Track similarity evaluation method, device, electronic device and storage medium

Abstract

The present invention provides a track similarity assessment method, device, electronic device and storage medium, which can obtain various index data that characterize the degree of deviation between the preset track and the actual track. Then determine the number of qualified index data in each index data. When the number of qualified index data is not less than one, the preset track and the actual track are processed respectively based on the preset similarity algorithm and the preset distance algorithm to obtain the various deviation distances between the preset track and the actual track. Each deviation distance is processed based on the preset normalization algorithm to obtain the normalized result of each deviation distance. Each of the normalized results is processed based on the preset scoring algorithm to obtain the similarity score of the preset track and the actual track. When the number of qualified index data is not equal to the number of index data, the score of each index data needs to be subtracted. The present invention realizes the quantitative evaluation of the similarity between the planned track and the actual track of flying equipment such as drones.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle testing, and in particular to a track similarity evaluation method, device, electronic equipment and storage medium. Background Art

[0002] To ensure the stability, safety, and accuracy of drone flight in drone inspection systems, evaluating the deviation between the actual drone flight trajectory and the preset trajectory is a key verification method. This helps testers quantify test results and more objectively evaluate drone performance.

[0003] Currently, when evaluating drone similarity, the first step is to obtain the drone's actual three-dimensional flight track data using a recording and positioning module. This track data is then pre-processed using methods such as the Douglas-Peucker algorithm and interpolation. A mathematically based algorithm for calculating track similarity is then used to calculate similarity. Existing evaluation methods are unable to provide a comprehensive and quantitative assessment of track similarity. Summary of the Invention

[0004] In order to solve the problems of difficult quantification and complex evaluation in the existing technology, the present invention provides a track similarity evaluation method, device, electronic device and storage medium, which have the characteristics of accurate quantitative evaluation.

[0005] A track similarity evaluation method provided according to a specific embodiment of the present invention includes:

[0006] Obtain various indicator data representing the degree of deviation between the preset track and the actual track;

[0007] Determine the number of qualified indicator data in each indicator data based on the similarity evaluation index, wherein the qualified indicator data is the indicator data in each indicator data that meets the corresponding benchmark data requirements in the similarity evaluation index;

[0008] When the number of qualified index data is not less than one, the preset track and the actual track are processed based on a preset similarity algorithm and a preset distance algorithm respectively to obtain each deviation distance between the preset track and the actual track;

[0009] Processing each of the deviation distances based on a preset normalization algorithm to obtain a normalized result of each of the deviation distances;

[0010] Processing each of the normalized results based on a preset scoring algorithm to obtain a similarity score between the preset track and the actual track;

[0011] When the number of the qualified indicator data is not equal to the number of the indicator data, the score of each indicator data is subtracted from the similarity score, and the score of each indicator data is obtained by processing each indicator data and the benchmark data corresponding to each indicator data by a preset scoring algorithm.

[0012] Furthermore, the obtaining of various indicator data representing the degree of deviation between the preset track and the actual track includes:

[0013] Based on the distance between each collection point of the preset track and the corresponding collection point in the actual track, a maximum deviation distance, an average value of the deviation distance, and a standard deviation of the deviation distance are obtained, respectively, which characterize the degree of deviation between the preset track and the actual track.

[0014] Furthermore, the determining the number of qualified indicator data in each indicator data based on the similarity evaluation index includes:

[0015] Comparing the maximum deviation distance with a reference deviation distance to determine whether the maximum deviation distance is qualified;

[0016] Comparing the average value of the deviation distances with a benchmark average value to determine whether the average value of the deviation distances is qualified;

[0017] The standard deviation of the deviation distance is compared with the reference standard deviation to determine whether the standard deviation of the deviation distance is qualified.

[0018] Furthermore, when the number of qualified index data is not less than one, the preset track and the actual track are processed based on a preset similarity algorithm and a preset distance algorithm respectively to obtain each deviation distance between the preset track and the actual track, including:

[0019] Processing the preset track and the actual track based on a dynamic time normalization algorithm to obtain a first deviation distance;

[0020] Processing the preset track and the actual track based on a longest common string algorithm to obtain a second deviation distance;

[0021] Processing the preset track and the actual track based on a Fréchet distance algorithm to obtain a third deviation distance;

[0022] The preset track and the actual track are processed based on a Hausdorff distance algorithm to obtain a fourth deviation distance.

[0023] Furthermore, the processing of each of the deviation distances based on a preset normalization algorithm to obtain a normalized result of each of the deviation distances includes:

[0024] based on

[0025] DTW_score=1-diffdis_DTW / (diffdis_DTW+diffdis_FD+diffdis_HD);

[0026] LCSS_score=diffdis_LCSS;

[0027] FD_score=1-diffdis_FD / (diffdis_DTW+diffdis_FD+diffdis_HD);

[0028] HD_score=1-diffdis_HD / (diffdis_DTW+diffdis_FD+diffdis_HD);

[0029] The normalized results of each deviation distance are obtained respectively, DTW_score is the planning result of the first deviation distance, LCSS_score is the planning result of the second deviation distance, FD_score is the planning result of the third deviation distance, HD_score is the planning result of the fourth deviation distance, diffdis_DTW is the first deviation distance, diffdis_LCSS is the second deviation distance, diffdis_FD is the third deviation distance, and diffdis_HD is the fourth deviation distance.

[0030] Furthermore, the processing of each normalized result based on a preset scoring algorithm to obtain a similarity score between the preset track and the actual track includes:

[0031] based on

[0032] score=a*(DTW_score+LCSS_score)+b*(FD_score+HD_score)+c*p_score;

[0033] The similarity score is obtained, where score is the similarity score, p_score is the score given by manual participation, a, b, and c are all weight coefficients, and the sum of a, b, and c is equal to 1.

[0034] Furthermore, when the number of the qualified indicator data is not equal to the number of the indicator data, the score of each indicator data is subtracted from the similarity score to obtain a final score, and the score of each indicator data is obtained by processing each indicator data and the benchmark data corresponding to each indicator data by a preset scoring algorithm, including:

[0035] based on

[0036] final_score=score–(case1_diff_score+case2_diff_score+case3_diff_score);

[0037] case1_diff_score=|dis-maxdev_Dis| / maxdev_Dis;

[0038] case2_diff_score=|avr-maxdev_Avr| / maxdev_Avr;

[0039] case3_diff_score=|std-maxdev_Std| / maxdev_Std;

[0040] Get the final score, final_score is the final score, case1_diff_score is the score of the maximum deviation distance, case2_diff_score is the score of the average value of the deviation distance, case3_diff_score is the score of the standard deviation of the deviation distance, dis is the maximum deviation distance, maxdev_Dis is the benchmark deviation distance, avr is the average value of the deviation distance, maxdev_Avr is the benchmark average value, std is the standard deviation of the deviation distance, and maxdev_Std is the benchmark standard deviation.

[0041] A track similarity evaluation device provided according to a specific embodiment of the present invention includes:

[0042] An index acquisition module is used to obtain various index data representing the degree of deviation between the preset track and the actual track;

[0043] An indicator determination module is used to determine the number of qualified indicator data in each indicator data based on the similarity evaluation index, wherein the qualified indicator data is the indicator data in each indicator data that meets the corresponding benchmark data requirements in the similarity evaluation index;

[0044] a similarity calculation module, configured to, when the number of qualified index data is not less than one, process the preset track and the actual track based on a preset similarity algorithm and a preset distance algorithm respectively to obtain each deviation distance between the preset track and the actual track;

[0045] A normalization module, configured to process each of the deviation distances based on a preset normalization algorithm to obtain a normalized result of each of the deviation distances;

[0046] a scoring module, configured to process each of the normalized results based on a preset scoring algorithm to obtain a similarity score between the preset track and the actual track; and

[0047] an adjustment module for, when the number of the qualified indicator data is not equal to the number of the indicator data, subtracting the score of each indicator data from the similarity score, where the score of each indicator data is obtained by processing each indicator data and the benchmark data corresponding to each indicator data by a preset scoring algorithm.

[0048] An electronic device provided according to a specific embodiment of the present invention includes: a memory and a processor;

[0049] The memory is used to store programs;

[0050] The processor is used to execute the program to implement the various steps of the track similarity evaluation method described above.

[0051] According to a specific embodiment of the present invention, a storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, each step of the track similarity evaluation method described above is implemented.

[0052] The track similarity evaluation method provided by the present invention can obtain various index data that characterize the degree of deviation between the preset track and the actual track. Then, based on the similarity evaluation index, the number of qualified index data in each index data is determined, wherein the qualified index data is the index data in each index data that meets the corresponding benchmark data requirements in the similarity evaluation index. When the number of qualified index data is not less than one, the preset track and the actual track are processed respectively based on the preset similarity algorithm and the preset distance algorithm to obtain each deviation distance between the preset track and the actual track. Each deviation distance is processed based on the preset normalization algorithm to obtain a normalized result of each deviation distance. Each of the normalized results is processed based on the preset scoring algorithm to obtain a similarity score between the preset track and the actual track. When the number of qualified index data is not equal to the number of index data, the score of each index data is subtracted from the similarity score, wherein the score of each index data is obtained by processing each index data and the benchmark data corresponding to each index data by the preset scoring algorithm. This track similarity assessment method realizes the quantitative evaluation of the similarity between the planned track and the actual track of flight equipment such as drones, and presents the similarity in the form of specific score values. It can provide a standard and unified evaluation of the completion of flight missions, reducing personnel's subjective assumptions and large-scale data analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0054] Figure 1 is a flowchart of a method for evaluating track similarity according to an exemplary embodiment;

[0055] Figure 2 is a structural diagram of a track provided according to an exemplary embodiment;

[0056] Figure 3 is a comparison diagram of a preset track and an actual track provided according to an exemplary embodiment;

[0057] Figure 4 is a structural diagram of a track similarity evaluation device provided according to an exemplary embodiment;

[0058] Figure 5 is a structural diagram of an electronic device provided according to an exemplary embodiment. DETAILED DESCRIPTION

[0059] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0060] Reference Figure 1 As shown, an embodiment of the present invention provides a track similarity evaluation method, which may include the following steps:

[0061] 101. Obtain various indicator data representing the degree of deviation between the preset track and the actual track.

[0062] Reference Figure 2As shown, when evaluating the trajectory of drones and other flight equipment, the standard or preset trajectory used can include straight segments, Z-shaped segments, curved segments, and S-bend segments. During testing, the actual measured trajectory must meet trajectory specifications and constraints, including: coverage of straight segments, curved segments, S-bend segments, and Z-bend segments; minimum requirements for the total length of straight segments and continuous broken line segments; and requirements for the number of curved segments, S-bend segments, and Z-bend segments. The data required for usable collection points varies for different segments. For example, a straight segment requires the latitude and longitude coordinates of the starting point, the end point, and the number of sampling points. A Z-shaped segment requires the latitude and longitude coordinates of the starting point, the end point, the latitude and longitude coordinates of inflection point 1, and the latitude and longitude coordinates of inflection point 2. A curved segment requires the latitude and longitude coordinates of the starting point, the center point, the radius length R1 (unit: meter), and the angle θ1 (unit: degree). The S-curve segment requires the latitude and longitude coordinates of the starting point, the latitude and longitude coordinates of center 1, the radius length R1 (unit: m), the angle θ1 (unit: deg), the latitude and longitude coordinates of center 2, the radius length R2 (unit: m), and the angle θ2 (unit: deg). The ranges of each angle and the length of each radius can be set according to actual application conditions and are not limited by the present invention.

[0063] Based on the drone's flight performance requirements, the distance between each acquisition point on the actual track and the corresponding acquisition point on the preset track can be calculated and compared to determine the maximum deviation distance (dis). The average value (avr) of the deviation distances between the actual and preset tracks, as well as the standard deviation (std) of the deviation distances between the actual and preset tracks, can then be calculated.

[0064] 102. Determine the number of qualified indicator data in each indicator data based on the similarity evaluation index, where the qualified indicator data is indicator data in each indicator data that meets the corresponding benchmark data requirement in the similarity evaluation index.

[0065] Compare the evaluation index with the obtained index data, and make a judgment to obtain qualified index data that meets the requirements. The maximum deviation distance is compared with the benchmark deviation distance, the average value of the deviation distance is compared with the benchmark average value, and the standard deviation of the deviation distance is compared with the benchmark standard deviation. That is, by judging whether there is a distance dis>maxdev_Dis, an average value avr>maxdev_Avr, and std>maxdev_Std, where maxdev_Dis is the benchmark deviation distance, that is, at any moment of the flight, the distance between the actual track of the drone and the corresponding point of the preset track shall not be greater than the maximum deviation distance. maxdev_Avr is the benchmark average value, that is, throughout the flight, the average value of the deviation distances of all points to points shall not exceed the maximum deviation average value. maxdev_Std is the benchmark standard deviation, that is, throughout the flight, the standard deviation of the deviation distances of all points to points shall not be greater than the specified standard deviation. For example, refer to Figure 3 As shown, the upper part is the actual trajectory and the lower part is the preset trajectory. The maximum deviation distance between the two trajectories is 2.3m, which is smaller than the required benchmark deviation value and is qualified. The standard deviation is 1.2m, which is smaller than the benchmark standard deviation of 2.5m and is also qualified.

[0066] If all of the above criteria are met, and any indicator data exceeds the benchmark, the actual track evaluation result is deemed unqualified. If only one or two of the above criteria are met, the following steps can be performed, but the corresponding score will be deducted. If none of the above criteria are met, the actual track evaluation result will proceed to the following stage without any score deduction.

[0067] 103. When the number of qualified indicator data is not less than one, the preset track and the actual track are processed based on the preset similarity algorithm and the preset distance algorithm respectively to obtain the deviation distances between the preset track and the actual track.

[0068] The DTW algorithm (dynamic time warping algorithm) is used to perform a distance-based similarity evaluation on the preset track and the actual track data to obtain the first deviation distance diffdis_DTW. The result range is [0, +∞]. The larger the data, the greater the deviation.

[0069] The LCSS algorithm (Longest Common String algorithm) is selected to perform a distance-based similarity judgment on the preset track and the actual track data to obtain the second deviation distance diffdis_LCSS. The result range is [0,1]. The larger the data, the smaller the deviation.

[0070] The Fréchet distance algorithm is selected to perform distance-based similarity judgment on the preset track and the actual track data to obtain the third deviation distance diffdis_FD. The result interval is [0,+∞]. The larger the data, the greater the deviation.

[0071] The Hausdorff distance algorithm is selected to perform distance-based similarity judgment on the preset track and the actual track data to obtain the fourth deviation distance diffdis_HD. The result interval is [0,+∞]. The larger the data, the greater the deviation.

[0072] 104. Process each of the deviation distances based on a preset normalization algorithm to obtain a normalized result of each of the deviation distances.

[0073] The obtained deviation distances are normalized as follows:

[0074] based on

[0075] DTW_score=1-diffdis_DTW / (diffdis_DTW+diffdis_FD+diffdis_HD);

[0076] LCSS_score=diffdis_LCSS;

[0077] FD_score=1-diffdis_FD / (diffdis_DTW+diffdis_FD+diffdis_HD);

[0078] HD_score=1-diffdis_HD / (diffdis_DTW+diffdis_FD+diffdis_HD);

[0079] The normalized results of each deviation distance are obtained respectively. DTW_score is the planning result of the first deviation distance, LCSS_score is the planning result of the second deviation distance, FD_score is the planning result of the third deviation distance, and HD_score is the planning result of the fourth deviation distance.

[0080] 105. Process each normalized result based on a preset scoring algorithm to obtain a similarity score between the preset track and the actual track.

[0081] Based on the comprehensive consideration of distance and shape, the scores are scored using a weighted approach, as follows:

[0082] score=a*(DTW_score+LCSS_score)+b*(FD_score+HD_score)+c*p_score.

[0083] Where score is the similarity score, p_score is the manual score, which can generally be 0, a, b, and c are weight coefficients, and the sum of a, b, and c is equal to 1. For example, a = 0.3, b = 0.7.

[0084] It is understandable that those skilled in the art may adjust the coefficients according to actual needs, and the present invention does not limit this.

[0085] 106. When the number of qualified indicator data is not equal to the number of indicator data, the score of each indicator data is subtracted from the similarity score, where the score of each indicator data is obtained by processing each indicator data and the benchmark data corresponding to each indicator data using a preset scoring algorithm.

[0086] Specifically, considering the satisfaction of the above-mentioned hard indicators, the final score needs to deduct the indicator score:

[0087] final_score=score-(case1_diff_score+case2_diff_score+case3_diff_score);

[0088] Among them, final_score is the final score, case1_diff_score is the score of the maximum deviation distance, case2_diff_score is the score of the average deviation distance, and case3_diff_score is the score of the standard deviation of the deviation distance.

[0089] in

[0090] case1_diff_score=|dis-maxdev_Dis| / maxdev_Dis;

[0091] case2_diff_score=|avr-maxdev_Avr| / maxdev_Avr;

[0092] case3_diff_score=|std-maxdev_Std| / maxdev_Std;

[0093] When the maximum deviation distance, the average deviation distance, and the standard deviation of the deviation distance are all qualified, diff_score = 0. When only one or two of the three indicator data are qualified, the corresponding scores can be calculated according to the above three formulas.

[0094] This track similarity assessment method uses the hard indicator data of UAV tracks and distance-based and shape-based algorithms to conduct a multi-dimensional, flexible, and quantitative similarity assessment of the actual flight conditions of UAVs using the data of preset tracks and actual tracks. This provides UAV track analysts with a standardized and unified evaluation of the completion of flight missions, reducing the need for subjective assumptions and large amounts of data analysis. Figure 3 The comparison chart of the actual track and the preset track shows a score of 372 using the DTW algorithm, 0.32 using the LCSS algorithm, and 2.3 using the Fréchet distance algorithm. The resulting similarity score is 60 out of 100, indicating that the actual track is acceptable.

[0095] Based on the same design ideas Figure 4 The embodiment of the present invention further provides a track similarity evaluation device, which can implement each step of the track similarity evaluation method when running. The device may include:

[0096] The index acquisition module 401 is used to obtain various index data representing the degree of deviation between the preset track and the actual track.

[0097] The indicator determination module 402 is used to determine the number of qualified indicator data in each indicator data based on the similarity evaluation indicator. The qualified indicator data is the indicator data in each indicator data that meets the corresponding benchmark data requirements in the similarity evaluation indicator.

[0098] The similarity calculation module 403 is used to process the preset track and the actual track based on the preset similarity algorithm and the preset distance algorithm respectively when the number of qualified index data is not less than one, and obtain each deviation distance between the preset track and the actual track.

[0099] The normalization module 404 is configured to process each deviation distance based on a preset normalization algorithm to obtain a normalized result of each deviation distance.

[0100] Scoring module 405 is used to process each normalized result based on a preset scoring algorithm to obtain a similarity score between the preset track and the actual track.

[0101] The adjustment module 406 is used to subtract the score of each indicator data from the similarity score when the number of qualified indicator data is not equal to the number of indicator data. The score of each indicator data is obtained by processing each indicator data and the benchmark data corresponding to each indicator data using a preset scoring algorithm.

[0102] Furthermore, the indicator acquisition module 401 is specifically used to obtain the maximum deviation distance, the average value of the deviation distance and the standard deviation of the deviation distance, which represent the degree of deviation between the preset track and the actual track, based on the distance between each collection point of the preset track and the corresponding collection point in the actual track.

[0103] Furthermore, the indicator determination module 402 is specifically configured to compare the maximum deviation distance with the reference deviation distance to determine whether the maximum deviation distance is qualified.

[0104] Compare the average value of the deviation distance with the benchmark average value to determine whether the average value of the deviation distance is qualified.

[0105] Compare the standard deviation of the deviation distance with the benchmark standard deviation to determine whether the standard deviation of the deviation distance is qualified.

[0106] Furthermore, the similarity calculation module 403 is specifically configured to process the preset track and the actual track based on a dynamic time normalization algorithm to obtain a first deviation distance when the number of qualified index data is not less than one.

[0107] The preset track and the actual track are processed based on the longest common string algorithm to obtain a second deviation distance.

[0108] The preset track and the actual track are processed based on the Fréchet distance algorithm to obtain the third deviation distance.

[0109] The preset track and the actual track are processed based on the Hausdorff distance algorithm to obtain a fourth deviation distance.

[0110] Furthermore, the normalization module 404 is specifically configured to:

[0111] based on

[0112] DTW_score=1-diffdis_DTW / (diffdis_DTW+diffdis_FD+diffdis_HD);

[0113] LCSS_score=diffdis_LCSS;

[0114] FD_score=1-diffdis_FD / (diffdis_DTW+diffdis_FD+diffdis_HD);

[0115] HD_score=1-diffdis_HD / (diffdis_DTW+diffdis_FD+diffdis_HD);

[0116] The normalized results of each deviation distance are obtained respectively. DTW_score is the planning result of the first deviation distance, LCSS_score is the planning result of the second deviation distance, FD_score is the planning result of the third deviation distance, HD_score is the planning result of the fourth deviation distance, diffdis_DTW is the first deviation distance, diffdis_LCSS is the second deviation distance, diffdis_FD is the third deviation distance, and diffdis_HD is the fourth deviation distance.

[0117] Furthermore, the scoring module 405 is specifically configured to:

[0118] based on

[0119] score=a*(DTW_score+LCSS_score)+b*(FD_score+HD_score)+c*p_score;

[0120] Get the similarity score, score is the similarity score, p_score is the score of manual participation, a, b, c are all weight coefficients, and the sum of a, b, c is equal to 1.

[0121] Furthermore, the adjustment module 406 is specifically configured to:

[0122] based on

[0123] final_score=score–(case1_diff_score+case2_diff_score+case3_diff_score);

[0124] case1_diff_score=|dis-maxdev_Dis| / maxdev_Dis;

[0125] case2_diff_score=|avr-maxdev_Avr| / maxdev_Avr;

[0126] case3_diff_score=|std-maxdev_Std| / maxdev_Std;

[0127] Get the final score, final_score is the final score, case1_diff_score is the score of the maximum deviation distance, case2_diff_score is the score of the average value of the deviation distance, case3_diff_score is the score of the standard deviation of the deviation distance, dis is the maximum deviation distance, maxdev_Dis is the benchmark deviation distance, avr is the average value of the deviation distance, maxdev_Avr is the benchmark average value, std is the standard deviation of the deviation distance, and maxdev_Std is the benchmark standard deviation.

[0128] The track similarity evaluation device has the same beneficial effects as the track similarity evaluation method described above. Its specific implementation can refer to the embodiment of the track similarity evaluation method described above, and the present invention will not elaborate on it here.

[0129] Reference Figure 5 As shown, an embodiment of the present invention further provides an electronic device, which may include: a memory 501 and a processor 502.

[0130] The memory 501 is used to store programs.

[0131] The processor 502 is configured to execute the program to implement the various steps of the track similarity evaluation method described in the above embodiment.

[0132] An embodiment of the present invention further provides a storage medium storing a computer program. When the computer program is executed by a processor, the computer program implements the steps of the track similarity evaluation method described in the above embodiment.

[0133] For simplicity of description, the aforementioned method embodiments are described as a series of actions. However, those skilled in the art should be aware that the present invention is not limited by the order of the actions described, as certain steps can be performed in other orders or simultaneously according to the present invention. Furthermore, those skilled in the art should also be aware that the embodiments described in this specification are preferred embodiments, and the actions and modules involved are not necessarily required for the present invention.

[0134] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similarities between the various embodiments can be referred to in conjunction with each other. For device embodiments, since they are generally similar to method embodiments, their description is relatively simple, and for relevant details, reference can be made to the description of the method embodiments.

[0135] The steps in the methods of the various embodiments of the present invention can be adjusted in sequence, combined, and deleted according to actual needs, and the technical features recorded in the various embodiments can be replaced or combined.

[0136] The modules and submodules in the devices and terminals of various embodiments of the present invention may be combined, divided, or deleted according to actual needs.

[0137] In the several embodiments provided herein, it should be understood that the disclosed terminals, devices, and methods can be implemented in other ways. For example, the terminal embodiments described above are merely illustrative. For example, the division of modules or submodules is merely a logical functional division. In actual implementation, other division methods may be used, such as combining or integrating multiple submodules or modules into another module, or omitting or not implementing certain features. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between devices or modules via some interface, which may be electrical, mechanical, or other forms.

[0138] The modules or submodules described as separate components may or may not be physically separate, and the components of the modules or submodules may or may not be physical modules or submodules, that is, they may be located in one place or distributed across multiple network modules or submodules. Some or all of the modules or submodules may be selected to achieve the purpose of this embodiment according to actual needs.

[0139] In addition, the functional modules or submodules in the various embodiments of the present invention may be integrated into a single processing module, or each module or submodule may exist physically separately, or two or more modules or submodules may be integrated into a single module. The aforementioned integrated modules or submodules may be implemented in the form of hardware or software functional modules or submodules.

[0140] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the components and steps of each example according to their functions. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0141] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, software units executed by a processor, or a combination of the two. The software units may be placed in random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0142] Finally, it should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or device comprising the element.

[0143] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A track similarity evaluation method, characterized in that: include: Obtain various indicator data representing the degree of deviation between the preset track and the actual track; The obtaining of various indicator data representing the degree of deviation between the preset track and the actual track includes: Based on the distance between each collection point of the preset track and the corresponding collection point in the actual track, respectively obtaining a maximum deviation distance, an average value of the deviation distance, and a standard deviation of the deviation distance, which represent the degree of deviation between the preset track and the actual track; Determining the number of qualified indicator data in each indicator data based on the similarity evaluation index, wherein the qualified indicator data is indicator data in each indicator data that meets the corresponding benchmark data requirements in the similarity evaluation index; determining the number of qualified indicator data in each indicator data based on the similarity evaluation index includes: Comparing the maximum deviation distance with a reference deviation distance to determine whether the maximum deviation distance is qualified; Comparing the average value of the deviation distances with a benchmark average value to determine whether the average value of the deviation distances is qualified; Comparing the standard deviation of the deviation distance with the benchmark standard deviation to determine whether the standard deviation of the deviation distance is qualified; When the number of qualified index data is not less than one, the preset track and the actual track are processed based on a preset similarity algorithm and a preset distance algorithm respectively to obtain each deviation distance between the preset track and the actual track; Processing each of the deviation distances based on a preset normalization algorithm to obtain a normalized result of each of the deviation distances; Processing each of the normalized results based on a preset scoring algorithm to obtain a similarity score between the preset track and the actual track; When the number of the qualified indicator data is not equal to the number of the indicator data, the score of each indicator data is subtracted from the similarity score, and the score of each indicator data is obtained by processing each indicator data and the benchmark data corresponding to each indicator data by a preset scoring algorithm.

2. The method according to claim 1, characterized in that When the number of the qualified index data is not less than one, the preset track and the actual track are processed based on a preset similarity algorithm and a preset distance algorithm respectively to obtain each deviation distance between the preset track and the actual track, including: Processing the preset track and the actual track based on a dynamic time normalization algorithm to obtain a first deviation distance; Processing the preset track and the actual track based on a longest common string algorithm to obtain a second deviation distance; Processing the preset track and the actual track based on a Fréchet distance algorithm to obtain a third deviation distance; The preset track and the actual track are processed based on a Hausdorff distance algorithm to obtain a fourth deviation distance.

3. The method according to claim 2, characterized in that The processing of each of the deviation distances based on a preset normalization algorithm to obtain a normalized result of each of the deviation distances includes: based on DTW_score =1- diffdis_DTW / (diffdis_DTW+diffdis_FD+diffdis_HD); LCSS_score = diffdis_LCSS; FD_score = 1- diffdis _FD / (diffdis_DTW+diffdis_FD+diffdis_HD); HD_score = 1- diffdis_HD / (diffdis_DTW+diffdis_FD+diffdis_HD); The normalized results of each deviation distance are obtained respectively, DTW_score is the planning result of the first deviation distance, LCSS_score is the planning result of the second deviation distance, FD_score is the planning result of the third deviation distance, HD_score is the planning result of the fourth deviation distance, diffdis_DTW is the first deviation distance, diffdis_LCSS is the second deviation distance, diffdis _FD is the third deviation distance, and diffdis_HD is the fourth deviation distance.

4. The method according to claim 3, characterized in that The processing of each normalized result based on a preset scoring algorithm to obtain a similarity score between the preset track and the actual track includes: based on score=a*(DTW_score+LCSS_score)+b*(FD_score+HD_score) + c*p_score; The similarity score is obtained, where score is the similarity score, p_score is the score given by manual participation, a, b, and c are all weight coefficients, and the sum of a, b, and c is equal to 1.

5. The method according to claim 4, characterized in that When the number of qualified indicator data is not equal to the number of indicator data, the score of each indicator data is subtracted from the similarity score to obtain a final score, wherein the score of each indicator data is obtained by processing each indicator data and the benchmark data corresponding to each indicator data by a preset scoring algorithm, including: based on final_score=score– (case1_diff_score+ case2_diff_score+ case3_diff_score); case1_ diff_score = |dis - maxdev_Dis | / maxdev_Dis; case2_diff_score = |avr - maxdev_Avr | / maxdev_Avr; case3_diff_score = |std - maxdev_Std | / maxdev_Std; Get the final score, final_score is the final score, case1_diff_score is the score of the maximum deviation distance, case2_diff_score is the score of the average value of the deviation distance, case3_diff_score is the score of the standard deviation of the deviation distance, dis is the maximum deviation distance, maxdev_Dis is the benchmark deviation distance, avr is the average value of the deviation distance, maxdev_Avr is the benchmark average value, std is the standard deviation of the deviation distance, and maxdev_Std is the benchmark standard deviation.

6. A track similarity evaluation device, characterized in that: include: An index acquisition module is used to obtain various index data representing the degree of deviation between the preset track and the actual track; The obtaining of various indicator data representing the degree of deviation between the preset track and the actual track includes: Based on the distance between each collection point of the preset track and the corresponding collection point in the actual track, respectively obtaining a maximum deviation distance, an average value of the deviation distance, and a standard deviation of the deviation distance, which represent the degree of deviation between the preset track and the actual track; An indicator determination module is configured to determine the number of qualified indicator data in each indicator data based on a similarity evaluation indicator, wherein the qualified indicator data is indicator data in each indicator data that meets the corresponding benchmark data requirements in the similarity evaluation indicator; the determining the number of qualified indicator data in each indicator data based on the similarity evaluation indicator includes: Comparing the maximum deviation distance with a reference deviation distance to determine whether the maximum deviation distance is qualified; Comparing the average value of the deviation distances with a benchmark average value to determine whether the average value of the deviation distances is qualified; Comparing the standard deviation of the deviation distance with the benchmark standard deviation to determine whether the standard deviation of the deviation distance is qualified; a similarity calculation module, configured to, when the number of qualified index data is not less than one, process the preset track and the actual track based on a preset similarity algorithm and a preset distance algorithm respectively to obtain each deviation distance between the preset track and the actual track; A normalization module, configured to process each of the deviation distances based on a preset normalization algorithm to obtain a normalized result of each of the deviation distances; a scoring module, configured to process each of the normalized results based on a preset scoring algorithm to obtain a similarity score between the preset track and the actual track; and an adjustment module for, when the number of the qualified indicator data is not equal to the number of the indicator data, subtracting the score of each indicator data from the similarity score, where the score of each indicator data is obtained by processing each indicator data and the benchmark data corresponding to each indicator data by a preset scoring algorithm.

7. An electronic device, characterized in that: include: memory and processor; The memory is used to store programs; The processor is configured to execute the program to implement each step of the track similarity assessment method according to any one of claims 1 to 5.

8. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, each step of the track similarity evaluation method according to any one of claims 1 to 5 is implemented.

Images