An adaptive yaw hotspot link identification method and system

Abstract

The application discloses a kind of self-adapting yaw hot spot section identification method and system, wherein method includes: obtaining vehicle yaw information, the yaw data obtained is stored to database, the yaw data includes yaw coordinate point, original planning route and re-planning route;Based on the time interval of pre-set, extract yaw data from database and execute data preprocessing;The coincidence degree of route planning before and after yaw is calculated to the yaw data after preprocessing, and the yaw data belonging to pseudo-yaw is removed based on the coincidence degree;Data clustering is carried out to the yaw coordinate point in all yaw data, to obtain yaw point clustering cluster;The density of clustering cluster yaw point in clustering cluster envelope polygon is calculated;Based on each vertex of clustering cluster envelope polygon, road network data is intercepted, and the road section in the range of clustering cluster envelope polygon is marked as yaw hot spot section;The data of yaw hot spot section is counted, to output the yaw hotness index of yaw hot spot section.

Description

Technical Field

[0001] This invention relates to the technical field of urban road veergence hotspot identification technology, specifically to an adaptive veergence hotspot road segment identification method and system. Background Technology

[0002] With the widespread application of location-based services (LBS) technology, electronic map navigation is increasingly used in the transportation industry. Deviation is the phenomenon where a vehicle's trajectory deviates from the pre-planned route. Deviation is influenced by factors such as road complexity, accessibility, road signs, and road conditions, as well as driver behavior. Deviation tends to cluster locally, particularly noticeable on urban roads. Identifying deviation hotspots in urban roads through big data analysis helps determine whether deviation is intentional detour, providing a basis for determining liability for ride-hailing drivers. Furthermore, it allows for advance navigation guidance and enlarged road maps when drivers approach these hotspots, significantly improving the service level of electronic navigation maps.

[0003] Chinese invention patent CN112815948A discloses a method, apparatus, computer device, and storage medium for identifying yaw patterns. This invention distinguishes between active yaw caused by user subjective selection and passive yaw caused by route attributes. The main steps include: determining the yaw point on the navigation route corresponding to the yaw behavior by comparing trajectory data and navigation data; obtaining yaw statistics for that yaw point and obtaining route attribute information for both the yaw route and the navigation route; and identifying whether the aforementioned yaw behavior is active yaw caused by user subjective selection or passive yaw caused by route attributes based on a combination of the yaw statistics, the yaw route, and the route attribute information of the navigation route.

[0004] Chinese invention patent CN103955596A discloses a comprehensive method for determining accident hotspots based on traffic accident data collection technology. This method includes: acquiring basic attribute data for each road segment of each road in the road network; merging and classifying similar road segments; acquiring information data on accidents occurring on each road segment of each road in the road network within a certain historical period; calculating the equivalent value of accidents occurring on the road segment under test within a historical year; calculating the equivalent index of accidents occurring on the road segment under test within a historical year; calculating the critical value of the average equivalent index of accidents occurring on similar road segments of the road segment under test within a historical year; and determining whether the road segment under test belongs to an accident hotspot based on the critical value between the equivalent index and the average equivalent index.

[0005] Chinese invention patent CN112365595A discloses an analysis method for identifying traffic accident hotspots based on alarm data point elements. The implementation steps are as follows: collecting alarm traffic accident data and generating WGS84 coordinates, importing them into a GIS platform, modeling accident point elements, and integrating collected temperature data; using Getis-Ord Gi* hotspot analysis to identify regional accident hotspots; performing cluster analysis on the accidents and identifying local accident hotspots through outlier analysis and outlier values ​​around accident hotspots; and using Geographic Information System (GIS) software, Thiessen polygons, kernel density analysis, and cluster analysis methods combining hotspot analysis and outlier analysis to identify accident hotspots.

[0006] As can be seen from the existing technologies described above, the methods for identifying traffic hotspots in the current technologies mainly involve counting the number of sub-segments or using methods such as hotspot analysis and spatial clustering to identify hotspot areas. The former is easily affected by the sub-segment segmentation parameters; the latter fails to locate the road structure and is mainly used for regional feature analysis, but cannot directly support business applications such as detour judgment and safety warning. Summary of the Invention

[0007] To overcome the above-mentioned technical defects, the present invention provides an adaptive method and system for identifying yaw hotspots.

[0008] To solve the above problems, the present invention is implemented according to the following technical solution:

[0009] In a first aspect, the present invention discloses an adaptive method for identifying yaw hotspots, comprising the following steps:

[0010] Step S1: Obtain vehicle yaw information and store the obtained yaw data in the database. The yaw data includes yaw coordinates, the original planned route, and the replanned route.

[0011] Step S2: Based on a preset time interval, extract yaw data from the database and perform data preprocessing;

[0012] Step S3: Calculate the overlap of route planning before and after yaw in the preprocessed yaw data, and remove yaw data that are pseudo-yaws based on the overlap.

[0013] Step S4: Perform data clustering on the yaw coordinates in all yaw data to obtain yaw point clusters, and then obtain the number of yaw points in the yaw point clusters and the area of ​​the polygon enclosing the cluster.

[0014] Step S5: Calculate the density of cluster skew points in the cluster outer polygons, and take the top n% of cluster outer polygons with the highest density of cluster skew points as hotspot regions;

[0015] Step S6: Extract road network data based on each vertex of the outer polygon of the cluster, and mark the road segments within the range of the outer polygon of the cluster as eccentricity hotspots.

[0016] Step S7: Count the number of deviation points and the number of passage trajectories included in the deviation hotspot road segment to output the deviation heat index of the deviation hotspot road segment.

[0017] As a preferred embodiment of the first aspect of the present invention, the step of calculating the overlap of route planning before and after yaw in the preprocessed yaw data, and removing yaw data that belongs to pseudo-yaw based on the overlap, specifically includes the following sub-steps:

[0018] Analyze the yaw data to extract the yaw coordinates, the original planned route, and the replanned route.

[0019] Obtain the latitude and longitude (x) of the trajectory point sequence in the original planned route. a1 ,y a1 ,x a2 ,y a2 ,x a3 ,y a3 ....x an ,y an );

[0020] Obtain the yaw point (x) p y p The coordinates (x) of the nearest trajectory point in the original planned route sequence are compared with those of the nearest trajectory point. ap ,y ap );

[0021] Using the coordinates (x) of the nearest trajectory point ap ,y ap Starting from , the original planned route is intercepted to obtain the sequence of trajectory guidance points (x). ap ,y ap ,x ap+1 ,y ap+2 ,x ap+3 ,y ap+3 ....x an ,y an ( ), to form a baseline planning route;

[0022] Obtain the latitude and longitude (x) of the replanning guide point sequence when replanning the route after yaw. b1 ,y b1 ,x b2 ,y b2 ,x b3 ,y b3 ....x bn ,y bn ( ), to form a route to be compared;

[0023] Obtain a specified threshold, and then obtain the buffer zone A of the baseline planning route based on the specified threshold;

[0024] Statistics on the guide points of the planned routes to be compared (x) b1 ,y b1 ,x b2 ,y b2 ,x b3 ,y b3 ....x bn ,y bn The number of items within the buffer area (num) x ;

[0025] The overlap between the planned route to be compared and the baseline planned route is calculated using the following formula:

[0026]

[0027] Wherein, the num x The number of guide points for the planned routes to be compared within the buffer zone A of the baseline route;

[0028] The number cnt This represents the total number of guide points for the planned routes to be compared.

[0029] The Ratio overlap The route overlap is defined as [0,1], and its value ranges from [0,1].

[0030] After obtaining the route overlap, the planned routes to be compared with a route overlap greater than a preset value are marked as pseudo-yawing yawing data.

[0031] Remove all yaw data that are false yaws.

[0032] As a preferred embodiment of the first aspect of the present invention, the step of performing data clustering on the yaw coordinate points in all yaw data to obtain yaw point clusters, and then obtaining the number of yaw points in the yaw point clusters and the area of ​​the enclosing polygon of the clusters, specifically includes the following sub-steps:

[0033] Get the latitude and longitude coordinates (x1, y1), (x2, y2), ..., (x2, y2) of all yaw points within a specified time interval. n ,y n );

[0034] Set the distance calculation method for yaw point clustering;

[0035] Considering the road network structure, a similarity model is constructed, using the shortest driving distance between two points;

[0036] Clustering algorithms that do not require pre-specifying the number of clusters, including the BIRCH and DBSCAN algorithms, are used to calculate the yaw point clusters.

[0037] The yaw point cluster includes a sequence of yaw points and the coordinates of the center point;

[0038] Count the number of eccentric points Pt in the eccentric point cluster. cnt ;

[0039] Get the coordinates (x) of all yaw points in the yaw point cluster. a1 ,y a1 ,x a2 ,y a2 ,...,x an ,y an The algorithm for generating minimum bounding polygons is used to calculate the bounding polygons (Poly(x)) corresponding to the yaw point clusters. b1 ,y b1 ,x b2 ,y b2 ,...,x bn ,y bn Then, the area A of the polygon Poly that encloses the cluster is calculated. poly .

[0040] As a preferred embodiment of the first aspect of the present invention, the step of calculating the density of cluster eccentricity points in the cluster bounding polygons and taking the top n% of cluster bounding polygons in terms of the density of cluster eccentricity points as hotspot regions specifically includes the following sub-steps:

[0041] The density of yaw points in the bounding polygon of the cluster corresponding to the yaw point cluster is calculated using the following formula:

[0042]

[0043] Wherein, the Pt cnt The number of yaw points in the cluster, A poly The area of ​​the polygon enclosing the cluster;

[0044] The z-score normalization method is used to normalize the point density data, specifically through the following formula:

[0045]

[0046] Among them, the σ is the average density of yaw points of the clusters within the bounding polygon of the cluster. A This is the standard deviation of the density of cluster yaw points in the polygon enclosing the cluster;

[0047] After obtaining the density of cluster yaw points in the outer polygon of each cluster, the outer polygon of the cluster is sorted based on the density of the corresponding cluster yaw points.

[0048] Get the preset range of values ​​for hotspot areas;

[0049] The polygons surrounding the clusters whose density ranks the top n% of the skew points are selected as hotspot regions.

[0050] As a preferred embodiment of the first aspect of the present invention, the specific calculation formula for the yaw heat index is as follows:

[0051]

[0052] Wherein, the Pt cnt The data for the yaw points contained in the yaw segment is obtained by creating a buffer for the segment and summing the number of yaw points contained in the buffer.

[0053] The Trip cnt The number of driving trajectories passing through this road segment within a specified time period is obtained by creating a buffer zone for this road segment and counting the number of trajectories intersecting with the buffer zone.

[0054] The z-score normalization method is used to normalize the YawIndex.

[0055] Secondly, the present invention also discloses an adaptive yaw hotspot identification system, comprising:

[0056] Yaw monitoring module M1 is used to acquire vehicle yaw information and store the acquired yaw data in a database. The yaw data includes yaw coordinates, the original planned route, and the replanned route.

[0057] The data preprocessing module M2 is used to extract yaw data from the database and perform data preprocessing based on a preset time interval.

[0058] The interference removal module M3 is used to calculate the overlap of route planning before and after yaw in the preprocessed yaw data, and remove yaw data that belongs to false yaw based on the overlap.

[0059] The data clustering module M4 is used to cluster the yaw coordinates in all yaw data to obtain yaw point clusters, and then obtain the number of yaw points in the yaw point clusters and the area of ​​the polygons surrounding the clusters.

[0060] The density calculation module M5 is used to calculate the density of cluster eccentricity points in the outer polygon of the cluster, and takes the top n% of the cluster outer polygons with the highest density of cluster eccentricity points as hotspot regions.

[0061] The hotspot marking module M6 is used to extract road network data based on each vertex of the polygon surrounding the cluster and mark the road segments within the polygon surrounding the cluster as eccentric hotspot road segments.

[0062] The heat output module M7 is used to count the number of deviation points and the number of passage trajectories contained in the deviation hotspot road segment, so as to output the deviation heat index of the deviation hotspot road segment.

[0063] In a preferred embodiment of the second aspect of the present invention, the interference removal module M3 performs the following sub-steps during operation:

[0064] Analyze the yaw data to extract the yaw coordinates, the original planned route, and the replanned route.

[0065] Obtain the latitude and longitude (x) of the trajectory point sequence in the original planned route. a1 ,y a1 ,x a2 ,y a2 ,x a3 ,y a3 ....x an ,y an );

[0066] Obtain the yaw point (x) p y p The coordinates (x) of the nearest trajectory point in the original planned route sequence are compared with those of the nearest trajectory point. ap ,y ap );

[0067] Using the coordinates (x) of the nearest trajectory point ap ,y ap Starting from , the original planned route is intercepted to obtain the sequence of trajectory guidance points (x). ap ,y ap ,x ap+1 ,y ap+2 ,x ap+3 ,y ap+3 ....x an ,y an ( ), to form a baseline planning route;

[0068] Obtain the latitude and longitude (x) of the replanning guide point sequence when replanning the route after yaw. b1 ,y b1 ,x b2 ,y b2 ,x b3 ,y b3 ....x bn ,y bn ( ), to form a route to be compared;

[0069] Obtain a specified threshold, and then obtain the buffer zone A of the baseline planning route based on the specified threshold;

[0070] Statistics on the guide points of the planned routes to be compared (x) b1 ,y b1 ,x b2 ,y b2 ,x b3 ,y b3 ....x bn ,y bn The number of items within the buffer area (num) x ;

[0071] The overlap between the planned route to be compared and the baseline planned route is calculated using the following formula:

[0072]

[0073] Wherein, the num x The number of guide points for the planned routes to be compared within the buffer zone A of the baseline route;

[0074] The number cnt This represents the total number of guide points for the planned routes to be compared.

[0075] The Ratio overlap The route overlap is defined as [0,1], and its value ranges from [0,1].

[0076] After obtaining the route overlap, the planned routes to be compared with a route overlap greater than a preset value are marked as pseudo-yawing yawing data.

[0077] Remove all yaw data that are false yaws.

[0078] In a preferred embodiment of the second aspect of the present invention, the data clustering module M4, when running, specifically performs the following sub-steps:

[0079] Get the latitude and longitude coordinates (x1, y1), (x2, y2), ..., (x2, y2) of all yaw points within a specified time interval. n ,y n );

[0080] Set the distance calculation method for yaw point clustering;

[0081] Considering the road network structure, a similarity model is constructed, using the shortest driving distance between two points;

[0082] Clustering algorithms that do not require pre-specifying the number of clusters, including the BIRCH and DBSCAN algorithms, are used to calculate the yaw point clusters.

[0083] The yaw point cluster includes a sequence of yaw points and the coordinates of the center point;

[0084] Count the number of eccentric points Pt in the eccentric point cluster. cnt ;

[0085] Get the coordinates (x) of all yaw points in the yaw point cluster. a1 ,y a1 ,x a2 ,y a2 ,...,x an ,y an The algorithm for generating minimum bounding polygons is used to calculate the bounding polygons (Poly(x)) corresponding to the yaw point clusters. b1 ,y b1 ,x b2 ,y b2 ,...,x bn ,y bn Then, the area A of the polygon Poly that encloses the cluster is calculated. poly .

[0086] In a preferred embodiment of the second aspect of the present invention, the density calculation module M5, when running, specifically performs the following sub-steps:

[0087] The density of yaw points in the bounding polygon of the cluster corresponding to the yaw point cluster is calculated using the following formula:

[0088]

[0089] Wherein, the Pt cnt The number of yaw points in the cluster, A poly The area of ​​the polygon enclosing the cluster;

[0090] The z-score normalization method is used to normalize the point density data, specifically through the following formula:

[0091]

[0092] Among them, the σ is the average density of yaw points of the clusters within the bounding polygon of the cluster. A This is the standard deviation of the density of cluster yaw points in the polygon enclosing the cluster;

[0093] After obtaining the density of cluster yaw points in the outer polygon of each cluster, the outer polygon of the cluster is sorted based on the density of the corresponding cluster yaw points.

[0094] Get the preset range of values ​​for hotspot areas;

[0095] The polygons surrounding the clusters whose density ranks the top n% of the skew points are selected as hotspot regions.

[0096] As a preferred embodiment of the second aspect of the present invention, the specific calculation formula for the yaw heat index is as follows:

[0097]

[0098] Wherein, the Pt cnt The data for the yaw points contained in the yaw segment is obtained by creating a buffer for the segment and summing the number of yaw points contained in the buffer.

[0099] The Trip cnt The number of driving trajectories passing through this road segment within a specified time period is obtained by creating a buffer zone for this road segment and counting the number of trajectories intersecting with the buffer zone.

[0100] The z-score normalization method is used to normalize the YawIndex.

[0101] Compared with the prior art, the beneficial effects of the present invention are:

[0102] This invention creatively utilizes a data-driven approach to analyze historical data and identify deviance hotspots without requiring pre-dividing into sub-segments, exhibiting adaptive characteristics. The adaptive deviance hotspot identification method disclosed in this invention is less affected by sub-segmentation parameters, can pinpoint the road surface, and directly supports detour detection, safety warnings, and other business applications, making deviance warnings faster and more accurate. Based on the deviance hotspot index and deviance hotspot area, it can promptly remind drivers to focus their attention and warn against intentional detours, optimizing deviance display during navigation. Attached Figure Description

[0103] The specific embodiments of the present invention will be further described in detail below with reference to the accompanying drawings, wherein:

[0104] Figure 1 This is a flowchart illustrating the adaptive yaw hotspot identification method of the present invention.

[0105] Figure 2 This is a schematic diagram of the adaptive yaw hotspot identification system of the present invention. Detailed Implementation

[0106] Preferred embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While preferred embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that the present disclosure will be thorough and complete, and will fully convey the scope of the present disclosure to those skilled in the art.

[0107] The term "comprising" and its variations as used herein signify open inclusion, i.e., "including but not limited to". Unless otherwise stated, the term "or" means "and / or". The term "based on" means "at least partially based on". The terms "one example embodiment" and "one embodiment" mean "at least one example embodiment". The term "another embodiment" means "at least one additional embodiment". The terms "first", "second", etc., may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0108] Access devices and servers can be connected directly or indirectly via wired or wireless communication. Access devices can be terminals or servers. The target application runs on the access device. The target application is an application capable of making data requests to the server, such as social applications, payment applications, and game applications. The server can be an application server providing services to the target application, or a proxy server distinct from the application server corresponding to the target application. The server identifies whether each access device is malicious and intercepts data packets from malicious devices. When the server acts as a proxy server, it forwards data packets not originating from malicious devices to the application server. Terminals can be desktop terminals or mobile terminals. Mobile terminals can include smartphones, tablets, laptops, desktop computers, smart speakers, smartwatches, etc., but are not limited to these. Servers can be independent physical servers, server clusters or distributed systems composed of multiple physical servers, or cloud servers providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms.

[0109] Example 1

[0110] like Figure 1 As shown, in a first aspect, the present invention discloses an adaptive yaw hotspot identification method, comprising the following steps:

[0111] Step S1: Obtain vehicle yaw information and store the obtained yaw data in the database. The yaw data includes yaw coordinates, the original planned route, and the replanned route.

[0112] Specifically, the driver's app listens for deviation events from the map navigation module. Upon deviation, the driver's app reports the deviation record to the data server. The data server extracts at least the following data from the deviation record: deviation point longitude, deviation point latitude, deviation time, order number, driver number, and the latitude and longitude sequence of the original planned route guidance point (x...). a1 ,y a1 ,x a2 ,y a2 ,...,x an ,y an ,), replan the latitude and longitude sequence of the guide point (x b1 ,y b1 ,x b2 ,y b2 ,...,x bn ,y bn ,).

[0113] In this example, a pgsql database is preferably used to store yaw technology data. The data server uses a geometry format to store the planned route guidance point data, which facilitates spatial processing and analysis.

[0114] Step S2: Based on a preset time interval, extract yaw data from the database and perform data preprocessing;

[0115] Specifically, the specified time interval can be one week, one month, one quarter, or one year. The data server extracts the yaw records within the time range based on the timestamps of the yaw records and stores them as a temporary table.

[0116] Preferably, the data preprocessing includes at least: outlier removal and data normalization.

[0117] Abnormal data removal includes at least the following processing: First, removal of abnormal latitude and longitude data at deviation points, removing data with longitude values ​​outside the range of [-180, 180] and latitude values ​​outside the range of [-90, 90]. Second, removal of deviation records where the straight-line distance between the deviation point and the starting point of the replanned route exceeds a threshold.

[0118] Data standardization processing includes at least the following: First, using a statistical coordinate system, such as the 2000 National Geodetic Coordinate System, GCJ-02 coordinate system, or WGS84 coordinate system. Second, storing latitude and longitude coordinates in double-precision format, retaining 6 decimal places.

[0119] Step S3: Calculate the overlap of route planning before and after yaw in the preprocessed yaw data, and remove yaw data that are considered pseudo-yaws based on the overlap. This includes the following sub-steps:

[0120] Analyze the yaw data to extract the yaw coordinates, the original planned route, and the replanned route.

[0121] Obtain the latitude and longitude (x) of the trajectory point sequence in the original planned route. a1 ,y a1 ,x a2 ,y a2 ,x a3 ,y a3 ....x an ,y an );

[0122] Obtain the yaw point (x) p y p The coordinates (x) of the nearest trajectory point in the original planned route sequence are compared with those of the nearest trajectory point. ap ,y ap );

[0123] Using the coordinates (x) of the nearest trajectory point ap ,y ap Starting from , the original planned route is intercepted to obtain the sequence of trajectory guidance points (x). ap ,y ap ,x ap+1 ,y ap+2 ,x ap+3 ,y ap+3 ....x an ,y an ( ), to form a baseline planning route;

[0124] Obtain the latitude and longitude (x) of the replanning guide point sequence when replanning the route after yaw. b1 ,y b1 ,x b2 ,y b2 ,x b3 ,y b3 ....x bn ,y bn ( ), to form a route to be compared;

[0125] Obtain a specified threshold, and then obtain the buffer zone A of the baseline planning route based on the specified threshold;

[0126] Statistics on the guide points of the planned routes to be compared (x) b1 ,y b1 ,x b2 ,y b2 ,x b3 ,y b3 ....x bn ,y bn The number of items within the buffer area (num) x ;

[0127] The overlap between the planned route to be compared and the baseline planned route is calculated using the following formula:

[0128]

[0129] Wherein, the num x The number of guide points for the planned routes to be compared within the buffer zone A of the baseline route;

[0130] The number cnt This represents the total number of guide points for the planned routes to be compared.

[0131] The Ratio overlap The route overlap is defined as [0,1], and its value ranges from [0,1].

[0132] After obtaining the route overlap, the planned routes to be compared with a route overlap greater than a preset value are marked as pseudo-yawing yawing data. For example, the planned routes with an overlap greater than 95% are marked as pseudo-yawing.

[0133] Remove all yaw data that are false yaws.

[0134] Preferably, the GeoTools open-source code package is used, and the `geometry.buffer(double distance)` function is called to generate the buffer for the line segment. The `distance` is the buffer distance, which is of double precision. Specifically, the buffer distance is set to 20 meters.

[0135] Step S4: Perform data clustering on the yaw coordinates in all yaw data to obtain yaw point clusters, and then obtain the number of yaw points in each cluster and the area of ​​the enclosing polygon of the cluster; specifically including the following sub-steps:

[0136] Get the latitude and longitude coordinates (x1, y1), (x2, y2), ..., (x2, y2) of all yaw points within a specified time interval. n ,y n );

[0137] Set the distance calculation method for yaw point clustering;

[0138] Considering the road network structure, a similarity model is constructed, using the shortest driving distance between two points;

[0139] Clustering algorithms that do not require pre-specifying the number of clusters, including the BIRCH and DBSCAN algorithms, are used to calculate the yaw point clusters.

[0140] The yaw point cluster includes a sequence of yaw points and the coordinates of the center point;

[0141] Count the number of eccentric points Pt in the eccentric point cluster. cnt;

[0142] Get the coordinates (x) of all yaw points in the yaw point cluster. a1 ,y a1 ,x a2 ,y a2 ,...,x an ,y an The algorithm for generating minimum bounding polygons is used to calculate the bounding polygons (Poly(x)) corresponding to the yaw point clusters. b1 ,y b1 ,x b2 ,y b2 ,...,x bn ,y bn Then, the area A of the polygon Poly that encloses the cluster is calculated. poly .

[0143] Step S5: Calculate the density of cluster eccentricity points in the bounding polygons of the clusters, and select the top n% of the cluster bounding polygons by density of cluster eccentricity points as hotspot regions; specifically including the following sub-steps:

[0144] In this preferred embodiment, a clustering algorithm that does not require pre-specifying the number of clusters, such as the BIRCH or DBSCAN algorithm, is used to calculate the yaw point clusters. Specifically, the BIRCH and DBSCAN clustering algorithms are implemented using the scikit-learn open-source machine learning library.

[0145] The circumscribed polygon is a polygon formed by connecting the outermost points of the point set. In this example, the GeoTools open-source code package is preferably used, and the geometry.convexHull() function is called to generate the circumscribed polygon of the point set.

[0146] The density of yaw points in the bounding polygon of the cluster corresponding to the yaw point cluster is calculated using the following formula:

[0147]

[0148] Wherein, the Pt cnt The number of yaw points in the cluster, A poly The area of ​​the polygon enclosing the cluster;

[0149] The z-score normalization method is used to normalize the point density data, specifically through the following formula:

[0150]

[0151] Among them, the σ is the average density of yaw points of the clusters within the bounding polygon of the cluster. A This is the standard deviation of the density of cluster yaw points in the polygon enclosing the cluster;

[0152] After obtaining the density of cluster yaw points in the outer polygon of each cluster, the outer polygon of the cluster is sorted based on the density of the corresponding cluster yaw points.

[0153] Get the preset range of values ​​for hotspot areas;

[0154] The polygons surrounding the clusters whose density ranks the top n% of the skew points are selected as hotspot regions.

[0155] Specifically, in this embodiment, the yaw point clusters with the highest point density in the top 20% are selected as hotspot areas.

[0156] Step S6: Extract road network data based on each vertex of the outer polygon of the cluster, and mark the road segments within the range of the outer polygon of the cluster as eccentricity hotspots.

[0157] The circumscribed polygon of the hotspot area is the circumscribed polygon of the cluster of yaw points with the highest point density (top n%). Extracting road network data refers to overlaying the polygon with the road network data to extract the road segments contained within the polygon.

[0158] In this example, the GeoTools open-source code package is preferably used, and the ClippedFeatureCollection class is used to calculate the clipped road network data. Specifically, after the road network clipping is completed, the road network topology should be reconstructed.

[0159] Step S7: Count the number of deviation points and the number of passage trajectories included in the deviation hotspot road segment to output the deviation heat index of the deviation hotspot road segment.

[0160] As a preferred embodiment of the first aspect of the present invention, the specific calculation formula for the yaw heat index is as follows:

[0161]

[0162] Wherein, the Pt cnt The data for the yaw points contained in the yaw segment is obtained by creating a buffer for the segment and summing the number of yaw points contained in the buffer.

[0163] The Trip cnt The number of driving trajectories passing through this road segment within a specified time period is obtained by creating a buffer zone for this road segment and counting the number of trajectories intersecting with the buffer zone.

[0164] The z-score normalization method is used to normalize the YawIndex.

[0165] This invention creatively utilizes a data-driven approach to analyze historical data and identify deviance hotspots without requiring pre-dividing into sub-segments, exhibiting adaptive characteristics. The adaptive deviance hotspot identification method disclosed in this invention is less affected by sub-segmentation parameters, can pinpoint the road surface, and directly supports detour detection, safety warnings, and other business applications, making deviance warnings faster and more accurate. Based on the deviance hotspot index and deviance hotspot area, it can promptly remind drivers to focus their attention and warn against intentional detours, optimizing deviance display during navigation.

[0166] This invention takes a ride-hailing scenario as an example. It monitors the map navigation module, and when a deviation is triggered, records the deviation coordinates, the original planned route, and the replanned route, storing these in a database. At specified time intervals, it extracts deviation records from the database and performs data preprocessing. It calculates the overlap between the planned routes before and after the deviation, eliminating false deviation data. It clusters deviation point data and calculates the area of ​​the bounding polygon, statistically analyzes point density, and extracts the top n% as hotspot areas. It uses the vertices of the bounding polygon of the cluster to extract road network data, marking road segments within the boundary polygon range as deviation hotspot road segments. It statistically analyzes the number of deviation points and the number of travel trajectories contained in the deviation hotspot road segments, calculating the deviation heat index of the road segments.

[0167] This invention uses a data-driven approach to analyze historical data and identify deviance hotspots without requiring pre-division of sub-segments, exhibiting adaptive characteristics. Beneficial effects include: (1) When a driver passes through this segment, the navigation system provides a deviation warning voice broadcast, improving driver attention. (2) In ride-hailing safety warning applications, it provides a data basis for determining whether a driver intentionally takes a detour; if the driver triggers navigation on a non-deviation segment, there is a greater chance of triggering a deliberate detour warning. (3) It provides input support for navigation visual optimization; the electronic map navigation page optimizes the display at deviation points, showing a magnified view to reduce the probability of drivers taking the wrong route and deviating from the intended path.

[0168] Other steps of the adaptive yaw hotspot identification method described in this embodiment are described in the prior art.

[0169] Example 2

[0170] like Figure 2 As shown, in a second aspect, the present invention also discloses an adaptive yaw hotspot identification system, comprising:

[0171] Yaw monitoring module M1 is used to acquire vehicle yaw information and store the acquired yaw data in a database. The yaw data includes yaw coordinates, the original planned route, and the replanned route.

[0172] The data preprocessing module M2 is used to extract yaw data from the database and perform data preprocessing based on a preset time interval.

[0173] The interference removal module M3 is used to calculate the overlap of route planning before and after yaw in the preprocessed yaw data, and remove yaw data that belongs to false yaw based on the overlap.

[0174] The data clustering module M4 is used to cluster the yaw coordinates in all yaw data to obtain yaw point clusters, and then obtain the number of yaw points in the yaw point clusters and the area of ​​the polygons surrounding the clusters.

[0175] The density calculation module M5 is used to calculate the density of cluster eccentricity points in the outer polygon of the cluster, and takes the top n% of the cluster outer polygons with the highest density of cluster eccentricity points as hotspot regions.

[0176] The hotspot marking module M6 is used to extract road network data based on each vertex of the polygon surrounding the cluster and mark the road segments within the polygon surrounding the cluster as eccentric hotspot road segments.

[0177] The heat output module M7 is used to count the number of deviation points and the number of passage trajectories contained in the deviation hotspot road segment, so as to output the deviation heat index of the deviation hotspot road segment.

[0178] In a preferred embodiment of the second aspect of the present invention, the interference removal module M3 performs the following sub-steps during operation:

[0179] Analyze the yaw data to extract the yaw coordinates, the original planned route, and the replanned route.

[0180] Obtain the latitude and longitude (x) of the trajectory point sequence in the original planned route. a1 ,y a1 ,x a2 ,y a2 ,x a3 ,y a3 ....x an ,y an );

[0181] Obtain the yaw point (x) p y p The coordinates (x) of the nearest trajectory point in the original planned route sequence are compared with those of the nearest trajectory point. ap ,y ap );

[0182] Using the coordinates (x) of the nearest trajectory point ap ,y ap Starting from , the original planned route is intercepted to obtain the sequence of trajectory guidance points (x). ap,y ap ,x ap+1 ,y ap+2 ,x ap+3 ,y ap+3 ....x an ,y an ( ), to form a baseline planning route;

[0183] Obtain the latitude and longitude (x) of the replanning guide point sequence when replanning the route after yaw. b1 ,y b1 ,x b2 ,y b2 ,x b3 ,y b3 ....x bn ,y bn ( ), to form a route to be compared;

[0184] Obtain a specified threshold, and then obtain the buffer zone A of the baseline planning route based on the specified threshold;

[0185] Statistics on the guide points of the planned routes to be compared (x) b1 ,y b1 ,x b2 ,y b2 ,x b3 ,y b3 ....x bn ,y bn The number of items within the buffer area (num) x ;

[0186] The overlap between the planned route to be compared and the baseline planned route is calculated using the following formula:

[0187]

[0188] Wherein, the num x The number of guide points for the planned routes to be compared within the buffer zone A of the baseline route;

[0189] The number cnt This represents the total number of guide points for the planned routes to be compared.

[0190] The Ratio overlap The route overlap is defined as [0,1], and its value ranges from [0,1].

[0191] After obtaining the route overlap, the planned routes to be compared with a route overlap greater than a preset value are marked as pseudo-yawing yawing data.

[0192] Remove all yaw data that are false yaws.

[0193] In a preferred embodiment of the second aspect of the present invention, the data clustering module M4, when running, specifically performs the following sub-steps:

[0194] Get the latitude and longitude coordinates (x1, y1), (x2, y2), ..., (x2, y2) of all yaw points within a specified time interval. n ,y n );

[0195] Set the distance calculation method for yaw point clustering;

[0196] Considering the road network structure, a similarity model is constructed, using the shortest driving distance between two points;

[0197] Clustering algorithms that do not require pre-specifying the number of clusters, including the BIRCH and DBSCAN algorithms, are used to calculate the yaw point clusters.

[0198] The yaw point cluster includes a sequence of yaw points and the coordinates of the center point;

[0199] Count the number of eccentric points Pt in the eccentric point cluster. cnt ;

[0200] Get the coordinates (x) of all yaw points in the yaw point cluster. a1 ,y a1 ,x a2 ,y a2 ,...,x an ,y an The algorithm for generating minimum bounding polygons is used to calculate the bounding polygons (Poly(x)) corresponding to the yaw point clusters. b1 ,y b1 ,x b2 ,y b2 ,...,x bn ,y bn Then, the area A of the polygon Poly that encloses the cluster is calculated. poly .

[0201] In a preferred embodiment of the second aspect of the present invention, the density calculation module M5, when running, specifically performs the following sub-steps:

[0202] The density of yaw points in the bounding polygon of the cluster corresponding to the yaw point cluster is calculated using the following formula:

[0203]

[0204] Wherein, the Pt cnt The number of yaw points in the cluster, A poly The area of ​​the polygon enclosing the cluster;

[0205] The z-score normalization method is used to normalize the point density data, specifically through the following formula:

[0206]

[0207] Among them, the σ is the average density of yaw points of the clusters within the bounding polygon of the cluster. A This is the standard deviation of the density of cluster yaw points in the polygon enclosing the cluster;

[0208] After obtaining the density of cluster yaw points in the outer polygon of each cluster, the outer polygon of the cluster is sorted based on the density of the corresponding cluster yaw points.

[0209] Get the preset range of values ​​for hotspot areas;

[0210] The polygons surrounding the clusters whose density ranks the top n% of the skew points are selected as hotspot regions.

[0211] As a preferred embodiment of the second aspect of the present invention, the specific calculation formula for the yaw heat index is as follows:

[0212]

[0213] Wherein, the Pt cnt The data for the yaw points contained in the yaw segment is obtained by creating a buffer for the segment and summing the number of yaw points contained in the buffer.

[0214] The Trip cnt The number of driving trajectories passing through this road segment within a specified time period is obtained by creating a buffer zone for this road segment and counting the number of trajectories intersecting with the buffer zone.

[0215] The z-score normalization method is used to normalize the YawIndex.

[0216] In summary, the adaptive yaw hotspot identification system described in this embodiment of the invention can execute all the steps of the adaptive yaw hotspot identification method described in Embodiment 1 during operation and achieve the same technical effect.

[0217] Other structures of the adaptive yaw hotspot identification system described in this embodiment are available in the prior art.

[0218] Example 3

[0219] This invention also discloses an electronic device, including at least one processor and a memory communicatively connected to the at least one processor. The memory stores instructions executable by the at least one processor. When the at least one processor executes the instructions, it specifically implements the following steps: acquiring vehicle yaw information; storing the acquired yaw data in a database, the yaw data including yaw coordinates, the original planned route, and the replanned route; extracting yaw data from the database and performing data preprocessing based on a preset time interval; calculating the overlap between the preprocessed yaw data and the planned routes before and after the yaw, based on... Overlapping data is used to remove pseudo-yawing data; yawing coordinates in all yawing data are clustered to obtain yawing point clusters, and then the number of yawing points in each cluster and the area of ​​the enclosing polygon of the cluster are obtained; the density of yawing points in the enclosing polygon of the cluster is calculated, and the top n% of the cluster enclosing polygons in terms of density are taken as hotspot areas; road network data is extracted based on each vertex of the enclosing polygon of the cluster, and road segments within the range of the enclosing polygon of the cluster are marked as yawing hotspot road segments; the number of yawing points and the number of passage trajectories contained in the yawing hotspot road segments are counted to output the yawing heat index of the yawing hotspot road segments.

[0220] Example 4

[0221] This invention also discloses a storage medium storing a computer program. When the computer program is executed by a processor, it specifically implements the following steps: acquiring vehicle yaw information and storing the acquired yaw data in a database, the yaw data including yaw coordinates, the original planned route, and the replanned route; extracting yaw data from the database and performing data preprocessing based on a preset time interval; calculating the overlap degree of the route planning before and after yaw on the preprocessed yaw data, and removing yaw data that are considered pseudo-yawing based on the overlap degree; and performing data processing on the yaw coordinates in all yaw data. The system performs row data clustering to obtain detour point clusters, and then obtains the number of detour points in each cluster and the area of ​​the enclosing polygon of the cluster. It calculates the density of detour points within the enclosing polygon of each cluster, and selects the top n% of the clusters by density as hotspot regions. Based on the vertices of the enclosing polygons, road network data is extracted, and road segments within the range of the enclosing polygons are marked as detour hotspot road segments. The number of detour points and the number of passage trajectories contained in each detour hotspot road segment are counted to output the detour heat index of the detour hotspot road segment.

[0222] This disclosure can be a method, apparatus, system, and / or computer program product. A computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for performing various aspects of this disclosure.

[0223] Computer-readable storage media can be tangible devices capable of holding and storing instructions for use by an instruction execution device. Computer-readable storage media can be, for example—but not limited to—electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any suitable combination thereof. The computer-readable storage media used herein are not to be construed as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.

[0224] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0225] Computer program instructions used to perform the operations of this disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, Java, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing the status information of the computer-readable program instructions to implement various aspects of this disclosure.

[0226] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0227] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processing unit of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0228] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0229] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which includes one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0230] Various embodiments of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical applications, or improvements to the technology in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. An adaptive yaw hotspot identification method, characterized in that, Includes the following steps: Obtain vehicle yaw information and store the obtained yaw data in a database. The yaw data includes yaw coordinates, the original planned route, and the replanned route. Based on preset time intervals, yaw data is extracted from the database and data preprocessing is performed; The overlap of route planning before and after yaw is calculated on the preprocessed yaw data, and yaw data that is a pseudo yaw is removed based on the overlap. Data clustering is performed on the yaw coordinates in all yaw data to obtain yaw point clusters, and then the number of yaw points in the yaw point clusters and the area of ​​the enclosing polygon of the cluster are obtained. Calculate the density of cluster eccentricity points in the outer polygons of clusters, and select the top n% of cluster outer polygons by density of cluster eccentricity points as hotspot regions; Road network data is extracted from each vertex of the outer polygon of the cluster, and road segments within the range of the outer polygon of the cluster are marked as eccentricity hotspots. The number of deviation points and the number of passage routes included in the deviation hotspots are counted to output the deviation heat index of the deviation hotspots.

2. The adaptive yaw hotspot identification method according to claim 1, characterized in that, The step of calculating the overlap of route planning before and after yaw in the preprocessed yaw data, and removing yaw data that is considered false yaw based on the overlap, specifically includes the following sub-steps: Analyze the yaw data to extract the yaw coordinates, the original planned route, and the replanned route. Obtain the latitude and longitude (x) of the trajectory point sequence in the original planned route. a1 ,y a1 ,x a2 ,y a2 ,x a3 ,y a3 ....x an ,y an ); Obtain the yaw point (x) p y p The coordinates (x) of the nearest trajectory point in the original planned route sequence are compared with those of the nearest trajectory point. ap ,y ap ); Using the coordinates (x) of the nearest trajectory point ap ,y ap Starting from , the original planned route is intercepted to obtain the sequence of trajectory guidance points (x). ap ,y ap ,x ap+1 ,y ap+2 ,x ap+3 ,y ap+3 ....x an ,y an ( ), to form a baseline planning route; Obtain the latitude and longitude of the replanning guide point sequence when replanning the route after yaw. (x b1 ,y b1 ,x b2 ,y b2 ,x b3 ,y b3 ....x bn ,y bn ( ), to form a route to be compared; Obtain a specified threshold, and then obtain the buffer zone A of the baseline planning route based on the specified threshold; Statistics on the guide points of the planned routes to be compared (x) b1 ,y b1 ,x b2 ,y b2 ,x b3 ,y b3 ....x bn ,y bn The number of items within the buffer area (num) x ; The overlap between the planned route to be compared and the baseline planned route is calculated using the following formula: Wherein, the num x The number of guide points for the planned routes to be compared within the buffer zone A of the baseline route; The number cnt This represents the total number of guide points for the planned routes to be compared. The Ratio overlap The route overlap is defined as [0,1], and its value ranges from [0,1]. After obtaining the route overlap, the planned routes to be compared with a route overlap greater than a preset value are marked as pseudo-yawing yawing data. Remove all yaw data that are false yaws.

3. The adaptive yaw hotspot identification method according to claim 2, characterized in that, The step of clustering yaw coordinates in all yaw data to obtain yaw point clusters, and then obtaining the number of yaw points in each cluster and the area of ​​the enclosing polygon of the cluster, specifically includes the following sub-steps: Get the latitude and longitude coordinates (x1, y1), (x2, y2), ..., (x2, y2) of all yaw points within a specified time interval. n ,y n ); Set the distance calculation method for yaw point clustering; Considering the road network structure, a similarity model is constructed, using the shortest driving distance between two points; Clustering algorithms that do not require pre-specifying the number of clusters, including the BIRCH and DBSCAN algorithms, are used to calculate the yaw point clusters. The yaw point cluster includes a sequence of yaw points and the coordinates of the center point; Count the number of eccentric points Pt in the eccentric point cluster. cnt ; Get the coordinates (x) of all yaw points in the yaw point cluster. a1 ,y a1 ,x a2 ,y a2 ,...,x an ,y an The algorithm for generating minimum bounding polygons is used to calculate the bounding polygons (Poly(x)) corresponding to the yaw point clusters. b1 ,y b1 ,x b2 ,y b2 ,...,x bn ,y bn Then, the area A of the polygon Poly that encloses the cluster is calculated. poly .

4. The adaptive yaw hotspot identification method according to claim 3, characterized in that, The calculation of the density of cluster eccentricity points in the bounding polygons of clusters, and the selection of the top n% of cluster bounding polygons by density of cluster eccentricity points as hotspot regions, specifically includes the following sub-steps: The density of yaw points in the bounding polygon of the cluster corresponding to the yaw point cluster is calculated using the following formula: Wherein, the Pt cnt The number of yaw points in the cluster, A poly The area of ​​the polygon enclosing the cluster; The z-score normalization method is used to normalize the point density data, specifically through the following formula: Among them, the σ is the average density of yaw points of the clusters within the bounding polygon of the cluster. A This is the standard deviation of the density of cluster yaw points in the polygon enclosing the cluster; After obtaining the density of cluster yaw points in the outer polygon of each cluster, the outer polygon of the cluster is sorted based on the density of the corresponding cluster yaw points. Get the preset range of values ​​for hotspot areas; The polygons surrounding the clusters whose density ranks the top n% of the skew points are selected as hotspot regions.

5. The adaptive yaw hotspot identification method according to claim 4, characterized in that: The specific formula for calculating the yaw heat index is as follows: Wherein, the Pt cnt The data for the yaw points contained in the yaw segment is obtained by creating a buffer for the segment and summing the number of yaw points contained in the buffer. The Trip cnt The number of driving trajectories passing through this road segment within a specified time period is obtained by creating a buffer zone for this road segment and counting the number of trajectories intersecting with the buffer zone. The z-score normalization method is used to normalize the YawIndex.

6. An adaptive yaw hotspot identification system, characterized in that, include: The yaw monitoring module is used to acquire vehicle yaw information and store the acquired yaw data in a database. The yaw data includes yaw coordinates, the original planned route, and the replanned route. The data preprocessing module is used to extract yaw data from the database and perform data preprocessing based on preset time intervals. The interference removal module is used to calculate the overlap of route planning before and after yaw in the preprocessed yaw data, and remove yaw data that belongs to pseudo yaw based on the overlap. The data clustering module is used to cluster the yaw coordinates in all yaw data to obtain yaw point clusters, and then obtain the number of yaw points in the yaw point clusters and the area of ​​the polygons surrounding the clusters. The density calculation module is used to calculate the density of cluster eccentricity points in the outer polygon of the cluster, and selects the top n% of the cluster outer polygons with the highest density of cluster eccentricity points as hotspot regions. The hotspot marking module is used to extract road network data based on each vertex of the polygon surrounding the cluster, and mark the road segments within the range of the polygon surrounding the cluster as eccentric hotspot road segments; The heat output module is used to count the number of deviation points and the number of passage trajectories contained in the deviation hotspot road segments, so as to output the deviation heat index of the deviation hotspot road segments.

7. The adaptive yaw hotspot identification system according to claim 6, characterized in that, When the interference removal module is running, it specifically performs the following sub-steps: Analyze the yaw data to extract the yaw coordinates, the original planned route, and the replanned route. Obtain the latitude and longitude (x) of the trajectory point sequence in the original planned route. a1 ,y a1 ,x a2 ,y a2 ,x a3 ,y a3 ....x an ,y an ); Obtain the yaw point (x) p y p The coordinates (x) of the nearest trajectory point in the original planned route sequence are compared with those of the nearest trajectory point. ap ,y ap ); Using the coordinates (x) of the nearest trajectory point ap ,y ap Starting from , the original planned route is intercepted to obtain the sequence of trajectory guidance points (x). ap ,y ap ,x ap+1 ,y ap+2 ,x ap+3 ,y ap+3 ....x an ,y an ( ), to form a baseline planning route; Obtain the latitude and longitude of the replanning guide point sequence when replanning the route after yaw. (x b1 ,y b1 ,x b2 ,y b2 ,x b3 ,y b3 ....x bn ,y bn ( ), to form a route to be compared; Obtain a specified threshold, and then obtain the buffer zone A of the baseline planning route based on the specified threshold; Statistics on the guide points of the planned routes to be compared (x) b1 ,y b1 ,x b2 ,y b2 ,x b3 ,y b3 ....x bn ,y bn The number of items within the buffer area (num) x ; The overlap between the planned route to be compared and the baseline planned route is calculated using the following formula: Wherein, the num x The number of guide points for the planned routes to be compared within the buffer zone A of the baseline route; The number cnt This represents the total number of guide points for the planned routes to be compared. The Ratio overlap The route overlap is defined as [0,1], and its value ranges from [0,1]. After obtaining the route overlap, the planned routes to be compared with a route overlap greater than a preset value are marked as pseudo-yawing yawing data. Remove all yaw data that are false yaws.

8. The adaptive yaw hotspot identification system according to claim 7, characterized in that, When the data clustering module is running, it specifically performs the following sub-steps: Get the latitude and longitude coordinates (x1, y1), (x2, y2), ..., (x2, y2) of all yaw points within a specified time interval. n ,y n ); Set the distance calculation method for yaw point clustering; Considering the road network structure, a similarity model is constructed, using the shortest driving distance between two points; Clustering algorithms that do not require pre-specifying the number of clusters, including the BIRCH and DBSCAN algorithms, are used to calculate the yaw point clusters. The yaw point cluster includes a sequence of yaw points and the coordinates of the center point; Count the number of eccentric points Pt in the eccentric point cluster. cnt ; Get the coordinates (x) of all yaw points in the yaw point cluster. a1 ,y a1 ,x a2 ,y a2 ,...,x an ,y an The algorithm for generating minimum bounding polygons is used to calculate the bounding polygons (Poly(x)) corresponding to the yaw point clusters. b1 ,y b1 ,x b2 ,y b2 ,...,x bn ,y bn Then, the area A of the polygon Poly that encloses the cluster is calculated. poly .

9. The adaptive yaw hotspot identification system according to claim 8, characterized in that, When the density calculation module is running, it specifically performs the following sub-steps: The density of yaw points in the bounding polygon of the cluster corresponding to the yaw point cluster is calculated using the following formula: Wherein, the Pt cnt The number of yaw points in the cluster, A poly The area of ​​the polygon enclosing the cluster; The z-score normalization method is used to normalize the point density data, specifically through the following formula: Among them, the σ is the average density of yaw points of the clusters within the bounding polygon of the cluster. A This is the standard deviation of the density of cluster yaw points in the polygon enclosing the cluster; After obtaining the density of cluster yaw points in the outer polygon of each cluster, the outer polygon of the cluster is sorted based on the density of the corresponding cluster yaw points. Get the preset range of values ​​for hotspot areas; The polygons surrounding the clusters whose density ranks the top n% of the skew points are selected as hotspot regions.

10. The adaptive yaw hotspot identification system according to claim 9, characterized in that: The specific formula for calculating the yaw heat index is as follows: Wherein, the Pt cnt The data for the yaw points contained in the yaw segment is obtained by creating a buffer for the segment and summing the number of yaw points contained in the buffer. The Trip cnt The number of driving trajectories passing through this road segment within a specified time period is obtained by creating a buffer zone for this road segment and counting the number of trajectories intersecting with the buffer zone. The z-score normalization method is used to normalize the YawIndex.

Images