Method, device and equipment for providing data plane location service based on eSIM card and medium

eSIM card positioning technology, which utilizes multi-source data fusion and distributed edge computing, solves the problems of positioning accuracy, privacy, power consumption, network dependence, and standardization in existing technologies, and provides high-precision, secure, and stable location services.

CN118972944APending Publication Date: 2024-11-15SHENZHEN CHENGTIAN WEIYE TECH

Patent Information

Application Number
CN202411439927.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-15
Publication Date
2024-11-15

AI Technical Summary

Technical Problem

Existing eSIM-based data plane positioning technologies suffer from problems such as low positioning accuracy, privacy and security issues, strong network dependence, high power consumption, insufficient standardization and compatibility, and insufficient real-time performance.

Method used

By combining multi-source mobile positioning data, dynamic frequency adjustment and noise filtering algorithms, intelligent location inference, distributed computing and edge computing, and utilizing data communication between the eSIM card and the mobile network, traffic information is analyzed to infer location, and encryption and anonymization technologies are introduced to ensure security.

Benefits of technology

It significantly improves positioning accuracy and stability, reduces power consumption and latency, ensures the continuity and accuracy of positioning services, enhances privacy protection and network resource utilization, and achieves global standardization and interoperability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118972944A_ABST
    Figure CN118972944A_ABST
Patent Text Reader

Abstract

The invention discloses a method, a device, equipment and a medium for providing data plane position service based on an eSIM card, and the method comprises the steps: obtaining multi-source mobile positioning data, and determining the geographic position of the equipment through the analysis of data plane information according to the data communication between the eSIM card in the equipment and the multi-source mobile positioning data; a dynamic frequency adjustment and noise filtering algorithm is constructed, the used frequency and the data acquisition frequency are dynamically adjusted by analyzing the signal strength, the signal stability and the historical position information of the equipment, noise filtering is carried out, and the noise is filtered by combining the dynamic frequency adjustment and the noise filtering algorithm. According to the method, the positioning frequency can be adaptively adjusted in different environments, noise and errors in positioning data are remarkably reduced through Kalman filtering and a machine learning algorithm, and finally the accuracy and stability of data plane position service provided by the eSIM card are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of mobile communication technologies, and in particular to a method, device, equipment and medium for providing data plane location services based on an eSIM card. Background Art

[0002] The eSIM card is a programmable SIM card embedded in the device, which can be activated and managed remotely without the need for physical replacement. Compared with traditional SIM cards, the eSIM card provides more flexibility and higher integration for mobile devices.

[0003] But there are some technical problems in practical application: 1. Low positioning accuracy: Compared with GPS and other satellite-based positioning systems, data plane-based positioning accuracy is usually lower. Network signal fluctuations, base station density and coverage, etc. will affect positioning accuracy.

[0004] 2. Privacy and security issues: Collecting location information through the data plane may lead to the risk of privacy leakage. If this data is intercepted by malicious attackers during transmission or storage, it may lead to the leakage of user location information. In addition, data collection and use without user consent may also violate privacy protection regulations.

[0005] 3. Strong network dependence: This method is highly dependent on the quality and coverage of the mobile network. In areas with weak network signals or no network coverage, data plane-based positioning services may not work properly.

[0006] 4. Power consumption: Compared with traditional GPS positioning, data plane-based positioning services may cause higher power consumption of devices, especially when the device is constantly exchanging data with the network. This may have an adverse effect on the battery life of mobile devices.

[0007] 5. Standardization and compatibility issues: Since there is no completely unified standard for eSIM technology and data plane positioning services worldwide, there may be compatibility issues between different devices, operators and regions. This will affect the popularity and consistency of services.

[0008] 6. Lack of real-time performance: Data plane positioning services usually require location inference during data stream transmission. Compared with real-time positioning systems, there may be a certain delay, which performs poorly in application scenarios that require high real-time performance. Summary of the invention

[0009] In order to solve one of the above technical problems, a method, device, equipment and medium for providing data plane location services based on eSIM cards are provided, which mainly utilizes the data communication between the eSIM card and the mobile network to determine the geographical location of the device by analyzing the traffic information on the data plane. The eSIM card can send data related to the location information to the location service provider through the network, and the service provider will infer the location information of the device based on these data. Compared with traditional GPS positioning, positioning based on the data plane may be more dependent on the distribution characteristics of network signals, such as signal strength, distance and location of base stations. The purpose of this technical solution is to solve the above-mentioned existing low positioning accuracy: Compared with GPS and other satellite-based positioning systems, the positioning accuracy based on the data plane is usually lower. The fluctuation of network signals, the density and coverage of base stations, etc. will affect the accuracy of positioning.

[0010] In order to achieve the above purpose, the technical solution adopted by the present invention is: Part 1: A method for providing data plane location services based on an eSIM card, comprising: Acquire multi-source mobile positioning data, and determine the geographic location of the device by analyzing data plane information according to data communication between an eSIM card in the device and the multi-source mobile positioning data; the multi-source mobile positioning data includes GPS data, Wi-Fi positioning data, Bluetooth beacon auxiliary data, cellular network signal positioning data and data plane information; Construct a dynamic frequency adjustment and noise filtering algorithm to dynamically adjust the frequency used and the frequency of data collection and perform noise filtering by analyzing the signal strength, signal stability and historical location information of the device; Build intelligent location inference algorithms to determine the geographic location of devices based on traffic data from data plane information analysis, and intelligently optimize and infer location services by learning user behavior patterns, geographic area characteristics, and environmental variables; According to the data communication between the eSIM card and the multi-source mobile positioning data, distributed computing and edge computing are obtained, wherein the distributed computing distributes part of the location computing and data processing tasks among the device, the network node and the central server, the device processes the local data in real time and performs preliminary positioning calculation, the network node processes the positioning data of multiple devices in the area, and finally sends the comprehensive results to the central server; The edge computing processes real-time data at the edge of the network based on the computing power of device access points or network nodes.

[0011] Preferably, the dynamic frequency adjustment dynamically adjusts the frequency of positioning data collection according to the motion state of the device, signal strength and distribution of signal sources, specifically including: Motion state detection: The motion state of the device is determined by the data of the accelerometer and gyroscope, and the modulus of acceleration of the device is calculated. , the expression is: ; in, The equipment is , , Acceleration in the axis direction; The motion state of the device includes a stationary state, a low-speed movement, and a high-speed movement; Static state: When Less than a certain threshold for a long time (For example ), the device is judged to be in a stationary state; Slow speed movement: If it fluctuates around the threshold but is small overall, it is judged as slow movement; High-speed movement: If the duration is greater than a certain threshold, it is considered as high-speed movement; Frequency adjustment strategy: adjust the sampling frequency according to the detected motion state of the device ; Quiescent state: Reduce sampling frequency to save power: ; Slow-speed movement: appropriately increase the sampling frequency to ensure the continuity of positioning: ; High-speed movement: significantly increase sampling frequency to improve positioning accuracy: ; Signal strength analysis: The signal strength RSSI (Received Signal Strength Indicator) is used to determine the signal quality and adjust the sampling frequency.

[0012] Strong signal: When RSSI is greater than a certain threshold , the sampling frequency can be reduced.

[0013] ; Weak signal: When RSSI is less than the threshold , increase the sampling frequency.

[0014] ; Comprehensive frequency adjustment: final sampling frequency The expression is: ; in, : is the fundamental frequency, : is an adjustment factor based on the state of motion, is an adjustment factor based on signal strength.

[0015] Preferably, the noise filtering algorithm filters the noise in the multi-source mobile positioning data according to the multipath effect of the multi-source mobile positioning data and the erroneous position information caused by the instantaneous signal interference, and specifically includes: Based on the Kalman filter algorithm, it provides the best estimate by combining historical data and current observations; Assume the position status is , the observed value is , then the update process of Kalman filter is as follows: Status prediction: ; Among them, A is the state transfer matrix, B is the control input matrix, is the control quantity.

[0016] Error covariance prediction: ; in, is the forecast error covariance matrix, is the process noise covariance matrix.

[0017] Kalman gain calculation: ; in, is the observation matrix, is the observation noise covariance matrix.

[0018] Status Update: ; Error covariance update: ; Through Kalman filtering, the system can effectively eliminate the instantaneous positioning error caused by noise and provide smooth position information; Machine learning anomaly detection algorithms: Machine learning anomaly detection algorithms based on historical data, including isolation forest and local anomaly factor; Isolation Forest: Isolate outliers by building random decision trees and determine whether the data is abnormal based on the anomaly score; Local anomaly factor: Calculate the local density of each data point and compare it with the density of surrounding data points to identify anomalies with significantly different densities; For example, for each new location data , its local anomaly factor can be calculated :

[0019] in, yes The k nearest neighbors of Represents the average distance from point x to its k nearest neighbors.

[0020] when When it is significantly greater than 1, the data is judged as an outlier and filtered out.

[0021] Preferably, by learning the user's behavior patterns, geographic area characteristics and environmental variables, intelligent optimization and inference of location services are performed, specifically including: The learning of user behavior patterns and geographic area features includes user location sequence modeling, state transition probability matrix A, observation probability matrix B and initial state probability vector and time series forecasting.

[0022] The learning goal of learning the user's behavior pattern is to extract the user's daily activity pattern by analyzing the user's historical location information, so as to predict his or her possible location at a future moment.

[0023] The user location sequence modeling assumes that the user's location sequence in T time steps is ,in When the user is: ; The state transition probability matrix A: represents the probability of a user transferring from one location to another: ; The observation probability matrix B represents the probability of observing a certain feature (such as Wi-Fi signal, GPS coordinates) at a specific location: ; The initial state probability vector : represents the probability that the user is initially in each position: ; The forward-backward algorithm is used to calculate the possible state (position) sequence of the user in the future, and the Viterbi algorithm is used to find the most likely state sequence.

[0024] The time series prediction: uses a long short-term memory network (LSTM) to predict the user's future location information. LSTM can effectively capture patterns in long time series data.

[0025] The input sequence is , the output is the predicted position at the future moment: ; in, is the time step of the prediction, is the predicted future position.

[0026] Preferably, the environmental variables include weather, time, and traffic conditions, specifically including: A multimodal deep learning model is constructed, wherein the multimodal deep learning model is a multimodal neural network that fuses environmental variables with the user's historical location data.

[0027] The input vector of the multimodal neural network includes the user position sequence and the environment variable vector ,in Including weather, time, and traffic conditions; The output of the multimodal deep learning model is the optimized position information: ; The multimodal deep learning model structure is: ; in, is the activation function, is the weight matrix, is the bias, vector, Indicates a connection operation.

[0028] Smart location inference: In practical applications, when the user's location signal is lost, AI can perform location inference based on the aforementioned behavioral patterns and environmental variables to maintain positioning continuity.

[0029] Position inference algorithm: In the case of signal loss, the user's location is inferred through Bayesian filtering. Bayesian filtering combines the prior probability with newly acquired information (such as environmental variables) to perform a posteriori inference of the location.

[0030] Prediction Steps: ; Update steps: In the new observation Update the posterior probabilities when available:

[0031] in, is the new observation model, which represents the position Observed probability.

[0032] Path Smoothing: After the signal is restored, in order to avoid sudden displacement jumps, spline interpolation or Kalman filtering is used to smooth the path.

[0033] Among them, spline interpolation: Assume that the path during the signal loss period is , the position after signal recovery is . Use spline interpolation to find a smooth transition path: ; Kalman filter: The Kalman filter smoothes the path by recursively estimating the state variables.

[0034] Preferably, the acquisition of distributed computing and edge computing, and construction of a distributed computing model, the distributed computing model includes device-side computing, network node computing and central server computing, and construction of the edge computing model includes edge node processing and edge intelligent optimization.

[0035] Preferably, the method further includes an enhanced privacy and security protection mechanism to ensure the security of the location information during transmission and storage, specifically including: Use strong encryption protocols on the data plane to encrypt and transmit location information; During the storage and analysis of location data, anonymization and de-identification are applied so that the user's identity information is not directly associated with the location information; Provides a detailed privacy control panel that allows users to choose to view and manage historical location information.

[0036] Part II: A device for providing data plane location services based on an eSIM card, comprising: A multi-source data fusion positioning module is used to obtain multi-source mobile positioning data, and determine the geographical location of the device by analyzing data plane information according to data communication between the eSIM card in the device and the multi-source mobile positioning data; A dynamic frequency adjustment and noise module is used to construct a dynamic frequency adjustment and noise filtering algorithm, dynamically adjust the frequency used and the frequency of data collection, and perform noise filtering by analyzing the signal strength, signal stability and historical location information of the device; Intelligent location inference module, which is used to build intelligent location inference algorithms, determine the geographical location of the device based on the traffic data of the data plane information, and intelligently optimize and infer location services by learning the user's behavior patterns, geographic area characteristics and environmental variables; A distributed computing module, used to obtain distributed computing and edge computing according to the data communication between the eSIM card and the multi-source mobile positioning data, wherein the distributed computing distributes part of the position calculation and data processing tasks among the device, the network node and the central server, processes the local data in real time according to the device and performs preliminary positioning calculation, and the network node processes the positioning data of multiple devices in the area, and finally sends the comprehensive results to the central server; The edge module is used for edge computing to process real-time data at the edge of the network according to the computing power of the device access point or network node.

[0037] Compared with the prior art, the present invention has the following beneficial effects: The present invention proposes a method for providing data plane location services based on an eSIM card. 1. eSIM technology allows switching mobile network operators through remote configuration without changing the physical SIM card; Second, by combining dynamic frequency adjustment and noise filtering algorithms, the present invention can adaptively adjust the positioning frequency in different environments. At the same time, through Kalman filtering and machine learning algorithms, it can significantly reduce the noise and error in the positioning data, and ultimately improve the accuracy and stability of the data plane location service provided by the eSIM card; 3. Through the above The integration of algorithms can intelligently infer the user's location, especially in the case of signal loss or large positioning errors, to maintain the continuity and accuracy of positioning. This method can significantly improve the stability of the data plane location service provided by the eSIM card and effectively reduce power consumption and latency; Fourth, through the combination of distributed computing and edge computing, the invention shares computing tasks at all levels, thereby reducing the pressure on the central server, and can quickly process data at the edge of the network, reduce latency, and improve positioning accuracy and real-time performance. The specific implementation of the combination of distributed computing and edge computing ensures the continuity and accuracy of location services in complex environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 A flow chart of a method for providing data plane location services based on an eSIM card; Figure 2 A module diagram of a device for providing data plane location services based on an eSIM card; Figure 3 It is a schematic diagram of the structure of the electronic device of the present invention; Figure 4 It is a schematic diagram of the computer-readable storage medium structure of the present invention. DETAILED DESCRIPTION

[0039] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0040] eSIM technology: eSIM technology allows switching mobile network operators through remote configuration without replacing the physical SIM card. This technology is widely used in mobile devices, Internet of Things (IoT) devices and other fields.

[0041] Data Plane: The data plane is the part of the network responsible for actual data transmission. Unlike the control plane, the control plane is responsible for the transmission of signaling and control information, while the data plane handles the actual user data flow.

[0042] Location-based services: Location-based services (LBS) provide related services based on the location information of the device, such as navigation, tracking, and location-based advertising.

[0043] Embodiment 1: Reference Figure 1 As shown, a method for providing data plane location service based on an eSIM card includes: Acquire multi-source mobile positioning data, and determine the geographic location of the device by analyzing data plane information according to data communication between an eSIM card in the device and the multi-source mobile positioning data; the multi-source mobile positioning data includes GPS data, Wi-Fi positioning data, Bluetooth beacon auxiliary data, cellular network signal positioning data and data plane information; Specifically, GPS data fusion: When the device turns on GPS, the high-precision location information provided by GPS is used first, and combined with other data sources to enhance the stability of positioning.

[0044] Wi-Fi positioning data: In indoor environments or where GPS signals are weak, Wi-Fi hotspot signal strength and MAC addresses are used for auxiliary positioning. Combined with the positioning database in the network, the device location can be inferred through the geographical distribution of Wi-Fi.

[0045] Bluetooth beacon auxiliary data: Use surrounding Bluetooth beacons (such as iBeacon) for close-range precise positioning. Especially in indoor environments, Bluetooth beacons can provide more accurate location information than Wi-Fi.

[0046] Cellular network signal (Cell-ID) positioning data: Utilizes cellular network information such as base station signal (Cell-ID), signal strength and time difference (RTT) to perform large-scale coarse positioning as an auxiliary to other positioning methods.

[0047] Construct a dynamic frequency adjustment and noise filtering algorithm to dynamically adjust the frequency used and the frequency of data collection and perform noise filtering by analyzing the signal strength, signal stability and historical location information of the device; Build intelligent location inference algorithms to determine the geographic location of devices based on traffic data from data plane information analysis, and intelligently optimize and infer location services by learning user behavior patterns, geographic area characteristics, and environmental variables; According to the data communication between the eSIM card and the multi-source mobile positioning data, distributed computing and edge computing are obtained, wherein the distributed computing distributes part of the location computing and data processing tasks among the device, the network node and the central server, the device processes the local data in real time and performs preliminary positioning calculation, the network node processes the positioning data of multiple devices in the area, and finally sends the comprehensive results to the central server; Specifically, in order to improve positioning accuracy and reduce errors, the present invention discloses a dynamic frequency adjustment and noise filtering algorithm. The algorithm dynamically adjusts the frequency used and the frequency of data collection, and performs noise filtering by analyzing signal strength, signal stability and historical location information.

[0048] The edge computing processes real-time data at the edge of the network based on the computing power of device access points or network nodes.

[0049] Specifically, the dynamic frequency adjustment dynamically adjusts the frequency of positioning data collection according to the motion state of the device, signal strength, and distribution of signal sources, and specifically includes: Motion state detection: The motion state of the device is determined by the data of the accelerometer and gyroscope, and the modulus of acceleration of the device is calculated. , the expression is: ; in, The equipment is , , Acceleration in the axis direction; The motion state of the device includes a stationary state, a low-speed movement, and a high-speed movement; Static state: When Less than a certain threshold for a long time (For example ), the device is judged to be in a stationary state; Slow speed movement: If it fluctuates around the threshold but is small overall, it is judged as slow movement; High-speed movement: If the duration is greater than a certain threshold, it is considered as high-speed movement; Frequency adjustment strategy: adjust the sampling frequency according to the detected motion state of the device ; Quiescent state: Reduce sampling frequency to save power: ; Slow-speed movement: appropriately increase the sampling frequency to ensure the continuity of positioning: ; High-speed movement: significantly increase sampling frequency to improve positioning accuracy: ; Signal strength analysis: The signal strength RSSI (Received Signal Strength Indicator) is used to determine the signal quality and adjust the sampling frequency.

[0050] Strong signal: When RSSI is greater than a certain threshold , the sampling frequency can be reduced.

[0051] ; Weak signal: When RSSI is less than the threshold , increase the sampling frequency.

[0052] ; Comprehensive frequency adjustment: final sampling frequency The expression is: ; in, : is the fundamental frequency, : is an adjustment factor based on the state of motion, is an adjustment factor based on signal strength.

[0053] Specifically, the noise filtering algorithm filters the noise in the multi-source mobile positioning data according to the multipath effect of the multi-source mobile positioning data and the erroneous position information caused by the instantaneous signal interference, and specifically includes: Based on the Kalman filter algorithm, it provides the best estimate by combining historical data and current observations; Assume the position status is , the observed value is , then the update process of Kalman filter is as follows: Status prediction: ; Among them, A is the state transfer matrix, B is the control input matrix, is the control quantity.

[0054] Error covariance prediction: ; in, is the forecast error covariance matrix, is the process noise covariance matrix.

[0055] Kalman gain calculation: ; in, is the observation matrix, is the observation noise covariance matrix.

[0056] Status Update: ; Error covariance update: ; Through Kalman filtering, the system can effectively eliminate the instantaneous positioning error caused by noise and provide smooth position information; Machine learning anomaly detection algorithms: Machine learning anomaly detection algorithms based on historical data, including isolation forest and local anomaly factor; Isolation Forest: Isolate outliers by building random decision trees and determine whether the data is abnormal based on the anomaly score; Local anomaly factor: Calculate the local density of each data point and compare it with the density of surrounding data points to identify anomalies with significantly different densities; For example, for each new location data , its local anomaly factor can be calculated :

[0057] in, yes The k nearest neighbors of Represents the average distance from point x to its k nearest neighbors.

[0058] when When it is significantly greater than 1, the data is judged as an outlier and filtered out.

[0059] By combining dynamic frequency adjustment and noise filtering algorithms, the present invention can adaptively adjust the positioning frequency in different environments. At the same time, through Kalman filtering and machine learning algorithms, it can significantly reduce the noise and errors in the positioning data, and ultimately improve the accuracy and stability of the data plane location service provided by the eSIM card.

[0060] For example, when the signal is weak or the device is moving at high speed, the acquisition frequency is increased to improve positioning accuracy.

[0061] Noise filtering algorithm: Identify and filter abnormal data and noise through machine learning and statistical analysis techniques.

[0062] For example, the historical location information and the smoothing of the movement trajectory can be used to filter out the erroneous location information caused by the multipath effect or the instantaneous signal interference.

[0063] Specifically, by learning user behavior patterns, geographic area characteristics and environmental variables, location services are intelligently optimized and inferred, including: The learning of user behavior patterns and geographic area features includes user location sequence modeling, state transition probability matrix A, observation probability matrix B and initial state probability vector and time series forecasting.

[0064] The learning goal of learning the user's behavior pattern is to extract the user's daily activity pattern by analyzing the user's historical location information, so as to predict his or her possible location at a future moment.

[0065] The user location sequence modeling assumes that the user's location sequence in T time steps is ,in When the user is: ; The state transition probability matrix A: represents the probability of a user transferring from one location to another: ; The observation probability matrix B represents the probability of observing a certain feature (such as Wi-Fi signal, GPS coordinates) at a specific location: ; The initial state probability vector : represents the probability that the user is initially in each position: ; The forward-backward algorithm is used to calculate the possible state (position) sequence of the user in the future, and the Viterbi algorithm is used to find the most likely state sequence.

[0066] The time series prediction: uses a long short-term memory network (LSTM) to predict the user's future location information. LSTM can effectively capture patterns in long time series data.

[0067] The input sequence is , the output is the predicted position at the future moment: ; in, is the time step of the prediction, is the predicted future position.

[0068] Artificial intelligence is used to analyze users’ daily activity patterns and geographic paths to infer possible location information. For example, artificial intelligence can learn users’ commuting routes, infer in advance where users may be at a certain time, and optimize the parameters of the positioning algorithm.

[0069] Environmental variable analysis: AI can adjust the priority and positioning methods of positioning services based on environmental variables such as weather, time, and regional congestion. For example, on rainy days, AI can prioritize the use of indoor Wi-Fi and Bluetooth beacons for positioning to avoid errors caused by GPS signal attenuation.

[0070] Intelligent location inference: Combining user behavior patterns and environmental variables, AI can infer location when the signal is lost for a short period of time, and smooth the path after the signal is restored to ensure positioning continuity.

[0071] Specifically, the environmental variables include weather, time, and traffic conditions, including: A multimodal deep learning model is constructed, wherein the multimodal deep learning model is a multimodal neural network that fuses environmental variables with the user's historical location data.

[0072] The input vector of the multimodal neural network includes the user position sequence and the environment variable vector ,in Including weather, time, and traffic conditions; The output of the multimodal deep learning model is the optimized position information: ; The multimodal deep learning model structure is: ; in, is the activation function, is the weight matrix, is the bias, vector, Indicates a connection operation.

[0073] Smart location inference: In practical applications, when the user's location signal is lost, AI can perform location inference based on the aforementioned behavioral patterns and environmental variables to maintain positioning continuity.

[0074] Position inference algorithm: In the case of signal loss, the user's location is inferred through Bayesian filtering. Bayesian filtering combines the prior probability with newly acquired information (such as environmental variables) to perform a posteriori inference of the location.

[0075] Prediction Steps: ; Update steps: In the new observation Update the posterior probabilities when available:

[0076] in, is the new observation model, which represents the position Observed probability.

[0077] Path Smoothing: After the signal is restored, in order to avoid sudden displacement jumps, spline interpolation or Kalman filtering is used to smooth the path.

[0078] Among them, spline interpolation: Assume that the path during the signal loss period is , the position after signal recovery is . Use spline interpolation to find a smooth transition path: ; Kalman filter: The Kalman filter smoothes the path by recursively estimating the state variables.

[0079] Through the above The integration of algorithms can intelligently infer the user's location, especially in the case of signal loss or large positioning errors, to maintain the continuity and accuracy of positioning. This method can significantly improve the stability of the data plane location service provided by the eSIM card and effectively reduce power consumption and latency; Specifically, in order to solve the real-time problem of data processing and reduce the burden on the central server, the distributed computing and edge computing are obtained, and a distributed computing model is constructed. The distributed computing model includes device-side computing, network node computing (such as base station) and central server computing. The edge computing model includes edge node processing and edge intelligent optimization.

[0080] In the distributed computing model, location calculation tasks are decomposed and distributed to different levels, and processed on the device side, network nodes (such as base stations) and central servers respectively.

[0081] Device-side calculation: Each device can process its own sensor data (such as GPS and Wi-Fi signal strength) in real time to make a preliminary location estimate.

[0082] Assume that the signal data collected by the device is (including timestamp, signal strength, noise, etc.), the location estimate can be calculated using the following weighted average algorithm: ; in, is a position estimate calculated based on each signal source, is the corresponding weight, determined based on signal strength or confidence: ; It represents the variance of the signal and reflects the stability of the signal.

[0083] Network node calculation: A network node (such as a base station) receives preliminary location estimates from multiple devices and performs an aggregate calculation within the area.

[0084] Assume that a base station serves an area with devices, and the initial estimated position of each device is , then the base station can calculate the aggregated position estimate within the area:

[0085] Among them, wj is the device The weight can be determined based on factors such as signal strength, device credibility, and historical location accuracy.

[0086] Central server computing: The central server collects location information from multiple network nodes and combines data from a larger range to make a final comprehensive location estimate. This process can be done through the Bayesian Fusion method to integrate information from different nodes: ; Where L is the final position, D is the dataset provided by all network nodes, P(L) is the prior distribution, and P(DL) is the likelihood function, calculated based on the data received from the nodes.

[0087] Edge computing model: The edge computing model uses the computing power of access points or base stations to process data at the edge of the network, thereby reducing transmission delays and improving response speed.

[0088] Edge Node Processing At edge nodes (such as base stations), high-precision positioning is performed using the signal arrival time difference.

[0089] Assume that a device transmits a signal to three base stations, and the time difference between base station i and base station j receiving the signal is , the device's position is estimated to be: ; in, is the actual location of the device, and Base Station and location, is the signal propagation speed.

[0090] Edge intelligence optimization: To further improve positioning accuracy, edge nodes can use machine learning algorithms, such as gradient boosted decision trees (GBDT) or convolutional neural networks (CNN), to analyze historical and real-time data to predict and optimize the user's location.

[0091] Assume that the input data is X (including historical location, environmental parameters, signal data, etc.), and the output is the optimized location information : ; in, Represents a machine learning model.

[0092] Distributed and edge computing work together: In practical applications, distributed computing and edge computing work together. The device side, network nodes, edge nodes, and central servers coordinate through low-latency communication to ensure the real-time and accuracy of positioning.

[0093] Data synchronization and consistency guarantee: Use Paxos or Raft consensus algorithms to ensure data consistency between distributed computing nodes: ; During the final position calculation, if the consensus of most nodes is passed, the position estimate is updated.

[0094] Feedback loop for edge computing: The computation results of the edge node can directly optimize the position estimate on the device through a feedback loop: ; in, is the adjustment factor, which is determined based on the signal quality between the device and the edge node.

[0095] By combining distributed computing with edge computing, the invention shares computing tasks at all levels, thereby reducing the pressure on the central server, and can quickly process data at the edge of the network, reduce latency, and improve positioning accuracy and real-time performance. The specific implementation of the combination of distributed computing and edge computing ensures the continuity and accuracy of location services in complex environments.

[0096] Embodiment 2: Reference Figure 2 As shown, based on the technology of the first embodiment, the present invention also includes an enhanced privacy and security protection mechanism to ensure the security of location information during transmission and storage, specifically including: Use strong encryption protocols on the data plane to encrypt and transmit location information; During the storage and analysis of location data, anonymization and de-identification are applied so that the user's identity information is not directly associated with the location information; Provides a detailed privacy control panel that allows users to choose to view and manage historical location information.

[0097] Specifically, a strong encryption protocol (such as TLS 1.3 or higher) is used on the data plane to encrypt and transmit location information to prevent the data from being intercepted or tampered with during transmission.

[0098] In the process of storing and analyzing location data, anonymization and de-identification technology is applied to ensure that the user's identity information is not directly associated with the location information. Location information will only be used for personalized services with the user's authorization.

[0099] Provides a detailed privacy control panel that allows users to choose which apps or services can access their location information and set specific usage scenarios or time periods. Users can also view and manage historical location information at any time.

[0100] In other embodiments, it also includes: when the device is stationary for a long time or the user explicitly indicates that positioning services are not needed, the system automatically enters a low power consumption mode, suspends frequent data collection and processing, and extends the battery life of the device.

[0101] AI is used to analyze device usage scenarios and user behavior, and intelligently adjust the frequency and accuracy of positioning services. For example, when the user is charging, the device can increase the frequency and accuracy of positioning services; when the battery is low, the device will automatically reduce the positioning frequency or start positioning services only when necessary.

[0102] Combined with the power management function of the hardware, the CPU frequency and sensor working status of the device are dynamically adjusted to achieve the best power consumption balance. For example, when the device is in an area with poor network coverage, the priority of the positioning service is automatically reduced or low-power positioning methods are temporarily used.

[0103] In order to solve the standardization and compatibility issues, the present invention promotes the global standardization of eSIM card-based positioning services and enhances interoperability.

[0104] Cooperate with international standardization organizations (such as 3GPP and GSMA) to promote the formulation and improvement of eSIM card-based positioning service standards to ensure compatibility between different devices, operators and regions.

[0105] Design universal API interfaces and protocols to enable different types of devices and networks to work seamlessly together and provide a consistent location-based service experience. For example, ensure that eSIM devices of different brands can smoothly perform location-based services in different countries and on operators’ networks.

[0106] Testing and Optimization In order to ensure the practical application effect of the solution, the present invention has designed a comprehensive testing and optimization process.

[0107] Laboratory testing: Conduct multiple rounds of experiments in a controlled environment to test the actual effects of technologies such as multi-source data fusion, dynamic frequency adjustment, and AI inference, and continuously optimize the algorithm.

[0108] Field testing: Conduct field tests in a variety of real-world scenarios (such as cities, rural areas, indoors, subways, etc.) to collect positioning data and adjust system parameters to adapt to the challenges of various environments.

[0109] User feedback and continuous optimization: Through real user feedback, we continuously optimize the user experience and accuracy of positioning services. We establish a data analysis platform to monitor the performance of the system in real time and continuously update and optimize it. In summary, the advantages of the present invention are: through innovative means such as privacy protection and adaptive power consumption management, an advanced method for providing data plane location services based on eSIM cards is proposed. The invention not only solves key problems in the prior art such as positioning accuracy, privacy protection, power consumption management, network dependence, and standardization, but also provides users with a more accurate, safer, and more efficient positioning service experience.

[0110] The present invention introduces a multi-level intelligent location optimization mechanism, including dynamic location estimation at the device end, network nodes and edge nodes, and prediction and optimization models based on machine learning. This multi-level optimization mechanism ensures the accuracy of location estimation and can be dynamically adjusted to adapt to different environments and conditions.

[0111] Significant progress: Dynamic adaptive capability: Through multi-level location estimation and optimization, the system can adjust the positioning strategy in real time according to environmental changes (such as weather, number of devices, network conditions, etc.), avoiding the limitations of fixed algorithms in existing technologies.

[0112] Improve positioning accuracy: Machine learning algorithms that combine historical and real-time data can continuously optimize position estimates, especially in complex environments or those with severe signal interference, greatly improving positioning accuracy.

[0113] For example: In an environment like an underground parking lot where GPS signals are poor, existing technologies may have difficulty providing accurate positioning services. In the present invention, edge nodes can use multi-frequency TDOA algorithms and machine learning models to accurately calculate the device location from surrounding base station signals, providing high-precision positioning services even when GPS fails.

[0114] 3. Efficient resource utilization and energy-saving mechanism: Creative breakthroughs: Through distributed computing, edge computing and intelligent optimization, the present invention significantly improves the utilization rate of system resources, and at the same time introduces an energy-saving mechanism to reduce the consumption of computing and communication resources when the device does not need to frequently update location information.

[0115] Significant progress: Reduced energy consumption: By intelligently adjusting the location update frequency and computing intensity, the present invention reduces the energy consumption of the device side and extends the battery life without affecting the service quality.

[0116] Optimize the use of network resources: Since part of the computing tasks are completed in the network nodes or edge nodes, the present invention reduces long-distance data transmission and reduces the occupancy of network bandwidth.

[0117] For example: On a device that does not move for a long time (such as a smart home device), the existing technology may frequently update the location information, wasting computing and communication resources. In the present invention, the device can use an intelligent algorithm to determine whether the location information needs to be updated, reducing unnecessary computing and communication, thereby reducing energy consumption.

[0118] 4. Improvements in data consistency and fault tolerance mechanisms: Creative breakthroughs: In distributed systems, data consistency and fault tolerance are key issues. This invention introduces consistency algorithms such as Paxos or Raft to ensure data consistency between distributed computing nodes. Even if some nodes fail, the system can still maintain service continuity and accuracy. Significant improvements: Improve the fault tolerance of the system: Through the consistency algorithm, the present invention coordinates between multiple computing nodes, so that the system can continue to work normally even when a node fails.

[0119] Enhanced data security: The application of consistency algorithms not only ensures the accuracy of data, but also prevents positioning errors caused by data inconsistency, thereby improving the reliability of the system.

[0120] For example: In the case of natural disasters or partial network interruption, the existing technology may cause the overall positioning service to be interrupted or erroneous due to the failure of some nodes. However, the consistency algorithm in the present invention ensures that the system can still provide accurate location information services even when some nodes fail, ensuring that the user experience is not affected.

[0121] Embodiment three: A device for providing data plane location services based on an eSIM card, comprising: A multi-source data fusion positioning module is used to obtain multi-source mobile positioning data, and determine the geographical location of the device by analyzing data plane information according to data communication between the eSIM card in the device and the multi-source mobile positioning data; A dynamic frequency adjustment and noise module is used to construct a dynamic frequency adjustment and noise filtering algorithm, dynamically adjust the frequency used and the frequency of data collection, and perform noise filtering by analyzing the signal strength, signal stability and historical location information of the device; Intelligent location inference module, which is used to build intelligent location inference algorithms, determine the geographical location of the device based on the traffic data of the data plane information, and intelligently optimize and infer location services by learning the user's behavior patterns, geographic area characteristics and environmental variables; A distributed computing module, used to obtain distributed computing and edge computing according to the data communication between the eSIM card and the multi-source mobile positioning data, wherein the distributed computing distributes part of the position calculation and data processing tasks among the device, the network node and the central server, processes the local data in real time according to the device and performs preliminary positioning calculation, and the network node processes the positioning data of multiple devices in the area, and finally sends the comprehensive results to the central server; The edge module is used for edge computing to process real-time data at the edge of the network according to the computing power of the device access point or network node.

[0122] The foregoing Figure 1The various variations and specific examples of the method for providing data plane location services based on an eSIM card in Example 1 are also applicable to a device for providing data plane location services based on an eSIM card in this embodiment. Through the above detailed description of the method for providing data plane location services based on an eSIM card, those skilled in the art can clearly understand the implementation method of the device for providing data plane location services based on an eSIM card in this embodiment. Therefore, for the sake of brevity of the specification, it will not be described in detail here.

[0123] Furthermore, the method or system according to the embodiment of the present application can also be Figure 3 The electronic device architecture shown in FIG. Figure 3 As shown, the electronic device 500 may include a bus 501, one or more CPUs 502, a read-only memory (ROM) 503, a random access memory (RAM) 504, a communication port 505 connected to a network, an input / output component 506, a hard disk 507, etc. The storage device in the electronic device 500, such as the ROM 503 or the hard disk 507, may store a method for providing a data plane location service based on an eSIM card provided in the present application. The electronic device 500 may also include a user interface 508. Of course, Figure 3 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different devices. Figure 3 One or more components of an electronic device are shown.

[0124] Figure 4 Schematic diagram of a computer-readable storage medium structure provided by an embodiment of the present application. Figure 4 As shown, a computer-readable storage medium 600 according to an embodiment of the present application is shown. Computer-readable instructions are stored on the computer-readable storage medium 600. When the computer-readable instructions are executed by the processor, the path planning method according to the embodiment of the present application described with reference to the above figures can be executed. The storage medium 600 includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0125] The methods, apparatuses, and devices of the present application may be implemented in many ways. For example, the methods, apparatuses, and devices of the present application may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of steps for the method is for illustration only, and the steps of the method of the present application are not limited to the order specifically described above unless otherwise specified. In addition, in some embodiments, the present application may also be implemented as programs recorded in a recording medium, which include machine-readable instructions for implementing the method according to the present application. Therefore, the present application also covers recording media storing programs for executing the method according to the present application.

[0126] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. A method for providing data plane location services based on an eSIM card, characterized in that: include: Acquire multi-source mobile positioning data, and determine the geographic location of the device by analyzing data plane information based on data communication between an eSIM card in the device and the multi-source mobile positioning data; The multi-source mobile positioning data includes GPS data, Wi-Fi positioning data, Bluetooth beacon assistance data, cellular network signal positioning data and data plane information; Construct a dynamic frequency adjustment and noise filtering algorithm to dynamically adjust the frequency used and the frequency of data collection and perform noise filtering by analyzing the signal strength, signal stability and historical location information of the device; Build intelligent location inference algorithms to determine the geographic location of devices based on traffic data from data plane information analysis, and intelligently optimize and infer location services by learning user behavior patterns, geographic area characteristics, and environmental variables; According to the data communication between the eSIM card and the multi-source mobile positioning data, distributed computing and edge computing are obtained, wherein the distributed computing distributes part of the location computing and data processing tasks among the device, the network node and the central server, the device processes the local data in real time and performs preliminary positioning calculation, the network node processes the positioning data of multiple devices in the area, and finally sends the comprehensive results to the central server; The edge computing processes real-time data at the edge of the network based on the computing power of device access points or network nodes.

2. The method for providing data plane location services based on an eSIM card according to claim 1, characterized in that: The dynamic frequency adjustment dynamically adjusts the frequency of positioning data collection according to the motion state of the device, signal strength and distribution of signal sources, specifically including: Motion state detection: The motion state of the device is determined by the data of the accelerometer and gyroscope, and the modulus of acceleration of the device is calculated. , the expression is: ; in, The equipment is , , Acceleration in the axis direction; The motion state of the device includes a stationary state, a low-speed movement, and a high-speed movement; Frequency adjustment strategy: adjust the sampling frequency according to the detected motion state of the device ; Signal strength analysis: judge the signal quality through the signal strength RSSI (received signal strength indicator) and adjust the sampling frequency; Comprehensive frequency adjustment: final sampling frequency The expression is: ; in, is the fundamental frequency, is an adjustment factor based on the state of motion, is an adjustment factor based on signal strength.

3. The method for providing data plane location service based on eSIM card according to claim 2, characterized in that: The noise filtering algorithm filters the noise in the multi-source mobile positioning data according to the multipath effect of the multi-source mobile positioning data and the erroneous position information caused by the instantaneous signal interference; Specifically include: Based on the Kalman filter algorithm, it provides the best estimate by combining historical data and current observations; Machine learning anomaly detection algorithm: Machine learning anomaly detection algorithm based on historical data, including isolation forest and local anomaly factor.

4. The method for providing data plane location service based on eSIM card according to claim 1, characterized in that: By learning user behavior patterns, geographic area characteristics and environmental variables, intelligent optimization and inference of location services are carried out, including: The learning of user behavior patterns and geographic area features includes user location sequence modeling, state transition probability matrix A, observation probability matrix B and initial state probability vector and time series forecasting.

5. The method for providing data plane location service based on eSIM card according to claim 4, characterized in that: The environmental variables include weather, time, and traffic conditions, specifically including: Constructing a multimodal deep learning model, wherein the multimodal deep learning model is a multimodal neural network that fuses environmental variables with the user's historical location data; The input vector of the multimodal neural network includes the user position sequence and the environment variable vector ,in Including weather, time, and traffic conditions; The output of the multimodal deep learning model is the optimized position information: ; The multimodal deep learning model structure is: ; in, is the activation function, is the weight matrix, is the bias, vector Indicates a connection operation.

6. The method for providing data plane location service based on eSIM card according to claim 1, characterized in that: The distributed computing and edge computing are obtained, and a distributed computing model is constructed. The distributed computing model includes device-side computing, network node computing and central server computing. The edge computing model is constructed including edge node processing and edge intelligent optimization.

7. The method for providing data plane location service based on eSIM card according to claim 1, characterized in that: The method also includes an enhanced privacy and security protection mechanism to ensure that the device location information is secure during transmission and storage, including: Use strong encryption protocols on the data plane to encrypt and transmit device location information; During the storage and analysis of location data, anonymization and de-identification are applied so that the user's identity information is not directly associated with the location information; Provides a detailed privacy control panel that allows users to choose to view and manage historical location information.

8. The device for providing data plane location service based on an eSIM card according to claim 1, applied to the method for providing data plane location service based on an eSIM card according to any one of items 1 to 7, characterized in that: include: A multi-source data fusion positioning module is used to obtain multi-source mobile positioning data, and determine the geographical location of the device by analyzing data plane information according to data communication between the eSIM card in the device and the multi-source mobile positioning data; A dynamic frequency adjustment and noise module is used to construct a dynamic frequency adjustment and noise filtering algorithm, dynamically adjust the frequency used and the frequency of data collection, and perform noise filtering by analyzing the signal strength, signal stability and historical location information of the device; Intelligent location inference module, which is used to build intelligent location inference algorithms, determine the geographical location of the device based on the traffic data of the data plane information, and intelligently optimize and infer location services by learning the user's behavior patterns, geographic area characteristics and environmental variables; A distributed computing module, used to obtain distributed computing and edge computing according to the data communication between the eSIM card and the multi-source mobile positioning data, wherein the distributed computing distributes part of the position calculation and data processing tasks among the device, the network node and the central server, processes the local data in real time according to the device and performs preliminary positioning calculation, and the network node processes the positioning data of multiple devices in the area, and finally sends the comprehensive results to the central server; The edge module is used for edge computing to process real-time data at the edge of the network according to the computing power of the device access point or network node.

9. An electronic device, characterized in that: include: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute a method for providing data plane location services based on an eSIM card as described in any one of claims 1-7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, a method for providing data plane location services based on an eSIM card according to any one of claims 1 to 7 is implemented.

Citation Information

Patent Citations

  • GIS device state intelligent monitoring system and method based on edge computing technology

    CN110401262A

  • Intelligent health care Internet of Things health monitoring method based on edge calculation

    CN118507080A

  • Non-contact multi-mode parameter detection and deep learning driven intelligent detection system

    CN118737458A

  • Adaptive multimodal safety systems and methods

    US11676291B1

Cited By

  • RFID (Radio Frequency Identification Device) and GPS (Global Positioning System) fused pet identity recognition and positioning system and method

    CN121276559A

  • Pet identity recognition and positioning system and method based on RFID and GPS fusion

    CN121276559B

  • Embedded light emitting method and system for intelligent card

    CN122395784A