A bluetooth-based apple device detection and positioning method

Abstract

The application discloses a kind of apple equipment detection and positioning method based on Bluetooth.The method is by passive listening apple device emitted Bluetooth broadcast packet, extracts its phase information to construct unique " phase pattern " fingerprint, and is combined with time disturbance, signal strength, frequency deviation and load characteristics to construct multi-dimensional joint feature vector, realize the high-precision identification of apple equipment and redundant signal filtering.Further, by constructing virtual antenna array to extract signal angle of arrival, combined with multi-node time difference information, realize meter-level indoor positioning.The application also introduces adaptive scanning scheduling algorithm to balance energy consumption and detection rate, and through multipath interference suppression and privacy protection mechanism, the robustness and compliance of system are improved.The application can be widely applied to shopping mall crowd statistics, security monitoring, intelligent office and the like.

Description

Technical Field

[0001] This invention belongs to the field of wireless communication and signal processing technology, and in particular relates to a method for detecting and locating Apple devices based on Bluetooth. Background Technology

[0002] With the increasing prevalence of Apple mobile devices (such as iPhones, iPads, and AirPods), their distribution density in public places is rising, leading to a growing demand for the detection, identification, and location of these devices. However, existing technologies generally suffer from the following shortcomings, making it difficult to meet the high-precision identification and location requirements of Apple mobile devices:

[0003] (1) Conflict between privacy protection and identification accuracy: In order to protect user privacy, manufacturers such as Apple randomize the device MAC address, which makes the traditional device identification method with fixed MAC address invalid; while identification methods based solely on general features such as RSSI and broadcast UUID cannot accurately distinguish Apple device models and have low identification accuracy.

[0004] (2) Positioning accuracy and environmental adaptability: The RSSI-based ranging method is easily affected by environmental factors such as multipath effect and signal attenuation. The ranging error is usually several meters or even tens of meters, which cannot achieve high-precision positioning in indoor scenarios.

[0005] (3) It is difficult to balance energy consumption and detection rate: Most solutions adopt a fixed cycle scanning mode. If the scanning cycle is too short, the energy consumption of the detection node will surge, which is not conducive to large-scale long-term deployment. If the scanning cycle is too long, the detection rate of the equipment will be reduced, and real-time monitoring cannot be achieved.

[0006] (4) Lack of device status awareness: Existing methods can only determine whether a device exists, but cannot infer the device's operating status (such as screen lock, unlock, power saving mode, accessory connection status, etc.). The functions are relatively simple and cannot meet the application needs of complex scenarios.

[0007] For example, patent document CN118590823A discloses a Bluetooth ranging method that relies on RSSI and propagation model to calculate distance. It does not involve the extraction of unique features of the device's radio frequency front end, cannot solve the device identification problem caused by MAC address randomization, and the positioning accuracy is significantly affected by the environment.

[0008] Patent document CN119788529A discloses a BLE device identification system and method based on traffic flow. It identifies devices by analyzing the communication traffic characteristics of BLE (Bluetooth Low Energy) devices. However, it can only determine whether a device exists and cannot obtain detailed information such as device model and operating status. Furthermore, it does not mention positioning-related technologies.

[0009] Therefore, there is an urgent need for an Apple device detection technology that can take into account high-precision identification, positioning, low power consumption, and status awareness. Summary of the Invention

[0010] In view of this, the present invention aims to overcome the shortcomings of the above-mentioned problems in the prior art and proposes a Bluetooth-based method for detecting and locating Apple devices.

[0011] To achieve the above objectives, the technical solution of the present invention is implemented as follows:

[0012] In a first aspect, the present invention provides a Bluetooth-based method for detecting and locating Apple devices, comprising the following steps:

[0013] Acquire Bluetooth broadcast packets emitted by Apple mobile terminals that are passively monitored by the probe node;

[0014] Extract the phase information of the broadcast packet to construct a phase fingerprint to characterize the uniqueness of the device;

[0015] By fusing the phase fingerprint and other radio frequency features, a multi-dimensional joint feature vector is constructed.

[0016] Based on the joint feature vector, the device model is identified and redundant signals are filtered;

[0017] The identified device is located by utilizing the collaborative information from multiple detection nodes.

[0018] Furthermore, due to the unique coupling characteristics between the RF front-end circuitry (such as oscillators and power amplifiers) and the antenna in Apple devices, Bluetooth broadcast packets exhibit unique inter-packet phase changes on a microscopic time scale. This invention records the phase sequence of continuous broadcast packets using probe nodes, employing this sequence as a phase fingerprint of the device for unique device identification.

[0019] The implementation process is as follows:

[0020] The probe node receives continuous Bluetooth broadcast packets from the same Apple device and records the phase information φ of each packet. i,k (i is the probe node number, k is the packet sequence number).

[0021] Calculate the phase difference sequence of adjacent packets

[0022] ∆φ i =[φ i,2 -φ i,1 ,φ i,3 -φ i,2 ,...]

[0023] The phase difference sequence is processed by removing 2π jumps (eliminating jump errors caused by phase periodicity) and normalizing.

[0024] Calculate the statistical characteristics (such as mean, variance, and power spectral density) of the normalized phase difference sequence, and construct the device phase ripple vector p as the core feature for device uniqueness identification.

[0025] Furthermore, since a single feature is insufficient to fully characterize the radio frequency characteristics of Apple devices, this invention integrates broadcast packet time perturbation, signal strength, phase ripple, frequency offset, and load pattern to construct a multi-dimensional joint feature vector, thereby improving the accuracy and robustness of device identification.

[0026] Feature vector composition:

[0027] The joint feature vector x = [jitter, RSSI(t), p, Δf, payload_pattern] has the following meanings for each dimension:

[0028] jitter: Statistical characteristics of the broadcast packet interval disturbance (such as mean μ) jitter ,variance σ jitter This reflects the clock stability of the device's Bluetooth module.

[0029] RSSI(t): Statistical characteristics of the RSSI time series (such as mean μ) r ,variance σ r This helps determine the distance range between the device and the detection node;

[0030] p: Phase ripple vector, which serves as the core for unique device identification.

[0031] Radio frequency offset, calculated by the detection node through short-time Fourier transform, reflects the frequency deviation characteristics of the device oscillator.

[0032] payload_pattern: Discretized features of the broadcast packet payload (such as the hash value of the bit-pattern histogram) used to filter redundant signals (such as Airdrop temporary signals) and prevent leakage of privacy information.

[0033] Furthermore, the step of identifying the device model and filtering redundant signals based on the joint feature vector includes:

[0034] The joint feature vector is input into a pre-trained machine learning classifier, which outputs the device category probability.

[0035] Determine whether the device is an Apple device and its specific model based on probability;

[0036] At the same time, redundant signals are filtered based on load characteristics.

[0037] Furthermore, this invention improves the phase measurement accuracy of the detection nodes by using a virtual antenna array, and combines the time difference of arrival (TDoA) and angle of arrival (AoA) information of multiple nodes to achieve meter-level positioning accuracy for Apple devices.

[0038] The implementation method is as follows:

[0039] Virtual antenna array construction: On a single detection node, a virtual antenna array is formed by using "multi-physical antenna parallel acquisition" or "single antenna time-division multiplexing acquisition" to improve the spatial resolution of phase difference measurement;

[0040] AoA estimation: Phase difference guessed based on virtual antenna array (m is the element number), combined with the element spacing d and the Bluetooth signal wavelength Through formula ( (Angle of arrival of the signal) Calculate the azimuth angle of the device relative to the detection node;

[0041] TDoA positioning: Utilizes time synchronization among multiple probe nodes (achieved via GPS, network clock, or local high-precision oscillator) to record the reception time of the same broadcast packet at different nodes. Construct the TDoA equation:

[0042]

[0043] s represents the location of the emission source. Let be the position of node i, and c be the speed of light. This is to account for measurement error. The value of s can be solved by solving multiple pairs of equations.

[0044] Phase synthesis and fusion: By integrating AoA and TDoA information from multiple nodes, the device position is solved using a Bayesian fusion algorithm or a constrained least squares method, overcoming multipath interference and improving positioning accuracy to the meter level.

[0045] Furthermore, this invention estimates the probability of Apple devices appearing using a Bayesian prediction model and dynamically adjusts the scanning frequency of the detection nodes, thereby reducing energy consumption while ensuring a high detection rate.

[0046] The implementation logic is as follows:

[0047] Probabilistic modeling: Treating the occurrence of device states as a stochastic process, a Bayesian update strategy is used to estimate the probability π of device occurrence at time t in real time. t ;

[0048] Scanning decision: Set a probability threshold η (adjust according to actual scenario requirements, such as η=0.3), when π t When the value is greater than η, high-frequency scanning is activated (to improve the detection rate); otherwise, low-frequency scanning is switched (to reduce energy consumption).

[0049] Cost optimization: Define the energy cost function:

[0050] in Energy consumption per unit scan For scanning action (0 = low frequency, 1 = high frequency). Let E be the loss when a device exists but is not detected. Dynamic programming is used to find the optimal scanning strategy, balancing energy consumption and detection rate. E represents the expected total cost incurred during the entire scanning process due to randomness in device presence, detection results, and state transitions.

[0051] Furthermore, since multipath effects in indoor environments (interference signals formed after signals are reflected by walls and furniture) can seriously affect the accuracy of RSSI and phase measurements, this invention improves feature measurement accuracy through multipath decomposition and machine learning denoising, thereby optimizing recognition and positioning performance.

[0052] The specific methods are as follows:

[0053] Multipath decomposition: Using short-time Fourier transform (STFT) or wavelet decomposition techniques, the received I / Q (orthogonal in the same direction) signals are decomposed into direct path components (signals directly transmitted by the device) and reflected components (multipath interference signals).

[0054] Principal component selection: Based on the statistical stability of the signal (e.g., the direct component has stronger power and more regular phase changes), the direct component is selected and multipath interference is identified;

[0055] Machine learning denoising: For the filtered RSSI, phase, and other time series, LSTM (Long Short-Term Memory) network or Transformer model is used for denoising to eliminate residual random interference and improve the stability and reliability of features.

[0056] Furthermore, this invention introduces privacy protection measures throughout the entire process of data collection, storage, and output to avoid collecting and leaking user-identifiable information (such as the original MAC address and complete payload data), ensuring that the technical solution complies with privacy compliance requirements.

[0057] The protective measures are as follows:

[0058] Data acquisition phase: Only high-order features of Bluetooth broadcast packets (such as phase and frequency offset) are collected, the original MAC address is hashed, and information that can be directly associated with user identity is not stored;

[0059] Data storage stage: Encrypted storage is used, retaining only aggregated information such as device existence, category probability, and location results, and not storing the original feature sequence of a single device;

[0060] Data output stage: A differential privacy mechanism is introduced to inject Laplace noise into statistical results (such as device counts and regional device density) to limit the risk of sensitive information leakage; at the same time, verifiable anonymization is supported, and administrators can verify the authenticity of data under compliant authorization, but cannot infer users' personal information.

[0061] Secondly, the present invention provides an electronic device, including a processor and a memory communicatively connected to the processor and used to store executable instructions of the processor, wherein the processor is used to execute the above-described Bluetooth-based Apple device detection and positioning method.

[0062] Thirdly, the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements a Bluetooth-based method for detecting and locating Apple devices.

[0063] Compared with existing technologies, the Bluetooth-based Apple device detection and positioning method described in this invention has the following advantages:

[0064] This invention achieves comprehensive optimization of Apple mobile terminal detection and positioning in the following aspects:

[0065] (1) Significantly improved recognition performance

[0066] This invention solves the problem of MAC address randomization: it achieves unique identification of Apple devices through phase fingerprinting without relying on fixed MAC addresses, with a device manufacturer identification accuracy of 100% and a model identification accuracy of over 98%.

[0067] Highly efficient redundant signal filtering: It can accurately remove redundant signals such as AirDrop and device interconnection, with a false recognition rate of less than 2%, ensuring the accuracy of statistical data.

[0068] (2) Positioning accuracy breaks through the meter level

[0069] Overcoming environmental interference: Through multipath self-correction and virtual antenna array phase synthesis, the effects of indoor multipath effect and signal attenuation are effectively eliminated, and the positioning accuracy is stabilized at 1-3 meters, meeting the needs of scenarios such as precise navigation and regional population flow statistics.

[0070] Fast positioning response: The positioning response time of multi-node collaborative computing is less than 1 second, enabling real-time updates of device location.

[0071] (3) Optimization of energy consumption deployment costs

[0072] Low-energy operation: The adaptive scanning scheduling algorithm reduces the energy consumption of the probe node by 40%-60%, and extends the battery life of a single node to 6-12 months, significantly reducing the maintenance cost of replacing batteries.

[0073] High compatibility: The probe nodes support Bluetooth 5.0 and above protocols, are compatible with existing Bluetooth devices, and require no hardware or software modifications to Apple terminals, making deployment easy.

[0074] (4) The functional scenarios are expanded and enriched.

[0075] Comprehensive device status awareness: It can determine the lock screen, unlock status, etc. of Apple devices in real time, which can be used in smart office (such as associating employee device unlock status with computer login permissions) and retail service (such as pushing low-power product information based on power saving mode) scenarios.

[0076] Multi-scenario adaptability: Suitable for various indoor public places such as shopping malls, airports, train stations, office buildings, and campuses, it can realize diverse applications such as people flow statistics, precision marketing, and security monitoring (such as monitoring abnormal stay of equipment in key areas).

[0077] (5) Privacy compliance protection

[0078] End-to-end privacy protection: Through measures such as hash processing, encrypted storage, differential privacy, and noise injection, no user-identifiable information is collected or leaked, complying with domestic and international privacy protection regulations;

[0079] Verifiable and traceable: It supports administrators in verifying the authenticity of data under compliant authorization, while retaining operation logs to ensure the traceability of data processing and avoid the risk of abuse. Attached Figure Description

[0080] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings:

[0081] Figure 1 This is a schematic diagram of the overall architecture in an embodiment of the present invention. Detailed Implementation

[0082] It should be noted that, unless otherwise specified, the embodiments and features described in the present invention can be combined with each other.

[0083] The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0084] This invention provides a Bluetooth-based method for detecting and locating Apple devices, the process of which is as follows: Figure 1 As shown. The following describes the solution of the present invention through different embodiments.

[0085] Example 1: Foot traffic statistics and area positioning for Apple devices in shopping malls

[0086] 1. System Deployment

[0087] Detection node deployment: Ten detection nodes are deployed in key locations such as passageways and shop entrances on each floor of the mall, with a node spacing of 10-15 meters; each node is equipped with two physical antennas to form a virtual antenna array.

[0088] Time synchronization: Time synchronization of each detection node is achieved through the NTP (Network Time Protocol) server inside the mall, with synchronization accuracy controlled within 10ms;

[0089] Central server: Deployed in the mall's computer room, equipped with an Intel Xeon E5 processor, 32GB of memory, and running a Linux system, responsible for receiving node data, executing identification and positioning algorithms, and providing a web-based visual interface.

[0090] 2. Data Acquisition and Preprocessing

[0091] The probe node receives Bluetooth broadcast packets in passive scanning mode, with the scanning frequency initially set to 1Hz (low frequency).

[0092] For each received broadcast packet, record the following information:

[0093] Reception time (The local timestamp of node i, after time synchronization calibration);

[0094] RSSI value (Range -100dBm to -30dBm);

[0095] Packet payload hash value (calculated using SHA-265 to avoid storing the original payload);

[0096] Phase information (Acquired directly via node radio frequency module);

[0097] Frequency offset (Calculated via short-time Fourier transform, sampling rate 1MHz).

[0098] The node performs local preprocessing on the raw data: removing weak signals with RSSI < -90dBm, and de-diminishing the phase sequence. The process involves a jump, followed by uploading only the preprocessed feature data (phase texture vector, joint feature vector) to the central server, thus reducing the amount of data transmission.

[0099] 3. Phase pattern extraction and device identification

[0100] The central server receives feature data uploaded by each node and broadcasts packets continuously to the same device (with a set time window W=5 seconds). Phase ripple vector p is extracted by calculating the phase difference sequence of adjacent packets within 5 seconds. ;

[0101] (1) To Perform normalization (map to the [-1,1] interval);

[0102] (2) Calculate the mean of the normalized sequence ,variance Power spectrum main peak frequency , build

[0103] Constructing the joint feature vector:

[0104]

[0105] Input to a pre-trained XGBoost classifier (the training dataset contains feature data from 1000 different Apple devices).

[0106] The classifier outputs the probability of the device category. It identifies the device as an Apple device and further outputs the specific model (e.g., if the probability of iPhone 15 is 0.92, then it is identified as iPhone 15); at the same time, it filters AirDrop signals based on payload_hash (a pre-built AirDrop payload hash feature library) to avoid redundant design.

[0107] 4. Multi-node collaborative positioning

[0108] Select three or more detection nodes that receive signals from the same Apple device (to ensure the uniqueness of the location calculation), and perform the following steps:

[0109] (1) Time Difference Positioning (TDoA): Using node 1 as the reference, calculate the reception time difference between nodes 2 and 3 and node 1. , Substituting these equations into the TDoA equation, we obtain two distance equations.

[0110] (2) AoA estimation: Based on the virtual antenna array of node 1, calculate the phase difference. (Element spacing d = 0.1 meters, Bluetooth wavelength) =0.12 meters), through Azimuth angle of the computing device relative to node 1 Similarly, calculate the azimuth angles of nodes 2 and 3. , ;

[0111] (3) Positioning fusion: The Bayesian fusion algorithm is adopted, which combines the TDoA distance difference and AoA azimuth angle to solve the equipment position coordinates (the plane rectangular coordinate system is used inside the mall, with the machine room as the origin), and the positioning result error is controlled within 2 meters;

[0112] (4) Multipath correction: Wavelet decomposition (using db4 wavelet basis) is performed on the received I / Q signal, direct components are filtered, and TDoA and AoA are recalculated. This further reduces the positioning error.

[0113] 5. Adaptive scan scheduling

[0114] The central server calculates the probability of Apple devices appearing in each region in real time, and estimates the probability of devices appearing in the local music and entertainment venue of each node through Bayesian updates. :

[0115] Shopping mall peak hours, If the value is generally >0.5, switch the node to high-frequency scanning (5Hz) to ensure no missed detections;

[0116] Off-peak hours: When the value is less than 0.1, the node switches to a low-frequency scan (0.5Hz) to reduce energy consumption.

[0117] Actual testing showed that this scheduling strategy reduced the daily energy consumption of nodes from a fixed 1000mAh at 5Hz to 450mAh. Energy consumption was reduced by 55%, while the equipment detection rate remained above 96%.

[0118] 6. Privacy Protection and Results Output

[0119] The central server performs privacy processing on statistical data: Laplace noise (noise intensity) is injected into the number of Apple devices on each floor. =0.1, which meets the differential privacy requirements), for example, if the actual number is 200, the output is 201 (noise range [-2,2]);

[0120] Administrators can view the following results through a web interface:

[0121] Real-time pedestrian flow: Number and density of Apple devices on each floor;

[0122] Location information: Device dwell time and movement trajectory in key areas (anonymized);

[0123] Status statistics: percentage of locked and unlocked devices, percentage of devices connected to accessories (e.g., 30% connected to AirPods).

[0124] Example 2: Detection of Apple devices in a confidential area

[0125] 1. System Deployment

[0126] Deploy 3-5 detection nodes on each floor of the confidential office area, with the nodes linked to the security system;

[0127] Set abnormal dwell time and area (such as a confidential meeting room, dwell time exceeding 2 minutes). When the device stays for too long, a security alert will be triggered.

[0128] 2. Implementation of core functions

[0129] Confidential Area Monitoring: Detection nodes locate Apple devices in real time. If a device stays in a confidential office area for more than a set time, an alert will be sent to the security system (including device location, stay time, and other detailed information, with anonymization options depending on the administrator settings).

[0130] Example 3: Smart Office Adaptation for Apple Devices in Office Buildings

[0131] 1. System Deployment

[0132] Deploy 3-5 detection nodes on each floor of the office building. The nodes are connected to the office computers and access control system via a local area network.

[0133] The central server is linked to the phase fingerprint of employees' Apple devices (registered when employees join the company; only the hashed phase fingerprint is stored and not linked to personal information).

[0134] 2. Implementation of core functions

[0135] Device unlock linkage: When an employee brings an Apple device into the office, the detection node recognizes the phase pattern and automatically unlocks the office computer. When the corresponding Apple device leaves the office area, it automatically locks the office computer screen.

[0136] Example 4:

[0137] An electronic device includes a processor and a memory communicatively connected to the processor and used to store processor-executable instructions, the processor being used to execute the aforementioned Bluetooth-based Apple device detection and positioning method.

[0138] Example 5:

[0139] A computer-readable storage medium storing a computer program, which, when executed by a processor, implements the aforementioned Bluetooth-based Apple device detection and positioning method.

[0140] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in this disclosure all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0141] It should be noted that personal information collected from users should be used for legitimate and reasonable purposes and should not be shared or sold outside of these legitimate uses. Furthermore, such collection / sharing should only be conducted after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign an agreement / authorization that includes authorization of relevant user information before the user uses the function. In addition, any necessary steps must be taken to protect and safeguard access to such personal information data and ensure that others with access to personal information data comply with their privacy and procedures.

[0142] This disclosure is intended to provide implementation schemes for users to selectively prevent the use or access to their personal information data. Specifically, this disclosure is intended to provide hardware and / or software to prevent or block access to such personal information data. Once personal information data is no longer needed, risks can be minimized by restricting data collection and deleting data. Furthermore, where applicable, such personal information is de-identified to protect user privacy.

[0143] The acquisition, transmission, storage, use, and processing of data in this disclosed technical solution all comply with the relevant provisions of national laws and regulations.

[0144] It should be noted that in the embodiments disclosed herein, certain software, components, models, and other existing solutions in the industry may be mentioned. These should be considered as exemplary and are intended only to illustrate the feasibility of implementing the technical solution of this application. However, they do not mean that the applicant has used or necessarily used such solutions.

[0145] In the foregoing descriptions of the embodiments, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this disclosure. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0146] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this disclosure, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0147] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of preferred embodiments of this disclosure includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of this disclosure pertain.

[0148] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0149] It should be understood that various parts of this disclosure can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0150] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0151] Furthermore, the functional units in the various embodiments of this disclosure can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0152] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of the present disclosure have been shown and described above, it is to be understood that the above embodiments are exemplary and should not be construed as limiting the present disclosure. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present disclosure.

Claims

1. A method for detecting and locating Apple devices based on Bluetooth, characterized in that: Includes the following steps: Acquire Bluetooth broadcast packets emitted by Apple mobile terminals that are passively monitored by the probe node; Extract the phase information of the broadcast packet to construct a phase fingerprint to characterize the uniqueness of the device; By fusing the phase fingerprint and other radio frequency features, a multi-dimensional joint feature vector is constructed. Based on the joint feature vector, the device model is identified and redundant signals are filtered; The identified device is located by utilizing the collaborative information from multiple detection nodes.

2. The method for detecting and locating Apple devices based on Bluetooth according to claim 1, characterized in that: The step of extracting the phase information of the broadcast packet and constructing a phase fingerprint to characterize the uniqueness of the device includes: Record the phase sequence of consecutive broadcast packets emitted by the same device; Calculate the phase difference between adjacent broadcast packets and perform 2π transition removal processing; The processed phase difference sequence is normalized, its statistical features are extracted, and the device phase ripple vector is constructed.

3. The method for detecting and locating Apple devices based on Bluetooth according to claim 1, characterized in that: The multidimensional joint feature vector includes at least one of the following features or a combination thereof: Characteristics of broadcast packet interval perturbation; Statistical characteristics of RSSI time series; Phase ripple vector; Radio frequency deviation; Discretization characteristics of broadcast packet payload.

4. The method for detecting and locating Apple devices based on Bluetooth according to claim 1, characterized in that: The process of identifying the device model and filtering redundant signals based on the joint feature vector includes: The joint feature vector is input into a pre-trained machine learning classifier, which outputs the device category probability. Determine whether the device is an Apple device and its specific model based on probability; At the same time, redundant signals are filtered based on load characteristics.

5. The method for detecting and locating Apple devices based on Bluetooth according to claim 1, characterized in that: The method of locating the identified device using the collaborative information of multiple detection nodes includes: Construct a virtual antenna array and extract the signal arrival angle; Calculate the signal arrival time difference using the time synchronization information of multiple probe nodes; By fusing information on arrival angle and time difference of arrival, the device location is calculated using Bayesian fusion or least squares method.

6. The method for detecting and locating Apple devices based on Bluetooth according to claim 1, characterized in that: It also includes an adaptive scan scheduling step: Real-time estimation of device occurrence probability based on Bayesian model; The scanning frequency of the detection nodes is dynamically adjusted based on probability to balance detection rate and energy consumption.

7. The method for detecting and locating Apple devices based on Bluetooth according to claim 1, characterized in that: It also includes a multipath interference suppression step: Perform time-frequency analysis on the received I / Q signals to separate the direct signal from the reflected signal; Direct signals are selected for subsequent feature extraction and localization calculations; A machine learning model is used to denoise the feature sequences.

8. The method for detecting and locating Apple devices based on Bluetooth according to claim 1, characterized in that: It also includes privacy protection steps: Hash the original MAC address; Encrypted storage is used; the original feature sequence of a single device is not stored. Differential privacy noise is injected into the output statistics.

9. An electronic device comprising a processor and a memory communicatively connected to the processor and used for storing processor-executable instructions, characterized in that: The processor is used to execute the method described in any one of claims 1-8.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, it implements the method described in any one of claims 1-8.

Images