High-precision positioning system based on Beidou

Abstract

The invention discloses a Beidou-based high-precision positioning system, and relates to the technical field of positioning, and the system comprises a positioning data collection module which collects the real-time positioning parameters of a target device; the threshold setting module is used for calculating a confidence interval of the positioning characteristic parameters and setting the confidence interval as a dynamic positioning threshold under the period duration of the time resolution; the judging module is used for judging whether a plurality of positioning characteristic parameters of the target equipment exceed a dynamic positioning threshold value or not; the offset evaluation module is used for analyzing the abnormal development trend of the target equipment according to the abnormal positioning characteristic parameters of the target equipment under the period duration; the risk probability evaluation module is used for constructing a target equipment state monitoring model; and the operation state evaluation module determines the positioning state of the target equipment. According to the Beidou-based high-precision positioning system provided by the invention, a safer guarantee is provided for equipment positioning through the technical means of real-time data acquisition, dynamic threshold setting, anomaly detection, positioning offset evaluation, risk prediction and the like.

Description

Technical Field

[0001] The present invention relates to the field of positioning technology, and in particular to a Beidou-based high-precision positioning system. Background Art

[0002] With the rapid development of positioning technology, especially the application of the Beidou satellite system, precise positioning has played an important role in various smart devices, logistics tracking, unmanned driving and other fields. Traditional positioning systems mostly rely on static data or regularly updated data, lacking sufficient dynamic monitoring and risk prediction mechanisms. In order to improve the accuracy and reliability of the positioning system and timely discover potential risk problems, more and more high-precision positioning technologies have been proposed, and combined with data analysis, machine learning and other technologies to help achieve comprehensive monitoring and risk assessment of equipment status.

[0003] In the existing technology, the positioning system faces problems such as abnormal positioning and error fluctuations, which may reduce the safety and stability of the equipment and even affect the operational efficiency of the entire system. Therefore, the assessment of abnormal fluctuations, positioning offsets and their potential risks in the positioning system has become an important research direction. In order to solve these problems, a high-precision positioning system based on Beidou satellites came into being. It can not only obtain positioning data in real time, but also conduct in-depth analysis of the data, assess risks, and handle positioning anomalies in a timely manner to ensure the safety and stability of equipment and systems. Summary of the invention

[0004] In order to solve the above technical problems, a high-precision positioning system based on Beidou is provided. This technical solution solves the above problems.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] A high-precision positioning system based on Beidou, comprising:

[0007] The positioning data acquisition module is used to collect the real-time positioning parameters of the target device according to the preset time resolution based on the Beidou satellite system, pre-process the parameters, and obtain the positioning feature parameters;

[0008] A threshold setting module, the threshold setting module is electrically connected to the feature extraction module, and the threshold setting module statistically analyzes the mean and standard deviation of the positioning feature parameters according to the positioning feature parameters of the target device under the cycle duration, calculates the confidence interval of the positioning feature parameters, and sets it as the dynamic positioning threshold under the cycle duration of the time resolution;

[0009] A judgment module, the judgment module is electrically connected to the threshold setting module, and the judgment module is used to judge whether a number of positioning characteristic parameters of the target device exceed the dynamic positioning threshold. If not, it is judged that there is no abnormality. If so, it is judged that there is an abnormality and the abnormal positioning characteristic parameters are marked;

[0010] An offset assessment module, the offset assessment module is electrically connected to the judgment module, and the offset assessment module is used to analyze the abnormal development trend of the target device according to the abnormal positioning characteristic parameters of the target device under the period length of the time resolution, and obtain the positioning offset index of the target device;

[0011] A risk probability assessment module, the risk probability assessment module is electrically connected to the offset assessment module, and the risk probability assessment module is used to take the positioning offset index of the target device as an influencing condition, construct a target device state monitoring model, take the abnormal positioning feature parameters of the target device as input, and take the positioning risk probability of the target device as output;

[0012] The operating status assessment module is electrically connected to the risk probability assessment module, and the operating status assessment module is used to determine the positioning status of the target device according to the positioning risk probability of the target device.

[0013] Preferably, the positioning data acquisition module specifically includes:

[0014] A time domain conversion unit, which uses the time resolution as a real-time positioning parameter timestamp of the target device, converts it into a time series diagram based on a timing tool, and determines the time domain of the positioning parameter of the target device;

[0015] The frequency domain conversion unit analyzes the sine wave in the time domain of the target device positioning parameter through Fourier transform, and converts the time domain of the target device positioning parameter into the frequency domain of the target device positioning parameter;

[0016] The feature extraction unit extracts the positioning feature parameters of the target device based on the frequency domain of the positioning parameters of the target device and according to the period duration of the time resolution.

[0017] Preferably, the analyzing the sine wave in the time domain of the target device positioning parameter by Fourier transform and converting the time domain of the target device positioning parameter into the frequency domain of the target device positioning parameter specifically includes:

[0018] Among them, the Fourier transform formula is:

[0019]

[0020] Where X(f) is the output of Fourier transform, f is the frequency, x(t) is the time domain signal of the positioning parameter of the target device, and e -j2πftis a complex exponential function, d is the symbol of a small time increment, and an integral operation is performed on the time variable t, where t is the time variable.

[0021] Preferably, the threshold setting module internally includes:

[0022] A grouping unit, based on the period length of the time resolution, groups the positioning characteristic parameters of the target devices according to the same timestamp to obtain an array of positioning characteristic parameters of several target devices;

[0023] A mean evaluation unit, which calculates a mean value of a characteristic parameter of a positioning characteristic parameter array of a target device;

[0024] A standard deviation evaluation unit, which calculates a standard deviation of a characteristic parameter of a positioning characteristic parameter array of a target device according to a characteristic parameter mean of the positioning characteristic parameter array of the target device;

[0025] A critical value unit sets the confidence level of the positioning parameter analysis based on the overall mean of the positioning characteristic parameters of the target device, and calculates the critical value of the standard normal distribution corresponding to the confidence level;

[0026] The confidence interval unit calculates the confidence interval based on the feature parameter mean, standard deviation and critical value of the standard normal distribution of the positioning feature parameter array of the target device through the confidence calculation formula;

[0027] The dynamic threshold setting unit sets the dynamic positioning threshold of the positioning feature parameter array of the target device according to the confidence interval under the period duration of the time resolution.

[0028] Preferably, the confidence interval is calculated based on the characteristic parameter mean, standard deviation and critical value of the standard normal distribution of the positioning characteristic parameter array of the target device through the confidence calculation formula, specifically including:

[0029] The confidence calculation formula is:

[0030]

[0031] In the formula, CI h is the confidence interval under the period length h of the time resolution, μ is the mean of the characteristic parameters of the target device positioning, σ is the standard deviation, z α / 2 is the critical value of the standard normal distribution, and n is the sample size.

[0032] Preferably, the offset assessment module internally includes:

[0033] A standardization parameter unit, which determines a baseline value of the initialized target device according to the positioning parameter of the target device under the period length of the first observation time resolution, wherein the baseline value of the target device refers to the positioning parameter of the device under a standard state;

[0034] The offset unit uses the period length of the time resolution as the observation time window, and iteratively calculates the absolute offset between the abnormal positioning characteristic parameters of the target device and the baseline value of the initialized target device in the time window;

[0035] The offset index calculation unit calculates the positioning offset index of the target device based on the absolute offset of the target device in the observation time window and the baseline value of the initialized target device through an offset analysis algorithm.

[0036] Preferably, the offset analysis algorithm expression is:

[0037] Δ i,j =|X i,j -X b |

[0038] In the formula, Δ i,j is the positioning offset index of the target device in the i-th time window, X i,j is the jth abnormality location feature parameter, X b is the baseline value for the target device.

[0039] Preferably, the risk probability assessment module includes:

[0040] The monitoring model building unit builds a target equipment status monitoring model based on logistic regression;

[0041] an abnormal feature marking unit, marking abnormal positioning feature parameters in the positioning feature parameters of the target device;

[0042] The risk probability prediction unit takes the positioning deviation index of the target device as an influencing condition, substitutes the abnormal positioning feature parameters in the positioning feature parameters of the target device into the target device state monitoring model, and takes the positioning risk probability of the target device as an output.

[0043] Preferably, the construction of the target equipment status monitoring model based on logistic regression specifically includes:

[0044] Among them, the target equipment status monitoring model formula is:

[0045]

[0046] Where Y is the positioning risk probability of the target device, X i is the i-th positioning feature parameter, β 0 is the regression coefficient of the model, e is a natural constant, and n is the input variable X i The total number, β i For each input variable X i The degree of influence on the target output Y.

[0047] Preferably, the positioning status assessment module is used to apply the following standards according to the positioning risk probability of the target device:

[0048]

[0049] Where RL is the risk level output by the model. When the risk probability Y is less than 0.2, the system determines the risk level to be low risk. When the risk probability Y is between 0.2 and 0.5, the system determines the risk level to be medium risk. When the risk probability Y is greater than or equal to 0.5, the system determines the risk level to be high risk.

[0050] Compared with the prior art, the present invention has the following beneficial effects:

[0051] The present invention proposes a high-precision positioning system based on Beidou, which provides more accurate, stable and safer guarantees for equipment positioning through technical means such as real-time data collection, dynamic threshold setting, anomaly detection, positioning offset assessment and risk prediction, effectively reducing the risks in equipment operation and improving the performance and safety of the overall system. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 It is a system framework diagram of the present invention;

[0053] Figure 2 This is an internal system framework diagram of the threshold setting module in the present invention. DETAILED DESCRIPTION

[0054] 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.

[0055] Reference Figure 1 As shown, a high-precision positioning system based on Beidou includes:

[0056] The positioning data acquisition module is used to collect the real-time positioning parameters of the target device according to the preset time resolution based on the Beidou satellite system, pre-process the parameters, and obtain the positioning feature parameters;

[0057] A threshold setting module, the threshold setting module is electrically connected to the feature extraction module, and the threshold setting module statistically analyzes the mean and standard deviation of the positioning feature parameters according to the positioning feature parameters of the target device under the cycle duration, calculates the confidence interval of the positioning feature parameters, and sets it as the dynamic positioning threshold under the cycle duration of the time resolution;

[0058] A judgment module, the judgment module is electrically connected to the threshold setting module, and the judgment module is used to judge whether a number of positioning characteristic parameters of the target device exceed the dynamic positioning threshold. If not, it is judged that there is no abnormality. If so, it is judged that there is an abnormality and the abnormal positioning characteristic parameters are marked;

[0059] An offset assessment module, the offset assessment module is electrically connected to the judgment module, and the offset assessment module is used to analyze the abnormal development trend of the target device according to the abnormal positioning characteristic parameters of the target device under the period length of the time resolution, and obtain the positioning offset index of the target device;

[0060] A risk probability assessment module, the risk probability assessment module is electrically connected to the offset assessment module, and the risk probability assessment module is used to take the positioning offset index of the target device as an influencing condition, construct a target device state monitoring model, take the abnormal positioning feature parameters of the target device as input, and take the positioning risk probability of the target device as output;

[0061] The operating status assessment module is electrically connected to the risk probability assessment module, and the operating status assessment module is used to determine the positioning status of the target device according to the positioning risk probability of the target device.

[0062] The positioning data acquisition module specifically includes:

[0063] A time domain conversion unit, which uses the time resolution as a real-time positioning parameter timestamp of the target device, converts it into a time series diagram based on a timing tool, and determines the time domain of the positioning parameter of the target device;

[0064] The frequency domain conversion unit analyzes the sine wave in the time domain of the target device positioning parameter through Fourier transform, and converts the time domain of the target device positioning parameter into the frequency domain of the target device positioning parameter;

[0065] A feature extraction unit extracts the positioning feature parameters of the target device based on the frequency domain of the positioning parameters of the target device and according to the period duration of the time resolution;

[0066] This module uses the Beidou satellite system and preset time resolution to collect real-time positioning parameters of the target device and pre-process them. This dynamic real-time data collection and processing method can accurately obtain the positioning characteristics of the target device, thereby providing accurate data for subsequent analysis and evaluation.

[0067] Through Fourier transform, the sine wave in the time domain of the target device positioning parameter is analyzed, and the target device positioning parameter time domain is converted into the target device positioning parameter frequency domain, which specifically includes:

[0068] Among them, the Fourier transform formula is:

[0069]

[0070] Where X(f) is the output of Fourier transform, f is the frequency, x(t) is the time domain signal of the positioning parameter of the target device, and e -j2πft is a complex exponential function, d is the symbol of a small time increment, and an integral operation is performed on the time variable t, where t is the time variable.

[0071] Reference Figure 2 As shown, the threshold setting module includes:

[0072] A grouping unit, based on the period length of the time resolution, groups the positioning characteristic parameters of the target devices according to the same timestamp to obtain an array of positioning characteristic parameters of several target devices;

[0073] A mean evaluation unit, which calculates a mean value of a characteristic parameter of a positioning characteristic parameter array of a target device;

[0074] A standard deviation evaluation unit, which calculates a standard deviation of a characteristic parameter of a positioning characteristic parameter array of a target device according to a characteristic parameter mean of the positioning characteristic parameter array of the target device;

[0075] A critical value unit sets the confidence level of the positioning parameter analysis based on the overall mean of the positioning characteristic parameters of the target device, and calculates the critical value of the standard normal distribution corresponding to the confidence level;

[0076] The confidence interval unit calculates the confidence interval based on the feature parameter mean, standard deviation and critical value of the standard normal distribution of the positioning feature parameter array of the target device through the confidence calculation formula;

[0077] A dynamic threshold setting unit sets a dynamic positioning threshold of a positioning feature parameter array of a target device according to a confidence interval under a period duration of a time resolution;

[0078] This module is based on the positioning feature parameters of the target device. It statistically analyzes the mean and standard deviation and dynamically sets the positioning threshold in combination with the confidence interval. This dynamically adjusted threshold setting scheme can flexibly respond to various actual scenarios according to the positioning changes of the device in different time periods, thereby improving the stability and adaptability of the system.

[0079] Based on the feature parameter mean, standard deviation and critical value of the standard normal distribution of the positioning feature parameter array of the target device, the confidence interval is calculated by the confidence calculation formula, including:

[0080] The confidence calculation formula is:

[0081]

[0082] In the formula, CI his the confidence interval under the period length h of the time resolution, μ is the mean of the characteristic parameters of the target device positioning, σ is the standard deviation, z α / 2 is the critical value of the standard normal distribution, and n is the sample size.

[0083] The offset assessment module internally includes:

[0084] The standardized parameter unit determines the baseline value of the initialized target device according to the positioning parameter of the target device under the period length of the first observation time resolution. The baseline value of the target device refers to the positioning parameter of the device under the standard state.

[0085] The offset unit uses the period length of the time resolution as the observation time window, and iteratively calculates the absolute offset between the abnormal positioning characteristic parameters of the target device and the baseline value of the initialized target device in the time window;

[0086] The offset index calculation unit calculates the positioning offset index of the target device based on the absolute offset of the target device in the observation time window and the baseline value of the initialized target device through an offset analysis algorithm.

[0087] The offset analysis algorithm expression is:

[0088] Δ i,j =|X i,j -X b |

[0089] In the formula, Δ i,j is the positioning offset index of the target device in the i-th time window, X i,j is the jth abnormality location feature parameter, X b is the baseline value of the target device;

[0090] By analyzing the abnormal positioning characteristics of the target device, the module can obtain the positioning offset index of the device and evaluate its abnormal development trend. This evaluation mechanism can predict the possible positioning error of the device in advance and adjust the offset, thereby improving the accuracy and stability of device positioning.

[0091] The risk probability assessment module includes:

[0092] The monitoring model building unit builds a target equipment status monitoring model based on logistic regression;

[0093] an abnormal feature marking unit, marking abnormal positioning feature parameters in the positioning feature parameters of the target device;

[0094] The risk probability prediction unit takes the positioning deviation index of the target device as an influencing condition, substitutes the abnormal positioning characteristic parameters in the positioning characteristic parameters of the target device into the target device state monitoring model, and takes the positioning risk probability of the target device as an output;

[0095] This module uses the positioning deviation index of the target device to evaluate the positioning risk probability of the device by building a condition monitoring model. This innovative method can accurately evaluate the operating risk of the equipment in a data-driven manner and issue an early warning when the equipment positioning deviates.

[0096] Based on logistic regression, the construction of the target equipment status monitoring model specifically includes:

[0097] Among them, the target equipment status monitoring model formula is:

[0098]

[0099] Where Y is the positioning risk probability of the target device, X i is the i-th positioning feature parameter, β 0 is the regression coefficient of the model, e is a natural constant, and n is the input variable X i The total number, β i For each input variable X i The degree of influence on the target output Y.

[0100] The positioning status assessment module is used to determine the positioning risk probability of the target device according to the following standards:

[0101]

[0102] Where RL is the risk level output by the model. When the risk probability Y is less than 0.2, the system determines the risk level to be low risk. When the risk probability Y is between 0.2 and 0.5, the system determines the risk level to be medium risk. When the risk probability Y is greater than or equal to 0.5, the system determines the risk level to be high risk.

[0103] This module can automatically assess the risk level of the equipment and make corresponding judgments by setting risk probability standards. This assessment mechanism can adjust risk response measures according to the actual risk situation, thereby ensuring the safe operation of the equipment and reducing potential losses.

[0104] In summary, the advantages of the present invention are:

[0105] The system is based on the Beidou satellite system, combines time domain and frequency domain conversion, and extracts positioning feature parameters through Fourier transform to achieve real-time monitoring and high-precision positioning of equipment, greatly improving the accuracy and stability of positioning;

[0106] The threshold setting module analyzes the mean, standard deviation and confidence interval of the positioning feature parameters, and can calculate and set the dynamic positioning threshold in real time to monitor the positioning feature parameters of the device, so as to detect anomalies in time and improve the fault tolerance and security of the positioning system.

[0107] The system uses the offset assessment module to calculate the positioning offset index of the equipment, and analyzes the abnormal development trend of the equipment in combination with the abnormal positioning characteristic parameters, providing data support for subsequent risk prediction. This can effectively assess the risk status of the equipment and help users prevent and adjust problems before they occur.

[0108] The risk probability assessment module combines the logistic regression model to analyze the positioning offset and abnormal characteristic parameters of the equipment, thereby predicting the positioning risk of the equipment. By monitoring the risk probability of the equipment in real time, corresponding countermeasures can be taken according to different risk levels to effectively reduce the losses caused by potential risks.

[0109] The operating status assessment module automatically determines the risk level of the equipment based on the risk probability of the equipment, providing managers with accurate decision-making basis. Through low-risk, medium-risk, and high-risk classification management, more reasonable maintenance and management decisions can be made based on the equipment status.

[0110] The system uses periodic setting and dynamic adjustment of time resolution, which can adapt to different scenarios and application requirements, improving the flexibility and adaptability of the system. For example, under different time resolutions, the system can automatically adjust parameters according to the actual operating status of the equipment to ensure long-term operation stability.

[0111] 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 high-precision positioning system based on Beidou, characterized in that: include: The positioning data acquisition module is used to collect the real-time positioning parameters of the target device based on the Beidou satellite system according to the preset time resolution, pre-process the parameters, and obtain the positioning feature parameters; The threshold setting module statistically analyzes the mean and standard deviation of the positioning feature parameters according to the positioning feature parameters of the target device under the cycle duration, calculates the confidence interval of the positioning feature parameters, and sets it as the dynamic positioning threshold under the cycle duration of the time resolution; A judgment module judges whether several positioning characteristic parameters of the target device exceed the dynamic positioning threshold. If not, it is judged that there is no abnormality. If so, it is judged that there is an abnormality and marks the abnormal positioning characteristic parameters; The offset evaluation module is used to analyze the abnormal development trend of the target device according to the abnormal positioning characteristic parameters of the target device under the period length of the time resolution, and obtain the positioning offset index of the target device; The risk probability assessment module is used to take the positioning deviation index of the target device as an influencing condition, build a target device status monitoring model, take the abnormal positioning characteristic parameters of the target device as input, and take the positioning risk probability of the target device as output; The operation status assessment module is used to determine the positioning status of the target device according to the positioning risk probability of the target device.

2. A Beidou-based high-precision positioning system according to claim 1, characterized in that: The positioning data acquisition module specifically includes: A time domain conversion unit, which uses the time resolution as a real-time positioning parameter timestamp of the target device, converts it into a time series diagram based on a timing tool, and determines the time domain of the positioning parameter of the target device; The frequency domain conversion unit analyzes the sine wave in the time domain of the target device positioning parameter through Fourier transform, and converts the time domain of the target device positioning parameter into the frequency domain of the target device positioning parameter; The feature extraction unit extracts the positioning feature parameters of the target device based on the frequency domain of the positioning parameters of the target device and according to the period duration of the time resolution.

3. A Beidou-based high-precision positioning system according to claim 2, characterized in that: The sine wave in the time domain of the target device positioning parameter is analyzed by Fourier transform, and the time domain of the target device positioning parameter is converted into the frequency domain of the target device positioning parameter. include: Among them, the Fourier transform formula is: Where X(f) is the output of Fourier transform, f is the frequency, x(t) is the time domain signal of the positioning parameter of the target device, and e -j2πft is a complex exponential function, d is the symbol of a small time increment, and an integral operation is performed on the time variable t, where t is the time variable.

4. A Beidou-based high-precision positioning system according to claim 3, characterized in that: The threshold setting module includes: A grouping unit, based on the period length of the time resolution, groups the positioning characteristic parameters of the target devices according to the same timestamp to obtain an array of positioning characteristic parameters of several target devices; A mean evaluation unit, which calculates a mean value of a characteristic parameter of a positioning characteristic parameter array of a target device; A standard deviation evaluation unit, which calculates a standard deviation of a characteristic parameter of a positioning characteristic parameter array of a target device according to a characteristic parameter mean of the positioning characteristic parameter array of the target device; A critical value unit sets the confidence level of the positioning parameter analysis based on the overall mean of the positioning characteristic parameters of the target device, and calculates the critical value of the standard normal distribution corresponding to the confidence level; The confidence interval unit calculates the confidence interval based on the feature parameter mean, standard deviation and critical value of the standard normal distribution of the positioning feature parameter array of the target device through the confidence calculation formula; The dynamic threshold setting unit sets the dynamic positioning threshold of the positioning feature parameter array of the target device according to the confidence interval under the period duration of the time resolution.

5. A Beidou-based high-precision positioning system according to claim 4, characterized in that: The confidence interval is calculated based on the characteristic parameter mean, standard deviation and critical value of the standard normal distribution of the positioning characteristic parameter array of the target device through the confidence calculation formula. include: The confidence calculation formula is: In the formula, CI h is the confidence interval under the period length h of the time resolution, μ is the mean of the characteristic parameters of the target device positioning, σ is the standard deviation, z α / 2 is the critical value of the standard normal distribution, and n is the sample size.

6. A Beidou-based high-precision positioning system according to claim 5, characterized in that: The offset assessment module internally includes: A standardization parameter unit, which determines a baseline value of the initialized target device according to the positioning parameter of the target device under the period length of the first observation time resolution, wherein the baseline value of the target device refers to the positioning parameter of the device under a standard state; The offset unit uses the period length of the time resolution as the observation time window, and iteratively calculates the absolute offset between the abnormal positioning characteristic parameters of the target device and the baseline value of the initialized target device in the time window; The offset index calculation unit calculates the positioning offset index of the target device based on the absolute offset of the target device in the observation time window and the baseline value of the initialized target device through an offset analysis algorithm.

7. A Beidou-based high-precision positioning system according to claim 6, characterized in that: The offset analysis algorithm expression is: Δ i,j =|X i,j -X b | In the formula, Δ i,j is the positioning offset index of the target device in the i-th time window, X i,j is the jth abnormality location feature parameter, X b is the baseline value for the target device.

8. A Beidou-based high-precision positioning system according to claim 7, characterized in that: The risk probability assessment module includes: The monitoring model building unit builds a target equipment status monitoring model based on logistic regression; an abnormal feature marking unit, marking abnormal positioning feature parameters in the positioning feature parameters of the target device; The risk probability prediction unit takes the positioning deviation index of the target device as an influencing condition, substitutes the abnormal positioning feature parameters in the positioning feature parameters of the target device into the target device state monitoring model, and takes the positioning risk probability of the target device as an output.

9. A Beidou-based high-precision positioning system according to claim 8, characterized in that: The target equipment status monitoring model is constructed based on logistic regression. include: Among them, the target equipment status monitoring model formula is: Where Y is the positioning risk probability of the target device, X i is the i-th positioning feature parameter, β0 is the regression coefficient of the model, e is a natural constant, and n is the input variable X i The total number, β i For each input variable X i The degree of influence on the target output Y.

10. A Beidou-based high-precision positioning system according to claim 9, characterized in that: The positioning status assessment module is used to determine the positioning risk probability of the target device according to the following standards: Where RL is the risk level output by the model. When the risk probability Y is less than 0.2, the system determines the risk level to be low risk. When the risk probability Y is between 0.2 and 0.5, the system determines the risk level to be medium risk. When the risk probability Y is greater than or equal to 0.5, the system determines the risk level to be high risk.

Images