Arrival point mining method, electronic device and storage medium

Abstract

The disclosed embodiment discloses an arrival point mining method, electronic device and storage medium, the method comprising: obtaining basic data of a building block where a target point of interest to be mined is located; the basic data includes the arrival points of at least one other point of interest with a credible terminal position in the building block and the surrounding road data of the building block; clustering the orientation angles of the other points of interest to obtain clusters; wherein the orientation angles of the other points of interest are determined based on the geographical locations of the other points of interest and the arrival points of the other points of interest; determining the cluster center of the cluster with the largest number of cluster members as the target orientation angle of the target point of interest; extending the geographical location of the target point of interest along the direction of the target orientation angle, and determining the arrival point of the target point of interest based on the position where the extension intersects with the surrounding roads. This technical solution can improve the accuracy of the arrival points of target points of interest for which there is no data to rely on.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to an arrival point mining method, an electronic device, and a storage medium. Background Art

[0002] With the development of location-based services (LBS), more and more applications are integrating digital map-related services. For example, users can use map navigation apps or ride-hailing apps to search for points of interest (POIs) on digital maps and plan navigation routes to them. POIs on digital maps represent real-world locations such as residential communities, basement stores, subway stations, and public restrooms.

[0003] In location-based service systems, corresponding arrival points are mined for different POIs based on existing data. This allows the service recipient, whose destination is set to the POI, to be guided to the corresponding arrival point during the location service process. In actual applications, some POIs may not have corresponding data, making it impossible to mine their arrival points based on their own existing data. Existing technologies for such POIs typically use a display capture method to determine the arrival point, that is, to determine the initial arrival point from the location information displayed on the map data. However, the initial arrival point is not very accurate and is prone to misguidance. Therefore, how to mine accurate arrival points for POIs without data is one of the technical problems that need to be solved in the current technical field. Summary of the Invention

[0004] Embodiments of the present disclosure provide an arrival point mining method, an electronic device, and a computer-readable storage medium.

[0005] In a first aspect, an embodiment of the present disclosure provides an arrival point mining method, which includes:

[0006] Obtain basic data of the building block where the target point of interest to be mined is located; the basic data includes the arrival point of at least one other point of interest with a reliable terminal position in the building block and the surrounding road data of the building block;

[0007] Clustering the orientation angles of the other points of interest to obtain clusters; wherein the orientation angles of the other points of interest are determined based on the geographical locations of the other points of interest and the arrival points of the other points of interest;

[0008] Determining the cluster center of the cluster with the largest number of cluster members as the target orientation angle of the target point of interest;

[0009] The geographical location of the target point of interest is extended along the direction of the target heading angle, and an arrival point of the target point of interest is determined based on a position where the extended geographical location intersects with surrounding roads.

[0010] Furthermore, the orientation angles of the other points of interest are clustered to obtain clusters, including:

[0011] Selecting one of the orientation angles of the other points of interest and clustering it with the existing clusters; if there is no existing cluster or it cannot be clustered into the existing clusters, generating a new cluster until all orientation angles are clustered into corresponding clusters;

[0012] Calculate the target cluster center of the generated cluster cluster, and re-cluster the orientation angles of the other points of interest according to the target cluster center. After clustering is completed, recalculate the target cluster center of the cluster cluster obtained by clustering, and repeat the previous step until the target cluster center no longer changes.

[0013] Furthermore, one of the orientation angles of the other points of interest is selected and clustered with the existing cluster. If there is no existing cluster or it cannot be clustered into an existing cluster, a new cluster is generated until all orientation angles are clustered into corresponding clusters, including:

[0014] Taking the orientation angle of one of the other interest points as a candidate cluster center of the initial cluster, and the remaining orientation angles of the other interest points constitute a queue of orientation angles to be clustered;

[0015] The orientation angle read from the queue of orientation angles to be clustered is used as the orientation angle to be clustered, and compared with the candidate cluster centers of the existing clusters. The orientation angles to be clustered that meet the conditions are clustered into the clusters, and for the orientation angles to be clustered that do not meet the conditions, a new cluster family is generated and used as the candidate cluster center of the new cluster cluster. The above steps are repeated until the orientation angles in the queue of orientation angles to be clustered are clustered into the corresponding clusters.

[0016] Further, the orientation angles read from the queue of orientation angles to be clustered are used as orientation angles to be clustered, compared with the candidate cluster centers of the existing clusters, and the orientation angles to be clustered that meet the conditions are clustered into the clusters, including:

[0017] When the angle difference between the orientation angle to be clustered and the candidate cluster center is less than or equal to a preset angle value, the orientation angle to be clustered and the candidate cluster center are clustered into the cluster cluster.

[0018] Furthermore, the method further comprises:

[0019] When the difference between the number of members of the cluster with the largest number of members and the number of members of the cluster with the second largest number of members is within a preset range, the arrival point of the target point of interest is filtered.

[0020] Furthermore, the method further comprises:

[0021] When the length of the first side where the line between the arrival point of the target point of interest and the geographic location of the target point of interest intersects with the building block boundary is greater than or equal to the length of the second side where the line between the initial end position of the target point of interest and the geographic location of the target point of interest intersects with the building block boundary, the arrival point of the target point of interest is filtered.

[0022] Furthermore, the method further comprises at least one of the following:

[0023] When the types of the target point of interest do not match those of the arrival point, filtering the arrival point of the target point of interest;

[0024] filtering the arrival point of the target point of interest when a first distance between the geographic location of the target point of interest and the arrival point of the target point of interest is greater than or equal to a second distance between the geographic location of the target point of interest and an initial destination location of the target point of interest; the initial destination location being the initial arrival point of the target point of interest predetermined based on map data;

[0025] When a line between the target point of interest and the arrival point of the target point of interest crosses other building blocks, filtering the arrival point of the target point of interest;

[0026] When the attribute of the road where the arrival point of the target point of interest is located does not meet the preset attribute, the arrival point of the target point of interest is filtered.

[0027] Furthermore, the method further comprises:

[0028] When the road where the arrival point of the target point of interest is located intersects with the road where the initial end position of the target point of interest is located, and the distances between the arrival point of the target point of interest and the initial end position and the intersection are all less than a preset distance threshold, the arrival point of the target point of interest is updated to the position of the intersection.

[0029] Furthermore, the method further comprises:

[0030] If the road where the arrival point of the target point of interest is located is a road with separated upper and lower lines, and the first distance from the downstream node of the road where the arrival point is located to the arrival point is less than or equal to a first distance threshold, and the second distance from the upstream node of the road where the arrival point is located to the arrival point is greater than or equal to a second distance threshold, then the arrival point is updated to the location of the downstream node.

[0031] Further, determining the arrival point of the target point of interest based on the position where the extended path intersects with the surrounding roads includes:

[0032] Among the multiple location points intersecting with the surrounding roads after extension, the location point with the shortest geographical location distance to the target point of interest is determined as the arrival point.

[0033] In the second aspect, an embodiment of the present disclosure provides a method for providing location-based services, wherein the method uses the arrival point determined by the method described in the first aspect to provide location-based services to the service object, and the location-based services include: navigation, map rendering, route planning or one or more.

[0034] In a third aspect, an embodiment of the present disclosure provides an arrival point excavation device, comprising:

[0035] An acquisition module is configured to acquire basic data of a building block where a target point of interest of a to-be-mined arrival point is located; the basic data includes arrival points of at least one other point of interest with a credible destination position in the building block and surrounding road data of the building block;

[0036] a clustering module configured to cluster the orientation angles of the other points of interest to obtain clusters; wherein the orientation angles of the other points of interest are determined based on the geographical locations of the other points of interest and the arrival points of the other points of interest;

[0037] A first determining module is configured to determine the cluster center of the cluster with the largest number of cluster members as the target orientation angle of the target interest point;

[0038] The second determining module is configured to extend the geographical location of the target point of interest along the direction of the target heading angle, and determine the arrival point of the target point of interest based on a position where the extended geographical location intersects with surrounding roads.

[0039] In a fourth aspect, an embodiment of the present disclosure provides a location-based service providing device, wherein the device uses the arrival point determined by the arrival point mining device described in the third aspect to provide location-based services to the service object, and the location-based services include: navigation, map rendering, route planning or one or more.

[0040] The functions can be implemented by hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the functions.

[0041] In one possible design, the apparatus includes a memory and a processor. The memory is configured to store one or more computer instructions that enable the apparatus to perform the corresponding method, and the processor is configured to execute the computer instructions stored in the memory. The apparatus may also include a communication interface for communicating with other devices or a communication network.

[0042] In a fifth aspect, an embodiment of the present disclosure provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the method described in any one of the above aspects.

[0043] In a sixth aspect, an embodiment of the present disclosure provides a computer-readable storage medium for storing computer instructions used by any of the above-mentioned devices, and when the computer instructions are executed by a processor, they are used to implement the method described in any of the above-mentioned aspects.

[0044] In a seventh aspect, an embodiment of the present disclosure provides a computer program product, which includes computer instructions, and when the computer instructions are executed by a processor, they are used to implement the method described in any of the above aspects.

[0045] The technical solutions provided by the embodiments of the present disclosure may have the following beneficial effects:

[0046] The disclosed embodiment is aimed at a target point of interest for which there is no data. When mining the arrival point of the target point of interest, the arrival points of other points of interest in the building block where the target point of interest is located and the surrounding road data of the building block are obtained, and the orientation angles of the other points of interest are determined based on the arrival points of the other points of interest. Then, the orientation angles of the other points of interest are clustered to obtain a cluster with the largest number of members, and the cluster center of the cluster is determined as the orientation angle of the target point of interest; the arrival point of the target point of interest is determined based on the orientation angle of the target point of interest and the geographical location of the target point of interest. In this way, when there is no data to mine for the target point of interest, the orientation angle of the target point of interest can be obtained by referring to the orientation angles of other points of interest in the building block where the target point of interest is located, and the arrival point of the target point of interest can be mined based on the orientation angle, which can improve the accuracy of the arrival point of the target point of interest for which there is no data to rely on.

[0047] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Other features, objectives and advantages of the present disclosure will become more apparent through the following detailed description of non-limiting embodiments in conjunction with the accompanying drawings. In the accompanying drawings:

[0049] Figure 1A flowchart showing an arrival point mining method according to an embodiment of the present disclosure is shown;

[0050] Figure 2 The following is a flowchart showing an implementation of an improved kmeans clustering algorithm according to an embodiment of the present disclosure;

[0051] Figure 3 A schematic diagram illustrating an application scenario of a method for mining arrival points of ground floor shops without data according to one embodiment of the present disclosure is shown;

[0052] Figure 4 A structural block diagram of an arrival point excavation device according to an embodiment of the present disclosure is shown;

[0053] Figure 5 It is a structural diagram of an electronic device suitable for implementing the arrival point mining and / or location-based service providing method according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0054] Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily implement them. In addition, for the sake of clarity, parts not related to the description of the exemplary embodiments are omitted in the accompanying drawings.

[0055] In the present disclosure, it should be understood that terms such as "including" or "having" are intended to indicate the presence of features, numbers, steps, behaviors, components, parts, or combinations thereof disclosed in the present specification, and do not exclude the possibility that one or more other features, numbers, steps, behaviors, components, parts, or combinations thereof exist or are added.

[0056] It should also be noted that, in the absence of conflict, the embodiments and features of the embodiments of the present disclosure may be combined with each other. The present disclosure will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0057] The details of the embodiments of the present disclosure are described in detail below through specific examples.

[0058] Figure 1 FIG. 1 is a flow chart showing a method for mining arrival points according to an embodiment of the present disclosure. Figure 1 As shown, the arrival point mining method includes the following steps:

[0059] In step S101, basic data of the building block where the target point of interest to be mined is located is obtained; the basic data includes the arrival points of at least one other point of interest with a reliable terminal position in the building block and the surrounding road data of the building block;

[0060] In step S102, clustering the orientation angles of the other points of interest to obtain clusters; wherein the orientation angles of the other points of interest are determined based on the geographical locations of the other points of interest and the arrival points of the other points of interest;

[0061] In step S103, the cluster center of the cluster with the largest number of cluster members is determined as the target orientation angle of the target interest point;

[0062] In step S104, the geographical location of the target point of interest is extended along the direction of the target heading angle, and the arrival point of the target point of interest is determined based on the position where the extended geographical location intersects with the surrounding roads.

[0063] In this embodiment, the arrival point can be understood as a guidance arrival point pre-set for each POI in a location-based service system such as navigation or route planning. When the service object requests the route planning service or navigation service of the POI, the location-based service system will guide the service object to the arrival point corresponding to the POI.

[0064] Typically, the following requirements apply to a POI's arrival point: At the arrival point, POI landmarks, such as signs, storefronts, entrances, and buildings within the courtyard, must be visible within the field of vision, and the POI must be reachable on foot. Furthermore, the arrival point must be visible and accessible, the planned route must not pass through the courtyard, and must be the shortest reasonable route.

[0065] In a location-based service system, the arrival points of different POIs can be mined based on different strategies. Mining strategies may include but are not limited to parent-child guidance strategy, multi-door guidance strategy, manual arrival point guidance strategy, mined arrival point guidance strategy, heading angle guidance strategy, and displayed road tracking guidance strategy.

[0066] For POIs with available data, parent-child guidance strategies, multi-door guidance strategies, manual arrival point guidance strategies, orientation angle guidance strategies, etc. can be adopted. For POIs without data, display path guidance strategies and excavation arrival point strategies can be adopted. The display path guidance strategy refers to the arrival point obtained based on the displayed coordinates of the electronic map and the location of the path. For some POIs, such as basements in buildings, the accuracy of the arrival point obtained by this strategy is low. Therefore, the embodiment of the present disclosure adopts the excavation arrival point strategy to obtain the corresponding arrival point for target points of interest for which no data is available. In some embodiments, in the display path guidance strategy, the approximate direction of the POI can be determined by the displayed coordinates of the POI on the electronic map and the relative position of the POI in the building block. Then, a vertical line is drawn to the nearest edge of the building block based on the direction, and the intersection of the vertical line and the nearest road can be determined as the arrival point.

[0067] In some embodiments, the target POI may be a POI with no data, and the accuracy of the arrival point obtained by displaying the route tracking guidance strategy is not high. For example, the target POI may be a basement POI within a building.

[0068] Basic data may include, but is not limited to, data on other POIs in the building block where the target point of interest is located, data on the building block, and data on surrounding roads. Data on other POIs may include, but is not limited to, data on the arrival point corresponding to the POI, the mining strategy corresponding to the arrival point, the geographical location of the POI, and the like. The geographical location may be the real-world location of the POI shown on the map. Data on the building block may include, but is not limited to, whether the building block is a rendered building block or a satellite building block, the boundary position information of the building block on the map, the POIs included in the building block, and the like. Surrounding road data may include, but is not limited to, road network data and node data on the road network. Node data may include, but is not limited to, intersection nodes between various road sections in the road network, and the like.

[0069] Other points of interest that are credible at the destination location can be understood as points of interest with a high credibility of arrival points mined using existing data. Other points of interest that are credible at the destination location may include, but are not limited to, points of interest determined by the manual arrival point guidance strategy, points of interest determined by the mining arrival point guidance strategy, points of interest determined by the heading angle guidance strategy, points of interest determined by the display road-grabbing guidance strategy, points of interest determined by the global mining high-credibility guidance strategy, and points of interest determined by the session mining high-credibility guidance strategy. Among them, the heading angle guidance strategy and the global mining high-credibility guidance strategy both obtain arrival points based on image mining of interest points, while the session mining high-credibility guidance strategy obtains arrival points based on user behavior mining. The mining arrival point guidance strategy is based on the arrival points obtained by the arrival point mining method proposed in the embodiment of the present disclosure. The credibility of the arrival points obtained by each of the above guidance strategies is relatively high, so the arrival points mined by the above guidance strategies can be used as the data basis for arrival point mining of the current target interest point.

[0070] In this embodiment, after obtaining the basic data of the building block where the target point of interest is located, other points of interest with credible destination locations can be screened out, and the orientation angles of the other points of interest can be determined based on their geographical locations and the locations of the arrival points. In some embodiments, the orientation angle can be defined as the angle between the orientation of the signs of the other points of interest and the orientation of the starting point; for example, with due north as the starting point, the angle of the orientation of the signs of the other points of interest rotated clockwise from the starting point is the orientation angle of the other points of interest. It should be noted that the starting point orientation can be determined according to actual conditions and is not specifically limited here.

[0071] In this embodiment, the orientation angles corresponding to other points of interest in the building block where the target point of interest is located are clustered. The resulting clustering results may include one or more clusters, each of which may include one or more members, each of which may be orientation angles corresponding to other points of interest. Each cluster may also include a cluster center. In some embodiments, a cluster with the largest number of members may be selected from the multiple clusters, and the cluster center of the cluster may be determined as the target orientation angle of the target point of interest.

[0072] In some embodiments, when clustering the orientation angles corresponding to other points of interest, clustering is performed based on the angular differences between the orientation angles. One or more orientation angles with similar angular differences (e.g., greater than a preset angular threshold) are clustered into one category, while one or more orientation angles with larger angular differences (less than or equal to the preset angular threshold) are clustered into different categories. Therefore, when a cluster has a large number of members, it can be understood that the orientation angles of the large number of points of interest within the building block are roughly similar. Therefore, the orientation angle of the target point of interest is likely close to these points of interest. Therefore, the cluster center of the cluster can be determined as the orientation angle of the target point of interest.

[0073] After determining the orientation angle of the target point of interest, the position of the target point of interest on the electronic map can be extended along the orientation angle, and the extended ray intersects with the road around the building block, and the arrival point of the target point of interest can be determined based on the intersection position.

[0074] The disclosed embodiment is aimed at a target point of interest for which there is no data. When mining the arrival point of the target point of interest, the arrival points of other points of interest in the building block where the target point of interest is located and the surrounding road data of the building block are obtained, and the orientation angles of the other points of interest are determined based on the arrival points of the other points of interest. Then, the orientation angles of the other points of interest are clustered to obtain a cluster with the largest number of members, and the cluster center of the cluster is determined as the orientation angle of the target point of interest; the arrival point of the target point of interest is determined based on the orientation angle of the target point of interest and the geographical location of the target point of interest. In this way, when there is no data to mine for the target point of interest, the orientation angle of the target point of interest can be obtained by referring to the orientation angles of other points of interest in the building block where the target point of interest is located, and the arrival point of the target point of interest can be mined based on the orientation angle, which can improve the accuracy of the arrival point of the target point of interest for which there is no data to rely on.

[0075] In an optional implementation of this embodiment, step S102, i.e., clustering the orientation angles of the other points of interest to obtain clusters, further includes the following steps:

[0076] Selecting one of the orientation angles of the other points of interest and clustering it with the existing clusters; if there is no existing cluster or it cannot be clustered into the existing clusters, generating a new cluster until all orientation angles are clustered into corresponding clusters;

[0077] Calculate the target cluster center of the generated cluster cluster, and re-cluster the orientation angles of the other points of interest according to the target cluster center. After clustering is completed, recalculate the target cluster center of the cluster cluster obtained by clustering, and repeat the previous step until the target cluster center no longer changes.

[0078] In this optional implementation, initial clustering can be performed on the orientation angles of all other points of interest. The initial clustering method can be to take any orientation angle as the cluster center of a cluster, and then compare other orientation angles with the cluster center of the cluster. If they can be clustered into one category, they are added to the cluster. If they cannot be clustered into one category, a new cluster is generated. Subsequent orientation angles are compared with the cluster centers of the existing clusters. If they cannot be clustered into one category, a new cluster is still generated, and so on, until all orientation angles are traversed, and one or more clusters obtained by the initial clustering are obtained.

[0079] For the initial clustering

[0080] One or more clusters are calculated, and the target cluster center is calculated respectively. All the orientation angles are compared with the existing target cluster center, and the orientation angle is clustered to the cluster where the closest target cluster center is located. The above steps are repeated until all the orientation angles are traversed. Then the target cluster center of each cluster is recalculated, and all the orientation angles are re-clustered until the target cluster center no longer changes.

[0081] The cluster corresponding to the target cluster center is the final cluster.

[0082] In an optional implementation of this embodiment, step S102, i.e., selecting one of the orientation angles of the other points of interest and clustering it with the existing cluster, generating a new cluster when there is no existing cluster or it cannot be clustered into an existing cluster, until all orientation angles are clustered into corresponding clusters, further includes the following steps:

[0083] Taking the orientation angle of one of the other interest points as a candidate cluster center of the initial cluster, and the remaining orientation angles of the other interest points constitute a queue of orientation angles to be clustered;

[0084] The orientation angle read from the queue of orientation angles to be clustered is used as the orientation angle to be clustered, and compared with the candidate cluster centers of the existing cluster clusters. The orientation angles to be clustered that meet the conditions are clustered into the cluster clusters, and for the orientation angles to be clustered that do not meet the conditions, a new cluster family is generated and used as the candidate cluster center of the new cluster cluster. The above steps are repeated until the orientation angles in the queue of orientation angles to be clustered are clustered into the corresponding cluster clusters.

[0085] In this optional implementation, the classic kmeans clustering algorithm is improved so that the number of clusters in the clustering result is not fixed. In the classic kmeans algorithm, the number of clusters is determined by a given k (less than or equal to k).

[0086] In this embodiment, one of the orientation angles of other points of interest is extracted as the candidate cluster center of the initial cluster; then, an orientation angle is extracted from the remaining orientation angles, and the extracted orientation angle is clustered with the candidate cluster center. If the extracted orientation angle can be clustered into the same category as the candidate cluster center, the extracted orientation angle is added to the cluster where the candidate cluster center is located. If they cannot be clustered into the same category, a new cluster is generated, and the extracted orientation angle is determined as the candidate cluster center of the new cluster. Repeat the above steps, cluster the remaining orientation angles with the candidate cluster centers of the generated clusters, and after the remaining orientation angles are traversed, one or more clusters can be obtained, and each cluster includes a candidate cluster center.

[0087] Then, for the generated one or more clusters, the target cluster center in each cluster is calculated. In some embodiments, the target cluster center can be obtained by calculating the average value of all members (ie, orientation angles) in the cluster.

[0088] After calculating the target cluster center for each cluster, all the orientation angles of other points of interest can be clustered again. That is, all orientation angles can be clustered with all target cluster centers. For orientation angles that cannot be clustered with any target cluster center, new clusters can be generated. Repeat this step. After all orientation angles have been clustered with the target cluster center in the above steps, the target cluster center in each cluster is calculated again, and each orientation angle is clustered with the new target cluster center. This process continues until the target cluster center no longer changes position.

[0089] In an optional implementation of this embodiment, the step of taking the orientation angles read from the queue of orientation angles to be clustered as the orientation angles to be clustered, comparing them with the candidate cluster centers of the existing clusters, and clustering the orientation angles to be clustered that meet the conditions into the clusters further includes the following steps:

[0090] When the angle difference between the orientation angle to be clustered and the candidate cluster center is less than or equal to a preset angle value, the orientation angle to be clustered and the candidate cluster center are clustered into the cluster cluster.

[0091] In this optional implementation, during the clustering process, by adding an angular difference limit between the orientation angle to be clustered and the cluster center, the number of clusters can be dynamically changed according to actual conditions. That is, during the clustering process, when the angular difference between the orientation angle to be clustered and the cluster center of a cluster is less than or equal to a preset angle value, the orientation angle to be clustered is clustered to the cluster center. When the angular difference between the orientation angle to be clustered and the cluster center is greater than the preset angle value, the orientation angle cluster to be clustered is not clustered with the cluster center. In some embodiments, the preset angle value can be set according to actual needs, for example, it can be set to 15 degrees.

[0092] When the angle difference between the orientation angle to be clustered and the candidate cluster center is greater than the preset angle value, the orientation angle to be clustered and the candidate cluster center are clustered into different clusters.

[0093] This embodiment is based on the idea of ​​the kmeans clustering algorithm, which ensures the dynamic balance of the final clustering result, so that the clustering result achieves the expected effect.

[0094] Figure 2 FIG. 1 shows a flow chart of an improved kmeans clustering algorithm according to an embodiment of the present disclosure. Figure 2 As shown, the method includes the following steps:

[0095] In step S201, an initial orientation angle queue A is constructed based on the orientation angles of other points of interest.

[0096] In step S202, an angle b1 is randomly extracted (in some other embodiments, it can also be extracted by other means) from the initial orientation angle queue and used as the candidate cluster center of the cluster cluster in the current clustering result. The remaining orientation angles constitute the orientation angle queue S1 to be clustered.

[0097] In step S203, an angle b2 is randomly extracted from S1. If the angle difference between b2 and b1 is less than or equal to 15 degrees, (b1, b2) are clustered into a cluster, and b1 is still the candidate cluster center of the cluster. If the angle difference between b2 and b1 is greater than 15 degrees, (b2) is generated as a separate cluster, and the candidate cluster center of the cluster is b2. At this time, two clusters are generated, namely (b1) and (b2), and b1 is one cluster center and b2 is the other cluster center.

[0098] In step S204, it is determined whether S1 is empty. If it is not empty, the operation in step 203 is repeated to traverse the angles in S1; if it is empty, go to step S205.

[0099] In step S205, for all generated clusters, the cluster center of each cluster is calculated (for example, the cluster center can be obtained by calculating the average value of the orientation angles in each cluster), and then all the orientation angles in the initial orientation angle queue A are re-clustered according to the cluster center calculated above. This clustering method is similar to the above 3. It is determined whether the angle difference between the orientation angle and the cluster center is less than or equal to 15 degrees to determine whether it can be clustered into the cluster where the cluster center is located. For orientation angles that cannot be clustered into a cluster with any cluster center, a new cluster can be regenerated.

[0100] In step S206, it is determined whether the obtained cluster center has changed compared with the previous time. If so, step 205 is repeated until the obtained cluster center no longer changes; if not, the process goes to step S207.

[0101] In step S207 , a clustering result is output; the clustering result includes all members in the cluster (ie, the orientation angles clustered into the cluster) and the cluster center.

[0102] In an optional implementation of this embodiment, the method further includes the following steps:

[0103] When the difference between the number of members of the cluster with the largest number of members and the number of members of the cluster with the second largest number of members is within a preset range, the arrival point of the target point of interest is filtered.

[0104] In this optional implementation, after the arrival point of the target point of interest is mined based on the arrival points of other points of interest with reliable destination locations within the same building block and the road data surrounding the building block, in order to further improve the accuracy of the arrival point, the mined arrival points can be filtered to remove arrival points with insufficient accuracy. It should be noted that for the target point of interest that has been filtered out, its arrival point can be restored to the arrival point obtained by displaying the captured image.

[0105] In some embodiments, one filtering method is to filter the arrival points of the target point of interest based on a comparison result between the number of members of the cluster with the largest number of members and the number of members of the cluster with the second largest number of members. In this method, if, among the multiple generated clusters, the number of members of the first cluster with the largest number of members and the second cluster with the second largest number of members is similar, for example, the difference is within 3, then the orientation angle of the target point of interest may be consistent with the cluster center of the first cluster or the cluster center of the second cluster. In order to avoid errors in the arrival points mined for the target point of interest, the arrival points of the target point of interest can be filtered.

[0106] In an optional implementation of this embodiment, the method further includes the following steps:

[0107] When the length of the first side where the line between the arrival point of the target point of interest and the geographic location of the target point of interest intersects with the building block boundary is greater than or equal to the length of the second side where the line between the initial end position of the target point of interest and the geographic location of the target point of interest intersects with the building block boundary, the arrival point of the target point of interest is filtered.

[0108] In this optional implementation, after the arrival point of the target point of interest is mined based on the arrival points of other points of interest with reliable destination locations within the same building block and the road data surrounding the building block, in order to further improve the accuracy of the arrival point, the mined arrival points can be filtered to remove arrival points with insufficient accuracy. It should be noted that for the target point of interest that has been filtered out, its arrival point can be restored to the arrival point obtained by displaying the captured image.

[0109] In some embodiments, one filtering method is to filter the arrival points of the target POI based on a comparison between the length of a first side of a line connecting the arrival point of the target POI and its geographic location and the building block boundary, and the length of a second side of a line connecting the initial destination location of the target POI and its geographic location and the building block boundary. In this method, if the side of the line connecting the arrival point to the target POI at the building block boundary is shorter, for example, longer than the length of the side of the line connecting the initial destination location to the target POI at the building block boundary, the arrival point can be considered to have low accuracy and can be filtered.

[0110] In an optional implementation of this embodiment, the method further includes at least one of the following steps:

[0111] filtering the arrival points of the target point of interest based on the type of the target point of interest;

[0112] filtering the arrival point of the target point of interest based on a comparison result of a first distance between the geographic location of the target point of interest and the arrival point of the target point of interest and a second distance between the geographic location of the target point of interest and an initial destination position of the target point of interest; the initial destination position being the initial arrival point of the target point of interest predetermined based on map data;

[0113] filtering the arrival point of the target point of interest based on whether a line between the target point of interest and the arrival point of the target point of interest crosses other building blocks;

[0114] The arrival point of the target point of interest is filtered based on a comparison result between the attribute of the road where the arrival point of the target point of interest is located and the attribute of the road where the initial destination position of the target point of interest is located.

[0115] In this optional implementation, after the arrival point of the target point of interest is mined based on the arrival points of other points of interest with reliable destination locations within the same building block and the road data surrounding the building block, in order to further improve the accuracy of the arrival point, the mined arrival points can be filtered to remove arrival points with insufficient accuracy. It should be noted that for the target point of interest that has been filtered out, its arrival point can be restored to the arrival point obtained by displaying the captured image.

[0116] The filtering method also includes one or more combinations of the following methods:

[0117] 1. Filter the arrival points of a target POI based on its type. In this method, if the type of the target POI is known, it can be filtered based on the matching degree between the type and the arrival points. The type of the target POI can be, for example, a scenic spot, a transportation facility, a place name, or an address.

[0118] 2. Filter the arrival points of the target POI based on a comparison of the first distance between the geographic location of the target POI and the arrival point of the target POI, and the second distance between the geographic location of the target POI and the initial destination location of the target POI; the initial destination location is the initial arrival point of the target POI pre-determined based on the map data. In this method, the initial destination location is the arrival point obtained by displaying the screenshot. If the straight-line distance between the discovered arrival point and the target POI is longer than the straight-line distance between the initial destination location and the target POI obtained by displaying the screenshot, there is a high probability that the discovered arrival point is incorrect, and therefore the arrival point of the target POI is filtered.

[0119] 3. Filter the arrival points of the target POI based on whether the line connecting the target POI and the arrival point of the target POI crosses other buildings. In this way, if the line connecting the mined arrival point and the target POI crosses other buildings, it can be considered that the mined arrival point is far from the target POI and needs to bypass other buildings. Therefore, the arrival point is likely to be incorrect and can be filtered out.

[0120] 4. Filter the arrival points of the target POI based on the attributes of the road where the arrival point is located. In this method, the arrival point is more accurately located on a public road. Therefore, the accuracy of the arrival point can be determined by determining the attributes of the road where the discovered arrival point is located. If the attributes of the road where the arrival point is located do not meet the pre-set settings, such as if the road is not a public road, the arrival point can be filtered. In some embodiments, the attributes of the road where the discovered arrival point is located can also be compared with the attributes of the initial destination location obtained by displaying the captured image. If the attributes do not match, the discovered arrival point can be filtered.

[0121] In an optional implementation of this embodiment, the method further includes the following steps:

[0122] When the road where the arrival point of the target point of interest is located intersects the road where the initial destination location of the target point of interest is located, and the distances between the arrival point of the target point of interest and the initial destination location and the intersection are both less than a preset distance threshold, the arrival point of the target point of interest is updated to the location of the intersection. In this optional implementation, to improve the accuracy of the arrival point, the arrival point mined using the method described above can also be moved to a more accurate new arrival point through optimized relocation.

[0123] In some embodiments, the method of optimizing the displacement includes at least the following methods:

[0124] When the road where the arrival point of the target point of interest is located intersects the road where the initial end point of the target point of interest is located, and the distances between the arrival point and the initial end point and the intersection are all less than a preset distance threshold, the position of the arrival point is updated to the position of the intersection.

[0125] In an optional implementation of this embodiment, the method further includes the following steps:

[0126] If the road where the arrival point of the target point of interest is located is a road with separated upper and lower lines, and the first distance from the downstream node of the road where the arrival point is located to the arrival point is less than or equal to a first distance threshold, and the second distance from the upstream node of the road where the arrival point is located to the arrival point is greater than or equal to a second distance threshold, then the arrival point is updated to the location of the downstream node.

[0127] In some embodiments, the method of optimizing the displacement includes at least the following methods:

[0128] When the road where the arrival point of the mined target point of interest is located is a road with separated upper and lower lines, and the first distance from the downstream node of the road where the arrival point is located to the arrival point is less than or equal to the first distance threshold, and the second distance from the upstream node of the road where the arrival point is located to the arrival point is greater than or equal to the second distance threshold, the arrival point is updated to the location of the downstream node. Among them, the road with separated upper and lower lines refers to a road with a barrier between the upward road and the downward road, or the road is a highway or the like, that is, it is impossible to turn around directly from the upward road or the downward road to the opposite downward road or upward road, but it is necessary to detour to the upstream node to turn around. The upstream node can be understood as the intersection with other roads in front of the road, and the downstream node can be understood as the intersection with other roads behind the road.

[0129] In an optional implementation of this embodiment, the step of determining the arrival point of the target point of interest based on the position where the extended point intersects with the surrounding roads in step S104 further includes the following steps:

[0130] Among the multiple location points intersecting with the surrounding roads after extension, the location point with the shortest geographical location distance to the target point of interest is determined as the arrival point.

[0131] In this optional method, after determining the orientation angle of the target POI, a ray is extended outward from the displayed location of the target POI on the map in the direction of the orientation angle to find the intersection with the roads surrounding the building. Typically, this extension will result in more than one intersection with the road; for example, in the case of multiple parallel roads, multiple intersections may be obtained. Among these obtained road intersections, the road intersection with the shortest line segment connecting the displayed location and the road intersection is found and used as the target POI's arrival point.

[0132] According to an embodiment of the present disclosure, a location-based service providing method includes: using the arrival point determined by the above-mentioned arrival point mining method to provide location-based services to the service object, and the location-based services include: one or more of navigation, map rendering, and route planning.

[0133] In this embodiment, the location-based service provision method can be executed on a terminal, which can be a mobile phone, iPad, computer, smart watch, vehicle, etc. In this disclosed embodiment, for a target point of interest on an electronic map, the arrival point of the target point of interest is mined using the arrival point mining method mentioned above. During the location-based service process, the arrival point can be used to guide the service recipient to the vicinity of the target point of interest, so that the service recipient can accurately locate the target point of interest after arriving at the arrival point.

[0134] The served object can be a mobile phone, iPad, computer, smart watch, vehicle, robot, etc. In the process of guiding the served object, the arrival point obtained by the above-mentioned arrival point mining method can be used for guidance. For details, please refer to the above description of the arrival point mining method, which will not be repeated here.

[0135] Figure 3 The following is a schematic diagram showing an application scenario of a method for mining arrival points of shops without data according to an embodiment of the present disclosure. Figure 3 As shown, when mining for basement entrances with no data for a specific business district in City A, the server collects basic data for that business district. This basic data may include, but is not limited to, manual arrival point guidance strategy POIs, mined arrival point guidance strategy POIs, orientation angle guidance strategy POIs, displayed road tracking guidance strategy POIs, high-confidence arrival point POIs (including globally mined high-confidence POIs and session-mined high-confidence POIs), basic road information (road network information and node information), and basic building information (rendered building blocks and satellite building blocks). The above-mentioned POIs refer to POIs whose arrival points have been obtained based on corresponding guidance strategies. For example, manual arrival guidance strategy POIs are POIs that obtain their arrival points manually. Some POIs' guidance strategies are more reliable because they use data related to the POI to obtain their arrival points, while some POIs' guidance strategies are less reliable because no data is available. In this solution, POIs with reliable arrival points are referred to as basement entrances with data, while POIs with unreliable arrival points are referred to as basement entrances without data.

[0136] After collecting the aforementioned basic data, the server processes it. During this processing, it first distinguishes between basement POIs with data and those without data within the same building. Basement POIs without data primarily include those with the displayed road tracking strategy collected from the aforementioned basic data. POIs with the manual arrival point guidance strategy, the mining arrival point guidance strategy, and the orientation angle guidance strategy are considered to have mining strategies and are therefore considered to have data. Furthermore, high-confidence POIs mined globally and through session mining are also considered to have data.

[0137] The server also calculates the orientation angle of each basement POI with data based on the road data, node information and information about other surrounding buildings around each building in the basic data. The orientation angle can be determined based on the direction of the ray corresponding to the line connecting the POI's displayed position on the electronic map and the known arrival point. For example, the north direction can be preset to 0 degrees, and the angle increases in a clockwise direction.

[0138] The server also mines the arrival points of basement POIs without data based on the orientation angles of the basement POIs with data, including:

[0139] The improved kmeans clustering algorithm is applied to the orientation angles of all the ground floor POIs with data in the same building to generate multiple clusters. The number of clusters is not fixed, and each cluster includes multiple members, each of which is the orientation angle of a ground floor POI with data.

[0140] The cluster center of the cluster with the largest number of members is determined as the orientation angle of the POI with no data.

[0141] Draw a ray based on the displayed coordinates and orientation angle of the undocumented basement POI on the map, calculate the intersection of the ray and the roads around the building, find the intersection with the displayed coordinates and the shortest line segment between multiple intersections, determine it as the excavation arrival point for the undocumented basement POI, and save the road attributes of the road where the excavation arrival point is located.

[0142] The above mining process is executed for all buildings in the business district to obtain the mining arrival points of all the ground floor POIs with no data in the buildings.

[0143] The server further filters and optimizes the mined arrival points. During the filtering process, potentially erroneous mined arrival points are deleted, and the arrival points of the undocumented basement POIs are restored to those obtained using the road tracking strategy. During the optimization process, to avoid detours, the mined arrival points are relocated to more optimal locations using an optimization strategy, ultimately resulting in the arrival points for the undocumented basement POIs of each building within the commercial district.

[0144] The following are embodiments of the apparatus disclosed herein, which can be used to execute embodiments of the method disclosed herein.

[0145] Figure 4 The block diagram of the structure of the arrival point mining device according to one embodiment of the present disclosure is shown. The device can be implemented as part or all of an electronic device through software, hardware or a combination of both. Figure 4 As shown, the arrival point excavation device includes:

[0146] The acquisition module 401 is configured to acquire basic data of the building block where the target point of interest of the arrival point to be mined is located; the basic data includes the arrival point of at least one other point of interest with a reliable terminal position in the building block and the surrounding road data of the building block;

[0147] The clustering module 402 is configured to cluster the orientation angles of the other points of interest to obtain clusters; wherein the orientation angles of the other points of interest are determined based on the geographical locations of the other points of interest and the arrival points of the other points of interest;

[0148] The first determining module 403 is configured to determine the cluster center of the cluster with the largest number of cluster members as the target orientation angle of the target interest point;

[0149] The second determining module 404 is configured to extend the geographical location of the target point of interest along the direction of the target heading angle, and determine the arrival point of the target point of interest based on a position where the extended geographical location intersects with surrounding roads.

[0150] In an optional implementation of this embodiment, the clustering module includes:

[0151] an initial clustering submodule configured to select one of the orientation angles of the other points of interest and cluster it with the existing clusters; and to generate a new cluster when there is no existing cluster or the point of interest cannot be clustered into an existing cluster, until all orientation angles are clustered into corresponding clusters;

[0152] The optimization clustering submodule is configured to calculate the target cluster center of the generated cluster cluster, and re-cluster the orientation angles of the other points of interest according to the target cluster center. After clustering is completed, the target cluster center of the cluster cluster obtained by clustering is recalculated, and the previous step is repeated until the target cluster center no longer changes.

[0153] In an optional implementation of this embodiment, the initial clustering submodule includes:

[0154] a constituting submodule configured to use the orientation angle of one of the other interest points as a candidate cluster center of an initial cluster, and the remaining orientation angles of the other interest points constitute an orientation angle queue to be clustered;

[0155] The reading submodule is configured to take the orientation angle read from the queue of orientation angles to be clustered as the orientation angle to be clustered, compare it with the candidate clustering center of the existing clustering cluster, cluster the orientation angle to be clustered that meets the conditions into the clustering cluster, and generate a new cluster family for the orientation angle to be clustered that does not meet the conditions, and use it as the candidate clustering center of the new clustering cluster, repeating the above steps until the orientation angles in the queue of orientation angles to be clustered are clustered into the corresponding clustering cluster.

[0156] In an optional implementation of this embodiment, the reading submodule includes:

[0157] The clustering submodule is configured to cluster the orientation angle to be clustered and the candidate cluster center into the cluster cluster when the angle difference between the orientation angle to be clustered and the candidate cluster center is less than or equal to a preset angle value.

[0158] In an optional implementation of this embodiment, the apparatus further includes:

[0159] The first filtering module is configured to filter the arrival point of the target point of interest when the difference between the number of members of the cluster with the largest number of members and the number of members of the cluster with the second largest number of members is within a preset range.

[0160] In an optional implementation of this embodiment, the apparatus further includes:

[0161] The second filtering module is configured to filter the arrival point of the target interest point based on the comparison result between the length of the first side of the line between the arrival point of the target interest point and the geographical location of the target interest point and the boundary of the building block, and the length of the second side of the line between the initial end position of the target interest point and the geographical location of the target interest point and the boundary of the building block.

[0162] In an optional implementation of this embodiment, the apparatus further includes at least one of the following:

[0163] a third filtering module, configured to filter the arrival points of the target POI based on the type of the target POI;

[0164] a fourth filtering module configured to filter the arrival point of the target point of interest based on a comparison result of a first distance between the geographic location of the target point of interest and the arrival point of the target point of interest and a second distance between the geographic location of the target point of interest and an initial destination position of the target point of interest; the initial destination position being the initial arrival point of the target point of interest predetermined based on map data;

[0165] a fifth filtering module configured to filter the arrival point of the target point of interest based on whether a line between the target point of interest and the arrival point of the target point of interest crosses other building blocks;

[0166] The sixth filtering module is configured to filter the arrival point of the target point of interest based on the attribute of the road where the arrival point of the target point of interest is located.

[0167] In an optional implementation of this embodiment, the apparatus further includes:

[0168] The first updating module is configured to update the arrival point of the target point of interest to the position of the intersection when the road where the arrival point of the target point of interest is located intersects the road where the initial end position of the target point of interest is located, and the distances between the arrival point of the target point of interest and the initial end position and the intersection are all less than a preset distance threshold.

[0169] In an optional implementation of this embodiment, the apparatus further includes:

[0170] The second updating module is configured to update the arrival point of the target point of interest to the location of the downstream node when the road where the arrival point is located is a road with separated upper and lower lines, and the first distance from the downstream node of the road where the arrival point is located to the arrival point is less than or equal to the first distance threshold, and the second distance from the upstream node of the road where the arrival point is located to the arrival point is greater than or equal to the second distance threshold.

[0171] In an optional implementation of this embodiment, the second determining module includes:

[0172] The determination submodule is configured to determine, among the multiple location points intersecting with the surrounding roads after extension, the location point with the shortest geographical distance to the target point of interest as the arrival point.

[0173] The arrival point excavation device in this embodiment corresponds to the arrival point excavation method described above. For specific details, please refer to the above description of the arrival point excavation method, which will not be repeated here.

[0174] According to an embodiment of the present disclosure, a location-based service providing device can be implemented as part or all of an electronic device through software, hardware, or a combination of both. The location-based service providing device uses the arrival points determined by the arrival point mining device to provide location-based services to the service recipients. The location-based services include one or more of navigation, map rendering, and route planning.

[0175] The location-based service providing apparatus in this embodiment corresponds to the location-based service providing method described above. For specific details, please refer to the description of the location-based service providing method described above, which will not be repeated here.

[0176] Figure 5 It is a structural diagram of an electronic device suitable for implementing the arrival point mining and / or location-based service providing method according to an embodiment of the present disclosure.

[0177] like Figure 5 As shown, the electronic device 500 includes a processing unit 501, which can be implemented as a processing unit such as a CPU, a GPU, an FPGA, an NPU, etc. The processing unit 501 can perform various processes in the embodiment of any of the above methods of the present disclosure according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage portion 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the electronic device 500 are also stored. The processing unit 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0178] The following components are connected to the I / O interface 505: an input section 506 including a keyboard, a mouse, and the like; an output section 507 including devices such as a cathode ray tube (CRT), a liquid crystal display (LCD), and a speaker; a storage section 508 including a hard disk; and a communication section 509 including a network interface card such as a LAN card or a modem. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the I / O interface 505 as needed. A removable medium 511, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 510 as needed, so that computer programs read therefrom can be installed into the storage section 508 as needed.

[0179] In particular, according to embodiments of the present disclosure, any of the methods described above with reference to the embodiments of the present disclosure may be implemented as a computer software program. For example, embodiments of the present disclosure include a computer program product comprising a computer program tangibly embodied on a machine-readable medium, the computer program comprising program code for executing any of the methods described in the embodiments of the present disclosure. In such embodiments, the computer program may be downloaded and installed from a network via the communication portion 509 and / or installed from a removable medium 511.

[0180] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the diagram or block diagram can represent a module, program segment or part of the code, and the module, program segment or part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, as well as the combination of boxes in the block diagram and / or flow chart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or can be implemented using a combination of dedicated hardware and computer instructions.

[0181] The units or modules described in the embodiments of the present disclosure may be implemented in software or hardware. The units or modules described may also be provided in a processor, and the names of these units or modules do not, in certain circumstances, limit the units or modules themselves.

[0182] As another aspect, the present disclosure further provides a computer-readable storage medium. This computer-readable storage medium may be included in the apparatus described in the above embodiments, or may be a standalone computer-readable storage medium not incorporated into the apparatus. The computer-readable storage medium stores one or more programs, which are used by one or more processors to execute the methods described in the present disclosure.

[0183] The above description is merely a preferred embodiment of the present disclosure and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of the invention herein is not limited to the technical solutions formed by the specific combination of the above-mentioned technical features, but also encompasses other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the inventive concept. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions disclosed in this disclosure.

Claims

1. A method for mining an arrival point, wherein: include: Obtain basic data of the building block where the target point of interest to be mined is located, where the target point of interest is a point of interest with no data; The basic data includes the arrival points of other points of interest with a credible terminal position in at least one of the building blocks and the surrounding road data of the building block; Clustering the orientation angles of the other points of interest to obtain clusters; wherein the orientation angles of the other points of interest are determined based on the geographical locations of the other points of interest and the arrival points of the other points of interest; Determining the cluster center of the cluster with the largest number of cluster members as the target orientation angle of the target point of interest; The geographical location of the target point of interest is extended in the direction of the target heading angle, and an arrival point of the target point of interest is determined based on a position where the extended geographical location intersects with surrounding roads.

2. The method according to claim 1, wherein Clustering the orientation angles of the other points of interest to obtain clusters includes: Selecting one of the orientation angles of the other points of interest and clustering it with the existing clusters; if there is no existing cluster or it cannot be clustered into the existing clusters, generating a new cluster until all orientation angles are clustered into corresponding clusters; Calculate the target cluster center of the generated cluster cluster, and re-cluster the orientation angles of the other points of interest according to the target cluster center. After clustering is completed, recalculate the target cluster center of the cluster cluster obtained by clustering, and repeat the previous step until the target cluster center no longer changes.

3. The method according to claim 1, wherein Select one of the orientation angles of the other points of interest and cluster it with the existing cluster. If there is no existing cluster or it cannot be clustered into an existing cluster, generate a new cluster until all orientation angles are clustered into corresponding clusters, including the following steps: Taking the orientation angle of one of the other interest points as a candidate cluster center of the initial cluster, and the remaining orientation angles of the other interest points constitute a queue of orientation angles to be clustered; The orientation angle read from the queue of orientation angles to be clustered is used as the orientation angle to be clustered, and compared with the candidate cluster center of the existing cluster cluster. The orientation angle to be clustered that meets the conditions is clustered into the cluster cluster, and for the orientation angle to be clustered that does not meet the conditions, a new cluster cluster is generated and used as the candidate cluster center of the new cluster cluster. The above steps are repeated until the orientation angles in the queue of orientation angles to be clustered are clustered into the corresponding cluster cluster.

4. The method according to claim 3, wherein: The orientation angles read from the queue of orientation angles to be clustered are used as orientation angles to be clustered, compared with the candidate cluster centers of the existing clusters, and the orientation angles to be clustered that meet the conditions are clustered into the clusters, including: When the angle difference between the orientation angle to be clustered and the candidate cluster center is less than or equal to a preset angle value, the orientation angle to be clustered and the candidate cluster center are clustered into the cluster cluster.

5. The method according to any one of claims 1 to 3, wherein: The method further comprises: When the difference between the number of members of the cluster with the largest number of members and the number of members of the cluster with the second largest number of members is within a preset range, the arrival point of the target point of interest is filtered.

6. The method according to any one of claims 1 to 3, wherein: The method further comprises: When the length of the first side where the line between the arrival point of the target point of interest and the geographic location of the target point of interest intersects with the building block boundary is greater than or equal to the length of the second side where the line between the initial end position of the target point of interest and the geographic location of the target point of interest intersects with the building block boundary, the arrival point of the target point of interest is filtered.

7. The method according to any one of claims 1 to 3, wherein: The method further comprises at least one of the following: When the types of the target point of interest do not match those of the arrival point, filtering the arrival point of the target point of interest; filtering the arrival point of the target point of interest when a first distance between the geographic location of the target point of interest and the arrival point of the target point of interest is greater than or equal to a second distance between the geographic location of the target point of interest and an initial destination location of the target point of interest; the initial destination location being the initial arrival point of the target point of interest predetermined based on map data; When a line between the target point of interest and the arrival point of the target point of interest crosses other building blocks, filtering the arrival point of the target point of interest; When the attribute of the road where the arrival point of the target point of interest is located does not meet the preset attribute, the arrival point of the target point of interest is filtered.

8. The method according to any one of claims 1 to 3, wherein: The method further comprises: When the road where the arrival point of the target point of interest is located intersects with the road where the initial end position of the target point of interest is located, and the distances between the arrival point of the target point of interest and the initial end position and the intersection are all less than a preset distance threshold, the arrival point of the target point of interest is updated to the position of the intersection.

9. The method according to any one of claims 1 to 3, wherein: The method further comprises: If the road where the arrival point of the target point of interest is located is a road with separated upper and lower lines, and the first distance from the downstream node of the road where the arrival point is located to the arrival point is less than or equal to a first distance threshold, and the second distance from the upstream node of the road where the arrival point is located to the arrival point is greater than or equal to a second distance threshold, then the arrival point is updated to the location of the downstream node.

10. The method according to any one of claims 1 to 3, wherein: Determining the arrival point of the target point of interest based on the position where the extended point intersects with the surrounding roads includes: Among the multiple location points intersecting with the surrounding roads after extension, the location point with the shortest geographical location distance to the target point of interest is determined as the arrival point.

11. A method for providing location-based services, wherein: The method provides location-based services for a service recipient using the arrival point determined by the method according to any one of claims 1 to 10. The location-based services include one or more of navigation, map rendering, and route planning.

12. A computer program product comprising computer instructions, wherein: When the computer instructions are executed by a processor, the method according to any one of claims 1 to 10 is implemented.

Images