Method, device, medium and product for evaluating precision of GNSS failure simulation model
Patent Information
- Application Number
- CN202210910812.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-07-29
- Publication Date
- 2026-10-30
- Estimated Expiration
- 2042-07-29
AI Technical Summary
[0004]本申请实施例提供一种GNSS故障仿真模型精度评估方法、装置、介质及产品，能够解决GNSS故障仿真模型精度评估准确性差的问题
[0019]在本申请实施例中，通过从待评估的GNSS故障仿真模型对应的真实故障数据中获取K个真实故障数据，真实故障数据属于同一GNSS故障类型；从GNSS故障仿真模型生成的仿真故障数据中获取M个仿真故障数据；根据K个真实故障数据所对应的真实数据分布和M个仿真故障数据所对应的仿真数据分布，计算真实数据分布和仿真数据分布之间的第一推土机距离；根据第一推土机距离，确定用于评估GNSS故障仿真模型精度的第一量化因子；根据第一量化因子，评估GNSS故障仿真模型的精度。如此，能够基于K个真实故障数据所对应的真实数据分布和M个仿真故障数据所对应的仿真数据分布之间的推土机距离确定出用于评估GNSS故障仿真模型精度的量化因子，再根据该量化因子即可评估GNSS故障仿真模型的精度，能够提高GNSS故障仿真模型精度评估的准确性。
Smart Images
Figure CN115358142B_ABST
Abstract
Description
Technical Field
[0001] This application belongs to the field of positioning technology, and in particular relates to a method, device, medium and product for evaluating the accuracy of a GNSS fault simulation model. Background Technology
[0002] Global Navigation Satellite System (GNSS) fault simulation technology studies the mechanisms of various types of faults in the GNSS system, thereby establishing appropriate GNSS fault simulation models to describe fault characteristics. It serves as an important basis for GNSS system robustness testing, integrity monitoring, and software and hardware algorithm optimization, making the accuracy of GNSS fault simulation models particularly important.
[0003] In related technologies, traditional statistical indicators such as correlation coefficient, standard deviation, and root mean square error are mainly used to evaluate GNSS fault simulation models. However, traditional statistical indicators have limited ability to evaluate the accuracy of GNSS fault simulation models and cannot accurately assess the accuracy of GNSS fault simulation models. Summary of the Invention
[0004] This application provides a method, apparatus, medium, and product for evaluating the accuracy of GNSS fault simulation models, which can solve the problem of poor accuracy in evaluating the accuracy of GNSS fault simulation models.
[0005] In a first aspect, embodiments of this application provide a method for evaluating the accuracy of a GNSS fault simulation model, including:
[0006] K real fault data points are obtained from the real fault data corresponding to the GNSS fault simulation model to be evaluated. The real fault data points belong to the same GNSS fault type, and K is a positive integer.
[0007] M simulation fault data points are obtained from the simulation fault data generated by the GNSS fault simulation model, where M is a positive integer;
[0008] Based on the real data distribution corresponding to K real fault data and the simulation data distribution corresponding to M simulated fault data, calculate the first bulldozer distance between the real data distribution and the simulation data distribution;
[0009] Based on the distance of the first bulldozer, a first quantization factor is determined to evaluate the accuracy of the GNSS fault simulation model.
[0010] The accuracy of the GNSS fault simulation model is evaluated based on the first quantization factor.
[0011] Secondly, embodiments of this application provide a GNSS fault simulation model accuracy evaluation device, comprising:
[0012] The first acquisition module is used to acquire K real fault data from the real fault data corresponding to the GNSS fault simulation model to be evaluated, wherein the real fault data belong to the same GNSS fault type and K is a positive integer;
[0013] The second acquisition module is used to acquire M simulation fault data from the simulation fault data generated by the GNSS fault simulation model, where M is a positive integer;
[0014] The calculation module is used to calculate the first bulldozer distance between the real data distribution and the simulation data distribution based on the real data distribution corresponding to K real fault data and the simulation data distribution corresponding to M simulated fault data.
[0015] The determination module is used to determine a first quantization factor for evaluating the accuracy of the GNSS fault simulation model based on the distance of the first bulldozer.
[0016] The evaluation module is used to evaluate the accuracy of the GNSS fault simulation model based on a first quantization factor.
[0017] Thirdly, embodiments of this application provide a computer-readable storage medium storing computer program instructions, which, when executed by a processor, implement the fault simulation model accuracy evaluation method of the first aspect.
[0018] Fourthly, embodiments of this application provide a computer program product in which instructions, when executed by the processor of an electronic device, cause the electronic device to perform the fault simulation model accuracy evaluation method as described in the first aspect.
[0019] In this embodiment, K real fault data points, belonging to the same GNSS fault type, are obtained from the real fault data corresponding to the GNSS fault simulation model to be evaluated; M simulated fault data points are obtained from the simulated fault data generated by the GNSS fault simulation model; a first bulldozer distance between the real data distribution and the simulated data distribution corresponding to the K real fault data points and the M simulated fault data points is calculated; a first quantization factor for evaluating the accuracy of the GNSS fault simulation model is determined based on the first bulldozer distance; and the accuracy of the GNSS fault simulation model is evaluated based on the first quantization factor. Thus, a quantization factor for evaluating the accuracy of the GNSS fault simulation model can be determined based on the bulldozer distance between the real data distribution corresponding to the K real fault data points and the simulated data distribution corresponding to the M simulated fault data points, and the accuracy of the GNSS fault simulation model can then be evaluated based on this quantization factor, thereby improving the accuracy of the GNSS fault simulation model accuracy evaluation. Attached Figure Description
[0020] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0021] Figure 1 This is a flowchart illustrating the accuracy evaluation method for GNSS fault simulation models provided in this application embodiment;
[0022] Figure 2 This is a schematic diagram of the GNSS fault simulation model accuracy evaluation device provided in the embodiments of this application. Detailed Implementation
[0023] The features and exemplary embodiments of various aspects of this application will be described in detail below. To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.
[0024] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.
[0025] The following description, in conjunction with the accompanying drawings, details the GNSS fault simulation model accuracy evaluation method, apparatus, medium, and product provided in this application through specific embodiments and application scenarios.
[0026] Figure 1 This is a flowchart illustrating the accuracy evaluation method for GNSS fault simulation models provided in this application embodiment. Figure 1 As shown, the accuracy evaluation method for GNSS fault simulation models may include:
[0027] S101: Obtain K real fault data from the real fault data corresponding to the GNSS fault simulation model to be evaluated, where the real fault data belong to the same GNSS fault type, and K is a positive integer;
[0028] S102: Obtain M simulation fault data from the simulation fault data generated by the GNSS fault simulation model, where M is a positive integer;
[0029] S103: Based on the real data distribution corresponding to K real fault data and the simulation data distribution corresponding to M simulated fault data, calculate the first bulldozer distance between the real data distribution and the simulation data distribution;
[0030] S104: Determine the first quantization factor for evaluating the accuracy of the GNSS fault simulation model based on the distance of the first bulldozer;
[0031] S105: Evaluate the accuracy of the GNSS fault simulation model based on the first quantization factor.
[0032] The specific implementation methods of each of the above steps will be described in detail below.
[0033] In this embodiment, K real fault data points, belonging to the same GNSS fault type, are obtained from the real fault data corresponding to the GNSS fault simulation model to be evaluated; M simulated fault data points are obtained from the simulated fault data generated by the GNSS fault simulation model; a first bulldozer distance between the real data distribution and the simulated data distribution corresponding to the K real fault data points and the M simulated fault data points is calculated; a first quantization factor for evaluating the accuracy of the GNSS fault simulation model is determined based on the first bulldozer distance; and the accuracy of the GNSS fault simulation model is evaluated based on the first quantization factor. Thus, a quantization factor for evaluating the accuracy of the GNSS fault simulation model can be determined based on the bulldozer distance between the real data distribution corresponding to the K real fault data points and the simulated data distribution corresponding to the M simulated fault data points, and the accuracy of the GNSS fault simulation model can then be evaluated based on this quantization factor, thereby improving the accuracy of the GNSS fault simulation model accuracy evaluation.
[0034] Furthermore, the fault simulation model accuracy evaluation method provided in this application embodiment is widely applicable to various GNSS fault simulation models. Whether it is a simple fault simulation model that is low-dimensional, single-factor, and linear (e.g., a satellite clock fault simulation model), or a complex fault simulation model that is high-dimensional, multi-factor, nonlinear, and based on machine learning technology (e.g., an atmospheric correlation time series fault simulation model, a data-driven multipath fault simulation model, etc.), the fault simulation model accuracy evaluation method provided in this application embodiment has good evaluation capabilities.
[0035] It should be noted that the embodiments of this application do not limit the process of establishing a GNSS fault simulation model, and any available establishment process can be applied to the embodiments of this application.
[0036] For example, a large amount of GNSS data from different carriers, with different dynamics, and in different scenarios is collected to form a complete GNSS database. Then, the sources of GNSS faults are analyzed and decomposed into N. f A sample database D for modeling fault type f is extracted from the full GNSS database, including but not limited to: signal-related faults, atmosphere-related faults, and scene-related faults. f Where the fault type f is N f Fault type among GNSS fault types.
[0037] For fault type f, from the sample database D f Extract fault data corresponding to significant fault characteristics and label them. Store the labeled fault data belonging to the same fault type f in the same fault database. In t, a suitable machine learning model is selected based on this fault database. The machine learning model is trained using the data t to obtain the GNSS fault simulation model corresponding to fault type f.
[0038] Similarly, we can obtain N. f GNSS fault simulation models corresponding to fault types other than fault type f among the GNSS fault types.
[0039] For a GNSS fault simulation model corresponding to fault type f, its fault dimension is n, which can be obtained from a fault database. Obtain K real fault data points x1, x2, ..., x K Let the i-th dimension of the actual fault data be denoted as column vector X. (i) ,but
[0040]
[0041] Let X be any n-dimensional K real fault data points.
[0042] X = {X (1) ,X (2) ,…,X (n)}
[0043] Then, using the GNSS fault simulation model, several simulated fault data are generated, and M simulated fault data y1, y2, ..., y3 are obtained from the generated simulated fault data. M .
[0044] The simulated fault data of the i-th dimension is denoted as column vector Y. (i) ,but
[0045]
[0046] Let Y be the n-dimensional M simulation fault data.
[0047] Y = {Y (1) ,Y (2) ,…,Y (n)}
[0048] The distribution of the real data corresponding to the K real fault data is P. real The simulation data distribution corresponding to the M simulation fault data is P simu .
[0049] In some possible implementations of the embodiments of this application, K and M may be equal or unequal.
[0050] Real data distribution P real With simulation data distribution P simu The distance W(P) between the P-order bulldozers real ,P simu ) p As shown in formula (1) below.
[0051]
[0052] In formula (1), ∏(P real ,P simu ) is the true data distribution P real The simulation data distribution is P simu The set of all possible joint distributions, where γ represents a possible joint distribution belonging to this set, d(XY). p Let X be the distance between the set of K real fault data and the set of M simulated fault data, and inf denote the infimum, i.e., the minimum. (x,y)~γ refers to sampling on the joint distribution γ; E(x,y)~γ[d(XY)] p ] represents the expected distance of the sampled data.
[0053] The bulldozer distance between the real data distribution and the simulated data distribution can be calculated using the above formula (1).
[0054] In some possible implementations of the embodiments of this application, the smaller the bulldozer distance, the lower the cost of moving the simulation data distribution to the real data distribution, the higher the similarity between the two distributions, and the higher the accuracy of the GNSS fault simulation model.
[0055] In some possible implementations of the embodiments of this application, the bulldozer distance in the embodiments of this application can be a second-order bulldozer distance.
[0056] In some possible implementations of the embodiments of this application, the bulldozer distance between the real data distribution and the simulated data distribution is denoted as W. f For two n-dimensional normal distributions μ1~N(m1,C1) and μ2~N(m2,C2), their second-order bulldozer distance has a closed-form solution, denoted as W2(μ1,μ2). 2 .
[0057]
[0058] In formula (2), trace(*) represents the trace of matrix *.
[0059] We choose μ1 as an n-dimensional standard normal distribution, μ2 as a vector with a mean of 0, and the diagonal elements of the covariance matrix as σ. 2 If the n-dimensional Gaussian distribution is followed, then formula (2) can be simplified to:
[0060] W2(μ1,μ2) 2 = n×(σ-1) 2 (3)
[0061] Let W f =W2(μ1,μ2) 2 Since σ≥1, solving for σ yields:
[0062]
[0063] σ can be used as a measure of the quality of a GNSS fault simulation model; the smaller σ is, the higher the accuracy of the GNSS fault simulation model. Therefore, σ can be used as a quantization factor to evaluate the accuracy of a GNSS fault simulation model. Based on this, S104 may include: determining the first quantization factor according to the above formula (4), where σ is the first quantization factor, W f The distance between the real data distribution and the simulated data distribution is the bulldozer distance, and n is the dimension of the fault data.
[0064] In some possible implementations of the embodiments of this application, once a quantization factor for evaluating the accuracy of the GNSS fault simulation model is determined, the accuracy of the GNSS fault simulation model can be evaluated based on the quantization factor.
[0065] For example, if the absolute value of the quantization factor is less than a certain preset threshold (e.g., 2), the GNSS fault simulation model is judged to be a high-precision model; otherwise, the GNSS fault simulation model is judged to be a low-precision model and is not recommended for engineering use.
[0066] In some possible implementations of the embodiments of this application, S105 may include: calculating a second bulldozer distance between the real data distributions of two sets of real fault data, wherein the two sets of real fault data and K real fault data belong to the same GNSS fault type; determining a second quantization factor corresponding to the real data distributions of the two sets of real fault data based on the second bulldozer distance; determining a model score of the GNSS fault simulation model based on the first quantization factor and the second quantization factor; and evaluating the accuracy of the GNSS fault simulation model based on the model score.
[0067] In some possible implementations of the embodiments of this application, for the GNSS fault simulation model corresponding to fault type f, it can be obtained from the above-mentioned fault database. Two sets of real fault data are selected to ensure that the two sets of real fault data and K real fault data belong to the same GNSS fault type.
[0068] In some possible implementations of the embodiments of this application, the bulldozer distance between the real data distributions of the two sets of real fault data can be calculated according to the above formula (1), and then the quantization factor corresponding to the real data distributions of the two sets of real fault data can be calculated based on the above formula (4).
[0069] In some possible implementations of the embodiments of this application, determining the model score of the GNSS fault simulation model based on the first quantization factor and the second quantization factor may include: determining the increase of the first quantization factor relative to the second quantization factor based on the first quantization factor and the second quantization factor; and determining the model score of the GNSS fault simulation model based on the increase.
[0070] For example, for a GNSS fault simulation model corresponding to fault type f, the quantization factor corresponding to the actual data distribution and the simulation data distribution is denoted as σ. f The quantization factor corresponding to the true data distribution of the two sets of real fault data is denoted as . σ f Compared to The increase is denoted as σ. inc ,
[0071] The model score of the GNSS fault simulation model can be determined according to formula (5):
[0072]
[0073] In formula (5), score is the model score of the GNSS fault simulation model.
[0074] For example, suppose σ inc =20%, then score=80.
[0075] In this embodiment of the application, the higher the model score of the GNSS fault simulation model, the higher the accuracy of the GNSS fault simulation model.
[0076] In some possible implementations of the embodiments of this application, determining the model score of the GNSS fault simulation model based on the first quantization factor and the second quantization factor may include: calculating the difference between the first quantization factor and the second quantization factor and the sum of the first quantization factor and the second quantization factor; and determining the model score of the GNSS fault simulation model based on the difference and the sum.
[0077] For example, for a GNSS fault simulation model corresponding to fault type f, the quantization factor corresponding to the actual data distribution and the simulation data distribution is denoted as σ. f The quantization factor corresponding to the true data distribution of the two sets of real fault data is denoted as
[0078] The model score of the GNSS fault simulation model can be determined according to formula (6):
[0079]
[0080] For example, suppose σ f It is 1.5. If the value is 1, then the score is 80.
[0081] In this embodiment of the application, the higher the model score of the GNSS fault simulation model, the higher the accuracy of the GNSS fault simulation model.
[0082] In this application embodiment, the model scoring criteria based on the quantification factor of the GNSS fault simulation model can provide a strong reference for users to select models and effectively enhance the persuasiveness of subsequent fault simulation robustness verification.
[0083] In some possible implementations of the embodiments of this application, the GNSS fault simulation model to be evaluated in the embodiments of this application can be any one of multiple GNSS fault simulation models, and the dimensions of the fault data corresponding to the multiple GNSS fault simulation models are different.
[0084] For example, a large amount of GNSS data from different carriers, with different dynamics, and in different scenarios is collected to form a complete GNSS database. Then, GNSS fault sources are analyzed and decomposed into N... f For each GNSS fault type, establish a corresponding N f N GNSS fault types f A GNSS fault simulation model. f The dimensions of the fault data corresponding to each GNSS fault simulation model are different.
[0085] For example, the dimension of the fault data in GNSS fault simulation model X is n, and the dimension of the fault data in GNSS fault simulation model Y is m.
[0086] It is understood that the different dimensions in the embodiments of this application include unequal numbers of dimensions and equal numbers of dimensions but different meanings of the abstract concepts represented by the dimensions.
[0087] This application also provides a GNSS fault simulation model accuracy evaluation device, such as... Figure 2 As shown. Figure 2 This is a schematic diagram of the GNSS fault simulation model accuracy evaluation device provided in this application embodiment. The GNSS fault simulation model accuracy evaluation device 200 may include:
[0088] The first acquisition module 201 is used to acquire K real fault data from the real fault data corresponding to the GNSS fault simulation model to be evaluated. The real fault data belong to the same GNSS fault type, and K is a positive integer.
[0089] The second acquisition module 202 is used to acquire M simulation fault data from the simulation fault data generated by the GNSS fault simulation model, where M is a positive integer;
[0090] The calculation module 203 is used to calculate the first bulldozer distance between the real data distribution and the simulation data distribution based on the real data distribution corresponding to K real fault data and the simulation data distribution corresponding to M simulated fault data.
[0091] The determination module 204 is used to determine a first quantization factor for evaluating the accuracy of the GNSS fault simulation model based on the distance of the first bulldozer.
[0092] Evaluation module 205 is used to evaluate the accuracy of the GNSS fault simulation model based on a first quantization factor.
[0093] In this embodiment, K real fault data points, belonging to the same GNSS fault type, are obtained from the real fault data corresponding to the GNSS fault simulation model to be evaluated; M simulated fault data points are obtained from the simulated fault data generated by the GNSS fault simulation model; a first bulldozer distance between the real data distribution and the simulated data distribution corresponding to the K real fault data points and the M simulated fault data points is calculated; a first quantization factor for evaluating the accuracy of the GNSS fault simulation model is determined based on the first bulldozer distance; and the accuracy of the GNSS fault simulation model is evaluated based on the first quantization factor. Thus, a quantization factor for evaluating the accuracy of the GNSS fault simulation model can be determined based on the bulldozer distance between the real data distribution corresponding to the K real fault data points and the simulated data distribution corresponding to the M simulated fault data points, and the accuracy of the GNSS fault simulation model can then be evaluated based on this quantization factor, thereby improving the accuracy of the GNSS fault simulation model accuracy evaluation.
[0094] In some possible implementations of the embodiments of this application, the determining module 204 may specifically be used for:
[0095] The first quantization factor is determined according to the above formula (4).
[0096] In some possible implementations of embodiments of this application, the evaluation module 205 includes:
[0097] The calculation submodule is used to calculate the second bulldozer distance between the real data distributions of two sets of real fault data, wherein the two sets of real fault data and K real fault data belong to the same GNSS fault type;
[0098] The first determination submodule is used to determine the second quantization factor corresponding to the true data distribution of the two sets of true fault data based on the second bulldozer distance;
[0099] The second determination submodule is used to determine the model score of the GNSS fault simulation model based on the first quantization factor and the second quantization factor.
[0100] The evaluation submodule is used to evaluate the accuracy of the GNSS fault simulation model based on the model score.
[0101] In some possible implementations of the embodiments of this application, the second determining submodule may specifically be used for:
[0102] Based on the first quantization factor and the second quantization factor, determine the increase of the first quantization factor relative to the second quantization factor;
[0103] The model score of the GNSS fault simulation model is determined based on the increase.
[0104] In some possible implementations of the embodiments of this application, the second determining submodule may specifically be used for:
[0105] Calculate the difference between the first quantization factor and the second quantization factor, and the sum of the first quantization factor and the second quantization factor;
[0106] The model score of the GNSS fault simulation model is determined based on the difference and sum.
[0107] In some possible implementations of the embodiments of this application, the GNSS fault simulation model to be evaluated is any one of multiple GNSS fault simulation models, and the fault data corresponding to the multiple GNSS fault simulation models have different dimensions.
[0108] In addition, in conjunction with the GNSS fault simulation model accuracy evaluation method in the above embodiments, this application also provides a computer-readable storage medium for implementation. This computer-readable storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement the GNSS fault simulation model accuracy evaluation method provided in this application. Examples of computer-readable storage media include non-transitory computer-readable media, such as ROM, RAM, magnetic disks, or optical disks.
[0109] This application provides a computer program product. When the instructions in the computer program product are executed by the processor of an electronic device, the electronic device executes the GNSS fault simulation model accuracy evaluation method provided in this application embodiment, and can achieve the same technical effect. To avoid repetition, it will not be described again here.
[0110] The electronic device may include a processor and a memory storing computer program instructions.
[0111] Specifically, the processor may include a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.
[0112] Memory may include mass storage for data or instructions. For example, and not limitingly, memory may include hard disk drives (HDDs), floppy disk drives, flash memory, optical disks, magneto-optical disks, magnetic tape, or Universal Serial Bus (USB) drives, or combinations of two or more of these. Where appropriate, memory may include removable or non-removable (or fixed) media. Where appropriate, memory may be internal or external to an electronic device. In some specific embodiments, memory is non-volatile solid-state memory.
[0113] In some specific embodiments, the memory may include read-only memory (ROM), random access memory (RAM), disk storage media devices, optical storage media devices, flash memory devices, and electrical, optical, or other physical / tangible memory storage devices. Therefore, typically, memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the GNSS fault simulation model accuracy evaluation method according to this application.
[0114] In some possible implementations of the embodiments of this application, the electronic device may be a terminal or other devices besides a terminal. For example, the electronic device may be a laptop, a handheld computer, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), etc., and may also be a server, network attached storage (NAS), etc. The embodiments of this application do not specifically limit the scope.
[0115] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.
[0116] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. Programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable read-only memory (EROM), floppy disks, compact disc read-only memory (CD-ROM), optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.
[0117] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.
[0118] The aspects of this disclosure have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.
[0119] The above description is merely a specific implementation of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.
Claims
1. A method for evaluating the accuracy of a GNSS fault simulation model, characterized in that, The method includes: K real fault data points are obtained from the real fault data corresponding to the GNSS fault simulation model to be evaluated, wherein the real fault data points belong to the same GNSS fault type, and K is a positive integer; M simulation fault data points are obtained from the simulation fault data generated by the GNSS fault simulation model, where M is a positive integer; Based on the real data distribution corresponding to the K real fault data and the simulation data distribution corresponding to the M simulated fault data, calculate the first bulldozer distance between the real data distribution and the simulation data distribution; Based on the distance of the first bulldozer, a first quantization factor is determined for evaluating the accuracy of the GNSS fault simulation model; The step of determining a first quantization factor for evaluating the accuracy of the GNSS fault simulation model based on the distance of the first bulldozer includes: The first quantization factor is determined according to the following formula. in, The first quantization factor, Where n is the distance to the first bulldozer, and n is the dimension of the fault data; The accuracy of the GNSS fault simulation model is evaluated based on the first quantization factor. The step of evaluating the accuracy of the GNSS fault simulation model based on the first quantization factor includes: Calculate the second bulldozer distance between the real data distributions of the two sets of real fault data, wherein the two sets of real fault data and the K real fault data belong to the same GNSS fault type; Based on the second bulldozer distance, determine the second quantization factor corresponding to the true data distribution of the two sets of true fault data; The model score of the GNSS fault simulation model is determined based on the first quantization factor and the second quantization factor. The accuracy of the GNSS fault simulation model is evaluated based on the model score.
2. The method according to claim 1, characterized in that, The step of determining the model score of the GNSS fault simulation model based on the first quantization factor and the second quantization factor includes: Based on the first quantization factor and the second quantization factor, determine the increase of the first quantization factor relative to the second quantization factor; Based on the increase, the model score of the GNSS fault simulation model is determined.
3. The method according to claim 1, characterized in that, The step of determining the model score of the GNSS fault simulation model based on the first quantization factor and the second quantization factor includes: Calculate the difference between the first quantization factor and the second quantization factor, and the sum of the first quantization factor and the second quantization factor; The model score of the GNSS fault simulation model is determined based on the difference and the sum.
4. The method according to claim 1, characterized in that, The GNSS fault simulation model to be evaluated is any one of multiple GNSS fault simulation models, and the fault data corresponding to the multiple GNSS fault simulation models have different dimensions.
5. A GNSS fault simulation model accuracy evaluation device, characterized in that, The device includes: The first acquisition module is used to acquire K real fault data from the real fault data corresponding to the GNSS fault simulation model to be evaluated, wherein the real fault data belong to the same GNSS fault type and K is a positive integer; The second acquisition module is used to acquire M simulation fault data from the simulation fault data generated by the GNSS fault simulation model, where M is a positive integer; The calculation module is used to calculate the first bulldozer distance between the real data distribution and the simulated data distribution based on the real data distribution corresponding to the K real fault data and the simulated data distribution corresponding to the M simulated fault data. The determination module is used to determine a first quantization factor for evaluating the accuracy of the GNSS fault simulation model based on the distance of the first bulldozer. The determining module is specifically used for: The first quantization factor is determined according to the following formula. in, The first quantization factor, Where n is the distance to the first bulldozer, and n is the dimension of the fault data; An evaluation module is used to evaluate the accuracy of the GNSS fault simulation model based on the first quantization factor. The evaluation module is specifically used for: Calculate the second bulldozer distance between the real data distributions of the two sets of real fault data, wherein the two sets of real fault data and the K real fault data belong to the same GNSS fault type; Based on the second bulldozer distance, determine the second quantization factor corresponding to the true data distribution of the two sets of true fault data; The model score of the GNSS fault simulation model is determined based on the first quantization factor and the second quantization factor. The accuracy of the GNSS fault simulation model is evaluated based on the model score.
6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions, which, when executed by a processor, implement the GNSS fault simulation model accuracy evaluation method as described in any one of claims 1-4.
7. A computer program product, characterized in that, When the instructions in the computer program product are executed by the processor of the electronic device, the electronic device performs the GNSS fault simulation model accuracy evaluation method as described in any one of claims 1-4.