Bus station position determination method and device, electronic equipment and storage medium

Abstract

Embodiments of the present disclosure disclose a bus station position determination method and device, electronic equipment and storage medium. The method comprises: obtaining a plurality of user riding trajectory data, the user riding trajectory data comprising data of a trajectory point of a user in a bus navigation scenario when the user selects a bus navigation route to ride a bus; for each user riding trajectory data, matching the trajectory point in the user riding trajectory data with a bus station on a bus route in the corresponding bus navigation route to obtain a bus station of the bus route matched with the trajectory point in the user riding trajectory data; the bus navigation route comprising one or more bus routes; and determining a station position corresponding to a bus station on the same bus route according to data of the trajectory points in the plurality of user riding trajectory data matched with the bus station on the same bus route. The technical solution can accurately mine a bus station position with low cost and high efficiency.

Description

Technical Field

[0001] This disclosure relates to the field of public transportation technology, specifically to a method, apparatus, electronic device, and storage medium for determining the location of bus stops. Background Technology

[0002] In recent years, with the rapid development of the internet, people have become increasingly accustomed to using electronic maps to find bus routes and stop locations when traveling. Navigating to the correct bus stops is crucial for convenient public transportation, making the accuracy of bus stop locations a critical issue. Currently, to ensure accuracy, bus stop locations are mostly determined online based on in-person data collection, which is costly and inefficient. Therefore, determining accurate bus stop locations efficiently and cost-effectively is a pressing technical challenge. Summary of the Invention

[0003] To address the problems in the related technologies, this disclosure provides a method, apparatus, electronic device, and storage medium for determining the location of bus stops.

[0004] Firstly, this disclosure provides a method for determining the location of a bus stop.

[0005] Specifically, the method for determining the location of the bus stop includes:

[0006] Acquire multiple user ride trajectory data, which includes data on trajectory points when a user takes a bus according to the bus navigation route selected by the user in a public transportation navigation scenario, and the trajectory point data includes the location of the trajectory point;

[0007] For each user's travel trajectory data, based on the trajectory points in the user's travel trajectory data and the initial location of the bus stops on the bus route selected by the user in the public transport navigation route, the trajectory points in the user's travel trajectory data are matched with the bus stops on the bus route to obtain the bus stops of the bus route that match the trajectory points in the user's travel trajectory data; wherein, the public transport navigation route includes one or more bus routes.

[0008] Based on the data of trajectory points that match bus stops on the same bus route from the multiple user travel trajectory data, the location of the bus stop on the same bus route is determined.

[0009] Secondly, this disclosure provides a bus stop location determination device, comprising:

[0010] The data acquisition module is configured to acquire multiple user ride trajectory data, which includes data on trajectory points when a user takes a bus according to the bus navigation route selected by the user in a public transportation navigation scenario, and the trajectory point data includes the location of the trajectory point.

[0011] The matching module is configured to, for each user's travel trajectory data, match the trajectory points in the user's travel trajectory data with the bus stops on the bus routes selected by the user in the public transport navigation route, based on the trajectory point data in the user's travel trajectory data and the initial location of the bus stops on the bus routes selected by the user in the public transport navigation route, to obtain the bus stops of the bus routes that match the trajectory points in the user's travel trajectory data; wherein, the public transport navigation route includes one or more bus routes.

[0012] The location determination module is configured to determine the location of the bus stop on the same bus route based on the data of trajectory points that match the bus stops on the same bus route in the multiple user travel trajectory data.

[0013] This disclosure provides an electronic device including a memory and a processor, wherein the memory is used to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement the method as described in any one of the first aspects.

[0014] Thirdly, this disclosure provides a computer-readable storage medium having computer instructions stored thereon, which, when executed by a processor, implement the method as described in any one of the first aspects.

[0015] Fourthly, this disclosure provides a computer program product including computer instructions that, when executed by a processor, implement the method steps as described in any one of the first aspects.

[0016] According to the technical solution provided in this disclosure, multiple user travel trajectory data can be obtained. The user travel trajectory data includes data on trajectory points when a user takes a bus along a selected bus route in a public transport navigation scenario. The trajectory point data includes the location of the trajectory point. For each user travel trajectory data, based on the trajectory point data and the initial location of the bus stop on the selected bus route, the trajectory points in the user travel trajectory data are matched with the bus stops on the bus route. This yields the bus stops of the bus routes that match the trajectory points in the user travel trajectory data. Following the principle that trajectory points cluster at bus stops when a user takes a bus, the data on trajectory points matching bus stops on the same bus route from multiple user travel trajectory data can be analyzed. This automatic mining of bus stop locations based on user travel trajectory data with strong associations to bus stops is cost-effective and efficient. Since the trajectory points in the user travel trajectory data accurately reflect the characteristics of users getting on and off buses at bus stops and vehicles stopping at bus stops, the locations of bus stops can be accurately mined.

[0017] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0018] Other features, objects, and advantages of this disclosure will become more apparent from the following detailed description of non-limiting embodiments, taken in conjunction with the accompanying drawings. In the drawings:

[0019] Figure 1 A flowchart illustrating a method for determining bus stop locations according to an embodiment of the present disclosure is shown;

[0020] Figure 2A This diagram illustrates the clustering of target trajectory points according to an embodiment of the present disclosure.

[0021] Figure 2B A schematic diagram showing a user's travel trajectory data according to an embodiment of the present disclosure;

[0022] Figure 2C A schematic diagram illustrating another user travel trajectory data according to an embodiment of the present disclosure;

[0023] Figure 3 A structural block diagram of a bus stop location determination device according to an embodiment of the present disclosure is shown;

[0024] Figure 4 A structural block diagram of an electronic device according to an embodiment of the present disclosure is shown;

[0025] Figure 5A schematic diagram of the structure of a computer system suitable for implementing the method according to embodiments of the present disclosure is shown. Detailed Implementation

[0026] In the following, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings to enable those skilled in the art to readily implement them. Furthermore, for clarity, portions unrelated to the description of exemplary embodiments have been omitted from the drawings.

[0027] In this disclosure, it should be understood that terms such as “comprising” or “having” are intended to indicate the presence of features, figures, steps, behaviors, components, parts or combinations thereof disclosed in this specification, and do not preclude the possibility of the presence or addition of one or more other features, figures, steps, behaviors, components, parts or combinations thereof.

[0028] It should also be noted that, unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other. This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0029] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation portals are provided for users to choose to authorize or refuse.

[0030] As mentioned above, in recent years, with the rapid development of the internet, people have gradually become accustomed to using electronic maps to check bus routes and boarding / alighting points when traveling. Navigating users to the correct bus stops is crucial for convenient public transportation, making the accuracy of bus stop locations a critical issue. Currently, to ensure accuracy, bus stop locations are mostly determined online based on in-person data collection, which is costly and inefficient. Therefore, determining accurate bus stop locations efficiently and cost-effectively is a pressing technical problem that needs to be solved.

[0031] This disclosure provides a method for determining the location of bus stops. This method can mine the location of bus stops based on user travel trajectory data that has a strong binding relationship with bus stops. Since the trajectory points in the user travel trajectory data can truly reflect the characteristics of users getting on and off buses at bus stops and vehicles stopping at bus stops, the accurate location of bus stops can be mined at low cost and high efficiency.

[0032] Figure 1A flowchart illustrating a method for determining bus stop locations according to an embodiment of this disclosure is shown. Figure 1 As shown, the method for determining the location of a bus stop includes the following steps S101-S103:

[0033] In step S101, multiple user ride trajectory data are acquired. The user ride trajectory data includes data of trajectory points when the user takes a bus according to the bus navigation route selected by the user in the public transportation navigation scenario. The data of trajectory points includes the location of the trajectory points.

[0034] In step S102, for each user's travel trajectory data, based on the data of the trajectory points in the user's travel trajectory data and the initial positions of the bus stops on the corresponding bus routes in the bus navigation line, the trajectory points in the user's travel trajectory data are matched with the bus stops on the bus routes to obtain the bus stops of the bus routes that match the trajectory points in the user's travel trajectory data; wherein, the bus navigation line includes one or more bus routes.

[0035] In step S103, the location of the bus stop on the same bus route is determined based on the data of trajectory points that match the bus stops on the same bus route in the multiple user travel trajectory data.

[0036] In one possible implementation, the bus stop location determination method is applicable to devices such as computers, computing devices, servers, and server clusters capable of determining bus stop locations.

[0037] In one possible implementation, in real life, there are nearly four million bus stops nationwide, and these bus stops may change due to urban construction such as road construction or bus route adjustments. If it is necessary to collect data on-site regularly, the cost will be very high. Therefore, a method for determining the location of bus stops is provided, which can automatically mine the location of bus stops from the user's travel trajectory data, so that the currently recorded location of the stops can be calibrated.

[0038] In one possible implementation, when a user travels, they can use public transportation navigation to select the public transportation route they need. Guided by the selected public transportation navigation route, the user's trajectory data from the starting point to the boarding stop, waiting for the bus, boarding the bus, getting off at the alighting stop, and from the alighting stop to the destination can be recorded as a user's travel trajectory data. Each user's travel trajectory data corresponds to a public transportation navigation route.

[0039] In one possible implementation, the user's travel trajectory data refers to the data of trajectory points when the user travels along the selected bus navigation route. This trajectory point data includes the location of the trajectory points, which can be acquired by a positioning sensor in response to positioning events. For example, the positioning sensor can periodically acquire the location of the trajectory points. In other implementations, the trajectory point data may also include the time of the trajectory points, or it may include the speed of the trajectory points. Since users will get on and off at bus stops along this bus route, and buses will stop at these stops to wait for users to board and alight, the trajectory points in the user's travel trajectory data will cluster at bus stops, and the speed of the trajectory points at bus stops will be lower. This demonstrates a strong correlation between the user's travel trajectory data and bus stops, accurately reflecting the trajectory point characteristics of users getting on and off at bus stops and vehicles stopping at bus stops.

[0040] In one possible implementation, each bus navigation route includes one or more bus routes. A bus route refers to an entire bus route corresponding to a single bus line traveling in one direction. Each bus line corresponds to two fixed round-trip bus routes. The bus routes within the navigation route refer to the parts of the route that involve the bus's travel. When the navigation route is a direct route without transfers, it includes part or all of a single bus route. When the navigation route requires one transfer, it includes part or all of each of two bus routes, and so on. The server records the names and initial locations of the bus stops where the bus on that route will stop. The location of the bus stop may have changed or is inaccurate, no longer at its initial location. This implementation mainly involves mining the location of the bus stops and calibrating any changed locations to obtain accurate locations.

[0041] In one possible implementation, for each user's travel trajectory data, the trajectory points in the user's travel trajectory data can be matched with the bus stops on the corresponding bus routes in the public transportation navigation system. For example, based on the location of the trajectory points in the user's travel trajectory data and the initial location of the bus stops on the corresponding bus routes in the public transportation navigation system, the trajectory points in the user's travel trajectory data can be matched with the nearest bus stops. In this way, the bus stops of the bus routes that match the trajectory points in the user's travel trajectory data can be obtained.

[0042] In one possible implementation, different user travel trajectory data may correspond to different bus routes or the same bus route. For example, user travel trajectory data 1 corresponds to a bus navigation route from station A1 to station A2 on bus route 1; user travel trajectory data 2 corresponds to a bus navigation route from station A1 through station A2 to station A3 on bus route 1; user travel trajectory data 3 corresponds to a bus navigation route from station B1 to station B2 on bus route 2; and user travel trajectory data 4 corresponds to a bus navigation route from station B2 to station B1 on bus route 2. In this case, user travel trajectory data 1 and user travel trajectory data 2 correspond to the same bus route and are matched with bus stops of bus route 1 corresponding to bus route 1; user travel trajectory data 3 and user travel trajectory data 4 correspond to two round-trip bus routes. User travel trajectory data 3 is matched with bus stops of bus route 2A corresponding to bus route 2, and user travel trajectory data 4 is matched with bus stops of bus route 2B in the other direction of bus route 2. However, some user travel trajectory data corresponds to two different bus routes in the bus navigation. For example, user travel trajectory data 5 corresponds to a bus navigation route where the user first takes bus route 1 from station A1 to station A2, and then transfers to bus route 2 from station A2 to station B1. In this case, the trajectory point data from station A1 to station A2 in user travel trajectory data 5 corresponds to the same bus route as user travel trajectory data 1 and user travel trajectory data 2, and matches the bus stop on bus route 1 of bus route 1.

[0043] In one possible implementation, since the locations of the same bus stop with the same name may differ on different bus routes, the location of the bus stop is determined for each bus route. Therefore, trajectory analysis requires analyzing the trajectory points corresponding to different bus routes. Thus, trajectory point data matching the bus stops for the same bus route can be obtained from multiple user travel trajectory data sets, thereby obtaining different trajectory points corresponding to different bus routes. Taking the above example, the trajectory point data from station A1 to station A2 in user travel trajectory data 1, user travel trajectory data 2, and user travel trajectory data 5 can be obtained as the trajectory point data matching the bus stops of bus route 1.

[0044] In one possible implementation, the data of trajectory points matching bus stops along the same bus route can be analyzed. Typically, on the same bus route, users will get on and off at bus stops along that route, and buses will also stop at those stops to wait for passengers. Therefore, user trajectory points will cluster at bus stops. Trajectory points from the same user's travel trajectory data will cluster at the bus stops where passengers get on and off. This shows a strong correlation between the user's travel trajectory data and bus stops, accurately reflecting the trajectory point characteristics of users getting on and off at bus stops and vehicles stopping at bus stops. Therefore, based on this strong correlation between user travel trajectory data and bus stops, data analysis can be performed on the trajectory points matching bus stops along the same bus route from multiple user travel trajectory data sets. This identifies the trajectory points clustered at each bus stop along the bus route, and the locations of the bus stops along the bus route can be determined based on the positions of these clustered trajectory points.

[0045] This implementation can acquire multiple user travel trajectory data, including trajectory points when a user takes a bus along a selected bus route in a public transport navigation scenario. The trajectory point data includes the location of each point. For each user travel trajectory data, based on the trajectory point data and the initial location of the bus stop on the selected bus route, the trajectory points in the user travel trajectory data are matched with the bus stops on the bus route. This yields the bus stops for the bus routes that match the trajectory points in the user travel trajectory data. Following the principle that trajectory points cluster at bus stops, the data of trajectory points matching bus stops for the same bus route from multiple user travel trajectory data can be analyzed. This automatic mining of bus stop locations based on user travel trajectory data strongly associated with bus stops is cost-effective and efficient. Because the trajectory points in the user travel trajectory data accurately reflect the characteristics of users getting on and off buses at bus stops and the characteristics of vehicles stopping at bus stops, the locations of bus stops can be accurately mined.

[0046] In one possible implementation, determining the location of a bus stop on the same bus route based on trajectory points matching bus stops on the same bus route from the multiple user travel trajectory data includes:

[0047] Based on the data of trajectory points matching bus stops on the same bus route from multiple user travel trajectory data, multiple target trajectory points are obtained. The target trajectory points are the trajectory points when the user boards the bus and / or when the user alights on the same bus route; or, the target trajectory points are the trajectory points when the user rides the bus on the same bus route.

[0048] Based on the target trajectory points that match the same bus stop among multiple target trajectory points, the location of the bus stop corresponding to the same bus stop is determined.

[0049] In this embodiment, taking the above example as an example, the data of trajectory points matching the bus stops of bus route 1 can be obtained from user ride trajectory data 1-5. These data include the trajectory points in user ride trajectory data 1, the trajectory points in user ride trajectory data 2, and the trajectory points from station A1 to station A2 in user ride trajectory data 5. The data of these trajectory points are then analyzed to determine the target trajectory points among these trajectory points.

[0050] In this embodiment, the target trajectory point can be the trajectory point when the user boards the bus on the same bus route and / or the trajectory point when the user alights. For example, the trajectory point when the user boards the bus at station A1 on bus route 1 and the trajectory point when the user alights at station A2 on bus route 1 can be obtained from the user's travel trajectory data 1, and the trajectory point when the user boards the bus at station A1 on bus route 1 and the trajectory point when the user alights at station A3 on bus route 1 can be obtained from the user's travel trajectory data 2. Typically, before boarding a bus at a bus stop, a user waits at that stop (during this time, the user's trajectory point is generally near the bus stop). When the bus arrives, the user boards at the designated stop. As the bus starts moving away from the bus stop, the user is quickly pulled away (at this time, the user's trajectory point moves rapidly away from the bus stop). Before getting off at another bus stop, the user is on the bus (during this time, the user's trajectory point moves rapidly towards the bus stop). When the bus arrives, the user gets off (at this time, the user's walking trajectory point changes slowly near the bus stop). Therefore, based on the trajectory point data (trajectory point time and trajectory point location), we can determine the user's trajectory point when boarding (for example, the last trajectory point before the user's speed increases near the boarding bus stop) and the user's trajectory point when getting off (for example, the last trajectory point before the user's speed decreases near the disembarking bus stop).

[0051] In this embodiment, the target trajectory point can also be the trajectory point of the user riding the bus on the same bus route, that is, the trajectory point between the user getting on the bus and getting off the bus. For a user's bus trajectory data, after determining the trajectory point when the user gets on the bus and the trajectory point when the user gets off the bus on the same bus route, the trajectory point between the trajectory point when the user gets on the bus and the trajectory point when the user gets off the bus can be directly determined as the target trajectory point.

[0052] In this embodiment, the multiple target trajectory points are the trajectory points when a user boards the bus and / or when a user alights on the same bus route. For example, when multiple users are navigating on bus route 1 of bus route 1, the trajectory points when these users board and alight can be obtained from the trajectory points of these multiple users as target trajectory points. Assume there are 100 target trajectory points a1-a100, where a1-a10 are the boarding trajectory points at station A1 on bus route 1 of bus route 1, a2-a22 are the alighting trajectory points at station A1 on bus route 1 of bus route 1, a23-a50 are the boarding trajectory points at station A3 on bus route 1 of bus route 1, and so on. Previously, bus stops for bus routes matching the trajectory points in the user's travel trajectory data have been obtained, i.e., bus stops for bus routes matching these target trajectory points have been obtained. These target trajectory points are obtained from trajectory points matching bus stops for the same bus route. Therefore, these target trajectory points are trajectory points corresponding to the same bus route. We can further obtain target trajectory points from these multiple target trajectory points that match the same bus stop (i.e., the same bus stop for the same bus route), i.e., obtain trajectory points for getting on and off at the same bus stop. Based on the location distribution of these trajectory points, we can mine the location of the same bus stop. For example, we can determine the location of the same bus stop based on the location distribution of these trajectory points, or we can determine the location of the same bus stop based on the location distribution of these trajectory points, and so on.

[0053] Alternatively, the multiple target trajectory points can be the trajectory points of different users traveling on the same bus route. For example, target trajectory points b1-b1000, b1-b100 are the trajectory points in user trajectory data 1 from when the user boarded bus route 1 at station A1 to when they got off at station A2, and b101-b288 are the trajectory points in user trajectory data 2 from when the user boarded bus route 1 at station A1, passed through station A2, and got off at station A3, and so on. Previously, bus stops for bus routes matching the trajectory points in the user's travel trajectory data were obtained, i.e., bus stops for bus routes matching these target trajectory points were obtained from trajectory points matching bus stops for the same bus route. Therefore, these target trajectory points are trajectory points corresponding to the same bus route. We can further obtain target trajectory points from these multiple target trajectory points that match the same bus stop (i.e., the same bus stop for the same bus route). That is, we obtain trajectory points that arrive at, stop at, and move away from the same bus stop when the user takes the bus. When the bus stops at the same bus stop, most trajectory points will gather at that same bus stop. Therefore, based on the location distribution of these target trajectory points matching the same bus stop, we can mine the location of the same bus stop. For example, we can determine the center location of the area where many trajectory points gather as the location of the same bus stop based on the location distribution of these trajectory points, and so on.

[0054] In one possible implementation, determining the location of the same bus stop based on target trajectory points matched to the same bus stop from among multiple target trajectory points includes:

[0055] Clustering is performed on target trajectory points that match the same bus stop among multiple target trajectory points to obtain at least one cluster, and the at least one cluster corresponds to the same bus stop;

[0056] Calculate the site credibility of each cluster in the at least one cluster;

[0057] The cluster with the highest site confidence among at least one cluster is identified as the target cluster;

[0058] Based on the location distribution of target trajectory points in the target cluster, the location of the bus stop corresponding to the same bus stop is determined.

[0059] In this implementation, when the target trajectory point is the trajectory point where a user boards and / or alights on the same bus route, the target trajectory points matching the same bus stop among these multiple target trajectory points can be clustered. This results in one or more clusters, each cluster representing the boarding and alighting locations at the same bus stop. The clustering algorithm used can be a hierarchical clustering method. For example, each target trajectory point can be considered a cluster, the distance between each cluster can be calculated, the two closest clusters can be found and grouped together, and this process can be repeated until the distance between clusters is too large to be aggregated, thus obtaining multiple clusters. The area covered by the target trajectory points within each cluster could potentially be the location of the same bus stop. Therefore, the station confidence level of each cluster can be calculated. This station confidence level refers to the degree of confidence that the area covered by the cluster is the location of the bus stop. The cluster with the highest station confidence level among at least one cluster is identified as the target cluster containing the bus stop. Based on the location distribution of the target trajectory points in the target cluster, the location of the same bus stop can be determined. For example, the center of the cluster can be identified as the location of the same bus stop.

[0060] In this implementation, when the target trajectory point is a trajectory point on the same bus route traveled by a user, the target trajectory points matching the same bus stop among the multiple target trajectory points are clustered. The clustering algorithm used can be meanshift, achieving unsupervised automatic clustering. For example, Figure 2A This diagram illustrates the clustering of target trajectory points according to an embodiment of the present disclosure, such as... Figure 2A As shown, the trajectory points of a user riding a bus along a bus route can be clustered into multiple clusters. Figure 2A Each trajectory point within a dashed circle represents a cluster. Each cluster consists of user trajectory points near the same bus stop. Therefore, the station reliability of each cluster can be calculated. For example, travel trajectories near actual stations tend to be slower, resulting in more target trajectory points. Clusters with a larger number of target trajectory points and slower travel speeds can have higher station reliability. The cluster with the highest station reliability among at least one cluster is identified as the target cluster containing the station location corresponding to the same bus stop. Based on the location distribution of target trajectory points within this target cluster, the station location corresponding to the same bus stop is determined. For instance, the center of this cluster can be identified as the station location corresponding to the same bus stop.

[0061] It should be noted that other clustering algorithms, such as density-based clustering algorithms, can also be used when clustering target trajectory points.

[0062] In one possible implementation, the trajectory point data further includes trajectory point speed. The step of obtaining multiple target trajectory points based on trajectory point data matching bus stops for the same bus route from multiple user travel trajectory data includes:

[0063] For each travel trajectory data, the trajectory point when the user boarded the bus and the trajectory point when the user alighted the bus were determined based on the trajectory point speed of the trajectory point that matched the boarding and alighting bus stops of the same bus route in the user's travel trajectory data.

[0064] The trajectory points when the user gets on the vehicle and / or when the user gets off the vehicle are used as the target trajectory points, or the trajectory points between the trajectory points when the user gets on the vehicle and when the user gets off the vehicle are used as the target trajectory points.

[0065] In this implementation, each user's travel data corresponds to a bus navigation route. A bus navigation route may include one or more bus routes (for example, if the bus navigation route is a transfer route, it may include two or more bus routes).

[0066] In this embodiment, for each user's travel data, if the bus navigation route corresponding to the user's travel data is a direct route without transfers, the bus navigation route corresponding to the user's travel trajectory data includes the boarding and alighting bus stops of one bus route; if the bus navigation route corresponding to the user's travel data is a direct route requiring transfers, the bus navigation route corresponding to the user's travel trajectory data includes the boarding and alighting bus stops of two or more bus routes. Therefore, in this embodiment, for each user's travel data, trajectory points matching the boarding and alighting bus stops of the same bus route can be obtained.

[0067] Example, Figure 2B This diagram illustrates a user's travel trajectory data according to an embodiment of the present disclosure, such as... Figure 2B As shown, this user's travel trajectory data is a direct route that does not require transfers, from station A1 to station A2 of bus route 1. From this user's travel trajectory data, the matching trajectory points of the boarding bus station A1 and the alighting bus station A2 of bus route 1 can be obtained. Figure 2C A schematic diagram illustrating another user travel trajectory data according to an embodiment of this disclosure is shown, such as... Figure 2CAs shown, this user's travel trajectory data indicates a transfer route, from bus line 1's A1 stop to A2 stop, then transferring to bus line 2's A2 stop to B1 stop. From this user's travel trajectory data, we can obtain the matching trajectory points between the boarding bus stop A1 and the alighting bus stop A2 for bus line 1, and the matching trajectory points between the boarding bus stop A2 and the alighting bus stop B1 for bus line 2.

[0068] In this embodiment, such as Figure 2B As shown in Figure 2C, before boarding the bus at the boarding stop, the user moves at a walking speed (low speed, i.e., adjacent trajectory points are relatively close). After boarding, the user moves at a high speed with the bus (i.e., adjacent trajectory points are relatively far apart). Before alighting, the user moves at a high speed with the bus. After alighting at the alighting stop, the user returns to a walking speed (low speed). Therefore, for each user's travel trajectory data, the user's boarding and alighting trajectory points can be determined based on the speeds of trajectory points matched with the boarding and alighting stops on the same bus route—that is, the speeds of trajectory points near the boarding and alighting stops. For example, a preset speed threshold of 10 km / h can be set (normally, human walking speed cannot continuously reach 10 km / h, but it can be continuously reached after boarding a bus). Figure 2B As shown, if the speed of two or more consecutive trajectory points is greater than 10 km / h (i.e., high-speed point), the user is considered to be on a bus; if the speed of trajectory points is less than 10 km / h (low-speed point), the user is considered to be walking. For example, the last low-speed trajectory point before two consecutive trajectory points with speeds greater than 10 km / h among the trajectory points matched with the boarding bus stop can be considered the trajectory point 201 when the user boarded the bus. Similarly, the first low-speed trajectory point after two consecutive trajectory points with speeds greater than 10 km / h among the trajectory points matched with the alighting bus stop can be considered the trajectory point 202 when the user alighted. Of course, in other embodiments, the target trajectory point can also be determined based on the rate of change of the trajectory point's speed. For example, the last trajectory point before the rate of change suddenly increases among the trajectory points matched with the boarding bus stop can be considered the trajectory point when the user boarded the bus, and the first trajectory point after the rate of change suddenly increases among the trajectory points matched with the alighting bus stop can be considered the trajectory point when the user alighted, and so on.

[0069] In this embodiment, after determining the trajectory points when a user boards the bus and / or when a user alights on the same bus route in each user's travel trajectory, the trajectory points when the user boards the bus and / or when the user alights can be used as target trajectory points, or the trajectory points between the trajectory points when the user boards the bus and when the user alights can be used as target trajectory points.

[0070] In one possible implementation, calculating the site credibility of each cluster in the at least one cluster includes:

[0071] For each of the at least one clusters, the site credibility of the cluster is calculated based on the site credibility impact data of the target trajectory points within the cluster. The site credibility impact data includes the number of users, location variance, speed consistency, and relationship with traffic light intersections for the target trajectory points within the cluster.

[0072] In this embodiment, the data affecting the credibility of a station refers to various data that affect the credibility of the location of the bus stop within the area covered by the cluster. This data may include at least one of the following: the number of users of the target trajectory point within the cluster, location variance, speed consistency, and relationship with traffic light intersections.

[0073] In this implementation, the more users there are for the target trajectory points within a cluster, the more diverse the reference samples, and the higher the station's credibility. Trajectory points near bus stops are usually clustered; therefore, the smaller the location variance of the target trajectory points within a cluster, the more clustered the target trajectory points are, and the higher the station's credibility. Since the speeds of trajectory points at bus stops are generally low, their speed consistency is high, while the speed consistency of target trajectory points in clusters outside bus stops is low (some target trajectory points may have higher speeds, while others may have lower speeds due to traffic congestion). Therefore, higher speed consistency also indicates higher station credibility. Besides bus stop areas, which are prone to forming clusters with a large number of users, low location variance, or high speed consistency, traffic light intersections are also prone to forming such clusters. Therefore, the station's credibility can be determined based on the relationship between the cluster and the traffic light intersection; the closer the cluster is to the traffic light intersection, the lower the station's credibility.

[0074] In this embodiment, the site credibility of the cluster can be calculated based on one or more site credibility influence data and the influence weight of various site credibility influence data on the site credibility.

[0075] In one possible implementation, calculating the site credibility of each cluster in the at least one cluster includes:

[0076] For each of the at least one clusters, a pre-trained evaluation model is used to evaluate the station credibility of the cluster based on the trajectory point characteristics of the target trajectory point within the cluster and the road segment characteristics of the road segment where the target trajectory point is located within the cluster.

[0077] In this embodiment, the evaluation model can be a time series prediction model based on the LSTM (Long Short Term Memory) model. The input of the evaluation model is the trajectory point features of the target trajectory points within the cluster and the road segment features of the road segments where the trajectory points are located within the cluster. The output is the station credibility of the cluster. The evaluation model is used to perform feature analysis on the trajectory point features and the road segment features of the road segments where the trajectory points are located within the cluster to determine the station credibility of the cluster.

[0078] In this embodiment, the trajectory point feature refers to the feature extracted from the trajectory point data of the target trajectory points within the cluster that can reflect the station credibility of the cluster. The trajectory point feature may include the number of target trajectory points within the cluster, the speed distribution characteristics of the target trajectory points within the cluster, such as the number of ultra-low speed (speed less than or equal to 3 km / h) target trajectory points within the cluster, the number of medium-low speed (speed greater than 3 km / h and less than or equal to 6 km / h) target trajectory points within the cluster, the number of medium speed (speed greater than 6 km / h and less than or equal to 10 km / h) target trajectory points within the cluster, the number of medium-high speed (speed greater than 10 km / h and less than or equal to 15 km / h) target trajectory points within the cluster, the number of ultra-high speed (speed greater than 15 km / h) target trajectory points within the cluster, and at least one of the following: average speed, maximum speed, minimum speed, speed standard deviation, upper quartile speed, lower quartile speed, and median speed of the target trajectory points within the cluster.

[0079] In this embodiment, the road segment feature refers to the feature extracted from the relevant data of the road segment where the target trajectory point is located within the cluster, which can reflect the station credibility of the cluster. The road segment feature includes the static features of the road segment, which may include at least one of the following: the number of in-degree roads, the number of out-degree roads, whether it is an intersection, whether there is a traffic light at the starting point of the road segment, whether there is a traffic light at the ending point of the road segment, road grade (first-class highway, second-class highway, etc.), road type (intersection, auxiliary road, ramp, etc.), functional level (such as arterial road, secondary arterial road, branch road, etc.), traffic status (such as both pedestrians and vehicles can pass, pedestrians only, vehicles only, neither pedestrians nor vehicles can pass, etc.), road location type (such as ordinary road, ferry route, tunnel, bridge, underground traffic passage, etc.), road paving status (not investigated, unpaved dirt road, paved, partially paved), whether it is an elevated road, whether it is in an urban area, etc. In addition to the static features mentioned above, the road segment characteristics can also include influence features extended from the static features, such as the influence coefficient when there is a traffic light at the start of the road segment, the influence coefficient when there is a traffic light at the end of the road segment, the influence coefficient when the start of the road segment is an intersection, and the influence coefficient when the end of the road segment is an intersection. Among these, when there is a traffic light at the start or end of the road segment, the closer the traffic light is to the area covered by the cluster, the greater the influence coefficient. When the start or end of the road segment is an intersection, the closer the intersection is to the area covered by the cluster, the greater the influence coefficient.

[0080] In this embodiment, the trajectory features and road segment features corresponding to the cluster can be input into the evaluation model, and by executing the evaluation model, the station credibility of the cluster can be obtained from the output of the evaluation model.

[0081] In this implementation, a training sample can be used to train the evaluation model. This training sample includes clusters formed by grouping target trajectory points from multiple user-generated travel trajectory data, and the actual station locations on the bus routes corresponding to these data. The evaluation model can be trained using this training sample until the accuracy of the station credibility assessment of the clusters reaches a predetermined requirement. It should be noted that this accuracy can be referenced to the actual station locations; the cluster containing the actual station location has the highest station credibility, indicating accurate evaluation.

[0082] In one possible implementation, before matching the trajectory points in the user's travel trajectory data with the initial locations of bus stops on their corresponding public transport navigation routes, the method may include the following steps:

[0083] For each user's travel trajectory data, the data of abnormal trajectory points in the user's travel trajectory data are cleared.

[0084] In this implementation, each user's travel trajectory data can be detected. If there are abnormal trajectory points in the data, such as two trajectory points having the same timing but different locations (which is impossible), or if a trajectory point in the data is clearly a jump point with an abnormal relative position to its preceding and following time points, this is also considered abnormal. Abnormal trajectory points in each user's travel trajectory data can be removed to ensure the accuracy of each user's travel trajectory data, thereby ensuring the accuracy of the subsequently determined station locations.

[0085] In one possible implementation, for each user's travel trajectory data, when the bus navigation route corresponding to the user's travel trajectory data is a transfer route, the trajectory points in the user's travel trajectory data are matched with the bus stops on the bus route based on the data of the trajectory points in the user's travel trajectory data and the initial positions of the bus stops on the bus route selected by the user in the bus navigation route, to obtain the bus stops of the bus route that match the trajectory points in the user's travel trajectory data, including:

[0086] Obtain the transfer trajectory points in the user's travel trajectory data that match the two bus stops before and after the transfer;

[0087] In response to the discontinuity of trajectory points matching the same bus stop in the transfer trajectory points, the trajectory points in the previous time period of the time period in which the transfer trajectory points are located are matched to the alighting bus stop of the bus route before the transfer, and the trajectory points in the next time period are matched to the boarding bus stop of the bus route after the transfer.

[0088] In this implementation, for each user's travel trajectory data, when the corresponding bus navigation route is a transfer route (i.e., the bus navigation route includes two or more bus routes), matching the trajectory points in the user's travel trajectory data with the initial positions of bus stops on the corresponding bus navigation route yields the transfer trajectory points in the user's travel trajectory data that match adjacent bus stops on the two bus routes before and after the transfer. For example,... Figure 2C As shown, the bus navigation route involves first taking bus route 1 from stop A1 to stop A2, then transferring to bus route 2 from stop A2 to stop B1. Therefore, stops A2 of bus route 1 and A2 of bus route 2 are adjacent bus stops on the two bus routes before and after the transfer. The trajectory points matching stop A2 of bus route 1 and stop A2 of bus route 2 can be obtained as the transfer trajectory points.

[0089] In this implementation, the discontinuity of trajectory points matching the same bus stop in the transfer trajectory points means that there are trajectory points that match the same bus stop but also match a different bus stop. For example, the trajectory point at one moment matches the A2 stop of bus route 1, the trajectory point at another moment matches the A2 stop of bus route 2, and the trajectory point at the moment after that matches the A2 stop of bus route 1 again. This indicates that the trajectory points matching the A2 stop of bus route 1 are discontinuous.

[0090] In this embodiment, in response to the discontinuous nature of the trajectory points matched to the same bus stop in the transfer trajectory points, the time period of the transfer trajectory point can be divided into two time periods according to the order of getting off at the bus stop of the bus route before the transfer and getting on at the bus stop of the bus route after the transfer. The trajectory points in the first time period are matched to the bus stop where the passenger got off at the bus route before the transfer, and the trajectory points in the second time period are matched to the bus stop where the passenger got on at the bus route after the transfer.

[0091] In this embodiment, the start time of the previous time period is the start time of the transfer trajectory point, and the end time of the previous time period is after the trajectory point time of the alighting trajectory point of the previous bus stop in the transfer trajectory point and before the trajectory point time of the boarding trajectory point of the next bus stop in the transfer trajectory point; the start time of the next time period is the end time of the previous time period, and the end time of the next time period is the end time of the transfer trajectory point.

[0092] In one possible implementation, before matching the trajectory points in the user's travel trajectory data with the initial locations of bus stops on their corresponding public transport navigation routes, the method further includes:

[0093] If the similarity between the actual trajectory line formed by the trajectory points in the user's travel trajectory data and its corresponding public transport navigation line is lower than a predetermined threshold, or if the direction of the actual trajectory line is different from the direction of the corresponding public transport navigation line, the user's travel trajectory data will be removed.

[0094] In this embodiment, when a user uses the corresponding bus navigation route to travel, they may get off the bus midway for reasons such as other reasons and not follow the corresponding bus navigation route. In this case, the actual trajectory line formed by the trajectory points in the user's travel trajectory data will have a low similarity to the corresponding bus navigation route, which is below a predetermined threshold. At this time, the user's travel trajectory data is not related to the bus route in the corresponding bus navigation route, and the user's travel trajectory data cannot be used to mine bus stops. Therefore, the user's travel trajectory data can be removed.

[0095] In this implementation, when a user uses the corresponding bus navigation route to travel, they may board the wrong bus. Although the actual trajectory line formed by the trajectory points in the user's travel trajectory data will be highly similar to the corresponding bus navigation route, the direction of the actual trajectory line is different from the direction of the corresponding bus navigation route, and is in the opposite direction. In this case, the user's travel trajectory data is not related to the bus route in the corresponding bus navigation route, and the user's travel trajectory data should be removed.

[0096] Figure 3 A structural block diagram of a bus stop location determination device according to an embodiment of the present disclosure is shown. This device can be implemented as part or all of an electronic device through software, hardware, or a combination of both. Figure 3 As shown, the bus stop location determination device includes:

[0097] The data acquisition module 301 is configured to acquire multiple user ride trajectory data, which includes data of trajectory points when a user takes a bus according to the bus navigation route selected by the user in a public transportation navigation scenario, and the data of trajectory points includes the location of the trajectory points.

[0098] The matching module 302 is configured to, for each user's travel trajectory data, match the trajectory points in the user's travel trajectory data with the bus stops on the bus routes selected by the user in the bus navigation route, based on the trajectory point data in the user's travel trajectory data and the initial positions of the bus stops on the bus routes, to obtain the bus stops of the bus routes that match the trajectory points in the user's travel trajectory data; wherein, the bus navigation route includes one or more bus routes.

[0099] The location determination module 303 is configured to determine the location of the bus stop on the same bus route based on the data of trajectory points that match the bus stops on the same bus route in the multiple user travel trajectory data.

[0100] In one possible implementation, the location determination module is configured to:

[0101] Based on the data of trajectory points matching bus stops on the same bus route from multiple user travel trajectory data, multiple target trajectory points are obtained. The target trajectory points are the trajectory points when the user boards the bus and / or when the user alights on the same bus route; or, the target trajectory points are the trajectory points when the user rides the bus on the same bus route.

[0102] Based on the target trajectory points that match the same bus stop among multiple target trajectory points, the location of the bus stop corresponding to the same bus stop is determined.

[0103] In one possible implementation, the part of the location determination module that determines the location of the same bus stop based on target trajectory points matched to the same bus stop among multiple target trajectory points is configured as follows:

[0104] Clustering is performed on target trajectory points that match the same bus stop among multiple target trajectory points to obtain at least one cluster, and the at least one cluster corresponds to the same bus stop;

[0105] Calculate the site credibility of each cluster in the at least one cluster;

[0106] The cluster with the highest site confidence among at least one cluster is identified as the target cluster;

[0107] Based on the location distribution of target trajectory points in the target cluster, the location of the bus stop corresponding to the same bus stop is determined.

[0108] In one possible implementation, the trajectory point data further includes trajectory point velocity, and the part of the location determination module that obtains multiple target trajectory points based on the trajectory point data matching bus stops for the same bus route from multiple user travel trajectory data is configured as follows:

[0109] For each user's travel trajectory data, the trajectory point when the user boards the bus and the trajectory point when the user alights are determined based on the trajectory point speed of the trajectory point that matches the boarding and alighting bus stops of the same bus route in the user's travel trajectory data.

[0110] The trajectory points when the user gets on the vehicle and / or when the user gets off the vehicle are used as the target trajectory points, or the trajectory points between the trajectory points when the user gets on the vehicle and when the user gets off the vehicle are used as the target trajectory points.

[0111] In one possible implementation, the portion of the location determination module that calculates the site credibility of each cluster in the at least one cluster is configured to:

[0112] For each of the at least one clusters, the site credibility of the cluster is calculated based on the site credibility impact data of the target trajectory points within the cluster. The site credibility impact data includes at least one of the following: number of users, location variance, speed consistency, and relationship with traffic light intersections for the target trajectory points within the cluster.

[0113] In one possible implementation, the portion of the location determination module that calculates the site credibility of each cluster in the at least one cluster is configured to:

[0114] For each of the at least one clusters, a pre-trained evaluation model is used to evaluate the station credibility of the cluster based on the trajectory point characteristics of the target trajectory point within the cluster and the road segment characteristics of the road segment where the target trajectory point is located within the cluster.

[0115] In one possible implementation, the device further includes:

[0116] The data cleaning module is configured to remove abnormal trajectory points from each user's ride trajectory data before matching the trajectory points in the user's ride trajectory data with the initial locations of bus stops on the corresponding bus navigation routes.

[0117] In one possible implementation, for each user's travel trajectory data, when the corresponding public transport navigation route is a transfer route, the matching module is configured as follows:

[0118] Obtain the transfer trajectory points in the user's travel trajectory data that match the two bus stops before and after the transfer;

[0119] In response to the discontinuity of trajectory points matching the same bus stop in the transfer trajectory points, the trajectory points in the previous time period of the time period in which the transfer trajectory points are located are matched to the alighting bus stop of the bus route before the transfer, and the trajectory points in the next time period are matched to the boarding bus stop of the bus route after the transfer.

[0120] In one possible implementation, the device further includes:

[0121] The elimination module is configured to eliminate the user's travel trajectory data before matching the trajectory points in the user's travel trajectory data with the initial positions of bus stops on the corresponding bus navigation routes, in response to the fact that the similarity between the actual trajectory corresponding to the trajectory point in the user's travel trajectory data and the corresponding bus navigation route is lower than a predetermined threshold, or the trajectory direction of the actual trajectory is different from the route direction of the corresponding bus navigation route.

[0122] The technical terms and features mentioned in this device implementation are the same or similar. For the explanation and description of the technical terms and features involved in this device, please refer to the explanation of the above method implementation, which will not be repeated here.

[0123] This disclosure also discloses an electronic device, Figure 4 A structural block diagram of an electronic device according to an embodiment of the present disclosure is shown.

[0124] like Figure 4As shown, the electronic device 400 includes a memory 401 and a processor 402, wherein the memory 401 is used to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor 402 to implement the method according to an embodiment of the present disclosure.

[0125] Figure 5 A schematic diagram of the structure of a computer system suitable for implementing the method according to embodiments of the present disclosure is shown.

[0126] like Figure 5 As shown, the computer system 500 includes a processing unit 501, which can execute various processes described in the above embodiments according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage section 508 into a random access memory (RAM) 503. The RAM 503 also stores various programs and data required for the operation of the computer system 500. The processing unit 501, ROM 502, and RAM 503 are interconnected via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0127] The following components are connected to I / O interface 505: an input section 506 including a keyboard, mouse, etc.; an output section 507 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to I / O interface 505 as needed. A removable medium 511, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 510 as needed so that computer programs read from it can be installed into storage section 508 as needed. The processing unit 501 can be implemented as a CPU, GPU, TPU, FPGA, NPU, etc.

[0128] In particular, according to embodiments of this disclosure, the methods described above can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising computer instructions that, when executed by a processor, implement the steps of the methods described above. In such embodiments, the computer program product can be downloaded and installed from a network via communication section 509, and / or installed from removable media 511.

[0129] 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 this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated 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 operation, or using a combination of dedicated hardware and computer instructions.

[0130] The units or modules described in the embodiments of this disclosure can be implemented in software or programmable hardware. The described units or modules can also be located in a processor, and the names of these units or modules do not necessarily constitute a limitation on the unit or module itself.

[0131] In another aspect, this disclosure also provides a computer-readable storage medium, which may be a computer-readable storage medium included in the electronic device or computer system described above; or it may be a standalone computer-readable storage medium not assembled into a device. The computer-readable storage medium stores one or more programs, which are used by one or more processors to perform the methods described in this disclosure.

[0132] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

Claims

1. A method for determining the location of a bus stop, comprising: Acquire multiple user ride trajectory data, which includes data on trajectory points when a user takes a bus according to the bus navigation route selected by the user in a public transportation navigation scenario, and the trajectory point data includes the location of the trajectory point; For each user's travel trajectory data, based on the trajectory points in the user's travel trajectory data and the initial location of the bus stops on the bus route selected by the user in the public transport navigation route, the trajectory points in the user's travel trajectory data are matched with the bus stops on the bus route to obtain the bus stops of the bus route that match the trajectory points in the user's travel trajectory data; wherein, the public transport navigation route includes one or more bus routes. Based on the data of trajectory points that match bus stops on the same bus route in the multiple user travel trajectory data, multiple target trajectory points are obtained. The target trajectory points are the trajectory points when the user gets on the bus and / or when the user gets off the bus on the same bus route, or the target trajectory points are the trajectory points when the user rides the bus on the same bus route. Based on the target trajectory points that match the same bus stop among multiple target trajectory points, the location of the bus stop corresponding to the same bus stop is determined.

2. The method according to claim 1, wherein, The step of determining the location of the same bus stop based on target trajectory points matched to the same bus stop from multiple target trajectory points includes: Clustering is performed on target trajectory points that match the same bus stop among multiple target trajectory points to obtain at least one cluster, and the at least one cluster corresponds to the same bus stop; Calculate the site credibility of each cluster in the at least one cluster; The cluster with the highest site confidence among at least one cluster is identified as the target cluster; Based on the location distribution of target trajectory points in the target cluster, the location of the bus stop corresponding to the same bus stop is determined.

3. The method according to claim 1, wherein, The trajectory point data includes trajectory point speed. The process of obtaining multiple target trajectory points based on trajectory point data matching bus stops for the same bus route from multiple user travel trajectory data includes: For each user's travel trajectory data, the trajectory point when the user boards the bus and the trajectory point when the user alights are determined based on the trajectory point speed of the trajectory point that matches the boarding and alighting bus stops of the same bus route in the user's travel trajectory data. The trajectory points when the user gets on the vehicle and / or when the user gets off the vehicle are used as the target trajectory points, or the trajectory points between the trajectory points when the user gets on the vehicle and when the user gets off the vehicle are used as the target trajectory points.

4. The method according to claim 2, wherein, The calculation of the site credibility of each cluster in the at least one cluster includes: For each of the at least one clusters, the site credibility of the cluster is calculated based on the site credibility impact data of the target trajectory points within the cluster. The site credibility impact data includes at least one of the following: number of users, location variance, speed consistency, and relationship with traffic light intersections for the target trajectory points within the cluster.

5. The method according to claim 1, wherein, For each user's travel trajectory data, when the corresponding bus navigation route is a transfer route, the trajectory points in the user's travel trajectory data are matched with the bus stops on the selected bus route based on the trajectory point data and the initial location of the bus stops on the bus route. This yields the bus stops for the bus routes that match the trajectory points in the user's travel trajectory data, including: Determine the transfer trajectory points in the user's travel trajectory data that match the two bus stops before and after the transfer; In response to the discontinuity of trajectory points matching the same bus stop in the transfer trajectory points, the trajectory points in the previous time period of the time period in which the transfer trajectory points are located are matched to the alighting bus stop of the bus route before the transfer, and the trajectory points in the next time period are matched to the boarding bus stop of the bus route after the transfer.

6. The method according to claim 1, wherein, Before matching the trajectory points in the user's travel trajectory data with the initial locations of bus stops on their corresponding public transport navigation routes, the method further includes: If the similarity between the actual trajectory corresponding to a trajectory point in the user's travel trajectory data and its corresponding public transportation navigation route is lower than a predetermined threshold, or if the trajectory direction of the actual trajectory is different from the route direction of its corresponding public transportation navigation route, the user's travel trajectory data will be removed.

7. A bus stop location determination device, comprising: The data acquisition module is configured to acquire multiple user ride trajectory data, which includes data on trajectory points when a user takes a bus according to the bus navigation route selected by the user in a public transportation navigation scenario, and the trajectory point data includes the location of the trajectory point. The matching module is configured to, for each user's travel trajectory data, match the trajectory points in the user's travel trajectory data with the bus stops on the bus routes selected by the user in the public transport navigation route, based on the trajectory point data in the user's travel trajectory data and the initial location of the bus stops on the bus routes selected by the user in the public transport navigation route, to obtain the bus stops of the bus routes that match the trajectory points in the user's travel trajectory data; wherein, the public transport navigation route includes one or more bus routes. The location determination module is configured to obtain multiple target trajectory points based on the trajectory points matching bus stops on the same bus route from the multiple user travel trajectory data. The target trajectory points are the trajectory points when the user boards the bus and / or when the user alights on the same bus route, or the target trajectory points are the trajectory points when the user rides the bus on the same bus route. Based on the target trajectory points that match the same bus stop from the multiple target trajectory points, the module determines the station location corresponding to the same bus stop.

8. An electronic device comprising a memory and a processor; wherein, The memory is used to store one or more computer instructions, which are executed by the processor to implement the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having computer instructions stored thereon, wherein, When executed by a processor, the computer instructions implement the method described in any one of claims 1-6.

Images