for acquiring handwriting data" is a device that electronically acquires information entered by a user in their handwriting and collects that data.

[0482] A "device for modeling as personal identification information" is a device that converts acquired handwriting data into a digital model while retaining individual characteristics, and structures it as data for identifying individuals.

[0483] A "device for verifying identity by comparing handwriting data with handwriting data entered during authentication" is a device that compares a registered digital model with newly entered handwriting data and authenticates whether the person is who they claim to be based on the degree of matching.

[0484] A "device for executing transaction processing upon successful authentication" is a device that automatically proceeds with a predetermined electronic transaction or procedure when the user's identity is successfully authenticated.

[0485] This invention is a handwriting authentication system for securely conducting electronic transactions using a smart device. In this system, the terminal acquires handwriting data and converts it into a digital format. When a user handwrites their signature into the smart device, the terminal recognizes it and converts it into the necessary digital data. By utilizing the latest drawing libraries (e.g., Draw2D) in this device, accurate handwriting information can be acquired.

[0486] The converted digital data is sent to the server via a secure communication protocol (e.g., HTTPS). The server receives this data and models it as personal identification information using a pre-trained generative AI model. This module utilizes advanced machine learning frameworks such as TensorFlow, which play a role in improving the accuracy of handwriting recognition. Cloud-based systems such as Amazon RDS are used for database management to ensure data consistency and availability.

[0487] When an authentication request is received, the server compares a trained personal model with real-time input handwriting data. This process calculates a similarity score and verifies the user's identity by evaluating whether it exceeds a certain threshold. If authentication is successful, the server immediately returns the result to the terminal, and the next stage, transaction processing, is executed. This transaction processing includes online shopping and electronic payments, allowing users to enjoy secure and fast services.

[0488] For example, when a user pays for coffee purchased at a cafe using this system, real-time authentication is performed, and the user is notified immediately upon completion of the payment, thus minimizing the use of cash or cards.

[0489] An example of a prompt might be: "Show a scenario where a user purchases coffee at a cafe, uses a smart device to digitally sign, and is successfully authenticated and securely completes the electronic payment."

[0490] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0491] Step 1:

[0492] The user inputs their signature by hand on a smart device. The device acquires the input signature as handwriting data and converts it into a digital format. The input is a handwritten signature, and the output is the digital data of that signature. A drawing library on the device (e.g., Draw2D) is used for this conversion.

[0493] Step 2:

[0494] The terminal transmits the handwriting data, converted into a digital format, to the server via a secure communication protocol. The input is the digital handwriting data, and the output is the result of the data transmission to the server. The HTTPS protocol is used for secure data transfer.

[0495] Step 3:

[0496] The server inputs the received handwriting data into a generating AI model to create a model that serves as personal identification information. The input is the received handwriting data, and the output is the personal model. An AI framework such as TensorFlow is used to perform the data modeling.

[0497] Step 4:

[0498] When a user requests authentication, the terminal converts the newly entered handwriting data back into a digital format and sends it to the server. The input is a signature entered in real time, and the output is the digitally converted real-time handwriting data.

[0499] Step 5:

[0500] The server compares a trained model with real-time handwriting data and calculates a similarity score. The input is the trained model and real-time data, and the output is the similarity score. An AI model is used to calculate the similarity score.

[0501] Step 6:

[0502] The server evaluates the similarity score and determines that authentication is successful if it exceeds the threshold. The input is the calculated similarity score, and the output is whether authentication was successful or not. The threshold value is pre-set and is determined here.

[0503] Step 7:

[0504] If authentication is successful, the server returns the result to the terminal, and the transaction process is executed. The input is the authentication result, and the output is the result of the transaction process execution. A specific transaction, such as online shopping or food delivery, is initiated.

[0505] 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.

[0506] This invention relates to a system that makes the authentication process secure and flexible by incorporating emotion recognition into a personal authentication system using handwriting data. This system mainly consists of three roles: server, terminal, and user, and by adding an emotion engine, it enables advanced authentication based on the user's emotional state.

[0507] First, the user inputs a signature or specific text by hand into the device. The device captures this as handwriting data, converts it into digital data, and uses an emotion engine to extract emotional data from the handwriting. The emotion engine analyzes elements such as pen pressure, speed, and changes in letter shape to evaluate the user's emotional state.

[0508] The device sends this data to the server. The server analyzes the received handwriting and sentiment data to train a user identification model. This model combines handwriting and sentiment characteristics to capture the user's personality in more detail. The model is then stored in a database and used for subsequent authentication requests.

[0509] When an authentication request arises, the user enters their handwritten signature again on the device. The device captures emotional data along with the handwriting and sends it to the server. The server uses a trained model to perform authentication based on the new data. Here, the emotional data plays a supporting role, allowing for additional processing, such as issuing a separate warning if a stressed or agitated state is detected.

[0510] The authentication result is returned from the server to the terminal, which then displays it to the user. If successful, the user is allowed to proceed to the next step (logging into the system or starting a transaction). If it fails, the user receives feedback about the error and is given the option to retry.

[0511] As a concrete example, it is used in corporate security systems when employees access confidential information. In addition to basic authentication using handwriting, it can prevent unauthorized access by checking the stress level and emotional stability at the time.

[0512] Thus, the present invention provides more comprehensive security and improves the user experience by combining emotion recognition with conventional identity verification methods.

[0513] The following describes the processing flow.

[0514] Step 1:

[0515] Users input signatures or specific sentences using the device's handwriting input interface. During this process, handwriting data, including pen pressure and writing speed, is recorded.

[0516] Step 2:

[0517] The device sends the input handwriting data to an emotion engine, which estimates the user's emotional state from the characteristics of the handwriting. The emotion engine analyzes pen pressure, speed, and changes in letter shape to extract emotional parameters such as the degree of relaxation or stress.

[0518] Step 3:

[0519] The device sends the acquired handwriting data and emotion parameters to the server. Encryption is applied to maintain data integrity and confidentiality.

[0520] Step 4:

[0521] The server analyzes the received data and creates or updates a user identification model. This model combines both handwriting and emotions to record the user's characteristics with high accuracy.

[0522] Step 5:

[0523] During the authentication request, the user re-enters their handwriting into the device. The device retrieves the handwriting data and sentiment information in real time and sends it to the server.

[0524] Step 6:

[0525] The server performs authentication by comparing the new handwriting data with a previously acquired handwriting model. If the similarity exceeds a certain threshold, it makes a final authentication decision after considering emotional information.

[0526] Step 7:

[0527] The server returns the authentication result to the terminal. The result includes information such as whether authentication was successful or failed, and whether or not there are any emotional abnormalities.

[0528] Step 8:

[0529] The device displays the received authentication result to the user. If authentication is successful, it grants permission for the next action (e.g., access to confidential information). If necessary, the user will also be notified of any emotional disturbances.

[0530] (Example 2)

[0531] 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."

[0532] Conventional identity verification systems rely solely on handwriting data for authentication, which presents security challenges. Furthermore, they fail to consider the user's emotional state, making them prone to unauthorized access and misidentification. Therefore, there is a need to establish a more secure and flexible identity verification method.

[0533] 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.

[0534] In this invention, the server includes a device for acquiring handwriting data, a device for modeling the acquired handwriting data as personal identification information, and an emotion analysis device for evaluating emotional states from the handwriting data. This makes it possible to authenticate users from multiple perspectives, considering both handwriting and emotions.

[0535] "Handwriting data" refers to information that includes characteristics such as the shape of characters and signatures entered by hand, as well as pen pressure and speed.

[0536] "Personal identification information" refers to data used to identify a specific individual, and is modeled based on handwriting characteristics and emotional states.

[0537] An "emotion analysis device" is a device that analyzes physical characteristics such as pen pressure and drawing speed from handwriting data to evaluate the user's emotional state.

[0538] "Identity verification" is the process of confirming and authenticating a specific individual based on entered handwriting data and emotional state data.

[0539] "Anomaly detection" is a process for identifying deviations from normal handwriting data and emotional states, and for identifying suspicious behavior or conditions.

[0540] This invention is a personal authentication system that combines handwriting data and emotional state. The system mainly consists of a server, a terminal, and a user interface.

[0541] Users input signatures or specific text using a stylus pen or a tablet's touchscreen. The device captures the handwriting data and saves it as digital data, including details such as speed and pressure. In addition, the device incorporates an emotion analyzer that analyzes the user's emotions based on changes in their handwriting and generates data accordingly.

[0542] The device sends this data to the server. The server uses a generative AI model to create a user identification model based on the handwriting data and sentiment data. This model accurately represents the user's unique handwriting and sentiment characteristics and is stored in a database.

[0543] A concrete example of its application is a company's security system. For instance, when an employee accesses confidential information, this authentication system can be used to perform authentication in two stages—by analyzing handwriting and emotions—contributing to the prevention of unauthorized access.

[0544] An example of a prompt to input into a generative AI model is: "Please describe the design of a system that performs user authentication based on data of a user's handwritten signature and its emotional state."

[0545] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0546] Step 1:

[0547] Users input handwritten signatures or specific text into the device. Input includes physical writing via a stylus pen or tablet touchscreen. Output is captured handwriting data of the handwritten letters and signatures. This data includes information such as pressure, speed, and letterform, and is converted into a digital format.

[0548] Step 2:

[0549] The terminal transmits the captured handwriting data to an emotion analysis device, which evaluates the emotional state from the handwriting. The input is the handwriting data obtained in step 1. The emotion analysis device analyzes changes in pen pressure and writing style to extract emotional characteristics. As output, emotion data indicating the user's emotional state is generated.

[0550] Step 3:

[0551] The terminal transmits handwriting data and sentiment data to the server. The input is handwriting data and sentiment data, and the output is secure data transmission to the server. Data security is crucial in this process, and encrypted communication is used.

[0552] Step 4:

[0553] The server uses the received data to train a personal identification model using a generative AI model. The input consists of handwriting data and sentiment data sent from the terminal. The server combines these to create a detailed personal authentication model, and the output is stored in a database. This model represents the user's handwriting characteristics and sentiment characteristics.

[0554] Step 5:

[0555] When an authentication request is received, the user enters their handwritten signature again on the device. The input is a newly recorded handwritten signature. The output is a capture of the latest handwriting and sentiment data.

[0556] Step 6:

[0557] The terminal sends new handwriting and emotion data to the server. The input is the data captured in step 5, and the output is the data transmission to the server.

[0558] Step 7:

[0559] The server uses a trained personal identification model to perform authentication based on new data. The input is data newly sent from the terminal. The server analyzes the input data based on the model and outputs a result indicating whether authentication was successful or failed.

[0560] Step 8:

[0561] The server returns the authentication result to the terminal, and the terminal displays the result to the user. The input is the authentication result received from the server, and the output is the notification of the result to the user. If authentication is successful, the user is allowed to proceed to the next step; if it fails, feedback is provided for retrying.

[0562] (Application Example 2)

[0563] 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."

[0564] Traditional authentication systems rely on static personal identification information, resulting in security vulnerabilities and making it difficult to prevent unauthorized access. Furthermore, by failing to consider the user's emotional state, opportunities for improving usability in the authentication process were lost.

[0565] 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.

[0566] In this invention, the server includes means for analyzing emotional information from handwriting data, means for generating a personal identification model incorporating the emotional information, and means for performing access control based on the user's mental state. This makes it possible to improve the accuracy of personal identification, more effectively prevent unauthorized access, and improve usability.

[0567] "Handwriting data" refers to information that digitally represents characters or signatures entered by a user through handwriting.

[0568] "Emotional information" refers to data that represents the user's emotional state, analyzed from handwriting data.

[0569] A "personal identification model" is a model constructed to identify individuals using handwriting data and sentiment information.

[0570] "Access control" is the process of managing users' access rights to specific information and allowing access only within the permitted scope.

[0571] A description of embodiments for carrying out the present invention will be provided.

[0572] This system primarily consists of three roles: server, terminal, and user. The user uses a dedicated input device to handwrite a signature or specific text into the terminal. The terminal captures the handwriting data and converts it into digital data. Furthermore, the terminal uses an emotion engine to analyze emotional information from the handwriting data and evaluate the user's emotional state. In this process, factors such as handwriting pressure, speed, and changes in letter shape are analyzed to extract the user's emotional characteristics.

[0573] The server receives handwriting data and emotional information transmitted from the terminal and generates a personal identification model based on this data. This model combines handwriting data and emotional information to capture the user's personality in detail. The generated personal identification model is stored in a database and used in subsequent authentication requests.

[0574] When an authentication request occurs, the user re-enters their handwritten signature into the terminal. The terminal captures the new handwriting data and emotional information and sends it to the server. The server uses a trained personal identification model to authenticate the user based on the new data. The authentication process considers both handwriting characteristics and emotional characteristics. Using emotional information allows for flexible responses, such as issuing warnings when the user is stressed or agitated.

[0575] For example, this system may be used when employees of large companies remotely access confidential files. The system automatically sends an alert to security personnel if an employee's stress level is unusual.

[0576] An example of a prompt for a generative AI model would be, "Explain the process of authenticating an individual using handwriting and sentiment data."

[0577] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0578] Step 1:

[0579] Users input signatures or specific text by hand on the device. The input handwriting data is captured in real time by the device and converted into a digital format. This input data includes detailed parameters such as pen pressure, speed, and letter shape.

[0580] Step 2:

[0581] The device passes the acquired handwriting data to the emotion engine. The emotion engine analyzes each element of the handwriting and extracts the user's emotional characteristics. Specifically, it evaluates stress levels, relaxation levels, etc., based on variations in speed and pressure. Emotional information is generated as a result of this analysis.

[0582] Step 3:

[0583] The handwriting data and emotional information generated on the device are sent to the server. The server receives this information and generates an individual identification model based on it. In model generation, a generative AI model is used to train a composite data combining handwriting characteristics and emotional characteristics. Big data analysis technology is utilized in this process.

[0584] Step 4:

[0585] The server stores the generated personal identification model in a database. This model is stored in a secure environment because it will be used in subsequent authentication processes.

[0586] Step 5:

[0587] If a new authentication request arises, the user enters their handwritten signature again on the device. The device then recaptures the latest handwriting data and sentiment information and sends it to the server.

[0588] Step 6:

[0589] The server compares the newly transmitted data with existing personal identification models. This comparison is used to authenticate the user's identity. If a discrepancy is detected between the handwriting and sentiment during this process, access will be restricted.

[0590] Step 7:

[0591] The authentication result is sent back from the server to the terminal. If authentication is successful, the user can access the system normally. If it fails, the user is shown an error message and prompted to try again. This feedback process improves the user experience.

[0592] 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.

[0593] 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.

[0594] 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.

[0595] [Fourth Embodiment]

[0596] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0597] 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.

[0598] 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).

[0599] 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.

[0600] 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.

[0601] 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).

[0602] 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.

[0603] 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.

[0604] 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.

[0605] 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.

[0606] 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.

[0607] 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.

[0608] 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".

[0609] This invention relates to a handwriting authentication system that uses a user's handwriting as personal identification information to achieve highly reliable identity verification using common hardware. The embodiment of this system mainly consists of three main roles: server, terminal, and user.

[0610] First, the user handwrites their signature or a specific sentence onto the device. The device acquires this as handwriting data and converts it into a digital format. The converted data is then sent to a server via the network.

[0611] The server analyzes the received handwriting data and trains it as a user-specific personal identification model. This handwriting model reflects the user's characteristics and is used in the subsequent authentication process. The trained model is stored in a database and referenced in subsequent authentication requests.

[0612] When an authentication request occurs, the user re-enters handwriting data. The device collects this new data and sends it to the server in real time. The server compares the real-time handwriting data with a trained model and calculates a similarity score. If this score exceeds a pre-set threshold, the server determines that the user's identity has been successfully verified.

[0613] The authentication result is returned from the server to the terminal, which then displays the result to the user. If authentication is successful, the user can proceed to the next stage, for example, to complete logging into the system or to initiate a secure transaction.

[0614] In addition, this system also has a function to detect anomalies in handwriting data, preventing unauthorized access. Furthermore, to accommodate changes in handwriting over time, a mechanism has been introduced to periodically retrain the data and update the model.

[0615] Thus, this invention aims to enhance security and improve the user experience by utilizing user handwriting input. A specific example is its usefulness in secure, paperless identity verification during online banking. This configuration allows users to enjoy a high level of security using their everyday devices without any special preparation.

[0616] The following describes the processing flow.

[0617] Step 1:

[0618] The user uses the terminal's input interface to handwrite a signature or specific text. At this point, the terminal captures the handwriting data and formats it as digital data.

[0619] Step 2:

[0620] The device sends the captured handwriting data to the server. The transmission is performed using a secure network protocol to protect the confidentiality of the data.

[0621] Step 3:

[0622] The server analyzes the received handwriting data and generates a user-specific personal identification model. This model learns the user's handwriting characteristics and stores that information in a database.

[0623] Step 4:

[0624] If an authentication request occurs, the user will again enter their signature by hand on the device. The device will capture this new handwriting data and send it to the server in real time.

[0625] Step 5:

[0626] The server compares the newly received handwriting data with existing personal identification models. Using a comparison algorithm, it calculates the similarity of the handwriting and determines whether it exceeds a threshold.

[0627] Step 6:

[0628] The server determines the success or failure of authentication based on the similarity score. If authentication is successful, it generates a success message; if it fails, it generates a message prompting the user to retry.

[0629] Step 7:

[0630] The server sends the authentication result to the terminal. The terminal displays this result to the user, and if authentication is successful, it grants the next action (e.g., access permission to the system).

[0631] Step 8:

[0632] If necessary, the server updates the handwriting model by relearning data at regular intervals. This compensates for the effects of time on handwriting and maintains authentication accuracy.

[0633] (Example 1)

[0634] 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".

[0635] There is a need to effectively utilize handwritten information from individuals as identification data and enable sophisticated individual verification. However, conventional technologies suffer from insufficient identification accuracy, and the complexity of data updates as the number of users increases. In particular, processing of information fluctuations and anomaly detection is inadequate, and there is a need to ensure user convenience while maintaining security.

[0636] 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.

[0637] In this invention, the server includes a device for receiving information input from a user, a device for converting the received information and transmitting it over a network, and a device for analyzing the received information, learning it as individual identification data, and storing it. This enables highly accurate identification and management of information.

[0638] A "device for receiving information input from the user" refers to an input device or interface that allows the user to input handwriting and other information as digital data.

[0639] "A device for converting the received information and transmitting it via a network" refers to a device that has the function of converting input digital data into a predetermined format and securely transmitting it to another device or system via a communication network.

[0640] A "device for analyzing received information, learning it as individual identification data, and storing it" is a device that analyzes data received via a network using a specific algorithm, creates an identification model that reflects the characteristics of an individual, and stores it in a memory device.

[0641] A "device for individual verification" is a device that compares a stored individual identification model with newly entered data to identify and verify an individual.

[0642] A "device for outputting results to a display device" is a device that displays the results of individual verification on a screen or other output means in order to inform the user or a specific system of the results in an easily understandable manner.

[0643] A "device for relearning information and updating individual identification data" is a device that relearns individual characteristics that change over time and due to information fluctuations, and maintains existing identification models in an up-to-date state.

[0644] A "device for detecting anomalies in information" is a device that inspects input or processed data for anomalies and issues a warning if a problem occurs.

[0645] The system provided in this invention is for individual verification using the user's handwritten information and mainly consists of three elements: a server, a terminal, and the user.

[0646] First, the user inputs information via a device. This device could be a tablet or a smartphone, for example. The device is equipped with a mechanism that converts handwritten information, such as a stylus pen or touchscreen, into digital data. This conversion to digital format is performed using a dedicated application installed on the device, which has a handwriting recognition function.

[0647] The converted data is securely encrypted by the terminal and sent to the server over the network. The terminal uses encryption technologies such as TLS (Transport Layer Security) to transmit the data and prevent it from being leaked to third parties.

[0648] The server is equipped with hardware and software to analyze the received digital information and learn the user's unique characteristics as identification data. Examples of software used include machine learning frameworks such as TensorFlow and PyTorch. These are used to build a generative AI model that captures the characteristics of handwriting.

[0649] The generated model is stored in the database, and when a new individual verification request is received, the existing data is compared with the newly entered data. This comparison verifies the user's identity, and the result is returned to the terminal and displayed to the user.

[0650] This system includes a function to periodically retrain data, updating identification data to account for changes in user handwriting over time. It also features a function to detect anomalies in the information, playing a role in preventing unauthorized access. In this way, the system achieves highly reliable and secure individual verification while providing users with convenient access.

[0651] Specific examples of its use include online banking and secure electronic signatures. An example of a prompt message might be, "I would like to use your handwriting to securely access online services. Please enter your signature on the terminal."

[0652] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0653] Step 1:

[0654] The user uses a dedicated application on the device to input their signature or a designated text by hand. The input information is acquired as digital data, including pen pressure, speed, and angle. The device picks up this input data and measures various handwriting characteristics using its handwriting recognition function.

[0655] Step 2:

[0656] The device digitizes the acquired handwritten data and converts it into a data format. Specifically, it extracts features from the raw data and represents them as vectorized data. This digital data is encrypted and sent to the server using the TLS protocol to ensure security.

[0657] Step 3:

[0658] The server receives digitized handwriting data transmitted from the terminal. A pre-configured data cleaning algorithm is applied to the received data to remove noise and normalize the data. A clean dataset is then prepared.

[0659] Step 4:

[0660] The server trains a generative AI model using normalized data. In this step, machine learning libraries such as TensorFlow and PyTorch are used to learn the user's handwriting features. The model is then adjusted to recognize user-specific patterns, and the trained model is stored in a database.

[0661] Step 5:

[0662] If another individual verification request is made, the user re-enters the handwritten data on the device. The device acquires this new handwriting data in real time, encrypts it again, and sends it to the server.

[0663] Step 6:

[0664] The server compares the newly received handwriting data with the trained model. It calculates a similarity score and evaluates whether this score exceeds a pre-set threshold. If so, it determines that user verification was successful.

[0665] Step 7:

[0666] The server returns the authentication result to the terminal, which then displays this result to the user. If successful, access to the system and execution of transactions are permitted.

[0667] Step 8:

[0668] In addition to this process, the server can periodically retrain each user's handwriting model to improve and update its accuracy. This allows the system to take into account changes in handwriting over time.

[0669] (Application Example 1)

[0670] 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".

[0671] Traditional authentication methods have made it difficult to conduct secure electronic transactions while maintaining a balance between trustworthiness and convenience. Furthermore, these methods cannot completely prevent unauthorized access, and the transaction procedures are cumbersome.

[0672] 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.

[0673] In this invention, the server includes a device for acquiring handwriting data, a device for modeling the acquired handwriting data as personal identification information, a device for performing identity verification by comparing the modeled handwriting data with the handwriting data entered during authentication, and a device for executing transaction processing upon successful authentication. This enables users to conduct electronic transactions simply and securely.

[0674] A "device for acquiring handwriting data" is a device that electronically acquires information entered by a user in their handwriting and collects that data.

[0675] A "device for modeling as personal identification information" is a device that converts acquired handwriting data into a digital model while retaining individual characteristics, and structures it as data for identifying individuals.

[0676] A "device for verifying identity by comparing handwriting data with handwriting data entered during authentication" is a device that compares a registered digital model with newly entered handwriting data and authenticates whether the person is who they claim to be based on the degree of matching.

[0677] A "device for executing transaction processing upon successful authentication" is a device that automatically proceeds with a predetermined electronic transaction or procedure when the user's identity is successfully authenticated.

[0678] This invention is a handwriting authentication system for securely conducting electronic transactions using a smart device. In this system, the terminal acquires handwriting data and converts it into a digital format. When a user handwrites their signature into the smart device, the terminal recognizes it and converts it into the necessary digital data. By utilizing the latest drawing libraries (e.g., Draw2D) in this device, accurate handwriting information can be acquired.

[0679] The converted digital data is sent to the server via a secure communication protocol (e.g., HTTPS). The server receives this data and models it as personal identification information using a pre-trained generative AI model. This module utilizes advanced machine learning frameworks such as TensorFlow, which play a role in improving the accuracy of handwriting recognition. Cloud-based systems such as Amazon RDS are used for database management to ensure data consistency and availability.

[0680] When an authentication request is received, the server compares a trained personal model with real-time input handwriting data. This process calculates a similarity score and verifies the user's identity by evaluating whether it exceeds a certain threshold. If authentication is successful, the server immediately returns the result to the terminal, and the next stage, transaction processing, is executed. This transaction processing includes online shopping and electronic payments, allowing users to enjoy secure and fast services.

[0681] For example, when a user pays for coffee purchased at a cafe using this system, real-time authentication is performed, and the user is notified immediately upon completion of the payment, thus minimizing the use of cash or cards.

[0682] An example of a prompt might be: "Show a scenario where a user purchases coffee at a cafe, uses a smart device to digitally sign, and is successfully authenticated and securely completes the electronic payment."

[0683] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0684] Step 1:

[0685] The user inputs their signature by hand on a smart device. The device acquires the input signature as handwriting data and converts it into a digital format. The input is a handwritten signature, and the output is the digital data of that signature. A drawing library on the device (e.g., Draw2D) is used for this conversion.

[0686] Step 2:

[0687] The terminal transmits the handwriting data, converted into a digital format, to the server via a secure communication protocol. The input is the digital handwriting data, and the output is the result of the data transmission to the server. The HTTPS protocol is used for secure data transfer.

[0688] Step 3:

[0689] The server inputs the received handwriting data into a generating AI model to create a model that serves as personal identification information. The input is the received handwriting data, and the output is the personal model. An AI framework such as TensorFlow is used to perform the data modeling.

[0690] Step 4:

[0691] When a user requests authentication, the terminal converts the newly entered handwriting data back into a digital format and sends it to the server. The input is a signature entered in real time, and the output is the digitally converted real-time handwriting data.

[0692] Step 5:

[0693] The server compares a trained model with real-time handwriting data and calculates a similarity score. The input is the trained model and real-time data, and the output is the similarity score. An AI model is used to calculate the similarity score.

[0694] Step 6:

[0695] The server evaluates the similarity score and determines that authentication is successful if it exceeds the threshold. The input is the calculated similarity score, and the output is whether authentication was successful or not. The threshold value is pre-set and is determined here.

[0696] Step 7:

[0697] If authentication is successful, the server returns the result to the terminal, and the transaction process is executed. The input is the authentication result, and the output is the result of the transaction process execution. A specific transaction, such as online shopping or food delivery, is initiated.

[0698] 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.

[0699] This invention relates to a system that makes the authentication process secure and flexible by incorporating emotion recognition into a personal authentication system using handwriting data. This system mainly consists of three roles: server, terminal, and user, and by adding an emotion engine, it enables advanced authentication based on the user's emotional state.

[0700] First, the user inputs a signature or specific text by hand into the device. The device captures this as handwriting data, converts it into digital data, and uses an emotion engine to extract emotional data from the handwriting. The emotion engine analyzes elements such as pen pressure, speed, and changes in letter shape to evaluate the user's emotional state.

[0701] The device sends this data to the server. The server analyzes the received handwriting and sentiment data to train a user identification model. This model combines handwriting and sentiment characteristics to capture the user's personality in more detail. The model is then stored in a database and used for subsequent authentication requests.

[0702] When an authentication request arises, the user enters their handwritten signature again on the device. The device captures emotional data along with the handwriting and sends it to the server. The server uses a trained model to perform authentication based on the new data. Here, the emotional data plays a supporting role, allowing for additional processing, such as issuing a separate warning if a stressed or agitated state is detected.

[0703] The authentication result is returned from the server to the terminal, which then displays it to the user. If successful, the user is allowed to proceed to the next step (logging into the system or starting a transaction). If it fails, the user receives feedback about the error and is given the option to retry.

[0704] As a concrete example, it is used in corporate security systems when employees access confidential information. In addition to basic authentication using handwriting, it can prevent unauthorized access by checking the stress level and emotional stability at the time.

[0705] Thus, the present invention provides more comprehensive security and improves the user experience by combining emotion recognition with conventional identity verification methods.

[0706] The following describes the processing flow.

[0707] Step 1:

[0708] Users input signatures or specific sentences using the device's handwriting input interface. During this process, handwriting data, including pen pressure and writing speed, is recorded.

[0709] Step 2:

[0710] The device sends the input handwriting data to an emotion engine, which estimates the user's emotional state from the characteristics of the handwriting. The emotion engine analyzes pen pressure, speed, and changes in letter shape to extract emotional parameters such as the degree of relaxation or stress.

[0711] Step 3:

[0712] The device sends the acquired handwriting data and emotion parameters to the server. Encryption is applied to maintain data integrity and confidentiality.

[0713] Step 4:

[0714] The server analyzes the received data and creates or updates a user identification model. This model combines both handwriting and emotions to record the user's characteristics with high accuracy.

[0715] Step 5:

[0716] During the authentication request, the user re-enters their handwriting into the device. The device retrieves the handwriting data and sentiment information in real time and sends it to the server.

[0717] Step 6:

[0718] The server performs authentication by comparing the new handwriting data with a previously acquired handwriting model. If the similarity exceeds a certain threshold, it makes a final authentication decision after considering emotional information.

[0719] Step 7:

[0720] The server returns the authentication result to the terminal. The result includes information such as whether authentication was successful or failed, and whether or not there are any emotional abnormalities.

[0721] Step 8:

[0722] The device displays the received authentication result to the user. If authentication is successful, it grants permission for the next action (e.g., access to confidential information). If necessary, the user will also be notified of any emotional disturbances.

[0723] (Example 2)

[0724] 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".

[0725] Conventional identity verification systems rely solely on handwriting data for authentication, which presents security challenges. Furthermore, they fail to consider the user's emotional state, making them prone to unauthorized access and misidentification. Therefore, there is a need to establish a more secure and flexible identity verification method.

[0726] 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.

[0727] In this invention, the server includes a device for acquiring handwriting data, a device for modeling the acquired handwriting data as personal identification information, and an emotion analysis device for evaluating emotional states from the handwriting data. This makes it possible to authenticate users from multiple perspectives, considering both handwriting and emotions.

[0728] "Handwriting data" refers to information that includes characteristics such as the shape of characters and signatures entered by hand, as well as pen pressure and speed.

[0729] "Personal identification information" refers to data used to identify a specific individual, and is modeled based on handwriting characteristics and emotional states.

[0730] An "emotion analysis device" is a device that analyzes physical characteristics such as pen pressure and drawing speed from handwriting data to evaluate the user's emotional state.

[0731] "Identity verification" is the process of confirming and authenticating a specific individual based on entered handwriting data and emotional state data.

[0732] "Anomaly detection" is a process for identifying deviations from normal handwriting data and emotional states, and for identifying suspicious behavior or conditions.

[0733] This invention is a personal authentication system that combines handwriting data and emotional state. The system mainly consists of a server, a terminal, and a user interface.

[0734] Users input signatures or specific text using a stylus pen or a tablet's touchscreen. The device captures the handwriting data and saves it as digital data, including details such as speed and pressure. In addition, the device incorporates an emotion analyzer that analyzes the user's emotions based on changes in their handwriting and generates data accordingly.

[0735] The device sends this data to the server. The server uses a generative AI model to create a user identification model based on the handwriting data and sentiment data. This model accurately represents the user's unique handwriting and sentiment characteristics and is stored in a database.

[0736] A concrete example of its application is a company's security system. For instance, when an employee accesses confidential information, this authentication system can be used to perform authentication in two stages—by analyzing handwriting and emotions—contributing to the prevention of unauthorized access.

[0737] An example of a prompt to input into a generative AI model is: "Please describe the design of a system that performs user authentication based on data of a user's handwritten signature and its emotional state."

[0738] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0739] Step 1:

[0740] Users input handwritten signatures or specific text into the device. Input includes physical writing via a stylus pen or tablet touchscreen. Output is captured handwriting data of the handwritten letters and signatures. This data includes information such as pressure, speed, and letterform, and is converted into a digital format.

[0741] Step 2:

[0742] The terminal transmits the captured handwriting data to an emotion analysis device, which evaluates the emotional state from the handwriting. The input is the handwriting data obtained in step 1. The emotion analysis device analyzes changes in pen pressure and writing style to extract emotional characteristics. As output, emotion data indicating the user's emotional state is generated.

[0743] Step 3:

[0744] The terminal transmits handwriting data and sentiment data to the server. The input is handwriting data and sentiment data, and the output is secure data transmission to the server. Data security is crucial in this process, and encrypted communication is used.

[0745] Step 4:

[0746] The server uses the received data to train a personal identification model using a generative AI model. The input consists of handwriting data and sentiment data sent from the terminal. The server combines these to create a detailed personal authentication model, and the output is stored in a database. This model represents the user's handwriting characteristics and sentiment characteristics.

[0747] Step 5:

[0748] When an authentication request is received, the user enters their handwritten signature again on the device. The input is a newly recorded handwritten signature. The output is a capture of the latest handwriting and sentiment data.

[0749] Step 6:

[0750] The terminal sends new handwriting and emotion data to the server. The input is the data captured in step 5, and the output is the data transmission to the server.

[0751] Step 7:

[0752] The server uses a trained personal identification model to perform authentication based on new data. The input is data newly sent from the terminal. The server analyzes the input data based on the model and outputs a result indicating whether authentication was successful or failed.

[0753] Step 8:

[0754] The server returns the authentication result to the terminal, and the terminal displays the result to the user. The input is the authentication result received from the server, and the output is the notification of the result to the user. If authentication is successful, the user is allowed to proceed to the next step; if it fails, feedback is provided for retrying.

[0755] (Application Example 2)

[0756] 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".

[0757] Traditional authentication systems rely on static personal identification information, resulting in security vulnerabilities and making it difficult to prevent unauthorized access. Furthermore, by failing to consider the user's emotional state, opportunities for improving usability in the authentication process were lost.

[0758] 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.

[0759] In this invention, the server includes means for analyzing emotional information from handwriting data, means for generating a personal identification model incorporating the emotional information, and means for performing access control based on the user's mental state. This makes it possible to improve the accuracy of personal identification, more effectively prevent unauthorized access, and improve usability.

[0760] "Handwriting data" refers to information that digitally represents characters or signatures entered by a user through handwriting.

[0761] "Emotional information" refers to data that represents the user's emotional state, analyzed from handwriting data.

[0762] A "personal identification model" is a model constructed to identify individuals using handwriting data and sentiment information.

[0763] "Access control" is the process of managing users' access rights to specific information and allowing access only within the permitted scope.

[0764] A description of embodiments for carrying out the present invention will be provided.

[0765] This system primarily consists of three roles: server, terminal, and user. The user uses a dedicated input device to handwrite a signature or specific text into the terminal. The terminal captures the handwriting data and converts it into digital data. Furthermore, the terminal uses an emotion engine to analyze emotional information from the handwriting data and evaluate the user's emotional state. In this process, factors such as handwriting pressure, speed, and changes in letter shape are analyzed to extract the user's emotional characteristics.

[0766] The server receives handwriting data and emotional information transmitted from the terminal and generates a personal identification model based on this data. This model combines handwriting data and emotional information to capture the user's personality in detail. The generated personal identification model is stored in a database and used in subsequent authentication requests.

[0767] When an authentication request occurs, the user re-enters their handwritten signature into the terminal. The terminal captures the new handwriting data and emotional information and sends it to the server. The server uses a trained personal identification model to authenticate the user based on the new data. The authentication process considers both handwriting characteristics and emotional characteristics. Using emotional information allows for flexible responses, such as issuing warnings when the user is stressed or agitated.

[0768] For example, this system may be used when employees of large companies remotely access confidential files. The system automatically sends an alert to security personnel if an employee's stress level is unusual.

[0769] An example of a prompt for a generative AI model would be, "Explain the process of authenticating an individual using handwriting and sentiment data."

[0770] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0771] Step 1:

[0772] Users input signatures or specific text by hand on the device. The input handwriting data is captured in real time by the device and converted into a digital format. This input data includes detailed parameters such as pen pressure, speed, and letter shape.

[0773] Step 2:

[0774] The device passes the acquired handwriting data to the emotion engine. The emotion engine analyzes each element of the handwriting and extracts the user's emotional characteristics. Specifically, it evaluates stress levels, relaxation levels, etc., based on variations in speed and pressure. Emotional information is generated as a result of this analysis.

[0775] Step 3:

[0776] The handwriting data and emotional information generated on the device are sent to the server. The server receives this information and generates an individual identification model based on it. In model generation, a generative AI model is used to train a composite data combining handwriting characteristics and emotional characteristics. Big data analysis technology is utilized in this process.

[0777] Step 4:

[0778] The server stores the generated personal identification model in a database. This model is stored in a secure environment because it will be used in subsequent authentication processes.

[0779] Step 5:

[0780] If a new authentication request arises, the user enters their handwritten signature again on the device. The device then recaptures the latest handwriting data and sentiment information and sends it to the server.

[0781] Step 6:

[0782] The server compares the newly transmitted data with existing personal identification models. This comparison is used to authenticate the user's identity. If a discrepancy is detected between the handwriting and sentiment during this process, access will be restricted.

[0783] Step 7:

[0784] The authentication result is sent back from the server to the terminal. If authentication is successful, the user can access the system normally. If it fails, the user is shown an error message and prompted to try again. This feedback process improves the user experience.

[0785] 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.

[0786] 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.

[0787] 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.

[0788] 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.

[0789] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0790] 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.

[0791] 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.

[0792] 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.

[0793] 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."

[0794] 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.

[0795] 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.

[0796] 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.

[0797] 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.

[0798] 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.

[0799] 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.

[0800] 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.

[0801] 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.

[0802] 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.

[0803] 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.

[0804] 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.

[0805] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0806] The following is further disclosed regarding the embodiments described above.

[0807] (Claim 1)

[0808] Means for obtaining handwriting data,

[0809] A means for modeling the acquired handwriting data as personal identification information,

[0810] A means for performing identity verification by comparing the modeled handwriting data with the handwriting data entered during authentication,

[0811] A means for outputting the results of the aforementioned identity verification,

[0812] A system that includes this.

[0813] (Claim 2)

[0814] The system according to claim 1, comprising means for retraining handwriting data and updating the model.

[0815] (Claim 3)

[0816] The system according to claim 1, comprising means for detecting anomalies in handwriting data.

[0817] "Example 1"

[0818] (Claim 1)

[0819] A device for receiving information input from the user,

[0820] A device for converting the received information and transmitting it over a network,

[0821] A device for analyzing received information, learning it as individual identification data, and storing it,

[0822] A device for performing individual verification by comparing the learned data with the information entered during verification,

[0823] A device for outputting the results of the individual verification to a display device,

[0824] A system that includes this.

[0825] (Claim 2)

[0826] The system according to claim 1, comprising a device for relearning information and updating individual identification data.

[0827] (Claim 3)

[0828] The system according to claim 1, comprising a device for detecting anomalies in information.

[0829] "Application Example 1"

[0830] (Claim 1)

[0831] A device for acquiring handwriting data,

[0832] A device for modeling the acquired handwriting data as personal identification information,

[0833] A device for performing user authentication by comparing the modeled handwriting data with the handwriting data entered during authentication,

[0834] A device for outputting the results of the aforementioned personal authentication,

[0835] A device for executing transaction processing upon successful authentication,

[0836] A system that includes this.

[0837] (Claim 2)

[0838] The system according to claim 1, comprising a device for retraining handwriting data and updating a model.

[0839] (Claim 3)

[0840] The system according to claim 1, comprising a device for detecting anomalies in handwriting data.

[0841] "Example 2 of combining an emotion engine"

[0842] (Claim 1)

[0843] A device for acquiring handwriting data,

[0844] A device for modeling the acquired handwriting data as personal identification information,

[0845] An emotion analysis device for evaluating emotional states from handwriting data,

[0846] A device for performing identity verification by comparing the modeled handwriting data and emotional state data with the handwriting data and emotional state data entered during authentication.

[0847] A device for outputting the results of user authentication and issuing warnings based on those results,

[0848] A system that includes this.

[0849] (Claim 2)

[0850] The system according to claim 1, comprising a device for retraining handwriting data and emotional state data and updating the model.

[0851] (Claim 3)

[0852] The system according to claim 1, comprising a device for detecting abnormalities in handwriting data and emotional state data.

[0853] "Application example 2 when combining with an emotional engine"

[0854] (Claim 1)

[0855] Means for obtaining handwriting data,

[0856] A means for modeling the acquired handwriting data as personal identification information,

[0857] A means for performing identity verification by comparing the modeled handwriting data with the handwriting data entered during authentication,

[0858] A means for outputting the results of the aforementioned identity verification,

[0859] Methods for analyzing emotional information from handwriting data,

[0860] A means for generating a personal identification model incorporating the aforementioned emotional information,

[0861] A means for controlling access based on the user's mental state,

[0862] A system that includes this.

[0863] (Claim 2)

[0864] The system according to claim 1, comprising means for retraining and updating a personal identification model based on handwriting data and sentiment information.

[0865] (Claim 3)

[0866] The system according to claim 1, comprising means for detecting anomalies in handwriting data and emotional information. [Explanation of Symbols]

[0867] 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. Means for obtaining handwriting data, A means for modeling the acquired handwriting data as personal identification information, A means for performing identity verification by comparing the modeled handwriting data with the handwriting data entered during authentication, A means for outputting the results of the aforementioned identity verification, A system that includes this.

2. The system according to claim 1, comprising means for retraining handwriting data and updating the model.

3. The system according to claim 1, comprising means for detecting anomalies in handwriting data.

Images