A method, apparatus, and medium for satellite positioning

Abstract

The application discloses a satellite positioning method, device and medium, and is suitable for the technical field of positioning and navigation. A prediction protection level correction model is called to input attribute information; an output parameter of the prediction protection level correction model is acquired as a correction coefficient; a theoretical protection level is corrected according to the correction coefficient to obtain a corrected protection level; and a positioning result of satellite positioning is analyzed according to the corrected protection level to obtain an analysis result. By introducing data driving (attribute information), the attribute information is based on actual data of actual operation, the relationship between the positioning error obtained by PPP-RTK positioning and service information and observation information is mined, the prediction of the protection level correction coefficient is realized, the protection level is corrected, the satellite is positioned by the corrected protection level, the probability of dangerous events is reduced, and the reliability of the protection level in a complex environment is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of positioning and navigation, and in particular to a satellite positioning method, device and medium. BACKGROUND

[0002] Global Navigation Satellite System (GNSS) high-precision positioning has a wide application prospect. Compared with the traditional Precise Point Positioning (PPP) technology, the PPP-RTK technology can greatly shorten the convergence time and realize rapid ambiguity fixing. At the same time, compared with the Real Time Kinematic (RTK) technology, the PPP-RTK needs fewer base stations and has higher service reliability. Therefore, the PPP-RTK is expected to be widely used in the field of automatic driving. In order to realize the application of PPP-RTK in the field of automatic driving, integrity monitoring needs to be performed at the PPP-RTK user end, and the position error upper bound information under the acceptable risk, i.e. the protection level, is output to the user.

[0003] The existing research on PPP-RTK technology mainly focuses on system implementation, improvement of positioning accuracy and increase of ambiguity fixing rate, and there is little research on PPP-RTK integrity monitoring. However, for applications related to life safety such as automatic driving, integrity is a crucial performance indicator. Integrity refers to the ability to provide an alarm to the user in time when the navigation system is unavailable, and it reflects the degree of trust in the correctness of the navigation information provided by the navigation system. Specifically, the navigation system is usually unavailable due to faults in the measurements or product information involved in positioning. However, the receiver is often subject to interference such as multipath and non-straight signal in actual operation, which results in a probability of actual positioning error exceeding the theoretically derived protection level much higher than the theoretical value, making the user face risks.

[0004] Therefore, how to modify the protection level to improve the integrity monitoring of the positioning system is an urgent problem to be solved by those skilled in the art. SUMMARY

[0005] The purpose of the present application is to provide a satellite positioning method, device and medium, which modifies the protection level, reduces the probability of dangerous events, and improves the reliability of the protection level in complex environments.

[0006] To solve the above technical problems, the present application provides a satellite positioning method, comprising:

[0007] The prediction protection level correction model is called to input attribute information, wherein the attribute information is obtained through PPP-RTK service information, observation information of a receiver, and information obtained through PPP-RTK positioning;

[0008] An output parameter of the prediction protection level correction model is obtained as a correction coefficient;

[0009] A theoretical protection level is corrected according to the correction coefficient to obtain a corrected protection level, wherein the theoretical protection level is obtained based on a theoretical model;

[0010] A positioning result of satellite positioning is analyzed according to the corrected protection level to obtain an analysis result.

[0011] Preferably, the PPP-RTK service information at least includes orbit information, clock difference information, bias information, and atmospheric information of a GNSS satellite;

[0012] The observation information at least includes pseudo-range information and carrier observation information of the receiver;

[0013] The attribute information at least includes quantity information of visible satellites, carrier-to-noise ratio information, residual error information, ambiguity fixing state information, and ambiguity fixing quantity information.

[0014] Preferably, the establishment process of the prediction protection level correction model specifically includes:

[0015] Sample service information, sample observation information, and reference trajectory information stored in a database are obtained;

[0016] PPP-RTK positioning is performed according to the sample service information and the sample observation information to obtain offline positioning information and offline attribute information;

[0017] Processing is performed according to the offline positioning information and the reference trajectory information to obtain positioning error information;

[0018] An offline correction coefficient is determined according to a relationship between the theoretical protection level and the positioning error information;

[0019] The offline correction coefficient and the offline attribute information are trained through a machine learning algorithm to obtain the prediction protection level correction model.

[0020] Preferably, the offline correction coefficient is determined according to a relationship between the theoretical protection level and the positioning error information, and includes:

[0021] In a case that the theoretical protection level does not envelop all of the positioning error information or the theoretical protection level envelops all of the positioning error information and a difference between the theoretical protection level and the positioning error information is less than a threshold, the offline correction coefficient is set.

[0022] Preferably, the theoretical protection level is obtained by a fault-free protection level formula or a multi-solution separation protection level formula.

[0023] Preferably, the sample service information and the sample observation information are obtained, including:

[0024] A PPP-RTK acquisition system is built.

[0025] Road testing is performed according to different scenarios to record the sample service information and the sample observation information.

[0026] Correspondingly, the reference trajectory information stored in the database is obtained, including:

[0027] A true value reference system is built.

[0028] The reference trajectory information is obtained according to post-processing software.

[0029] Preferably, after the corrected protection level is obtained, the method further includes:

[0030] The prompting information for prompting the staff is output.

[0031] To solve the above technical problems, the application further provides a satellite positioning device, including:

[0032] A calling module is configured to call a predicted protection level correction model to input attribute information, wherein the attribute information is obtained by PPP-RTK positioning based on PPP-RTK service information and receiver observation information.

[0033] A obtaining module is configured to obtain an output parameter of the predicted protection level correction model as a correction coefficient.

[0034] A correction module is configured to correct a theoretical protection level based on the correction coefficient to obtain a corrected protection level, wherein the theoretical protection level is obtained based on a theoretical model.

[0035] An analysis module is configured to analyze a positioning result of satellite positioning based on the corrected protection level to obtain an analysis result.

[0036] To solve the above technical problems, the application further provides a satellite positioning device, including:

[0037] A memory is configured to store a computer program.

[0038] a processor for implementing the steps of the method of satellite positioning as described above when executing the computer program.

[0039] To solve the above technical problems, the application further provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program implements the steps of the method of satellite positioning as described above when executed by a processor.

[0040] The application provides a method of satellite positioning, comprising: calling a prediction protection level correction model to input attribute information, wherein the attribute information is obtained through PPP-RTK positioning based on PPP-RTK service information and receiver observation information; obtaining an output parameter of the prediction protection level correction model as a correction coefficient; correcting a theoretical protection level based on the correction coefficient to obtain a corrected protection level, wherein the theoretical protection level is obtained based on a theoretical model; and analyzing a positioning result of satellite positioning based on the corrected protection level to obtain an analysis result. The method introduces data driving (attribute information), which is based on actual data in actual operation, mines the relationship between the positioning error obtained through PPP-RTK positioning based on service information and observation information, predicts the correction coefficient of the protection level, corrects the protection level, corrects the protection level for satellite positioning, reduces the probability of dangerous events, and improves the reliability of the protection level in a complex environment.

[0041] In addition, the application further provides a satellite positioning device and medium, which have the same beneficial effects as the method of satellite positioning described above. BRIEF DESCRIPTION OF DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the application, the drawings needed in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor on the basis of these drawings.

[0043] Figure 1 A flowchart of a method of satellite positioning provided for the embodiments of the application;

[0044] Figure 2 A flowchart of another method of satellite positioning provided for the embodiments of the application;

[0045] Figure 3 A schematic diagram of machine learning training provided for the embodiments of the application;

[0046] Figure 4 A schematic diagram of a machine learning prediction process provided for the embodiments of the application;

[0047] Figure 5 A structural diagram of a satellite positioning device provided by an embodiment of the present application is shown in FIG. 1.

[0048] Figure 6 A structural diagram of another satellite positioning device provided by an embodiment of the present application is shown in FIG. 2. DETAILED DESCRIPTION

[0049] The technical solutions in the embodiments of the present application will be clearly and completely described with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0050] The core of the present application is to provide a satellite positioning method, device and medium, to correct the protection level and reduce the probability of dangerous events, and to improve the reliability of the protection level in a complex environment.

[0051] In order to enable those skilled in the art to better understand the present application, the present application will be further described in detail below with reference to the drawings and specific embodiments.

[0052] It should be noted that the basic principle of the PPP-RTK technology is to estimate and generate the orbit, clock error and bias product of the GNSS satellite in real time on the server side by using the globally distributed reference stations, and to generate regional atmospheric delay information in real time by using the regionally distributed reference stations; the above information generated by the server side is broadcast to the user side through the Internet or satellite link; on the user side, the position is estimated based on the Kalman filtering and other state estimation methods by using the pseudorange, carrier observation output by the receiver and the received server information, and the ambiguity is fixed to enhance the positioning accuracy. The existing user side integrity monitoring of the PPP-RTK technology mainly adopts two schemes, one is to push the protection level based on the fault-free mode, and the other is to obtain a relatively safe protection level by considering different fault modes. The satellite positioning method of the present application is based on the above-mentioned another mode.

[0053] In addition, the existing integrity monitoring measurement error model is difficult to accurately describe the actual error distribution, resulting in that the protection level obtained by the existing PPP-RTK user side integrity monitoring method cannot safely envelope the actual positioning error. Specifically, when the receiver antenna is affected by trees, buildings and the like, the actual PPP-RTK positioning error may exceed the given protection level, thereby bringing danger to the user. In order to improve the reliability of the protection level in a complex environment and reduce the probability of the above-mentioned dangerous events, the protection level needs to be corrected.

[0054] Figure 1A flowchart of a satellite positioning method provided by an embodiment of the present application is shown in Figure 1 as follows, which comprises:

[0055] S11: calling a predicted protection level correction model to input attribute information, wherein the attribute information is obtained through PPP-RTK service information, receiver observation information and information obtained by PPP-RTK positioning;

[0056] S12: obtaining an output parameter of the predicted protection level correction model as a correction coefficient;

[0057] S13: correcting a theoretical protection level to obtain a corrected protection level according to the correction coefficient, wherein the theoretical protection level is obtained based on a theoretical model;

[0058] S14: analyzing a positioning result of satellite positioning according to the corrected protection level to obtain an analysis result.

[0059] Specifically, the predicted protection level correction model is called to solve the problem that the protection level cannot completely envelop the actual positioning error in a complex challenge environment. The protection level correction method based on machine learning is used to mine the relationship between the attribute information and the positioning error, so as to realize the prediction of the protection level correction coefficient. As an embodiment, the establishment process of the predicted protection level correction model specifically comprises:

[0060] obtaining sample service information, sample observation information and reference trajectory information stored in a database;

[0061] performing PPP-RTK positioning according to the sample service information and the sample observation information to obtain offline positioning information and offline attribute information;

[0062] processing the offline positioning information and the reference trajectory information to obtain positioning error information;

[0063] determining an offline correction coefficient according to the relationship between the theoretical protection level and the positioning error information;

[0064] training the offline correction coefficient and the offline attribute information through a machine learning algorithm to obtain the predicted protection level correction model.

[0065] It can be understood that the model is established by sample data offline, and a large amount of observation data needs to be collected, that is, sample service information, sample observation information and reference trajectory information. The sample service information is mainly the product information of the PPP-RTK technology, such as the orbit information, clock error information and bias information of the GNSS satellite. The observation information is mainly the pseudo-range information and carrier observation information output by the receiver, and the reference trajectory information is the positioning result obtained by the PPP-RTK positioning technology based on the real data stored in the database, and does not need to be obtained by the positioning result obtained by the positioning processing based on the real data this time.

[0066] The offline positioning information and offline attribute information are obtained by PPP-RTK positioning based on the sample service information and sample observation information. When the PPP-RTK positioning technology is performed, the offline positioning information is recorded, that is, the positioning result obtained by the positioning processing based on the offline data this time. The offline attribute information is process information including the number of visible satellites, signal-to-noise ratio, residual error, ambiguity fixing state, ambiguity fixing number and the like.

[0067] The positioning error information is obtained by processing the offline positioning information and the reference trajectory information, that is, the positioning error information is obtained by comparing the positioning information obtained based on the current offline information with the sample positioning information of the reference trajectory information.

[0068] The offline correction coefficient is determined according to the relationship between the theoretical protection level and the positioning error information. Since the protection level calculated based on the theoretical model may not safely envelope the actual positioning error in some scenarios, the protection level is manually corrected based on the actual error sequence, and the correction coefficient is the offline correction coefficient. The corresponding correction process can be set according to the actual situation, and the present application does not make specific limitation.

[0069] The offline correction coefficient and the offline attribute information are trained by a machine learning algorithm to obtain a prediction protection level correction model. The present application does not make any setting for the machine learning algorithm, which can be based on a support vector machine, a neural network or the like.

[0070] After the attribute information is input into the established prediction protection level correction model, the correction coefficient is output. It can be understood that the attribute information has the same parameters as the offline attribute information described above, and the specific data under the parameters is obtained based on the real-time running data, that is, the information obtained by PPP-RTK positioning based on the PPP-RTK service information and the observation information of the receiver.

[0071] As an embodiment, the PPP-RTK service information at least includes the orbit information, clock error information, bias information and atmospheric information of the GNSS satellite.

[0072] The observation information at least includes pseudo-range information and carrier observation information of the receiver.

[0073] The attribute information at least includes number information of visible satellites, carrier-to-noise ratio information, residual information, ambiguity fixing state information and ambiguity fixing number information.

[0074] It can be understood that the PPP-RTK service information and the observation information of the receiver can be the same as the sample service information and the sample observation information in the above-mentioned embodiments, or can include parameters other than the above-mentioned embodiments, that is, at least include the parameters in the above-mentioned embodiments, but the data of the specific parameters is different from the sample information in the above-mentioned embodiments, and is obtained according to the actual data collected in real-time operation.

[0075] The correction coefficient is obtained based on the recorded attribute information (number of visible satellites, carrier-to-noise ratio, residual, and process information) and the pre-trained model, and the theoretical protection level is corrected to obtain the corrected protection level after the correction coefficient is obtained. It can be understood that the theoretical protection level is obtained based on the theoretical model, and can be the same as or different from the calculation formula used for the theoretical protection level of the prediction protection level correction model, in order to improve the accuracy, the calculation formula is the same.

[0076] According to the corrected protection level, the positioning result of satellite positioning is evaluated to determine the accuracy of the positioning result, that is, the positioning result is analyzed to obtain an analysis result.

[0077] The method for satellite positioning provided by the embodiment of the application comprises the following steps: calling a prediction protection level correction model to input attribute information, wherein the attribute information is obtained through PPP-RTK positioning based on PPP-RTK service information and observation information of a receiver; obtaining an output parameter of the prediction protection level correction model as a correction coefficient; correcting a theoretical protection level according to the correction coefficient to obtain a corrected protection level, wherein the theoretical protection level is obtained based on a theoretical model; and analyzing a positioning result of satellite positioning according to the corrected protection level to obtain an analysis result. The method introduces data driving (attribute information), the attribute information is based on actual data obtained in actual operation, mines the relationship between the positioning error obtained through PPP-RTK positioning based on service information and observation information, realizes prediction of a protection level correction coefficient, corrects the protection level, corrects the protection level, and reduces the probability of a dangerous event occurring, and improves the reliability of the protection level in a complex environment.

[0078] On the basis of the above-mentioned embodiments, the offline correction coefficient is determined according to the relationship between the theoretical protection level and the positioning error information, and the offline correction coefficient is determined according to the relationship between the theoretical protection level and the positioning error information.

[0079] If the theoretical protection level does not fully encompass the positioning error information, or if the theoretical protection level fully encompasses the positioning error information, and the difference between the theoretical protection level and the positioning error information is greater than a threshold, an offline correction coefficient is set.

[0080] Specifically, the protection level calculated based on the theoretical model may not be able to safely encompass the actual positioning error in some scenarios. Therefore, based on the actual error sequence, the corresponding protection level is manually corrected to ensure that the protection level meets two conditions: one is that the theoretical protection level does not fully encompass the positioning error information; the other is that, based on fully encompassing the positioning error information, the difference between the theoretical protection level and the positioning error information is greater than a threshold. An offline correction coefficient is then set based on these two conditions. An initial offline correction coefficient can be set and continuously input into the original model to adjust its correction coefficient until the two preset conditions are met, resulting in the final offline correction coefficient.

[0081] The embodiments of the present invention provide a model that uses offline attribute information to predict the protection level correction coefficient by setting an offline correction coefficient, thereby obtaining a model that is more accurate.

[0082] Based on the above embodiments, as one embodiment, the theoretical protection level is obtained based on the theoretical model. It can be the same as or different from the calculation formula used for the theoretical protection level in establishing the predicted protection level correction model. Specifically, the theoretical protection level is obtained through the fault-free protection level formula or the multi-solution separation protection level formula.

[0083] The fault-free protection level can be calculated using the following formula:

[0084] ;

[0085] in, It is a Gaussian probability function. To be assigned to the Integrity risks in one direction For the first Protection level in each direction, That is the corresponding standard deviation of error.

[0086] The theoretical protection level can also be calculated using the multi-solution separation protection level calculation formula, as follows:

[0087] ;

[0088] in, This is the sum of probabilities of unmonitored failure modes. The standard deviation of the error under all-in-view. The number of monitored fault modes, the error standard deviation of the first subset, the detection threshold corresponding to the first subset, and the probability of all-in-view and the first subset, respectively.

[0089] The theoretical protection level provided by the embodiment is obtained by the failure-free protection level formula or the multi-solution separation protection level formula. The theoretical protection level is obtained by the protection level formula, and the theoretical protection level is convenient for subsequent correction according to the correction coefficient to obtain the corrected protection level.

[0090] On the basis of the above embodiment, in the process of establishing the prediction protection level correction model, the sample service information and the sample observation information are obtained, including:

[0091] The PPP-RTK collection system is built.

[0092] According to different scenes, road testing is performed to record sample service information and sample observation information.

[0093] Correspondingly, the reference trajectory information stored in the database is obtained, including:

[0094] The true value reference system is built.

[0095] The reference trajectory information is obtained according to the post-processing software.

[0096] It can be understood that a large amount of road test data is collected by building a PPP-RTK test collection vehicle, selecting high-speed, elevated and other scenes for a large amount of road testing, and recording receiver output data and PPP-RTK service data. The true value reference data is collected: a true value reference system (such as Novatel SPAN system) is built on the PPP-RTK test collection vehicle, and high-precision trajectory true value is obtained by using post-processing software (such as Novatel Inertial Explorer).

[0097] The sample service information, sample observation information and reference trajectory information stored in the database provided by the embodiment are provided for offline training to provide sample data to establish the prediction protection level correction model.

[0098] On the basis of the above embodiment, after obtaining the corrected protection level, it further includes:

[0099] The prompt information for prompting the staff is output.

[0100] After obtaining the corrected protection level, a prompt message is output, and the protection level is also sent to the user for subsequent integrity monitoring. There are no restrictions on the output method of the prompt message; it can be voice output, email notification, or SMS notification, depending on the actual situation.

[0101] The embodiments of this invention provide an output prompt message for staff after obtaining the corrected protection level. This prompts staff to facilitate subsequent integrity monitoring.

[0102] Figure 2 A flowchart of another satellite positioning method provided in an embodiment of the present invention is shown below. Figure 2 As shown, the PPP-RTK user-side protection level correction based on machine learning consists of two main parts: offline training and real-time operation. The purpose of offline training is to utilize a large amount of drive test data and corresponding trajectory ground truth values ​​to uncover the relationship between the number of visible satellites, carrier-to-noise ratio, residuals, and positioning errors, thereby training a protection level correction model. Then, in real-time operation, the trained model is used to predict the protection level correction coefficients, obtain the corrected protection level, and output it to the user.

[0103] Figure 3 This is a schematic diagram of machine learning training provided in an embodiment of the present invention. Figure 4 This is a schematic diagram of a machine learning prediction process provided in an embodiment of the present invention, such as... Figure 3 As shown, using the protection level correction coefficient obtained in the "manual determination of protection level correction coefficient" step and process information such as the number of visible satellites, carrier-to-noise ratio, residual, and fixed ambiguity number stored in the "user-end positioning & error calculation" step, a model is trained based on machine learning methods such as support vector machines and neural networks. This yields a model that predicts the protection level correction coefficient using process information. Figure 4 As shown, using actual visible satellite count, carrier-to-noise ratio, residuals, and fixed ambiguity values, etc., the process information is analyzed. Figure 3 The correction coefficient for the protection level predicted by the trained model.

[0104] The foregoing has described in detail various embodiments of the satellite positioning method. Based on this, the present invention also discloses a satellite positioning apparatus corresponding to the above-described method. Figure 5 This is a structural diagram of a satellite positioning device provided in an embodiment of the present invention. Figure 5 As shown, the satellite positioning device includes:

[0105] Module 11 is invoked to invoke the predictive protection level correction model to input attribute information, wherein the attribute information is obtained by PPP-RTK positioning through PPP-RTK service information and receiver observation information;

[0106] The acquisition module 12 is configured to acquire an output parameter of the prediction protection level correction model as a correction coefficient.

[0107] The correction module 13 is configured to correct the theoretical protection level based on the correction coefficient to obtain a corrected protection level, wherein the theoretical protection level is obtained based on a theoretical model.

[0108] The analysis module 14 is configured to analyze a positioning result of satellite positioning based on the corrected protection level to obtain an analysis result.

[0109] Since the embodiments of the device part correspond to the embodiments described above, the embodiments of the device part are described with reference to the embodiments of the method part described above, and will not be described herein.

[0110] For the device for satellite positioning provided by the present application, please refer to the method embodiments described above, and the present application will not be described herein, which has the same beneficial effects as the method for satellite positioning described above.

[0111] Figure 6 The structure diagram of another device for satellite positioning provided by the embodiments of the present application is shown in FIG. 2, which comprises: Figure 6

[0112] The memory 21 is configured to store a computer program.

[0113] The processor 22 is configured to execute the computer program to realize the steps of the method for satellite positioning.

[0114] The device for satellite positioning provided by the embodiments of the present application can include but is not limited to a smart phone, a tablet computer, a notebook computer, or a desktop computer, etc.

[0115] ​The processor 22 may include one or more processing cores, such as a quad-core processor or an octa-core processor. The processor 22 may be implemented using at least one of the following hardware forms: Digital Signal Processor (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 22 may also include a main processor and a coprocessor. The main processor, also known as the Central Processing Unit (CPU), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor 22 may integrate a Graphics Processing Unit (GPU), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, the processor 22 may also include an Artificial Intelligence (AI) processor, which handles computational operations related to machine learning.

[0116] The memory 21 may include one or more computer-readable storage media, which may be non-transitory. The memory 21 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In this embodiment, the memory 21 is used to store at least the following computer program 211, which, after being loaded and executed by the processor 22, is capable of implementing the relevant steps of the satellite positioning method disclosed in any of the foregoing embodiments. In addition, the resources stored in the memory 21 may also include an operating system 212 and data 213, etc., and the storage method may be temporary storage or permanent storage. The operating system 212 may include Windows, Unix, Linux, etc. The data 213 may include, but is not limited to, the data involved in the satellite positioning method, etc.

[0117] In some embodiments, the satellite positioning device may further include a display screen 23, an input / output interface 24, a communication interface 25, a power supply 26, and a communication bus 27.

[0118] Those skilled in the field can understand, Figure 6 The structure shown does not constitute a limitation on the satellite positioning device and may include more or fewer components than illustrated.

[0119] The processor 22 implements the satellite positioning method provided in any of the above embodiments by calling instructions stored in the memory 21.

[0120] For the satellite positioning device provided by the present application, refer to the above method embodiments, and the present application will not be described here again, which has the same beneficial effects as the above satellite positioning method.

[0121] Further, the present application also provides a computer readable storage medium, and the computer readable storage medium stores a computer program, and the computer program is executed by the processor 22 to realize the steps of the above satellite positioning method.

[0122] It can be understood that if the method in the above embodiments is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and executes all or part of the steps of the method described in each embodiment of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0123] For the computer readable storage medium provided by the present application, refer to the above method embodiments, and the present application will not be described here again, which has the same beneficial effects as the above satellite positioning method.

[0124] The above provides a detailed description of the satellite positioning method, satellite positioning device and medium provided by the present application. The embodiments in the specification are described in a progressive manner, and each embodiment mainly describes the differences from other embodiments. The same or similar parts of each embodiment can be referred to. For the device disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple, and the related parts can be referred to the method part. It should be pointed out that for ordinary skilled in the art, without departing from the principles of the present application, the present application can be improved and modified, and these improvements and modifications also fall within the protection scope of the claims of the present application.

[0125] It also needs to be explained that in the present specification, the relational terms such as first and second and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by "comprises... a" does not, without more constraints, exclude the existence of additional identical elements in the process, method, article, or apparatus that comprises the element.

Claims

1. A satellite positioning method, characterized in that, include: The predictive protection level correction model is invoked to input attribute information, wherein the attribute information is obtained by PPP-RTK positioning through PPP-RTK service information and receiver observation information; The output parameters of the predicted protection level correction model are obtained as correction coefficients; The corrected protection level is obtained by correcting the theoretical protection level according to the correction coefficient, wherein the theoretical protection level is obtained based on the theoretical model; The satellite positioning results are analyzed based on the revised protection level to obtain the analysis results; Correspondingly, the process of establishing the predicted protection level correction model specifically includes: Obtain sample service information, sample observation information, and reference trajectory information stored in the database; Based on the sample service information and the sample observation information, PPP-RTK positioning is performed to obtain offline positioning information and offline attribute information; The positioning error information is obtained by processing the offline positioning information and the reference trajectory information. The offline correction coefficient is determined based on the relationship between the theoretical protection level and the positioning error information; The predicted protection level correction model is obtained by training the offline correction coefficients and the offline attribute information using a machine learning algorithm.

2. The satellite positioning method according to claim 1, characterized in that, The PPP-RTK service information includes at least the orbital information, clock bias information, deviation information, and atmospheric information of the GNSS satellites; The observation information includes at least the pseudorange information and carrier observation information of the receiver; The attribute information includes at least the number of visible satellites, carrier-to-noise ratio, residual information, ambiguity fixation status information, and ambiguity fixation quantity information.

3. The satellite positioning method according to claim 2, characterized in that, The step of determining the offline correction coefficient based on the relationship between the theoretical protection level and the positioning error information includes: If the theoretical protection level does not fully encompass the positioning error information, or if the theoretical protection level fully encompasses the positioning error information, and the difference between the theoretical protection level and the positioning error information is less than a threshold, then the offline correction coefficient is set.

4. The satellite positioning method according to claim 3, characterized in that, The theoretical protection level is obtained through the formula for the fault-free protection level or the formula for the multi-solution separation protection level.

5. The satellite positioning method according to claim 2, characterized in that, Obtaining the sample service information and the sample observation information includes: Build a PPP-RTK data acquisition system; Drive tests are conducted according to different scenarios to record the sample service information and the sample observation information; Correspondingly, the reference trajectory information stored in the database is obtained, including: Build a truth reference system; The reference trajectory information is obtained using post-processing software.

6. The satellite positioning method according to any one of claims 1 to 5, characterized in that, After obtaining the revised protection level, the following is also included: Output a prompt message for staff.

7. A satellite positioning device, characterized in that, include: The calling module is used to call the predictive protection level correction model to input attribute information, wherein the attribute information is obtained by PPP-RTK positioning through PPP-RTK service information and receiver observation information; The acquisition module is used to acquire the output parameters of the predicted protection level correction model as correction coefficients; The correction module is used to correct the theoretical protection level according to the correction coefficient to obtain the corrected protection level, wherein the theoretical protection level is obtained based on the theoretical model; An analysis module is used to analyze the satellite positioning results based on the corrected protection level to obtain analysis results; Correspondingly, the process of establishing the predicted protection level correction model specifically includes: Obtain sample service information, sample observation information, and reference trajectory information stored in the database; Based on the sample service information and the sample observation information, PPP-RTK positioning is performed to obtain offline positioning information and offline attribute information; The positioning error information is obtained by processing the offline positioning information and the reference trajectory information. The offline correction coefficient is determined based on the relationship between the theoretical protection level and the positioning error information; The predicted protection level correction model is obtained by training the offline correction coefficients and the offline attribute information using a machine learning algorithm.

8. A satellite positioning device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the steps of the satellite positioning method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the satellite positioning method as described in any one of claims 1 to 6.

Images