Yaw track point identification method and device, computer equipment and medium
By hexagonally processing the actual driving trajectory and navigation trajectory of online ride-hailing drivers, comparing the index value differences, and identifying yaw trajectory points, the problems of inaccurate identification and poor timeliness in the existing technology are solved, and more accurate is achieved and timely yaw trajectory point identification.
Patent Information
- Application Number
- CN202411037368.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-30
- Publication Date
- 2024-11-26
AI Technical Summary
The existing yaw trajectory point recognition method is inaccurate on tortuous routes and non-intersection roads, and has poor timeliness. Especially when online ride-hailing drivers upload new navigation routes after performing yaw behavior, resulting in yaw trajectory points. Identify lags.
By hexagonally processing the driver's actual driving trajectory and theoretical navigation trajectory, the index values of the two hexagons are compared to identify and locate the yaw trajectory points, and the accuracy and timeliness of recognition are improved.
It improves the accuracy and timeliness of yaw trajectory points recognition, reduces tortuous route interference, enhances the ability to identify roads in non-intersection forms, and promptly recognizes yaw behavior.
Smart Images

Figure CN119022943A_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present application relate to the field of navigation planning technology, and in particular to a method, device, computer equipment and medium for identifying off-course trajectory points. Background Art
[0002] During the process of picking up and dropping off passengers, online car-hailing drivers may need to re-upload the navigation route due to business needs, traffic congestion, APP (Application) cold start, etc., which may cause the new navigation route to deviate from the original route. This deviation behavior may cause the online car-hailing driver to pick up the passenger late, further increasing the passenger's journey time. Therefore, online car-hailing tenants on the SaaS (Software as a Service) platform need to judge the deviation behavior of online car-hailing drivers. Online car-hailing tenants generally use map software to mark the deviation trajectory points on the map based on the travel history records provided by the online car-hailing driver, and then carry out deviation behavior assessment work with the identification of the deviation trajectory points as the core.
[0003] However, the inventors realize that the current yaw trajectory point identification method still has these problems: if the yaw trajectory point is calculated by calculating the intersection of the navigation routes uploaded twice by the online car-hailing vehicle, this will be interfered by the tortuous route (such as a cross intersection), resulting in inaccurate identification and positioning of the yaw trajectory point. If the first trajectory point in the newly uploaded navigation route of the online car-hailing vehicle is used as the yaw trajectory point, this method alleviates the interference of the tortuous route to a certain extent. However, for routes in the form of non-intersections (such as long slope and curved routes), directly using the first trajectory point in the new navigation route as the yaw trajectory point will result in inaccurate identification of the azimuth of the yaw trajectory point. Secondly, the online car-hailing driver will upload the new navigation route only after performing the yaw behavior, which will cause a lag effect in the first trajectory point in the new navigation route, resulting in poor timeliness in the identification of the yaw trajectory point. Summary of the invention
[0004] In view of the above shortcomings or disadvantages, the present application provides a method, device, computer equipment and medium for identifying off-course trajectory points. The present application improves the accuracy and timeliness of off-course trajectory point identification by processing the driver's actual driving trajectory and theoretical navigation trajectory into hexagons, and then comparing the index value difference of the two hexagons to identify and locate the off-course trajectory points.
[0005] According to a first aspect, the present application provides a method for identifying off-course trajectory points, which is applied to a cloud platform and includes:
[0006] Acquire the current trip track information and navigation path information of the target driver; the trip track information includes the trip starting point, the driver's current location and multiple first trip track points in the middle, and the navigation path information includes the trip starting point, the trip end point and multiple second trip track points in the middle;
[0007] Smoothing the corresponding travel trajectory according to the travel trajectory information;
[0008] Based on the preset grid accuracy, a plurality of first-class hexagons are generated for the smoothed new travel trajectory, and a plurality of second-class hexagons are generated for the navigation trajectory corresponding to the navigation path information;
[0009] Assign corresponding index values to each type I hexagon and each type II hexagon;
[0010] The yaw trajectory point is determined according to the index value difference between each of the first-type hexagons and each of the second-type hexagons.
[0011] In some embodiments, smoothing the corresponding travel trajectory is performed according to the travel trajectory information, and the method includes:
[0012] Calculate the distance between the trip starting point and the adjacent first trip trajectory point, the distance between each adjacent pair of first trip trajectory points, and the distance between the driver's current position and the adjacent first trip trajectory points to obtain an adjacent distance matrix;
[0013] The required amount of supplementary points is determined according to the preset supplementary point spacing and the adjacent distance matrix to obtain the supplementary point quantity matrix of the travel trajectory;
[0014] According to the matrix of the number of supplementary points, a corresponding number of first trip trajectory points are inserted between the starting point of the trip and the adjacent first trip trajectory point, between each adjacent pair of first trip trajectory points, and between the driver's current position and the adjacent first trip trajectory point to obtain a smoothed trip trajectory.
[0015] In some embodiments, each element in the adjacent distance matrix sequentially represents the geographical distance between the trip starting point and the adjacent first trip trajectory point, the geographical distance between each adjacent pair of first trip trajectory points, and the geographical distance between the driver's current position and the adjacent first trip trajectory point, and the supplementary point spacing is a specific geographical distance threshold; the supplementary point demand is determined according to the preset supplementary point spacing and the adjacent distance matrix to obtain the supplementary point quantity matrix of the trip trajectory, and the method includes:
[0016] Determine the target element that exceeds the geographic distance threshold in the adjacent distance matrix according to the filling point spacing, and map the target element to the local track that needs to be filled in the travel track;
[0017] According to the size of each displayed target element and the geographical distance threshold, the required number of points to be supplemented for each local trajectory is calculated;
[0018] A point-filling quantity matrix is generated according to the point-filling requirements of each local trajectory; wherein the element value mapped to the non-target element in the point-filling quantity matrix is 0, and the element value mapped to the target element is equal to the corresponding point-filling requirement.
[0019] In some embodiments, the grid accuracy determines the side length and area of each type I hexagon and each type II hexagon; generating a plurality of type I hexagons for the smoothed new travel trajectory, the method comprising:
[0020] Generate a new trip trajectory point longitude and latitude matrix according to the longitude and latitude of the trip starting point in the new trip trajectory, the longitude and latitude of the driver's current location, and the longitude and latitude of the plurality of first trip trajectory points after smoothing;
[0021] The longitude and latitude elements of the same group in each column or row of the longitude and latitude matrix of the new travel trajectory points are set as the longitude and latitude of the center points of each type of hexagon;
[0022] Based on the center points of each of the first-class hexagons, a plurality of first-class hexagons are set with the same hexagonal posture.
[0023] In some embodiments, a plurality of second-class hexagons are generated for a navigation track corresponding to the navigation path information, the method comprising:
[0024] Generate a navigation track point longitude and latitude matrix according to the longitude and latitude of the trip starting point, the longitude and latitude of the trip end point, and the longitude and latitude of a plurality of second trip track points in the middle of the navigation track;
[0025] The longitude and latitude elements of the same group in each column or row of the longitude and latitude matrix of the navigation track points are set as the longitude and latitude of the center points of each second-class hexagon;
[0026] Based on the center points of each of the second-class hexagons, multiple second-class hexagons are set with the same hexagonal posture.
[0027] In some embodiments, each type-one hexagon and each type-two hexagon is assigned a corresponding index value, and the method includes:
[0028] According to the longitude and latitude matrix of the new travel trajectory points, the longitude and latitude matrix of the navigation trajectory points, and the area of each first-class hexagon and each second-class hexagon, the index value of each first-class hexagon and each second-class hexagon is determined to generate a first index value matrix for the first-class hexagon and a second index value matrix for the second-class hexagon.
[0029] In some embodiments, the first index value matrix includes a plurality of index value elements of 1 row and n+m columns, and the second index value matrix includes a plurality of index value elements of 1 row and t columns, where m is the required amount of supplementary points; or, the first index value matrix includes a plurality of index value elements of 1 column and n+m rows, and the second index value matrix includes a plurality of index value elements of 1 column and m rows, where n and t are both natural numbers greater than or equal to 3, m is a natural number greater than or equal to 0, and n+m≤t; determining the yaw trajectory point according to the index value difference between each first-class hexagon and each second-class hexagon, the method includes:
[0030] Based on the n+m-2 column index value elements of the first index value matrix, the t-2 column index value elements in the second index value matrix are compared one by one; or based on the n+m-2 row index value elements of the first index value matrix, the t-2 row index value elements in the second index value matrix are compared one by one;
[0031] In response to a difference in the index value element of a certain column or a certain row, the first travel trajectory point corresponding to the current type of hexagon or the current position of the driver is determined as the off-course trajectory point.
[0032] According to a second aspect, the present application provides a device for identifying off-course trajectory points, the system comprising:
[0033] A trip information acquisition module, used to acquire the current trip track information and navigation path information of the target driver; the trip track information includes the trip starting point, the driver's current position and multiple first trip track points in the middle, and the navigation path information includes the trip starting point, the trip end point and multiple second trip track points in the middle;
[0034] A trajectory smoothing processing module is used to smooth the corresponding travel trajectory according to the travel trajectory information;
[0035] A hexagon generation module, used to generate a plurality of first-class hexagons for the smoothed new travel trajectory based on a preset grid accuracy, and to generate a plurality of second-class hexagons for the navigation trajectory corresponding to the navigation path information;
[0036] An index value assigning module, used for assigning corresponding index values to each first-class hexagon and each second-class hexagon;
[0037] The yaw trajectory point positioning module is used to determine the yaw trajectory point according to the index value difference between each first-class hexagon and each second-class hexagon.
[0038] According to a third aspect, the present application provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned off-course trajectory point identification methods are implemented.
[0039] According to a fourth aspect, the present application provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the steps of the above-mentioned off-course trajectory point identification method when executing the computer program.
[0040] The method described in the above embodiment can be applied to the SaaS cloud platform. The online car-hailing tenants on the SaaS cloud platform need to use the built-in functions of the cloud platform to identify and locate the yaw points of the target driver, and then carry out the evaluation of the yaw behavior. The SaaS cloud platform first obtains the current travel trajectory information and navigation path information of the target driver, and then smoothes the corresponding travel trajectory by filling in points. Then, according to the preset grid accuracy, multiple first-class hexagons are generated for the smoothed new travel trajectory, and multiple second-class hexagons are generated for the navigation trajectory corresponding to the navigation path information. Among them, the grid accuracy determines the size of the generated first-class hexagons and second-class hexagons. The SaaS cloud platform can adjust the recognition accuracy of the yaw trajectory point by changing the grid accuracy. Then, the corresponding index value is assigned to each first-class hexagon and each second-class hexagon to simplify the hexagon comparison process, thereby improving the timeliness of the yaw trajectory point identification. Finally, the yaw trajectory point is determined according to the index value difference between each first-class hexagon and each second-class hexagon. In this way, the accuracy and timeliness of the yaw trajectory point identification are improved. BRIEF DESCRIPTION OF THE DRAWINGS
[0041] Figure 1 A schematic diagram of a flow chart of a method for identifying off-course trajectory points in one or more embodiments of the present application;
[0042] Figure 2 An example of displaying the travel trajectory information of a target driver on a map in one or more embodiments of the present application;
[0043] Figure 3 A schematic flow chart of a method for smoothing a travel trajectory in one or more embodiments of the present application;
[0044] Figure 4 A schematic flow chart of a method for determining a matrix of supplementary points of a travel trajectory in one or more embodiments of the present application;
[0045] Figure 5 This is an example of a smoothing result of a travel trajectory in one or more embodiments of the present application;
[0046] Figure 6 A schematic flow chart of a method for generating a type of hexagon in one or more embodiments of the present application;
[0047] Figure 7This is an example of a generation result of a type of hexagon in one or more embodiments of the present application;
[0048] Figure 8 A schematic flow chart of a method for generating a second type of hexagon in one or more embodiments of the present application;
[0049] Fig. 9 A schematic flow chart of a method for locating a yaw trajectory point in one or more embodiments of the present application;
[0050] Fig.10 This is an example of a positioning result of a yaw trajectory point in one or more embodiments of the present application;
[0051] Fig.11 A schematic diagram of the structure of a yaw trajectory point identification device in one or more embodiments of the present application;
[0052] Fig.12 A schematic diagram of the structure of a computer device in one or more embodiments of the present application. DETAILED DESCRIPTION
[0053] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0054] According to a first aspect, the present application provides a method for identifying off-course trajectory points, such as Figure 1 As shown, the method is applied to a cloud platform and includes:
[0055] S110: Acquire the current trip trajectory information and navigation path information of the target driver; the trip trajectory information includes the trip starting point, the driver's current position, and a plurality of first trip trajectory points along the way; the navigation path information includes the trip starting point, the trip end point, and a plurality of second trip trajectory points along the way;
[0056] Specifically, this method can be applied to a SaaS cloud platform, where online car-hailing tenants on the SaaS cloud platform need to use the built-in functions of the cloud platform to identify and locate the deviation points of the target driver, and then conduct an evaluation of the deviation behavior. Among them, the travel trajectory information is the historical driving trajectory route newly uploaded by the target driver. The historical driving trajectory route must include the starting point of the trip and the current location of the driver, while the multiple first travel trajectory points in the middle are discontinuous and incomplete, one to multiple trajectory points. Navigation path information refers to the idealized optimal path calculated by the SaaS cloud platform. The optimal path must include the starting point of the trip, the end point of the trip, and countless continuous and smooth second travel trajectory points in the middle.
[0057] For example, Figure 2 The shown example shows the display of the target driver's travel trajectory information on a map, wherein point 9 is the driver's current location, point 1 is the starting point of the trip, and points 2, 3, 5, 6, and 8 are the first five travel trajectory points along the way.
[0058] S120: Smoothing the corresponding travel trajectory according to the travel trajectory information;
[0059] In some embodiments, the corresponding travel trajectory is smoothed according to the travel trajectory information, such as Figure 3 As shown, the method includes:
[0060] S210: Calculate the distance between the trip starting point and the adjacent first trip trajectory point, the distance between each adjacent pair of first trip trajectory points, and the distance between the driver's current position and the adjacent first trip trajectory points to obtain an adjacent distance matrix;
[0061] Specifically, assuming that the calculated result of the distance between the starting point of the trip and the adjacent first trip trajectory point is L1, the distance between each pair of adjacent first trip trajectory points [L1, .... L n-1 ], the distance L between the driver's current position and the adjacent first trip trajectory point n , then the adjacent distance matrix is [L1,....L n-1 ,L n ]. Wherein, n is a natural number greater than or equal to 3.
[0062] For example, in Figure 2 In the example of displaying the travel trajectory information on the map, it is assumed that the calculated result of the distance between point 1 and point 2 is 10 meters, the distance between each adjacent pair of first travel trajectory points (point 2 and point 3, point 5 and point 3, point 6 and point 5, point 8 and point 6) is [40, 10, 90, 90] meters, and the distance between point 9 and point 8 is 10 meters, then the adjacent distance matrix is [10, 40, 10, 90, 90, 10] meters.
[0063] S220: determining the required amount of supplementary points according to the preset supplementary point spacing and the adjacent distance matrix to obtain a supplementary point quantity matrix of the travel trajectory;
[0064] Specifically, assuming that the known spacing between supplementary points is M0, n=6, and the adjacent distance matrix is [L1,....L4,L6], where L4 and L5 are both greater than M0 and not greater than 2*M0, and the remaining L1, L2, L3 and L6 are all less than M0, then the supplementary point number matrix of the travel trajectory can be obtained as [0, 0, 0, 1, 1, 0].
[0065] In some embodiments, each element in the adjacent distance matrix represents the geographical distance between the trip starting point and the adjacent first trip trajectory point, the geographical distance between each adjacent pair of first trip trajectory points, and the geographical distance between the driver's current position and the adjacent first trip trajectory point, and the filling point spacing is a specific geographical distance threshold; the filling point demand is determined according to the preset filling point spacing and the adjacent distance matrix to obtain the filling point quantity matrix of the trip trajectory, such as Figure 4 As shown, the method includes:
[0066] S310: determining the target element in the adjacent distance matrix that exceeds the geographic distance threshold according to the filling point spacing, and mapping the target element to the local track that needs to be filled in the travel track;
[0067] Specifically, assuming that the spacing between the supplementary points is M0, n=6, and the adjacent distance matrix is [L1,....L4,L6], where L4 and L5 are both greater than M0, and the remaining L1, L2, L3 and L6 are all less than M0, it can be determined that the target elements exceeding the geographic distance threshold are L4 and L5.
[0068] S320: Calculate the required amount of supplementary points for each local trajectory according to the size of each displayed target element and the geographical distance threshold;
[0069] Specifically, it is known that L4 and L5 are both greater than M0, but L4 and L5 are not greater than 2*M0, then the demand for L4 and L5 is 1. Alternatively, assuming that L4 and L5 are both greater than 8*M0, but not greater than 9*M0, then the demand for L4 and L5 is 8.
[0070] S330: Generate a point-filling quantity matrix according to the point-filling requirements of each local trajectory; wherein the element value mapped to the non-target element in the point-filling quantity matrix is 0, and the element value mapped to the target element is equal to the corresponding point-filling requirement.
[0071] For example, in Figure 2 In the example of displaying the itinerary trajectory information on the map, it is known that the adjacent distance matrix is [10, 40, 10, 90, 90, 10] meters. Assuming that the spacing between the supplementary points M0 = 50 meters, the matrix of the number of supplementary points obtained by the above method is [0, 0, 0, 1, 1, 0]. Alternatively, assuming that the spacing between the supplementary points M0 = 10 meters, the matrix of the number of supplementary points obtained by the above method is [0, 3, 0, 8, 8, 0]. Through the steps of the above method, the number of supplementary points during smoothing can be calculated based on the intermittent and incomplete itinerary trajectory newly uploaded by the online car-hailing service, thereby improving the accuracy of subsequent off-course trajectory point recognition.
[0072] S230: According to the supplementary point number matrix, a corresponding number of first trip trajectory points are inserted between the trip starting point and the adjacent first trip trajectory point, between each adjacent pair of first trip trajectory points, and between the driver's current position and the adjacent first trip trajectory point to obtain a smoothed trip trajectory.
[0073] For example, Figure 5 The example of the smoothing result of the travel trajectory shown can be the travel trajectory after smoothing as described above. Assuming that the spacing between the supplementary points M0 = 10 meters and the matrix of the number of supplementary points is [0, 3, 0, 8, 8, 0], the first travel trajectory point is not inserted between point 1 and point 3, between point 3 and point 4, and between point 5 and point 6, while 3, 8, and 8 first travel trajectory points are inserted between point 2 and point 3, between point 4 and point 5, and between point 5 and point 6, respectively. Through the steps of the above method, it is possible to smooth the intermittent and incomplete travel trajectories newly uploaded by the online car-hailing service, thereby improving the accuracy of subsequent off-course trajectory point identification.
[0074] S130: Based on a preset grid accuracy, generating a plurality of first-class hexagons for the smoothed new travel trajectory, and generating a plurality of second-class hexagons for the navigation trajectory corresponding to the navigation path information;
[0075] In some embodiments, the grid accuracy determines the side length and area of each type I hexagon and each type II hexagon; multiple type I hexagons are generated for the smoothed new travel trajectory, such as Figure 6 As shown, the method includes:
[0076] S410: generating a new trip trajectory point longitude and latitude matrix according to the longitude and latitude of the trip starting point in the new trip trajectory, the longitude and latitude of the driver's current location, and the longitude and latitude of the plurality of first trip trajectory points after smoothing;
[0077] Specifically, assuming that the total number of all trajectory points in the new travel trajectory is n+m, the longitude and latitude of each travel trajectory point can be expressed as The longitude and latitude matrix of the new travel trajectory point can be expressed as: Wherein, the number of supplementary points m is a natural number greater than or equal to 1; or, the longitude and latitude matrix of the new itinerary trajectory points can also be expressed as:
[0078] S420: setting the same group of longitude and latitude elements in each column or row of the longitude and latitude matrix of the new travel trajectory points as the longitude and latitude of the center points of each type of hexagon;
[0079] Specifically, for the new trip trajectory point longitude and latitude matrix For , each column element represents the latitude and longitude of a corresponding travel trajectory point. Similarly, for the longitude and latitude matrix of the new travel trajectory point In general, each row element represents the latitude and longitude of a corresponding travel trajectory point.
[0080] S430: Based on the center points of each of the first-class hexagons, a plurality of first-class hexagons are set with the same hexagonal posture.
[0081] Specifically, the same hexagonal posture means that the corresponding sides of each hexagon are parallel to each other on the map. Figure 7 The shown Multiple hexagons generated for the center transform.
[0082] For example, the center of a hexagon formed by points 3-6, point 10 and point 11 can be the trajectory point Through the steps of the above method, the actual driving trajectory of the driver is processed into hexagons, which is convenient for subsequent index value difference analysis to improve the accuracy of off-course trajectory point recognition.
[0083] In some embodiments, a plurality of second-class hexagons are generated for the navigation track corresponding to the navigation path information, such as Figure 8 As shown, the method includes:
[0084] S510: Generate a navigation track point longitude and latitude matrix according to the longitude and latitude of the trip starting point, the longitude and latitude of the trip end point, and the longitude and latitude of a plurality of second trip track points in the middle of the navigation track;
[0085] Specifically, assuming that the number of all track points in the navigation track is t, the longitude and latitude matrix of the navigation track points can be expressed as: Wherein, t is a natural number greater than or equal to n; or, the latitude and longitude matrix of the navigation track point can also be expressed as:
[0086] S520: setting the same group of longitude and latitude elements in each column or row in the longitude and latitude matrix of the navigation track points as the longitude and latitude of the center points of each second type of hexagon;
[0087] Specifically, for the navigation trajectory point latitude and longitude matrix For example, each column element represents the latitude and longitude of a corresponding navigation track point. Similarly, for the navigation track point latitude and longitude matrix In general, each row of elements represents the latitude and longitude of a corresponding navigation track point.
[0088] S530: Based on the center points of each of the second-type hexagons, a plurality of second-type hexagons are set with the same hexagonal posture.
[0089] Through the steps of the above method, the driver's navigation trajectory is processed into a hexagon, which is convenient for subsequent index value difference analysis to improve the accuracy of off-course trajectory point recognition.
[0090] S140: assigning corresponding index values to each first-class hexagon and each second-class hexagon;
[0091] In some embodiments, each type-one hexagon and each type-two hexagon is assigned a corresponding index value, and the method includes:
[0092] According to the longitude and latitude matrix of the new travel trajectory points, the longitude and latitude matrix of the navigation trajectory points, and the area of each first-class hexagon and each second-class hexagon, the index value of each first-class hexagon and each second-class hexagon is determined to generate a first index value matrix for the first-class hexagon and a second index value matrix for the second-class hexagon.
[0093] Specifically, assuming that the longitude and latitude matrix of the new travel trajectory point is The latitude and longitude matrix of the navigation trajectory point is: And the area of each type I hexagon and each type II hexagon is S0, then the first index value matrix of the generated type I hexagon can be S0[I1,...I n ,...I n+m ], the second index value matrix of the second type of hexagon can be S0[I1,...I n ,...I t ]. If the area of each type I hexagon is S1, the area of each type II hexagon is S2, and S1≠S1, then the first index value matrix of the generated type I hexagon can be S1[I1,...I n ,...I n+m ], the second index value matrix of the second type of hexagon can be S2[I1,...I n ,...I t ]. Through the steps of the above method, it is achieved to assign corresponding index values to each type I hexagon and each type II hexagon, simplifying the hexagon comparison process, so as to facilitate the subsequent index value difference analysis to improve the accuracy and timeliness of the off-course trajectory point identification.
[0094] S150: Determine a yaw trajectory point according to the index value difference between each first-type hexagon and each second-type hexagon.
[0095] In some embodiments, the first index value matrix includes a plurality of index value elements of 1 row and n+m columns, and the second index value matrix includes a plurality of index value elements of 1 row and t columns, where m is the required number of supplementary points; or, the first index value matrix includes a plurality of index value elements of 1 column and n+m rows, and the second index value matrix includes a plurality of index value elements of 1 column and t rows, where n and t are both natural numbers greater than or equal to 3, m is a natural number greater than or equal to 0, and n+m≤t; the yaw trajectory point is determined according to the index value difference between each first-class hexagon and each second-class hexagon, such as Fig. 9 As shown, the method includes:
[0096] S610: Based on the n+m-2 column index value elements of the first index value matrix, compare the t-2 column index value elements in the second index value matrix one by one; or, based on the t-2 row index value elements of the first index value matrix, compare the n+m-2 row index value elements in the second index value matrix one by one;
[0097] Specifically, in Fig.10 In the example of off-course point identification shown, it can be concluded that if an off-course point occurs, there must be at least 2 pairs of first index values and second index values that differ. This is because the off-course route requires at least 2 pairs of different trajectory points to form two different straight line sections (i.e., at least 4 non-overlapping trajectory points are required). Or there is a pair of index value differences near the off-course point, and there is also a pair of index value differences between the driver's current position and the end position of the navigation track. Therefore, when comparing the elements in the second index value matrix based on the first index value matrix, it is necessary to eliminate the pair of index values between the driver's current position and the end position of the navigation track, and also to eliminate the pair of index values at the starting position. A total of 2 pairs of index values need to be eliminated, so theoretically the number of index value comparisons should be n+m-2.
[0098] For example, it is known that the first index value matrix S0[I1,...I n ,...I n+m ], the second index value matrix can be S0[I1,...I n ,...I t ], then the elements that need to be compared are S0[I2,...I n ,...I n+m-1 ]. Alternatively, if the first index value matrix is known The second index value matrix can be The elements that actually need to be compared are
[0099] S620: In response to a difference in the index value element of a certain column or a certain row, a first travel trajectory point corresponding to the current type of hexagon or a current position of the driver is determined as a yaw trajectory point.
[0100] For example, it is assumed that the first index value matrix S0[I1,...I n ,...I n+m ] and the second index value matrix S0[I1,...I n ,...I t ], the difference is that the I5 element and its subsequent element are different between the two, that is, [I5,...I n ,...I n+m-1If there are differences, the first travel trajectory point corresponding to I5 can be determined as the yaw trajectory point. Or, given the first index value matrix and the second index value matrix The specific difference between them is I n+m-1 When, that is, given The last row element in and There is a difference in the elements of the (n + m - 1)th row (n + m - 1 < n + m ≤ t), then it can be determined that the driver's current position is the yaw trajectory point. Among them, the driver's current position is the position of the last first travel trajectory point, corresponding to the last row or the last column element I n+m . As can be seen from the above, if a yaw point appears, there must be at least 2 pairs of first index values and second index values that are different. Therefore, when the difference between the first index value matrix and the second index value matrix is [I n+m-1 , I n+m , [I n+m-1 , I n+m can respectively form 2 different shortest straight line segments. At this time, the driver's current position should be regarded as the yaw trajectory point.
[0101] Through the steps of the above method, by hexagonizing the actual driving trajectory of the driver and the theoretical navigation trajectory, and then comparing the index value differences of the two hexagons, the yaw trajectory point is identified and located, improving the accuracy and timeliness of the yaw trajectory point identification.
[0102] According to the second aspect of the present application, an identification device for yaw trajectory points is provided, as Fig.11 shown, the device includes:
[0103] A travel information acquisition module 110, configured to acquire the current travel trajectory information and navigation path information of the target driver; the travel trajectory information includes the travel start point, the driver's current position, and multiple first travel trajectory points in the middle; the navigation path information includes the travel start point, the travel end point, and multiple second travel trajectory points in the middle;
[0104] A trajectory smoothing processing module 120, configured to smooth the corresponding travel trajectory according to the travel trajectory information;
[0105] A hexagon generation module 130, configured to generate multiple first-class hexagons for the newly smoothed travel trajectory based on a preset grid accuracy, and generate multiple second-class hexagons for the navigation trajectory corresponding to the navigation path information;
[0106] An index value assignment module 140, configured to assign corresponding index values to each first-class hexagon and each second-class hexagon;
[0107] The off-course trajectory point positioning module 150 is used to determine the off-course trajectory point according to the index value difference between each type I hexagon and each type II hexagon.
[0108] In some embodiments, the trajectory smoothing processing module 120 is further used to calculate the distance between the trip starting point and the adjacent first trip trajectory point, the distance between each adjacent pair of first trip trajectory points, and the distance between the driver's current position and the adjacent first trip trajectory point to obtain an adjacent distance matrix;
[0109] The required amount of supplementary points is determined according to the preset supplementary point spacing and the adjacent distance matrix to obtain the supplementary point quantity matrix of the travel trajectory;
[0110] According to the matrix of the number of supplementary points, a corresponding number of first trip trajectory points are inserted between the starting point of the trip and the adjacent first trip trajectory point, between each adjacent pair of first trip trajectory points, and between the driver's current position and the adjacent first trip trajectory point to obtain a smoothed trip trajectory.
[0111] In some embodiments, each element in the adjacent distance matrix represents the geographical distance between the trip starting point and the adjacent first trip trajectory point, the geographical distance between each adjacent pair of first trip trajectory points, and the geographical distance between the driver's current position and the adjacent first trip trajectory point, and the filling point spacing is a specific geographical distance threshold; the trajectory smoothing processing module 120 is further used to determine the target element in the adjacent distance matrix that exceeds the geographical distance threshold according to the filling point spacing, and the target element is mapped to the local trajectory that needs to be filled in the trip trajectory;
[0112] According to the size of each displayed target element and the geographical distance threshold, the required number of points to be supplemented for each local trajectory is calculated;
[0113] A point-filling quantity matrix is generated according to the point-filling requirements of each local trajectory; wherein the element value mapped to the non-target element in the point-filling quantity matrix is 0, and the element value mapped to the target element is equal to the corresponding point-filling requirement.
[0114] In some embodiments, the grid accuracy determines the side length and area of each first-class hexagon and each second-class hexagon. The hexagon generation module 130 is further used to generate a new trip trajectory point longitude and latitude matrix according to the longitude and latitude of the trip starting point in the new trip trajectory, the longitude and latitude of the driver's current position, and the longitude and latitude of the smoothed first trip trajectory points.
[0115] The longitude and latitude elements of the same group in each column or row of the longitude and latitude matrix of the new travel trajectory points are set as the longitude and latitude of the center points of each type of hexagon;
[0116] Based on the center points of each of the first-class hexagons, a plurality of first-class hexagons are set with the same hexagonal posture.
[0117] In some embodiments, the hexagon generation module 130 is further used to generate a navigation track point longitude and latitude matrix according to the longitude and latitude of the trip starting point, the longitude and latitude of the trip end point, and the longitude and latitude of multiple second trip track points in the middle of the navigation track;
[0118] The longitude and latitude elements of the same group in each column or row of the longitude and latitude matrix of the navigation track points are set as the longitude and latitude of the center points of each second-class hexagon;
[0119] Based on the center points of each of the second-class hexagons, multiple second-class hexagons are set with the same hexagonal posture.
[0120] In some embodiments, the index value assigning module 140 is also used to determine the index value of each Class I hexagon and each Class II hexagon based on the longitude and latitude matrix of the new travel trajectory points, the longitude and latitude matrix of the navigation trajectory points, and the areas of each Class I hexagon and each Class II hexagon, and generate a first index value matrix for Class I hexagons and a second index value matrix for Class II hexagons.
[0121] In some embodiments, the first index value matrix includes a plurality of index value elements of 1 row and n+m columns, and the second index value matrix includes a plurality of index value elements of 1 row and t columns, where m is the required amount of supplementary points; or, the first index value matrix includes a plurality of index value elements of 1 column and n+m rows, and the second index value matrix includes a plurality of index value elements of 1 column and m rows, where n and t are both natural numbers greater than or equal to 3, m is a natural number greater than or equal to 0, and n+m≤t;
[0122] Based on the n+m-2 column index value elements of the first index value matrix, the t-2 column index value elements in the second index value matrix are compared one by one; or based on the n+m-2 row index value elements of the first index value matrix, the t-2 row index value elements in the second index value matrix are compared one by one; the yaw trajectory point positioning module 150 is further used to:
[0123] In response to a difference in the index value element of a certain column or a certain row, the first travel trajectory point corresponding to the current type of hexagon or the current position of the driver is determined as the off-course trajectory point.
[0124] According to a third aspect, the present application provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned off-course trajectory point identification methods are implemented.
[0125] According to a fourth aspect, the present application provides a computer device, such as Fig.12 As shown, it includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of any of the above-mentioned off-course trajectory point identification methods are implemented.
[0126] The specific definition of the device for identifying off-course trajectory points can be found in the above definition of the method for identifying off-course trajectory points, which will not be repeated here. Each module in the above-mentioned device for identifying off-course trajectory points can be implemented in whole or in part by software, hardware, and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.
[0127] Among them, any reference to memory, storage, database or other media used in the embodiments provided in the present application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (RamCUs), direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
[0128] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0129] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.
[0130] Finally, 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 "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.
Claims
1. A method for identifying off-course trajectory points, characterized in that: The method is applied to a cloud platform and includes: Acquire the current travel trajectory information and navigation path information of the target driver; the travel trajectory information includes the travel starting point, the driver's current position and multiple first travel trajectory points in the middle, and the navigation path information includes the travel starting point, the travel end point and multiple second travel trajectory points in the middle; Smoothing the corresponding travel trajectory according to the travel trajectory information; Based on a preset grid accuracy, generating a plurality of first-class hexagons for the smoothed new travel trajectory, and generating a plurality of second-class hexagons for the navigation trajectory corresponding to the navigation path information; Assigning corresponding index values to each of the first type of hexagons and each of the second type of hexagons; The yaw trajectory point is determined according to the index value difference between each of the first type of hexagons and each of the second type of hexagons.
2. The method according to claim 1, characterized in that Smoothing the corresponding travel trajectory according to the travel trajectory information includes: Calculating the distance between the trip starting point and the adjacent first trip trajectory point, the distance between each adjacent pair of the first trip trajectory points, and the distance between the driver's current position and the adjacent first trip trajectory points to obtain an adjacent distance matrix; Determine the required amount of supplementary points according to the preset supplementary point spacing and the adjacent distance matrix to obtain the supplementary point quantity matrix of the travel trajectory; According to the supplementary point quantity matrix, a corresponding number of first trip trajectory points are inserted in sequence between the trip starting point and the adjacent first trip trajectory point, between each adjacent pair of the first trip trajectory points, and between the driver's current position and the adjacent first trip trajectory point to obtain the smoothed trip trajectory.
3. The method according to claim 2, characterized in that Each element in the adjacent distance matrix represents, in sequence, the geographical distance between the trip starting point and the adjacent first trip trajectory point, the geographical distance between each adjacent pair of the first trip trajectory points, and the geographical distance between the driver's current position and the adjacent first trip trajectory point, and the supplementary point spacing is a specific geographical distance threshold; Determining the required amount of supplementary points according to the preset supplementary point spacing and the adjacent distance matrix to obtain the supplementary point quantity matrix of the travel trajectory includes: Determine, according to the filling point spacing, a target element in the adjacent distance matrix that exceeds the geographic distance threshold, wherein the target element is mapped to a local track that needs to be filled in the travel track; Calculating the required amount of additional points for each of the local trajectories according to the size of each of the target elements and the geographic distance threshold; The point-filling quantity matrix is generated according to the point-filling requirements of each of the local trajectories; wherein the element value mapped to the non-target element in the point-filling quantity matrix is 0, and the element value mapped to the target element is equal to the corresponding point-filling requirement.
4. The method according to claim 1, characterized in that The grid accuracy determines the side length and area of each of the first-class hexagons and each of the second-class hexagons; generating a plurality of first-class hexagons for the smoothed new travel trajectory, including: Generate a new trip trajectory point longitude and latitude matrix according to the longitude and latitude of the trip starting point in the new trip trajectory, the longitude and latitude of the driver's current location, and the longitude and latitude of a plurality of smoothed first trip trajectory points; The longitude and latitude elements of the same group in each column or row of the longitude and latitude matrix of the new travel trajectory points are set as the longitude and latitude of the center points of each type of hexagon; Based on the center points of each type of hexagon, a plurality of the type of hexagons are set in the same hexagonal posture.
5. The method according to claim 4, characterized in that Generating a plurality of second-class hexagons for the navigation track corresponding to the navigation path information, including: Generate a navigation track point longitude and latitude matrix according to the longitude and latitude of the trip starting point, the longitude and latitude of the trip end point, and the longitude and latitude of a plurality of second trip track points in the middle of the navigation track; The longitude and latitude elements of the same group in each column or row of the longitude and latitude matrix of the navigation track points are set as the longitude and latitude of the center points of each second type of hexagon; Based on the center points of the second type of hexagons, a plurality of the second type of hexagons are set in the same hexagonal posture.
6. The method according to claim 5, characterized in that Assigning corresponding index values to each of the first type of hexagons and each of the second type of hexagons includes: According to the longitude and latitude matrix of the new travel trajectory points, the longitude and latitude matrix of the navigation trajectory points, and the area of each of the first-class hexagons and each of the second-class hexagons, the index values of each of the first-class hexagons and each of the second-class hexagons are determined, and a first index value matrix of the first-class hexagons and a second index value matrix of the second-class hexagons are generated.
7. The method according to claim 6, characterized in that The first index value matrix includes a plurality of index value elements of 1 row and n+m columns, and the second index value matrix includes a plurality of index value elements of 1 row and t columns, where m is the required amount of supplementary points; or, the first index value matrix includes a plurality of index value elements of 1 column and n+m rows, and the second index value matrix includes a plurality of index value elements of 1 column and t rows, wherein n and t are both natural numbers greater than or equal to 3, m is a natural number greater than or equal to 0, and n+m≤t; determining the yaw trajectory point according to the index value difference between each of the first type of hexagons and each of the second type of hexagons, including: Based on the n+m-2 column index value elements of the first index value matrix, compare the t-2 column index value elements in the second index value matrix one by one; or based on the n+m-2 row index value elements of the first index value matrix, compare the t-2 row index value elements in the second index value matrix one by one; In response to a difference in the index value elements of a certain column or a certain row, the first travel trajectory point corresponding to the current type of hexagon or the current position of the driver is determined as a yaw trajectory point.
8. A device for identifying off-course trajectory points, characterized in that: The device includes: A trip information acquisition module, used to acquire the current trip track information and navigation path information of the target driver; the trip track information includes the trip starting point, the driver's current position and multiple first trip track points in the middle, and the navigation path information includes the trip starting point, the trip end point and multiple second trip track points in the middle; A trajectory smoothing processing module, used for smoothing the corresponding travel trajectory according to the travel trajectory information; A hexagon generation module, used to generate a plurality of first-class hexagons for the new travel trajectory after smoothing based on a preset grid accuracy, and to generate a plurality of second-class hexagons for the navigation trajectory corresponding to the navigation path information; An index value assigning module, used for assigning a corresponding index value to each of the first type of hexagons and each of the second type of hexagons; The yaw trajectory point positioning module is used to determine the yaw trajectory point according to the index value difference between each of the first type of hexagons and each of the second type of hexagons.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.
10. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.
