Positioning monitoring method and device supporting base station and satellite dual-mode switching and medium

Abstract

The invention provides a positioning monitoring method and device supporting base station and satellite dual-mode switching and a medium, and belongs to the technical field of positioning monitoring. The positioning monitoring method comprises the following steps: acquiring a base station signal and a satellite signal; analyzing the signal quality of the base station signal and the satellite signal in real time by using a dynamic signal evaluation model based on deep learning; selecting an optimal signal conforming to the current motion state from the base station signal and the satellite signal according to the signal quality by using a self-adaptive weight adjustment algorithm; and when the current signal source of the positioning monitoring equipment is not the optimal signal, switching the current signal source to the optimal signal by using a seamless switching algorithm based on space-time joint calibration. According to the invention, the problems of low reliability and high time delay of a positioning scheme in the prior art can be solved.

Description

Technical Field

[0001] This application belongs to the field of positioning monitoring technology, specifically relating to a positioning monitoring method, device, and medium that supports dual-mode switching between base stations and satellites. Background Technology

[0002] Currently, most positioning monitoring equipment on the market relies on a single signal source, such as base station-dependent monitoring equipment and pure satellite positioning equipment. These types of equipment face significant challenges in practical applications. Specifically, base station-dependent monitoring equipment performs poorly in areas with weak coverage, such as remote mountainous areas, oceans, and deserts. Pure satellite positioning equipment also has significant drawbacks; in urban environments, it is severely affected by tall buildings blocking the signal. Tests show that the positioning availability of pure BeiDou equipment in densely populated urban areas is only 78%, and the continuous power consumption of the satellite module, up to 2W, severely limits the equipment's battery life.

[0003] To overcome the aforementioned shortcomings of single-signal-source positioning and monitoring equipment, although some manufacturers have attempted to adopt a base station + satellite dual-mode positioning solution, several technical bottlenecks remain. Traditional switching technologies employ a sequential search strategy, resulting in high latency of 500ms to 1 second. This can lead to significant errors in high-speed moving scenarios; for example, a 1-second delay at a vehicle speed of 120km / h translates to a positioning deviation of 33.3 meters. Existing fixed-threshold switching strategies are ill-suited to signal fluctuations in real-world environments. For instance, a logistics tracking device switched 3-5 times per minute at tunnel entrances and exits due to signal jitter, affecting both positioning continuity and significantly increasing power consumption. These technical deficiencies have particularly pronounced impacts in specialized fields. Taking geological disaster monitoring as an example, complex mountainous terrain often leads to satellite signal loss. Data from a landslide monitoring point shows that traditional equipment achieves less than 55% effective data acquisition during the rainy season. Emergency communication capabilities are also worrisome; the average latency of existing short message transmissions is 38 seconds, far exceeding the 10-second warning timeliness requirement.

[0004] In summary, there is an urgent need for a new type of dual-mode positioning and monitoring device with high reliability (availability > 99%), low latency (switching < 100ms), and intelligent power consumption management to meet the stringent requirements of fields such as emergency communication and intelligent transportation, and to break through current technological bottlenecks. Summary of the Invention

[0005] This application aims to provide a positioning monitoring solution that supports dual-mode switching between base stations and satellites. It seeks to address the problems of low reliability and high latency in existing dual-mode positioning monitoring equipment, which fails to meet the needs of fields such as emergency communication and intelligent transportation.

[0006] According to a first aspect of this application, embodiments of this application provide a positioning monitoring method supporting dual-mode switching between base stations and satellites, comprising:

[0007] Acquire base station signals and satellite signals;

[0008] A deep learning-based dynamic signal evaluation model is used to analyze the signal quality of base station signals and satellite signals in real time.

[0009] An adaptive weight adjustment algorithm is used to select the optimal signal that matches the current motion state from base station signals and satellite signals based on signal quality.

[0010] When the current signal source of the positioning and monitoring device is not the optimal signal, a seamless switching algorithm based on spatiotemporal joint calibration is used to switch the current signal source to the optimal signal.

[0011] Preferably, after the step of switching the current signal source to the optimal signal using a seamless switching algorithm based on spatiotemporal joint calibration, the above-mentioned positioning and monitoring method further includes:

[0012] Using intelligent power management strategies, the positioning frequency and power consumption mode of the positioning monitoring device are dynamically adjusted according to the current motion state and the current application environment.

[0013] The steps for dynamically adjusting the positioning frequency and power consumption mode of a positioning monitoring device using an intelligent power management strategy based on the current motion state and application environment include:

[0014] Using intelligent power consumption management strategies, the power consumption operation modes of the positioning monitoring equipment are set to normal mode, energy-saving mode, and emergency mode; among them...

[0015] In normal mode, the positioning monitoring device is set to the normal frequency for positioning base stations and the normal frequency for positioning satellites.

[0016] In energy-saving mode, carrier phase observation of positioning monitoring equipment is turned off, and dead reckoning (DR) is used for auxiliary monitoring.

[0017] In emergency mode, full-band scanning and short message backup transmission are enabled.

[0018] Preferably, in the above positioning and monitoring method, the step of switching the current signal source to the optimal signal using a seamless switching algorithm based on spatiotemporal joint calibration includes:

[0019] The TDD time alignment algorithm is used to perform TA compensation for base station signals and synchronization time calibration for satellite signals.

[0020] A real-time conversion model between the WGS-84 coordinate system and the local coordinate system was established using a spatial calibration algorithm.

[0021] Using a real-time conversion model, base station signals and satellite signals are placed in the local coordinate system corresponding to the positioning and monitoring equipment;

[0022] When it is necessary to switch between base station signals and satellite signals, the time-aligned base station signals or satellite signals are switched to the current signal source in the local coordinate system.

[0023] Preferably, in the above positioning and monitoring method, the step of switching the time-aligned base station signal or satellite signal to the current signal source in the local coordinate system includes:

[0024] Acquire the inertial navigation data of the positioning and monitoring equipment itself;

[0025] Using the federated Kalman filter algorithm:

[0026] FKF=α×KF_base+β×KF_sat+γ×KF_imu

[0027] By fusing inertial navigation data, base station ranging from base station signals, and satellite ranging from satellite signals, fused ranging data is obtained. Here, KF_base represents base station ranging from base station signals, KF_sat represents satellite ranging from satellite signals, KF_imu represents inertial navigation data, FKF represents fused ranging data, and α, β, and γ represent the corresponding weights of each item.

[0028] Using a unified spatiotemporal benchmark algorithm:

[0029]

[0030] Aligning inertial navigation data, base station signals, and satellite signals with a spatiotemporal reference, wherein, Indicates base station signal, Indicates satellite signal, Let α represent inertial navigation data, where α, β, and γ represent the weights of each item, and α + β + γ = 1.

[0031] Preferably, in the above positioning monitoring method, the step of using a deep learning-based dynamic signal evaluation model to analyze the signal quality of base station signals and satellite signals in real time includes:

[0032] Construct a deep learning-based signal quality assessment model:

[0033] Q=α×(S / N)+β×(1-BER)+γ×C / N0+δ×(1-|Δf| / f max );

[0034] Where Q represents the overall quality index, S represents the signal power, N represents the noise power, S / N represents the signal-to-noise ratio, BER represents the bit error rate, C represents the carrier power, NO represents the noise power spectral density, C / N0 represents the carrier-to-noise power density ratio, Δf represents the frequency offset, and f maxΔf| / fmax represents the maximum allowable frequency offset, |Δf| / fmax represents the normalized frequency offset, and α, β, γ, δ represent the weighting coefficients of the above variables, respectively.

[0035] Using a signal quality assessment model, the comprehensive quality index Q of base station signals and satellite signals is calculated in real time, and the comprehensive quality index is used to assess the signal quality of base station signals and satellite signals.

[0036] Preferably, in the above positioning monitoring method, the step of using a signal quality assessment model to calculate the comprehensive quality index Q of the base station signal and satellite signal in real time, and using the comprehensive quality index to assess the signal quality of the base station signal and satellite signal, includes:

[0037] A training dataset is generated using measured data of base station signals and satellite signals from various scenarios. The training dataset includes signal quality features.

[0038] The signal quality features in the measured dataset are input into the signal quality assessment model to train the signal quality assessment model with a dual DQN network architecture.

[0039] The evaluation network using the signal quality assessment model evaluates the overall quality index corresponding to the measured dataset;

[0040] The target network using the signal quality assessment model is used to correct the overall quality index;

[0041] Repeatedly train the signal quality assessment model until the error function between the target network and the assessment network converges;

[0042] The signal quality characteristics of the base station signal and satellite signal obtained in real time are input into the signal quality assessment model to obtain the signal quality of the base station signal and satellite signal.

[0043] Preferably, in the above positioning and monitoring method, the step of using an adaptive weight adjustment algorithm to select the optimal signal from base station signals and satellite signals that matches the current motion state based on signal quality includes:

[0044] When the signal quality of the base station signal is greater than or equal to the first quality threshold, the base station signal is selected as the optimal signal.

[0045] When the rate of degradation of the base station signal quality is greater than or equal to a predetermined degradation threshold, the satellite signal is time-aligned and the optimal signal is hot-switched to the satellite signal.

[0046] When the signal quality of the base station signal is less than or equal to the second quality threshold, the satellite signal is selected as the optimal signal.

[0047] When an LTE CRS signal is detected, the optimal signal will be hot-switched to the base station signal.

[0048] According to a second aspect of this application, this application also provides a positioning monitoring device that supports dual-mode switching between base stations and satellites, comprising:

[0049] Reconfigurable antenna array, signal quality assessment processor, and RF switching switch; among which,

[0050] Reconfigurable antenna arrays are used to acquire base station signals and satellite signals;

[0051] The signal quality assessment processor is used to analyze the signal quality of base station signals and satellite signals in real time using a deep learning-based dynamic signal assessment model. It uses an adaptive weight adjustment algorithm to select the optimal signal from the base station signals and satellite signals that matches the current motion state based on the signal quality.

[0052] The radio frequency switching switch is used to switch the current signal source to the optimal signal according to a seamless switching algorithm based on spatiotemporal joint calibration when the current signal source of the positioning and monitoring device is not the optimal signal.

[0053] Preferably, the aforementioned signal quality assessment processor is specifically used to construct a deep learning-based signal quality assessment model:

[0054] Q=α×(S / N)+β×(1-BER)+γ×C / N0+δ×(1-|Δf| / f max );

[0055] Where Q represents the overall quality index, S represents the signal power, N represents the noise power, S / N represents the signal-to-noise ratio, BER represents the bit error rate, C represents the carrier power, NO represents the noise power spectral density, C / N0 represents the carrier-to-noise power density ratio, Δf represents the frequency offset, and f max Δf| / fmax represents the maximum allowable frequency offset, |Δf| / fmax represents the normalized frequency offset, and α, β, γ, δ represent the weighting coefficients of the above variables, respectively.

[0056] Using the aforementioned signal quality assessment model, the comprehensive quality index Q of the base station signal and satellite signal is calculated in real time, and the signal quality of the base station signal and satellite signal is assessed using the comprehensive quality index.

[0057] Preferably, in the above-mentioned positioning monitoring device, the signal quality assessment processor is specifically used to generate a training dataset using measured data of base station signals and measured data of satellite signals in multiple scenarios;

[0058] The signal quality features in the measured dataset are input into the signal quality assessment model to train the signal quality assessment model with a dual DQN network architecture.

[0059] The evaluation network of the signal quality evaluation model is used to evaluate the overall quality index corresponding to the measured dataset;

[0060] The comprehensive quality index is corrected using the target network of the aforementioned signal quality assessment model.

[0061] Repeatedly train the signal quality assessment model until the error function between the target network and the assessment network converges;

[0062] The signal quality characteristics corresponding to the base station signal and satellite signal are acquired in real time and input into the signal quality evaluation model to obtain the signal quality of the base station signal and satellite signal.

[0063] Preferably, in the above-mentioned positioning monitoring device, the quality assessment processor is further used to acquire the inertial navigation data of the positioning monitoring device itself; using a federated Kalman filter algorithm:

[0064] FKF=α×KF_base+β×KF_sat+γ×KF_imu

[0065] Specifically, it is also used to fuse the inertial navigation data, base station ranging in the base station signal, and satellite ranging in the satellite signal to obtain fused ranging data, where KF_base represents base station ranging of the base station signal, KF_sat represents satellite ranging of the satellite signal, KF_imu represents inertial navigation data, FKF represents the fused ranging data, and α, β, and γ represent the corresponding weights of each item.

[0066] Specifically, it is also used in algorithms for unifying spatiotemporal references:

[0067]

[0068] Align the spatiotemporal references of the inertial navigation data, the base station signals, and the satellite signals, wherein, Indicates base station signal, Indicates satellite signal, The inertial navigation data is represented by α, β, and γ, which represent the weights of each item, and α+β+γ=1.

[0069] Preferably, the above-mentioned positioning and monitoring device further includes:

[0070] A dual-mode hot-backup power supply system electrically connected to the reconfigurable antenna array, signal quality assessment processor, and RF switching switch; wherein,

[0071] The dual-mode hot backup power system includes supercapacitors and solar energy.

[0072] According to a third aspect of this application, this application also provides a computer storage medium storing computer-executable instructions thereon, wherein when the computer program is executed by a processor, it implements the positioning and monitoring method supporting dual-mode switching between base stations and satellites as provided in any of the above technical solutions.

[0073] The technical solution of this application has at least the following technical effects:

[0074] This application provides a positioning monitoring scheme supporting dual-mode handover between base stations and satellites. It employs a deep learning-based dynamic signal evaluation model to analyze the quality characteristics of base station and satellite signals in real time, including seven key indicators such as signal strength, bit error rate, and Doppler shift. An adaptive weight adjustment algorithm is used to select the optimal signal source. Furthermore, a seamless handover technology based on spatiotemporal joint calibration is developed, using pre-synchronization and trajectory prediction algorithms. In practice, the handover latency is controlled to within 80ms, and the position drift is less than 2 meters. In summary, this application's technical solution effectively solves key problems in existing technologies such as insufficient signal coverage, prolonged handover time, and discontinuous positioning through an innovative multi-mode collaborative positioning architecture and adaptive handover algorithm. In addition, the positioning monitoring scheme also proposes an intelligent power consumption management strategy. By dynamically adjusting the positioning frequency and module operating mode, the power consumption of the device in hybrid positioning mode is reduced to 1.2W, a reduction of more than 40% compared to existing technologies. Attached Figure Description

[0075] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0076] Figure 1 A flowchart illustrating a positioning monitoring method supporting dual-mode switching between base station and satellite, provided in an embodiment of this application;

[0077] Figure 2 for Figure 1 The illustrated embodiment provides a flowchart of a signal quality analysis method;

[0078] Figure 3 for Figure 2 The illustrated embodiment provides a flowchart of a signal quality assessment method;

[0079] Figure 4 for Figure 1 The illustrated embodiment provides a flowchart of an optimal signal selection method;

[0080] Figure 5 for Figure 1 The illustrated embodiment provides a flowchart of a method for switching the current signal source;

[0081] Figure 6 A flowchart illustrating an intelligent power management strategy provided in an embodiment of this application;

[0082] Figure 7 A flowchart illustrating a signal switching method provided in an embodiment of this application;

[0083] Figure 8 This is a schematic diagram of a positioning monitoring device that supports dual-mode switching between base station and satellite, provided in an embodiment of this application. Detailed Implementation

[0084] To more clearly illustrate the overall concept of this application, a detailed explanation is provided below with reference to the accompanying drawings.

[0085] Many specific details are set forth in the following description to provide a thorough understanding of this application. However, this application may also be implemented in other ways different from those described herein. Therefore, the scope of protection of this application is not limited to the specific embodiments disclosed below. It should be noted that, unless otherwise specified, the embodiments of this application and the features thereof can be combined with each other.

[0086] In this application, unless otherwise expressly specified and limited, the terms "above" and "below" the second feature can refer to direct contact between the first and second features, or indirect contact between the first and second features through an intermediate medium. In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. 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 can be combined in any suitable manner in one or more embodiments or examples.

[0087] The existing technology has the following drawbacks:

[0088] Traditional switching technologies employ a sequential search strategy, resulting in high latency of 500ms to 1 second. This can lead to significant errors in high-speed moving scenarios; for example, a 1-second delay at a vehicle speed of 120km / h translates to a positioning deviation of 33.3 meters. Existing fixed-threshold switching strategies are ill-suited to adapting to signal fluctuations in real-world environments. One logistics tracking device switched 3-5 times per minute at tunnel entrances and exits due to signal jitter, affecting not only positioning continuity but also significantly increasing power consumption.

[0089] These technological deficiencies have a particularly pronounced impact in specialized fields. Taking geological disaster monitoring as an example, the complex terrain of mountainous areas often leads to satellite signal loss. Data from a landslide monitoring point showed that traditional equipment achieved an effective data acquisition rate of less than 55% during the rainy season. Emergency communication capabilities are equally concerning; the average delay for existing short message transmissions is 38 seconds, far exceeding the 10-second warning timeframe requirement. For instance, during the Yarlung Tsangpo River landslide dam emergency in 2024, frequent equipment switching leading to power depletion directly resulted in the loss of critical data, exposing the serious inadequacies of current technology.

[0090] In summary, the market urgently needs a new type of dual-mode positioning and monitoring equipment with high reliability (availability > 99%), low latency (switching < 100ms), and intelligent power consumption management to meet the stringent requirements of fields such as emergency communication and intelligent transportation, and to break through current technological bottlenecks.

[0091] To address the aforementioned technical problems, the following embodiments of this application provide a positioning monitoring scheme that supports dual-mode switching between base stations and satellites. Through an innovative multi-mode collaborative positioning architecture and a seamless switching algorithm based on spatiotemporal joint calibration, it effectively solves key problems in the prior art such as insufficient signal coverage, prolonged switching time, and discontinuous positioning.

[0092] To achieve the above objectives, see [link to relevant documentation]. Figure 1 , Figure 1 This is a flowchart illustrating a positioning monitoring method supporting dual-mode switching between base station and satellite, provided as an embodiment of this application. Figure 1 As shown, this positioning monitoring method, which supports dual-mode switching between base stations and satellites, is applicable to positioning monitoring devices.

[0093] The device's hardware architecture employs a multi-band reconfigurable RF front-end, which uses a three-stage cascaded RF architecture design:

[0094] First stage: Wideband low-noise amplifier (NF<1.2dB).

[0095] Second stage: Tunable bandpass filter (adjustable bandwidth 20MHz).

[0096] Third stage: Zero intermediate frequency quadrature downconverter.

[0097] The positioning monitoring device provided in this application supports synchronous reception of 1559-1610MHz (BeiDou B1 / B2 band) and 700-3800MHz (cellular band), and achieves dynamic channel configuration through a high-speed radio frequency switch (switching time <50ns).

[0098] like Figure 1 As shown, this positioning monitoring method supporting dual-mode switching between base station and satellite includes:

[0099] S110: Acquire base station signals and satellite signals. In this embodiment, precise ephemeris data is automatically downloaded during the initialization phase (via 4G / 5G); and a differential connection to the base station is established. Base station signals and satellite signals can be obtained through the above methods.

[0100] S120: Uses a deep learning-based dynamic signal evaluation model to analyze the signal quality of base station signals and satellite signals in real time.

[0101] Specifically, as a preferred embodiment, such as Figure 2 As shown, step S120 involves using a deep learning-based dynamic signal evaluation model to analyze the signal quality of base station signals and satellite signals in real time, specifically including:

[0102] S121: Constructing a deep learning-based signal quality assessment model:

[0103] Q=α×(S / N)+β×(1-BER)+γ×C / N0+δ×(1-|Δf| / f max );

[0104] Where Q represents the overall quality index, S represents the signal power, N represents the noise power, S / N represents the signal-to-noise ratio, BER represents the bit error rate, C represents the carrier power, NO represents the noise power spectral density, C / N0 represents the carrier-to-noise power density ratio, Δf represents the frequency offset, and f max Δf| / fmax represents the maximum allowable frequency offset, |Δf| / fmax represents the normalized frequency offset, and α, β, γ, δ represent the weighting coefficients of the above variables, respectively.

[0105] In this signal quality assessment model, the weight coefficients (α, β, γ, δ) are dynamically adjusted through online learning, and a dual DQN network architecture is adopted: the evaluation network consists of three fully connected layers (256-128-64 nodes). The target network employs a delayed update strategy.

[0106] S122: Using a signal quality assessment model, calculate the comprehensive quality index Q of base station signals and satellite signals in real time, and use the comprehensive quality index to assess the signal quality of base station signals and satellite signals.

[0107] This application presents a deep learning-based dynamic signal evaluation model that can analyze the quality characteristics of base station and satellite signals in real time. The input parameters include seven key indicators such as signal strength, bit error rate, and Doppler shift. The optimal signal source selection is achieved through an adaptive weight adjustment algorithm.

[0108] Specifically, as a preferred embodiment, such as Figure 3As shown, the steps for using a signal quality assessment model to calculate the comprehensive quality index Q of base station signals and satellite signals in real time, and to evaluate the signal quality of base station signals and satellite signals using the comprehensive quality index, include:

[0109] S1221: Use measured data of base station signals and satellite signals in multiple scenarios to generate a training dataset, which includes signal quality features;

[0110] S1222: Input the signal quality features in the measured dataset into the signal quality assessment model and train the signal quality assessment model with a dual DQN network architecture;

[0111] S1223: The evaluation network using the signal quality assessment model evaluates the overall quality index corresponding to the measured dataset;

[0112] S1224: Correct the overall quality index of the target network using the signal quality assessment model;

[0113] S1225: Repeatedly train the signal quality evaluation model until the error function between the target network and the evaluation network converges;

[0114] S1226: Input the real-time acquired signal quality characteristics corresponding to the base station signal and satellite signal into the signal quality assessment model to obtain the signal quality of the base station signal and satellite signal.

[0115] The technical solution provided in this application embodiment uses a signal quality assessment model that is essentially a DQN network. This model includes an evaluation network and a target network. The model's evaluation, i.e., the value network, is used for updates in each iteration, while the target network is used to calculate the target value, maintaining its stability and thus improving training stability and convergence speed. Additionally, the target network copies the parameters of the value network at a certain frequency.

[0116] During model training, an error occurs between the evaluation network and the target network. This error is the difference between the predicted Q-value in the current state and the actual reward plus the maximum Q-value in the next state. The specific formula for the error function is as follows:

[0117] loss=reward+gamma*max(Q(next_state))-Q(state,action).

[0118] Here, reward represents the actual reward obtained in the current state; gamma is a discount factor, which mainly controls the impact of new values ​​on the neural network; Q(next_state) is the Q value of the next state, and max(Q(next_state)) is the maximum Q value in the next state, which is taken as the target value here; Q(state,action) is the Q value of the corresponding action in the current state; the training objective of DQN is to minimize the loss, so that the network's predicted Q value is as close as possible to the true Q value.

[0119] Figure 1 The technical solution provided in the illustrated embodiment, after the step of using a deep learning-based dynamic signal evaluation model to analyze the signal quality of base station signals and satellite signals in real time, further includes:

[0120] S130: Using an adaptive weight adjustment algorithm, the optimal signal that matches the current motion state is selected from the base station signal and satellite signal based on the signal quality.

[0121] As can be seen from the specific form of the above signal quality assessment model, the signal strength of the base station signal and satellite signal that the positioning monitoring device can receive varies depending on its motion state. This application uses an adaptive weight adjustment algorithm to adaptively adjust the weight coefficients α, β, γ, and δ of the signal quality assessment model, enabling selective adjustment of the signal quality output by the model. Based on this signal quality, the current signal source is adjusted to either a base station signal or a satellite signal.

[0122] Specifically, as a preferred embodiment, such as Figure 4 As shown, in the above positioning and monitoring method, step S130, which involves using an adaptive weight adjustment algorithm to select the optimal signal from the base station signal and satellite signal that matches the current motion state based on signal quality, includes:

[0123] S131: When the signal quality of the base station signal is greater than or equal to the first quality threshold, the base station signal is selected as the optimal signal.

[0124] S132: When the rate of decline of the base station signal quality is greater than or equal to a predetermined rate decline threshold, the satellite signal is time-aligned and the optimal signal is hot-switched to the satellite signal.

[0125] S133: When the signal quality of the base station signal is less than or equal to the second quality threshold, the satellite signal is selected as the optimal signal;

[0126] S134: When an LTE CRS signal is detected, the optimal signal will be hot-switched to the base station signal.

[0127] Specific combination Figure 7As shown in the signal switching diagram, when the signal quality Q of the base station signal is greater than 0.7, the base station signal is selected as the optimal signal; when the signal quality Q of the base station signal is less than 0.4, the current signal source is adjusted to the satellite signal. When the rate of decrease of the signal quality Q of the base station signal is greater than 5% / s, a time alignment operation is completed. Within ±20ns of this time alignment operation, the satellite signal is selected as the optimal signal. When an LTE CRS signal is detected, the optimal signal is hot-switched to the base station signal. The above signal switching is implemented using a hot-switching state mechanism, the code of which is as follows:

[0128] stateDiagram-v2

[0129] [*]-->Idle

[0130] Idle-->BaseStation:Q_value>0.7

[0131] Idle --> Satellite: Q_value < 0.4

[0132] BaseStation --> Switching: Q_value decrease rate > 5% / s

[0133] Switching --> Satellite: Completion time alignment (±20ns)

[0134] Satellite --> BaseStation: LTE CRS signal detected.

[0135] Figure 1 The positioning monitoring device provided in the illustrated embodiment, after the step of selecting the optimal signal that matches the current motion state from base station signals and satellite signals based on signal quality, further includes:

[0136] S140: When the current signal source of the positioning and monitoring device is not the optimal signal, a seamless switching algorithm based on spatiotemporal joint calibration is used to switch the current signal source to the optimal signal. This application embodiment develops a seamless switching technology based on spatiotemporal joint calibration. Actual testing shows that this technology, employing pre-synchronization and trajectory prediction algorithms, can control the switching delay to within 80ms and the position drift to less than 2 meters.

[0137] Specifically, as a preferred embodiment, such as Figure 5 As shown, step S140, which involves switching the current signal source to the optimal signal using a seamless switching algorithm based on spatiotemporal joint calibration, includes:

[0138] S141: Use the TDD time alignment algorithm to perform TA compensation for base station signals and synchronization time calibration for satellite signals respectively;

[0139] S142: Use a spatial calibration algorithm to establish a real-time conversion model between the WGS-84 coordinate system and the local coordinate system;

[0140] S143: Use a real-time conversion model to place base station signals and satellite signals in the local coordinate system corresponding to the positioning and monitoring equipment;

[0141] S144: When it is necessary to switch between base station signals and satellite signals, in the local coordinate system, switch the time-aligned base station signals or satellite signals to the current signal source.

[0142] The seamless switching algorithm based on spatiotemporal joint calibration provided in this application includes two parts: a time synchronization subsystem and a spatial calibration algorithm. Specifically:

[0143] (1) Time synchronization subsystem

[0144] Using TDD time alignment technology

[0145] Base station side: Utilize 5G NR's Timing Advance (TA) compensation.

[0146] Satellite side: Calibrated using BeiDou timing signals (accuracy ±20ns).

[0147] (2) Spatial calibration algorithm

[0148] Establish a real-time transformation model between WGS84 and the local coordinate system:

[0149] [X]local=R(θ)×[X]WGS84+T

[0150] Among them, the rotation matrix R is dynamically corrected by IMU data, and the translation vector T is estimated in real time using the least squares method; [X]local represents the coordinate value in the local coordinate system, and [X]WGS84 represents the coordinate value in the WGS84 coordinate system.

[0151] The technical solution provided in this application, which features a seamless switching algorithm based on spatiotemporal joint calibration, is designed for high-speed mobile scenarios. It incorporates a trajectory prediction and compensation algorithm that reduces the trajectory interruption distance at 120 km / h from 33.3 meters to 1.8 meters, fully meeting the needs of high-dynamic applications such as high-speed rail monitoring. In specialized fields such as geological disaster monitoring, by integrating BeiDou PPP-RTK, base station UWB ranging, and MEMS inertial navigation data, a static monitoring accuracy of ±2 mm is achieved, representing a 20-fold improvement over a single satellite solution.

[0152] The step of switching the time-aligned base station signal or satellite signal to the current signal source is achieved through a multi-source data high-precision fusion algorithm. This multi-source data high-precision fusion algorithm includes a federated Kalman filter algorithm and a spatiotemporal reference unification algorithm.

[0153] Specifically, in a preferred embodiment, in this positioning and monitoring method, step S144: switching the time-aligned base station signal or satellite signal to the current signal source in the local coordinate system includes:

[0154] S1441: Acquire the inertial navigation data of the positioning monitoring device itself;

[0155] S1442: Using the Federated Kalman Filter Algorithm:

[0156] FKF=α×KF_base+β×KF_sat+γ×KF_imu

[0157] S1443: Integrate inertial navigation data, base station ranging from base station signals, and satellite ranging from satellite signals to obtain fused ranging data. Here, KF_base represents base station ranging from base station signals, KF_sat represents satellite ranging from satellite signals, KF_imu represents inertial navigation data, FKF represents fused ranging data, and α, β, and γ represent the corresponding weights of each item.

[0158] The Federal Kalman Filter (FKF) employed in this embodiment fuses base station UWB ranging, BeiDou PPP-RTK, and MEMS inertial data to resolve the base station-satellite positioning jump problem. Practical verification has shown that the error has been reduced from greater than 15m to less than 2m.

[0159] In addition, the technology provided in this application also includes a unified spatiotemporal reference algorithm.

[0160] S1444: Using the spatiotemporal benchmark unification algorithm:

[0161]

[0162] Aligning inertial navigation data, base station signals, and satellite signals with a spatiotemporal reference, wherein, Indicates base station signal, Indicates satellite signal, Let α represent inertial navigation data, where α, β, and γ represent the weights of each item, and α + β + γ = 1.

[0163] This unified spatiotemporal reference algorithm can realize real-time conversion of inertial navigation data, base station signals and satellite signals between the WGS84 coordinate system and the CGCS2000 coordinate system.

[0164] In summary, the positioning monitoring scheme supporting dual-mode handover between base stations and satellites provided in this application analyzes the quality characteristics of base station and satellite signals in real time, including seven key indicators such as signal strength, bit error rate, and Doppler shift, by designing a deep learning-based dynamic signal evaluation model. It achieves optimal signal source selection through an adaptive weight adjustment algorithm. Furthermore, it develops a seamless handover technology with spatiotemporal joint calibration, employing pre-synchronization and trajectory prediction algorithms, achieving a handover latency of less than 80ms and a position drift of less than 2 meters in actual measurements. In summary, the technical solution of this application effectively solves key problems in existing technologies such as insufficient signal coverage, prolonged handover time, and discontinuous positioning through an innovative multi-mode collaborative positioning architecture and adaptive handover algorithm. In addition, the positioning monitoring scheme provided in this application also proposes an intelligent power consumption management strategy, reducing the power consumption of the device in hybrid positioning mode to 1.2W by dynamically adjusting the positioning frequency and module operating mode, which is more than 40% lower than existing technologies.

[0165] In addition, as a preferred embodiment, after step S140: switching the current signal source to the optimal signal using a seamless switching algorithm based on spatiotemporal joint calibration, the positioning and monitoring method further includes:

[0166] S150: Employs intelligent power management strategies to dynamically adjust the positioning frequency and power consumption mode of the positioning monitoring device based on the current motion state and application environment.

[0167] The intelligent power management strategy provided in this application reduces the power consumption of the device in the hybrid positioning mode to 1.2W by dynamically adjusting the positioning frequency and module working mode, which is more than 40% lower than the prior art.

[0168] Specifically, such as Figure 6 As shown, the steps of using an intelligent power management strategy to dynamically adjust the positioning frequency and power consumption mode of the positioning monitoring device according to the current motion state and application environment include:

[0169] S151: Use intelligent power management strategy to set the power operation mode of the positioning monitoring device to normal mode, energy saving mode and emergency mode respectively.

[0170] S152: In normal mode, set the positioning monitoring device to the base station positioning frequency as the normal frequency, and set the satellite positioning frequency as the normal frequency.

[0171] S153: In energy-saving mode, the carrier phase observation of the positioning monitoring equipment is turned off, and dead reckoning (DR) is used for auxiliary monitoring.

[0172] S154: In emergency mode, enable full-band scanning mode and short message backup transmission mode.

[0173] The technical solution provided in this application embodiment features a three-tiered power management strategy: normal mode, energy-saving mode, and emergency mode. Specifically,

[0174] (1) Normal mode (1.5W):

[0175] Base station positioning: 1Hz update

[0176] Satellite positioning: Heartbeat mode (wakes up once per minute).

[0177] (2) Energy saving mode (0.8W): Turn off carrier phase observation; use DR (dead reckoning) assistance.

[0178] (3) Emergency mode (3.2W): Full-band scanning (100Hz), and short message backup transmission is required.

[0179] It should be noted that in the normal mode, the positioning monitoring device is set to a conventional frequency for positioning base stations and a conventional frequency (1.5W) for positioning satellites.

[0180] In the energy-saving mode, carrier phase observation of the positioning and monitoring equipment is turned off, and dead reckoning (DR) is used for assisted monitoring.

[0181] In the emergency mode, full-band scanning and short message backup transmission are enabled.

[0182] The technical solution provided in this application represents a revolutionary advancement in system reliability. The dual-mode hot backup mechanism can complete signal switching within 68ms, an order of magnitude improvement over the traditional 500ms solution. Combined with a 300F supercapacitor, it can maintain critical system operation for 15 minutes. In the 2024 earthquake test, it demonstrated excellent performance by continuing operation for 3 hours after base station damage. The intelligent fault-tolerant system can diagnose abnormal states such as open-circuit antennas and outdated ephemeris in real time, and automatically implement recovery measures such as backup antenna switching and emergency ephemeris download within 1-10 seconds. By adopting automotive-grade chips and a three-level temperature control strategy, the equipment's operating temperature range is extended to -40℃ to +85℃, significantly improving its adaptability to extreme environments.

[0183] Additionally, it should be noted that different power management modes will be triggered under different operating environments. Specifically, the typical operating environment modes are as follows:

[0184] (1) Urban Model:

[0185] Base station positioning is the primary method (1Hz update).

[0186] Satellite positioning assistance (verified every 10 seconds)

[0187] Typical power consumption: 1.1W

[0188] (2) Wilderness Mode:

[0189] Satellite positioning is the primary method (RTK mode).

[0190] Base station location backup (maintains heartbeat connection only)

[0191] Typical power consumption: 1.8W

[0192] (3) Emergency Mode:

[0193] Full system wake-up (5Hz positioning)

[0194] Short message transmission interval compressed to 5 seconds

[0195] Maximum power consumption: 4.5W (for 15 minutes)

[0196] In summary, the technical solutions provided in the above embodiments of this application achieve significant technological breakthroughs and enhanced practical value in multiple dimensions through an innovative multi-mode collaborative positioning architecture and intelligent switching mechanism. Regarding positioning performance, the solution employs a multipath suppression algorithm and base station-assisted differential positioning technology, significantly improving the positioning availability in densely populated urban areas from 78% of traditional solutions to 99.3%, with positioning errors controlled within 1.5 meters. The trajectory prediction and compensation algorithm designed for high-speed movement scenarios reduces the trajectory interruption distance at 120 km / h from 33.3 meters to 1.8 meters, fully meeting the needs of high-dynamic applications such as high-speed rail monitoring. In professional fields such as geological disaster monitoring, by integrating BeiDou PPP-RTK, base station UWB ranging, and MEMS inertial navigation data, a static monitoring accuracy of ±2 mm is achieved, representing a 20-fold improvement compared to single-satellite solutions.

[0197] According to verification by a third-party testing organization, the key performance indicators (positioning performance, handover performance, and power consumption) of the positioning monitoring method in this application are as follows:

[0198] (1) Positioning performance:

[0199] Static accuracy: Horizontal 0.8m (RMS), Elevation 1.2m.

[0200] Dynamic accuracy: 1.5m (speed ≤ 120km / h).

[0201] (2) Switching performance:

[0202] Average latency: 68ms (σ = 12ms).

[0203] Position change: <1.8m (CEP95).

[0204] (3) Power consumption performance:

[0205] Normal operating temperature: 1.25W@1Hz.

[0206] Battery life: 28 days (with 10Wh battery).

[0207] Specifically, the technical solution of this application achieves an innovative breakthrough in energy efficiency management. The dynamic power consumption control system can intelligently adjust the working mode according to the needs of the scenario. In the 1Hz standard mode, the power consumption is only 1.2W. Combined with the solar energy + supercapacitor solution, it can maintain a battery life of 28 days in continuous rainy environments, which is 4 times better than traditional equipment. The satellite module adopts a "heartbeat + event trigger" dual wake-up mechanism, which reduces its average power consumption from 2W to 0.4W, significantly extending the service life of the equipment. In terms of application value, the hardware cost of the solution is reduced by 40% compared with the dual-machine redundancy system, the maintenance cycle is extended from 3 months to 1 year, and the geological disaster early warning time is improved to the second level. It has successfully achieved a 32-minute early warning in the Yarlung Tsangpo landslide dam event. At present, this technology has been deployed and applied at 12,000 monitoring points across the country, supports BD2-SBM / RNSS, GPS L1 / L5 and 3GPP R16 5G positioning protocols, and has the expansion capability to upgrade to direct connection with low-orbit satellites.

[0208] The positioning and monitoring method supporting dual-mode switching between base station and satellite is illustrated using a typical application scenario.

[0209] Taking geological disaster monitoring as an example, the specific workflow includes the initialization phase, the monitoring phase, and the early warning phase. Specifically:

[0210] (1) Initialization phase:

[0211] Automatically downloads precise ephemeris data (via 4G / 5G).

[0212] Establish differential connections between reference stations.

[0213] (2) Monitoring phase:

[0214] Main mode: RTK positioning (base station assisted).

[0215] Backup mode: PPP positioning (satellite independent).

[0216] (3) Early warning stage:

[0217] Triggering condition: Displacement rate > 10 mm / h.

[0218] The emergency actions are as follows: a) Switch to 10Hz sampling; b) Activate the short message queue (QoS guarantee); c) Start the supercapacitor backup power supply.

[0219] Furthermore, the beneficial effects of the product embodiments provided in the following embodiments of this application are the same as the beneficial effects of the positioning monitoring method supporting dual-mode switching of base stations and satellites provided in the above embodiments, and other technical features in the product embodiments are the same as the features disclosed in the methods of the above embodiments, and will not be repeated here.

[0220] See Figure 8 , Figure 8 This is a schematic diagram of a positioning monitoring device supporting dual-mode switching between base station and satellite, provided as an embodiment of this application. Figure 8 As shown, the positioning monitoring device that supports dual-mode switching between base station and satellite includes:

[0221] The system comprises a reconfigurable antenna array 110, a signal quality assessment processor 120, and an RF switching switch 130; wherein,

[0222] The reconfigurable antenna array 110 is used to acquire base station signals and satellite signals;

[0223] The signal quality assessment processor 120 is used to analyze the signal quality of base station signals and satellite signals in real time using a deep learning-based dynamic signal assessment model, and to select the optimal signal from the base station signals and satellite signals that matches the current motion state based on the signal quality using an adaptive weight adjustment algorithm.

[0224] The radio frequency switching switch 130 is used to switch the current signal source to the optimal signal according to a seamless switching algorithm based on spatiotemporal joint calibration when the current signal source of the positioning monitoring device is not the optimal signal.

[0225] Specifically, as a preferred embodiment, such as Figure 8 As shown, the positioning monitoring device provided in this application embodiment, in addition to the above-described structure, also includes:

[0226] A dual-mode hot-backup power supply system 140 is electrically connected to the reconfigurable antenna array 110, the signal quality assessment processor 120, and the RF switching switch 130, respectively; wherein,

[0227] The dual-mode hot backup power system 140 includes supercapacitors and solar energy.

[0228] The hardware design of the positioning monitoring device supporting dual-mode switching between base station and satellite provided in this application embodiment is described in detail below using a specific hardware system as an example:

[0229] (1) Core processing unit:

[0230] Main control chip: HiSilicon Hi3559AV100 dual-core A73 + quad-core A53 architecture; Positioning processor: ST Teseo-VIC3D multi-mode GNSS chipset; Cellular communication: Integrated Quectel RM500Q 5G module; Inertial measurement: Equipped with TDK ICM-20690 six-axis IMU (±16g / ±2000dps); (2) RF front-end design:

[0231] Antenna system:

[0232] Beidou antenna: Right-hand circularly polarized microstrip antenna (gain 5.5dBi@B1 frequency)

[0233] Cellular antenna: Four-element MIMO array (ECC<0.3)

[0234] RF link:

[0235] Low-noise amplifier: Skyworks SKY67100 (NF = 0.8dB)

[0236] Filter bank: Murata BPF series (out-of-band rejection >40dBc)

[0237] (3) Specific circuit design of the radio frequency front end:

[0238] 1) BeiDou receiving channel:

[0239] ①LNA circuit:

[0240] #The matching network optimized using ADS simulation has an L1 = 3.9nH (Murata LQG18HN3N9S00)

[0241] C1 = 1.2pF(AVX AQ21A1R2BA1TE)

[0242] Bias_Tee:Mini-Circuits ZX85-12G+(DC-12GHz)

[0243] ② Down-converter:

[0244] Local oscillator: Si5351A (phase noise -110dBc / Hz@10kHz)

[0245] Mixer: ADL5801 (conversion loss 6.5dB)

[0246] 2) Cellular communication channel:

[0247] Impedance matching:

[0248] Z_{match}=\frac{1}{jωC}+jωL\quad(C=2.7pF,L=6.8nH)(4) Digital baseband processing FPGA selection: Xilinx Zynq UltraScale+XCZU19EG (specific configuration)

[0249] / / Example of parallel processing channels

[0250] module bds_baseband(

[0251] input clk_61.44MHz, / / TCXO reference clock

[0252] input[7:0]adc_data,

[0253] output[31:0]nav_data );

[0255] / / Using IP core: Fast Fourier Transform v9.0

[0256] / / Correlator spacing: 1 / 16 chip

[0257] Endmodule

[0258] In addition, based on the actual production testing, the relevant performance indicators are as follows:

[0259] (1) Radio frequency performance testing:

[0260] Using the Keysight UXM5G comprehensive tester

[0261] Test items:

[0262] Receiver sensitivity: ≤-130dBm (BeiDou B1)

[0263] Adjacent channel selectivity: ≥45dB (cellular band)

[0264] (2) Positioning performance test:

[0265] Using the Spirent GSS9000 emulator

[0266] Test scenario:

[0267] Urban Canyon (6-channel multi-path)

[0268] Highway (dynamic speed limit 120km / h)

[0269] The following is an example of how to install and deploy this system:

[0270] (1) Installation of geological disaster monitoring points:

[0271] ① Equipment fixing: Use stainless steel bracket (GB / T 3098.6); installation tilt angle: 15°±2° (facing the equator).

[0272] ②System debugging: Input the coordinates of the reference station (CGCS2000 coordinate system); set the displacement warning threshold (default 10mm / hour).

[0273] (2) Installation of in-vehicle applications:

[0274] Antenna layout: The main antenna is in the center of the roof; the auxiliary antenna is above the trunk.

[0275] Power management: Main power: vehicle 12V system; Backup power: supercapacitor (300F).

[0276] In summary, this implementation method fully demonstrates the feasibility of the invention through specific hardware selection, algorithm implementation, and deployment scheme. Actual testing shows excellent performance in the following key indicators:

[0277] Cold start TTFF: ≤8 seconds (with base station assistance)

[0278] Hot start TTFF: ≤1 second

[0279] Trajectory continuity: ≥99.1% (v≤150km / h)

[0280] Operating temperature range: -40℃~+85℃

[0281] In practice, the following parameters can be adjusted according to the application scenario:

[0282] (1) Signal evaluation model update frequency

[0283] (2) Switching trigger thresholds

[0284] (3) Conditions for switching power management modes

[0285] These adjustments are all implemented through configuration interfaces, without requiring any modification to the hardware design.

[0286] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the positioning monitoring method in the above embodiments.

[0287] The computer-readable storage medium provided in this application can be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium can be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0288] The aforementioned computer-readable storage medium carries one or more programs that, when executed by the model-building device, can be written in one or more programming languages ​​or a combination thereof to perform the operations of this application. These programming languages ​​include object-oriented programming languages—such as Java, Smalltalk, and C++—and conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0289] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram can represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or can be implemented using a combination of dedicated hardware and computer instructions.

[0290] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0291] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0292] The above description is merely an embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A positioning monitoring method supporting dual-mode switching between base station and satellite, characterized in that, include: Acquire base station signals and satellite signals; A deep learning-based dynamic signal evaluation model is used to analyze the signal quality of the base station signal and satellite signal in real time. An adaptive weight adjustment algorithm is used to select the optimal signal that matches the current motion state from the base station signal and the satellite signal based on the signal quality. When the current signal source of the positioning and monitoring device is not the optimal signal, a seamless switching algorithm based on spatiotemporal joint calibration is used to switch the current signal source to the optimal signal.

2. The positioning and monitoring method as described in claim 1, characterized in that, The step of using a deep learning-based dynamic signal evaluation model to analyze the signal quality of the base station signal and satellite signal in real time includes: Construct a deep learning-based signal quality assessment model: Q=α×(S / N)+β×(1-BER)+γ×C / N0+δ×(1-|Δf| / f max ); Where Q represents the overall quality index, S represents the signal power, N represents the noise power, S / N represents the signal-to-noise ratio, BER represents the bit error rate, C represents the carrier power, NO represents the noise power spectral density, C / N0 represents the carrier-to-noise power density ratio, Δf represents the frequency offset, and f max Δf| / fmax represents the maximum allowable frequency offset, and |Δf| / fmax represents the normalized frequency offset. α, β, γ, and δ represent the weighting coefficients of the above variables, respectively. Using the aforementioned signal quality assessment model, the comprehensive quality index Q of the base station signal and satellite signal is calculated in real time, and the signal quality of the base station signal and satellite signal is assessed using the comprehensive quality index.

3. The positioning and monitoring method as described in claim 2, characterized in that, The step of using the signal quality assessment model to calculate the comprehensive quality index Q of the base station signal and satellite signal in real time, and using the comprehensive quality index to assess the signal quality of the base station signal and satellite signal, includes: A training dataset is generated using measured data of base station signals and satellite signals from various scenarios. The signal quality features in the measured dataset are input into the signal quality assessment model to train the signal quality assessment model with a dual DQN network architecture. The evaluation network of the signal quality evaluation model is used to evaluate the overall quality index corresponding to the measured dataset; The comprehensive quality index is corrected using the target network of the aforementioned signal quality assessment model. Repeatedly train the signal quality assessment model until the error function between the target network and the assessment network converges; The signal quality characteristics corresponding to the base station signal and satellite signal are acquired in real time and input into the signal quality evaluation model to obtain the signal quality of the base station signal and satellite signal.

4. The method as described in claim 1, characterized in that, The step of selecting the optimal signal from the base station signal and satellite signal that matches the current motion state using an adaptive weight adjustment algorithm includes: When the signal quality of the base station signal is greater than or equal to the first quality threshold, the base station signal is selected as the optimal signal; When the rate of degradation of the signal quality of the base station signal is greater than or equal to a predetermined rate degradation threshold, the satellite signal is time-aligned and the optimal signal is hot-switched to the satellite signal. When the signal quality of the base station signal is less than or equal to the second quality threshold, the satellite signal is selected as the optimal signal; When an LTE CRS signal is detected, the optimal signal is hot-switched to the base station signal.

5. The positioning and monitoring method as described in claim 1, characterized in that, The step of switching the current signal source to the optimal signal using a seamless switching algorithm based on spatiotemporal joint calibration includes: The TDD time alignment algorithm is used to perform TA compensation on the base station signal and synchronization time calibration on the satellite signal. A real-time conversion model between the WGS-84 coordinate system and the local coordinate system was established using a spatial calibration algorithm. Using the real-time conversion model, the base station signal and satellite signal are placed in the local coordinate system corresponding to the positioning and monitoring device; When it is necessary to switch the base station signal or satellite signal, the time-aligned base station signal or satellite signal is switched to the current signal source in the local coordinate system.

6. The positioning and monitoring method as described in claim 5, characterized in that, The step of switching the time-aligned base station signal or satellite signal to the current signal source in the local coordinate system includes: Obtain the inertial navigation data of the positioning and monitoring device itself; Using the federated Kalman filter algorithm: FKF=α×KF_base+β×KF_sat+γ×KF_imu By fusing the inertial navigation data, base station ranging from the base station signal, and satellite ranging from the satellite signal, fused ranging data is obtained. Here, KF_base represents base station ranging from the base station signal, KF_sat represents satellite ranging from the satellite signal, KF_imu represents inertial navigation data, FKF represents the fused ranging data, and α, β, and γ represent the corresponding weights of each item. Using a unified spatiotemporal benchmark algorithm: Align the spatiotemporal references of the inertial navigation data, the base station signals, and the satellite signals, wherein, Indicates base station signal, Indicates satellite signal, The inertial navigation data is represented by α, β, and γ, which represent the weights of each item, and α+β+γ=1.

7. The positioning and monitoring method as described in claim 1, characterized in that, After the step of switching the current signal source to the optimal signal using a seamless switching algorithm based on spatiotemporal joint calibration, the method further includes: Using an intelligent power consumption management strategy, the positioning frequency and power consumption mode of the positioning monitoring device are dynamically adjusted according to the current motion state and the current application environment. The step of using an intelligent power management strategy to dynamically adjust the positioning frequency and power consumption mode of the positioning monitoring device according to the current motion state and the current application environment specifically includes: Using an intelligent power consumption management strategy, the power consumption operation modes of the positioning monitoring device are set to normal mode, energy-saving mode, and emergency mode, respectively; wherein... In the normal mode, the positioning monitoring device is set to a normal frequency for positioning base stations and a normal frequency for positioning satellites. In the energy-saving mode, carrier phase observation of the positioning and monitoring equipment is turned off, and dead reckoning (DR) is used for assisted monitoring. In the emergency mode, full-band scanning and short message backup transmission are enabled.

8. A positioning monitoring device supporting dual-mode switching between base station and satellite, characterized in that, include: Reconfigurable antenna array, signal quality assessment processor, and RF switching switch; among which, The reconfigurable antenna array is used to acquire base station signals and satellite signals; The signal quality assessment processor is used to analyze the signal quality of the base station signal and satellite signal in real time using a deep learning-based dynamic signal assessment model, and to select the optimal signal that conforms to the current motion state from the base station signal and satellite signal based on the signal quality using an adaptive weight adjustment algorithm. The radio frequency switching switch is used to switch the current signal source to the optimal signal according to a seamless switching algorithm based on spatiotemporal joint calibration when the current signal source of the positioning and monitoring device is not the optimal signal.

9. The positioning and monitoring device as described in claim 8, characterized in that, Also includes: A dual-mode hot-backup power supply system is electrically connected to the reconfigurable antenna array, the signal quality assessment processor, and the RF switching switch, respectively; wherein, The dual-mode hot backup power system includes a supercapacitor and a solar energy device.

10. A computer storage medium storing computer-executable instructions thereon, characterized in that, When the computer program is executed by the processor, it implements the positioning and monitoring method supporting dual-mode switching between base stations and satellites as described in any one of claims 1 to 7.

Images