WO2025190096A1 - 路线检测方法、装置、设备、存储介质和计算机程序产品 - Google Patents

路线检测方法、装置、设备、存储介质和计算机程序产品

Info

Publication number
WO2025190096A1
WO2025190096A1 PCT/CN2025/080155 CN2025080155W WO2025190096A1 WO 2025190096 A1 WO2025190096 A1 WO 2025190096A1 CN 2025080155 W CN2025080155 W CN 2025080155W WO 2025190096 A1 WO2025190096 A1 WO 2025190096A1
Authority
WO
WIPO (PCT)
Prior art keywords
navigation route
pass
abnormal
time range
specified time
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
PCT/CN2025/080155
Other languages
English (en)
French (fr)
Inventor
余圆圆
谢真灼
孟繁荣
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tencent Technology (Shenzhen) Co Ltd
Original Assignee
Tencent Technology (Shenzhen) Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Tencent Technology (Shenzhen) Co Ltd filed Critical Tencent Technology (Shenzhen) Co Ltd
Priority to EP25769268.1A priority Critical patent/EP4779267A1/en
Publication of WO2025190096A1 publication Critical patent/WO2025190096A1/zh
Anticipated expiration legal-status Critical
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3407—Route searching; Route guidance specially adapted for specific applications
    • G01C21/3415—Dynamic re-routing, e.g. recalculating the route when the user deviates from calculated route or after detecting real-time traffic data or accidents
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/28—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
    • G01C21/30—Map- or contour-matching
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags or using precalculated routes
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3453—Special cost functions, i.e. other than distance or default speed limit of road segments
    • G01C21/3461—Preferred or disfavoured areas, e.g. dangerous zones, toll or emission zones, intersections, manoeuvre types or segments such as motorways, toll roads or ferries
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3453—Special cost functions, i.e. other than distance or default speed limit of road segments
    • G01C21/3469—Fuel consumption; Energy use; Emission aspects
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3453—Special cost functions, i.e. other than distance or default speed limit of road segments
    • G01C21/3484—Personalized, e.g. from learned user behaviour or user-defined profiles
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3453—Special cost functions, i.e. other than distance or default speed limit of road segments
    • G01C21/3492—Special cost functions, i.e. other than distance or default speed limit of road segments employing speed data or traffic data, e.g. real-time or historical
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/36—Input/output arrangements for on-board computers
    • G01C21/3605—Destination input or retrieval
    • G01C21/3617—Destination input or retrieval using user history, behaviour, conditions or preferences, e.g. predicted or inferred from previous use or current movement
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/36—Input/output arrangements for on-board computers
    • G01C21/3691—Retrieval, searching and output of information related to real-time traffic, weather, or environmental conditions
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
    • G01C21/3804—Creation or updating of map data
    • G01C21/3807—Creation or updating of map data characterised by the type of data
    • G01C21/3815—Road data

Definitions

  • the present application relates to the field of computer technology, and in particular to a route detection method, apparatus, computer equipment, storage medium, and computer program product.
  • a route detection method includes:
  • a passage number sequence corresponding to the target navigation route is obtained based on the number of times each of the two adjacent road sections passes through within a specified time range, and it is determined based on the passage number sequence whether the target navigation route passes through an abnormal road section.
  • a route detection device includes:
  • An acquisition module configured to acquire a target navigation route to be detected, wherein the target navigation route includes a plurality of sequentially connected road sections;
  • an adjacent road segment determining module configured to determine a plurality of pairs of adjacent road segments based on the plurality of sequentially connected road segments
  • a travel frequency query module is used to query the travel frequency of each of the two adjacent road sections within a specified time range based on the historical navigation route;
  • the anomaly detection module is used to obtain a passage number sequence corresponding to the target navigation route based on the passage number of each of the two adjacent road sections within a specified time range, and determine whether the target navigation route passes through an abnormal road section based on the passage number sequence.
  • a computer device comprising a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the above-mentioned route detection method when executing the computer-readable instructions.
  • a computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the route detection method described above.
  • a computer program product which includes computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the route detection method are implemented.
  • FIG1 is a diagram illustrating an application environment of a route detection method in some embodiments.
  • FIG2 is a schematic diagram of a navigation route
  • FIG3 is an enlarged view of a local section of a navigation route
  • Figure 4 is an enlarged view of the distribution of traffic flow change trajectories
  • FIG5 is a schematic flow chart of a route detection method in some embodiments.
  • FIG6 is a schematic diagram of a process for counting the number of passes of adjacent road segments in some embodiments.
  • FIG7 is a schematic diagram of navigation routes in some other embodiments.
  • FIG8 is a schematic diagram of navigation routes in yet other embodiments.
  • FIG9 is a schematic diagram of the overall framework of route correction in some embodiments.
  • FIG10 is a schematic diagram of a route before and after correction in some embodiments.
  • FIG11 is a block diagram of a route detection device in some embodiments.
  • FIG12 is a diagram illustrating the internal structure of a computer device in some embodiments.
  • the route detection method provided in the embodiment of the present application can be applied to the application environment shown in Figure 1.
  • the terminal 102 communicates with the server 104 through the network.
  • the data storage system can store the data that the server 104 needs to process.
  • the data storage system can be integrated on the server 104, or it can be placed on the cloud or other servers.
  • the server 104 obtains a target navigation route generated based on the starting position and the end position, and the target navigation route includes a plurality of sequentially connected road sections. Based on the plurality of sequentially connected road sections, multiple pairs of adjacent road sections are determined.
  • the number of passes of the adjacent road sections within a specified time range is queried based on the historical navigation route. According to the number of passes of each adjacent road section within the specified time range, a pass number sequence corresponding to the navigation route is obtained, and it is judged whether the target navigation route passes through an abnormal road section based on the pass number sequence.
  • Terminal 102 may be, but is not limited to, various desktop computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices.
  • IoT devices may include intelligent voice interaction devices, smart TVs, smart air conditioners, smart vehicle-mounted devices, aircraft, etc.
  • Portable wearable devices may include smart watches, smart bracelets, head-mounted devices, etc.
  • Server 104 may be implemented as a standalone server or a server cluster consisting of multiple servers. The embodiments of the present application can be applied to various scenarios, including but not limited to cloud technology, artificial intelligence, smart transportation, and assisted driving.
  • Map road network data contains a large number of road segments (links).
  • a road segment is the smallest unit in road network data, and map road network data can be divided into hundreds of millions of road segments.
  • Multiple topologically connected road segments constitute a route, that is, a route is composed of a string of links.
  • link1 is connected to link2
  • the route direction is from link1 to link2
  • the number of vehicles passing from link1 to link2 within a specified time range (such as an hour, a day, a week, or a month) can be called the vehicle traffic flow from link1 to link2 within the specified time range.
  • anomalies can be detected based on the traffic volume on each road section in the road network. For example, if the traffic volume on a road section has been very low for a long time, or if the traffic volume on a road section has recently dropped sharply, then this road section may be identified as an abnormal road section. Because this approach fails to integrate the target navigation route, the detection effect is poor and its impact on the planned navigation route is limited. For example, if the traffic volume on a certain road section is neither particularly high nor particularly low based on traffic volume data, it can be identified as a side road. In this case, the navigation route planning process will likely not avoid this road section.
  • the route detection method provided in the embodiment of the present application when determining whether the target navigation route passes through an abnormal section, is not based on the number of passes of each section, but on the flow change trajectory of the target navigation route (reflected by the sequence of the number of passes) to identify the abnormal section.
  • the abnormal section can be detected through the flow change trajectory, so that the abnormal route in the target navigation route can be corrected, thereby improving the rationality and accuracy of route planning, avoiding the waste of computing resources and energy consumption of the route navigation equipment caused by unreasonable navigation route planning, and improving the user experience of route navigation.
  • navigation starts from a low-level road at the starting point, then moves to a high-level road, then back to a low-level road near the end point.
  • a route detection method is provided.
  • the method is described by taking the application of the method to the server 104 in FIG1 as an example, and includes the following steps:
  • Step 502 Acquire a target navigation route to be detected, where the target navigation route includes a plurality of sequentially connected road sections.
  • the target navigation route is a navigation route obtained by route planning based on the starting point and the end point, and the target navigation route includes a plurality of sequentially connected sections.
  • the terminal may send a navigation route generation request to a server providing map navigation services based on the starting point and the end point input by the user, and the server may generate at least one navigation route based on the received navigation route generation request, and the target navigation route may be one of the at least one navigation route.
  • the server may perform anomaly detection on the target navigation route.
  • the server may correct it, obtain a corrected navigation route, and return it to the terminal.
  • the server may also filter out the target navigation route with the abnormal section from the at least one navigation route, and return the remaining navigation route to the terminal.
  • Step 504 Determine multiple pairs of adjacent road sections based on multiple sequentially connected road sections.
  • the target navigation route obtained after the navigation route planning is completed is a relatively optimal path between the starting and ending points, which includes multiple sections connected in sequence, that is, multiple sections are connected in sequence according to a topological relationship.
  • the server can determine multiple pairs of adjacent sections according to the multiple sections included in the target navigation route.
  • the server can traverse the sections passed by the target navigation route in sequence, and construct the current traversed section and the next traversed section into a pair of adjacent sections until the traversal is completed when the current traversed section is the second to last section.
  • the server can start from the second traversed section and construct the current traversed section and the previous traversed section into a pair of adjacent sections until the traversal is completed when the current traversed section is the first to last section.
  • the target navigation route is a route formed by topologically connecting link1, link2, link3, link4, and link5 in sequence.
  • the server can determine that the multiple pairs of adjacent road segments included in the target navigation route are: link1-link2, link2-link3, link3-link4, link4-link5 in sequence.
  • Step 506 query the number of times two adjacent road sections have been traveled within a specified time range based on the historical navigation routes.
  • Historical navigation routes are routes generated and completed for vehicle navigation in the past.
  • the server can store the corresponding travel counts.
  • the "past period" can be the past 30 minutes, past hour, past day, past week, past month, past three months, and so on, with no specific time range restrictions.
  • the server can query the travel counts of two adjacent road segments within a specified time range based on historical navigation routes within that time range.
  • the server may periodically (e.g., every 30 minutes, every hour, every day, every month, etc.) perform the following steps:
  • Step 602 Acquire a set of historical navigation routes within a specified time range.
  • the server can set execution cycles and specified time ranges for different regions. For example, for hot areas such as cities, the server can be set to obtain a collection of historical navigation routes within the past hour every 30 minutes, or to obtain a collection of historical navigation routes within the past hour every hour. For areas with low traffic volume such as the outer ring road of the city, the server can be set to obtain a collection of historical navigation routes within the past hour every 2 hours. For other areas with less traffic volume, such as remote areas, it is set to obtain a collection of historical navigation routes within the past month every week. For the historical navigation routes in the historical navigation route set, the server also needs to obtain the number of navigations for each historical navigation route within the specified time range. For example, in the past period of time, the same historical navigation route was used by multiple users and the number of completed navigations was 200 times, then the corresponding number of navigations is 200.
  • Step 604 Decompose each historical navigation route in the historical navigation route set to obtain two adjacent road segments included in the historical navigation route.
  • Step 606 Obtain a set of pairwise adjacent road sections based on the decomposed pairwise adjacent road sections.
  • the server can disassemble each historical navigation route in the historical navigation route set to obtain the two adjacent road sections included in the historical navigation route.
  • the historical navigation route set obtained by the server within a specified time range includes 5 historical navigation routes, namely:
  • Historical navigation route 1 link1, link2, link3, link4, link5, the number of navigations is 500;
  • Historical navigation route 2 link3, link4, link5, link6, link7, the number of navigations is 100;
  • Historical navigation route 4 link1, link2, link4, link5, navigation times is 50;
  • the two adjacent road sections that are disassembled include:
  • Step 608 For each pair of adjacent road segments in the set of adjacent road segments, the number of navigations of the historical navigation routes including the adjacent road segments within the specified time range is accumulated to obtain the number of travels of the adjacent road segments within the specified time range.
  • link2-link3 the number of passes is 800;
  • link3-link4 the number of passes is 900;
  • link4-link5 the number of passes is 950;
  • link6-link7 the number of passes is 150;
  • link2-link5 the number of passes is 50;
  • link2-link4 number of passes: 50.
  • the server periodically updates the number of trips between two adjacent road segments within a specified timeframe, ensuring the validity and timeliness of the trip count data. This allows the server to accurately count and store the number of trips between two adjacent road segments with topological relationships within the map network data within a specified timeframe. This number of trips reflects the vehicle traffic volume between the two adjacent road segments. Therefore, after obtaining multiple pairs of two adjacent road segments within a target navigation route, the server can query the corresponding number of trips within the specified timeframe based on the aforementioned statistical data. This makes the subsequently generated trip count sequence more accurate, thereby improving the accuracy of abnormal route detection.
  • Step 508 Obtain a passage number sequence corresponding to the target navigation route based on the passage number of each pair of adjacent road sections within a specified time range, and determine whether the target navigation route passes through an abnormal road section based on the passage number sequence.
  • a pass number sequence corresponding to the target navigation route can be obtained.
  • the pass number sequence reflects the traffic change trend of the target navigation route, and abnormal sections in the target navigation route can be detected through the traffic change trend.
  • the abnormal section can be detected through the traffic change trend.
  • navigation starts from a low-level road at the starting point, navigates to a high-level road, and then navigates back to a low-level road near the end point.
  • the traffic flow from the starting point to the end point generally changes from low to high to low. If the traffic flow change trend corresponding to the navigation route is navigating from a high-flow road to a low-flow road with a sharp drop in traffic, and then returns to a high-flow road, it can be considered that this planned navigation route is likely to be abnormal.
  • the server can determine the corresponding traffic flow change trend based on the traffic count sequence corresponding to the target navigation route, and compare the traffic flow change trend corresponding to the target navigation route with the traffic flow change trends corresponding to the normal route or the abnormal route to determine whether the target navigation route passes through an abnormal section.
  • a pass count sequence corresponding to the target navigation route is obtained based on the number of times each pair of adjacent road sections passes through a specified time range, and whether the target navigation route passes through an abnormal road section is determined based on the pass count sequence, including: arranging the corresponding number of times each pair of adjacent road sections passes through a specified time range according to the order of each pair of adjacent road sections on the target navigation route to obtain a pass count sequence corresponding to the target navigation route; when the numerical change trend corresponding to the pass count sequence does not match the preset pass trajectory, it is determined that the target navigation route passes through an abnormal road section.
  • the preset passage trajectory reflects the traffic flow change trend corresponding to the normal route.
  • the preset passage trajectory is a trajectory from a low-flow section to a high-flow section and then back to the low-flow section.
  • the server can determine the numerical change trend corresponding to the pass count sequence, for example, whether it is a low value, a high value, and then a low value.
  • the numerical change trend corresponding to the pass count sequence is matched with a preset pass trajectory. If the numerical change trend does not match the preset pass trajectory, it is determined that the target navigation route passes through an abnormal section. If the numerical change trend matches the preset pass trajectory, it is determined that the target navigation route does not pass through an abnormal section, that is, the target navigation route passes the abnormality detection.
  • the target navigation route is determined to pass through an abnormal section, including: for each pass number in the pass number sequence, obtaining the adjacent pass numbers on both sides of the current pass number in the pass number sequence; when the current pass number is less than a preset threshold and the adjacent pass numbers on both sides of the current pass number are greater than N times the current pass number, determining that the numerical change trend corresponding to the pass number sequence does not match the preset pass trajectory, and determining that the two adjacent sections corresponding to the current pass number are abnormal sections, where N is a number greater than 10.
  • the adjacent pass counts on either side of the current pass count are relatively adjacent pass counts in the pass count sequence, not necessarily directly adjacent pass counts. In other words, as long as there is a subsequence in the pass count sequence whose numerical trend does not match the preset pass trajectory, an abnormal road section exists in that subsequence. If the current pass count is less than a preset threshold and the adjacent pass counts on either side of the current pass count are greater than N times the current pass count, it can be determined that the numerical trend corresponding to the pass count sequence does not match the preset pass trajectory.
  • the value of N can be determined based on actual data analysis; for example, N can be 20. For example, if the current pass count is 50, while the adjacent pass counts on both sides are 5000, a significant difference exists. This can indicate that an abnormality exists in the pairwise adjacent road sections corresponding to the current pass count, or in the later of the pairwise adjacent road sections.
  • the target navigation route is: link1-link2-link4-link5.
  • the corresponding pass count sequence of the target navigation route is: 600-50-950. It can be seen that the target navigation route has experienced the corresponding value change area, which does not match the normal traffic flow from the starting point to the end point, which is generally low -> high -> low. It can be determined that there are abnormal sections in the target navigation route, such as temporary road closures.
  • a pass count sequence corresponding to the target navigation route is obtained based on the number of times each pair of adjacent road sections passes through a specified time range, and whether the target navigation route passes through an abnormal road section is determined based on the pass count sequence, including: arranging the corresponding number of times each pair of adjacent road sections passes through a specified time range according to the order of each pair of adjacent road sections on the target navigation route to obtain a pass count sequence corresponding to the target navigation route; when the numerical change trend corresponding to the pass count sequence matches the preset pass trajectory, it is determined that the target navigation route passes through an abnormal road section.
  • the preset passage trajectory reflects the traffic flow change trend corresponding to the abnormal route.
  • the preset passage trajectory is a trajectory from a high-flow section to a low-flow section and then back to a high-flow section.
  • the server can determine the numerical change trend corresponding to the pass count sequence, for example, whether it is a high value to a low value and then to a high value, and match the numerical change trend corresponding to the pass count sequence with the preset pass trajectory.
  • the numerical change trend matches the preset pass trajectory, it is determined that the target navigation route passes through an abnormal section.
  • Figure 7 is a schematic diagram of a navigation route in one embodiment.
  • densely populated areas represent traffic-intensive areas, and white road sections represent the navigation route.
  • This navigation route clearly passes through sections with zero traffic (i.e., sections indicated by arrows in Figure 7), indicating that this navigation route is not planned properly.
  • the server may determine that the target navigation route passes through a "side road," i.e., a road section that is passable but has poor traffic capacity, if the current pass count is greater than a preset threshold and the adjacent pass counts on both sides of the current pass count are greater than M times the current pass count. If this type of road section is detected in the planned target navigation route, the server may prompt the terminal or display relevant prompt information for the user to select.
  • a side road i.e., a road section that is passable but has poor traffic capacity
  • Figure 8 is a schematic diagram of a navigation route in one embodiment.
  • denser areas with small circles represent heavier traffic.
  • the white line represents the navigation route.
  • the server can use finer-grained traffic flow data to detect anomalies, such as historical navigation routes within a one-hour period. This is because the traffic volume on the abnormal road section may still be very high within a day, making it difficult to detect the anomaly.
  • traffic flow data within a one-hour period can identify the anomaly. In other words, the more timely the traffic flow data, the better, such as historical navigation routes within half an hour, historical navigation routes within ten minutes, and so on.
  • the traffic flow within a fine-grained time range indicates an anomaly, it means that an abnormal event occurred within a relatively short period of time.
  • data within a longer time range can be used for anomaly detection.
  • querying the number of times two adjacent road segments are passed within a specified time range based on historical navigation routes includes: querying the number of times two adjacent road segments are passed within a specified time range based on historical navigation routes within a first specified time range; and when it is determined that the target navigation route does not pass through an abnormal road segment based on the number of times each two adjacent road segments are passed within the first specified time range, continuing to query the number of times two adjacent road segments are passed within a specified time range based on historical navigation routes within a second specified time range; wherein the time granularity of the second specified time range is greater than the time granularity of the first specified time range.
  • historical navigation route data within different specified time ranges is used to cover different areas.
  • the time granularity of the second specified time range is greater than that of the first specified time range.
  • the second specified time range is daily traffic, i.e., historical navigation route data within a day
  • the second specified time range is monthly traffic, i.e., historical navigation route data within a month.
  • the historical navigation route data with a longer time granularity i.e., the historical navigation route data within the second specified time range
  • anomaly detection of navigation routes in various regions of the map road network data can be covered.
  • the traffic volume is neither particularly high nor particularly low, but there is a significant difference in traffic volume from the adjacent road sections on both sides, anomalies can be identified, thereby improving the rationality of route planning.
  • a pass count sequence corresponding to a target navigation route is obtained based on the pass counts of each pair of adjacent road segments within a specified time range, and determining whether the target navigation route passes through an abnormal road segment based on the pass count sequence includes:
  • a second pass count sequence corresponding to the navigation route is obtained based on the pass count of each pair of adjacent sections within the second specified time range, and whether the target navigation route passes through an abnormal section is determined based on the second pass count sequence.
  • the time granularity is different, and the number of passes corresponding to two adjacent sections is different.
  • the server needs to determine the sequence of the number of passes corresponding to the target navigation route within different time ranges respectively, so as to accurately detect whether there are abnormal sections in the target navigation route.
  • the route detection method further includes:
  • the target navigation route is corrected by bypassing the abnormal section to obtain a corrected navigation route; and when it is judged that the target navigation route does not pass through an abnormal section based on the number of times each pair of adjacent road sections are passed within the first specified time range, and when it is judged that the target navigation route passes through an abnormal section based on the number of times each pair of adjacent road sections are passed within the second specified time range, the target navigation route is corrected by avoiding the abnormal section to obtain a corrected navigation route.
  • the time granularity is different, and the number of passes corresponding to two adjacent sections is different.
  • the server needs to determine whether there are abnormal sections in the sequence of pass times corresponding to the target navigation route within different time ranges, so as to accurately detect whether there are abnormal sections in the target navigation route.
  • the first step is to integrate traffic offline.
  • the traffic of road sections can be calculated by time granularity.
  • the server counts the traffic of daily, weekly, monthly, quarterly and hourly sections to obtain the number of passes for each road section corresponding to different time granularities.
  • the online navigation service can load the above statistical data.
  • the target navigation route is generated.
  • anomaly detection is performed, as shown in Figure 9, which specifically includes:
  • Step 902 load the daily road traffic, and identify whether there are abnormal sections in the target navigation route. If not, execute step 904 ; if so, execute step 908 .
  • Step 904 continue to load the weekly road traffic, identify whether there are abnormal sections in the target navigation route, if not, execute step 906 , if yes, execute step 908 .
  • Step 906 continue to load the monthly road traffic, identify whether there are abnormal sections in the target navigation route, if not, then end the identification and return to the recalled route, if so, execute step 908.
  • Step 908 determining abnormal road sections
  • Step 910 avoid abnormal road sections and perform local route correction
  • Step 912 Use the generated partial path to replace the abnormal path in the target navigation route to obtain a corrected navigation route
  • Step 914 Mark the abnormal road section.
  • the abnormal road section can be avoided during subsequent route planning.
  • the route correction method includes the following steps:
  • the number of navigations of the historical navigation routes including the adjacent road segments within the specified time range is accumulated to obtain the number of passages of the adjacent road segments within the specified time range.
  • the embodiments of the present application can be applied to vehicle navigation scenarios. For example, a user can input a starting and ending location through a terminal. The server will then plan a route based on the starting and ending locations based on the map network data, obtaining N navigation routes. The server will then perform an anomaly check on each navigation route using the method provided in the embodiments of the present application. If an abnormal section exists in the navigation route, the server may return a prompt to the terminal, or the server may correct the abnormal section and return the corrected navigation route to the terminal.
  • An acquisition module 1102 is configured to acquire a target navigation route to be detected.
  • the target navigation route includes a plurality of sequentially connected road segments;
  • the travel times query module 1106 is used to query the travel times of two adjacent road sections within a specified time range based on the historical navigation route;
  • the anomaly detection module 1108 is used to obtain a passage number sequence corresponding to the target navigation route based on the passage number of each pair of adjacent road sections within a specified time range, and determine whether the target navigation route passes through an abnormal road section based on the passage number sequence.
  • the route detection device 1100 further includes:
  • the statistical module is used to obtain a set of historical navigation routes within a specified time range, disassemble each historical navigation route in the historical navigation route set to obtain the pairwise adjacent road segments included in the historical navigation route, obtain a pairwise adjacent road segment set based on the disassembled pairwise adjacent road segments, and for each pair of pairwise adjacent road segments in the pairwise adjacent road segment set, accumulate the number of navigations of the historical navigation routes including the pairwise adjacent road segments within the specified time range to obtain the number of passages of the pairwise adjacent road segments within the specified time range.
  • the travel count query module 1106 is used to query the travel count of two adjacent road segments within a specified time range based on the historical navigation routes within a first specified time range; and is also used to continue to query the travel count of two adjacent road segments within a specified time range based on the historical navigation routes within a second specified time range when it is determined that the target navigation route does not pass through an abnormal road segment based on the travel count of each two adjacent road segments within the first specified time range; wherein the time granularity of the second specified time range is greater than the time granularity of the first specified time range.
  • the anomaly detection module 1108 is used to obtain a first pass count sequence corresponding to the navigation route based on the pass count of each pairwise adjacent road section within a first specified time range, and determine whether the target navigation route passes through an abnormal road section based on the first pass count sequence; and is also used to obtain a second pass count sequence corresponding to the navigation route based on the pass count of each pairwise adjacent road section within a second specified time range, when it is determined that the target navigation route does not pass through an abnormal road section based on the first pass count sequence, and determine whether the target navigation route passes through an abnormal road section based on the second pass count sequence.
  • the route detection device 1100 further includes:
  • the correction module is used to correct the target navigation route by avoiding the abnormal section when it is judged that the target navigation route passes through an abnormal section based on the number of times each pair of adjacent sections passes through within a first specified time range, so as to obtain a corrected navigation route; and is also used to correct the target navigation route by avoiding the abnormal section when it is judged that the target navigation route does not pass through an abnormal section based on the number of times each pair of adjacent sections passes through within the first specified time range, and when it is judged that the target navigation route passes through an abnormal section based on the number of times each pair of adjacent sections passes through within a second specified time range, so as to obtain a corrected navigation route.
  • the anomaly detection module 1108 is also used to arrange the corresponding number of passes of each pair of adjacent road sections within a specified time range according to the order of each pair of adjacent road sections on the target navigation route, so as to obtain a pass number sequence corresponding to the target navigation route; when the numerical change trend corresponding to the pass number sequence does not match the preset pass trajectory, it is determined that the target navigation route passes through an abnormal section.
  • the anomaly detection module 1108 is further used to obtain, for each pass number in the pass number sequence, the adjacent pass numbers on both sides of the current pass number in the pass number sequence; when the current pass number is less than a preset threshold and the adjacent pass numbers on both sides of the current pass number are greater than N times the current pass number, determine that the numerical change trend corresponding to the pass number sequence does not match the preset pass trajectory, and determine that the two adjacent road sections corresponding to the current pass number are abnormal road sections, where N is a number greater than 10.
  • the route detection device 1100 further includes:
  • a marking module is used to mark abnormal sections when the target navigation route passes through abnormal sections.
  • the route planning module is used to plan a route for the received navigation route generation request by avoiding the abnormal road section when the abnormal mark of the abnormal road section is not invalid.
  • the route detection device 1100 further includes:
  • the correction module is used to correct the target navigation route when the target navigation route passes through an abnormal section to obtain a corrected navigation route, which does not include the abnormal section.
  • the correction module is also used to determine the two endpoints corresponding to the abnormal section when the target navigation route passes through an abnormal section, regenerate a local path based on the two endpoints, and use the generated local path to replace the abnormal path in the target navigation route to obtain a navigation correction route.
  • the route detection device 1100 obtains a target navigation route, determines multiple pairs of adjacent road segments included in the target navigation route, queries the number of passes of the adjacent road segments within a specified time range based on the historical navigation route, obtains a pass number sequence corresponding to the target navigation route based on the number of passes of each adjacent road segment within the specified time range, and determines whether the target navigation route passes through an abnormal road segment based on the pass number sequence.
  • the abnormal road segment is identified based on the flow change trajectory of the target navigation route (reflected by the flow number sequence) rather than the number of passes of each road segment.
  • the abnormal road segment when the number of passes of a road segment fails to reflect an abnormality, the abnormal road segment can be detected through the flow change trajectory, thereby improving the rationality and accuracy of route planning, avoiding the waste of computing resources and energy consumption of the route navigation device caused by unreasonable navigation route planning, and improving the user experience of route navigation.
  • Each module in the route detection device 1100 may be implemented in whole or in part through software, hardware, or a combination thereof.
  • Each module may be embedded in or independent of a processor in a computer device in hardware form, or may be stored in a computer device memory in software form, so that the processor can call and execute the corresponding operations of each module.
  • a computer device which may be a server, and its internal structure diagram may be shown in Figure 12.
  • the computer device includes a processor, a memory, an input/output interface (I/O), and a communication interface.
  • the processor, memory, and I/O interface are connected via a system bus, and the communication interface is connected to the system bus via the I/O interface.
  • the processor of the computer device is used to provide computing and control capabilities.
  • the memory of the computer device includes a non-volatile storage medium and an internal memory.
  • the non-volatile storage medium stores an operating system, computer-readable instructions, and a database.
  • the internal memory provides an environment for the operation of the operating system and computer-readable instructions in the non-volatile storage medium.
  • the database of the computer device is used to store map road network data, abnormal road section data, etc.
  • the I/O interface of the computer device is used to exchange information between the processor and external devices.
  • the communication interface of the computer device is used to communicate with external terminals via a network connection.
  • FIG12 is merely a block diagram of a portion of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied.
  • the specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.
  • a computer device including a memory and a processor.
  • the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the route detection method provided in the embodiment of the present application are implemented.
  • a computer-readable storage medium on which computer-readable instructions are stored.
  • the steps of the route detection method provided in the embodiment of the present application are implemented.
  • user information including but not limited to user device information, user personal information, etc.
  • data including but not limited to data used for analysis, stored data, displayed data, etc.
  • any reference to memory, database or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory.
  • Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc.
  • Volatile memory can include random access memory (RAM) or external cache memory, etc.
  • RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).
  • the database involved in the various embodiments provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains.
  • the processors involved in the various embodiments provided in this application may be, but are not limited to, general-purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, data processing logic devices based on quantum computing, etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Automation & Control Theory (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Social Psychology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Atmospheric Sciences (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • Ecology (AREA)
  • Environmental & Geological Engineering (AREA)
  • Environmental Sciences (AREA)
  • Navigation (AREA)

Abstract

一种路线检测方法，包括：获取待检测的目标导航路线，目标导航路线包括多个依次连接的路段(502)；基于多个依次连接的路段，确定多对两两相邻路段(504)；基于历史导航路线查询两两相邻路段在指定时间范围内的通行次数(506)；根据各两两相邻路段在指定时间范围内的通行次数，得到目标导航路线对应的通行次数序列，根据通行次数序列判断目标导航路线是否途径异常路段(508)。

Description

路线检测方法、装置、设备、存储介质和计算机程序产品
本申请要求于2024年03月14日提交中国专利局，申请号为202410309879.1，申请名称为“路线检测方法、装置、设备、存储介质和计算机程序产品”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及计算机技术领域，特别是涉及一种路线检测方法、装置、计算机设备、存储介质和计算机程序产品。
背景技术
随着计算机技术和互联网技术的发展与进步，用户出行前可以通过地图导航应用进行路线导航，然而，倘若实际道路上临时出现了一些异常情况，如临时封路、交通事故等，则在生成导航路线时无法及时避开发生这些异常情况的路段，路线规划的合理性较差，当用户通过该导航路线进行路线导航，途径这些异常情况的路段的情况下，就不得不临时改变路线绕行，不仅浪费了导航设备的计算资源和耗能，还可能会增加额外的通行时间，给用户带来极大不便，导致用户体验不佳。
发明内容
根据本申请的各种实施例，提供了一种路线检测方法。所述方法包括：
获取待检测的目标导航路线，所述目标导航路线包括多个依次连接的路段；
基于所述多个依次连接的路段，确定多对两两相邻路段；
基于历史导航路线查询所述两两相邻路段在指定时间范围内的通行次数；
根据各所述两两相邻路段在指定时间范围内的通行次数，得到所述目标导航路线对应的通行次数序列，根据所述通行次数序列判断所述目标导航路线是否途径异常路段。
根据本申请的各种实施例，提供了一种路线检测装置。所述装置包括：
获取模块，用于获取待检测的目标导航路线，所述目标导航路线包括多个依次连接的路段；
相邻路段确定模块，用于基于所述多个依次连接的路段，确定多对两两相邻路段；
通行次数查询模块，用于基于历史导航路线查询所述两两相邻路段在指定时间范围内的通行次数；
异常检测模块，用于根据各所述两两相邻路段在指定时间范围内的通行次数，得到所述目标导航路线对应的通行次数序列，根据所述通行次数序列判断所述目标导航路线是否途径异常路段。
根据本申请的各种实施例，提供了一种计算机设备。所述计算机设备包括存储器和处理器，所述存储器存储有计算机可读指令，所述处理器执行所述计算机可读指令时实现上述路线检测方法的步骤。
根据本申请的各种实施例，提供了一种计算机可读存储介质。所述计算机可读存储介质，其上存储有计算机可读指令，计算机可读指令被处理器执行时实现上述路线检测方法的步骤。
根据本申请的各种实施例，提供了一种计算机程序产品。所述计算机程序产品，包括计算机可读指令，该计算机可读指令被处理器执行时实现上述路线检测方法的步骤。
本申请的一个或多个实施例的细节在下面的附图和描述中提出。本申请的其它特征、目的和优点将从说明书、附图以及权利要求书变得明显。
附图说明
为了更清楚地说明本申请实施例中的技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1为一些实施例中路线检测方法的应用环境图；
图2为一个导航路线的示意图；
图3为一个导航路线的局部路段的放大图；
图4为放大图的通行流量变化轨迹分布图；
图5为一些实施例中路线检测方法的流程示意图；
图6为一些实施例中统计相邻路段的通行次数的流程示意图；
图7为另一些实施例中导航路线的示意图；
图8为又一些实施例中导航路线的示意图；
图9为一些实施例中的路线修正的整体框架示意图；
图10为一些实施例中路线修正前后的示意图；
图11为一些实施例中路线检测装置的结构框图；
图12为一些实施例中计算机设备的内部结构图。
具体实施方式
为了使本申请的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本申请进行进一步详细说明。应当理解，此处描述的具体实施例仅仅用以解释本申请，并不用于限定本申请。
本申请实施例提供的路线检测方法，可以应用于如图1所示的应用环境中。其中，终端102通过网络与服务器104进行通信。数据存储系统可以存储服务器104需要处理的数据。数据存储系统可以集成在服务器104上，也可以放在云上或其他服务器上。在一些实施例中，服务器104获取基于起点位置和终点位置生成的目标导航路线，该目标导航路线包括多个依次连接的路段，基于多个依次连接的路段，确定多对两两相邻路段，基于历史导航路线查询两两相邻路段在指定时间范围内的通行次数，根据各两两相邻路段在指定时间范围内的通行次数，得到导航路线对应的通行次数序列，根据通行次数序列判断目标导航路线是否途径异常路段。
终端102可以但不限于是各种台式计算机、笔记本电脑、智能手机、平板电脑、物联网设备和便携式可穿戴设备，物联网设备可为智能语音交互设备、智能电视、智能空调、智能车载设备、飞行器等。便携式可穿戴设备可为智能手表、智能手环、头戴设备等。服务器104可以用独立的服务器或者是多个服务器组成的服务器集群来实现。本申请实施例可应用于各种场景，包括但不限于云技术、人工智能、智慧交通、辅助驾驶等。
在地图路网数据中，包含大量的路段(link)，路段是路网数据中的最小单元，地图路网数据可分割成数以亿计的路段。拓扑连接的多个路段构成一条路线，即路线由link串构成。当两个路段存在拓扑连接关系时，例如link1与link2连接，且路线方向是从link1到link2，则在指定时间范围内(如一个小时、一天、一周或一个月等)从link1到link2的车辆通行次数，可称为在该指定时间范围内从link1到link2车辆通行流量。
在一些实施方式中，为及时发现路网中那些无法通行(例如，临时封路或临时堵塞)的异常路段，可以基于路网中每条路段上的通行流量来检测异常。例如，若一条路段上的通行流量长期很低，或一条路段上的流量近期发生骤降，则该路段可被识别为异常路段。由于这种方式未能结合目标导航路线，导致检测效果不佳，对规划的导航路线产生的作用有限。例如，当基于通行流量数据发现某一条路段上的通行流量不算特别高也不算特别少，可将其识别为小路，那么在进行导航路线规划时，很可能不会避开该路段，而实际上，在该路段的邻近路段的通行流量比该路段的通行流量高出数倍(例如20倍)的情况下，很有可能该路段出现了异常，由于导航路线规划时未能避开该路段，导致规划的导航路线不能满足用户的需求，不仅浪费了路线导航设备的计算资源和耗能，还可能会增加额外的通行时间，给用户带来极大不便，导致用户体验不佳。
本申请实施例提供的路线检测方法，在判断目标导航路线是否途径异常路段时，不是基于每条路段的通行次数，而是基于目标导航路线的流量变化轨迹(通过通行次数序列来反应)识别出异常路段，尤其是在路段的通行次数未能体现异常的情况下，能够通过该流量变化轨迹检测出异常路段，从而可以对目标导航路线中的异常路线进行修正，从而提升路线规划的合理性与准确性，可以避免导航路线规划不合理所导致的路线导航设备的计算资源和耗能的浪费，同时提升路线导航的用户体验。
一般而言，导航是从起点的低等级道路，导航至高等级道路上，快到终点时又导航至低等级道路上，即从起点到终点的通行流量一般是低->高->低的变化趋势，比如，从A区公路进入高速道路，再从高速道路驶入B区公路，高速道路的通行流量相较于公路的通行流量较大。如果导航路线所对应的通行流量的变化趋势是从高通行流量道路导航至通行流量发生陡降的低流量道路上，后续又回到高通行流量道路上时，那可以认为这条规划的导航路线大概率存在异常。如图2所示，为一个导航路线的示意图，该导航路线从起点走到高速上，之后下高速走到终点，图3是该导航路线的局部路段的放大图，可以看出中途下高速又上高速。图4是放大图的通行流量变化轨迹分布图，圆点越密集的路段代表通行流量越大，可以看出，这个放大图，存在从高通行流量道路导航至低通行流量道路上，后续又回到高通行流量道路上的情况，而右侧存在另一条通行流量更高即更容易通行的路线。通过本申请实施例提供的路线检测方法，可以识别出这个局部异常路段，并进行路线修复。
在一些实施例中，如图5所示，提供了一种路线检测方法，以该方法应用于图1中的服务器104为例进行说明，包括以下步骤：
步骤502，获取待检测的目标导航路线，目标导航路线包括多个依次连接的路段。
目标导航路线是基于起点和终点进行路线规划得到的导航路线，目标导航路线包括多个依次连接的路段。在一些实施例中，终端可以基于用户输入的起点和终点，向提供地图导航服务的服务器发送导航路线生成请求，服务器基于接收到的导航路线生成请求，生成至少一条导航路线，该目标导航路线可以是该至少一条导航路线中的其中一条。服务器可通过对目标导航路线进行异常检测。在一些实施例中，对于检测出的存在异常路段的目标导航路线，服务器可对其进行修正，得到修正导航路线，并返回至终端。在一些实施例中，对于检测出的存在异常路段的目标导航路线，服务器还可以从该至少一条导航路线中滤除该存在异常路段的目标导航路线，将剩余的导航路线返回至终端。
步骤504，基于多个依次连接的路段，确定多对两两相邻路段。
导航路线规划完成后得到的目标导航路线，是起止点之间的较优路径，其包括多个依次连接的路段，即多个路段之间按照拓扑关系依次连接。基于此，服务器可以根据该目标导航路线所包括的多个路段，确定多对两两相邻路段。可选地，服务器可以依次遍历该目标导航路线所经过的路段，将当前遍历路段与下一遍历路段构造成一对两两相邻路段，直至当前遍历路段为倒数第二个路段时结束遍历。可选地，服务器可以从第二个遍历路段开始，将当前遍历路段与上一遍历路段构造成一对两两相邻路段，直至当前遍历路段为倒数第一个路段时结束遍历。
例如，目标导航路线是由link1、link2、link3、link4、link5依次拓扑连接形成的路线，则服务器可以确定目标导航路线所包括的多对两两相邻路段依次为：link1-link2,link2-link3,link3-link4,link4-link5。
步骤506，基于历史导航路线查询两两相邻路段在指定时间范围内的通行次数。
历史导航路线是过去生成并完成为车辆通行导航的路线，对于过去一段时间内的历史导航路线，服务器可以存储对应的通行次数，其中，过去一段时间具体可以是过去30分钟、过去1小时、过去1天、过去1周、过去1个月、过去3个月，等等，具体时间范围不作限制。服务器可以基于指定时间范围内的历史导航路线，查询两两相邻路段在指定时间范围内的通行次数。
如图6所示，在一些实施例中，，为了实现对两两相邻路段在指定时间范围内的通行次数进行周期性更新，保证通行次数数据的有效性与时效性，服务器可以周期性(如每隔30分钟、每隔1小时、每隔1天，每隔1个月等等)地执行以下步骤：
步骤602，获取在指定时间范围内的历史导航路线集合。
为了尽量保证通行流量数据的时效性，服务器可以针对不同地区有，设置执行周期以及设置指定时间范围。例如，对于城市等热点区域，服务器可以设置每隔30分钟获取过去1个小时以内的历史导航路线集合，或是，设置每隔1小时获取过去1个小时以内的历史导航路线集合。对于城市外环线等车流量不高的区域，服务器可以设置每隔2小时获取过去1个小时以内的历史导航路线集合。对于车流量较少的其它区域，如偏远地区，设置每隔1个星期获取过去1个月以内的历史导航路线集合。对于历史导航路线集合中的历史导航路线，服务器还要获取每条历史导航路线在指定时间范围内的导航次数，例如，在过去一段时间内，同一条历史导航路线被多个用户使用，完成导航的次数为200次，则对应的导航次数即为200。
步骤604，对历史导航路线集合中的每条历史导航路线进行拆解，得到历史导航路线所包括的两两相邻路段。
步骤606，根据拆解出的两两相邻路段，得到两两相邻路段集合。
为了确定两两相邻路段之间的通行次数，以准确反应路段上的通行流量变化趋势，服务器可以对历史导航路线集合中的每条历史导航路线进行拆解，得到历史导航路线所包括的两两相邻路段。
举例来说，服务器在指定时间范围内获取的历史导航路线集合包括5条历史导航路线，分别为：
历史导航路线1：link1、link2、link3、link4、link5，导航次数为500；
历史导航路线2：link3、link4、link5、link6、link7，导航次数为100；
历史导航路线3：link1、link2、link5、link6、link7，导航次数为50；
历史导航路线4：link1、link2、link4、link5，导航次数为50；
历史导航路线5：link2、link3、link4、link5，导航次数为300；
拆解出的两两相邻路段包括：
link1-link2；
link2-link3；
link3-link4；
link4-link5；
link5-link6；
link6-link7；
link2-link5；
link2-link4；
可以理解，上述数据仅为示意，实际实施过程中将会获得大量历史导航路线以及大量的两两相邻路段。
步骤608，对于两两相邻路段集合中的每一对两两相邻路段，累加包括两两相邻路段的历史导航路线在指定时间范围内的导航次数，得到两两相邻路段在指定时间范围内的通行次数。
在上面的例子中，可以确定每一对两两相邻路段在指定时间范围内的通行次数分别为：
link1-link2，通行次数为600；
link2-link3，通行次数为800；
link3-link4，通行次数为900；
link4-link5，通行次数为950；
link5-link6，通行次数为150；
link6-link7，通行次数为150；
link2-link5，通行次数为50；
link2-link4，通行次数50。
按照上述的步骤602-步骤608，服务器对两两相邻路段在指定时间范围内的通行次数进行周期性更新，保证通行次数数据的有效性与时效性，可以准确统计并存储地图路网数据中具有拓扑关系的两两相邻路段在指定时间范围内的通行次数，该通行次数反应了两两相邻路段之间的车辆通行流量。因此，在获得目标导航路线中的多对两两相邻路段之后，服务器可以根据上述数据统计结果，根据目标导航路线中的两两相邻路段查询对应的在指定时间范围内的通行次数，使得后续生成的通行次数序列更为准确，从而提升异常路线检测的准确性。
步骤508，根据各两两相邻路段在指定时间范围内的通行次数，得到目标导航路线对应的通行次数序列，根据通行次数序列判断目标导航路线是否途径异常路段。
本申请实施例中，通过将目标导航路线所包括的两两相邻路段在指定时间范围内的通行次数依次排列，可以得到目标导航路线对应的通行次数序列，该通行次数序列反应了目标导航路线的流量变化趋势，能够通过该流量变化趋势检测出目标导航路线中的异常路段，尤其是在路段的通行次数未能体现异常的情况下，能够通过该流量变化趋势检测出异常路段。
按照前面分析的，一般而言，导航是从起点的低等级道路，导航至高等级道路上，快到终点时又导航至低等级道路上，即从起点到终点的通行流量一般是低->高->低的变化趋势，如果导航路线所对应的通行流量的流量变化趋势是从高通行流量道路导航至通行流量发生陡降的低流量道路上，后续又回到高通行流量道路上时，那可以认为这条规划的导航路线大概率存在异常。因此，基于此，服务器可以基于目标导航路线对应的通行次数序列确定对应的流量变化趋势，并将该目标导航路线对应的流量变化趋势与正常路线或异常路线各自对应的流量变化趋势进行比较，来确定目标导航路线是否途径异常路段。
在一些实施例中，根据各两两相邻路段在指定时间范围内的通行次数，得到目标导航路线对应的通行次数序列，根据通行次数序列判断目标导航路线是否途径异常路段，包括：按照各两两相邻路段在目标导航路线上的先后顺序，将各两两相邻路段相应的在指定时间范围内的通行次数进行排列，得到目标导航路线对应的通行次数序列；在通行次数序列对应的数值变化趋势不匹配预设通行轨迹的情况下，判定目标导航路线途径异常路段。
本实施例中，预设通行轨迹反应了正常路线对应的流量变化趋势，例如，该预设通行轨迹是从低流量路段通行至高流量路段又返回至低流量路段的轨迹。
具体地，服务器可以在得到目标导航路线对应的通行次数序列之后，确定该通行次数序列对应的数值变化趋势，例如是否为数值低到数值高再到数值低。通过将通行次数序列对应的数值变化趋势与预设通行轨迹进行匹配，在该数值变化趋势不匹配预设通行轨迹的情况下，判定目标导航路线途径异常路段，在该数值变化趋势匹配预设通行轨迹的情况下，判断目标导航路线未途径异常路段，也就是目标导航路线通过了异常检测。
在一些实施例中，在通行次数序列对应的数值变化趋势不匹配预设通行轨迹的情况下，判定目标导航路线途径异常路段，包括：对于通行次数序列中的每个通行次数，在通行次数序列中获取位于当前通行次数两侧的邻近通行次数；在当前通行次数小于预设阈值、且当前通行次数两侧的邻近通行次数大于当前通行次数的N倍数值的情况下，确定通行次数序列对应的数值变化趋势不匹配预设通行轨迹，以及确定当前通行次数所对应的两两相邻路段为异常路段，其中，N为大于10的数。
其中，位于当前通行次数两侧的邻近通行次数，是通行次数序列中位于当前通行次数两侧的、相对邻近的通行次数，不一定是直接相邻的通行次数。也就是说，只要通行次数序列中存在数值变化趋势不匹配预设通行轨迹的子序列，该子序列中就存在异常路段。在当前通行次数小于预设阈值、且当前通行次数两侧的邻近通行次数大于当前通行次数的N倍数值的情况下，可以确定通行次数序列对应的数值变化趋势不匹配预设通行轨迹。N的取值可以根据实际数据分析确定，比如N可以取值为20。例如，当前通行次数为50次，而两侧的邻近通行次数为5000次，存在非常大的差异，这可以确定当前通行次数所对应的两两相邻路段存在异常或是两两相邻路段中的较后路段存在异常。
举例来说，目标导航路线为：link1-link2-link4-link5，在上面例子中，可以确定该目标导航路线对应的通行次数序列为：600-50-950，可见，该目标导航路线经历了对应的数值变化区域与正常情况下从起点到终点的通行流量一般是低->高->低的变化趋势，不匹配，可以判定该目标导航路线中存在异常路段，例如可能是出现临时封路等情况。
在一些实施例中，根据各两两相邻路段在指定时间范围内的通行次数，得到目标导航路线对应的通行次数序列，根据通行次数序列判断目标导航路线是否途径异常路段，包括：按照各两两相邻路段在目标导航路线上的先后顺序，将各两两相邻路段相应的在指定时间范围内的通行次数进行排列，得到目标导航路线对应的通行次数序列；在通行次数序列对应的数值变化趋势匹配预设通行轨迹的情况下，判定目标导航路线途径异常路段。
本实施例中，预设通行轨迹反应了异常路线对应的流量变化趋势，例如，该预设通行轨迹是从高流量路段通行至低流量路段又返回至高流量路段的轨迹。
具体地，服务器可以在得到目标导航路线对应的通行次数序列之后，确定该通行次数序列对应的数值变化趋势，例如是否为数值高到数值低再到数值高，将通行次数序列对应的数值变化趋势与预设通行轨迹进行匹配，在该数值变化趋势匹配预设通行轨迹的情况下，判定目标导航路线途径异常路段。
如图7所示，为一个实施例中导航路线的示意图。在图7中，密集填充区域是流量密集区域，白色路段是导航路线，该导航路线明显经过了零通行流量路段(即图7中箭头所指向的路段)，显然这条导航路线规划不合理。
在一些实施例中，服务器还可以在当前通行次数大于预设阈值、且当前通行次数两侧的邻近通行次数大于当前通行次数的M倍数值的情况下，可以确定目标导航路线经过了“小路”，即可通行但通行能力较差的路段。在对规划的目标导航路线检测出存在这种类型路段的情况下，服务器可以对终端进行提示，或是显示相关提示信息，以供用户进行选择。
如图8所示，为一个实施例中导航路线的示意图。在图8中，小圆圈越密集的地方代表通行流量越大，白色线段是导航路线，该导航路线经过了通行流量较低的路段(图8中箭头所指向的路段)后又回到了流量密集路段，服务器可以确定该路段为可通行的小路。
在一些实施例中，上述路线检测方法还包括：
在目标导航路线途径异常路段的情况下，为异常路段标注异常标记；
在异常路段的异常标记未失效的情况下，对于接收到的导航路线生成请求，避开异常路段对导航路线生成请求进行路线规划。
也就是说，对于检测出的异常路段，服务器可以为其标注异常标记，对于后续接收到的导航路线生成请求，在异常路段的异常标记未失效的情况下，服务器在进行路线规划时，可避开这些标注异常标记的路段进行规划。这样，异常检测结果可回流至地图路网数据，改善地图路网中数据不准确或是不够完善的问题，从而有助于后续的导航路线规划的合理性与完善性，提升路线导航的用户体验。可以理解，随着新的导航路线不断生成，新的通行流量也在发生变化，对于同一两两相邻路段，在指定时间范围内的通行次数也会随着周期性的检测不断发生变化，相应的异常标记可能会被标记失效。
在一个实施例中，上述路线检测方法还包括：
在目标导航路线途径异常路段的情况下，对目标导航路线进行修正处理，得到导航修正路线，导航修正路线不包括异常路段。
在一个实施例中，在目标导航路线途径异常路段的情况下，对目标导航路线进行修正处理，得到导航修正路线，包括：在目标导航路线途径异常路段的情况下，确定异常路段对应的两个端点，根据两个端点重新进行局部路径生成，使用生成的局部路径替换目标导航路线中的异常路径，得到导航修正路线。
在本实施中，对于目标导航路线，若检测出存在异常路径，则可针对该目标导航路线，基于该目标导航路线中剩余的正常路段在路网中的拓扑关系，重新进行路径规划，得到导航修正路线，该导航修正路线更为合理，能够提高导航通行效率。
上述路线检测方法，通过获取目标导航路线，确定目标导航路线所包括的多对两两相邻路段，基于历史导航路线查询两两相邻路段在指定时间范围内的通行次数，根据各两两相邻路段在指定时间范围内的通行次数，得到目标导航路线对应的通行次数序列，根据通行次数序列判断目标导航路线是否途径异常路段判断目标导航路线是否途径异常路段。也就是说，在判断目标导航路线是否途径异常路段时，不是基于每条路段的通行次数，而是基于目标导航路线的流量变化轨迹(通过通行次数序列来反应)识别出异常路段，尤其是在路段的通行次数未能体现异常的情况下，能够通过该流量变化轨迹检测出异常路段，从而提升路线规划的合理性与准确性，可以避免导航路线规划不合理所导致的路线导航设备的计算资源和耗能的浪费，同时提升路线导航的用户体验。
为了能够更及时地发现临时封路等道路上的突发异常情况，如1小时出现临时封路，在一些实施例中，服务器可以使用更细粒度流量来发现异常，例如1小时内的历史导航路线来检测异常，因为1天内在异常路段上的通行流量可能还是很大，无法检测出异常，使用1小时内的通行流量数据，就可以识别出异常，也就是说，通行流量数据的时效性越高越好，如半小时内的历史导航路线、十分钟内的历史导航路线，等等。当细粒度时间范围内的流量指示存在异常时，则说明在较短时间内发生了异常事件，当细粒度时间范围内的流量指示不存在异常时，可以使用更长时间范围内的数据进行异常检查。
在一些实施例中，基于历史导航路线查询两两相邻路段在指定时间范围内的通行次数，包括：基于第一指定时间范围内的历史导航路线查询两两相邻路段在指定时间范围内的通行次数；以及在根据各两两相邻路段在第一指定时间范围内的通行次数，判断目标导航路线未途径异常路段的情况下，继续基于第二指定时间范围内的历史导航路线查询两两相邻路段在指定时间范围内的通行次数；其中，第二指定时间范围的时间颗粒度大于第一指定时间范围的时间颗粒度。
本实施例中，使用不同指定时间范围内的历史导航路线数据，是为了覆盖不同的区域。第二指定时间范围的时间颗粒度大于第一指定时间范围内的时间颗粒度，例如第二指定时间范围是日度流量，即一天内的历史导航路线数据，第二指定时间范围是月度流量，即一个月以内的历史导航路线数据，当基于第一指定时间范围内的历史导航路线所指示的通行次数都很高的情况下，就不需要再使用第二指定时间范围内的历史导航路线进行检测，否则，当基于第一指定时间范围内的历史导航路线所指示的通行次数都很低的情况下，无法检测出异常的情况下，可以继续使用更长时间颗粒度即第二指定时间范围内的历史导航路线数据来检测问题，以此类推，这样，可以覆盖到地图路网数据中各个地区的导航路线的异常检测。尤其是在通行流量不算特别高也不算特别少，但与邻近两侧路段的通行流量存在巨大差异时，能够识别出异常，从而提升路线规划的合理性。
在一些实施例中，根据各两两相邻路段在指定时间范围内的通行次数，得到目标导航路线对应的通行次数序列，根据通行次数序列判断目标导航路线是否途径异常路段，包括：
根据各两两相邻路段在第一指定时间范围内的通行次数，得到导航路线对应的第一通行次数序列，根据第一通行次数序列判断目标导航路线是否途径异常路段；以及
在根据第一通行次数序列判断目标导航路线未途径异常路段的情况下，继续根据各两两相邻路段在第二指定时间范围内的通行次数，得到导航路线对应的第二通行次数序列，根据第二通行次数序列判断目标导航路线是否途径异常路段。
按照上述的方式，时间颗粒度不同，两两相邻路段对应的通行次数是不同的，在需要多次尝试使用不同时间范围内的数据检测异常的情况下，服务器就需要分别确定不同时间范围内目标导航路线对应的通行次数序列，以实现准确检测目标导航路线是否存在异常路段。
在一些实施例中，上述路线检测方法还包括：
在根据各两两相邻路段在第一指定时间范围内的通行次数，判断目标导航路线途径异常路段的情况下，绕过异常路段对目标导航路线进行修正，得到修正导航路线；以及在根据各两两相邻路段在第一指定时间范围内的通行次数，判断目标导航路线未途径异常路段、且根据各两两相邻路段在第二指定时间范围内的通行次数，判断目标导航路线途径异常路段的情况下，避开异常路段对目标导航路线进行修正，得到修正导航路线。
按照上述的方式，时间颗粒度不同，两两相邻路段对应的通行次数是不同的，在需要多次尝试使用不同时间范围内的数据检测异常的情况下，服务器就需要分别确定不同时间范围内目标导航路线对应的通行次数序列是否存在异常路段，以实现准确检测目标导航路线是否存在异常路段。
如图9所示，为一个实施例中的路线修正的整体框架示意图。参照图9，首先是离线整合流量，路段流量可按时间颗粒度，服务器统计日级路段流量、周级路段流量、月级路段流量、季度路段流量，还有小时级路段流量，得到每条路段对应在不同时间颗粒度对应的通行次数。接着是在线导航服务可加载上述的统计数据，当接收到路线导航请求时，生成目标导航路线，然后，进行异常检测，如图9所示，具体包括：
步骤902，加载日级路段流量，识别目标导航路线是否存在异常路段，若否，则执行步骤904，若是，则执行步骤908。
步骤904，继续加载周级路段流量，识别目标导航路线是否存在异常路段，若否，则执行步骤906，若是，则执行步骤908。
步骤906，继续加载月级路段流量，识别目标导航路线是否存在异常路段，若否，则识别结束，返回召回路线，若是，则执行步骤908。
步骤908，确定异常路段；
步骤910，避开异常路段进行路线局部修正；
步骤912，使用生成的局部路径替换目标导航路线中的异常路径，得到导航修正路线；
步骤914，对异常路段进行标记。
这样，可以使得后续路线规划时可避开该异常路段。
在一个具体的实施例中，路线修正方法包括如下步骤：
1、获取在指定时间范围内的历史导航路线集合；
2、对历史导航路线集合中的每条历史导航路线进行拆解，得到历史导航路线所包括的两两相邻路段；
3、根据拆解出的两两相邻路段，得到两两相邻路段集合；
4、对于两两相邻路段集合中的每一对两两相邻路段，累加包括两两相邻路段的历史导航路线在指定时间范围内的导航次数，得到两两相邻路段在指定时间范围内的通行次数。
5、获取待检测的目标导航路线；
6、确定目标导航路线所包括的多对两两相邻路段；
7、基于第一指定时间范围内的历史导航路线查询两两相邻路段在指定时间范围内的通行次数；
8、按照各两两相邻路段在目标导航路线上的先后顺序，将各两两相邻路段相应的在第一指定时间范围内的通行次数进行排列，得到目标导航路线对应的第一通行次数序列，在第一通行次数序列对应的数值变化趋势不匹配预设通行轨迹的情况下，判定目标导航路线途径异常路段，该预设通行轨迹是反应了正常路线对应的流量变化趋势；
9、在根据各两两相邻路段在第一指定时间范围内的通行次数，判断目标导航路线途径异常路段的情况下，避开异常路段对目标导航路线进行修正，得到修正导航路线；
10、在根据各两两相邻路段在第一指定时间范围内的通行次数，判断目标导航路线未途径异常路段的情况下，继续基于第二指定时间范围内的历史导航路线查询两两相邻路段在指定时间范围内的通行次数；
11、按照各两两相邻路段在目标导航路线上的先后顺序，将各两两相邻路段相应的在第二指定时间范围内的通行次数进行排列，得到目标导航路线对应的第二通行次数序列，在第二通行次数序列对应的数值变化趋势不匹配预设通行轨迹的情况下，判定目标导航路线途径异常路段；
12、根据各两两相邻路段在第二指定时间范围内的通行次数，判断目标导航路线未途径异常路段的情况下，确定目标导航路线中不存在异常路段；
13、根据各两两相邻路段在第二指定时间范围内的通行次数，判断目标导航路线途径异常路段的情况下，避开异常路段对目标导航路线进行修正，得到修正导航路线；
14、为异常路段标注异常标记，在异常路段的异常标记未失效的情况下，对于接收到的导航路线生成请求，避开异常路段对导航路线生成请求进行路线规划。
以一个具体的例子介绍本申请实施例。首先，加载地图路网的中存在拓扑连接关系的两个路段之间的通行流量，即通行次数，包括小时级、日级、周级、月级、季度级的流量，在路线规划完成得到目标导航路线后，计算整条目标导航路线上的通行次数，如路线规划后的link串为link1,link2,link3,link4,…,linkn,可以获得n-1个转移流量f1,f2,f3,f4,…,fn-1,其中f1表示link1、link2之间的通行次数，f2表示link2、link3之间的通行次数，依次类推，之后遍历通行次数，判断当前通行次数左右两侧是否存在比当前通行次数高很多倍(如20倍)且当前通行次数很小的情况，如通行次数序列为10，10，2000，2000，3000，4，3，5，100，1000，2000，20，10，10，中间有个流量陡降的过程，则导航路线穿过低流量地区，那么该导航路线存在异常。其中，使用小时级流量是为了能够更及时的发现动态封路、交规的问题，如1小时前封路，天级流量还是很多，识别不出来路线有问题，用小时级流量就能识别出来，流量时效性越高越好，如半小时流量，十分钟流量，小时级流量主要发现热点地区的问题，偏远地区小时级流量覆盖不到。使用日、周、月、季度流量也是为了覆盖不同区域，如果日级流量转移流量都很高，那就不需要再进行周、月、季度流量检测，当日级流量覆盖不全时，再尝试使用周级流量检测问题，周级也覆盖不到就用月级，最后用季度级流量，基本能覆盖全路网地区。此外，在检测出异常路段后，修复异常路段，如避开异常路段重新算路，或者，路线规划出多条导航路线的情况下，用未经过该异常路段的局部走法替换异常路段，等等。对于地图导航服务而言，每天可能存在千万级导航请求，使用该本申请实施例提供的路线检测方法，每天能识别百万级异常路段，针对识别出的异常路段，还可以对异常路段进行分类，如识别多种异常路段的类型，如交通限制、小路、大门、封路、冗余路等，这些路段标记上这些异常类别后，可以在后续路线规划时用上，以改善路线规划不合理的问题。
本申请实施例可应用车辆导航场景。例如，用户可以通过终端输入起止地点，服务器基于地图路网数据按照该起止地点进行路线规划，得到N条导航路线，服务器对于每条导航路线，按照本申请实施例提供的方法进行异常检查，若导航路线中存在异常路段，则服务器可以返回提示信息至终端，或是，服务器可以对其中的异常路段进行修正，返回导航修正路线至终端。
如图10所示，为一个实施例中路线修正前后的示意图，参照图10，将导航路线中异常路段识别出来后修复为更好的通行路线。通过本申请实施例提供的路线检测方法，可以在线实时发现路线规划中的问题，避免将不好的路线推给用户，提升产品体验。而且，自动发现数据问题，一定程度上减少数据作业人力的投入。
应该理解的是，虽然如上的各实施例所涉及的流程图中的各个步骤按照箭头的指示依次显示，但是这些步骤并不是必然按照箭头指示的顺序依次执行。除非本文中有明确的说明，这些步骤的执行并没有严格的顺序限制，这些步骤可以以其它的顺序执行。而且，如上的各实施例所涉及的流程图中的至少一部分步骤可以包括多个步骤或者多个阶段，这些步骤或者阶段并不必然是在同一时刻执行完成，而是可以在不同的时刻执行，这些步骤或者阶段的执行顺序也不必然是依次进行，而是可以与其它步骤或者其它步骤中的步骤或者阶段的至少一部分轮流或者交替地执行。
基于同样的发明构思，本申请实施例还提供了一种用于实现上述所涉及的路线检测方法的路线检测装置。该装置所提供的解决问题的实现方案与上述方法中所记载的实现方案相似，故下面所提供的一个或多个路线检测装置实施例中的具体限定可以参见上文中对于路线检测方法的限定，在此不再赘述。
在一个实施例中，如图11所示，提供了一种路线检测装置1100，包括：获取模块1102、相邻路段确定模块1104、通行次数查询模块1106和异常检测模块1108，其中：
获取模块1102，用于获取待检测的目标导航路线目标导航路线包括多个依次连接的路段；
相邻路段确定模块1104，用于基于多个依次连接的路段，确定多对两两相邻路段；
通行次数查询模块1106，用于基于历史导航路线查询两两相邻路段在指定时间范围内的通行次数；
异常检测模块1108，用于根据各两两相邻路段在指定时间范围内的通行次数，得到目标导航路线对应的通行次数序列，根据通行次数序列判断目标导航路线是否途径异常路段。
在一个实施例中，路线检测装置1100还包括：
统计模块，用于获取在指定时间范围内的历史导航路线集合，对历史导航路线集合中的每条历史导航路线进行拆解，得到历史导航路线所包括的两两相邻路段，根据拆解出的两两相邻路段，得到两两相邻路段集合，对于两两相邻路段集合中的每一对两两相邻路段，累加包括两两相邻路段的历史导航路线在指定时间范围内的导航次数，得到两两相邻路段在指定时间范围内的通行次数。
在一个实施例中，通行次数查询模块1106，用于基于第一指定时间范围内的历史导航路线查询两两相邻路段在指定时间范围内的通行次数；以及还用于在根据各两两相邻路段在第一指定时间范围内的通行次数，判断目标导航路线未途径异常路段的情况下，继续基于第二指定时间范围内的历史导航路线查询两两相邻路段在指定时间范围内的通行次数；其中，第二指定时间范围的时间颗粒度大于第一指定时间范围的时间颗粒度。
在一个实施例中，异常检测模块1108，用于根据各两两相邻路段在第一指定时间范围内的通行次数，得到导航路线对应的第一通行次数序列，根据第一通行次数序列判断目标导航路线是否途径异常路段；以及，还用于在根据第一通行次数序列判断目标导航路线未途径异常路段的情况下，继续根据各两两相邻路段在第二指定时间范围内的通行次数，得到导航路线对应的第二通行次数序列，根据第二通行次数序列判断目标导航路线是否途径异常路段。
在一个实施例中，路线检测装置1100还包括：
修正模块，用于在根据各两两相邻路段在第一指定时间范围内的通行次数，判断目标导航路线途径异常路段的情况下，避开异常路段对目标导航路线进行修正，得到修正导航路线；以及，还用于在根据各两两相邻路段在第一指定时间范围内的通行次数，判断目标导航路线未途径异常路段、且根据各两两相邻路段在第二指定时间范围内的通行次数，判断目标导航路线途径异常路段的情况下，避开异常路段对目标导航路线进行修正，得到修正导航路线。
在一个实施例中，异常检测模块1108，还用于按照各两两相邻路段在目标导航路线上的先后顺序，将各两两相邻路段相应的在指定时间范围内的通行次数进行排列，得到目标导航路线对应的通行次数序列；在通行次数序列对应的数值变化趋势不匹配预设通行轨迹的情况下，判定目标导航路线途径异常路段。
在一个实施例中，异常检测模块1108，还用于对于通行次数序列中的每个通行次数，在通行次数序列中获取位于当前通行次数两侧的邻近通行次数；在当前通行次数小于预设阈值、且当前通行次数两侧的邻近通行次数大于当前通行次数的N倍数值的情况下，确定通行次数序列对应的数值变化趋势不匹配预设通行轨迹，以及确定当前通行次数所对应的两两相邻路段为异常路段，其中，N为大于10的数。
在一个实施例中，路线检测装置1100还包括：
标注模块，用于在目标导航路线途径异常路段的情况下，为异常路段标注异常标记；
路线规划模块，用于在异常路段的异常标记未失效的情况下，对于接收到的导航路线生成请求，避开异常路段对导航路线生成请求进行路线规划。
在一个实施例中，路线检测装置1100还包括：
修正模块，用于在目标导航路线途径异常路段的情况下，对目标导航路线进行修正处理，得到导航修正路线，导航修正路线不包括异常路段。
在一个实施例中，该修正模块，还用于在目标导航路线途径异常路段的情况下，确定异常路段对应的两个端点，根据两个端点重新进行局部路径生成，使用生成的局部路径替换目标导航路线中的异常路径，得到导航修正路线。
上述路线检测装置1100，通过获取目标导航路线，确定目标导航路线所包括的多对两两相邻路段，基于历史导航路线查询两两相邻路段在指定时间范围内的通行次数，根据各两两相邻路段在指定时间范围内的通行次数，得到目标导航路线对应的通行次数序列，根据通行次数序列判断目标导航路线是否途径异常路段判断目标导航路线是否途径异常路段。也就是说，在判断目标导航路线是否途径异常路段时，不是基于每条路段的通行次数，而是基于目标导航路线的流量变化轨迹(通过通行次数序列来反应)识别出异常路段，尤其是在路段的通行次数未能体现异常的情况下，能够通过该流量变化轨迹检测出异常路段，从而提升路线规划的合理性与准确性，可以避免导航路线规划不合理所导致的路线导航设备的计算资源和耗能的浪费，同时提升路线导航的用户体验。
上述路线检测装置1100中的各个模块可全部或部分通过软件、硬件及其组合来实现。上述各模块可以硬件形式内嵌于或独立于计算机设备中的处理器中，也可以以软件形式存储于计算机设备中的存储器中，以便于处理器调用执行以上各个模块对应的操作。
在一个实施例中，提供了一种计算机设备，该计算机设备可以是服务器，其内部结构图可以如图12所示。该计算机设备包括处理器、存储器、输入/输出接口(Input/Output，简称I/O)和通信接口。其中，处理器、存储器和输入/输出接口通过系统总线连接，通信接口通过输入/输出接口连接到系统总线。其中，该计算机设备的处理器用于提供计算和控制能力。该计算机设备的存储器包括非易失性存储介质和内存储器。该非易失性存储介质存储有操作系统、计算机可读指令和数据库。该内存储器为非易失性存储介质中的操作系统和计算机可读指令的运行提供环境。该计算机设备的数据库用于存储地图路网数据、异常路段数据等等。该计算机设备的输入/输出接口用于处理器与外部设备之间交换信息。该计算机设备的通信接口用于与外部的终端通过网络连接通信。该计算机可读指令被处理器执行时以实现一种路线检测方法。
本领域技术人员可以理解，图12中示出的结构，仅仅是与本申请方案相关的部分结构的框图，并不构成对本申请方案所应用于其上的计算机设备的限定，具体的计算机设备可以包括比图中所示更多或更少的部件，或者组合某些部件，或者具有不同的部件布置。
在一个实施例中，提供了一种计算机设备，包括存储器和处理器，存储器中存储有计算机可读指令，该处理器执行计算机可读指令时实现本申请实施例提供的路线检测方法的步骤。
在一个实施例中，提供了一种计算机可读存储介质，其上存储有计算机可读指令，计算机可读指令被处理器执行时实现本申请实施例提供的路线检测方法的步骤。
在一个实施例中，提供了一种计算机程序产品，包括计算机可读指令，该计算机可读指令被处理器执行时实现本申请实施例提供的路线检测方法的步骤。
需要说明的是，本申请所涉及的用户信息(包括但不限于用户设备信息、用户个人信息等)和数据(包括但不限于用于分析的数据、存储的数据、展示的数据等)，均为经用户授权或者经过各方充分授权的信息和数据，且相关数据的收集、使用和处理需要遵守相关国家和地区的相关法律法规和标准。
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程，是可以通过计算机可读指令来指令相关的硬件来完成，该计算机可读指令可存储于一非易失性计算机可读取存储介质中，该计算机可读指令在执行时，可包括如上述各方法的实施例的流程。其中，本申请所提供的各实施例中所使用的对存储器、数据库或其它介质的任何引用，均可包括非易失性和易失性存储器中的至少一种。非易失性存储器可包括只读存储器(Read-Only Memory，ROM)、磁带、软盘、闪存、光存储器、高密度嵌入式非易失性存储器、阻变存储器(ReRAM)、磁变存储器(Magnetoresistive Random Access Memory，MRAM)、铁电存储器(Ferroelectric Random Access Memory，FRAM)、相变存储器(Phase Change Memory，PCM)、石墨烯存储器等。易失性存储器可包括随机存取存储器(Random Access Memory，RAM)或外部高速缓冲存储器等。作为说明而非局限，RAM可以是多种形式，比如静态随机存取存储器(Static Random Access Memory，SRAM)或动态随机存取存储器(Dynamic Random Access Memory，DRAM)等。本申请所提供的各实施例中所涉及的数据库可包括关系型数据库和非关系型数据库中至少一种。非关系型数据库可包括基于区块链的分布式数据库等，不限于此。本申请所提供的各实施例中所涉及的处理器可为通用处理器、中央处理器、图形处理器、数字信号处理器、可编程逻辑器、基于量子计算的数据处理逻辑器等，不限于此。
以上实施例的各技术特征可以进行任意的组合，为使描述简洁，未对上述实施例中的各个技术特征所有可能的组合都进行描述，然而，只要这些技术特征的组合不存在矛盾，都应当认为是本说明书记载的范围。
以上所述实施例仅表达了本申请的几种实施方式，其描述较为具体和详细，但并不能因此而理解为对本申请专利范围的限制。应当指出的是，对于本领域的普通技术人员来说，在不脱离本申请构思的前提下，还可以做出若干变形和改进，这些都属于本申请的保护范围。因此，本申请的保护范围应以所附权利要求为准。

Claims (20)

  1. 一种路线检测方法，由计算机设备执行，所述方法包括：
    获取待检测的目标导航路线，所述目标导航路线包括多个依次连接的路段；
    基于所述多个依次连接的路段，确定多对两两相邻路段；
    基于历史导航路线查询所述两两相邻路段在指定时间范围内的通行次数；
    根据各所述两两相邻路段在指定时间范围内的通行次数，得到所述目标导航路线对应的通行次数序列，根据所述通行次数序列判断所述目标导航路线是否途径异常路段。
  2. 根据权利要求1所述的方法，其特征在于，所述方法还包括：
    获取在指定时间范围内的历史导航路线集合；
    对所述历史导航路线集合中的每条历史导航路线进行拆解，得到所述历史导航路线所包括的两两相邻路段；
    根据拆解出的两两相邻路段，得到两两相邻路段集合；
    对于所述两两相邻路段集合中的每一对两两相邻路段，累加包括所述两两相邻路段的历史导航路线在所述指定时间范围内的导航次数，得到所述两两相邻路段在指定时间范围内的通行次数。
  3. 根据权利要求1所述的方法，其特征在于，所述基于历史导航路线查询所述两两相邻路段在指定时间范围内的通行次数，包括：
    基于第一指定时间范围内的历史导航路线查询所述两两相邻路段在指定时间范围内的通行次数；以及
    在根据各所述两两相邻路段在所述第一指定时间范围内的通行次数，判断所述目标导航路线未途径异常路段的情况下，继续基于第二指定时间范围内的历史导航路线查询所述两两相邻路段在指定时间范围内的通行次数；其中，所述第二指定时间范围的时间颗粒度大于所述第一指定时间范围的时间颗粒度。
  4. 根据权利要求3所述的方法，其特征在于，所述根据各所述两两相邻路段在指定时间范围内的通行次数，得到所述目标导航路线对应的通行次数序列，根据所述通行次数序列判断所述目标导航路线是否途径异常路段，包括：
    根据各所述两两相邻路段在所述第一指定时间范围内的通行次数，得到所述导航路线对应的第一通行次数序列，根据所述第一通行次数序列判断所述目标导航路线是否途径异常路段；以及
    在根据所述第一通行次数序列判断所述目标导航路线未途径异常路段的情况下，继续根据各所述两两相邻路段在第二指定时间范围内的通行次数，得到所述导航路线对应的第二通行次数序列，根据所述第二通行次数序列判断所述目标导航路线是否途径异常路段。
  5. 根据权利要求3所述的方法，其特征在于，所述方法还包括：
    在根据各所述两两相邻路段在所述第一指定时间范围内的通行次数，判断所述目标导航路线途径异常路段的情况下，避开所述异常路段对所述目标导航路线进行修正，得到修正导航路线；以及
    在根据各所述两两相邻路段在所述第一指定时间范围内的通行次数，判断所述目标导航路线未途径异常路段、且根据各所述两两相邻路段在第二指定时间范围内的通行次数，判断所述目标导航路线途径异常路段的情况下，避开所述异常路段对所述目标导航路线进行修正，得到修正导航路线。
  6. 根据权利要求1所述的方法，其特征在于，所述根据各所述两两相邻路段在指定时间范围内的通行次数，得到所述目标导航路线对应的通行次数序列，根据所述通行次数序列判断所述目标导航路线是否途径异常路段，包括：
    按照各所述两两相邻路段在所述目标导航路线上的先后顺序，将各所述两两相邻路段相应的在指定时间范围内的通行次数进行排列，得到所述目标导航路线对应的通行次数序列；
    在所述通行次数序列对应的数值变化趋势不匹配预设通行轨迹的情况下，判定所述目标导航路线途径异常路段。
  7. 根据权利要求6所述的方法，其特征在于，所述在所述通行次数序列对应的数值变化趋势不匹配预设通行轨迹的情况下，判定所述目标导航路线途径异常路段，包括：
    对于所述通行次数序列中的每个通行次数，在所述通行次数序列中获取位于当前通行次数两侧的邻近通行次数；
    在所述当前通行次数小于预设阈值、且所述当前通行次数两侧的邻近通行次数大于所述当前通行次数的N倍数值的情况下，确定所述通行次数序列对应的数值变化趋势不匹配预设通行轨迹，以及确定所述当前通行次数所对应的两两相邻路段为异常路段，其中，N为大于10的数。
  8. 根据权利要求1至7任一项所述的方法，其特征在于，所述方法还包括：
    在所述目标导航路线途径异常路段的情况下，为所述异常路段标注异常标记；
    在所述异常路段的异常标记未失效的情况下，对于接收到的导航路线生成请求，避开所述异常路段对所述导航路线生成请求进行路线规划。
  9. 根据权利要求1至7任一项所述的方法，其特征在于，所述方法还包括：
    在所述目标导航路线途径异常路段的情况下，对所述目标导航路线进行修正处理，得到导航修正路线，所述导航修正路线不包括所述异常路段。
  10. 根据权利要求9所述的方法，其特征在于，所述在所述目标导航路线途径异常路段的情况下，对所述目标导航路线进行修正处理，得到导航修正路线，包括：
    在所述目标导航路线途径异常路段的情况下，确定所述异常路段对应的两个端点，根据所述两个端点重新进行局部路径生成，使用生成的局部路径替换所述目标导航路线中的所述异常路径，得到导航修正路线。
  11. 一种路线检测装置，所述装置包括：
    获取模块，用于获取待检测的目标导航路线，所述目标导航路线包括多个依次连接的路段；
    相邻路段确定模块，用于基于所述多个依次连接的路段，确定多对两两相邻路段；
    通行次数查询模块，用于基于历史导航路线查询所述两两相邻路段在指定时间范围内的通行次数；
    异常检测模块，用于根据各所述两两相邻路段在指定时间范围内的通行次数，得到所述目标导航路线对应的通行次数序列，根据所述通行次数序列判断所述目标导航路线是否途径异常路段。
  12. 根据权利要求11所述的装置，其特征在于，所述装置还包括：
    统计模块，用于获取在指定时间范围内的历史导航路线集合；对所述历史导航路线集合中的每条历史导航路线进行拆解，得到所述历史导航路线所包括的两两相邻路段；根据拆解出的两两相邻路段，得到两两相邻路段集合；对于所述两两相邻路段集合中的每一对两两相邻路段，累加包括所述两两相邻路段的历史导航路线在所述指定时间范围内的导航次数，得到所述两两相邻路段在指定时间范围内的通行次数。
  13. 根据权利要求11所述的装置，其特征在于，所述通行次数查询模块，还用于基于第一指定时间范围内的历史导航路线查询所述两两相邻路段在指定时间范围内的通行次数；以及在根据各所述两两相邻路段在所述第一指定时间范围内的通行次数，判断所述目标导航路线未途径异常路段的情况下，继续基于第二指定时间范围内的历史导航路线查询所述两两相邻路段在指定时间范围内的通行次数；其中，所述第二指定时间范围的时间颗粒度大于所述第一指定时间范围的时间颗粒度。
  14. 根据权利要求13所述的装置，其特征在于，所述异常检测模块，还用于根据各所述两两相邻路段在所述第一指定时间范围内的通行次数，得到所述导航路线对应的第一通行次数序列，根据所述第一通行次数序列判断所述目标导航路线是否途径异常路段；以及在根据所述第一通行次数序列判断所述目标导航路线未途径异常路段的情况下，继续根据各所述两两相邻路段在第二指定时间范围内的通行次数，得到所述导航路线对应的第二通行次数序列，根据所述第二通行次数序列判断所述目标导航路线是否途径异常路段。
  15. 根据权利要求13所述的装置，其特征在于，所述路线检测装置还包括：
    修正模块，用于在根据各所述两两相邻路段在所述第一指定时间范围内的通行次数，判断所述目标导航路线途径异常路段的情况下，避开所述异常路段对所述目标导航路线进行修正，得到修正导航路线；以及在根据各所述两两相邻路段在所述第一指定时间范围内的通行次数，判断所述目标导航路线未途径异常路段、且根据各所述两两相邻路段在第二指定时间范围内的通行次数，判断所述目标导航路线途径异常路段的情况下，避开所述异常路段对所述目标导航路线进行修正，得到修正导航路线。
  16. 根据权利要求11所述的装置，其特征在于，所述异常检测模块，还用于按照各所述两两相邻路段在所述目标导航路线上的先后顺序，将各所述两两相邻路段相应的在指定时间范围内的通行次数进行排列，得到所述目标导航路线对应的通行次数序列；在所述通行次数序列对应的数值变化趋势不匹配预设通行轨迹的情况下，判定所述目标导航路线途径异常路段。
  17. 根据权利要求16所述的装置，其特征在于，所述异常检测模块，还用于对于所述通行次数序列中的每个通行次数，在所述通行次数序列中获取位于当前通行次数两侧的邻近通行次数；在所述当前通行次数小于预设阈值、且所述当前通行次数两侧的邻近通行次数大于所述当前通行次数的N倍数值的情况下，确定所述通行次数序列对应的数值变化趋势不匹配预设通行轨迹，以及确定所述当前通行次数所对应的两两相邻路段为异常路段，其中，N为大于10的数。
  18. 一种计算机设备，包括存储器和处理器，所述存储器存储有计算机可读指令，其特征在于，所述处理器执行所述计算机可读指令时实现权利要求1至10中任一项所述的方法的步骤。
  19. 一种计算机可读存储介质，其上存储有计算机可读指令，其特征在于，所述计算机可读指令被处理器执行时实现权利要求1至10中任一项所述的方法的步骤。
  20. 一种计算机程序产品，包括计算机可读指令，其特征在于，该计算机可读指令被处理器执行时实现权利要求1至10中任一项所述的方法的步骤。
PCT/CN2025/080155 2024-03-14 2025-03-03 路线检测方法、装置、设备、存储介质和计算机程序产品 Pending WO2025190096A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
EP25769268.1A EP4779267A1 (en) 2024-03-14 2025-03-03 Route detection method and apparatus, device, storage medium and computer program product

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202410309879.1 2024-03-14
CN202410309879.1A CN118111463A (zh) 2024-03-14 2024-03-14 路线检测方法、装置、设备、存储介质和计算机程序产品

Publications (1)

Publication Number Publication Date
WO2025190096A1 true WO2025190096A1 (zh) 2025-09-18

Family

ID=91215264

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2025/080155 Pending WO2025190096A1 (zh) 2024-03-14 2025-03-03 路线检测方法、装置、设备、存储介质和计算机程序产品

Country Status (3)

Country Link
EP (1) EP4779267A1 (zh)
CN (1) CN118111463A (zh)
WO (1) WO2025190096A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118111463A (zh) * 2024-03-14 2024-05-31 腾讯科技（深圳）有限公司 路线检测方法、装置、设备、存储介质和计算机程序产品
CN118394106B (zh) * 2024-06-24 2024-09-20 天津渤海职业技术学院 一种无人机返航路径确定方法和系统

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2015068770A (ja) * 2013-09-30 2015-04-13 アイシン・エィ・ダブリュ株式会社 ナビゲーションシステム、ナビゲーション方法、及びナビゲーションプログラム
CN111707285A (zh) * 2020-06-28 2020-09-25 北京百度网讯科技有限公司 规划路线的方法和装置
CN114705207A (zh) * 2022-03-30 2022-07-05 阿里巴巴（中国）有限公司 导航路线修正方法、装置、设备及计算机程序产品
CN114707060A (zh) * 2022-03-15 2022-07-05 高德软件有限公司 导航路线推荐方法、基于位置的服务提供方法及程序产品
CN116311897A (zh) * 2022-12-30 2023-06-23 阿波罗智联(北京)科技有限公司 一种交通诱导方法、装置、电子设备及介质
CN117351763A (zh) * 2023-09-12 2024-01-05 智慧互通科技股份有限公司 一种基于流量监测的路线规划方法
CN118111463A (zh) * 2024-03-14 2024-05-31 腾讯科技（深圳）有限公司 路线检测方法、装置、设备、存储介质和计算机程序产品

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2015068770A (ja) * 2013-09-30 2015-04-13 アイシン・エィ・ダブリュ株式会社 ナビゲーションシステム、ナビゲーション方法、及びナビゲーションプログラム
CN111707285A (zh) * 2020-06-28 2020-09-25 北京百度网讯科技有限公司 规划路线的方法和装置
CN114707060A (zh) * 2022-03-15 2022-07-05 高德软件有限公司 导航路线推荐方法、基于位置的服务提供方法及程序产品
CN114705207A (zh) * 2022-03-30 2022-07-05 阿里巴巴（中国）有限公司 导航路线修正方法、装置、设备及计算机程序产品
CN116311897A (zh) * 2022-12-30 2023-06-23 阿波罗智联(北京)科技有限公司 一种交通诱导方法、装置、电子设备及介质
CN117351763A (zh) * 2023-09-12 2024-01-05 智慧互通科技股份有限公司 一种基于流量监测的路线规划方法
CN118111463A (zh) * 2024-03-14 2024-05-31 腾讯科技（深圳）有限公司 路线检测方法、装置、设备、存储介质和计算机程序产品

Also Published As

Publication number Publication date
CN118111463A (zh) 2024-05-31
EP4779267A1 (en) 2026-07-22

Similar Documents

Publication Publication Date Title
Wang et al. Origin-destination matrix prediction via graph convolution: a new perspective of passenger demand modeling
Dai et al. Personalized route recommendation using big trajectory data
CN103077604B (zh) 交通传感器管理方法和系统
CN101930667B (zh) 统计交通信息生成装置以及方法
CN111860929B (zh) 一种拼车订单拼成率预估方法及系统
Liu et al. Popular route planning with travel cost estimation from trajectories
CN118111463A (zh) 路线检测方法、装置、设备、存储介质和计算机程序产品
CN119180372B (zh) 轨道交通客流od预测方法及其系统
CN117272849B (zh) 区域停车场饱和度的预测方法、系统及可读存储介质
CN111383450A (zh) 一种交通路网的描述方法及装置
Kosugi et al. Traffic congestion prediction using toll and route search log data
US20140089042A1 (en) Method, Apparatus and System for monitoring competition price and for providing corrective messages
Sahri et al. Customized eager-lazy data cleansing for satisfactory big data veracity
CN115523931A (zh) 地图导航缓存数据库的历史导航线路更新方法
Zhou et al. Short-term bus passenger flow prediction based on BiLSTM neural network
CN118571001A (zh) 高速公路的流量特征提取方法、系统、介质及电子设备
CN111243280B (zh) 一种实时计算交通状态的指标的方法及装置
CN116821259A (zh) 一种保洁员轨迹查重计算方法及设备
CN116822720A (zh) 车辆出发的实现方法、设备、服务器及存储介质
Zhang et al. Route guidance model with limited overlap on freeway network under traffic incidents
CN113077079A (zh) 一种基于数据驱动的轨道交通新线接入客流预测方法
Cen et al. Exploring Spatiotemporally Varying and Nonlinear Relationships between Ride-Hailing and Metro Ridership: A Case Study in Chicago
Wei et al. A Two‐Stage Multiobjective Optimization Approach for Expressway Guide Sign Information Selection
Yarahmadi et al. A context-aware approach to construct driving cycles in a volatile urban environment
Sarlas Processing low-frequency floating cardata for transportation applications

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 25769268

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2025769268

Country of ref document: EP