Position pushing method and device

Abstract

The embodiment of the invention discloses a position pushing method and device. A position obtaining request sent by a user terminal is received, the position obtaining request comprises a target position, a recommended position point is obtained according to the target position, the recommended position point comprises at least one of a virtual position point and a real position point, and the real position point is a position point registered in a real position point database. The virtual position points are unregistered position points generated through data mining, recommendation data are generated according to the recommendation position points and sent to the user terminal, and the recommendation data comprise the recommendation position points. Therefore, the interest points and the virtual position points are pushed to the user for selection together, the position point recommendation accuracy can be improved, and the operation process of the user is simplified.

Description

Technical Field

[0001] The present invention relates to the field of Internet technology, and in particular to a location push method and device. Background Art

[0002] With the development of Internet technology, online taxi services play an increasingly important role in people's travel. Among them, pushing accurate location points (pick-up point, drop-off point) to users plays an important role in improving user experience.

[0003] In the prior art, nearby points of interest are generally obtained based on the location information input by the user and pushed to the user. However, in many scenarios, there are no points of interest that can be accurately replaced near the location specified by the user, especially in scenarios where the points of interest are sparse and data is missing, such as scenic spots, villages and towns, etc. It is difficult for users to quickly locate the location they want to go to. At this time, users often choose other available locations, or reselect the location by other means, such as dragging the map. This makes the user's operation more cumbersome and affects the user experience. Summary of the invention

[0004] In view of this, an object of the embodiments of the present invention is to provide a location push method and device, which can improve the accuracy of location point recommendation and simplify the user's operation process.

[0005] In a first aspect, an embodiment of the present invention provides a location push method, the method comprising:

[0006] Receiving a location acquisition request sent by a user terminal, wherein the location acquisition request includes a target location;

[0007] Acquire a recommended location point according to the target location, the recommended location point comprising at least one of a virtual location point and a real location point, the real location point being a location point registered in a real location point database, and the virtual location point being a location point generated by data mining and not registered;

[0008] Recommendation data is generated according to the recommended location point and sent to the user terminal, wherein the recommendation data includes the recommended location point.

[0009] In some embodiments, the method further comprises:

[0010] Get the virtual location database.

[0011] In some embodiments, obtaining a virtual location point database includes:

[0012] Obtaining a historical location point, where the historical location point is a pick-up point or alighting point in a historical order;

[0013] Clustering the historical location points to obtain first candidate location points, where the first candidate location points are historical location points located in a clustering area;

[0014] Filtering the first candidate location points based on a nearest neighbor distance algorithm to obtain a second candidate location point;

[0015] Determine a name corresponding to each of the second candidate position points;

[0016] The virtual location point is generated based on the name corresponding to the second candidate location point, and is added to the virtual location point database.

[0017] In some embodiments, clustering the historical location points to obtain the first candidate location point includes:

[0018] Clustering the historical location points based on a DBSCAN algorithm to obtain at least one clustering region, wherein the clustering region includes a neighborhood and / or a cluster;

[0019] Determining a density corresponding to the neighborhood;

[0020] The historical location points within the cluster and / or within a neighborhood with a density greater than or equal to a first threshold are determined as the first candidate location points.

[0021] In some embodiments, filtering the first candidate location points based on the nearest neighbor distance algorithm to obtain the second candidate location points includes at least one of the following:

[0022] Determine the first distance of each first candidate location point in each clustering area based on the nearest neighbor distance algorithm, and filter the first candidate location points whose first distance is greater than or equal to the second threshold;

[0023] The second distance of each clustering area is determined based on the nearest neighbor distance algorithm, and the first candidate location points in the clustering area whose second distance is greater than or equal to the third threshold are filtered.

[0024] In some embodiments, determining the name corresponding to each of the second candidate location points includes:

[0025] The name of the second candidate location point is determined according to the priority of a predetermined naming rule.

[0026] In some embodiments, the naming rule includes at least one of the following:

[0027] Determine location point names based on frequently appearing shop or building names;

[0028] Determine location point names based on road intersections or transportation hubs;

[0029] Determine the location point name based on the POI with identification and description;

[0030] Determine the name of the location point based on the village, town and directional word.

[0031] In some embodiments, acquiring a recommended location point according to the target location includes:

[0032] Acquire a real location point matching the target location in the real location point database;

[0033] A virtual location point matching the target location is obtained in the virtual location point database.

[0034] In some embodiments, the method further comprises:

[0035] Determine the category of each of the recommended location points, the category including main points and sub-points;

[0036] Each main point is sorted according to a predetermined sorting rule, and the sub-points under each main point are sorted to generate a sorting result.

[0037] In some embodiments, the recommendation data also includes the ranking result.

[0038] In a second aspect, an embodiment of the present invention provides a location push method, the method comprising:

[0039] Sending a location acquisition request to a server, wherein the location acquisition request includes a target location;

[0040] Receiving recommendation data sent by a server, the recommendation data including recommended location points, the recommended location points including at least one of virtual location points and real location points, the real location points are location points registered in a real location point database, and the virtual location points are location points generated by data mining and not registered;

[0041] The recommended location point is displayed.

[0042] In some embodiments, the recommendation data further includes the ranking result, and the ranking result includes the ranking result of each main point and the ranking result of each sub-point under the main point.

[0043] In some embodiments, presenting the recommended location point includes:

[0044] The recommended location points are displayed according to the sorting results.

[0045] In a third aspect, an embodiment of the present invention provides a position push device, the device comprising:

[0046] A request receiving unit, configured to receive a location acquisition request sent by a user terminal, wherein the location acquisition request includes a target location;

[0047] a recommended location point acquisition unit, configured to acquire a recommended location point according to the target location, wherein the recommended location point includes at least one of a virtual location point and a real location point, wherein the real location point is a location point registered in a real location point database, and the virtual location point is a location point generated by data mining and not registered;

[0048] The recommendation data sending unit is used to generate recommendation data according to the recommended location point and send the recommendation data to the user terminal, wherein the recommendation data includes the recommended location point.

[0049] In a fourth aspect, an embodiment of the present invention provides a location push device, the device comprising:

[0050] A request sending unit, configured to send a location acquisition request to a server, wherein the location acquisition request includes a target location;

[0051] a recommendation data receiving unit, configured to receive recommendation data sent by a server, wherein the recommendation data includes a recommended location point, and the recommended location point includes at least one of a virtual location point and a real location point, wherein the real location point is a location point registered in a real location point database, and the virtual location point is a location point generated by data mining and not registered;

[0052] A display unit is used to display the recommended location point.

[0053] In a fifth aspect, an embodiment of the present invention provides an electronic device, comprising a memory and a processor, wherein the memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method described in the first aspect.

[0054] In a sixth aspect, an embodiment of the present invention provides a computer program product, wherein the computer program product includes a computer program. When the computer program runs on a computer, the computer executes the method described in the first aspect above.

[0055] In a seventh aspect, an embodiment of the present invention provides a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the method described in any one of the first aspects is implemented.

[0056] The technical solution of the embodiment of the present invention receives a location acquisition request sent by a user terminal, the location acquisition request includes a target location, obtains a recommended location point according to the target location, the recommended location point includes at least one of a virtual location point and a real location point, the real location point is a location point registered in a real location point database, the virtual location point is an unregistered location point generated by data mining, generates recommendation data according to the recommended location point and sends it to the user terminal, the recommendation data includes the recommended location point. Therefore, by pushing points of interest and virtual location points together to users for selection, the accuracy of location point recommendation can be improved and the user's operation process can be simplified. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] The above and other objects, features and advantages of the present invention will become more apparent through the following description of the embodiments of the present invention with reference to the accompanying drawings, in which:

[0058] Figure 1 is a flow chart of establishing a virtual location point database according to an embodiment of the present invention;

[0059] Figure 2 is a flowchart of obtaining a first candidate position according to an embodiment of the present invention;

[0060] Figure 3 is a flow chart of a method for pushing a location of a server according to an embodiment of the present invention;

[0061] Figure 4 is a flowchart of processing of a virtual location point according to an embodiment of the present invention;

[0062] Figure 5 is a flow chart of a method for pushing a location of a user terminal according to an embodiment of the present invention;

[0063] Figure 6 It is a schematic diagram of the position display interface of the comparison ratio;

[0064] Figure 7 is a schematic diagram of a location display interface of an embodiment of the present invention;

[0065] Figure 8 is a schematic diagram of a location push device of a server according to an embodiment of the present invention;

[0066] Fig. 9 is a schematic diagram of a device for pushing a position of a user terminal according to an embodiment of the present invention;

[0067] Fig.10 is a schematic diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0068] The present application is described below based on embodiments, but the present application is not limited to these embodiments. In the detailed description of the present application below, some specific details are described in detail. It is possible for those skilled in the art to fully understand the present application without the description of these details. In order to avoid confusing the essence of the present application, known methods, processes, flows, components and circuits are not described in detail.

[0069] In addition, persons of ordinary skill in the art will appreciate that the drawings provided herein are for illustration purposes and are not necessarily drawn to scale.

[0070] Unless the context clearly requires otherwise, the words "include", "comprising" and similar words throughout the application should be interpreted as including rather than exclusive or exhaustive; that is, the meaning is "including but not limited to".

[0071] In the description of this application, it should be understood that the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of this application, unless otherwise specified, the meaning of "plurality" is two or more.

[0072] The solutions described in this specification and in the examples, if they involve the processing of personal information, will be processed on the premise of having a legal basis (such as obtaining the consent of the subject of personal information, or being necessary for the performance of a contract, etc.), and will only be processed within the scope of regulations or agreements. If a user refuses to process personal information other than the necessary information for basic functions, it will not affect the user's use of basic functions.

[0073] POI (Point of Interest) refers to an observable point of interest in a geographic information system, which is often named after an entity, such as a house, a shop, a bus stop, etc. However, the actual POI points often cannot meet the growing and diverse needs of users. Especially for large-scale surface POIs, the traditional point representation method cannot meet the user's taxi needs. Users are more inclined to use "xx intersection", "next to xx sign", "north side of xx shopping mall" to describe their location, or some collection points. The embodiment of the present invention defines such points as "virtual points" or "virtual location points".

[0074] In the prior art, there is often no POI that can accurately replace popular "virtual points", but users have a strong desire to get on and off at the virtual points, which creates a contradiction: users cannot directly select the points they frequently use through the POI list, but can only drag the map to select or select other available points nearby.

[0075] This experience defect can manifest in two forms. The first is that POIs are sparse and data is missing. Virtual points can make up for the problem that users cannot quickly reach the location they want to go due to insufficient point density. This is particularly evident in scenic spots, villages and towns. The second is that some points are not suitable as sub-points of other points, or the descendant relationship of points is too complex to be concisely displayed to users.

[0076] Therefore, the embodiment of the present invention provides a location push method to solve the above defects, improve the accuracy of location point recommendation, and simplify the user's operation process.

[0077] Furthermore, the location push method of the embodiment of the present invention can be divided into two processes, namely, establishing a virtual location point database and location point push.

[0078] Figure 1 It is a flow chart of establishing a virtual location point database according to an embodiment of the present invention. Figure 1 The process of establishing a virtual location point database shown can be executed by various electronic devices with data processing functions, and the electronic device includes a memory and a processor, and the memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the process of establishing a virtual location point database according to an embodiment of the present invention, which specifically includes the following steps:

[0079] Step S110: Obtain historical location points.

[0080] In this embodiment, the historical location point is a boarding point or alighting point in a historical order. The virtual location point database includes a virtual location point database for boarding points and a virtual location point database for alighting points. If a virtual location point database for boarding points is established, the historical location point obtained is the boarding point in the historical order. If a virtual location point database for alighting points is established, the historical location point obtained is the alighting point in the historical order. For ease of description, the embodiment of the present invention is described by taking the establishment of a virtual location point database for alighting points as an example.

[0081] Specifically, when it is necessary to determine the virtual location point database of a certain area, historical orders within a predetermined historical period (e.g., 3 months) of the area are obtained, and the corresponding drop-off point of each order is determined to obtain the historical location point. The area can be divided based on various methods, such as administrative area division or grid division, which is not limited in the embodiment of the present invention.

[0082] Step S120: cluster the historical location points to obtain first candidate location points, where the first candidate location points are historical location points located in a clustering area.

[0083] In this embodiment, the historical location points are clustered based on a predetermined clustering algorithm to obtain first candidate location points, where the first candidate location points are historical location points located within the clustering area.

[0084] In some embodiments, the predetermined clustering algorithm is DBSCAN (Density-Based Spatial Clustering of Applications with Noise).

[0085] in, Figure 2 FIG. 1 is a flowchart of obtaining the first candidate position according to an embodiment of the present invention. Figure 2 As shown, clustering the historical location points to obtain the first candidate location point includes the following steps:

[0086] Step S121: cluster the historical location points based on the DBSCAN algorithm to obtain at least one clustering area.

[0087] In this embodiment, the clustering area includes a neighborhood and / or a cluster. Specifically, the embodiment of the present invention adopts a density-based clustering method DBSCAN to analyze and mine the user's points of interest (POI, Point of Interest). Compared with other clustering methods, DBSCAN is particularly good at processing complex data with noise, and can find clusters of any shape and size. The core idea of ​​DBSCAN is to connect similar high-density points into clusters by finding areas with higher density in the data set. Specifically, the DBSCAN algorithm first defines a neighborhood (eps-neighbourhood) for each data point, that is, a circle with each point as the center and a radius of eps. The algorithm counts the number of points contained in the neighborhood of each data point, which is called the density of the point. If the number of points in the neighborhood of a point is greater than or equal to a preset threshold MinPts, the point is regarded as a core point (Core point). When the neighborhoods of multiple core points overlap, they will be connected into clusters.

[0088] Corresponding to the embodiment of the present invention, the DBSCAN algorithm first defines a neighborhood (eps-neighborhood) for each historical location point, that is, a circle with each point as the center and a radius of eps, and counts the number of points contained in the neighborhood of each historical location point, which is called the density of the historical location point. If the number of points in the neighborhood of a historical location point is greater than or equal to a preset threshold MinPts, the point is regarded as a core point. When the neighborhoods of multiple core points overlap, they will be connected into clusters.

[0089] Thus, at least one clustering region may be obtained, wherein the clustering region includes a neighborhood and / or a cluster.

[0090] Step S122: Determine the density corresponding to the neighborhood.

[0091] In this embodiment, after the neighborhood and / or cluster is obtained through the above steps, since the cluster is generated when the neighborhoods of multiple core points overlap, and the density of the neighborhood of the core point is large, the density of the cluster is large, and thus, for the cluster, it is not necessary to determine its density. For the neighborhood, the density corresponding to each area is determined.

[0092] Step S123: Determine the historical location points within the cluster and / or within a neighborhood with a density greater than or equal to a first threshold as the first candidate location points.

[0093] In this embodiment, a cluster and a neighborhood with a density greater than or equal to a first threshold are selected, and a historical location point in the cluster and / or in the neighborhood with a density greater than or equal to the first threshold is determined as the first candidate location point. The first threshold is a preset value.

[0094] Therefore, in the application scenario of user alighting point data, the DBSCAN algorithm can mine areas where users frequently appear from massive, noisy data. These high-density areas may represent users' points of interest, such as popular attractions, shopping malls, or frequently visited transportation hubs. Those low-density points may be some abnormal alighting locations or infrequently visited areas. In this way, user behavior patterns can be accurately identified and analyzed to provide data support for further decision-making and service optimization. At the same time, the graphical display of the DBSCAN algorithm can also more intuitively understand the working principle of DBSCAN, including the distribution of core points, boundary points, and outliers, and thus better understand the relationship between clustering results and user points of interest.

[0095] Step S130: Filter the first candidate location points based on a nearest neighbor distance algorithm to obtain second candidate location points.

[0096] In this embodiment, the core idea of ​​the nearest_neighbor_distances algorithm is to calculate the distance between each point and its nearest neighbor, and then evaluate the distribution of points in the same cluster area. If the points in the cluster area are very close to each other, it means that the cluster area is a very tight group, representing the frequent activities or stays of users in a certain area. If the points in the cluster area are far away from each other, then the cluster area may be loose, unstable or random.

[0097] A common problem in the process of automatically generating points of interest is the jitter of points within a small scale. This jitter usually comes from the randomness or noise of the data, which may cause the generated points of interest to be unstable and change frequently, thus affecting the accuracy of the analysis. To solve this problem, the impact of jitter is reduced by filtering out data that is not obviously clustered within a small scale. Specifically, points with large nearest neighbor distances or loose clusters are considered noise or abnormal points and are removed from the list of automatically generated points of interest. In this way, only those dense and stable clusters will be retained to generate the final points of interest.

[0098] Among them, filtering the first candidate location points includes at least one of the following: determining the first distance of each first candidate location point in each clustering area based on the nearest neighbor distance algorithm, and filtering the first candidate location points whose first distance is greater than or equal to a second threshold; determining the second distance of each clustering area based on the nearest neighbor distance algorithm, and filtering the first candidate location points in the clustering area whose second distance is greater than or equal to a third threshold.

[0099] For filtering the first candidate position points whose first distance is greater than or equal to the second threshold, the first distance between each first candidate position point and its nearest neighbor point is calculated using the nearest neighbor distance algorithm. If the first distance is greater than or equal to the second threshold, it means that the corresponding first candidate position point is relatively dispersed from other points, and the corresponding first candidate position point is filtered.

[0100] For filtering the first candidate location points in the clustering area whose second distance is greater than or equal to the third threshold, the first distance between each first candidate location point and its nearest neighbor is calculated by the nearest neighbor distance algorithm, and the average value of the first distances corresponding to all the first candidate location points in the clustering area is determined as the second distance. If the second distance is greater than or equal to the third threshold, it means that the first candidate location points in the corresponding clustering area are relatively scattered, and the first candidate location points in the corresponding clustering area are filtered.

[0101] Therefore, by calculating the nearest neighbor distance, we can get the density distribution of each first candidate location point in the cluster area, and further identify whether the cluster area really represents the user's point of interest. For example, near a shopping mall or bus station, the user's drop-off points will be very concentrated, and such a cluster is of practical significance. In some scenarios, if the drop-off points in the cluster area are more dispersed, it may be a cluster caused by data noise or accidental events, and it should be filtered out.

[0102] Through the filtering mechanism of the embodiment of the present invention, not only can the stability of generating the second candidate point be significantly improved, but also the erroneous judgment caused by noise data can be reduced. In practice, this process is used in conjunction with the results of DBSCAN. First, DBSCAN is used to identify approximate high-density areas, and then the nearest neighbor distance algorithm is used to perform detailed analysis and filtering on these areas to ensure that the generated points of interest are highly accurate and reliable. By combining the DBSCAN algorithm and the nearest neighbor distance algorithm, it is possible to have a deeper understanding of the user's getting off behavior pattern, accurately identify the user's points of interest, and greatly reduce point jitter in the process of automatically generating points, thereby improving the accuracy and reliability of the overall analysis.

[0103] Step S140: Determine the name corresponding to each of the second candidate position points.

[0104] In this embodiment, after obtaining relatively confident second candidate location points, these second candidate location points will be reasonably named to facilitate user understanding and identification, and provide clear positioning for subsequent analysis, navigation or data visualization.

[0105] Furthermore, the embodiment of the present invention determines the name of the second candidate location point according to the priority of a predetermined naming rule.

[0106] The naming rules include at least one of the following:

[0107] Determine location point names based on frequently appearing shop or building names;

[0108] Determine location point names based on road intersections or transportation hubs;

[0109] Determine the location point name based on the POI with identification and description;

[0110] Determine the name of the location point based on the village, town and directional word.

[0111] The above-mentioned determination of location point names based on frequently appearing shop or building names, determination of location point names based on road intersections or transportation hubs, and determination of location point names based on POIs with identification and descriptive significance, belong to the naming based on surrounding POIs. Naming based on surrounding POIs is to give priority to using the names of these POIs to name the candidate points if there are other significant shops, buildings or landmarks within a certain range (for example, 50 meters) around the second candidate location point. This naming method is more intuitive and easy to identify, and can quickly help users associate candidate points with familiar places.

[0112] Determine the location point name based on the frequently appearing shop or building names: If there are shops or buildings near a second candidate location point where users frequently go out or get off, such as supermarkets, hotels, restaurants, office buildings, etc., then the names of these places can be used as the basis for naming. For example, if there is a well-known supermarket near the second candidate location point, it can be named "near XX supermarket".

[0113] Determine the location point name based on road intersections or transportation hubs: If the second candidate location point is at the intersection of two main roads, or there is an obvious bus stop or subway station nearby, choose to include these geographic information in the name. For example, "Intersection of XX Road and XX Road", "Opposite to XX Building", etc.

[0114] Determine location point names based on POIs that are meaningful and descriptive: Choose POI names that are meaningful, especially those where users place orders frequently. These landmarks are not only easy to identify, but also clearly descriptive, which can help other users locate them quickly. For example, if the candidate point is close to an office building, school, or hospital, it can be named "East of XX Hospital" or "Opposite the main entrance of XX School."

[0115] Determine the location point name based on villages and locative words: In some cases, there are no significant POIs or shops around the second candidate location point. This situation is more common in remote areas, rural areas or places with fewer geographical signs. In order to ensure that these points are still clearly named and descriptive, a naming strategy based on locative words is used. This method is not only suitable for second candidate location points without POIs, but also for those second candidate location points with only vague geographical features around them. Naming based on villages and towns: If the second candidate location point is located near a village or town, but there are no specific shops or buildings as a basis for naming, the point is described by combining locative words. For example, "Northeast entrance of XX village" or "South entrance of XX town". This naming method is concise and clear, which can help users quickly locate while retaining the accuracy of geographical location. For the selection of locative words: Common locative words include "east", "south", "west", "north" and "entrance", "exit" and other locative words. For example, "East entrance of XX village" or "Northwest exit of XX town" can clearly indicate the relative position of the point in the village and town, which is convenient for users to make geographic references.

[0116] In some embodiments, the priority of the naming rules is preset, and each second candidate location point is named in order from high to low priority. For example, an unnamed second candidate location point is selected and named according to the naming rule with the highest priority. If a name is obtained through the naming rule with the highest priority, check whether it is repeated with the name of a named location point (including a virtual location point and a real location point). If it is not repeated, use it as the name of the second candidate location point, and then select the next second candidate location point; if a name is not obtained through the naming rule with the highest priority, or a name is obtained through the naming rule with the highest priority but is repeated with the name of a named location point (including a virtual location point and a real location point), select the next priority naming rule to name it until a name is obtained. Among them, the selection order of the second candidate location points can be selected according to random selection or other rules, and the embodiments of the present invention do not limit this.

[0117] At the same time, the embodiment of the present invention does not limit the specific implementation method of the naming rules, and the above-listed naming rules can be added, modified, deleted, etc. At the same time, the priority order of the naming rules is also not limited and can be set according to the actual scenario.

[0118] In a specific implementation, an embodiment of the present invention comprehensively analyzes the surrounding environment of the candidate points, and gives priority to POIs that can provide prominent identification and are easy for users to identify and understand. For example, a candidate point near a popular restaurant or shopping mall is obviously easier for users to associate and remember than an unmarked residential area. When POIs are dense, the most representative or descriptive places will be selected as the basis for naming. For example, if the candidate point is close to multiple shops, the shop name with a higher frequency of user interaction and stronger identification is selected instead of randomly selecting one. In the case where POIs are sparse or there are no significant landmarks, use geographic location to name them to ensure that the points are still descriptive and avoid confusing users.

[0119] Through this naming strategy, the points of interest generated by the system will be more intuitive and descriptive, making it easier for users to quickly locate and understand them. At the same time, this naming method can also greatly enhance the actual application value of the points, especially in scenarios such as navigation, logistics, and user behavior analysis. Accurate point descriptions help optimize the overall process and improve user experience.

[0120] Step S150: Generate the virtual location point based on the name corresponding to the second candidate location point, and add it to the virtual location point database.

[0121] In this embodiment, a virtual location point is generated based on the name corresponding to the second candidate location point and added to the virtual location point database.

[0122] The embodiment of the present invention receives a location acquisition request sent by a user terminal, the location acquisition request includes a target location, obtains a recommended location point according to the target location, the recommended location point includes at least one of a virtual location point and a real location point, the real location point is a location point registered in a real location point database, and the virtual location point is an unregistered location point generated by data mining, generates recommendation data according to the recommended location point and sends it to the user terminal, the recommendation data includes the recommended location point. Therefore, by pushing points of interest and virtual location points together to users for selection, the accuracy of location point recommendation can be improved and the user's operation process can be simplified.

[0123] After obtaining these virtual locations and names, these virtual locations are further processed as virtual POIs (Point of Interest). Virtual POIs refer to location points generated by data mining that have not yet been registered in the existing POI database. Although they are not POIs in the traditional sense, they have high confidence through clustering analysis and naming strategies and can represent the actual behavior hotspots of users. The introduction of virtual POIs not only enriches the existing geographic data, but also better reflects the travel habits and behavior patterns of users.

[0124] Figure 3 It is a flow chart of the location push method of the server according to an embodiment of the present invention. Figure 3 The location push method shown can be executed by various electronic devices with data processing functions, the electronic device includes a memory and a processor, the memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the location push method of the embodiment of the present invention. The electronic device can be a server through location services. The location push method specifically includes the following steps:

[0125] Step S210: receiving a location acquisition request sent by a user terminal.

[0126] In this embodiment, the location acquisition request includes a target location, which is a push location specified by a user.

[0127] In some embodiments, taking the online car-hailing scenario as an example, the target location is the user's get-off location, and the target location can be obtained by the user entering text in the taxi-hailing interface, or by the user selecting it through a map. Correspondingly, the location acquisition request is a taxi-hailing request.

[0128] Step S220: Acquire a recommended location point according to the target location.

[0129] In this embodiment, the recommended location point includes at least one of a virtual location point and a real location point, the real location point is a location point registered in a real location point database, and the virtual location point is an unregistered location point generated by data mining.

[0130] Wherein, acquiring the recommended location point according to the target location includes:

[0131] Step S221: Acquire a real location point matching the target location in the real location point database.

[0132] In this embodiment, for the convenience of operation and maintenance, the location point database includes a real location point database and a virtual location point database. Among them, the real location point database includes real location points. The real location points in the real location point database are location points that have been registered and in use. They are relatively fixed, and the update cycle and update range are relatively small. The virtual location point database includes virtual location points. The virtual location points in the virtual location point database are location points that are mined through the above method and are not registered. Relatively speaking, the data changes are relatively large, and the update cycle and update range are relatively large.

[0133] Further, after receiving the location acquisition request, the real location point matching the target location is acquired in the real location point database. The real location point matching the target location is a real location point that satisfies a predetermined condition with the target location, and the predetermined condition may be that the distance is less than or equal to a predetermined threshold. Alternatively, the predetermined condition is to sort the distances from small to large, and select a predetermined number of real location points with the smallest distances as the real location points matching the target location.

[0134] Step S222: Acquire a virtual location point matching the target location from the virtual location point database.

[0135] In this embodiment, after receiving the location acquisition request, the virtual location point matching the target location is acquired in the virtual location point database. The real location point matching the target location is a real location point that satisfies a predetermined condition with the target location, and the predetermined condition may be that the distance is less than or equal to a predetermined threshold. Alternatively, the predetermined condition is to sort the distances from small to large, and select a predetermined number of virtual location points with the smallest distances as virtual location points matching the target location.

[0136] Specifically, the server first obtains a real location point matching the target location, the real location point including a main point and / or a sub-point, and obtains a virtual location point matching the target location as a main point from the virtual location point. Then, a virtual location point under the main point determined above and as a sub-point is obtained. Thus, the real location point and the virtual location point can be obtained.

[0137] Furthermore, the matched real location point and virtual location point are used as the recommended location point.

[0138] In some embodiments, the location push method further includes:

[0139] Determine the category of each of the recommended location points, the category includes a main point and a sub-point, sort each main point according to a predetermined sorting rule, and sort the sub-points under each main point to generate a sorting result.

[0140] Among them, the main point is the upper recommended location point, and the sub-point is the lower recommended location point. A main point may not include sub-points, or may include one or more sub-points. The main points are sorted in parallel, and the sub-points under the same main point are sorted in parallel.

[0141] In this embodiment, for each virtual location point, if the virtual location point is relatively independent, that is, there is no POI within a certain range nearby, it is taken as the main point. Alternatively, if the virtual location point is not very independent but has a high popularity, it is taken as the main point. If the virtual location point is less independent and has a low popularity, that is, there are one or more POIs within a certain range nearby, it is taken as a sub-point.

[0142] For those virtual locations displayed as main points in the embodiments of the present invention, they will be fully integrated into the existing POI recall logic. This means that these virtual locations will be processed and displayed in the same way as real locations in user search, recommendation, navigation and other scenarios. These virtual locations can not only provide users with commonly used point of interest services (such as navigation and route planning), but also further optimize the system recommendation and search results through their popularity data, thereby improving the user experience.

[0143] The introduction of virtual locations enriches the POI system, allowing the system to dynamically generate new locations and adjust and optimize based on user behavior. At the same time, virtual POIs maintain the accuracy of the system and enhance the user's actual experience through mixing and penetration strategies, which can effectively meet users' needs for new locations.

[0144] Step S230: Generate recommendation data according to the recommended location point and send it to the user terminal.

[0145] In this embodiment, the recommendation data includes the recommended location point.

[0146] In some embodiments, the recommendation data also includes the ranking result.

[0147] The embodiment of the present invention receives a location acquisition request sent by a user terminal, the location acquisition request includes a target location, obtains a recommended location point according to the target location, the recommended location point includes at least one of a virtual location point and a real location point, the real location point is a location point registered in a real location point database, and the virtual location point is an unregistered location point generated by data mining, generates recommendation data according to the recommended location point and sends it to the user terminal, the recommendation data includes the recommended location point. Therefore, by pushing points of interest and virtual location points together to users for selection, the accuracy of location point recommendation can be improved and the user's operation process can be simplified.

[0148] Figure 4 4 is a flowchart of processing a virtual position point according to an embodiment of the present invention. Figure 4 A specific implementation method for processing virtual position points is shown, which specifically includes the following steps:

[0149] Step S310: Obtain a virtual location point.

[0150] In this embodiment, virtual location points are obtained through data mining and stored in HDFS (Hadoop Distributed File System). HDFS is a highly fault-tolerant system that can provide high-throughput data access and is very suitable for applications on large-scale data sets.

[0151] The specific implementation method is as follows Figure 1 As shown, the embodiments of the present invention are not described in detail here.

[0152] Step S320: Offline fastload.

[0153] In this embodiment, offline database FastLoad generally refers to a technology or tool for efficiently loading offline data into an online storage system or database. Through offline database FastLoad, a large amount of data stored in an offline platform (HDFS) is quickly and efficiently imported into an online storage system or database for real-time reading and use by online services.

[0154] Step S330: Location acquisition request.

[0155] In this embodiment, the server obtains a location acquisition request sent by the user terminal, and calls point-api (location point acquisition interface) according to the location acquisition request to obtain a virtual location point.

[0156] Step S340: Read data in the online database according to the obtained version number.

[0157] In this embodiment, version control supports configuration version control, and all configuration releases have version records to facilitate backtracking and auditing.

[0158] apollotag-serve (tag service) obtains the version number and reads the data in the online database based on the obtained version number.

[0159] Step S350: Save the virtual location point.

[0160] In this embodiment, the virtual location point in the online database is read and saved.

[0161] Step S360: traverse and retrieve virtual location points.

[0162] In this embodiment, according to the target location in the location acquisition request, virtual location points matching the target location are traversed and retrieved.

[0163] The embodiment of the present invention receives a location acquisition request sent by a user terminal, the location acquisition request includes a target location, obtains a recommended location point according to the target location, the recommended location point includes at least one of a virtual location point and a real location point, the real location point is a location point registered in a real location point database, and the virtual location point is an unregistered location point generated by data mining, generates recommendation data according to the recommended location point and sends it to the user terminal, the recommendation data includes the recommended location point. Therefore, by pushing points of interest and virtual location points together to users for selection, the accuracy of location point recommendation can be improved and the user's operation process can be simplified.

[0164] Figure 5 FIG. 1 is a flow chart of a method for pushing a location of a user terminal according to an embodiment of the present invention. Figure 5 As shown, the location push method of the user terminal in the embodiment of the present invention includes the following steps:

[0165] Step S410: Send a location acquisition request to the server.

[0166] In this embodiment, the user terminal inputs the user's travel information through the taxi-hailing interface, and the travel information includes information such as the user's starting location and the end location. The user terminal sends a location acquisition request to the server, and the location acquisition request includes the target location. The embodiment of the present invention is described by taking the target location as the end location as an example.

[0167] Step S420: Receive the recommended location sent by the server.

[0168] In this embodiment, a location acquisition request sent by a user terminal is received, the location acquisition request includes a target location, a recommended location point is acquired based on the target location, the recommended location point includes at least one of a virtual location point and a real location point, the real location point is a location point registered in a real location point database, the virtual location point is an unregistered location point generated by data mining, recommendation data is generated based on the recommended location point and sent to the user terminal, the recommendation data includes the recommended location point.

[0169] In some embodiments, the recommendation data further includes the ranking result, and the ranking result includes the ranking result of each main point and the ranking result of each sub-point under the main point.

[0170] Step S430: display the recommended location points.

[0171] In this embodiment, the user terminal displays the recommended location points according to the sorting result.

[0172] Specifically, the ranking results include ranking results of main points and ranking results of sub-points, wherein the main points are displayed in parallel according to the ranking results of the main points. According to the ranking results of the sub-points, the sub-points under the same main point are displayed in parallel.

[0173] In order to optimize the interactive experience between users and POIs, virtual location points are divided into two categories: main points and sub-points, and different display strategies are adopted according to their popularity and independence.

[0174] Mixed display of sub-points: For those virtual locations with high popularity but weak independence, they are treated as sub-points. Sub-points are usually associated with a main point or other sub-points. User activities are mainly concentrated in a specific area, but they do not necessarily represent a completely independent point of interest. Therefore, in the user interface, such sub-points will be mixed with other sub-points and selectively displayed according to their popularity through algorithms. Only when the popularity of a sub-point reaches a certain threshold will it be displayed first in the user interface to avoid too much irrelevant information interfering with user decisions.

[0175] Independent display of main points: For popular and independent virtual locations, display them as main points. Main points are those that users frequently visit and have obvious geographical independence or functional independence. Such virtual locations have the same functions and status as real locations and can independently participate in the user's location recall logic. For example, if a virtual location is particularly popular for getting off at a commercial center and there are no other obvious POIs around it, display it to the user as a main point and recall it together with the real locations in the system for the user to choose.

[0176] For those virtual locations displayed as main points in the embodiments of the present invention, they will be fully integrated into the existing POI recall logic. This means that these virtual locations will be processed and displayed in the same way as real locations in user search, recommendation, navigation and other scenarios. These virtual locations can not only provide users with commonly used point of interest services (such as navigation and route planning), but also further optimize the system recommendation and search results through their popularity data, thereby improving the user experience.

[0177] The introduction of virtual locations enriches the POI system, allowing the system to dynamically generate new locations and adjust and optimize based on user behavior. At the same time, virtual POIs maintain the accuracy of the system and enhance the user's actual experience through mixing and penetration strategies, which can effectively meet users' needs for new locations.

[0178] Therefore, through the display strategy of virtual location points, not only can the popular areas where users frequently move around be identified, but also personalized sorting and display can be performed according to the characteristics of these virtual location points, thereby improving the flexibility and responsiveness of the overall system. This strategy provides users with richer and more diverse geographic information services, and through dynamic updates and adjustments, effectively improves user satisfaction with the system.

[0179] Figure 6 This is a schematic diagram of the position display interface for comparison. Figure 6 As shown, the position display interface of the comparative example includes a target position input area A1 and a recommended data display area A2. The recommended data display area A2 includes a main point display area A3 and a sub-point display area A4.

[0180] Depend on Figure 6 It can be seen that in the display interface in the comparative example, only real location points are displayed, resulting in fewer location points for the user to choose from.

[0181] Figure 7 Schematic diagram of the location display interface of an embodiment of the present invention. Figure 7 As shown, the location display interface of the embodiment of the present invention includes a target location input area A1 and a recommended data display area A2. The recommended data display area A2 includes a main point display area A3 and a sub-point display area A4.

[0182] Furthermore, in the sub-point display area A4, a real position point A4 and a virtual position point A6 are displayed.

[0183] Depend on Figure 7 It can be seen that in the display interface of the embodiment of the present invention, both real location points and virtual location points are displayed, so that the user can have more location points to choose from.

[0184] The embodiment of the present invention receives a location acquisition request sent by a user terminal, the location acquisition request includes a target location, obtains a recommended location point according to the target location, the recommended location point includes at least one of a virtual location point and a real location point, the real location point is a location point registered in a real location point database, and the virtual location point is an unregistered location point generated by data mining, generates recommendation data according to the recommended location point and sends it to the user terminal, the recommendation data includes the recommended location point. Therefore, by pushing points of interest and virtual location points together to users for selection, the accuracy of location point recommendation can be improved and the user's operation process can be simplified.

[0185] Figure 8 Schematic diagram of a server location push device according to an embodiment of the present invention. Figure 8 As shown, the location push device of the server in the embodiment of the present invention includes a request receiving unit 81, a recommended location point acquisition unit 82 and a recommended data sending unit 83. The request receiving unit 81 is used to receive a location acquisition request sent by a user terminal, and the location acquisition request includes a target location. The recommended location point acquisition unit 82 is used to acquire a recommended location point according to the target location, and the recommended location point includes at least one of a virtual location point and a real location point. The real location point is a location point registered in a real location point database, and the virtual location point is a location point generated by data mining and is not registered. The recommended data sending unit 83 is used to generate recommended data according to the recommended location point and send it to the user terminal, and the recommended data includes the recommended location point.

[0186] In some embodiments, the apparatus further comprises:

[0187] The database acquisition unit is used to acquire the virtual location point database.

[0188] In some embodiments, the database acquisition unit includes:

[0189] A historical location point acquisition subunit is used to acquire a historical location point, where the historical location point is a boarding point or alighting point in a historical order;

[0190] A first candidate location point acquisition subunit is used to cluster the historical location points to acquire first candidate location points, where the first candidate location points are historical location points located in a clustering area;

[0191] A filtering subunit, configured to filter the first candidate position points based on a nearest neighbor distance algorithm to obtain second candidate position points;

[0192] a name determination subunit, used to determine a name corresponding to each of the second candidate position points;

[0193] The database generating subunit is used to generate the virtual location point based on the name corresponding to the second candidate location point, and add it to the virtual location point database.

[0194] In some embodiments, the first candidate position point acquisition subunit is used to:

[0195] Clustering the historical location points based on a DBSCAN algorithm to obtain at least one clustering region, wherein the clustering region includes a neighborhood and / or a cluster;

[0196] Determining a density corresponding to the neighborhood;

[0197] The historical location points within the cluster and / or within a neighborhood with a density greater than or equal to a first threshold are determined as the first candidate location points.

[0198] In some embodiments, the filtering subunit is used to:

[0199] Determine the first distance of each first candidate location point in each clustering area based on the nearest neighbor distance algorithm, and filter the first candidate location points whose first distance is greater than or equal to the second threshold;

[0200] The second distance of each clustering area is determined based on the nearest neighbor distance algorithm, and the first candidate location points in the clustering area whose second distance is greater than or equal to the third threshold are filtered.

[0201] In some embodiments, the name determination subunit is used to:

[0202] The name of the second candidate location point is determined according to the priority of a predetermined naming rule.

[0203] In some embodiments, the naming rule includes at least one of the following:

[0204] Determine location point names based on frequently appearing shop or building names;

[0205] Determine location point names based on road intersections or transportation hubs;

[0206] Determine the location point name based on the POI with identification and description;

[0207] Determine the name of the location point based on the village, town and directional word.

[0208] In some embodiments, the recommended location point acquisition unit includes:

[0209] A first acquisition subunit, configured to acquire a real location point matching the target location in the real location point database;

[0210] The second acquisition subunit is configured to acquire a virtual location point matching the target location from the virtual location point database.

[0211] In some embodiments, the apparatus further comprises:

[0212] A category determination unit, used to determine the category of each of the recommended location points, wherein the category includes a main point and a sub-point;

[0213] The sorting unit is used to sort each main point according to a predetermined sorting rule, and sort the sub-points under each main point to generate a sorting result.

[0214] In some embodiments, the recommendation data also includes the ranking result.

[0215] The embodiment of the present invention receives a location acquisition request sent by a user terminal, the location acquisition request includes a target location, obtains a recommended location point according to the target location, the recommended location point includes at least one of a virtual location point and a real location point, the real location point is a location point registered in a real location point database, and the virtual location point is an unregistered location point generated by data mining, generates recommendation data according to the recommended location point and sends it to the user terminal, the recommendation data includes the recommended location point. Therefore, by pushing points of interest and virtual location points together to users for selection, the accuracy of location point recommendation can be improved and the user's operation process can be simplified.

[0216] Fig. 9 Schematic diagram of a device for pushing a location of a user terminal according to an embodiment of the present invention. Fig. 9 As shown, the location push device of the user terminal of the embodiment of the present invention includes a request sending unit 91, a recommended data receiving unit 92 and a display unit 93. The request sending unit 91 is used to send a location acquisition request to the server, and the location acquisition request includes a target location. The recommended data receiving unit 92 is used to receive recommended data sent by the server, and the recommended data includes a recommended location point, and the recommended location point includes at least one of a virtual location point and a real location point. The real location point is a location point registered in the real location point database, and the virtual location point is a location point generated by data mining and is not registered. The display unit 93 is used to display the recommended location point.

[0217] In some embodiments, the recommendation data further includes the ranking result, and the ranking result includes the ranking result of each main point and the ranking result of each sub-point under the main point.

[0218] In some embodiments, the display unit is used to:

[0219] The recommended location points are displayed according to the sorting results.

[0220] The embodiment of the present invention receives a location acquisition request sent by a user terminal, the location acquisition request includes a target location, obtains a recommended location point according to the target location, the recommended location point includes at least one of a virtual location point and a real location point, the real location point is a location point registered in a real location point database, and the virtual location point is an unregistered location point generated by data mining, generates recommendation data according to the recommended location point and sends it to the user terminal, the recommendation data includes the recommended location point. Therefore, by pushing points of interest and virtual location points together to users for selection, the accuracy of location point recommendation can be improved and the user's operation process can be simplified.

[0221] Fig.10 Schematic diagram of an electronic device according to an embodiment of the present invention. Fig.10 As shown, Fig.10 The electronic device shown is a general data processing device, which includes a general computer hardware structure, which at least includes a processor 101 and a memory 102. The processor 101 and the memory 102 are connected via a bus 103. The memory 102 is suitable for storing instructions or programs executable by the processor 101. The processor 101 can be an independent microprocessor or a collection of one or more microprocessors. Thus, the processor 101 executes the instructions stored in the memory 102, thereby executing the method flow of the embodiment of the present invention as described above to realize the processing of data and the control of other devices. The bus 103 connects the above-mentioned multiple components together, and at the same time connects the above-mentioned components to the display controller 104 and the display device and the input / output (I / O) device 105. The input / output (I / O) device 105 can be a mouse, a keyboard, a modem, a network interface, a touch input device, a somatosensory input device, a printer, and other devices known in the art. Typically, the input / output device 105 is connected to the system through an input / output (I / O) controller 106.

[0222] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, devices (equipment) or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present application may adopt a computer program product implemented on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0223] The present application is described with reference to flowcharts of methods, apparatuses (devices) and computer program products according to embodiments of the present application. It should be understood that each process in the flowchart can be implemented by computer program instructions.

[0224] These computer program instructions may be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device that implements the process Figure 1 A function specified in a process or multiple processes.

[0225] These computer program instructions may 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, so that the instructions executed by the processor of the computer or other programmable data processing device produce the instructions for implementing the process Figure 1 A device that specifies functions in a process or multiple processes.

[0226] Another embodiment of the present invention relates to a non-volatile storage medium for storing a computer-readable program, wherein the computer-readable program is used for a computer to execute part or all of the above method embodiments.

[0227] That is, those skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by specifying relevant hardware through a program, and the program is stored in a storage medium, including several instructions for a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0228] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A location push method, characterized in that: The method comprises: Receiving a location acquisition request sent by a user terminal, wherein the location acquisition request includes a target location; Acquire a recommended location point according to the target location, the recommended location point comprising at least one of a virtual location point and a real location point, the real location point being a location point registered in a real location point database, and the virtual location point being a location point generated by data mining and not registered; Recommendation data is generated according to the recommended location point and sent to the user terminal, wherein the recommendation data includes the recommended location point.

2. The method according to claim 1, characterized in that The method further comprises: Get the virtual location database.

3. The method according to claim 2, characterized in that The obtaining of the virtual location point database comprises: Obtaining a historical location point, where the historical location point is a pick-up point or alighting point in a historical order; Clustering the historical location points to obtain first candidate location points, where the first candidate location points are historical location points located in a clustering area; Filtering the first candidate location points based on a nearest neighbor distance algorithm to obtain a second candidate location point; Determine a name corresponding to each of the second candidate position points; The virtual location point is generated based on the name corresponding to the second candidate location point, and is added to the virtual location point database.

4. The method according to claim 3, characterized in that: The clustering of the historical location points to obtain the first candidate location point comprises: Clustering the historical location points based on a DBSCAN algorithm to obtain at least one clustering region, wherein the clustering region includes a neighborhood and / or a cluster; Determining a density corresponding to the neighborhood; The historical location points within the cluster and / or within a neighborhood with a density greater than or equal to a first threshold are determined as the first candidate location points.

5. The method according to claim 3, characterized in that: Filtering the first candidate location points based on the nearest neighbor distance algorithm to obtain the second candidate location points includes at least one of the following: Determine the first distance of each first candidate location point in each clustering area based on the nearest neighbor distance algorithm, and filter the first candidate location points whose first distance is greater than or equal to the second threshold; The second distance of each clustering area is determined based on the nearest neighbor distance algorithm, and the first candidate location points in the clustering area whose second distance is greater than or equal to the third threshold are filtered.

6. The method according to claim 3, characterized in that Determining the name corresponding to each of the second candidate position points includes: The name of the second candidate location point is determined according to the priority of a predetermined naming rule.

7. The method according to claim 6, characterized in that The naming rules include at least one of the following: Determine location point names based on frequently appearing shop or building names; Determine location point names based on road intersections or transportation hubs; Determine the location point name based on the POI with identification and description; Determine the name of the location point based on the village, town and directional word.

8. The method according to claim 2, characterized in that: The acquiring of the recommended location point according to the target location comprises: Acquire a real location point matching the target location in the real location point database; A virtual location point matching the target location is obtained in the virtual location point database.

9. The method according to claim 1, characterized in that: The method further comprises: Determine the category of each of the recommended location points, the category including main points and sub-points; Each main point is sorted according to a predetermined sorting rule, and the sub-points under each main point are sorted to generate a sorting result.

10. The method according to claim 9, characterized in that The recommendation data also includes the ranking result.

11. A location push method, characterized in that: The method comprises: Sending a location acquisition request to a server, wherein the location acquisition request includes a target location; Receiving recommendation data sent by a server, the recommendation data including recommended location points, the recommended location points including at least one of virtual location points and real location points, the real location points are location points registered in a real location point database, and the virtual location points are location points generated by data mining and not registered; The recommended location point is displayed.

12. The method according to claim 11, characterized in that The recommendation data also includes a ranking result, and the ranking result includes a ranking result of each main point and a ranking result of each sub-point under the main point.

13. The method according to claim 12, characterized in that The displaying of the recommended location point comprises: The recommended location points are displayed according to the sorting results.

14. A position push device, characterized in that: The device comprises: A request receiving unit, configured to receive a location acquisition request sent by a user terminal, wherein the location acquisition request includes a target location; a recommended location point acquisition unit, configured to acquire a recommended location point according to the target location, wherein the recommended location point includes at least one of a virtual location point and a real location point, wherein the real location point is a location point registered in a real location point database, and the virtual location point is a location point generated by data mining and not registered; The recommendation data sending unit is used to generate recommendation data according to the recommended location point and send the recommendation data to the user terminal, wherein the recommendation data includes the recommended location point.

15. A position push device, characterized in that: The device comprises: A request sending unit, configured to send a location acquisition request to a server, wherein the location acquisition request includes a target location; a recommendation data receiving unit, configured to receive recommendation data sent by a server, wherein the recommendation data includes a recommended location point, and the recommended location point includes at least one of a virtual location point and a real location point, wherein the real location point is a location point registered in a real location point database, and the virtual location point is a location point generated by data mining and not registered; A display unit is used to display the recommended location point.

16. An electronic device comprising a memory and a processor, characterized in that: The memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method according to any one of claims 1-13.

17. A computer program product, comprising a computer program, characterized in that: When the computer program is executed on a computer, the computer executes the method according to any one of claims 1 to 13.

18. A computer-readable storage medium storing computer program instructions, characterized in that: The computer program instructions, when executed by a processor, implement the method according to any one of claims 1 to 13.

Images