Apparatus and method for restoring near field communication signals using artificial intelligence technology

Abstract

The present invention relates to a Near Field Communication (NFC) signal restoration device, comprising: a preprocessing unit that receives and preprocesses an original NFC signal transmitted from an NFC signal transmitting device and detects a noisy NFC signal whose signal quality has degraded to a level below the signal quality required for NFC communication during the preprocessing process; a restoration unit that inputs the noisy NFC signal into a pre-prepared generation model and restores it into a clean NFC signal of the same signal quality as the original NFC signal by minimizing frequency distortion while maintaining the temporal continuity of the noisy NFC signal; and a data processing unit that analyzes the temporal characteristics of the restored clean NFC signal to detect a clock signal and generates data used in an application to which the NFC communication is applied based on the restored clean NFC signal and the detected clock signal.

Description

Technology Field

[0001] The present invention relates to an apparatus and method for restoring Near Field Communication (NFC) signals, and more particularly to an apparatus and method for restoring NFC signals of degraded quality due to signal attenuation, noise, and other environmental factors by utilizing an artificial intelligence model. Background Technology

[0003] NFC technology is a wireless communication technology that primarily operates in the 13.56 MHz frequency band and is generally used in mobile devices such as smartphones or electronic payment systems. Based on electromagnetic induction, NFC generates alternating current, enabling stable communication only over very short distances (within approximately 1 cm). Furthermore, a stable magnetic field is formed only when the transmitter and receiver are physically close, allowing for data transmission. Due to these characteristics, NFC can be applied in various fields, including mobile payments, transportation cards, access control, and data exchange.

[0004] However, due to the short communication distance of NFC (less than 1 cm), the signal weakens rapidly as the distance increases, which can lead to communication failure. Furthermore, as the communication distance increases, signal attenuation becomes more severe, and signal quality deteriorates due to noise or interference from the surrounding environment. Additionally, due to the short communication distance, NFC is used only in certain limited application fields, such as payment systems and access control systems. Moreover, as it requires physical tag or device contact, there are limitations in terms of broad applicability in production and industrial applications.

[0005] Therefore, research is needed on ways to overcome these limitations of NFC technology and enable reliable communication over a wider range. Prior art literature

[0007] Korean Patent Publication No. 10-2020-0062860 The problem to be solved

[0008] The present invention was devised to solve the above-mentioned problems, and the objective of the present invention is to provide an NFC signal recovery device and method utilizing an artificial intelligence model. means of solving the problem

[0010] An NFC signal restoration device according to an embodiment of the present invention for achieving the above objective comprises: a preprocessing unit that receives and preprocesses an original NFC signal transmitted from an NFC signal transmitting device and detects a noise NFC signal whose signal quality has degraded to a level below the signal quality required for NFC communication during the preprocessing process; a restoration unit that inputs the noise NFC signal into a pre-prepared generation model and restores it into a clean NFC signal of the same signal quality as the original NFC signal by minimizing frequency distortion while maintaining the temporal continuity of the noise NFC signal; and a data processing unit that analyzes the temporal characteristics of the restored clean NFC signal to detect a clock signal and generates data used in an application to which the NFC communication is applied based on the restored clean NFC signal and the detected clock signal.

[0011] An NFC signal restoration method according to an embodiment of the present invention for achieving the above objective comprises: a preprocessing unit receiving and preprocessing an original NFC signal transmitted from an NFC signal transmitting device, and detecting a noise NFC signal in which the signal quality has degraded to a level below the signal quality required for NFC communication during the preprocessing process; a restoration unit inputting the noise NFC signal into a pre-prepared generation model and restoring it to a clean NFC signal of the same signal quality as the original NFC signal by minimizing frequency distortion while maintaining the temporal continuity of the noise NFC signal; and a data processing unit analyzing the temporal characteristics of the restored clean NFC signal to detect a clock signal, and generating data used in an application to which the NFC communication is applied based on the restored clean NFC signal and the detected clock signal. Effects of the invention

[0013] According to one aspect of the present invention described above, by providing an NFC signal recovery device and method utilizing an artificial intelligence model, the NFC communication distance, which was previously limited to approximately 1 cm, is significantly extended to enable stable communication over a wider range.

[0014] Furthermore, by restoring attenuated signals through an artificial intelligence model that considers time-series characteristics, signal quality similar to the original NFC signal can be maintained even over long distances. This enables the application of NFC technology, which was previously limited to payment systems, to various fields such as smart homes, the Internet of Things (IoT), vehicle communication, and industrial systems.

[0015] Furthermore, NFC signal restoration can enhance the security of NFC communication by minimizing data loss and errors that may occur in the communication environment. Brief explanation of the drawing

[0017] FIG. 1 is a schematic diagram illustrating an NFC signal recovery device according to an embodiment of the present invention. FIG. 2 is a drawing showing detailed blocks of the NFC signal recovery device of FIG. 1. FIG. 3 is a diagram for explaining a generation model applied in the generation restorer of FIG. 2, And, FIG. 4 is a flowchart showing the NFC signal restoration operation of an NFC signal restoration device according to an embodiment of the present invention. Specific details for implementing the invention

[0018] The following detailed description of the invention refers to the accompanying drawings, which illustrate specific embodiments in which the invention may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the invention. It should be understood that various embodiments of the invention are different but need not be mutually exclusive. For example, specific shapes, structures, and characteristics described herein may be implemented in other embodiments without departing from the spirit and scope of the invention in relation to one embodiment. It should also be understood that the location or arrangement of individual components within each disclosed embodiment may be changed without departing from the spirit and scope of the invention. Accordingly, the following detailed description is not intended to be limiting, and the scope of the invention is limited only by the appended claims, including all equivalents to those claimed therein, provided they are appropriately described. Similar reference numerals in the drawings refer to the same or similar functions across various aspects.

[0019] The components according to the present invention are defined by functional distinction rather than physical distinction, and can be defined by the functions each performs. Each component may be implemented as hardware or as program code and processing units that perform each function, and the functions of two or more components may be included and implemented in a single component. Therefore, it should be noted that the names assigned to the components in the following embodiments are not intended to physically distinguish each component but are assigned to imply the representative function performed by each component, and that the technical concept of the present invention is not limited by the names of the components.

[0020] Preferred embodiments of the present invention will be described in more detail below with reference to the drawings.

[0021] FIG. 1 is a schematic diagram illustrating an NFC signal recovery device according to an embodiment of the present invention, FIG. 2 is a detailed block diagram illustrating the NFC signal recovery device of FIG. 1, and FIG. 3 is a diagram for explaining a generation model applied in the generation recovery device of FIG. 2.

[0022] The NFC signal recovery device illustrated in FIG. 1 includes a preprocessing unit (110), a recovery unit (120), and a data processing unit (130), and the detailed blocks of each component are as illustrated in FIG. 2. That is, the preprocessing unit (110) includes a receiving antenna (112), a sampler (114), an analog to digital (A / D) converter (116), and a decoder (118); the recovery unit (120) includes an NFC controller / driver (122) and a generation recovery unit (124); and the data processing unit (130) includes a clock signal detector (132) and a data generator (134).

[0023] The preprocessing unit (110) receives the original NFC signal transmitted from the NFC signal transmitting device through the receiving antenna (112) and preprocesses it, and detects a noisy NFC signal in which the signal quality has degraded to a level lower than the signal quality required for NFC communication during the preprocessing process.

[0024] The original NFC signal received through the receiving antenna (112) is an analog signal and can be properly received only over a very short distance. In particular, when the distance between the NFC signal transmitting device and the NFC signal recovery device receiving the original NFC signal increases or an obstacle is present, the original NFC signal may be attenuated or contain noise, and the signal quality may be degraded to a level below the signal quality required for NFC communication.

[0025] The preprocessing process of the original NFC signal is explained in more detail through FIG. 2. A sampler (114) samples the original NFC signal, which is an analog signal, to convert it into a digital signal, and an A / D converter (116) converts the sampled original NFC signal into a digital signal. At this time, the A / D converter (116) detects a signal that has been distorted or lost during the process of converting the analog signal into a digital signal as a noise NFC signal and transmits it to a generation restorer (124) through an NFC controller / driver (122).

[0026] The decoder (118) decodes the original NFC signal, which has been converted into a digital signal through the A / D converter (116), based on a predetermined modulation method, such as Amplitude Shift Keying (ASK), Frequency Shift Keying (FSK), or Phase Shift Keying (PSK). At this time, the decoder (118) detects a signal that failed to decode as a noise NFC signal and transmits it to a generation restorer (124) through the NFC controller / driver (122), and transmits a signal that succeeded in decoding to a data generator (134) through the NFC controller / driver (122).

[0027] A generative restorer (124) that receives a noise NFC signal from an A / D converter (116) and a decoder (118) inputs the noise NFC signal to a generative model, which is an artificial intelligence model that processes the original NFC signal and the noise NFC signal independently in separate domains, and restores the noise NFC signal to a clean NFC signal of the same signal quality as the original NFC signal by minimizing frequency distortion while maintaining the temporal continuity of the noise NFC signal. In an embodiment of the present invention, an NFC signal restoration device that restores the noise NFC signal to a clean NFC signal using cycleGAN (Generative Adversarial Network) as an example of a generative model is described. However, it goes without saying that the NFC signal restoration device proposed in the present invention may also restore the noise NFC signal to a clean NFC signal using other generative models such as a Transformer or a Variational Autoencoder.

[0028] The cycleGAN used in the generation restorer (124) is described in more detail through FIG. 3. The cycleGAN is a generative model that converts original NFC signal x and noise NFC signal y by considering them as different domains, and consists of a first generator and a first discriminator related to the conversion of the original NFC signal, and a second generator and a second discriminator related to the conversion of the noise NFC signal.

[0029] In addition, the above cycleGAN is provided through a process in which an original NFC signal x is input to a first generator to artificially degrade the signal quality of the original NFC signal x to generate a synthetic noise NFC signal y', a first discriminator is trained to distinguish between the noise NFC signal y and the synthetic noise NFC signal y' by comparing them, and a second generator is input to generate a synthetic clean NFC signal x' by minimizing frequency distortion while maintaining the temporal continuity of the noise NFC signal y, and a second discriminator is trained to distinguish between the synthetic clean NFC signal x' and the original NFC signal x by comparing them.

[0030] Here, each of the first and second generators consists of an initial 1D convolution layer, a residual block, and a final 1D convolution layer.

[0031] Since NFC signals have time-series characteristics, the generator uses a 1D convolution layer to learn temporal patterns. Additionally, a convolution layer with a large kernel size captures long-range dependencies within the signal, as long-range dependencies play an important role in time-domain NFC signals.

[0032] In addition, the generator uses residual blocks and 1D convolution layers together to accurately reflect the temporal dependency and frequency characteristics of time-series data, making it suitable for restoring NFC signals in noisy environments.

[0033] The last 1D convolution layer is a different large kernel-sized convolution layer, and the output signal maintains the data scale of the input signal.

[0034] In addition, each of the first and second discriminators consists of an initial 1D convolution layer, a residual block, a flatten layer, and a fully connected layer.

[0035] Initially, 1D convolution layers with small kernel sizes focus on local features of the signal and play an important role in distinguishing minute differences between the real signal and the generated fake signal, such as the frequency characteristics of communication data.

[0036] The residual block provides learning stability while increasing the depth of the network, and the flattening layer flattens the output values ​​to convert them into binary classifications, then applies a dense layer and a sigmoid activation function to ensure that the discriminator's prediction values ​​remain within an appropriate range.

[0037] The fully connected layer introduces frequency domain loss to minimize distortion occurring in the frequency domain, ensuring that the restored signal maintains the same frequency characteristics as the original signal.

[0038] In addition, cycleGAN is trained to generate a fake clean NFC signal x' that minimizes the difference from the original NFC signal x while minimizing frequency distortion by applying a frequency domain loss function and an adversarial loss function, and is trained to match the noise NFC signal y by applying a cycle consistency loss function to inversely transform the fake clean NFC signal x'.

[0039] As such, cycleGAN is trained using a final loss function calculated as a weighted sum of a frequency domain loss function, an adversarial loss function, and a cyclic consistency loss function, as shown in Equation 1 below.

[0040]

[0041] Here, G represents the first generator, F represents the second generator, and D Y represents the discriminator of domain Y, X represents the input of domain X, and Y represents the input of domain Y. Also, λ cycle represents the weight of the cycle consistency loss function, and λ freq represents the weights of the frequency domain loss function. In an embodiment of the present invention, the weights of the two loss functions are set high at the beginning of learning, and are gradually reduced as learning progresses to ensure the stability of learning.

[0042] That is, the weight λ of the cycle consistency loss function cycle and the weight λ of the frequency domain loss function freq It is dynamically adjusted as shown in Equations 2 and 3 to improve the performance of cycleGAN by focusing on maintaining frequency and cycle consistency during the early stages of training, and to stably maintain signal restoration performance during the later stages of training.

[0043] At this time, the learning process operates repeatedly, and in this process, λcycle and λ freq is updated in a direction that minimizes the final loss function mentioned in Equation 1. In particular, the weights appropriately adjust how quickly and finely the model parameters are updated in response to changes in the loss function; this is determined for each epoch by subtracting the initial weights by the proportion of the total epoch currently in progress, as shown in Equations 2 and 3. In this way, λ cycle and λ freq The process is carried out individually in the same way for each, and mathematical formulas 2 and 3 are derived.

[0044]

[0045]

[0046] By adjusting the weights and learning rate during training in this way, overfitting is prevented during the early training phase, and convergence is induced in the later stages of training to ensure better recovery performance.

[0047] The data processing unit (130) analyzes the temporal characteristics of the clean NFC signal restored through the restoration unit (120) to detect a clock signal, and generates data used in an application where NFC communication is applied based on the restored clean NFC signal and the detected clock signal.

[0048] As explained in more detail with reference to FIG. 2, the clock signal detector (132) detects a clock signal from the clean NFC signal restored through the restoration unit (120) and provides accurate timing. The clock signal occurs at a constant period while the NFC signal is being transmitted, and if this clock signal is not accurately synchronized, an error may occur during the NFC signal transmission process.

[0049] The clock signal detector (132) analyzes the temporal characteristics of the restored clean NFC signal to reconstruct an accurate clock signal and enables it to be used for data decoding. The reconstructed clock signal is used for decoding data encoded in Manchester code, and since Manchester code encodes data through phase changes of the signal, the clock signal must be accurately synchronized for the encoding and decoding of data to be performed correctly. By making this possible, the clock signal detector (132) ensures accurate data transmission even in the restored signal.

[0050] The data generator (134) generates data in a form that can be used in applications where NFC communication is applied, such as smart payment systems, authentication systems, and data transmission systems, based on the restored clean NFC signal and the detected clock signal. This is an important step to ensure that the restored data can be accurately utilized in actual systems, and plays an important role, especially in secure communication or data transmission between smartphones.

[0051] The final data generated in this way is processed with the same quality as the original data, i.e., the original NFC signal, enabling users to communicate stably without signal loss or errors that may occur during NFC communication.

[0052] FIG. 4 is a flowchart showing the NFC signal restoration operation of an NFC signal restoration device according to an embodiment of the present invention.

[0053] The NFC signal recovery device receives the original NFC signal transmitted from the NFC signal transmitting device and preprocesses it, and detects a noisy NFC signal in which the signal quality has degraded to a level lower than the signal quality required for NFC communication during the preprocessing process. (S401)

[0054] Then, the NFC signal restoration device inputs the noise NFC signal detected in S401 into a pre-prepared generation model and restores it into a clean NFC signal of the same signal quality as the original NFC signal by minimizing frequency distortion while maintaining the temporal continuity of the noise NFC signal. (S403)

[0055] Subsequently, the NFC signal recovery device analyzes the temporal characteristics of the clean NFC signal recovered in S403 to detect a clock signal, and generates data used in an application to which the NFC communication is applied based on the recovered clean NFC signal and the detected clock signal. (S405)

[0056] The NFC signal recovery method of the present invention, as described above, can be implemented in the form of program instructions that can be executed through various computer components and recorded on a computer-readable recording medium. The computer-readable recording medium may include program instructions, data files, data structures, etc., either individually or in combination.

[0057] The program instructions recorded on the above-mentioned computer-readable recording medium may be those specifically designed and configured for the present invention, or they may be those known and available to those skilled in the art of computer software.

[0058] Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specifically configured to store and execute program instructions such as ROM, RAM, and flash memory.

[0059] Examples of program instructions include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. The hardware device may be configured to operate as one or more software modules to perform processing according to the present invention, and vice versa.

[0060] Although various embodiments of the present invention have been illustrated and described above, the present invention is not limited to the specific embodiments described above. It is understood that various modifications can be made by those skilled in the art without departing from the essence of the invention as claimed in the claims, and such modifications should not be understood individually from the technical spirit or perspective of the present invention. Explanation of the symbols

[0062] 110: Preprocessing section 112: Receiving antenna 114: Sampler 116: A / D Converter 118: Decoder 120: Restoration section 122: NFC Controller / Driver 124: Create Restorer 130: Data processing unit 132: Clock signal detector 134: Data Generator

Claims

Claim 1 A preprocessing unit that receives and preprocesses an original NFC signal transmitted from a Near Field Communication (NFC) signal transmitting device, and detects a noisy NFC signal whose signal quality has degraded to below the signal quality required for NFC communication during the preprocessing process; a restoration unit that inputs the noisy NFC signal into a pre-prepared generation model and restores it into a clean NFC signal of the same signal quality as the original NFC signal by minimizing frequency distortion while maintaining the temporal continuity of the noisy NFC signal; and a data processing unit that analyzes the temporal characteristics of the restored clean NFC signal to detect a clock signal, and generates data used in an application to which the NFC communication is applied based on the restored clean NFC signal and the detected clock signal.An NFC signal restoration device comprising: a preprocessing unit further comprising an Analog to Digital (A / D) converter and a decoder; wherein the noise NFC signal is characterized as a signal in which distortion or loss occurred during the process of the A / D converter converting an analog signal into a digital signal, or a signal in which the decoder failed to decode; wherein the generation model is provided within the restoration unit, and wherein the generation model is provided through a process in which the original NFC signal is input to a first generator to artificially degrade the signal quality of the original NFC signal to generate a synthetic noise NFC signal, and a first discriminator is trained to distinguish between the noise NFC signal and the synthetic noise NFC signal by comparing them; wherein the noise NFC signal is input to a second generator to generate a synthetic clean NFC signal by minimizing frequency distortion while maintaining the temporal continuity of the noise NFC signal, and a second discriminator is trained to distinguish between the synthetic clean NFC signal and the original NFC signal by comparing them. Claim 2 delete Claim 3 delete Claim 4 An NFC signal recovery device according to claim 1, wherein the generation model is trained to generate a fake clean NFC signal that minimizes the difference from the original NFC signal while minimizing frequency distortion by applying a frequency domain loss function and an adversarial loss function, and is trained to ensure that the inverse transformation of the fake clean NFC signal matches the noise NFC signal by applying a cycle consistency loss function. Claim 5 An NFC signal recovery device according to claim 4, wherein the generation model is trained using a final loss function calculated as a weighted sum of the adversarial loss function, the cycle consistency loss function, and the frequency domain loss function. Claim 6 A preprocessing unit receives an original NFC signal transmitted from a Near Field Communication (NFC) signal transmitting device and preprocesses it, and detects a noisy NFC signal whose signal quality has degraded to a level below the signal quality required for NFC communication during the preprocessing process; a restoration unit inputs the noisy NFC signal into a pre-prepared generation model and restores it into a clean NFC signal of the same signal quality as the original NFC signal by minimizing frequency distortion while maintaining the temporal continuity of the noisy NFC signal; a data processing unit analyzes the temporal characteristics of the restored clean NFC signal to detect a clock signal, and generates data used in an application to which the NFC communication is applied based on the restored clean NFC signal and the detected clock signal.An NFC signal restoration method comprising: a preprocessing unit further comprising an Analog to Digital (A / D) converter and a decoder; wherein the noise NFC signal is characterized as a signal in which distortion or loss occurred during the process of the A / D converter converting an analog signal into a digital signal, or a signal in which the decoder failed to decode; wherein the generation model is provided within the restoration unit, and wherein the generation model is provided through a process in which the original NFC signal is input to a first generator to artificially degrade the signal quality of the original NFC signal to generate a synthetic noise NFC signal, and a first discriminator is trained to distinguish between the noise NFC signal and the synthetic noise NFC signal by comparing them; wherein the noise NFC signal is input to a second generator to generate a synthetic clean NFC signal by minimizing frequency distortion while maintaining the temporal continuity of the noise NFC signal, and a second discriminator is trained to distinguish between the synthetic clean NFC signal and the original NFC signal by comparing them. Claim 7 delete Claim 8 delete Claim 9 An NFC signal restoration method according to claim 6, wherein the generation model is trained to generate a fake clean NFC signal that minimizes the difference from the original NFC signal while minimizing frequency distortion by applying a frequency domain loss function and an adversarial loss function, and is trained to inversely transform the fake clean NFC signal to match the noise NFC signal by applying a cycle consistency loss function. Claim 10 An NFC signal recovery method according to claim 9, wherein the generative model is trained using a final loss function calculated as a weighted sum of the adversarial loss function, the cycle consistency loss function, and the frequency domain loss function.

Images