Boundary interpolation accuracy determination method, device, equipment and storage medium

Abstract

The embodiment of the present invention provides a method, device, equipment and storage medium for determining the accuracy of boundary interpolation, the method comprising: obtaining target data, the target data including the location information of the target boundary at the target time and the atmospheric parameter estimation of each station in a plurality of stations within a preset range; determining the interpolation subset corresponding to each station of the target boundary based on the target data and the preset station selection strategy; calculating the average interpolation distance of the interpolation station pairs in the interpolation subset based on the interpolation subset corresponding to each station in the plurality of stations; determining the spatial absolute error of the interpolation station pairs in the interpolation subset based on the target data and the preset interpolation method; inputting the average interpolation distance and the spatial absolute error into a pre-trained interpolation accuracy evaluation model to obtain the interpolation accuracy of the target boundary. The method according to the embodiment of the present invention can reduce the actual demand for station establishment in the boundary range, and realize the effective evaluation of the boundary interpolation service performance when there is no monitoring station at the boundary.

Description

Technical Field

[0001] The present invention belongs to the field of positioning and monitoring, and in particular relates to a method, device, equipment and storage medium for determining boundary interpolation accuracy. Background Art

[0002] For the performance evaluation of conventional regional correction service, actual performance monitoring stations must be deployed near the corresponding sites, and then the corresponding monitoring quantities estimated from known sites are used as evaluation quantities to evaluate the performance of the correction service. However, in practical applications, evaluation methods that rely on actual site construction are difficult to implement in some cases.

[0003] For example, in the scenario of boundary interpolation accuracy assessment, the coverage of a single station on the boundary is usually limited, and the assessment of the overall large-scale irregular boundary requires the support of multiple station construction sites. However, in the actual boundary range (such as highway belts, national borders, etc.), there are many constraints on station construction and the cost of station construction is high. Therefore, it is difficult to effectively evaluate the boundary interpolation accuracy, that is, the boundary performance. Summary of the invention

[0004] The embodiments of the present invention provide a method, device, equipment and storage medium for determining boundary interpolation accuracy, which can reduce the demand for actual station construction in the boundary range and realize effective evaluation of boundary interpolation service performance when there is no monitoring station at the boundary.

[0005] In a first aspect, an embodiment of the present invention provides a method for determining boundary interpolation accuracy, the method comprising: acquiring target data, the target data including location information of a target boundary at a target time and atmospheric parameter estimates of each of a plurality of stations within a preset range; determining an interpolation subset corresponding to each of a plurality of stations at the target boundary based on the target data and a preset station selection strategy; calculating an average interpolation distance of interpolation station pairs in the interpolation subset based on the interpolation subset corresponding to each of the plurality of stations; determining a spatial absolute error of interpolation station pairs in the interpolation subset based on the target data and a preset interpolation method; and inputting the average interpolation distance and the spatial absolute error into a pre-trained interpolation accuracy evaluation model to obtain the interpolation accuracy of the target boundary.

[0006] In an optional implementation, the interpolation accuracy evaluation model includes a first sub-model and a second sub-model; the first sub-model is used to characterize the relationship between the average interpolation distance and the interpolation accuracy; the second sub-model is used to characterize the relationship between the spatial absolute error and the interpolation accuracy;

[0007] The average interpolation distance and spatial absolute error are input into the pre-trained interpolation accuracy evaluation model to obtain the interpolation accuracy of the target boundary, including:

[0008] The average interpolation distance is input into the pre-trained first sub-model to obtain the interpolation accuracy of the interpolation distance;

[0009] The spatial absolute error is input into the pre-trained second sub-model to obtain the interpolation accuracy of the spatial absolute error;

[0010] The interpolation accuracy of the target boundary is determined based on the interpolation accuracy of the interpolation distance and the interpolation accuracy of the spatial absolute error.

[0011] In an optional implementation, the interpolation accuracy of the target boundary is determined based on the interpolation accuracy of the interpolation distance and the interpolation accuracy of the spatial absolute error, specifically including:

[0012] The interpolation accuracy of the target boundary is determined based on the interpolation accuracy of the interpolation distance, the interpolation accuracy of the spatial absolute error, and a preset weight coefficient.

[0013] In an optional implementation, before the average interpolation distance and the spatial absolute error are input into a pre-trained interpolation accuracy assessment model, the method further includes:

[0014] Obtain a training sample set, the training sample set includes multiple training samples, each training sample includes an average interpolation distance and a spatial absolute error of a boundary, and label data, the label data is an interpolation accuracy corresponding to the average interpolation distance and the spatial absolute error;

[0015] The preset interpolation accuracy evaluation model is trained using the training sample set until the training stop condition is met, thereby obtaining the trained interpolation accuracy evaluation model.

[0016] In an optional implementation, before acquiring the target data, the method further includes:

[0017] Obtain observation files and correction number files for each of the multiple stations at the target time target boundary;

[0018] An atmospheric parameter estimate for each of the plurality of stations is determined based on an observation file and a correction file for each of the plurality of stations.

[0019] In an optional implementation, based on the target data and a preset site selection strategy, determining an interpolation subset corresponding to each site in a plurality of sites on the target boundary includes:

[0020] Based on the target data, determine information of each site in a plurality of sites within the target boundary;

[0021] Based on information of each site in the plurality of sites, determining a preset number of interpolation sites corresponding to each site;

[0022] Based on a preset number of interpolation sites corresponding to each site, an interpolation subset corresponding to each site is constructed.

[0023] In an optional implementation, determining the spatial absolute error of the interpolation site pairs in the interpolation subset based on the target data and a preset interpolation method includes:

[0024] Based on the target data and the preset interpolation method, the interpolation site weight corresponding to each interpolation site in the interpolation subset is calculated;

[0025] Based on the target data and the interpolation site weights, the spatial absolute errors of the interpolation site pairs in the interpolation subset are determined.

[0026] In a second aspect, an embodiment of the present invention provides a device for determining boundary interpolation accuracy, the device comprising:

[0027] A first acquisition module is configured to acquire target data, the target data including location information of a target boundary at a target time and an estimated atmospheric parameter of each of a plurality of sites within a preset range;

[0028] A first processing module is configured to determine an interpolation subset corresponding to each of a plurality of sites on a target boundary based on target data and a preset site selection strategy;

[0029] A calculation module is configured to calculate an average interpolation distance of interpolation site pairs in the interpolation subset based on the interpolation subset corresponding to each site in the plurality of sites;

[0030] A second processing module is configured to determine the spatial absolute error of the interpolation site pairs in the interpolation subset based on the target data and a preset interpolation method;

[0031] The interpolation accuracy evaluation module is configured to input the average interpolation distance and the spatial absolute error into a pre-trained interpolation accuracy evaluation model to obtain the interpolation accuracy of the target boundary.

[0032] In a third aspect, an embodiment of the present invention provides a device for determining boundary interpolation accuracy, the device comprising: a processor, and a memory storing computer program instructions; the processor reads and executes the computer program instructions to implement the boundary interpolation accuracy determination method provided in the first aspect and any optional implementation manner in the first aspect.

[0033] In a fourth aspect, an embodiment of the present invention provides a computer storage medium having computer program instructions stored thereon. When the computer program instructions are executed by a processor, the method for determining boundary interpolation accuracy provided in the first aspect and any optional implementation manner in the first aspect is implemented.

[0034] The boundary interpolation accuracy determination method, device, equipment and storage medium of the embodiment of the present invention establish an interpolation accuracy evaluation model, pre-learn the relationship between key influencing quantities (average interpolation distance and spatial absolute error) and interpolation accuracy, and can use measured data, i.e., target data, and preset station selection strategies and interpolation methods to calculate the average interpolation distance and determine the spatial absolute error; the average interpolation distance and the spatial absolute error are input into the pre-trained interpolation accuracy evaluation model to obtain the interpolation accuracy of the target boundary; it does not rely on the actual station construction within the boundary range, and realizes the effective evaluation of the boundary interpolation service performance when there is no monitoring station at the boundary. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the following is a brief introduction to the drawings required for use in the embodiment of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0036] Figure 1 It is a schematic flow chart of a method for determining boundary interpolation accuracy provided by an embodiment of the present invention;

[0037] Figure 2 It is a schematic diagram of a model flow of an interpolation performance evaluation method applicable to range boundaries provided by an embodiment of the present invention;

[0038] Figure 3 is a schematic diagram of the mapping relationship of the interpolation process in an embodiment of the present invention;

[0039] Figure 4 It is a schematic diagram of the flow of the interpolation performance evaluation method of boundary points provided by an embodiment of the present invention;

[0040] Figure 5 It is a structural schematic diagram of a device for determining boundary interpolation accuracy provided by an embodiment of the present invention;

[0041] Figure 6 It is a structural schematic diagram of a boundary interpolation accuracy determination device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0042] The features and exemplary embodiments of various aspects of the present invention will be described in detail below. In order to make the purpose, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present invention, rather than to limit the present invention. For those skilled in the art, the present invention can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present invention by illustrating examples of the present invention.

[0043] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0044] The performance evaluation of conventional regional correction number services is mainly concentrated near known sites, and the corresponding monitoring quantity estimated by the known sites is used as the evaluation quantity to evaluate the performance of the correction number of the corresponding service. However, in the boundary range of the service (such as national borders, provincial boundaries, etc.), it is usually difficult to effectively evaluate the boundary performance due to the actual station construction conditions. The conventional correction number service performance evaluation method is to establish corresponding monitoring stations in the area near the boundary, and judge whether the corresponding area can meet the performance requirements by estimating the detection quantity of the corresponding monitoring station.

[0045] The disadvantage of the existing regional correction number service performance evaluation technology is that actual performance monitoring stations must be deployed near the corresponding sites. In actual border areas, such as highway belts and national borders, there are many constraints on building stations at the borders, the cost of building stations is high, and the evaluation of border performance is largely subject to physical factors. Usually, the coverage of a single station on the border is limited, and the evaluation of the overall large-scale irregular border requires the support of multiple station construction sites, which further increases the cost of border performance monitoring and evaluation.

[0046] Based on the above problems, the present application provides a method, device, equipment and storage medium for determining boundary interpolation accuracy, which is suitable for effectively evaluating the performance of irregular boundary interpolation services when there is no actual monitoring station at the boundary, and significantly reducing the cost of building monitoring stations and performance evaluation costs of interpolation-based services in boundary environments.

[0047] In order to better understand the present application, before introducing the specific implementation methods of the present application, the technical terms used in describing the implementation methods of the present application are first introduced.

[0048] (1) Global Navigation Satellite System (GNSS) refers to all satellite navigation systems, including global, regional and enhanced systems, such as the US GPS, Russia's Glonass, Europe's Galileo, China's BeiDou Satellite Navigation System, and related augmentation systems, such as the US WAAS (Wide Area Augmentation System), Europe's EGNOS (European Geostationary Navigation Overlay System) and Japan's MSAS (Multi-purpose Transport Satellite Augmentation System), and also covers other satellite navigation systems that are under construction or to be built in the future. The international GNSS system is a complex combination of multiple systems, multiple levels and multiple modes.

[0049] (2) Troposphere Delay (TD): In the field of GNSS, troposphere delay is one of the sources of positioning error. Troposphere delay in satellite navigation positioning generally refers to the signal delay caused by electromagnetic wave signals passing through the non-ionized neutral atmosphere below 50 km in altitude.

[0050] (3) Precise Point Positioning (PPP): Precise point positioning refers to the use of precise satellite orbits and satellite clock errors calculated using observation data from several ground tracking stations around the world to locate and resolve the phase and pseudorange observations collected by a single receiver.

[0051] Based on the above technical terms, the relevant technologies of boundary interpolation accuracy, i.e., boundary interpolation performance evaluation, have been briefly introduced.

[0052] A method for determining the accuracy of boundary interpolation provided by an embodiment of the present application is specifically introduced below. This method can be implemented based on a boundary interpolation accuracy determination system and is described by taking the zenith tropospheric delay ZTD integrity monitoring boundary performance evaluation as an example. A certain number of monitoring stations are configured in each area, and the monitoring stations may not be monitoring stations on the boundary. The monitoring station can output the corresponding observation file, and can obtain the corresponding broadcast ephemeris file, orbital clock error, ocean tide and other related correction number files. The corresponding interpolation type service can select the corresponding station selection strategy and interpolation method according to actual needs. For example, the station selection strategy can select the 3-5 nearest stations, and the interpolation method can select inverse distance weighted or Kriging interpolation, etc.

[0053] Please refer to the attached Figure 1 A flow chart of a method for determining boundary interpolation accuracy is provided. The method may include steps S101-S105.

[0054] Step S101 , obtaining target data, where the target data includes location information of a target boundary at a target time and an estimated atmospheric parameter of each of a plurality of sites within a preset range.

[0055] The system can obtain target data of the target boundary to be evaluated. The target data may specifically include the observation file and correction number file of each station, or the sample point coordinates of the boundary station calculated based on the observation file and correction number file, and the atmospheric parameter estimation of each station, which may specifically be the tropospheric wet component estimation.

[0056] In a specific example, if Figure 2 As shown in Figure 2, the main monitoring quantity for ZTD integrity performance monitoring is the tropospheric wet component estimation P est,i First, the tropospheric wet component estimate P of all stations is calculated based on the observation file and the related correction file. est,i Based on the relevant input information, the precise single point positioning method is used to obtain the sta of each station after the accuracy converges. i The corresponding tropospheric wet component estimate P on (i=1,2,,…,N) est,i , where N is the total number of sites to be evaluated.

[0057] Step S102: determining an interpolation subset corresponding to each of a plurality of sites on a target boundary based on target data and a preset site selection strategy.

[0058] The station selection strategy may select a preset number of interpolation stations closest to each station, and the preset number may specifically be 3 to 5. An interpolation subset is constructed based on each interpolation station.

[0059] In one example, step S102 may include steps S1021 - S1023 .

[0060] Step S1021, based on the target data, determine the information of each site in the multiple sites of the target boundary.

[0061] Step S1022: based on the information of each site in the plurality of sites, determine a preset number of interpolation sites corresponding to each site.

[0062] Step S1023: construct an interpolation subset corresponding to each site based on a preset number of interpolation sites corresponding to each site.

[0063] Step S103: based on the interpolation subset corresponding to each site in the plurality of sites, calculate the average interpolation distance of the interpolation site pairs in the interpolation subset.

[0064] In a specific example, the system divides the evaluation sample area, and based on all the sites in the evaluation sample area, uses the existing site selection strategy to search for each site sta from all the sites. i The interpolation station subset {sta1,sta2,…,sta j}, using the tropospheric wet component estimate P for all stations in a given time period est,i , based on the existing interpolation method, the interpolated tropospheric wet component P of each station is estimated ip,i .

[0065] by Figure 3 As an example, let the tropospheric wet component of the estimated station obtained by interpolation be P ip,i , the estimated tropospheric wet component at the interpolation site is P est,j , j = 1, ..., N, where N = 3. The corresponding interpolation weight obtained by the interpolation method is a i,j The interpolation calculation formula can be expressed as follows:

[0066]

[0067] Statistics and sorting of each site sta i The corresponding average interpolation site distance D i and spatial absolute error E i .

[0068] Among them, the average interpolation site distance D i The interpolation site distance D of the interpolation site pair i,j The average value is:

[0069]

[0070] Step S104, determining the spatial absolute error of the interpolation site pairs in the interpolation subset based on the target data and a preset interpolation method.

[0071] In an example, step S104 may specifically include steps S1041 - S1042 .

[0072] Step S1041, based on the target data and a preset interpolation method, calculate the interpolation site weight corresponding to each interpolation site in the interpolation subset.

[0073] Step S1042, based on the target data and the interpolation site weights, determine the spatial absolute error of the interpolation site pairs in the interpolation subset.

[0074] In a specific example, the spatial absolute error E i The interpolation site weight a can be calculated using the interpolation method i,j , interpolation site monitoring quantity P j And the interpolation result P ip,i The calculation formula is as follows:

[0075]

[0076] Step S105, inputting the average interpolation distance and the spatial absolute error into a pre-trained interpolation accuracy evaluation model to obtain the interpolation accuracy of the target boundary.

[0077] The boundary interpolation accuracy determination method provided in this embodiment establishes an interpolation accuracy evaluation model, pre-learns the relationship between key influencing quantities (average interpolation distance and spatial absolute error) and interpolation accuracy, and can use measured data, i.e., target data, and preset station selection strategies and interpolation methods to calculate the average interpolation distance and determine the spatial absolute error; the average interpolation distance and the spatial absolute error are input into the pre-trained interpolation accuracy evaluation model to obtain the interpolation accuracy of the target boundary; it is independent of the actual station construction within the boundary range, and realizes effective evaluation of the boundary interpolation service performance when there is no monitoring station at the boundary.

[0078] In one embodiment, the interpolation accuracy evaluation model in step S104 includes a first sub-model and a second sub-model; the first sub-model is used to characterize the relationship between the average interpolation distance and the interpolation accuracy; the second sub-model is used to characterize the relationship between the spatial absolute error and the interpolation accuracy.

[0079] Step S104 may specifically include steps S1041-S1043.

[0080] Step S1041, inputting the average interpolation distance into the pre-trained first sub-model to obtain the interpolation accuracy of the interpolation distance;

[0081] Step S1042, inputting the spatial absolute error into the pre-trained second sub-model to obtain the interpolation accuracy of the spatial absolute error;

[0082] Step S1043, determining the interpolation accuracy of the target boundary based on the interpolation accuracy of the interpolation distance and the interpolation accuracy of the spatial absolute error.

[0083] In an example, step S1043 may specifically include: determining the interpolation accuracy of the target boundary based on the interpolation accuracy of the interpolation distance, the interpolation accuracy of the spatial absolute error, and a preset weight coefficient.

[0084] In one example, before step S104, the method may further include steps S105-S106.

[0085] Step S105, obtaining a training sample set, the training sample set includes multiple training samples, each training sample includes an average interpolation distance and a spatial absolute error of a boundary, and label data of the boundary, the label data is the interpolation accuracy corresponding to the average interpolation distance and the spatial absolute error.

[0086] Step S106, using the training sample set to train a preset interpolation accuracy assessment model until a training stop condition is met, thereby obtaining a trained interpolation accuracy assessment model.

[0087] In a specific example, the construction and training process of the interpolation accuracy evaluation model can be as follows:

[0088] Please refer to Figure 2 , based on all samples, fit the interpolation accuracy sample P i and the average interpolated site distance sample D i For example, a third-order linear fit can be used to obtain the interpolation accuracy P d and the average interpolation site distance D.

[0089] P d =α3D 3 +α2D 2 +α1D+α0

[0090] Based on all samples, fit the interpolation accuracy samples Pi and the spatial absolute error samples Ei. For example, a third-order linear fit can be used to fit the relationship between the interpolation accuracy Pi and the average interpolation station distance Ei.

[0091] P e =β3E 3 +β2E 2 +β1E+β0

[0092] Based on the preset weight coefficients, such as and are each taken as 0.5. Combined with the fitting to obtain the influence of the average interpolation station distance on the interpolation accuracy and the influence of the spatial absolute error on the interpolation accuracy, an interpolation accuracy evaluation model under the influence of double factors can be obtained.

[0093] P=γ1P d +γ2P e

[0094] in,

[0095] γ1+γ2=1

[0096] In one embodiment, before step S101, the method may further include steps S107-S108.

[0097] Step S107, obtaining the observation file and correction number file of each station in the plurality of stations at the target time target boundary.

[0098] Step S108, determining an estimate of the tropospheric wet component of each of the multiple stations based on the observation file and the correction file of each of the multiple stations.

[0099] In a specific example, after the model is established, the interpolation performance evaluation method of the boundary points is as follows: Figure 4 shown.

[0100] Based on the coordinates of the boundary sample points to be evaluated, a given site selection strategy can obtain an interpolation site subset, and then based on the coordinates of the interpolation site subset, the average interpolation site distance can be obtained;

[0101] The spatial absolute error can be calculated based on the interpolation subset estimator and interpolation solution of the time period to be evaluated;

[0102] Based on the obtained average interpolation site distance and spatial absolute error, and by bringing them into the interpolation accuracy evaluation model, the interpolation accuracy of the boundary points can be obtained, which can serve as a reference for whether the boundary points can meet the corresponding service performance requirements.

[0103] The above embodiment uses a large sample statistical method to fit the influence relationship of key influencing quantities (average interpolation distance and spatial absolute error) on interpolation deviation. The average interpolation distance and spatial absolute error can be analyzed based on measured data under a specific station selection strategy and interpolation method, and do not rely on the actual station construction in the boundary range, so as to achieve effective evaluation of the boundary interpolation service performance when there is no monitoring station at the boundary.

[0104] Based on the boundary interpolation accuracy determination method provided in the above embodiment, correspondingly, the embodiment of the present application also provides a boundary interpolation accuracy determination device, please refer to Figure 5 ,include:

[0105] A first acquisition module 501 is configured to acquire target data, the target data including location information of a target boundary at a target time and an estimated atmospheric parameter of each of a plurality of sites within a preset range;

[0106] The first processing module 502 is configured to determine an interpolation subset corresponding to each of a plurality of sites on a target boundary based on target data and a preset site selection strategy;

[0107] The calculation module 503 is configured to calculate the average interpolation distance of the interpolation site pairs in the interpolation subset based on the interpolation subset corresponding to each site in the plurality of sites;

[0108] The second processing module 504 is configured to determine the spatial absolute error of the interpolation site pairs in the interpolation subset based on the target data and a preset interpolation method;

[0109] The interpolation accuracy evaluation module 505 is configured to input the average interpolation distance and the spatial absolute error into a pre-trained interpolation accuracy evaluation model to obtain the interpolation accuracy of the target boundary.

[0110] The boundary interpolation accuracy determination device provided in this embodiment has a built-in interpolation accuracy evaluation module, which can use the measured data obtained by the first acquisition module, that is, the target data and the preset station selection strategy and interpolation method, to calculate the average interpolation distance and determine the spatial absolute error through the first processing module, the calculation module and the second processing module; the average interpolation distance and the spatial absolute error are input into the interpolation accuracy evaluation module to obtain the interpolation accuracy of the target boundary; it does not rely on the actual station construction within the boundary range, and realizes the effective evaluation of the boundary interpolation service performance when there is no monitoring station at the boundary.

[0111] In one embodiment, the interpolation accuracy assessment model in the interpolation accuracy assessment module 505 includes a first sub-model and a second sub-model; the first sub-model is used to characterize the relationship between the average interpolation distance and the interpolation accuracy; the second sub-model is used to characterize the relationship between the spatial absolute error and the interpolation accuracy.

[0112] The interpolation accuracy evaluation module 505 may specifically include:

[0113] The first evaluation unit is configured to input the average interpolation distance into a pre-trained first sub-model to obtain an interpolation accuracy of the interpolation distance.

[0114] The second evaluation unit is configured to input the spatial absolute error into a pre-trained second sub-model to obtain an interpolation accuracy of the spatial absolute error.

[0115] The interpolation accuracy determination unit is configured to determine the interpolation accuracy of the target boundary based on the interpolation accuracy of the interpolation distance and the interpolation accuracy of the spatial absolute error.

[0116] In one example, the interpolation accuracy determination unit is specifically configured to determine the interpolation accuracy of the target boundary based on the interpolation accuracy of the interpolation distance, the interpolation accuracy of the spatial absolute error, and a preset weight coefficient.

[0117] In one embodiment, the device may further include a second acquisition module and a model training module.

[0118] The second acquisition module is configured to obtain a training sample set before inputting the average interpolation distance and the spatial absolute error into a pre-trained interpolation accuracy evaluation model. The training sample set includes multiple training samples, each training sample includes the average interpolation distance and the spatial absolute error of the boundary, and the label data of the boundary, and the label data is the interpolation accuracy corresponding to the average interpolation distance and the spatial absolute error.

[0119] The model training module is configured to train a preset interpolation accuracy evaluation model using a training sample set until a training stop condition is met, thereby obtaining a trained interpolation accuracy evaluation model.

[0120] In one embodiment, the device may further include a third acquisition module and a data determination module.

[0121] The third acquisition module is configured to acquire the observation file and the correction number file of each station in the plurality of stations at the target time target boundary before acquiring the target data.

[0122] The data determination module is configured to determine an estimate of an atmospheric parameter for each of the plurality of stations based on an observation file and a correction file for each of the plurality of stations.

[0123] In one embodiment, the first processing module 502 may specifically include a first judgment unit, a second judgment unit and an interpolation subset construction unit.

[0124] The first determination unit is configured to determine information of each site in a plurality of sites of a target boundary based on the target data.

[0125] The second determination unit is configured to determine a preset number of interpolation sites corresponding to each site based on information of each site in the plurality of sites.

[0126] The interpolation subset construction unit is configured to construct an interpolation subset corresponding to each site based on a preset number of interpolation sites corresponding to each site.

[0127] In one embodiment, the second processing module 504 may specifically include a weight calculation unit and a spatial absolute error determination unit.

[0128] The weight calculation unit is configured to calculate the interpolation site weight corresponding to each interpolation site in the interpolation subset based on the target data and a preset interpolation method.

[0129] The spatial absolute error determination unit is configured to determine the spatial absolute error of the interpolation site pairs in the interpolation subset based on the target data and the interpolation site weights.

[0130] The boundary interpolation accuracy determination method provided in the above embodiments can be obtained by Figure 6 The accuracy of the boundary interpolation shown determines the device implementation.

[0131] The boundary interpolation accuracy determination device may include a processor 601 and a memory 602 storing computer program instructions.

[0132] Specifically, the processor 601 may include a CPU, or an Application Specific Integrated Circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present invention.

[0133] The memory 602 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 602 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In one example, the memory 602 may include a removable or non-removable (or fixed) medium, or the memory 602 is a non-volatile solid-state memory. The memory 602 may be inside or outside the integrated gateway disaster recovery device.

[0134] In one example, the memory 602 may be a read-only memory (ROM). In one example, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM), or a flash memory, or a combination of two or more of these.

[0135] The memory 602 may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage media device, an optical storage media device, a flash memory device, an electrical, optical or other physical / tangible memory storage device. Thus, in general, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) 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 method according to an aspect of the present disclosure.

[0136] The processor 601 reads and executes the computer program instructions stored in the memory 602 to implement the object query method provided by any of the above embodiments and achieve the corresponding technical effects achieved by the method, which will not be repeated here for the sake of brevity.

[0137] In one example, the boundary interpolation accuracy determination device may further include a communication interface 603 and a bus 610. Figure 6 As shown, the processor 601, the memory 602, and the communication interface 603 are connected via a bus 610 and communicate with each other.

[0138] The communication interface 603 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiment of the present invention.

[0139] Bus 610 includes hardware, software or both, and couples the components of online data traffic billing equipment to each other. For example, but not limitation, the bus may include Accelerated Graphics Port (AGP) or other graphics bus, Enhanced Industry Standard Architecture (EISA) bus, Front Side Bus (FSB), Hyper Transport (HT) interconnection, Industry Standard Architecture (ISA) bus, InfiniBand interconnection, Low Pin Count (LPC) bus, Memory bus, Micro Channel Architecture (MCA) bus, Peripheral Component Interconnect (PCI) bus, PCI-Express (PCI-X) bus, Serial Advanced Technology Attachment (SATA) bus, Video Electronics Standards Association Local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 610 may include one or more buses. Although the embodiments of the present invention describe and illustrate specific buses, the present invention considers any suitable bus or interconnection.

[0140] The boundary interpolation accuracy determination device can use the measured data, i.e., the target data, and the preset station selection strategy and interpolation method to calculate the average interpolation distance and determine the spatial absolute error; the average interpolation distance and the spatial absolute error are input into a pre-trained interpolation accuracy evaluation model to obtain the interpolation accuracy of the target boundary; it is independent of the actual station construction within the boundary range, and realizes the effective evaluation of the boundary interpolation service performance when there is no monitoring station at the boundary.

[0141] In combination with the boundary interpolation precision determination method in the above embodiment, the embodiment of the present invention can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by a processor, any one of the boundary interpolation precision determination methods in the above embodiment is implemented.

[0142] It should be clear that the present invention is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present invention.

[0143] 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, it can be, for example, an electronic circuit, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), appropriate firmware, plug-in, function card, etc. When implemented in software, the elements of the present invention are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or communication link by a data signal carried in a carrier. "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 ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (Radio Frequency, RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0144] It should also be noted that the exemplary embodiments mentioned in the present invention describe some methods or systems based on a series of steps or devices. However, the present invention 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 from the embodiments, or several steps can be performed simultaneously.

[0145] Aspects of the present disclosure are described above with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiment of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram 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 device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. 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 can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0146] The above is only a specific implementation of the present invention. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the system, module and unit described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. It should be understood that the protection scope of the present invention is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be covered within the protection scope of the present invention.

Claims

1. A method for determining boundary interpolation accuracy, characterized in that: include: Acquire target data, the target data including location information of a target boundary at a target time and an estimated atmospheric parameter of each of a plurality of sites within a preset range; Based on the target data and a preset site selection strategy, determine an interpolation subset corresponding to each site in a plurality of sites on the target boundary; Based on the interpolation subset corresponding to each site in the plurality of sites, calculating the average interpolation distance of the interpolation site pairs in the interpolation subset; Determining the spatial absolute error of the interpolation site pairs in the interpolation subset based on the target data and a preset interpolation method; Inputting the average interpolation distance and the spatial absolute error into a pre-trained interpolation accuracy evaluation model to obtain the interpolation accuracy of the target boundary; The calculation formula of the spatial absolute error is include: Among them, E i is the spatial absolute error, a i,j is the interpolation site weight, P j is the interpolation site monitoring quantity, P ip,i is the interpolation result, i is the interpolation site number, and N is the total number of interpolation sites; Before inputting the average interpolation distance and the spatial absolute error into a pre-trained interpolation accuracy evaluation model, the method further includes: Acquire a training sample set, the training sample set comprising a plurality of training samples, each of the training samples comprising an average interpolation distance and a spatial absolute error of a boundary, and label data of the boundary, the label data being an interpolation accuracy corresponding to the average interpolation distance and the spatial absolute error; The preset interpolation accuracy evaluation model is trained using the training sample set until a training stop condition is met, thereby obtaining a trained interpolation accuracy evaluation model.

2. The method according to claim 1, characterized in that The interpolation accuracy evaluation model includes a first sub-model and a second sub-model; the first sub-model is used to characterize the relationship between the average interpolation distance and the interpolation accuracy; the second sub-model is used to characterize the relationship between the spatial absolute error and the interpolation accuracy; The step of inputting the average interpolation distance and the spatial absolute error into a pre-trained interpolation accuracy evaluation model to obtain the interpolation accuracy of the target boundary includes: Inputting the average interpolation distance into a pre-trained first sub-model to obtain an interpolation accuracy of the interpolation distance; Inputting the spatial absolute error into a pre-trained second sub-model to obtain an interpolation accuracy of the spatial absolute error; The interpolation accuracy of the target boundary is determined based on the interpolation accuracy of the interpolation distance and the interpolation accuracy of the spatial absolute error.

3. The method according to claim 2, characterized in that The determining the interpolation accuracy of the target boundary based on the interpolation accuracy of the interpolation distance and the interpolation accuracy of the spatial absolute error specifically includes: The interpolation accuracy of the target boundary is determined based on the interpolation accuracy of the interpolation distance, the interpolation accuracy of the spatial absolute error, and a preset weight coefficient.

4. The method according to claim 1, characterized in that: Before acquiring the target data, the method further includes: Obtain observation files and correction number files for each of the multiple stations at the target time target boundary; An estimate of an atmospheric parameter for each of the plurality of stations is determined based on the observation file and the correction file for each of the plurality of stations.

5. The method according to claim 1, characterized in that The step of determining, based on the target data and a preset site selection strategy, an interpolation subset corresponding to each site in a plurality of sites on the target boundary includes: Based on the target data, determine information of each site in a plurality of sites of the target boundary; Based on the information of each site in the plurality of sites, determining a preset number of interpolation sites corresponding to each site; Based on the preset number of interpolation sites corresponding to each site, an interpolation subset corresponding to each site is constructed.

6. The method according to claim 1, characterized in that The determining, based on the target data and a preset interpolation method, the spatial absolute error of the interpolation site pairs in the interpolation subset comprises: Based on the target data and a preset interpolation method, calculating the interpolation site weight corresponding to each interpolation site in the interpolation subset; Based on the target data and the interpolation site weights, the spatial absolute errors of the interpolation site pairs in the interpolation subset are determined.

7. A device for determining boundary interpolation accuracy, characterized in that: include: A first acquisition module is configured to acquire target data, wherein the target data includes location information of a target boundary at a target time and an estimated atmospheric parameter of each of a plurality of sites within a preset range; A first processing module is configured to determine an interpolation subset corresponding to each of a plurality of sites on the target boundary based on the target data and a preset site selection strategy; A calculation module is configured to calculate an average interpolation distance of interpolation site pairs in the interpolation subset based on the interpolation subset corresponding to each site in the plurality of sites; A second processing module is configured to determine the spatial absolute error of the interpolation site pairs in the interpolation subset based on the target data and a preset interpolation method; The calculation formula of the spatial absolute error is include: Among them, E i is the spatial absolute error, a i,j is the interpolation site weight, P j is the interpolation site monitoring quantity, P ip,i is the interpolation result, i is the interpolation site number, and N is the total number of interpolation sites; An interpolation accuracy assessment module is configured to input the average interpolation distance and the spatial absolute error into a pre-trained interpolation accuracy assessment model to obtain the interpolation accuracy of the target boundary; The second acquisition module is configured to obtain a training sample set before inputting the average interpolation distance and the spatial absolute error into a pre-trained interpolation accuracy evaluation model, wherein the training sample set includes a plurality of training samples, each training sample includes an average interpolation distance and a spatial absolute error of a boundary, and label data of the boundary, wherein the label data is an interpolation accuracy corresponding to the average interpolation distance and the spatial absolute error; The model training module is configured to train a preset interpolation accuracy evaluation model using a training sample set until a training stop condition is met, thereby obtaining a trained interpolation accuracy evaluation model.

8. A device for determining boundary interpolation accuracy, characterized in that: The device comprises: a processor and a memory storing computer program instructions; the processor reads and executes the computer program instructions to implement the boundary interpolation accuracy determination method according to any one of claims 1-6.

9. A computer storage medium, characterized in that The computer storage medium stores computer program instructions, and when the computer program instructions are executed by the processor, the method for determining the boundary interpolation accuracy according to any one of claims 1 to 6 is implemented.

Images