System and method for performing near field communication (NFC) traffic using user equipment

Abstract

A method of controlling an electronic device performing near field communication (NFC) traffic may include obtaining a plurality of contextual parameters related to NFC traffic to be performed; identifying an optimal radio frequency (RF) configuration from a plurality of RF configurations for performing the NFC traffic by inputting the plurality of contextual parameters into an artificial intelligence (AI) model; and performing the NFC traffic using the optimal RF configuration. The AI model may be configured to establish a correlation of the plurality of contextual parameters to the plurality of RF configurations.

Description

Technical Field

[0001] The present disclosure generally relates to the field of near field communication (NFC), and more particularly to a method and system for performing NFC transactions based on a context-based reconfigurable configuration to improve NFC transaction efficiency. Background Art

[0002] Mobile contactless transactions have recently become increasingly popular due to their convenience. In the future, most people will use contactless transactions on smart devices such as smartwatches, bracelets, and Near Field Communication (NFC) rings. NFC is a set of communication protocols based on radio frequency identification (RFID). NFC enables two devices to communicate with each other when they are within a predefined range (e.g., 4 cm or less). The use cases for NFC-based contactless transactions vary depending on demographics and user preferences. Figure 1A (Related Art) illustrates an example use case for NFC-based contactless transactions, where a user can use device 100 to perform contactless transactions. As shown in Figure 1A, device 100 can be used for various applications such as door keys, transportation cards, payments, and gym equipment access through its respective reader.

[0003] Device 100 may be pre-configured to support various applications. However, compared to other devices, such as smartphones, device 100 may have reduced capabilities. For example, device 100 may be a smartwatch; however, the NFC antenna in device 100 may have reduced capabilities compared to existing smartphones. This reduced capability makes successful communication with different applications and / or readers difficult.

[0004] Furthermore, contactless transactions are performed using an NFC antenna with a radio frequency (RF) configuration to support contactless features (e.g., contactless payments / transactions). In a related approach, such as for device 100, a single statically tuned RF configuration exists for the NFC antenna of device 100. As shown in FIG1B , according to related art, a static RF configuration 102 is loaded based on the device model of device 100. This single RF configuration 102 (e.g., version (26, C1)) is tuned to support various NFC applications across a geographic region, however, with varying success rates.

[0005] Using a single static RF configuration in different scenarios may result in one or more failed transactions. According to the related art, two such example scenarios depicting the reasons for the failure of transactions using a single static RF configuration have been shown in Figures 2A and 2B. As shown in Figure 2A, the static RF configuration 102 of the device 100 can be used for a transit pass application 104 and a door key application 106. The RF configuration 102 is suitable for the transit pass application 104. However, for the door key application 106, the RF configuration 102 may have a lower success rate. Therefore, the NFC transaction related to the transit pass application 104 may be successful, while the NFC transaction related to the door key application 106 may be unsuccessful.

[0006] As shown in FIG2B , user 108 may purchase device 100 in a first geographic area. User 108 may visit establishment 110 and perform a contactless transaction at a point-of-sale (PoS) reader 112 at establishment 110 within the first geographic area. Device 100 has a single static RF configuration that can be used for a successful transaction with PoS reader 112. User 108 may travel to a second geographic area and use device 100 to perform a contactless transaction, such as a transit pass 114 within the second geographic area. However, the transaction may fail for the transit pass within the second geographic area.

[0007] As is apparent from Figures 2A and 2B , this approach has several drawbacks. For example, a static RF configuration is loaded onto the device for a specific model, and aligning the RF configuration to accommodate all compatible NFC features can be cumbersome. Furthermore, region-specific NFC applications may require a customized RF configuration. Furthermore, users may wear the device in their left or right hand depending on their preference, which results in changes in antenna position and increases in service failure rates.

[0008] Therefore, an improved method and system are desired to solve the above problems. For example, a system and method to increase the success rate of NFC services and enhance user experience is desired. Summary of the Invention

[0009] This summary is provided to introduce some concepts in a simplified format that will be further described in the detailed description of the present disclosure. This summary is not intended to identify key or essential inventive concepts of the present disclosure, nor is it intended to determine the scope of the present disclosure.

[0010] According to one aspect of one or more example embodiments, a method for controlling an electronic device that performs a near field communication (NFC) transaction may include: obtaining a plurality of context parameters related to a to-be-performed NFC transaction; inputting the plurality of context parameters into an artificial intelligence (AI) model to identify an optimal radio frequency (RF) configuration from among a plurality of RF configurations for performing the NFC transaction; and performing the NFC transaction using the optimal RF configuration. The AI ​​model may be configured to establish a correlation between the plurality of context parameters and the plurality of RF configurations.

[0011] According to one aspect of one or more example embodiments, an electronic device for performing a near field communication (NFC) transaction may include: at least one memory storing instructions; and at least one processor connected to the at least one memory and configured to execute the instructions to: obtain multiple context parameters related to a to-be-performed NFC transaction; identify an optimal radio frequency (RF) configuration from multiple RF configurations for performing the NFC transaction by inputting the multiple context parameters into an artificial intelligence (AI) model; and perform the NFC transaction using the optimal RF configuration. The AI ​​model may be configured to establish a correlation between the multiple context parameters and the multiple RF configurations.

[0012] To further illustrate the advantages and features of the present disclosure, a more detailed description of the present disclosure will be presented by reference to specific embodiments of the present disclosure illustrated in the accompanying drawings. It should be understood that these drawings depict only typical embodiments of the present disclosure and, therefore, should not be considered as limiting the scope thereof. The present disclosure will be described and explained with additional features and details through the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The above and other aspects, features and advantages of certain embodiments of the present disclosure will become more apparent through the following description in conjunction with the accompanying drawings, in which:

[0014] FIG. 1A shows an example use case of an NFC-based contactless transaction according to the related art.

[0015] FIG. 1B illustrates an example of a static RF configuration in a device according to the related art.

[0016] FIG. 2A illustrates an example scenario depicting causes of service failure using a single static RF configuration according to the related art.

[0017] FIG. 2B illustrates an example scenario depicting reasons for failure of a service using a single static RF configuration according to the related art.

[0018] Figure 3 A schematic block diagram illustrating an environment for performing NFC transactions according to one or more embodiments of the present disclosure is shown.

[0019] Figure 4A schematic block diagram illustrating a user device and a system for performing an NFC transaction according to one or more embodiments of the present disclosure is shown.

[0020] Figure 5 A schematic block diagram illustrating one or more modules for performing NFC transactions based on a context-based reconfigurable RF configuration according to one or more embodiments of the present disclosure is shown.

[0021] Figure 6 A schematic overview of a system according to one or more embodiments of the present disclosure is shown.

[0022] Figure 7 A process flow for selecting a model export configuration during runtime on a user device is shown, in accordance with one or more embodiments of the present disclosure.

[0023] Figure 8 A process flow for performing an NFC transaction with a user device in real time according to one or more embodiments of the present disclosure is shown.

[0024] 9A illustrates an example process flow including a method for performing an NFC transaction using a user device according to one or more embodiments of the present disclosure.

[0025] FIG9B illustrates an example process flow including a method for training an artificial intelligence (AI) model according to one or more embodiments of the present disclosure.

[0026] 9C illustrates an example process flow including a method for selecting an optimal RF configuration based on an AI model, according to one or more embodiments of the present disclosure.

[0027] Figure 10 Various use cases for performing NFC transactions based on a context-based reconfigurable RF configuration according to one or more embodiments of the present disclosure are illustrated.

[0028] Figure 11 Various use cases for performing NFC transactions based on a context-based reconfigurable RF configuration according to one or more embodiments of the present disclosure are illustrated.

[0029] Figure 12 Various use cases for performing NFC transactions based on a context-based reconfigurable RF configuration according to one or more embodiments of the present disclosure are illustrated.

[0030] Furthermore, those skilled in the art will appreciate that the elements in the drawings are illustrated for simplicity and may not necessarily be drawn to scale. For example, a flow chart illustrates the method according to the most prominent steps involved to help improve understanding of various aspects of the present disclosure. Furthermore, with respect to the construction of the device, one or more components of the device may have been represented in the drawings by conventional symbols, and the drawings may show only those specific details that are relevant to understanding the embodiments of the present disclosure so as not to obscure the drawings with details that would be readily apparent to one of ordinary skill in the art having the benefit of the description herein. DETAILED DESCRIPTION

[0031] For the purpose of promoting an understanding of the principles of the present disclosure, reference will now be made to various embodiments, and specific language will be used to describe these embodiments. It will be understood, however, that no limitation of the scope of the present disclosure is intended thereby, and such changes and further modifications in the illustrated systems and such further applications of the principles of the present disclosure as illustrated therein are deemed to be within the ordinary scope of those skilled in the art to which the present disclosure relates.

[0032] Those skilled in the art will understand that both the foregoing general description and the following detailed description are illustrative of the present disclosure and are not intended to be restrictive.

[0033] Reference throughout this specification to "aspect," "another aspect," or similar language means that a particular feature, structure, or characteristic described in connection with an embodiment is included in at least one embodiment of the present disclosure. Thus, appearances of the phrases "in one or more embodiments," "in another embodiment," and similar language throughout this specification may, but do not necessarily, all refer to the same embodiment.

[0034] The terms "comprises," "comprising," or any other variation thereof are intended to encompass a non-exclusive inclusion, such that a process or method that includes a list of steps includes not only those steps but may also include other steps not expressly listed or inherent to such process or method. Similarly, without further constraints, the listing of one or more devices, subsystems, elements, structures, or components preceded by "comprises..." does not exclude the presence of other devices, subsystems, elements, structures, or components, or additional devices, subsystems, elements, structures, or components. As used herein, the expression "at least one of..." preceding a list of elements modifies the entire list of elements and does not modify the individual elements of the list. For example, the expression "at least one of a, b, and c" should be understood to include only a, only b, only c, both a and b, both a and c, both b and c, or all a, b, and c. As used herein, when the terms "same" or "equal" are used to compare the dimensions of two or more elements, the terms may encompass dimensions that are "substantially the same" or "substantially equal."

[0035] The present disclosure relates to a method and system for performing NFC transactions using a context-based reconfigurable RF configuration. The term "transaction" as used in this disclosure refers to the signal exchange between a reader and a device including an NFC-enabled antenna for a variety of applications, such as those associated with vehicle cards, door cards, financial payments, transmission cards, etc.

[0036] Figure 3 A schematic block diagram illustrates an environment 300 for performing NFC transactions. Environment 300 may include a user device 310 and multiple readers 320a, 320b, and 320c (collectively, "320"). Environment 300 may also include a system 330 configured to perform NFC transactions in conjunction with user device 310 and reader 320. In some embodiments, user device 310 may be a wearable device such as a smartwatch, bracelet, ring, or other wearable device. In some embodiments, reader 320 may be a POS device, a payment terminal, an NFC reader, a door key reader, a transmitting terminal reader, or the like. In some embodiments, user device 310 and reader 320 may be located at a predetermined distance, such as approximately 4 cm, to perform NFC transactions. In some embodiments, user device 310 may communicate with reader 320 via an RF protocol.

[0037] In some embodiments, system 330 may be an on-device system configured to cause NFC transactions via user device 310. In some embodiments, user device 310 may include system 330 integrated therein.

[0038] In some embodiments, system 330 can be distributed. For example, one or more components and / or functions of system 330 can be provided via user device 310, and one or more components and / or functions of system 330 can be provided via a cloud-based unit (such as cloud storage or a cloud-based server). In such embodiments, system 330 can be communicatively coupled to user device 310 via a communication network.

[0039] Figure 4 A schematic block diagram shows a user device 310 and a system 330 for performing an NFC transaction according to one or more embodiments of the present disclosure.

[0040] In some embodiments, user device 310 may include an antenna 402 configured to facilitate NFC communication with reader 320. User device 310 may include a power supply 404 configured to provide operating power to antenna 402. Antenna 402 may be referred to as an NFC antenna. User device 310 may also include one or more sensors 406 configured to sense a plurality of contextual parameters associated with user device 310 and / or a user associated with user device 310. In some embodiments, sensors 406 may include a GPS sensor 406A, an accelerometer 406B, and a gyroscope 406C.

[0041] In some embodiments, system 330 may include a processor / controller 410 (hereinafter referred to as "processor 410"), memory 412, one or more modules 414, an artificial intelligence (AI) model 416, and one or more NFC applications 418. In some embodiments, AI model 416 may be included in memory 412. In some embodiments, AI model 416 may be included in one or more modules 414. In some embodiments, one or more modules 414 may be included in memory 412.

[0042] In some embodiments, NFC application 418 may include software applications associated with vehicle cards, door cards, financial payments, transmission cards, etc. In some embodiments, memory 412 may be communicatively coupled to processor 410. Memory 412 may be configured to store data and instructions executable by processor 410. Memory 412 may include a database 412A configured to store data. One or more modules 414 may include a set of instructions that can be executed to cause system 330 to perform any one or more of the methods disclosed herein. One or more modules 414 may be configured to use the data stored in database 412A to perform the steps of the present disclosure to facilitate NFC transactions, as discussed throughout this disclosure. In one or more embodiments, each of one or more modules 414 may be a hardware unit that may be external to memory 412. In addition, memory 412 may include an operating system 412B for executing one or more tasks of system 330, such as that executed by a general-purpose operating system in the communication domain. Each of the one or more modules 414 may be physically implemented by analog and / or digital circuitry including one or more of logic gates, integrated circuits, microprocessors, microcontrollers, memory circuits, passive electronic components, active electronic components, and the like.

[0043] The memory 412 may include a configuration database 412C configured to store a plurality of RF configurations. In some embodiments, the plurality of RF configurations may relate to NFC antenna configurations, as each of the plurality of RF configurations may include a corresponding NFC antenna configuration. In some embodiments, each corresponding NFC antenna configuration may be associated with one or more of radio frequency parameters, impedance parameters, NFC firmware information, and hardware configuration parameters of the user device 310.

[0044] The memory(s) 412 are operable to store instructions executable by the processor(s) 410. The functions, actions, or tasks shown or described in the figures may be performed by the processor 410 programmed to execute the instructions stored in the memory 412. The functions, actions, or tasks are independent of the particular type of instruction set, storage medium, processor, or processing strategy, and may be performed by software, hardware, integrated circuits, firmware, microcode, etc., operating alone or in combination. Likewise, processing strategies may include multi-processing, multi-tasking, parallel processing, etc.

[0045] In some embodiments, the user device 310 may include a transceiver and an I / O interface. The I / O interface may provide a display function and one or more physical buttons on the user device 310. For the sake of brevity, the architecture and standard operation of the operating system 412B, memory 412, database 412A, and processor 410 are not discussed in detail. In at least one embodiment, the database 412A may be configured to store information required by one or more modules 414 and the processor 410 to perform one or more functions, thereby performing NFC transactions based on context parameters. In some embodiments, the I / O interface may be configured to receive user input and facilitate the execution of NFC transactions based on the user input.

[0046] In some embodiments, the memory 412 can communicate via a bus within the system 330. The memory 412 can include, but is not limited to, non-transitory computer-readable storage media, such as various types of volatile and non-volatile storage media, including, but not limited to, random access memory, read-only memory, programmable read-only memory, electrically programmable read-only memory, electrically erasable read-only memory, flash memory, magnetic tape or disk, optical media, and the like. In at least one example, the memory 412 can include a cache or random access memory for a processor. In alternative examples, the memory 412 is separate from the processor / controller, such as a processor's cache memory, system memory, or other memory.

[0047] In addition, the present disclosure contemplates a computer-readable medium that includes instructions or receives and executes instructions in response to a propagated signal so that a device connected to a network can transmit voice, video, audio, images, or any other data over the network. In addition, instructions can be sent or received over the network via a communication port or interface or using a bus. The communication port or interface can be part of the processor 410, or it can be a separate component. The communication port can be created in software, or it can be a physical connection in hardware. The communication port can be configured to connect to a network, external media, a display, or any other component in the system, or a combination thereof. The connection to the network can be a physical connection, such as a wired Ethernet connection, or it can be established wirelessly. Similarly, additional connections to other components of the system 330 can be physical or can be established wirelessly. The network can alternatively be directly connected to the bus.

[0048] In at least one embodiment, processor 410 may include specialized processing units, such as an integrated system (bus) controller, a memory management control unit, a floating point unit, a graphics processing unit, a digital signal processing unit, and the like. In at least one embodiment, processor 410 may include a central processing unit (CPU), a graphics processing unit (GPU), or both. Processor 410 may be one or more general-purpose processors, digital signal processors, application-specific integrated circuits, field-programmable gate arrays, servers, networks, digital circuits, analog circuits, combinations thereof, or other now known or later developed devices for analyzing and processing data. Processor 410 may implement a software program, such as manually generated (e.g., programmed) code.

[0049] The processor 410 may communicate with one or more input / output (I / O) devices via an I / O interface. The I / O interface may employ communication technologies such as Code Division Multiple Access (CDMA), High Speed ​​Packet Access (HSPA+), Global System for Mobile Communications (GSM), Long Term Evolution (LTE), and WiMax.

[0050] Processor 410 can communicate with a communications network via a network interface. The network interface can be an I / O interface. The network interface can connect to a communications network. The network interface can utilize connection protocols including, but not limited to, direct connection, Ethernet (e.g., twisted pair 10 / 100 / 1000 Base T), Transmission Control Protocol / Internet Protocol (TCP / IP), Token Ring, IEEE 802.11 a / b / g / n / x, and the like. Communications networks can include, but are not limited to, direct interconnection, a local area network (LAN), a wide area network (WAN), a wireless network (e.g., using the Wireless Application Protocol), the Internet, and the like. The network interface can utilize connection protocols including, but not limited to, direct connection, Ethernet (e.g., twisted pair 10 / 100 / 1000 Base T), Transmission Control Protocol / Internet Protocol (TCP / IP), Token Ring, IEEE 802.11 a / b / g / n / x, and the like.

[0051] Figure 5 A schematic block diagram of one or more modules 414 of a system 330 for performing NFC transactions based on a context-based reconfigurable RF configuration is shown. In at least one embodiment, the one or more modules 414 may include a transaction validator 502, an input feature processor 504, a context processor 506, a selection module 508, and a loading module 510. In addition, the one or more modules 414, together with the memory 412 and the AI ​​model 416, perform their designated functions. Figure 4 A detailed explanation of each of the modules 414 is discussed.

[0052] In some embodiments, one or more modules 414 can be communicatively coupled to other components of system 330, such as processor 410, memory 412, AI model 416, and NFC application 418. One or more modules 414 can also be coupled to user device 310, particularly one or more sensors 406 of user device 310.

[0053] In some embodiments, one or more modules 414 may be associated with one or more layers, such as an NFC framework layer 512 and an NFC controller interface (NCI) layer 514. In some embodiments, a device interface layer 516 may be provided, which may be associated with the antenna 402 and the NFC controller front end. Furthermore, a Linux kernel layer 518 may be provided, which may be associated with the NFC kernel driver. Furthermore, the NCI layer 514 may be associated with the NFC controller interface and the NCI hardware abstraction layer (HAL) layer. In some embodiments, the NCI HAL layer may be associated with the loader module 510. Furthermore, the NFC framework layer 512 may be associated with the NFC Java Native Interface (JNI) and NFC services. In some embodiments, the NFC services may be associated with the input feature handler 504, the context handler 506, and the selection module 508. Furthermore, the NFC framework layer 512 may communicate with the NFC application 418.

[0054] In some embodiments, the processor 410 may include one or more processors. The one or more processors may be general-purpose processors (such as a central processing unit (CPU), an application processor (AP), etc.), graphics processing units (such as a graphics processing unit (GPU), a visual processing unit (VPU)), and / or AI-specific processors (such as a neural processing unit (NPU)).

[0055] refer to Figure 4 and Figure 5 The processor 410 may be configured to obtain a plurality of context parameters related to the NFC service to be performed. The processor 410 may be configured to obtain the plurality of context parameters in conjunction with the input feature processor 504. The processor 410 may be configured to obtain the plurality of context parameters from one or more sensors 406 of the user device 310.

[0056] In some embodiments, processor 410 may be configured to receive readings indicating values ​​of corresponding contextual parameters of a plurality of contextual parameters from one or more sensors 406. In some embodiments, the plurality of contextual parameters may include an orientation of user device 310, an angle of contact of user device 310 relative to an NFC reader (e.g., reader 320), a key location of user device 310, a type of NFC transaction to be performed, NFC firmware information, and a geographic location at which the NFC transaction is to be performed.

[0057] It should be noted herein that antenna 402 can be positioned at a specific location within user device 310. In some embodiments, the orientation of user device 310 can refer to the orientation of user device 310 when worn by an associated user. For example, user device 310 can be a watch, and the orientation can refer to whether the watch is worn on the left or right wrist of the associated user. Thus, the orientation of user device 310 can affect the position of antenna 402 relative to reader 320. In some embodiments, the orientation of user device 310 can be dynamic, in that the orientation can change based on the preferences of the associated user.

[0058] In some embodiments, the touch angle of user device 310 may refer to, for example, the angle between user device 310 and reader 320 when an NFC transaction is being performed. For example, the touch angle may be 0 degrees, 60 degrees, 90 degrees, or any other suitable value. The touch angle may also affect the position of antenna 402 relative to reader 320. In some embodiments, the touch angle of user device 310 may be dynamic, in that the touch angle may change based on the preferences of an associated user while an NFC transaction is being performed.

[0059] In some embodiments, the key location of user device 310 may refer to the location of one or more physical keys (such as a household key or a royal key) on user device 310. The key location may also affect the position of antenna 402 relative to reader 320. In some embodiments, the key location of user device 310 may be dynamic, as the key location may change based on the preferences of the associated user. In some embodiments, the type of NFC transaction may refer to the NFC application 418 used to perform the NFC transaction, such as for a vehicle card, door card, financial payment, or transport card. In some embodiments, the type of NFC transaction may be static for a particular NFC transaction when it is performed.

[0060] In some embodiments, the NFC firmware information may include information associated with the user device, such as the firmware of the user device, chipset information of the user device, etc. In some embodiments, the geographic location may refer to the geographic area where the NFC service is being performed, such as a country, city, and / or place. In some embodiments, the NFC firmware information and the geographic area may be static for the user device 310.

[0061] In some embodiments, one or more sensors 406 may be configured to sense multiple contextual parameters and provide signals indicative thereof to processor 410. For example, gyroscope 406C may measure movement of user device 310, such as angular movement along one or more axes of user device 310. Additionally, accelerometer 406B may measure the rate of change of velocity during movement of user device 310. GPS sensor 406A may measure the location of user device 310.

[0062] The readings and measurements from the one or more sensors 406 may be received by the processor 410. The processor 410 may be configured to extract a plurality of context parameters related to the NFC transaction to be performed from the received readings. In some embodiments, the processor 410 may be configured to extract the plurality of context parameters in conjunction with the context handler 506.

[0063] In some embodiments, multiple context parameters may be associated with multiple RF configurations based on the AI ​​model 416. The multiple RF configurations may be stored in a configuration database 412C of the memory 412. In some embodiments, the configuration database 412C may be stored on the user device 310, and thus, the multiple RF configurations may be stored on the user device 310. As described above, the multiple RF configurations may be referred to as NFC antenna configurations.

[0064] In some embodiments, an AI model 416 may be generated to establish correlations between multiple context parameters and multiple RF configurations. In some embodiments, the AI ​​model may be trained based on a learning technique, which can be considered a method for training a predetermined target device using multiple learning data to enable, allow, or control the target device to make a determination or prediction. Examples of learning techniques include, but are not limited to, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning.

[0065] An AI model may include multiple neural network layers. Each layer may have multiple weight values, and layer operations may be performed using the computational results of previous layers and operations on multiple weight values. Examples of neural networks include, but are not limited to, convolutional neural networks (CNNs), deep neural networks (DNNs), recurrent neural networks (RNNs), restricted Boltzmann machines (RBMs), deep belief networks (DBNs), bidirectional recurrent deep neural networks (BRDNNs), generative adversarial networks (GANs), and deep Q-networks.

[0066] In some embodiments, generating an AI model based on training means using a training technique to train a basic AI model using multiple pieces of training data to obtain predefined operating rules or an AI model configured to perform desired features (or purposes). The AI ​​model may include multiple neural network layers. Each of the multiple neural network layers may include multiple weight values, and neural network calculations may be performed by calculating between the calculation results of the previous layer and the multiple weight values. The AI ​​model may perform neural network calculations based on the calculation results of the previous layer (or the first layer) and the multiple weight values ​​of the current layer (the second layer).

[0067] Inference prediction is a technique for logically reasoning and predicting by determining information, and includes, for example, knowledge-based reasoning, optimization prediction, preference-based planning, or recommendation.

[0068] In some embodiments, AI model 416 can be trained to learn and establish correlations between multiple context parameters and multiple RF configurations. In some embodiments, AI model 416 can be trained based on training data that includes multiple combinations of predefined context parameters. For example, different combinations of one or more of the orientation of user device 310, the angle of contact of user device 310, the key position of user device 310, the type of NFC transaction, NFC firmware information, and the geographic location where the NFC transaction is to be performed can be used as training data.

[0069] Based on the training data, for example, based on multiple predefined scenario parameter combinations, a corresponding success rate for each of the multiple RF configurations can be determined. When using the associated RF configuration, the corresponding success rate can define the probability of successful service for a specific scenario parameter combination. For example, the multiple RF configurations may include RF configuration 1, RF configuration 2, ..., RF configuration N. For a specific combination of predefined scenario parameters, such as combination 1, the success rate for RF configuration 1 can be determined to be 70%, for RF configuration 2, the success rate can be determined to be 50%, for RF configuration N, the success rate can be determined to be 45%, and so on. Similarly, for a different combination of predefined scenario parameters, such as combination 2, the success rate for RF configuration 1 can be determined to be 30%, for RF configuration 2, the success rate can be determined to be 90%, for RF configuration N, the success rate can be determined to be 50%, and so on.

[0070] In some embodiments, a set of NFC transactions can be performed using various readers (e.g., reader 320) for multiple predefined context parameter combinations. The NFC transactions can be performed for a predetermined number of iterations to determine corresponding success rates associated with multiple RF configurations. In other words, for a specific combination of predefined context parameters, a predetermined number of NFC transactions can be performed based on RF configuration 1. Thus, the success rate of RF configuration 1 for that specific combination of context parameters can be determined. NFC transactions can then be performed based on RF configuration 2, RF configuration 3, and so on, to determine the corresponding success rate for each of the multiple RF configurations.

[0071] Similarly, multiple other combinations of predefined scenario parameters may be used to determine corresponding success rates for multiple RF configurations for each of multiple other combinations of predefined scenario parameters. In some embodiments, the corresponding success rates may be determined based on equation (1),

[0072] (1):

[0073] Therefore, based on the plurality of predefined scenario parameter combinations and the corresponding success rate of each of the plurality of RF configurations for the plurality of predefined scenario parameter combinations, a success matrix can be generated. The success matrix can define the correlation between the plurality of predefined scenario parameter combinations and the plurality of RF configurations.

[0074] In some embodiments, the success matrix may be stored in a database, such as a database associated with AI model 416 or a database associated with memory 412. Thus, when an NFC transaction is being performed in real time, the success matrix may be referenced in order to select an optimal RF configuration for the NFC transaction, as further described below in this disclosure.

[0075] When an NFC transaction is to be performed, the processor 410 may be configured to receive readings from one or more sensors 406 in conjunction with the input feature handler 504 and the context handler 506 and extract a plurality of context parameters related to the NFC transaction from the received readings.

[0076] The processor 410 can be configured to reference the AI ​​model 416 in conjunction with the selection module 508 to select an optimal RF configuration from a plurality of RF configurations for performing the NFC transaction. In some embodiments, the processor 410 can be configured to select the optimal RF configuration based on established correlations between a plurality of contextual parameters and a plurality of RF configurations, for example, by referencing a stored success matrix.

[0077] In some embodiments, the processor 410 may be configured to identify a combination of the extracted multiple context parameters. The processor 410 may be configured to identify a relevant context parameter combination from the multiple predefined context parameter combinations in the success matrix. In other words, the processor 410 may be configured to identify a combination of context parameters related to the NFC service to be performed, where the combination matches at least one of the stored multiple predefined context parameter combinations, and the matching predefined context parameter combination is a relevant context parameter combination.

[0078] In addition, the processor 410 may be configured to identify multiple RF configurations and associated success rates for the identified relevant context parameter combination. The processor 410 may be configured to, for the relevant context parameter combination, determine, based on the success matrix, one RF configuration with the highest success rate among the multiple RF configurations. The one RF configuration with the highest success rate may be determined as the optimal RF configuration for performing the NFC service.

[0079] Therefore, the processor 410 and the selection module 508 may be configured to select the optimal RF configuration based on the established correlations between the obtained plurality of contextual parameters and the plurality of RF configurations.

[0080] Once the optimal RF configuration is determined, the processor 410 may be configured to load the optimal RF configuration for performing the NFC service in conjunction with the loading module 510. In some embodiments, the processor 410 and the loading module 510 may access multiple RF configurations, such as Figure 5 In some embodiments, the processor 410 and the loading module 510 can dynamically load the optimal RF configuration in advance before executing the NFC service. Figure 6 , showing a schematic overview of a system 330 according to one or more embodiments of the present disclosure. Figure 6 As seen in FIG, system 330 can communicate with one or more NFC applications 418. When an NFC transaction is to be performed, one or more modules 414 communicate with processor 410, memory 412, and AI model 416 (see FIG. Figure 4 ) together with the context parameters related to the NFC service and selects the optimal RF configuration for performing the NFC service. Therefore, since the optimal RF configuration is used for the NFC service, a higher success rate of the NFC service can be achieved.

[0081] For example, for an NFC transaction for a first application (e.g., financial payment), contextual parameters for executing the NFC transaction can be measured, such as correct orientation, correct key position, and a touch angle of 90 degrees. Consequently, system 330 can identify the optimal RF configuration as RF Configuration 2 from among multiple RF configurations—e.g., RF Configuration 1, RF Configuration 2, and RF Configuration N. Consequently, the NFC transaction can succeed.

[0082] In another example, for an NFC transaction for a second application (e.g., a door key), contextual parameters when performing the NFC transaction can be measured, such as orientation = left, key position = right, touch angle = 60 degrees, etc. Therefore, the system 330 can identify the optimal RF configuration as RF Configuration 1 from among multiple RF configurations—e.g., RF Configuration 1, RF Configuration 2, ..., RF Configuration N. Consequently, the NFC transaction can be successful again for the second application.

[0083] In some embodiments, before selecting the optimal RF configuration with reference to the AI ​​model 416, the processor 410 may be configured to initiate execution of an NFC transaction based on a default RF configuration. The default RF configuration may be one of multiple RF configurations. The processor 410 may also be configured to, in conjunction with the transaction validator 502, determine the status of the NFC transaction, such as whether the NFC transaction has failed or was previously successful. In some embodiments, the processor 410 and the transaction validator 502 may determine one or more failures of NFC transactions executed based on the default RF configuration. If the processor 410 determines that the NFC transaction failed, the processor 410 may determine that a different RF configuration should be used to execute the NFC transaction. Thus, the processor 410 may select a better (or optimal) RF configuration for the NFC transaction to be executed and execute the NFC transaction using the optimal RF configuration. In some embodiments, the processor 410 may determine that a different RF configuration should be used to execute the NFC transaction when an NFC transaction based on the default RF configuration has failed a predetermined number of attempts.

[0084] In some embodiments, the AI ​​model 416 may be updated based on feedback information related to the executed NFC transactions. In some embodiments, the feedback information may include inferences related to success and failure information of the executed NFC transactions.

[0085] In some embodiments, the default RF configuration may be updated based on the feedback information and the updated AI model. Thus, multiple RF configurations may be personalized for the user associated with the user device 310. Thus, the performance and success of NFC transactions may be improved.

[0086] Figure 7 A process flow 700 is shown for selecting a model-derived configuration (e.g., an optimal RF configuration) during runtime of a user device 310. The process begins at block 702 when the user device 310 is booted. At block 704, a default RF configuration may be loaded during the first boot. As described above, the default RF configuration may be one of a plurality of RF configurations.

[0087] At block 706, the NFC feature of the user device 310 may be turned on so that NFC will be supported by the user device 310. At block 708, the system 330, specifically the AI ​​model 416 and the processor 410, receives the context parameters and processes the context parameters to select the optimal RF configuration, as described in reference to FIG. Figures 4 and 5 As stated.

[0088] At block 710 , the processor 410 may check whether the optimal RF configuration determined based on the context parameters is different from the default RF configuration. If the optimal RF configuration determined based on the context parameters is different from the default RF configuration, at block 712 , the optimal RF configuration is loaded to replace the default RF configuration.

[0089] If the optimal RF configuration determined based on the contextual parameters is the same as the default RF configuration, the default RF configuration is not replaced at block 714. The selected RF configuration (optimal RF configuration or default RF configuration) can then be used for future NFC transactions. Furthermore, at step 716, the AI ​​model 416 can be updated based on feedback information—e.g., based on inferences made while executing NFC transactions. Thus, multiple RF configurations are personalized for associated users. In some embodiments, multiple RF configurations are personalized during runtime.

[0090] Figure 8 A process flow 800 is shown for performing a real-time NFC transaction with a user device 310. The process begins at block 802. At block 804, a context-based RF configuration update is completed. In some embodiments, the context-based RF configuration update may include loading a default RF configuration. In some embodiments, the context-based RF configuration update may include loading an RF configuration from a previous transaction. At block 806, the associated user may tag the user device 310 with a reader (such as reader 320) to perform a contactless NFC transaction. As described above, transactions may include payment, pairing, data transfer, and the like.

[0091] At block 808, a determination is made as to whether the NFC transaction was successful. If the NFC transaction was successful, a transaction success message may be displayed on user device 310 (e.g., on a user interface of user device 310) at block 810. Furthermore, at block 812, AI model 416 may be updated based on the successful transaction to better personalize the RF configuration. The current NFC transaction may then end at block 814.

[0092] If the NFC transaction is unsuccessful at block 808, then at block 816, a determination is made as to whether the NFC transaction has failed a predetermined number of times, e.g., whether a transaction failure threshold has been reached. If the transaction failure threshold has been reached, at block 818, a transaction failure message may be displayed on the user device 310, e.g., on a user interface of the user device 310. The NFC transaction may then end at block 814.

[0093] In the event that the service failure threshold is not reached, at block 820, the optimal RF configuration is selected and loaded based on the contextual parameters, as shown in FIG. Figure 4-5 In the event that the NFC transaction remains unsuccessful, the transaction process may be repeated from step 806. The transaction process may be repeated until a transaction failure threshold is reached, after which a transaction failure message may be displayed, as described with reference to block 818.

[0094] 9A illustrates an example process flow including a method 900 for performing an NFC transaction using user device 310, according to one or more embodiments of the present disclosure. In at least one embodiment, the steps of method 900 may be performed by system 330, as discussed above.

[0095] At step 902, method 900 includes obtaining a plurality of contextual parameters related to an NFC transaction to be performed. In some embodiments, the plurality of contextual parameters includes one or more of an orientation of the user device, a touch angle relative to an NFC reader, a key position of the user device, a type of NFC transaction to be performed, NFC firmware information, and a geographic location of the NFC transaction to be performed.

[0096] In some embodiments, the method may further include: receiving readings from one or more sensors at the user device indicating values ​​of corresponding context parameters in a plurality of context parameters. In some embodiments, the method may further include: extracting a plurality of context parameters related to the NFC transaction to be performed based on the received readings.

[0097] At step 904, method 900 includes referencing AI model 416 to select an optimal RF configuration from multiple RF configurations for performing NFC transactions. The AI ​​model can be generated (or configured) to correlate the obtained multiple context parameters with the multiple RF configurations. In some embodiments, the multiple RF configurations are pre-stored on user device 310. In some embodiments, each of the multiple RF configurations includes a corresponding NFC antenna configuration. In some embodiments, each of the corresponding NFC antenna configurations is associated with one or more of the user device's radio frequency parameters, impedance parameters, NFC firmware information, and hardware configuration parameters.

[0098] In some embodiments, the method 900 may further include selecting an optimal RF configuration from the plurality of RF configurations based on the established correlations between the obtained plurality of situational parameters and the plurality of RF configurations.

[0099] In some embodiments, method 900 may further include loading an optimal RF configuration for performing the NFC transaction.

[0100] In some embodiments, method 900 may further include updating the AI ​​model based on feedback information including inferences related to success and failure information associated with executed NFC transactions.

[0101] In some embodiments, method 900 may further include updating the default RF configuration based on the feedback information and the updated AI model. Thus, multiple RF configurations for a user associated with a user device may be personalized.

[0102] In some embodiments, method 900 may further include initiating execution of an NFC transaction based on a default RF configuration of the user device. In some embodiments, the method may further include determining one or more failures of executing an NFC transaction based on the default RF configuration, and further determining that a different RF configuration for executing the NFC transaction should be used.

[0103] In some embodiments, according to one or more embodiments of the present disclosure, method 900 may further include steps 906A-906D for training AI model 416, as shown in FIG9B . In at least one embodiment, the steps of method 900 depicted in FIG9B may be performed by system 330, as discussed above. In some embodiments, steps 906A-906D may be performed before step 902 or before step 904 depicted in FIG9A .

[0104] At step 906A, method 900 includes training an AI model by performing predetermined NFC transactions for a plurality of predefined context parameter combinations for each of a plurality of RF configurations. At step 906B, method 900 includes determining a corresponding success rate for each of the plurality of RF configurations for the plurality of predefined context parameter combinations.

[0105] At step 906C, the method 900 includes generating a success matrix based on the plurality of predefined scenario parameter combinations and the corresponding success rate of each of the plurality of RF configurations for the plurality of predefined scenario parameter combinations.At step 906D, the method 900 includes storing the success matrix in a database.

[0106] In some embodiments, according to one or more embodiments of the present disclosure, method 900 may include steps 904A to 904D for selecting an optimal RF configuration by referencing the trained AI model 416 as shown in FIG. 9C . In at least one embodiment, the steps of method 900 depicted in FIG. 9C may be performed by system 330, as discussed above. In some embodiments, steps 904A-904D may form substeps of step 904 depicted in FIG. 9A .

[0107] At step 904A, the method 900 includes identifying relevant context parameter combinations from a plurality of predefined context parameter combinations according to a stored success matrix based on the obtained plurality of context parameters.At step 904B, the method 900 includes identifying a plurality of RF configurations and associated success rates for the relevant context parameter combinations.

[0108] At step 904C, the method 900 includes determining, for the relevant scenario parameter combination, an RF configuration with the highest success rate among the multiple RF configurations according to the success matrix. At step 904D, the method 900 includes determining the RF configuration with the highest success rate as the optimal RF configuration.

[0109] Although the above steps in Figures 9A-9C are shown and described in a particular order, according to various embodiments, these steps may occur in variations of the order. In addition, detailed descriptions of the various steps in Figures 9A to 9C have been provided in conjunction with Figures 3 to 5 The related description is covered in , and is omitted in this article for the sake of brevity.

[0110] Figure 10 An example use case for performing NFC transactions based on a context-based reconfigurable RF configuration is shown. Figure 10As shown, user device 1002 (similar to user device 310 ) may be associated with multiple RF configurations 1004, such as RF ver. (26, C1), RF ver. (26, C2), RF ver. (26, C3), and so on. User device 1002 may be used for a transit pass application 1006 and a door key application 1008. Based on contextual parameters, system 1010 (similar to system 330 ) may determine the optimal RF configuration for each application (e.g., for transit pass application 1006 and door key application 1008). Contextual parameters may include, for example, location (subway, gym, etc.), service type (transit, door key, etc.), orientation (left or right), and region (country 1, country 2, etc.). System 1010 may select the optimal RF configuration 1012 (e.g., RF ver. (26, C1)) for transit pass application 1006 and may successfully perform an NFC transaction based on the optimal RF configuration 1012. Furthermore, the system 1010 may select an optimal RF configuration 1014 (e.g., RF ver. (26, C3)) for the door key application 1008 and may successfully perform an NFC transaction based on the optimal RF configuration 1014. Therefore, even for various applications, the NFC transaction will not fail because the RF configuration with the highest success rate will be utilized.

[0111] Figure 11 Another example use case for performing NFC transactions based on a context-based reconfigurable RF configuration is shown. Figure 11 As shown, user 1102 can purchase device 1104 (similar to user device 310) in a first geographic area. User 1102 can then visit establishment 1106 and perform an NFC transaction at a POS reader 1108 in establishment 1106 within the first geographic area. Furthermore, user 1102 can travel to a second geographic area and use device 1104 to perform another NFC transaction, such as payment for a transit pass 1110 in the second geographic area. The NFC transaction in the second geographic area can be successfully performed because the optimal RF configuration will be utilized based on contextual parameters (e.g., geographic area).

[0112] This disclosure provides various technical advances based on the key features discussed above. This disclosure provides systems and methods for enabling context-based selection of the optimal RF configuration for executing NFC transactions. The RF configuration is dynamically altered to enable ongoing NFC transactions to succeed without requiring user intervention. This reduces the failure rate of NFC transactions and improves the user experience when executing NFC transactions.

[0113] The systems and methods described herein enable successful transactions with various reader types and in diverse geographic regions. Users performing NFC transactions do not need to worry about hand position and touch angle, as the system described herein automatically selects the optimal RF configuration based on contextual parameters. Consequently, users can wear their devices according to their preferences without worrying about unsuccessful NFC transactions. Furthermore, the systems and methods facilitate personalized RF configurations based on the NFC transaction being performed, for example, at runtime, further enhancing success rates and user experience.

[0114] Although specific language has been used to describe this subject matter, it is not intended to limit any of the above. It will be apparent to those skilled in the art that various modifications may be made to the method to achieve the inventive concept as taught herein. The accompanying drawings and the foregoing description provide examples of embodiments. It will be understood by those skilled in the art that one or more of the described elements may be well combined into a single functional element. Alternatively, some elements may be divided into multiple functional elements. Elements from one embodiment may be added to another embodiment.

[0115] Figure 12 Various use cases for performing NFC transactions based on a context-based reconfigurable RF configuration according to one or more embodiments of the present disclosure are illustrated.

[0116] A method for controlling an electronic device that performs a near field communication (NFC) service, the method comprising: obtaining a plurality of context parameters related to the NFC service to be performed (S1205); and identifying (or selecting) an optimal radio frequency (RF) configuration for performing the NFC service from a plurality of RF configurations by inputting the plurality of context parameters into an artificial intelligence (AI) model (S1210), wherein the AI ​​model may be an AI model for establishing correlation between the plurality of context parameters and the plurality of RF configurations.

[0117] The electronic device may be described as a user device (310).

[0118] Electronic devices can communicate with external devices using NFC communication methods. Transactions can be described as transmissions or transactions. NFC transactions can include exchanging data (or information).

[0119] Context parameters can be described as parameters or context information.Context parameters can be described as communication environment information or communication environment parameters.

[0120] The optimal RF configuration may be described as a recommended RF configuration or a target RF configuration. The optimal RF configuration may be the final RF configuration described.

[0121] Identifying the optimal RF configuration may be described as "referring (step 904) to an artificial intelligence (AI) model (416) to identify the optimal RF configuration."

[0122] After obtaining multiple context parameters, the electronic device can input the multiple context parameters into the AI ​​model. In addition, the electronic device can obtain the optimal RF configuration as output data of the AI ​​model.

[0123] For one example, the AI ​​model may be stored in an electronic device.

[0124] For example, the AI ​​model may be stored in an external server. The electronic device may send multiple context parameters to the external server. The external server may obtain the optimal RF configuration by using the AI ​​model stored in the external server. The electronic device may receive the optimal RF configuration corresponding to the multiple context parameters from the external server.

[0125] The AI ​​model may establish (or obtain or identify) a correlation based on multiple context parameters and multiple RF configurations. The AI ​​model may obtain the correlation corresponding to the multiple context parameters. The AI ​​model may obtain the optimal RF configuration among the multiple RF configurations based on the established correlation.

[0126] Multiple RF configurations may be pre-stored on the electronic device.

[0127] For example, an electronic device may store multiple RF configurations. An AI model stored in the electronic device may use the multiple RF configurations.

[0128] For example, an external server may store multiple RF configurations. An AI model stored in the external server may use multiple RF configurations.

[0129] Identifying the optimal RF configuration includes: identifying (or selecting) the optimal RF configuration from the multiple RF configurations based on the established correlations between the multiple context parameters and the multiple RF configurations. The method may also include loading the optimal RF configuration for performing the NFC service.

[0130] The electronic device may obtain an established correlation based on a plurality of contextual parameters and a plurality of RF configurations.

[0131] For example, the plurality of RF configurations may include a first RF configuration and a second RF configuration. The electronic device may obtain a first correlation between the plurality of context parameters and the first RF configuration. The electronic device may obtain a second correlation between the plurality of context parameters and the second RF configuration. The electronic device may identify (or obtain or determine) an established correlation (or final correlation) between the first correlation and the second correlation.

[0132] Obtaining the plurality of context parameters may include receiving readings indicating values ​​of corresponding ones of the plurality of context parameters from one or more sensors at the electronic device, and obtaining (or extracting) the plurality of context parameters related to the NFC transaction to be performed based on the received readings.

[0133] A reading may be described as sensed data or sensed information. A reading may be described as a value of a context parameter. A reading may include a value corresponding to each of a plurality of context parameters. A reading may include a quantifiable value of a context parameter.

[0134] The plurality of contextual parameters may include one or more of an orientation of the electronic device, an angle of touch relative to the NFC reader, a key location of the electronic device, a type of NFC transaction to be performed, NFC firmware information, and a geographic location of the NFC transaction to be performed.

[0135] Before identifying (or selecting) the optimal RF configuration, the method may further include: initiating execution of an NFC transaction based on a default RF configuration of the electronic device; determining one or more failures of the NFC transaction executed based on the default RF configuration; and determining that a different RF configuration is required for executing the NFC transaction.

[0136] The method may further include: for each of a plurality of RF configurations, training an AI model by executing predetermined NFC services for a plurality of predefined scenario parameter combinations; determining a corresponding success rate for each of a plurality of RF configurations for the plurality of predefined scenario parameter combinations; generating a success matrix based on the plurality of predefined scenario parameter combinations and the corresponding success rate for each of the plurality of RF configurations for the plurality of predefined scenario parameter combinations; and storing the success matrix in a database.

[0137] For at least one example, the database can be on an electronic device.

[0138] For at least one example, the database may be on an external server.

[0139] Identifying (or selecting) the optimal RF configuration includes: based on multiple scenario parameters, identifying a relevant scenario parameter combination from multiple predefined scenario parameter combinations according to a stored success matrix; for the relevant scenario parameter combination, identifying multiple RF configurations and associated success rates; determining an RF configuration with the highest success rate among the multiple RF configurations according to the success matrix; and determining the RF configuration with the highest success rate as the optimal RF configuration.

[0140] The method may also include: updating the AI ​​model based on feedback information, the feedback information including inferences related to success and failure information associated with the executed NFC transactions; and updating the default RF configuration based on the feedback information and the updated AI model, thereby personalizing multiple RF configurations for users associated with the electronic device.

[0141] The electronic device may be a wearable device. Each of the plurality of RF configurations includes a corresponding NFC antenna configuration. Each of the corresponding NFC antenna configurations may be associated with one or more of a radio frequency parameter, an impedance parameter, NFC firmware information, and a hardware configuration parameter of the electronic device.

[0142] While certain example embodiments of the present disclosure have been particularly shown and described, it will be understood that various changes in form and details may be made therein without departing from the spirit and scope of the appended claims.

Claims

1. A method for controlling an electronic device that performs a near field communication (NFC) service, the method comprising: Obtaining multiple context parameters related to the NFC service to be performed; identifying an optimal radio frequency (RF) configuration from among multiple RF configurations for performing NFC transactions by inputting multiple situational parameters into an artificial intelligence (AI) model; and Performing NFC transactions using the optimal RF configuration, wherein the AI ​​model is configured to establish correlations between a plurality of situational parameters and a plurality of RF configurations, and The multiple context parameters include one or more of the following: The orientation of the electronic device, the angle of touch relative to the NFC reader, the key position of the electronic device, the type of NFC transaction to be performed, NFC firmware information, and the geographical location of the NFC transaction to be performed.

2. The method according to claim 1, in, Electronic devices are wearable devices, wherein each of the plurality of RF configurations includes a corresponding NFC antenna configuration, and Each of the corresponding NFC antenna configurations is associated with one or more of radio frequency parameters, impedance parameters, NFC firmware information, and hardware configuration parameters of the electronic device.

3. The method according to claim 1, wherein A plurality of RF configurations are pre-stored on the electronic device.

4. The method according to claim 1, in, Identifying the optimal RF configuration involves: identifying the optimal RF configuration from the plurality of RF configurations based on correlations between the plurality of contextual parameters and the plurality of RF configurations, and The method further comprises: The optimal RF configuration for performing the NFC transaction is loaded.

5. The method according to claim 1, wherein Get multiple context parameters including: receiving readings from one or more sensors at the electronic device indicating values ​​of corresponding context parameters of a plurality of context parameters; and A plurality of context parameters related to the NFC transaction to be performed are obtained based on the readings.

6. The method according to claim 1, further comprising: Before identifying the optimal RF configuration: Initiate execution of NFC services based on the default RF configuration of the electronic device; determining one or more failures of NFC transactions performed based on a default RF configuration; and It is determined that different RF configurations for performing NFC transactions should be used.

7. The method according to claim 1, further comprising: training the AI ​​model by performing predetermined NFC transactions for a plurality of predefined context parameter combinations for each of a plurality of RF configurations; For a plurality of predefined scenario parameter combinations, determining a corresponding success rate for each of a plurality of RF configurations; generating a success matrix based on the plurality of predefined scenario parameter combinations and corresponding success rates of each of the plurality of RF configurations for the plurality of predefined scenario parameter combinations; as well as Store the success matrix in a database.

8. The method according to claim 7, wherein: Identifying the optimal RF configuration involves: Based on the plurality of situational parameters, identifying relevant situational parameter combinations from a plurality of predefined situational parameter combinations according to a success matrix; For relevant scenario parameter combinations, identify multiple RF configurations and corresponding success rates, determining, according to the success matrix, an RF configuration having a highest success rate among the plurality of RF configurations for the relevant scenario parameter combination; One RF configuration with the highest success rate is determined as the optimal RF configuration.

9. The method according to claim 6, further comprising: Obtaining an updated AI model by updating the AI ​​model based on feedback information, the feedback information including inferences related to success and failure information associated with the NFC transaction; as well as The default RF configuration is updated based on the feedback information and the updated AI model, thereby personalizing the plurality of RF configurations for a user associated with the electronic device.

10. The method according to claim 1, wherein The AI ​​model consists of multiple neural network layers. Each of the plurality of neural network layers includes a plurality of weight values, and The method further includes performing neural network calculations by calculating based on calculation results of previous layers and multiple weight values ​​of the current layer.

11. An electronic device for performing a near field communication (NFC) service, comprising: at least one memory storing instructions; as well as at least one processor connected to the at least one memory and configured to execute instructions to: Obtaining multiple context parameters related to the NFC service to be performed; identifying an optimal radio frequency (RF) configuration from among multiple RF configurations for performing NFC transactions by inputting multiple situational parameters into an artificial intelligence (AI) model; and Performing NFC transactions using the optimal RF configuration, wherein the AI ​​model is configured to establish correlations between a plurality of situational parameters and a plurality of RF configurations, and The multiple context parameters include one or more of the following: The orientation of the electronic device, the angle of touch relative to the NFC reader, the key position of the electronic device, the type of NFC transaction to be performed, NFC firmware information, and the geographical location of the NFC transaction to be performed.

12. The electronic device according to claim 11, in, Electronic devices are wearable devices, wherein each of the plurality of RF configurations includes a corresponding NFC antenna configuration, and Each of the corresponding NFC antenna configurations is associated with one or more of radio frequency parameters, impedance parameters, NFC firmware information, and hardware configuration parameters of the electronic device.

13. The electronic device according to claim 11, wherein A plurality of RF configurations are pre-stored on the electronic device.

14. The electronic device according to claim 11, wherein The at least one processor is further configured to execute instructions to: identifying an optimal RF configuration from the plurality of RF configurations based on correlations between the plurality of contextual parameters and the plurality of RF configurations; and The optimal RF configuration for performing the NFC transaction is loaded.

15. The electronic device according to claim 11, wherein The at least one processor is further configured to execute instructions to: receiving readings from one or more sensors at the electronic device indicating values ​​of corresponding context parameters of a plurality of context parameters; and A plurality of context parameters related to the NFC transaction to be performed are obtained based on the readings.

Images