System and method for mobile access control using signal strength calibration

Abstract

Disclosed is a system (100) for mobile distance estimation and intent detection in physical access control. The system includes a user device (102), a reader (106), and a data processing apparatus (104) with processing circuitry (120). The processing circuitry is configured to receive a plurality of Received Signal Strength Indicator (RSSI) values from the reader corresponding to signals transmitted by the user device, determine an average RSSI value, determine a standard deviation of the RSSI values, set the average RSSI value as a calibrated received device RSSI (calRxDevRssi) value when the standard deviation is within a predefined limit, and determine an access threshold value based on the calRxDevRssi value for granting access to the user device.

Description

[0001] SYSTEM AND METHOD FOR MOBILE ACCESS CONTROL USING SIGNAL STRENGTH CALIBRATION

[0002] FIELD OF DISCLOSURE

[0003] The present disclosure relates to access control systems, and more particularly to a system and a method for mobile distance estimation and intent detection in physical access control.

[0004] BACKGROUND

[0005] Access control systems play a crucial role in securing physical spaces and managing entry to restricted areas. These systems have evolved from traditional key-based mechanisms to more sophisticated electronic and digital solutions that offer enhanced security, flexibility, and convenience.

[0006] In recent years, mobile-based access control systems have gained popularity due to the widespread use of smartphones. These systems typically utilize technologies such as Bluetooth Low Energy (BLE) or Near Field Communication (NFC) to establish communication between a user's mobile device and an access control reader. However, existing mobile access control systems often face challenges in accurately estimating the distance between the mobile device and the reader, leading to potential security vulnerabilities or user inconvenience. Additionally, many current systems struggle with reliably detecting user intent, which can result in unintended access grants or denials.

[0007] Furthermore, conventional mobile access control systems often rely on fixed signal strength thresholds to determine proximity, which may not account for variations in device hardware, environmental factors, or user behavior. This can lead to inconsistent performance across different mobile devices and usage scenarios. Some systems attempt to address these issues through manual calibration processes, but these can be time-consuming and may require frequent adjustments to maintain accuracy. Therefore, there exists a need for a technical solution that solves the aforementioned problems of conventional systems and methods for mobile distance estimation in physical access control.

[0008] SUMMARY

[0009] This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used as an aid in determining the scope of the claimed subject matter.

[0010] In an aspect of the present disclosure, a system for mobile distance estimation and intent detection in physical access control is disclosed. The system includes a user device, a reader adapted to communicate with the user device, and a data processing apparatus coupled to the reader. The data processing apparatus comprises processing circuitry configured to receive a plurality of Received Signal Strength Indicator (RS SI) values from the reader corresponding to signals transmitted by the user device. The processing circuitry determines an average RSSI value based on the plurality of RSSI values and determines a standard deviation of the plurality of RSSI values. The processing circuitry sets the average RSSI value as a calibrated received device RSSI (calRxDevRssi) value when the standard deviation is within a predefined limit. The processing circuitry determines an access threshold value based on the calRxDevRssi value for granting access to the user device.

[0011] In some aspects of the present disclosure, the reader includes a Near Field Communication (NFC) unit adapted to detect presence of the user device within a predefined distance from the reader.

[0012] In some aspects of the present disclosure, the processing circuitry is further configured to initiate a calibration process when the NFC unit detects the user device within the predefined distance and transmit calibration-specific frames to the user device during the calibration process. In some aspects of the present disclosure, the processing circuitry is further configured to store the calRxDevRssi value and the access threshold value in a database and use the stored access threshold value for subsequent access attempts by the user device.

[0013] In some aspects of the present disclosure, the processing circuitry is further configured to periodically update the calRxDevRssi value and the access threshold value based on subsequent RSSI measurements from the user device and implement and apply a machine learning model to identify patterns in the RSSI measurements for improving accuracy of the access threshold value.

[0014] In an aspect of the present disclosure, a method for mobile distance estimation and intent detection in physical access control is disclosed. The method includes receiving, by processing circuitry of a data processing apparatus, a plurality of Received Signal Strength Indicator (RSSI) values from a reader corresponding to signals transmitted by a user device. The method includes determining, by the processing circuitry, an average RSSI value based on the plurality of RSSI values and determining a standard deviation of the plurality of RSSI values. The method includes setting, by the processing circuitry, the average RSSI value as a calibrated received device RSSI (calRxDevRssi) value when the standard deviation is within a predefined threshold. The method includes determining, by the processing circuitry, an access threshold value based on the calRxDevRssi value for granting access to the user device.

[0015] In some aspects of the present disclosure, prior to receiving the plurality of RSSI value, the method includes detecting, by a Near Field Communication (NFC) unit of the reader, presence of the user device within a predefined distance from the reader and initiating, by the processing circuitry, a calibration process when the user device is detected within the predefined distance.

[0016] In some aspects of the present disclosure, for the calibration process, the method includes transmitting, by the processing circuitry, calibration-specific frames to the user device and receiving, by the processing circuitry, the plurality of RSSI values from the reader in response to the calibration-specific frames. In some aspects of the present disclosure, the method includes storing, by the processing circuitry, the calRxDevRssi value and the access threshold value in a database and using, by the processing circuitry, the stored access threshold value for subsequent access attempts by the user device.

[0017] In some aspects of the present disclosure, the method includes periodically updating, by the processing circuitry, the calRxDevRssi value and the access threshold value based on subsequent RSSI measurements from the user device and implementing and applying, by the processing circuitry, a machine learning model to identify patterns in the RSSI measurements for improving accuracy of the access threshold value.

[0018] BRIEF DESCRIPTION OF FIGURES

[0019] Non-limiting and non-exhaustive examples are described with reference to the following figures.

[0020] FIG. 1 illustrates a block diagram of a system for Mobile Distance Estimation and Intent Detection in Physical Access Control, according to an aspect of the present disclosure;

[0021] FIG. 2 illustrates a block diagram of a data processing apparatus of the system of FIG. 1, according to an aspect of the present disclosure;

[0022] FIG. 3 illustrates a flowchart of a method for Mobile reference calibration initiated by a user by holding a user device on a reader, according to an aspect of the present disclosure;

[0023] FIG. 4 illustrates a flowchart of a method for automated mobile reference calibration, according to an aspect of the present disclosure; and

[0024] FIG. 5 illustrates a flowchart depicting a method for determining an access threshold value based on Received Signal Strength Indicator (RSSI) measurements.

[0025] DETAILED DESCRIPTION

[0026] The following description sets forth exemplary aspects of the present disclosure. It should be recognized, however, that such description is not intended as a limitation on the scope of the present disclosure. Rather, the description also encompasses combinations and modifications to those exemplary aspects described herein.

[0027] The present disclosure provides a system and method for mobile access control using signal strength calibration. The system and method may offer an enhanced approach to mobile-based access control by leveraging a unique calibration algorithm to estimate the signal strength of a user's mobile device at a certain distance from an access control reader. The calibration method may utilize a series of Received Signal Strength Indicator (RSSI) values, which are processed to derive a calibrated received device RS SI (calRxDevRssi) value. The calRxDevRssi value may then be used to determine an access threshold value for granting access to the user device.

[0028] In some aspects, the system may include a Near Field Communication (NFC) unit within the reader, which can detect the presence of the user device within a predefined distance. The NFC detection capability may be utilized during the calibration process to ensure consistent positioning of devices, leading to more accurate reference RSSI values.

[0029] In other aspects, the system may employ a data processing apparatus that is configured to store the calRxDevRssi value and the access threshold value in a database. The stored access threshold value may be used for subsequent access attempts by the user device, providing a consistent and reliable access control experience.

[0030] In yet other aspects, the system may periodically update the calRxDevRssi value and the access threshold value based on subsequent RSSI measurements from the user device. The continuous data collection and threshold adjustment may compensate for variations in smartphone BLE radio performance over time, further enhancing the accuracy and reliability of the access control system.

[0031] In some cases, the system may implement and apply a machine learning model to identify patterns in the RSSI measurements, which can improve the accuracy of the access threshold value. The application of machine learning model represents a significant advancement over conventional mobile access control systems, offering the potential for more precise and adaptive access control decisions.

[0032] Overall, the disclosed system and method for mobile access control using signal strength calibration may provide a more robust, accurate, and user-friendly solution for mobile-based access control, addressing key challenges in signal strength variability and intent detection in physical access control applications.

[0033] Referring to FIG. 1, the figure illustrates a block diagram of a system 100 for mobile distance estimation and intent detection in physical access control. The system 100 may include a user device 102, a reader 106, and a data processing apparatus 104, all interconnected via a communication network 108.

[0034] The user device 102 may include several components. A user interface 110 may allow user interaction with the device. The user device memory 114 may store data and applications. A calibration application 116 stored in the memory may perform calibration processes. The communication interface 118 may facilitate communication with other components of the system 100.

[0035] The reader 106 may be a separate component, connected to the communication network 108. It may interact with the user device 102 and the data processing apparatus 104 through the network. In some aspects, the reader 106 may include an NFC unit 112 that may enable near-field communication capabilities. Specifically, the NFC unit 112 may be adapted to detect the presence of the user device 102 within a predefined distance from the reader 106. The NFC field detection capability may be utilized during the calibration process to ensure consistent positioning of devices, leading to more accurate reference RSSI values.

[0036] The data processing apparatus 104 may include processing circuitry 120 for executing various operations and algorithms. It may also include a database 122 for storing relevant data, such as calibration values and access thresholds. The processing circuitry 120 may be configured to receive a plurality of Received Signal Strength Indicator (RSSI) values from the reader 106, corresponding to signals transmitted by the user device 102. It may determine an average RSSI value based on the plurality of RSSI values, determine a standard deviation of the plurality of RSSI values, set the average RSSI value as a calibrated received device RSSI (calRxDevRssi) value when the standard deviation is within a predefined limit, and determine an access threshold value based on the calRxDevRssi value for granting access to the user device 102.

[0037] The communication network 108 may represent the medium through which the user device 102, reader 106, and data processing apparatus 104 exchange information. In some cases, the communication network 108 may be a wireless network, a wired network, or a combination of both.

[0038] In operation, the system 100 may be configured to facilitate mobile-based access control by utilizing signal strength measurements and calibration processes to determine the proximity of the user device 102 to the reader 106, and subsequently grant or deny access based on the determined values. The system 100 may provide a more robust, accurate, and user-friendly solution for mobile-based access control, addressing key challenges in signal strength variability and intent detection in physical access control applications.

[0039] The system 100 achieves enhanced functionality through a sophisticated calibration algorithm that leverages Received Signal Strength Indicator (RSSI) values. These RSSI values, transmitted by the user device 102 and received by the reader 106, are processed by the data processing apparatus 104 to derive a calibrated received device RSSI (calRxDevRssi) value. The calRxDevRssi value serves as a reference point for determining the proximity of the user device 102 to the reader 106.

[0040] To ensure accuracy, the system 100 employs a statistical approach. The processing circuitry 120 determines an average RSSI value from multiple measurements and determines the standard deviation of these values. Only when the standard deviation falls within a predefined limit is the average RSSI value set as the calRxDevRssi. The method helps to filter out anomalous readings and provides a more reliable baseline for access control decisions. Furthermore, the system 100 incorporates adaptive thresholding by determining an access threshold value based on the calRxDevRssi. The threshold is used to make informed decisions about granting or denying access, taking into account the specific characteristics of the user device 102 and the environmental conditions at the time of access attempt.

[0041] The system's robustness is further enhanced by its ability to continuously update and refine its calibration. By periodically updating the calRxDevRssi and access threshold values based on subsequent RSSI measurements, the system 100 can adapt to changes in device performance or environmental factors over time. The dynamic calibration process ensures that the access control system maintains its accuracy and reliability in the face of changing conditions.

[0042] Additionally, the integration of machine learning models allows the system 100 to identify patterns in RSSI measurements, further improving the accuracy of access threshold values. The advanced analytical capability enables the system to learn from historical data and make increasingly precise access control decisions.

[0043] By addressing the challenges of signal strength variability and intent detection, the system 100 offers a significant improvement over conventional mobile access control systems. Its ability to provide consistent and reliable performance across various devices and environmental conditions makes it a robust solution for modern physical access control applications.

[0044] Referring to FIG. 2, the figure illustrates a block diagram of a data processing apparatus 104 for mobile distance estimation and intent detection in physical access control. The data processing apparatus 104 may include processing circuitry 120, which comprises several interconnected components.

[0045] The processing circuitry 120 may be connected to a network interface 200 and an I / O interface 202 via a first communication bus 204. These interfaces may allow the data processing apparatus 104 to communicate with external devices and networks. Within the processing circuitry 120, several functional engines may be interconnected via a second communication bus 218. These engines may include a beacon collection engine 206, a beacon transmission engine 208, a standard deviation determination engine 210, an average value determination engine 212, an access threshold value determination engine 214, and an NFC field detection engine 216.

[0046] The beacon collection engine 206 may include suitable logic, circuitry, interfaces, and / or code, executable by the circuitry, to perform one or more operations. For example, the beacon collection engine 206 may be configured to collect beacon signals transmitted by the user device 102 and received by the reader 106.

[0047] The beacon transmission engine 208 may include suitable logic, circuitry, interfaces, and / or code, executable by the circuitry, to perform one or more operations. For example, the beacon transmission engine 208 may be configured to transmit beacon signals to the user device 102 during the calibration process.

[0048] The standard deviation determination engine 210 may include suitable logic, circuitry, interfaces, and / or code, executable by the circuitry, to perform one or more operations. For example, the standard deviation determination engine 210 may be configured to determine the standard deviation of the plurality of RSSI values received from the reader 106.

[0049] The average value determination engine 212 may include suitable logic, circuitry, interfaces, and / or code, executable by the circuitry, to perform one or more operations. For example, the average value determination engine 212 may be configured to determine an average RSSI value based on the plurality of RSSI values received from the reader 106.

[0050] The access threshold value determination engine 214 may include suitable logic, circuitry, interfaces, and / or code, executable by the circuitry, to perform one or more operations. For example, the access threshold value determination engine 214 may be configured to determine an access threshold value based on the calRxDevRssi value for granting access to the user device 102. The NFC field detection engine 216 may include suitable logic, circuitry, interfaces, and / or code, executable by the circuitry, to perform one or more operations. For example, the NFC field detection engine 216 may be configured to detect the presence of the user device 102 within a predefined distance from the reader 106.

[0051] The data processing apparatus 104 may also include a database 122, which is connected to the processing circuitry 120 via the first communication bus 204. The database 122 may store relevant data for the system's operation, such as the calRxDevRssi value and the access threshold value.

[0052] In operation, the data processing apparatus 104 may receive a plurality of RSSI values from the reader 106, determine an average RSSI value and a standard deviation of the RSSI values, set the average RSSI value as the calRxDevRssi value when the standard deviation is within a predefined limit, and determine an access threshold value based on the calRxDevRssi value for granting access to the user device 102. The determined calRxDevRssi value and the access threshold value may be stored in the database 122 for subsequent access attempts by the user device 102.

[0053] Referring to FIG. 3, the figure illustrates a flowchart depicting a method 300 for mobile signal strength calibration. The method 300 may be initiated by a user through a smartphone app running on the user device 102. The method 300 begins with step 302, where the user device 102, under the control of the calibration application 116, may send out calibration-specific frames to the reader 106. These frames may be transmitted over BLE advertisements or BLE connections, and may include information that identifies them as calibration-specific.

[0054] In step 304, the reader 106, under the control of the beacon collection engine 206, may collect 'n' calibration beacons' Received Signal Strength Indicator (RSSI) values. The number 'n' may be chosen such that there is a balance between the speed of calibration and accuracy of the calibrated value. The RSSI values represent the signal strength of the calibration-specific frames received by the reader 106 from the user device 102. The process then moves to step 306, where the reader 106, under the control of the beacon transmission engine 208, may send back the 'n' calibration beacons' RSSI values in an array to the user device 102. The array of RSSI values may be used by the user device 102 to determine the standard deviation and average of the RSSI values.

[0055] In step 308, the user device 102, under the control of the calibration application 116, may check the RSSI array for invalid values. Invalid values may include values that are outside a predefined range, values that are significantly different from other values in the array, or values that indicate a malfunction or error in the signal transmission or reception.

[0056] In step step 310 represents a decision point where the process checks if any invalid RSSI values are present. If invalid values are detected (Yes branch), the process moves to step 312, where the RSSI array is deleted. The process then loops back to step 302 to restart the calibration process.

[0057] If no invalid RSSI values are found (No branch), the process proceeds to step 314, where the standard deviation of the array is determined. The determination may be performed by the standard deviation determination engine 210 in the user device 102. Following the step 314, step 316 checks if the determined standard deviation is within predefined limits. These limits may be set to ensure that the RSSI values are consistent and reliable.

[0058] If the standard deviation is not within limits (No branch), the process returns to step 312 to delete the RSSI array and restart the calibration. If the standard deviation is within limits (Yes branch), the process moves to the final step 318, where the average value of all the 'n' samples is set at the calRxDevRssi. The determination may be performed by the average value determination engine 212 in the user device 102.

[0059] The calRxDevRssi is the value that will be used to further derive the final access threshold for that particular smartphone and hence the user. By using the above- mentioned algorithm, we can now estimate the average signal strength power that will be seen by the reader 106 for different smartphones but we cannot use the value as the access threshold as we need to consider differences between the reader’s radio performance as well.

[0060] Referring to FIG. 4, the figure illustrates a flowchart depicting a method 400 for automated calibration and access threshold determination in a mobile access control system. The method 400 begins with step 402, where a user performs tap access with default values. These default values may be selected so that all types of smartphones will be able to gain access.

[0061] In step 404, the reader 106, under the control of the beacon collection engine 206, may collect the Received Signal Strength Indicator (RSSI) at valid access of a user. The RS SI value represents the signal strength of the user device 102 at the time of access and is used to estimate the best threshold for that particular user’s smartphone.

[0062] Following this, in step 406, the reader 106, under the control of the beacon transmission engine 208, may send the captured RSSI for the user to cloud software via a gateway. The cloud software may be part of the data processing apparatus 104 and may be configured to maintain arrays of 'x' size per smartphone.

[0063] In step 408, the cloud software, under the control of the processing circuitry 120, may maintain an average of RSSI values per user phone and waits for X values to be acquired. As the accesses keep happening, the new values will be filling up the array.

[0064] When the array gets full, as determined in step 410, an average and standard deviation will be determined by the average value determination engine 212 and the standard deviation determination engine 210, respectively. If the standard deviation is outside the limits, as determined in step 412, then the array values are discarded and the system waits for new values to fill the array.

[0065] Once the standard deviation is acceptable, the average is set at the new calRxDevRssi in step 414. Using the value, the final accessThreshold is determined as described earlier by the access threshold value determination engine 214.

[0066] In step 416, the determined value is set as the new access threshold for the smartphone autonomously. This means that the user does not need to manually adjust the access threshold, as the system 100 automatically updates it based on the collected RSSI values.

[0067] The collection and update of the RSSI values and hence the access threshold keep on happening in the cloud, hence over time smartphone BLE radio variation of smartphone performance can be compensated for. The automated calibration process allows the system 100 to continuously adapt to changes in device performance and environmental conditions, ensuring that the access control system maintains its accuracy and reliability in the face of changing conditions.

[0068] In some aspects, the processing circuitry 120 may implement and apply a machine learning model to identify patterns in the RSSI measurements for improving accuracy of the access threshold value. Such advanced analytical capability enables the system to learn from historical data and make increasingly precise access control decisions. This represents a significant advancement over conventional mobile access control systems, offering the potential for more precise and adaptive access control decisions.

[0069] Referring to FIG. 5, the figure illustrates a flowchart depicting a method 500 for determining an access threshold value based on Received Signal Strength Indicator (RSSI) measurements. The method 500 may be implemented by the processing circuitry 120 of the data processing apparatus 104 in conjunction with the reader 106 and the user device 102.

[0070] At step 502, the NFC unit 112 of the reader 106 may detect presence of the user device (102) within a predefined distance from the reader 106.

[0071] At step 504, upon detecting presence of the user device 102 within a predefined distance from the reader 106, the processing circuitry 120 may initiate a calibration process when the user device 102 is detected within the predefined distance. Specifically, for the calibration process, the processing circuitry may transmit calibration- specific frames to the user device 102 and may further receive the plurality of RSSI values from the reader 106 in response to the calibration-specific frames. At step 506, upon initiating the calibration process when the user device 102 is detected within the predefined distance, the processing circuitry 120 may receive a plurality of Received Signal Strength Indicator (RSSI) values from the reader 106. These RSSI values correspond to signals transmitted by the user device 102. The RSSI values may be collected by the reader 106 when the user device 102 is within a predefined distance from the reader 106, as detected by the NFC unit 112. The RSSI values may be transmitted from the reader 106 to the data processing apparatus 104 via the communication network 108.

[0072] At step 508, the processing circuitry 120, specifically the average value determination engine 212, may determine an average RSSI value based on the plurality of RSSI values received from the reader 106. The average RSSI value represents the average signal strength of the user device 102 at the predefined distance from the reader 106.

[0073] At step 510, the processing circuitry 120, specifically the standard deviation determination engine 210, may determine a standard deviation of the plurality of RSSI values. The standard deviation provides a measure of the variability or dispersion of the RSSI values, which can be used to assess the reliability of the average RSSI value.

[0074] The processing circuitry 120 may check if the determined standard deviation is within a predefined limit. If the standard deviation is within the predefined limit, this indicates that the RSSI values are consistent and reliable, and the process proceeds to step 510. If the standard deviation is not within the predefined limit, this indicates that the RSSI values are inconsistent or unreliable, and the process may return to step 502 to receive new RSSI values.

[0075] At step 512, the processing circuitry 120 may set the average RSSI value as a calibrated received device RSSI (calRxDevRssi) value when the standard deviation is within the predefined limit. The calRxDevRssi value serves as a reference point for determining the proximity of the user device 102 to the reader 106.

[0076] At step 514, the processing circuitry 120, specifically the access threshold value determination engine 214, may determine an access threshold value based on the calRxDevRssi value for granting access to the user device 102. The access threshold value represents the minimum signal strength required for the user device 102 to be granted access by the reader 106. The access threshold value may be stored in the database 122 for subsequent access attempts by the user device 102.

[0077] At step 516, the processing circuitry 120 may store the calRxDevRssi value and the access threshold value in a database 122.

[0078] At step 518, the processing circuitry 120 may utilize the stored access threshold value for subsequent access attempts by the user device 102.

[0079] At step 520, the processing circuitry 120 may perform periodically or continuously to update the calRxDevRssi value and the access threshold value based on subsequent RS SI measurements from the user device 102. The continuous data collection and threshold adjustment may compensate for variations in smartphone BLE radio performance over time, further enhancing the accuracy and reliability of the access control system.

[0080] At step 522, processing circuitry 120 may implement a machine learning model to identify patterns in the RSSI measurements for improving accuracy of the access threshold value. The advanced analytical capability enables the system 100 to learn from historical data and make increasingly precise access control decisions.

[0081] In some aspects, the user device 102 may be a smartphone or a smartwatch. These devices may have different BLE radio designs, which can result in different RSSI values even at a constant distance from the reader 106. To account for these differences, the system 100 may implement a Mobile Reference Calibration Algorithm, which can identify the best operating threshold for mobile access by calibrating the RSSI values for each user device 102.

[0082] In some cases, the system 100 may use factory-characterized RSSI values for different readers to estimate the calRxDevRssi for each reader a user has permissions to. For example, let's consider two reader devices, referred to as Devi and Dev2. The factory characterized RSSI values for Devi and Dev2 may be represented as rxRefRssiDevl, txRefRssiDev 1 , rxRefRssiDev2, and txRefRssiDev2. If the user device 102 is calibrated on Devi and acquires the calRxDevRssiDevl, then the calRxDevRssiDev2 for Dev2 can be estimated by the following equation: calRxDevRssiDev2 = calRxDevRssiDevl - (rxRefRssiDev 1 - rxRefRssiDev2). This way, the system 100 can estimate the appropriate values per reader device and per user device 102.

[0083] In some aspects, the access threshold is determined by adding an offset to the calRxDevRssi. The access threshold value determination engine 214 may be configured to perform the determination. The access threshold is the value on which the reader 106 decides if the user device 102 is within the required distance to gain access. The access threshold, along with the NFC field detection, can be used to accurately detect the user device 102 tapping on the reader 106 and grant access.

[0084] In some cases, the system 100 can provide a tap-based BLE access method using the NFC field detection and BLE signal strength. The method allows users to access the door by just tapping the user device 102 on the reader 106 without actually using the NFC communication. This provides a similar user experience of tapping the access cards on the reader 106 but uses BLE instead of NFC. Therefore, user devices 102 which do not have NFC hardware can also get the same experience via BLE by implementing the method. This represents a significant advancement over conventional mobile access control systems, offering a more user-friendly and versatile access control solution.

[0085] Thus, the system 100 and the method 500 provides:

[0086] 1. Improved accuracy in mobile-based access control through adaptive signal strength calibration, accounting for variations in device hardware, environmental factors, and user behavior.

[0087] 2. Enhanced security by utilizing a combination of BLE signal strength measurements and NFC field detection for precise proximity sensing and intent detection. 3. Increased reliability of access control decisions through continuous data collection and threshold adjustment, compensating for smartphone BLE radio variations over time.

[0088] 4. Efficient calibration process leveraging NFC field detection to ensure consistent positioning of devices during calibration, resulting in more accurate reference RSSI values.

[0089] 5. Improved user experience by enabling tap-based BLE access without requiring NFC communication, allowing smartphones without NFC hardware to utilize the same convenient access method.

[0090] 6. Enhanced adaptability across different reader hardware through factory characterization and dynamic calRxDevRssi estimation, ensuring consistent performance across various access points.

[0091] These technical advancements collectively contribute to a more robust, accurate, and user-friendly mobile access control system, addressing key challenges in signal strength variability and intent detection in physical access control applications.

[0092] A number of implementations have been described. Nevertheless, it will be understood that various modifications may be made without departing from the spirit and scope of the disclosure. Accordingly, other implementations are within the scope of the following claims.

Claims

Claims:

1. A system (100) for mobile distance estimation and intent detection in physical access control, the system (100) comprising: a user device (102); a reader (106) that is adapted to communicate with the user device (102) and comprising a Near Field Communication (NFC) unit (112) adapted to detect presence of the user device (102) within a predefined distance from the reader (106); a data processing apparatus (104) that is coupled to the reader (106) and the user device (102), the data processing apparatus (104) comprising processing circuitry (120) configured to: receive, from the reader (106), a plurality of Received Signal Strength Indicator (RSSI) values corresponding to signals transmitted by the user device (102); determine an average RSSI value based on the plurality of RSSI values; determine a standard deviation of the plurality of RSSI values; set the average RSSI value as a calibrated received device RSSI (calRxDevRssi) value when the standard deviation is within a predefined limit; and determine an access threshold value based on the calRxDevRssi value to grant access to the user device (102).

2. The system (100) as claimed in claim 2, wherein the processing circuitry (120) is further configured to: initiate a calibration process when the NFC unit (112) detects the user device (102) within the predefined distance and transmit calibration-specific frames to the user device (102) during the calibration process.

3. The system (100) as claimed in claim 1, wherein the processing circuitry (120) is further configured to: store the calRxDevRssi value and the access threshold value in a database (122); and utilize the stored access threshold value for subsequent access attempts by the user device (102).

4. The system (100) as claimed in claim 4, wherein the processing circuitry (120) is further configured to: periodically update the calRxDevRssi value and the access threshold value based on subsequent RSSI measurements from the user device (102); and implement and apply a machine learning model to identify patterns in the RSSI measurements for improving accuracy of the access threshold value.

5. A method (500) for mobile distance estimation and intent detection in physical access control, the method (500) comprising: receiving (506), by way of processing circuitry (120) of a data processing apparatus (104), a plurality of Received Signal Strength Indicator (RSSI) values from a reader (106), wherein the RSSI values corresponds to signals transmitted by a user device (102); determining (508), by the processing circuitry (120), an average RSSI value based on the plurality of RSSI values; determining (510), by the processing circuitry (120), a standard deviation of the plurality of RSSI values; setting (512), by the processing circuitry (120), the average RSSI value as a calibrated received device RSSI (calRxDevRssi) value when the standard deviation is within a predefined threshold; and determining (514), by the processing circuitry (120), an access threshold value based on the calRxDevRssi value for granting access to the user device (102).

6. The method (500) as claimed in claim 6, prior to receiving the plurality of RSSI value, comprising: detecting (502), by a Near Field Communication (NFC) unit (112) of the reader (106), presence of the user device (102) within a predefined distance from the reader (106); and initiating (504), by the processing circuitry (120), a calibration process when the user device (102) is detected within the predefined distance.

7. The method (500) as claimed in claim 7, wherein for the calibration process, the method (500) comprising: transmitting, by the processing circuitry (120), calibration-specific frames to the user device (102); and receiving, by the processing circuitry (120), the plurality of RSSI values from the reader (106) in response to the calibration-specific frames.

8. The method (500) as claimed in claim 6, further comprising: storing (516), by the processing circuitry (120), the calRxDevRssi value and the access threshold value in a database (122); and utilizing (518), by the processing circuitry (120), the stored access threshold value for subsequent access attempts by the user device (102).

9. The method (500) as claimed in claim 6, further comprising: periodically updating (520), by the processing circuitry (120), the calRxDevRssi value and the access threshold value based on subsequent RSSI measurements from the user device (102); and implementing and applying (522), by the processing circuitry (120), a machine learning model to identify patterns in the RSSI measurements for improving accuracy of the access threshold value.

Images