A point recommendation method, device and electronic device

Abstract

Embodiments of the present invention disclose a point recommendation method, apparatus, and electronic device. By obtaining a target location, in response to the target location being a low-heat location, obtaining the boarding and alighting data and trajectory information corresponding to the target location, recalling at least one recommended point based on the boarding and alighting data and trajectory information of the target location, and controlling the point recall page of the user terminal to display at least one of the recommended points. Thus, when the target location is a low-heat location with insufficient historical data, the boarding and alighting points can be used interchangeably in the embodiments of the present invention, and the trajectory information is used as supplementary information for point recall, enriching the number of recallable points, improving the accuracy of point recommendation for low-heat locations, and further improving the user experience.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and more particularly, to a point recommendation method, device, and electronic device. Background Art

[0002] In transportation application scenarios, such as the online car-hailing scenario, the recommendation of pick-up and drop-off points often requires sufficient popularity information. However, in actual applications, there are a large number of low-popularity scenarios (such as newly added or low-popularity destinations), and there is not enough pick-up and drop-off behavior popularity information available for these low-popularity scenarios, making it difficult to recommend to reasonable locations. Summary of the Invention

[0003] In view of this, embodiments of the present invention provide a point recommendation method, device, and electronic device, so that when the target location is a low-popularity location with insufficient historical data, the pick-up and drop-off points can be interoperable, and the trajectory information is used as supplementary information for point recall, enriching the number of recallable points, improving the accuracy of point recommendation for low-popularity locations, and thus improving the user experience.

[0004] In a first aspect, an embodiment of the present invention provides a point recommendation method, the method including:

[0005] Obtain a target location;

[0006] In response to the target location being a low-popularity location, obtain the pick-up and drop-off data and trajectory information corresponding to the target location;

[0007] Determine at least one recommended point according to the pick-up and drop-off data and the trajectory information;

[0008] Control the point recall page of the user terminal to display at least one of the recommended points.

[0009] Further, the obtaining the pick-up and drop-off data and trajectory information corresponding to the target location includes:

[0010] Determine the grid area where the target location is located and the contour area of the target location, where the grid area is a geographical area with a predetermined size;

[0011] Obtain the pick-up and drop-off behaviors corresponding to the grid area and the pick-up and drop-off behaviors corresponding to the contour area to obtain the pick-up and drop-off data;

[0012] Obtain the trajectory data within a predetermined range of the target location to obtain the trajectory information.

[0013] Further, the determining at least one recommended point according to the pick-up and drop-off data and the trajectory information includes:

[0014] Aggregate each of the getting-on and off behaviors based on the corresponding point pairs of the getting-on and off behaviors to obtain a first candidate point set;

[0015] Sample the trajectory points of each trajectory in the trajectory information to obtain a second candidate point set;

[0016] Obtain the recommended points from the first candidate point set and the second candidate point set.

[0017] Further, the sampling the trajectory points in the trajectory information to obtain a second candidate point set includes:

[0018] Cluster the trajectory points of each trajectory in the trajectory information to obtain a staying area corresponding to each trajectory;

[0019] Sample the trajectory points in each of the staying areas to obtain the second candidate point set.

[0020] Further, the obtaining the recommended points from the first candidate point set and the second candidate point set includes:

[0021] Sort each of the candidate points according to the distance information and / or popularity information corresponding to the candidate points in the first candidate point set and the second candidate point set;

[0022] Determine a predetermined number of the candidate points ranked at the front as the recommended points.

[0023] Further, the method further includes:

[0024] Determine the fusion feature of each of the recommended points according to the feature of each of the recommended points, and the feature of the related points of each of the recommended points, and / or the trajectory feature corresponding to each of the recommended points;

[0025] Sort each of the recommended points according to the fusion feature to obtain a recommended order;

[0026] Push each of the recommended points to the point recall page of the user terminal based on the recommended order.

[0027] Further, the method further includes:

[0028] In response to that the online time of the target location is less than a predetermined duration and / or the location popularity of the target location is less than a predetermined popularity threshold, determine that the target location is a low-heat location.

[0029] In a second aspect, an embodiment of the present invention provides a point recommendation device, and the device includes:

[0030] A location acquisition unit configured to acquire a target location;

[0031] An information acquisition unit, configured to acquire alighting and boarding data and trajectory information corresponding to the target location in response to the target location being a low-temperature location;

[0032] A recommended point determination unit, configured to determine at least one recommended point according to the alighting and boarding data and the trajectory information;

[0033] A control unit, configured to control a point recall page of the user terminal to display at least one of the recommended points.

[0034] In a third aspect, an embodiment of the present invention provides an electronic device, including a memory and a processor, where the memory is used to store one or more computer program instructions, and wherein the one or more computer program instructions are executed by the processor to implement the method as described above.

[0035] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the method as described above is implemented.

[0036] In a fifth aspect, an embodiment of the present invention provides a computer program product, which when running on a computer causes the computer to execute the method as described above.

[0037] In the embodiment of the present invention, by acquiring a target location, in response to the target location being a low-temperature location, acquiring alighting and boarding data and trajectory information corresponding to the target location, recalling at least one recommended point according to the alighting and boarding data and the trajectory information of the target location, and controlling a point recall page of the user terminal to display at least one of the recommended points. Thus, in the embodiment of the present invention, when the target location is a low-temperature location with insufficient historical data, the alighting and boarding points can be used interchangeably, and the trajectory information is used as supplementary information for point recall, enriching the number of recallable points, improving the accuracy of point recommendation at low-temperature locations, and further improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Through the following description of the embodiments of the present invention with reference to the drawings, the above and other objects, features, and advantages of the present invention will become clearer. In the drawings:

[0039] Figure 1 is a flowchart of a point recommendation method according to an embodiment of the present invention;

[0040] Figure 2 is a flowchart of a data information acquisition method according to an embodiment of the present invention;

[0041] Figure 3 is a flowchart of a recommended point determination method according to an embodiment of the present invention;

[0042] Figure 4 It is a schematic diagram of a candidate point determination process according to an embodiment of the present invention;

[0043] Figure 5 It is a schematic diagram of another candidate point determination process according to an embodiment of the present invention;

[0044] Figure 6 It is a schematic diagram of yet another candidate point determination process according to an embodiment of the present invention;

[0045] Figure 7 It is a schematic diagram of a recommended point determination method according to an embodiment of the present invention;

[0046] Figure 8 It is a schematic diagram of a method for determining the order of recommended points according to an embodiment of the present invention;

[0047] Figure 9 It is a schematic diagram of the point recommendation process according to an embodiment of the present invention;

[0048] Figure 10 It is a schematic diagram of the point recommendation device according to an embodiment of the present invention;

[0049] Figure 11 It is a schematic diagram of the electronic device according to an embodiment of the present invention. Detailed implementation manners

[0050] The following describes the present application based on embodiments, but the present application is not limited to these embodiments. In the following detailed description of the present application, some specific details are described in detail. Those skilled in the art can fully understand the present application without the description of these details. In order to avoid obscuring the essence of the present application, well-known methods, processes, procedures, elements, and circuits are not described in detail.

[0051] In addition, those of ordinary skill in the art should understand that the drawings provided herein are for illustrative purposes only, and the drawings are not necessarily drawn to scale.

[0052] Unless the context clearly requires otherwise, words such as "including" and "comprising" in the entire application document should be interpreted in an inclusive sense rather than an exclusive or exhaustive sense; that is, it is the meaning of "including but not limited to".

[0053] In the description of the present application, it should be understood that terms such as "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of the present application, unless otherwise specified, the meaning of "a plurality of" is two or more.

[0054] In the solutions described in this specification and the embodiments, if personal information processing is involved, it will be processed on the premise of having a legal basis (such as obtaining the consent of the personal information subject, or being necessary for the performance of a contract, etc.), and will only be processed within the specified or agreed scope. If the user refuses to process personal information other than the necessary information required for the basic functions, it will not affect the user's use of the basic functions.

[0055] The embodiments of the present invention are mainly described by taking the online car-hailing scenario as an example. It should be understood that the point recommendation method of the embodiments of the present invention can be used for point recommendation in other transportation scenarios that require determining points (such as express delivery, food delivery, freight transportation, etc.).

[0056] In the relevant comparative examples, the low-heat scenarios of online car-hailing often recommend points based on distance. Due to reasons such as fewer candidate points and less historical data, it may lead to the inability to find a reasonable location. For example, the recommended points do not reach the destination or there are situations such as crossing roads or walls, resulting in a poor user experience. In other comparative examples, the low-heat locations are recommended based on nearby high-heat destinations. However, due to the large differences in point requirements for different destinations, the recommended points may be deviated, resulting in a poor user experience. In view of this, the embodiments of the present invention provide a point recommendation method, device, and electronic device, so that when the target location is a low-heat location with insufficient historical data, the pick-up and drop-off points can be used interchangeably, and the trajectory information is used as supplementary information for point recall, enriching the number of recallable points, improving the accuracy of point recommendation for low-heat locations, and thus improving the user experience.

[0057] Figure 1 It is a flowchart of the point recommendation method of the embodiments of the present invention. It should be understood that the point recommendation method of the embodiments of the present invention can be run by the user terminal when running the corresponding application program and requiring point recommendation, or after obtaining the target location through the user terminal, the server executes the step of determining the recommended points and sends the recommended points to the user terminal for display. That is, this embodiment does not limit the specific execution end of the method, and it can be deployed according to the requirements of the specific application program. As Figure 1 shown, the point recommendation method of the embodiments of the present invention may include the following steps:

[0058] Step S110, obtain the target location. Optionally, taking online car-hailing as an example, in this embodiment, the target location input by the user can be obtained through the location input box on the user terminal page, or the target location input by the user's voice can be obtained through the voice input control on the user terminal page, or the historical location triggered by the user on the user terminal page can be obtained to obtain the target location. The embodiments of the present invention do not limit how to obtain the target location of the user's current trip, and any one that can be implemented in the current application program or any one that appears in the future development can be used.

[0059] Further, the target location in this embodiment can be the target starting point or the target ending point. Among them, if the target location is the target starting point, the recommended location is the recommended boarding point. If the target location is the target ending point, the recommended location is the recommended alighting point.

[0060] Step S120: In response to the target location being a low-heat location, obtain the boarding and alighting data and trajectory information corresponding to the target location. Herein, a location with a location heat less than a predetermined heat threshold is regarded as a low-heat location. Optionally, this embodiment can use the number of trips or trip frequency corresponding to the location to characterize the heat of the location. For example, this embodiment can regard a location with the corresponding number of trips (or trip frequency) less than a predetermined threshold as a low-heat location. A trip corresponding to a location is a trip with this location as the starting point or the ending point.

[0061] Further, since in the actual application scenario, the location status may change and the value of historical data with a long time is limited, therefore, the location heat in this embodiment can be determined according to the historical data within a recent predetermined time period to improve the effectiveness of the historical data and further improve the accuracy of the location heat. Herein, the location status can characterize the opening and closing status of the location. For example, a certain location has been in a closed state or a partially closed state since a certain date due to facility changes.

[0062] Further optionally, this embodiment can regard a newly added location as a low-heat location. Herein, a newly added location is a location with an online time less than a predetermined duration.

[0063] After obtaining the target location in this embodiment, it can be determined whether the target location is a low-heat location according to the online time or location heat of the target location.

[0064] Figure 2 is a flowchart of the data information acquisition method of the embodiment of the present invention. In an optional implementation manner, the data information such as the boarding and alighting data and trajectory information in the embodiment of the present invention is obtained through the following steps:

[0065] Step S121: Determine the grid area where the target location is located and the contour area of the target location. Herein, the grid area is a geographical area with a predetermined size. Further, the grid area where the target location is located can be a grid area obtained by expanding a predetermined range centered on the longitude and latitude of the target location, or a grid area where the target location falls after the overall division of the map.

[0066] In an alternative implementation, this embodiment can determine the historical boarding and alighting data and trajectory data within a predetermined range around the target location based on the coordinates of the target location, and preprocess the historical boarding and alighting data and trajectory data to remove outliers, noise points, etc. Then, perform clustering analysis on the preprocessed historical boarding and alighting data and trajectory data to obtain the main activity areas in the historical travel routes, extract boundary points (such as the edge points of the activity areas, etc.) based on the clustering results and trajectory data, and select key points from the boundary points that can better describe the contour shape. Based on the obtained key points, perform contour reconstruction to obtain the contour area of the target location. Optionally, this embodiment can use a convex hull algorithm or other sorting algorithms to arrange the extracted key points in a certain order, and perform interpolation (such as linear interpolation, spline interpolation, etc.) and fitting to achieve contour reconstruction and obtain the contour area of the target location. In other alternative implementations, this embodiment can also determine the contour of the location based on the contour key points of the location collected in advance. Among them, the contour key points can be extracted according to an edge detection algorithm or can be manually marked. It should be understood that this embodiment does not limit the determination method of the contour area of the target location, and any of the above implementations, or other existing or future-developed location contour parsing methods can be applied in the embodiments of the present invention.

[0067] Furthermore, the grid area and contour area of the target location in this embodiment can be determined and stored in advance, or can be determined in real time when there is a need for point recommendation. This embodiment does not limit this.

[0068] Step S122: Obtain the boarding and alighting behaviors corresponding to the grid area where the target location is located and the boarding and alighting behaviors corresponding to its contour area to obtain the boarding and alighting data.

[0069] The boarding and alighting behaviors corresponding to the grid area where the target location is located include the boarding and alighting behaviors within this grid area. The contour area of the target location, that is, the geographical area formed by the contour of the target location, the corresponding boarding and alighting behaviors can include the boarding and alighting behaviors within the contour area, or can also include the boarding and alighting behaviors within the area after expanding the contour area by a predetermined range.

[0070] The boarding and alighting behaviors include the boarding behavior with the target location as the starting point and the boarding point within the grid area of the target location, and the alighting behavior with the target location as the ending point and the alighting point within the grid area of the target location. In another alternative implementation, the boarding and alighting behaviors can also include the boarding or alighting behavior with an associated location of the target location as the starting point or ending point. Among them, the associated location of the target location can be a location inside the target location, or a location containing the target location, or a location adjacent to the target location, etc.

[0071] Further, the getting-on and getting-off behaviors in this embodiment may further include the getting-on behavior and the getting-off behavior actively reported by the user. For example, if a new location is launched in the application, a reporting entry may be provided for the new location, so that the user can report the getting-on location starting from the new location or the getting-off location ending at the new location based on the reporting entry.

[0072] This embodiment aggregates the getting-on and getting-off behaviors corresponding to the historical trip information obtained after the user authorizes, as well as the getting-on and getting-off behaviors reported by the user, to obtain getting-on and getting-off data.

[0073] Step S123: Obtain the trajectory data within a predetermined range of the target location to obtain trajectory information.

[0074] Optionally, the predetermined range in this embodiment may be a geographical range formed by expanding a predetermined distance outward centered on the target location. Further optionally, the trajectory data within the predetermined range of the target location in this embodiment may include the trajectory data within the grid area where the target location is located and / or the trajectory data corresponding to the contour area of the target location. The trajectory data corresponding to the contour area of the target location includes the trajectory data within the contour area and may also include the trajectory data within the area obtained by expanding the contour area by a predetermined range.

[0075] Further, the trajectory data in this embodiment may include the trajectory of the historical trip information obtained after the user authorizes, and may also include the trajectory data around the target location actively reported by the user.

[0076] It should be understood that the steps of obtaining the above getting-on and getting-off data and trajectory information may be executed simultaneously or sequentially, and this embodiment does not limit the execution order thereof.

[0077] Step S130: Determine at least one recommended point based on the getting-on and getting-off data and trajectory information corresponding to the target location.

[0078] Figure 3 is a flowchart of the method for determining the recommended point in the embodiment of the present invention. In an alternative implementation, as Figure 3 shown, the recommended point in the embodiment of the present invention is obtained through the following steps:

[0079] Step S131: Aggregate the obtained getting-on and getting-off behaviors based on the points corresponding to each getting-on and getting-off behavior to obtain a first candidate point set.

[0080] Optionally, in this embodiment, the getting-on and getting-off behaviors within the grid area where the target location is located are aggregated to obtain a first subset of points.

[0081] Figure 4 is a schematic diagram of a process for determining a candidate point in the embodiment of the present invention. AsFigure 4 As shown, for the target location P1, which is located in the grid area G1, multiple points p1 corresponding to the boarding and alighting behaviors within the grid area G1 are obtained, and the points p1 are aggregated to obtain the first set of point subsets. Among them, the first set of point subsets includes multiple points p2. Each point cluster after aggregation obtains a corresponding candidate point p2.

[0082] Furthermore, in this embodiment, by aggregating the boarding and alighting behaviors corresponding to the contour area of the target location, a second set of point subsets is obtained. The aggregation process of the boarding and alighting behaviors corresponding to the contour area is similar to the aggregation process of the boarding and alighting behaviors corresponding to the grid area where the target location is located, and will not be elaborated here.

[0083] Furthermore, in this embodiment, the union of the first set of point subsets and the second set of point subsets is used as the first set of candidate points.

[0084] It should be understood that in this embodiment, the points corresponding to the boarding and alighting behaviors are jointly subjected to the aggregation algorithm. In other alternative implementation manners, due to certain differences between the boarding location and the alighting location in practical applications, this embodiment can also perform the aggregation algorithm on the points corresponding to the boarding behavior to obtain the candidate points corresponding to the boarding behavior, and perform the aggregation algorithm on the points corresponding to the alighting behavior to obtain the candidate points corresponding to the alighting behavior. Thus, in this embodiment, when recommending the alighting point, the weight of the candidate points corresponding to the alighting behavior can be made greater than the weight of the candidate points corresponding to the boarding behavior, and when recommending the boarding point, the weight of the candidate points corresponding to the boarding behavior can be made greater than the weight of the candidate points corresponding to the alighting behavior. Thus, the accuracy of point recommendation can be further improved.

[0085] Step S132, sample the trajectory points of each trajectory in the trajectory information to obtain a second set of candidate points.

[0086] Since the target location in this embodiment is a low-heat location and its historical boarding and alighting data is scarce, this embodiment can further perform point mining based on the trajectory information for point supplementation.

[0087] Furthermore, this embodiment can sample the trajectory points in the trajectory information based on a predetermined method.

[0088] In an alternative implementation, each trajectory corresponding to the target location is sampled at a predetermined step size to obtain a plurality of candidate points. Among them, the predetermined step size can be characterized by the distance between two sampling points or the time difference between two sampling points, and this embodiment does not limit this. Further optionally, since the change frequency of the roads around the target location is relatively low, multiple trajectories may overlap. In this embodiment, only the overlapping trajectories may be sampled n (n is greater than or equal to 1 and less than the number of trajectories in the overlapping trajectories) times to avoid excessive candidate points obtained based on the trajectory information, which may cause interference in the subsequent determination of recommended points.

[0089] Figure 5 FIG. is a schematic diagram of another process for determining candidate points in an embodiment of the present invention. Taking the sampling process of a trajectory as an example, assume that the predetermined step size is m (m > 0) meters. For example, m is a value between 10 and 100. As Figure 5 shown, for the trajectory L1 corresponding to the target location P1, sampling at a predetermined step size of m meters can obtain candidate points p3, p4, and p5.

[0090] In another alternative implementation, since the trajectory staying areas within a predetermined range of the target location can, to a certain extent, characterize the areas where parking (i.e., getting on and off) is possible, therefore, in this embodiment, the trajectory points of each trajectory in the trajectory information can be clustered to obtain the staying areas corresponding to each trajectory, and the trajectory points in each staying area are sampled to obtain a second set of candidate points. Further, in this embodiment, spatio-temporal clustering is performed on the trajectory points of each trajectory, that is, the trajectory points with a distance less than a predetermined distance between the trajectory points in the same time period are clustered to obtain the staying areas. Further optionally, since staying behaviors occur at traffic lights at the same time, in this embodiment, the staying areas with a distance less than a preset distance from the traffic lights are screened out, and the remaining staying areas are sampled to obtain a second set of candidate points.

[0091] Figure 6 FIG. is a schematic diagram of yet another process for determining candidate points in an embodiment of the present invention. As Figure 6 shown, for the trajectories L2 and L3 corresponding to the target location P1, spatio-temporal clustering is performed on the trajectory points on the trajectories L2 and L3 to obtain three point clusters, and candidate points p6, p7, and p8 are respectively sampled from the three point clusters.

[0092] Further, in this embodiment, one or more trajectory points in the same staying area can be sampled as candidate points. The number of candidate points sampled in the same staying area can be set according to the size of the staying area, and this embodiment does not limit this.

[0093] Further optionally, the candidate points obtained after sampling are further aggregated, that is, the candidate points with mutual distances all less than a preset corresponding distance are aggregated to form multiple clusters, and the central points of each cluster are combined into the above-mentioned second candidate point set.

[0094] Step S133, obtain at least one recommended point from the first candidate point set and the second candidate point set.

[0095] Figure 7 It is a schematic diagram of a method for determining a recommended point according to an embodiment of the present invention. As Figure 7 shown, the method for determining a recommended point according to an embodiment of the present invention includes the following steps:

[0096] Step S1331, sort each of the candidate points according to the distance information and / or popularity information corresponding to the candidate points in the first candidate point set and the second candidate point set. Among them, the distance information of the candidate point is used to represent the distance between the candidate point and the coordinates of the target location. The popularity information of the candidate point can be determined according to the number of points in the cluster where it is located. Further, if the candidate points in the second candidate point set are determined after further aggregating the candidate points obtained after sampling, the popularity information of the candidate points in the second candidate point set is determined according to the sum of the numbers of the clustering clusters where each point in the aggregation cluster where it is located.

[0097] Further, the popularity information of the candidate points in this embodiment can be determined by weighting the first popularity when the candidate point is a boarding point and the second popularity when the candidate point is an alighting point. Optionally, the weights of the first popularity and the second popularity can be the same or different. Further, if the recommended point is a boarding point, the weight corresponding to the first popularity is greater than the weight of the second popularity. If the recommended point is an alighting point, the weight corresponding to the first popularity is less than the weight of the second popularity.

[0098] Further, this embodiment can also set a first score weight corresponding to the distance information of the candidate point and a second score weight corresponding to the popularity information, so as to determine the scores of each candidate point based on the first score weight and the second score weight, and sort each candidate point based on the score.

[0099] Step S1332, determine the recommended point according to a predetermined number of candidate points ranked in the front.

[0100] In an alternative implementation, a predetermined number of candidate points ranked at the front are determined as recommended points, and the recommended order of the recommended points is determined based on this ranking. Based on this recommended order, each recommended point is pushed to the point recall page of the user terminal. In another alternative implementation, a predetermined number of candidate points ranked at the front are determined as recommended points, and each recommended point is re-ranked to obtain a new recommended order. Based on this new recommended order, each recommended point is pushed to the point recall page of the user terminal.

[0101] Figure 8 It is a schematic diagram of a method for determining the order of recommended points in an embodiment of the present invention. As Figure 8 shown, the method for determining the order of recommended points in this embodiment includes the following steps:

[0102] Step S210, determine the fusion feature of each recommended point according to the feature of each recommended point, the feature of the relevant points of each recommended point, and / or the trajectory feature corresponding to each recommended point.

[0103] Among them, the feature of each recommended point may include distance information and popularity information. The feature of the relevant points of each recommended point may include the popularity information of the first candidate points whose distance from the recommended point is less than a preset distance threshold. Among them, the first candidate points are located in the first candidate point set. The trajectory feature includes the popularity information of the second candidate points whose distance from the recommended point is less than a preset distance threshold. Among them, the second candidate points are located in the second candidate point set. It should be understood that the acquisition method of the popularity information of the points is the same as that in Figure 7 the described embodiment and will not be elaborated here.

[0104] Thus, the fusion feature Fi of each recommended point = {f1(d, r1), {r21,..., r2x}, {r31,... r3y}}. Where i is the i-th recommended point, f1 is also the distance information and popularity information of the i-th recommended point itself, r21 - r2x is the popularity information of x first candidate points whose distance from the i-th recommended point is less than the preset distance threshold, and r31 - r3y is the popularity information of y first candidate points whose distance from the i-th recommended point is less than the preset distance threshold.

[0105] Step S220, rank each of the recommended points according to the fusion feature to obtain a recommended order.

[0106] Determine the recommendation scores of each recommended location based on the fusion features of each recommended location, sort each recommended location based on the recommendation scores, and obtain the recommendation order. It should be understood that in this embodiment, the higher the popularity of the recommended location, the more the number of the first candidate location and the second candidate location corresponding to the recommended location, and the higher the popularity information of the first candidate location and the second candidate location corresponding to the recommended location, the higher the recommendation score of the recommended location. In a specific application scenario, corresponding weights can be set to calculate the recommendation scores of each recommended location, and this embodiment will not give examples one by one here.

[0107] Step S230, push each recommended location to the location recall page of the user terminal based on the recommendation order.

[0108] This embodiment can sort based on the distance information and popularity information of each candidate location to obtain recommended locations, and then perform fine sorting based on the fusion features of each recommended location to improve the accuracy of location recommendation, thereby improving the user experience. In other alternative implementation manners, this embodiment can also determine the fusion features of each candidate location in the first candidate location set and the second candidate location set, sort each candidate location based on the fusion features of each candidate location, determine the predetermined number of candidate locations ranked in the front as recommended locations, and use the ranking of the recommended locations as the recommendation order.

[0109] Step S140, control the location recall page of the user terminal to display at least one recommended location.

[0110] In this embodiment, the location recall page can be a page for the user to determine the boarding point or the alighting point, and it can be displayed after the user determines the input target starting point or target ending point.

[0111] In the embodiment of the present invention, by obtaining the target location, in response to the target location being a low-heat location, obtaining the boarding and alighting data and trajectory information corresponding to the target location, recalling at least one recommended location according to the boarding and alighting data and trajectory information of the target location, and controlling the location recall page of the user terminal to display at least one of the recommended locations. Thereby, when the target location is a low-heat location with insufficient historical data in the embodiment of the present invention, the boarding and alighting points can be interchanged and used, and the trajectory information is used as supplementary information for location recall, enriching the number of recallable locations, improving the accuracy of location recommendation for low-heat locations, and thus improving the user experience.

[0112] Figure 9 It is a schematic diagram of the location recommendation process in the embodiment of the present invention. As Figure 9 shown, after determining that the current target location is a low-heat target location, obtain the boarding and alighting behaviors corresponding to the grid area where the target location is located, the boarding and alighting behaviors corresponding to the contour area of the target location, so as to obtain the boarding and alighting data, and obtain the trajectory data within a predetermined range of the target location.

[0113] Further, aggregate the pick-up and drop-off behaviors based on the position pairs corresponding to each pick-up and drop-off behavior to obtain a first set of candidate positions. Sample the trajectory points of each trajectory in the trajectory information to obtain a second set of candidate positions. Sort each candidate position according to the distance information and / or popularity information corresponding to the candidate positions in the first set of candidate positions and the second set of candidate positions, and determine a predetermined number of the candidate positions ranked at the front as the recommended positions. Further, determine the fusion features of each of the recommended positions according to the features of each of the recommended positions, the features of the related positions of each of the recommended positions, and / or the trajectory features corresponding to each of the recommended positions, and sort each of the recommended positions according to the fusion features to obtain the recommended positions after fine ranking and push them to the user. It should be understood that each step in the position recommendation process of the embodiments of the present invention is similar to the above embodiments and will not be described in detail here.

[0114] In the embodiments of the present invention, by obtaining a target location, in response to the target location being a low-heat location, obtaining the pick-up and drop-off data and trajectory information corresponding to the target location, and recalling at least one recommended position according to the pick-up and drop-off data and trajectory information of the target location, controlling the position recall page of the user terminal to display at least one of the recommended positions. Thus, when the target location is a low-heat location with insufficient historical data, the pick-up and drop-off points can be used interchangeably, and the trajectory information can be used as supplementary information for position recall, enriching the number of recallable positions, improving the accuracy of position recommendation for low-heat locations, and further improving the user experience.

[0115] Figure 10 is a schematic diagram of the position recommendation device according to the embodiments of the present invention. As Figure 10 shown, the position recommendation device 10 according to the embodiments of the present invention includes a location acquisition unit 101, an information acquisition unit 102, a recommended position determination unit 103, and a control unit 104.

[0116] The location acquisition unit 101 is configured to acquire a target location. The information acquisition unit 102 is configured to, in response to the target location being a low-heat location, acquire the pick-up and drop-off data and trajectory information corresponding to the target location. The recommended position determination unit 103 is configured to determine at least one recommended position according to the pick-up and drop-off data and the trajectory information. The control unit 104 is configured to control the position recall page of the user terminal to display at least one of the recommended positions.

[0117] In an alternative implementation, the information acquisition unit 102 is further configured to determine the grid area where the target location is located and the contour area of the target location, where the grid area is a geographical area with a predetermined size, obtain the getting-on and off behaviors corresponding to the grid area and the getting-on and off behaviors corresponding to the contour area to obtain the getting-on and off data, and obtain the trajectory data within a predetermined range of the target location to obtain the trajectory information.

[0118] In an alternative implementation, the recommended point determination unit 103 is further configured to aggregate the obtained getting-on and off behaviors based on the points corresponding to each getting-on and off behavior to obtain a first candidate point set, sample the trajectory points of each trajectory in the trajectory information to obtain a second candidate point set, and obtain the recommended points from the first candidate point set and the second candidate point set.

[0119] In an alternative implementation, the recommended point determination unit 103 is further configured to cluster the trajectory points of each trajectory in the trajectory information to obtain the staying areas corresponding to each trajectory, and sample the trajectory points in each staying area to obtain the second candidate point set.

[0120] In an alternative implementation, the recommended point determination unit 103 is further configured to sort each candidate point according to the distance information and / or popularity information corresponding to the candidate points in the first candidate point set and the second candidate point set, and determine a predetermined number of the candidate points ranked at the front as the recommended points.

[0121] In an alternative implementation, the point recommendation device 10 further includes a refined ranking unit, which is configured to determine the combined features of each recommended point according to the features of each recommended point, the features of the related points of each recommended point, and / or the trajectory features corresponding to each recommended point, sort each recommended point according to the combined features to obtain a recommended order, and push each recommended point to the point recall page of the user terminal based on the recommended order.

[0122] In an alternative implementation, the point recommendation device 10 further includes a low-popularity location determination unit, which is configured to determine that the target location is a low-popularity location in response to the online time of the target location being less than a predetermined duration and / or the location popularity of the target location being less than a predetermined popularity threshold.

[0123] In an embodiment of the present invention, by obtaining a target location, in response to the target location being a low-heat location, obtaining the boarding and alighting data and trajectory information corresponding to the target location, recalling at least one recommended location based on the boarding and alighting data and trajectory information of the target location, and controlling the location recall page of the user terminal to display at least one of the recommended locations. Thus, when the target location is a low-heat location with insufficient historical data, the boarding and alighting points can be interconnected and used interchangeably in the embodiment of the present invention, and the trajectory information is used as supplementary information for location recall, enriching the number of recallable locations, improving the accuracy of location recommendation for low-heat locations, and further enhancing the user experience.

[0124] Figure 11 is a schematic diagram of an electronic device according to an embodiment of the present invention. As Figure 11 shown, the electronic device 110 is a general-purpose data processing device, which includes a general computer hardware structure, and at least includes a processor 111 and a memory 112. The processor 111 and the memory 112 are connected through a bus 113. The memory 112 is adapted to store instructions or programs executable by the processor 111. The processor 111 can be an independent microprocessor or a set of one or more microprocessors. Thus, by executing the instructions stored in the memory 112, the processor 111 implements the processing of data and the control of other devices by executing the method flow of the embodiment of the present invention as described above. The bus 113 connects the above-mentioned multiple components together, and at the same time connects the above-mentioned components to a display controller 114, a display device, and an input / output (I / O) device 115. The input / output (I / O) device 115 can be a mouse, a keyboard, a modem, a network interface, a touch input device, a body sensor input device, a printer, and other devices well known in the art. Typically, the input / output device 115 is connected to the system through an input / output (I / O) controller 116.

[0125] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a device (equipment), or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can be implemented as a computer program product on one or more computer-readable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program codes.

[0126] The present application is described with reference to the flowcharts of methods, devices (equipment), and computer program products according to the embodiments of the present application. It should be understood that each process in the flowchart can be implemented by computer program instructions.

[0127] These computer program instructions can be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufacture including an instruction device that implements the functions specified in the process Figure 1 or functions specified in one or more of the processes.

[0128] These computer program instructions can also be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, such that the instructions executed by the processor of the computer or other programmable data processing device produce a device for implementing the functions specified in the process Figure 1 or functions specified in one or more of the processes.

[0129] Another embodiment of the present invention relates to a non-volatile storage medium for storing a computer-readable program for a computer to execute some or all of the above method embodiments.

[0130] That is, those skilled in the art can understand that all or part of the steps in implementing the above method embodiments can be completed by specifying relevant hardware through a program. The program is stored in a storage medium and includes several instructions to enable a device (which can be a single-chip microcomputer, a chip, etc.) or a processor to execute all or part of the steps of the methods described in the embodiments of the present application. The foregoing storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs.

[0131] The foregoing are only the preferred embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various modifications and changes. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included within the protection scope of the present application.

Claims

1. A point position recommendation method, characterized in that, The method includes: Obtaining a target location; In response to the target location being a low-temperature location, obtaining the boarding and alighting data and trajectory information corresponding to the target location, where the boarding and alighting data includes the boarding and alighting behaviors corresponding to the grid area and the contour area where the target location is located, the contour area of the target location is determined based on contour key points, the contour key points are determined based on boundary points extracted from the clustering analysis results of historical boarding and alighting data and historical trajectory data within a predetermined range of the target location and the historical trajectory data, or the contour key points are key points based on pre-collected key points describing the contour shape of the target location; Determining at least one recommended point based on the boarding and alighting data and the trajectory information; Controlling the point recall page of the user terminal to display at least one of the recommended points; Wherein, the determining at least one recommended point based on the boarding and alighting data and the trajectory information includes: Aggregating each of the boarding and alighting behaviors based on the point pairs corresponding to each of the boarding and alighting behaviors to obtain a first candidate point set; Sampling the trajectory points of each trajectory in the trajectory information to obtain a second candidate point set, and the sampling method includes sampling the trajectory points on each trajectory according to a step size, or sampling the trajectory points in the staying area obtained by spatio-temporal clustering of the trajectory points on each trajectory; Obtaining the recommended points from the first candidate point set and the second candidate point set.

2. The method according to claim 1, wherein The obtaining the boarding and alighting data and the trajectory information corresponding to the target location includes: Determining the grid area where the target location is located and the contour area of the target location, and the grid area is a geographical area with a predetermined size; Obtaining the boarding and alighting behaviors corresponding to the grid area and the boarding and alighting behaviors corresponding to the contour area to obtain the boarding and alighting data; Obtaining the trajectory data within a predetermined range of the target location to obtain the trajectory information.

3. The method according to claim 1, characterized in that, The sampling the trajectory points in the trajectory information to obtain a second candidate point set includes: Clustering the trajectory points of each trajectory in the trajectory information to obtain the staying area corresponding to each trajectory; Sampling the trajectory points in each of the staying areas to obtain the second candidate point set.

4. The method according to claim 1, wherein The obtaining the recommended points from the first candidate point set and the second candidate point set includes: Sorting each of the candidate points according to the distance information and / or popularity information corresponding to the candidate points in the first candidate point set and the second candidate point set; Determining a predetermined number of the candidate points ranked at the front as the recommended points.

5. The method according to claim 1, wherein The method further includes: Determining the fusion features of each of the recommended points according to the features of each of the recommended points, the features of the related points of each of the recommended points, and / or the trajectory features corresponding to each of the recommended points; Sorting each of the recommended points according to the fusion features to obtain a recommended order; Pushing each of the recommended points to the point recall page of the user terminal based on the recommended order.

6. The method according to claim 1, wherein The method further includes: Determine that the target location is a low-heat location in response to the online time of the target location being less than a predetermined duration and / or the location heat of the target location being less than a predetermined heat threshold.

7. A point position recommendation device, characterized in that, The device includes: A location acquisition unit configured to acquire a target location; An information acquisition unit configured to, in response to the target location being a low-heat location, acquire the boarding and alighting data and trajectory information corresponding to the target location, where the boarding and alighting data includes the boarding and alighting behaviors corresponding to the grid area and contour area where the target location is located, the contour area of the target location is determined based on contour key points, the contour key points are determined based on boundary points extracted from the clustering analysis results of historical boarding and alighting data and historical trajectory data within a predetermined range of the target location and the historical trajectory data, or the contour key points are key points based on pre-collected key points describing the contour shape of the target location; A recommended point determination unit configured to determine at least one recommended point according to the boarding and alighting data and the trajectory information; A control unit configured to control the point recall page of the user terminal to display at least one of the recommended points; The recommended point determination unit is further configured to execute: Aggregate each of the boarding and alighting behaviors based on the point pairs corresponding to each of the boarding and alighting behaviors to obtain a first candidate point set; Sample the trajectory points of each trajectory in the trajectory information to obtain a second candidate point set, where the sampling method includes sampling the trajectory points on each trajectory according to a step size, or sampling the trajectory points in the staying area obtained by spatio-temporal clustering of the trajectory points on each trajectory; Obtain the recommended points from the first candidate point set and the second candidate point set.

8. An electronic device, comprising a memory and a processor, characterized in that, The memory is used to store one or more computer program instructions, where the one or more computer program instructions are executed by the processor to implement the method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the method according to any one of claims 1-6 is implemented.

10. A computer program product, characterized in that, When the computer program product runs on a computer, the computer is caused to execute the method according to any one of claims 1-6.

Images