A Location Push Method and Device

Abstract

A location push method and device are disclosed. By receiving a data acquisition request, the data acquisition request includes an initial location point, determining a target point of interest profile according to the initial location point, obtaining at least one candidate point of interest according to the target point of interest profile, determining the scores of the candidate points of interest, and determining the name of the recommended location point according to the scores and pushing it to the user terminal for display. Thereby, the name of the recommended location point can be made to match the user's expectations more closely, reducing the user's operation difficulty and improving the user experience and the order success rate.

Description

Technical Field

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

[0002] Online car-hailing refers to a service for hailing a taxi through an Internet platform, which can provide passengers with more convenient and personalized travel services. Among them, accurately recommending the boarding point has an important impact on improving the travel efficiency of users, reducing waiting time and distance, and increasing the order completion rate. However, the names of the boarding points in the existing technology generally do not match the names expected by users, resulting in users repeatedly operating or canceling orders because they think the location is incorrect, leading to high operation difficulty and poor experience for users, and a low order completion rate. Summary of the Invention

[0003] In view of this, an object of the embodiments of the present invention is to provide a location push method and device, which can make the name of the recommended location point more in line with the user's expectation, reduce the operation difficulty of the user, and improve the user experience and order completion rate.

[0004] In a first aspect, an embodiment of the present invention provides a location push method, and the method includes:

[0005] Receiving a data acquisition request, where the data acquisition request includes an initial location point;

[0006] Determining a target interest point profile according to the initial location point;

[0007] Obtaining at least one candidate interest point according to the target interest point profile;

[0008] Determining the score of each candidate interest point;

[0009] Determining the name of the recommended location point according to the score; and

[0010] Sending the name of the recommended location point to the user terminal.

[0011] In some embodiments, the method further includes:

[0012] Determining the recommended location point according to the initial location point.

[0013] In some embodiments, the determining the target interest point profile according to the initial location point includes:

[0014] Determining a profile set according to the initial location point, where the profile set includes interest point profiles within a predetermined range of the initial location point;

[0015] Determining the distance between the center of each interest point profile in the profile set and the initial location point; and

[0016] Determine the target interest point contour as the interest point contour with the minimum distance from the initial position point.

[0017] In some embodiments, the candidate interest points include at least one of the following:

[0018] Interest points on the edge of the target interest point contour;

[0019] Interest points within the target interest point contour;

[0020] Interest points obtained by other recall methods.

[0021] In some embodiments, the determining the scores of the candidate interest points includes:

[0022] Adjust the weights of the candidate interest points;

[0023] Determine the scores of the candidate interest points according to the adjusted weights.

[0024] In some embodiments, the adjusting the weights of the candidate interest points includes:

[0025] Determine the initial weights of the candidate interest points;

[0026] Determine the positional relationship between the initial position point and the target interest point contour;

[0027] In response to the initial position point not being within the target interest point contour, adjust the initial weights of the candidate interest points according to the distances between the initial position point and the candidate interest points to obtain first intermediate weights;

[0028] In response to the initial position point being within the target interest point contour, determine the type of the target interest point contour;

[0029] In response to the type of the target interest point contour being a predetermined type, adjust the initial weights according to the floors, popularity, and interest point types of the candidate interest points to obtain second intermediate weights; and

[0030] In response to the type of the target interest point contour not being a predetermined type, adjust the initial weights of the candidate interest points according to the distances between the initial position point and the candidate interest points to obtain third intermediate weights.

[0031] In some embodiments, the adjusting the weights of the candidate interest points further includes:

[0032] Adjust the second intermediate weights according to the distances between the initial position point and the candidate interest points to obtain fourth intermediate weights.

[0033] In some embodiments, the adjustment of the weights of the candidate points of interest further includes:

[0034] Adjusting the first intermediate weight, the third intermediate weight, and the fourth intermediate weight according to at least one of the position, type, and historical orders of the candidate points of interest to obtain a fifth intermediate weight.

[0035] In some embodiments, the specific determination of the scores of the candidate points of interest is as follows:

[0036] Determining the scores of the candidate points of interest according to the fifth intermediate weight.

[0037] In some embodiments, the specific determination of the name of the recommended location point according to the score is as follows:

[0038] Determining the main body of the name of the recommended location point as the name of the point of interest with the highest score.

[0039] In a second aspect, an embodiment of the present invention provides a location push device, which includes:

[0040] A request receiving unit, configured to receive a data acquisition request, where the data acquisition request includes an initial location point;

[0041] A target point of interest profile determination unit, configured to determine a target point of interest profile according to the initial location point;

[0042] A candidate point of interest acquisition unit, configured to acquire at least one candidate point of interest according to the target point of interest profile;

[0043] A score determination unit, configured to determine the scores of the candidate points of interest;

[0044] A name determination unit, configured to determine the name of the recommended location point according to the score; and

[0045] A name sending unit, configured to send the name of the recommended location point to a user terminal.

[0046] 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 in the first aspect.

[0047] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which computer program instructions are stored, and the computer program instructions, when executed by a processor, implement the method as described in the first aspect.

[0048] The technical solution of the embodiment of the present invention receives a data acquisition request, where the data acquisition request includes an initial position point, determines a target interest point profile according to the initial position point, obtains at least one candidate interest point according to the target interest point profile, determines the scores of the candidate interest points, and determines the name of the recommended position point according to the scores and pushes it to the user terminal for display. Thereby, the name of the recommended position point can be made more in line with the user's expectations, reducing the user's operation difficulty and improving the user experience and the order success rate. Description of the Drawings

[0049] 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:

[0050] Figure 1 is a schematic diagram of the online car-hailing system according to the embodiment of the present invention;

[0051] Figure 2 is a schematic diagram of the order placement interface according to an embodiment of the present invention;

[0052] Figure 3 is a flowchart of the position push method according to the embodiment of the present invention;

[0053] Figure 4 is a flowchart of determining the target interest point profile according to the embodiment of the present invention;

[0054] Figure 5 is a flowchart of determining the scores according to the embodiment of the present invention;

[0055] Figure 6 is a flowchart of adjusting the weights according to the embodiment of the present invention;

[0056] Figure 7 is a flowchart of obtaining the fifth intermediate weight according to the embodiment of the present invention;

[0057] Figure 8 is a schematic diagram of the order placement interface according to another embodiment of the present invention;

[0058] Figure 9 is a schematic diagram of the position push device according to the embodiment of the present invention;

[0059] Figure 10 is a schematic diagram of the electronic device according to the embodiment of the present invention. Detailed Embodiments

[0060] The present invention will be described based on embodiments below, but the present invention is not limited to these embodiments only. In the following detailed description of the present invention, some specific details are described in detail. Those skilled in the art can fully understand the present invention without the description of these details. In order to avoid obscuring the essence of the present invention, well-known methods, processes, procedures, elements and circuits are not described in detail.

[0061] 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.

[0062] Unless the context clearly requires otherwise, words such as "including", "comprising" and the like in the entire application document shall be construed in an inclusive sense rather than an exclusive or exhaustive sense; that is, the meaning of "including but not limited to".

[0063] In the description of the present invention, it should be understood that terms such as "first", "second" etc. are only used for descriptive purposes and cannot be construed as indicating or implying relative importance. In addition, in the description of the present invention, unless otherwise specified, the meaning of "a plurality of" is two or more.

[0064] Figure 1 is a schematic diagram of the online car-hailing system according to an embodiment of the present invention. As Figure 1 shown, the online car-hailing system according to an embodiment of the present invention includes a server 1, a user terminal 2 and a driver terminal 3. Among them, the user terminal 2 and the driver terminal 3 are communicatively connected to the server 1.

[0065] In this embodiment, the user terminal 2 is a terminal device used by a car-hailing user and can place an order through an APP (application), a web page, a mini-program, etc.

[0066] Among them, the user terminal 2 can be implemented by terminal devices such as mobile phones, tablet computers, laptop computers, desktop computers, etc.

[0067] In this embodiment, the driver terminal 3 is a terminal device used by a driver and can process orders through an APP (application), a web page, a mini-program, etc., for example, grab an order, accept an order, cancel an order, etc.

[0068] Among them, the driver terminal 3 can be implemented by terminal devices such as mobile phones, tablet computers, in-vehicle terminals, etc.

[0069] In this embodiment, the server 1 is a platform server, which can be implemented by a single server or a server cluster composed of multiple servers.

[0070] Figure 2It is a schematic diagram of an order placement interface according to an embodiment of the present invention. As Figure 2 shown, the order placement interface of the embodiment of the present invention is displayed on the display screen of the user terminal, and includes an electronic map A1 and an input box A4. Among them, the electronic map A1 shows the position A2 currently selected by the user, and the pick-up position point A3 recommended to the user.

[0071] Among them, the electronic map A1 shows the map within a certain range around the position currently selected by the user, and can be zoomed in or out through manual operations.

[0072] The position A2 currently selected by the user can be the default position. The default position can be the positioning of the user terminal, and the name "xx store" of the currently selected position is displayed. Alternatively, the position A2 currently selected by the user can be obtained by the user dragging the map. Specifically, a positioning label is displayed on the map (such as Figure 2 the mark composed of the black vertical line and the origin above xx store in the figure). When the user drags the map, the relative position of the positioning label to the display screen remains unchanged, but the relative position of the positioning label to the electronic map changes. When the user stops dragging, the position pointed to by the positioning label is the position currently selected by the user. Or, the position A2 currently selected by the user can be obtained by the user clicking on the map. Specifically, when the user clicks on a certain position on the electronic map, the clicked position is determined as the position A2 currently selected by the user.

[0073] Further, after the user terminal obtains the position currently selected by the user, it sends a data acquisition request to the server. The server obtains the recommended pick-up position point according to the position currently selected by the user and sends it to the user terminal, and the user terminal displays the pick-up position point A3.

[0074] In the input box A4, the recommended pick-up position point is displayed (such as "You will board from the east side of xx store"). At the same time, the input box A4 includes a destination input box (such as "Please enter the destination" in the figure), and the user can enter the destination to be reached through the destination input box.

[0075] At the same time, if the user feels that the pick-up position point is not accurate, the pick-up position point can also be adjusted by adjusting the position A2 currently selected by the user. Among them, adjusting the position A2 currently selected by the user can be achieved by dragging the electronic map or clicking on the electronic map.

[0076] Thus, functions such as inputting the destination, adjusting the pick-up point, and placing an order can be realized through the order placement interface.

[0077] Figure 3 It is a flowchart of the position push method according to an embodiment of the present invention. In Figure 3 the shown embodiment, the position push method is executed by the server, and specifically includes the following steps:

[0078] Step S100: Receive a data acquisition request, where the data acquisition request includes an initial position point.

[0079] In this embodiment, when a passenger has a need to take a taxi, an order placement interface as shown is opened through methods such as an APP, a web page, or a mini-program. At this time, the user terminal obtains the default position (usually the positioning of the user terminal) and sends it to the server. The server obtains the boarding position point based on the default position and sends it to the user terminal, and the user terminal displays the boarding position point. Figure 2 If the displayed boarding position point is not the boarding position point expected by the user, the user can select a new position point by dragging the electronic map or clicking on the electronic map. The selected new position point is the initial position point. The user terminal generates a data acquisition request based on the initial position point and sends it to the server, and the data acquisition request includes the initial position point.

[0080] It should be understood that this embodiment of the present invention takes the scenario where the user is not satisfied with the recommended boarding position point for this time and re-selects the position point as an example for description, but the application scenario of the position push method in this embodiment of the present invention is not limited. For example, the position push method can be applicable to the first time the user sends a data acquisition request to the server after opening the order placement interface, or it can also be applicable to the case where if the user is not satisfied with the recommended boarding position point continuously for multiple times and adjusts the position, and then sends a data acquisition request to the server for the Nth time (N is a positive integer greater than or equal to 2).

[0081]

[0082] Step S200: Determine the target interest point contour according to the initial position point.

[0083] In this embodiment, the server determines the target interest point contour according to the initial position point.

[0084] Figure 4 Specifically, Figure 4 is the flowchart of determining the target interest point contour in this embodiment of the present invention. As shown in, the server determines the target interest point contour according to the initial position point, including the following steps:

[0085]

[0086] Step S210: Determine a contour set according to the initial position point.

[0087] In this embodiment, the server obtains the interest point contours within a predetermined range of the initial position point and adds the obtained interest point contours to the contour set.

[0088] ​​​In an alternative implementation, the server obtains the point-of-interest profiles within a predetermined range of the initial position point specifically as follows: The server obtains a circle centered at the initial position point with a predetermined value as the radius, and determines the point-of-interest profiles within the circle and / or intersecting with the circle as the point-of-interest profiles within a predetermined range of the initial position point.

[0089] In another alternative implementation, the server obtains the point-of-interest profiles within a predetermined range of the initial position point specifically as follows: The server obtains the distances between the initial position point and the centers of the respective point-of-interest profiles, and determines the point-of-interest profiles with distances less than or equal to a predetermined threshold as the point-of-interest profiles within a predetermined range of the initial position point.

[0090] It should be understood that the embodiments of the present invention do not limit the specific implementation manners of obtaining the point-of-interest profiles within a predetermined range of the initial position point, and it can be implemented based on various existing manners.

[0091] Step S220: Determine the distances between the centers of the respective point-of-interest profiles in the profile set and the initial position point.

[0092] In this embodiment, the server obtains the centers of the respective point-of-interest profiles in the profile set and determines the distances between the centers of the respective point-of-interest profiles and the initial position point.

[0093] Among them, obtaining the centers of the point-of-interest profiles can be implemented based on various existing manners. For example, the centers of the respective point-of-interest profiles can be manually marked in advance, or the centers of the point-of-interest profiles can be obtained based on a predetermined algorithm, where the predetermined algorithm can be a machine learning algorithm, a deep learning algorithm, etc.

[0094] After obtaining the centers of the point-of-interest profiles, obtain the coordinates of the centers and the coordinates of the initial position point. The coordinates can be longitude and latitude coordinates, and calculate the distance between the two based on the coordinates.

[0095] Step S230: Determine the point-of-interest profile with the smallest distance from the initial position point as the target point-of-interest profile.

[0096] In this embodiment, after the server determines the distances between the centers of the respective point-of-interest profiles in the profile set and the initial position point, it determines the point-of-interest profile with the smallest distance from the initial position point as the target point-of-interest profile.

[0097] Step S300: Obtain at least one candidate point of interest according to the target point-of-interest profile.

[0098] In this embodiment, a point of interest (POI) refers to a house, a store, a mailbox, a bus stop, a door, etc.

[0099] Among them, the candidate points of interest include at least one of the following:

[0100] A point of interest on the edge of the target point of interest contour;

[0101] A point of interest within the target point of interest contour;

[0102] A point of interest obtained through other recall methods.

[0103] In the embodiment of the present invention, taking the simultaneous inclusion of the above three as an example for illustration, the server obtains a point of interest on the edge of the target point of interest contour, a point of interest within the target point of interest contour, and a point of interest obtained through other recall methods, and determines these points of interest as candidate points of interest.

[0104] Among them, the points of interest of other recall methods can be implemented based on various existing methods. For example, points of interest within a predetermined range of the initial position point, or points of interest related to the initial position point obtained based on historical data.

[0105] Step S400: Determine the scores of each candidate point of interest.

[0106] In this embodiment, the server determines the scores of each candidate point of interest.

[0107] Specifically, Figure 5 is a flowchart of determining scores in the embodiment of the present invention. As Figure 5 shown, the server determines the scores of each candidate point of interest including the following steps:

[0108] Step S410: Adjust the weights of the candidate points of interest.

[0109] Figure 6 is a flowchart of adjusting weights in the embodiment of the present invention. In Figure 6 the shown embodiment, adjusting the weights of the candidate points of interest includes the following steps:

[0110] Step S411: Select a candidate point of interest.

[0111] In this embodiment, the server selects a candidate point of interest from multiple candidate points of interest.

[0112] Step S412: Determine the initial weight of the candidate point of interest.

[0113] In this embodiment, after the server selects a candidate point of interest, it determines the initial weight of this candidate point of interest.

[0114] Specifically, for each candidate point of interest, it is necessary to evaluate from multiple dimensions, and the dimensions include boarding popularity, alighting popularity, retrieval times, distance, etc. Each dimension corresponds to a weight, and the server obtains the initial weights of each dimension. Among them, the initial weight can be a preset initial value. For example, an initial value is set for each dimension in advance, and this initial value is the initial weight. Or, the initial weight can be a value determined according to the actual information of each dimension. For example, the corresponding initial value is determined according to the actual values of boarding popularity, alighting popularity, retrieval times, and distance.

[0115] Step S413: The candidate point of interest is within the target point of interest contour.

[0116] In this embodiment, the server detects whether the candidate point of interest is within the target point of interest contour.

[0117] If not, go to step S414.

[0118] If so, go to step S415.

[0119] Step S414: Adjust the initial weight of the candidate point of interest according to the distance between the initial position point and the candidate point of interest to obtain the first intermediate weight.

[0120] In this embodiment, if the candidate point of interest is not within the target point of interest contour, the initial weight of the candidate point of interest is adjusted according to the distance between the initial position point and the candidate point of interest to obtain the first intermediate weight. Among them, the smaller the distance between the initial position point and the candidate point of interest, the greater the weight. On the contrary, the greater the distance between the initial position point and the candidate point of interest, the smaller the weight.

[0121] It should be noted that adjusting the initial weight in the embodiment of the present invention to obtain the first intermediate weight means adjusting the weight value of the distance dimension in the initial weight, and the weight values of other dimensions remain unchanged.

[0122] Step S415: The target point of interest contour is of a predetermined type.

[0123] The server determines whether the target point of interest contour is of a predetermined type. The predetermined type is a point of interest with multiple layers, and the boarding point may be on two or more of the multiple layers. For example, the predetermined type may be a comprehensive shopping mall type, and the boarding point of the comprehensive shopping mall type may be on any one of the basement first floor, basement second floor, first floor, second floor, etc.

[0124] If not, go to step S416.

[0125] If so, go to step S417.

[0126] Step S416. Adjust the initial weight of the candidate interest points according to the distance between the initial position point and the candidate interest points to obtain the third intermediate weight.

[0127] If the target interest point profile is not of a predetermined type, adjust the initial weight of the candidate interest points according to the distance between the initial position point and the candidate interest points to obtain the third intermediate weight. Among them, the smaller the distance between the initial position point and the candidate interest point, the greater the weight; conversely, the greater the distance between the initial position point and the candidate interest point, the smaller the weight.

[0128] It should be noted that adjusting the initial weight to obtain the third intermediate weight in the embodiments of the present invention means adjusting the weight value in the distance dimension of the initial weight, and the weight values in other dimensions remain unchanged.

[0129] Step S417. Adjust the initial weight according to the floor, popularity, and interest point type of the candidate interest points to obtain the second intermediate weight.

[0130] As described above, the predetermined type is an interest point with multiple floors, and the boarding point may be on two or more of the multiple floors. Therefore, if the target interest point profile is of the predetermined type, adjust the initial weight according to the floor and popularity of the candidate interest points to obtain the second intermediate weight.

[0131] Specifically, adjusting the initial weight to obtain the second intermediate weight specifically includes:

[0132] If the candidate interest point is underground or on a high floor above the second floor above ground, strongly reduce the weight of the floor dimension. The strong reduction of weight means that the amplitude of reducing the weight value is large.

[0133] If the candidate interest point is on the second floor, slightly reduce the weight of the floor dimension. Slightly reducing the weight means that the amplitude of reducing the weight value is small.

[0134] If the candidate interest point is on the first floor, adjust the initial weight according to the popularity and interest point type of the candidate interest point. Among them, the popularity includes relatively low popularity, low popularity, and high popularity. The interest point type includes door and non - door. Among them, the interest point type being a door means that the candidate interest point is a door, and the interest point type being a non - door means that the candidate interest point is not a door. The door can be the main door, side door, hall door, etc.

[0135] Among them, adjusting the initial weight according to the popularity and interest point type of the candidate interest point includes:

[0136] If the candidate interest point has relatively low popularity and is a non - door, slightly reduce the initial weight value. Slightly reducing the weight means that the amplitude of reducing the weight value is low. Specifically, slightly reduce the weight values corresponding to the popularity and the candidate interest point type.

[0137] If the candidate point of interest has low popularity, the initial weight value is downgraded. Downgrading means reducing the weight value by a normal margin. Specifically, the weight value corresponding to the popularity is downgraded.

[0138] If the candidate point of interest has high popularity, the initial weight value is upgraded. Upgrading means increasing the weight value. Specifically, the weight value corresponding to the popularity is upgraded.

[0139] It should be noted that in the embodiments of the present invention, the weight adjustment is achieved through a hierarchical classification method, including four levels: low downgrading, downgrading, strong downgrading, and upgrading. Each level can be adjusted in a predetermined manner. For example, low downgrading, downgrading, and strong downgrading are respectively reducing the numerical values by 0.1, 0.2, and 0.3, and upgrading can be 0.2. Or, low downgrading, downgrading, and strong downgrading are respectively reducing by 10%, 20%, and 30% on the basis of the original numerical value, and upgrading can be 20%. At the same time, the initial weight includes the initial values corresponding to each dimension. Adjusting the weight value specifically refers to adjusting the weight value of the dimension related to the corresponding index. For example, if the index is popularity, then the weight value related to popularity is adjusted; if the index is the type of point of interest, then the weight value related to the type of point of interest is adjusted.

[0140] Step S418: Adjust the second intermediate weight according to the distance between the initial position point and the candidate point of interest to obtain the fourth intermediate weight.

[0141] In this embodiment, after obtaining the second intermediate weight, the second intermediate weight of the candidate point of interest is adjusted according to the distance between the initial position point and the candidate point of interest to obtain the fourth intermediate weight. Among them, the smaller the distance between the initial position point and the candidate point of interest, the greater the weight; conversely, the larger the distance between the initial position point and the candidate point of interest, the smaller the weight.

[0142] It should be noted that in the embodiments of the present invention, adjusting the second intermediate weight to obtain the fourth intermediate weight means adjusting the weight value of the distance dimension in the initial weight, and the weight values of other dimensions remain unchanged.

[0143] Step S419: Obtain the fifth intermediate weight according to at least one of the position, type, and historical orders of the candidate point of interest.

[0144] In this embodiment, after obtaining the first intermediate weight, the third intermediate weight, or the fourth intermediate weight corresponding to the candidate point of interest, the first intermediate weight, the third intermediate weight, and the fourth intermediate weight are adjusted according to at least one of the position, type, and historical orders of the candidate point of interest to obtain the fifth intermediate weight.

[0145] Figure 7 is the flowchart of obtaining the fifth intermediate weight in the embodiments of the present invention. In Figure 7In the illustrated embodiment, the process is divided into four parts by a dashed box. Among them, the upper part is divided into left, middle, and right parts, and there is a lower part. The upper left part includes steps S41911 - S41914 to adjust the weight according to the position of the candidate point of interest. The upper middle part includes steps S41915 - S41925 to adjust the weight according to the type of the candidate point of interest. The upper right part includes steps S41927 - S41931 to adjust the weight according to the historical orders of the candidate point of interest. Specifically, obtaining the fifth intermediate weight according to at least one of the position, type, and historical order of the candidate point of interest includes the following steps:

[0146] Step S41911, the user drags the map.

[0147] As described in step S100, an application scenario of the embodiment of the present invention is that the user is not satisfied with the pick-up location point recommended last time and re-selects the location point by dragging the map.

[0148] Step S41912, on the opposite side of the original point of interest.

[0149] In this embodiment, the server determines whether the initial location point is on the opposite side of the original point of interest.

[0150] Further, the user is not satisfied with the pick-up location point recommended last time and re-selects the location point by dragging the map. The point of interest obtained last time is the original point of interest. Being on the opposite side of the original point of interest means being on the opposite side of the road of the original point of interest, that is, there is a road separating the initial location point and the original point of interest.

[0151] Specifically, in the scenario where the user changes the location point by dragging the map, after obtaining the candidate point of interest, it is determined whether the candidate point of interest is the original point of interest. The original point of interest refers to the point of interest obtained last time. If the candidate point of interest is the original point of interest, then it is determined whether the candidate point of interest is on the opposite side of the initial location point.

[0152] If not, then proceed to step S41913.

[0153] If so, then proceed to step S41914.

[0154] Step S41913, no special processing.

[0155] If the initial location point is not on the opposite side of the original point of interest, then there is no special processing. No special processing means that the weight does not need to be adjusted.

[0156] Step S41914, impose a penalty on the original point of interest.

[0157] If the initial location point is on the opposite side of the original point of interest, then impose a penalty on the original point of interest. Among them, imposing a penalty means reducing the weight values of each dimension in the original point of interest.

[0158] In the embodiment of the present invention, the penalty for a candidate point of interest and the initial position point when crossing a road is strengthened. That is, assuming that the map is dragged to the opposite side of the point of interest, a penalty will be added to the candidate point of interest for crossing the road, and the exposure will be reduced, so as to increase the weight of the candidate points of interest on the same side nearby, and try to make the dragged map point and the named candidate point of interest not cross the road.

[0159] Step S41915, all candidate points of interest.

[0160] In this embodiment, all candidate points of interest are processed.

[0161] Step S41916, whether it is a relatively far and low-heat bus stop.

[0162] Judge whether the candidate point of interest is a relatively far and low-heat bus stop. Among them, relatively far means that the distance between the candidate point of interest and the initial position point is relatively far. Low heat means low popularity.

[0163] If so, go to step S41917.

[0164] If not, go to step S41918.

[0165] Step S41917, reduce the weight.

[0166] Judge whether the candidate point of interest is a relatively far and low-heat bus stop. If so, perform weight reduction processing.

[0167] Step S41918, whether it is on the blacklist.

[0168] Judge whether the candidate point of interest is a relatively far and low-heat bus stop. If not, judge whether the candidate point of interest is on the blacklist. Among them, the blacklist can be determined according to berths, incoming calls, street power banks, toilets, restrooms, etc.

[0169] If so, go to step S41919.

[0170] If not, go to step S41920.

[0171] Step S41919, do not expose.

[0172] Judge whether the candidate point of interest is on the blacklist. If so, do not expose it. Among them, not exposing means adjusting the weight value of the candidate point of interest to 0 entirely.

[0173] Step S41920, whether it is extremely low priority.

[0174] Determine whether the candidate point of interest is on the blacklist. If not, determine whether the candidate point of interest is of extremely low priority. Extremely low priority means that there are other types of POIs within 150m. Try to reduce the display of the following POI types: road names, house numbers, road entrances and exits, bridges, and reduce the display by deweighting.

[0175] If so, go to step S41921.

[0176] If not, go to step S41922.

[0177] Step S41921: Deweight.

[0178] Determine whether the candidate point of interest is of extremely low priority. If so, perform deweighting processing.

[0179] Step S41922: Whether it is of low priority.

[0180] Determine whether the candidate point of interest is of extremely low priority. If not, determine whether the candidate point of interest is of low priority. Low priority means that the place name address is an intersection, a parking lot, a low-heat shopping area (furniture, home building materials, monitoring points), etc., and reduce the display by deweighting.

[0181] If so, go to step S41923.

[0182] If not, go to step S41924.

[0183] Step S41923: Deweight.

[0184] Determine whether the candidate point of interest is of low priority. If so, perform deweighting processing.

[0185] Step S41924: Whether it is of high priority.

[0186] Determine whether the candidate point of interest is of low priority. If not, determine whether the candidate point of interest is of high priority. High priority means a relatively popular hotel, motel, or inn within 50m, a relatively popular door point within 50m, a relatively popular bank within 50m, and a relatively popular subway entrance within 100m.

[0187] If so, go to step S41925.

[0188] If not, go to step S41926.

[0189] Step S41925: Boost weight.

[0190] Determine whether the candidate point of interest is of high priority. If so, perform boosting weight processing.

[0191] Step S41926: No special processing.

[0192] Determine whether the candidate point of interest is of high priority. If not, no special processing is required. No special processing means that the weight does not need to be adjusted.

[0193] Step S41927: The historical order meets the predetermined conditions.

[0194] In this embodiment, for each candidate point of interest, it is determined whether the historical order meets the predetermined conditions. Among them, the predetermined conditions can be set according to the actual situation. For example, the number of orders within a predetermined time within the predetermined range of the candidate point of interest is greater than the predetermined threshold.

[0195] In a specific implementation, the predetermined condition can be that the monthly order quantity within 15 meters of the candidate point of interest is greater than 5.

[0196] Step S41928: Weak weight increase.

[0197] If the historical order meets the predetermined conditions, weak weight increase is performed. Among them, weak weight increase means that the weight value is increased by a small margin.

[0198] Step S41929: Whether it is a non-building number with extremely low heat.

[0199] If the historical order does not meet the predetermined conditions, it is determined whether the candidate point of interest is a non-building number with extremely low heat. Among them, a non-building number with extremely low heat means that the candidate point of interest has extremely low heat and is not a building number.

[0200] Step S41930: Weight reduction.

[0201] If the candidate point of interest is a non-building number with extremely low heat, weight reduction processing is performed.

[0202] Step S41931: No special processing.

[0203] If the candidate point of interest is not a non-building number with extremely low heat, no special processing is required. No special processing means that the weight does not need to be adjusted.

[0204] Step S41932: Obtain the fifth intermediate weight.

[0205] In this embodiment, the above adjusted weight is determined as the fifth intermediate weight.

[0206] Step S420: Determine the scores of the candidate points of interest according to the adjusted weights.

[0207] In this embodiment, determining the scores of the candidate points of interest according to the adjusted weights specifically means: determining the scores of the candidate points of interest according to the fifth intermediate weight.

[0208] More specifically, according to the fifth intermediate weight, each dimension of the candidate point of interest is weighted and summed to obtain the score. Before the weighted summation, the indicators corresponding to each dimension need to be quantified according to the actual situation. Quantification means assigning values to each dimension, and then performing weighted summation according to the weights to obtain the score.

[0209] Step S500: Determine the name of the recommended location point according to the score.

[0210] In this embodiment, the specific method of determining the name of the recommended location point according to the score is: determining the name of the point of interest with the highest score as the main body of the name of the recommended location point.

[0211] In this embodiment, obtain the candidate point of interest with the highest score, and determine the name of the point of interest with the highest score as the main body of the name of the recommended location point. Then, expand the main body according to information such as the actual orientation to obtain the name of the recommended location point.

[0212] For example, assume that the name of the candidate point of interest with the highest score is "XX Community", and the recommended location point is on the east side of the community. Then, the finally obtained name of the recommended location point is "East Side of XX Community".

[0213] Step S600: Send the name of the recommended location point to the user terminal.

[0214] In this embodiment, after obtaining the name of the recommended location point, send it to the user terminal so that the user terminal can display the name of the recommended location point.

[0215] Figure 8 It is a schematic diagram of the order placement interface of another embodiment of the present invention. As Figure 8 shown, the order placement interface of the embodiment of the present invention is displayed on the display screen of the user terminal, including an electronic map B1 and an input box B4. Among them, the position B2 currently selected by the user and the pick-up location point B3 recommended to the user are displayed on the electronic map B1.

[0216] Combined with Figure 2 In the embodiment shown, assume that the previous order placement interface is Figure 2 , the name of the recommended pick-up location point is "East Side of XX Store", and the user is not satisfied with this name. The position is dragged from Figure 2 A2 shown to Figure 8 B2 shown. After dragging, the recommended pick-up location point does not change, but the name of the recommended pick-up location point changes from "East Side of XX Store" to "East Side of XX Building", which is more in line with the name expected by the user.

[0217] When the user manually drags the map to modify the pick-up point, the existing technology is not sensitive enough to distance and overemphasizes popularity. It may reverse-geocode to a poi that is hotter but farther away in the vicinity, and cannot reverse-geocode to a poi that is closer and hotter to the point where the map is dragged. There may be a situation where the name of the pick-up point has a low or even no correlation with the poi where the user pins after dragging the map. For example, when the user pins at point X after dragging the map, the recommended pick-up point is Y. At this time, the user will be quite confused and think that their map-dragging behavior is ineffective, thus giving up placing an order, affecting the transaction, and even leading to incoming calls for complaints. However, the fact that the user drags the map indicates that the user has a target poi. In the embodiments of the present invention, based on the user's map-dragging behavior, the contour of the poi closest to the map-dragging request point is first found, then the weight of distance is increased, and the priority of poi types is classified and adjusted, so that the name of the finally presented pick-up point is strongly correlated with the poi where the user pins after dragging the map. After adjusting the weights according to the above rules, all recalled pois will have a comprehensive score, which reflects the popularity, perceptibility, distance from the request point, etc. of the poi. The pois are sorted according to the level of the comprehensive score, and finally the poi with the highest ranking is presented as the main body of the pick-up point name.

[0218] In the embodiments of the present invention, by receiving a data acquisition request, the data acquisition request includes an initial position point, a target poi contour is determined according to the initial position point, at least one candidate poi is acquired according to the target poi contour, the scores of the candidate pois are determined, and the name of the recommended position point is determined according to the scores and pushed to the user terminal for display. Thereby, the name of the recommended position point can be made to better match the user's expectation, reduce the operation difficulty of the user, and improve the user experience and order success rate.

[0219] Figure 9 It is a schematic diagram of the position push device in the embodiments of the present invention. In Figure 9 In the shown embodiment, the position push device includes a request receiving unit 91, a target poi contour determination unit 92, a candidate poi acquisition unit 93, a score determination unit 94, a name determination unit 95, and a name sending unit 96. Among them, the request receiving unit 91 is used to receive a data acquisition request, and the data acquisition request includes an initial position point. The target poi contour determination unit 92 is used to determine a target poi contour according to the initial position point. The candidate poi acquisition unit 93 is used to acquire at least one candidate poi according to the target poi contour. The score determination unit 94 is used to determine the scores of the candidate pois. The name determination unit 95 is used to determine the name of the recommended position point according to the scores. The name sending unit 96 is used to send the name of the recommended position point to the user terminal.

[0220] In some embodiments, the device further includes:

[0221] A recommended position point determination unit, which is used to determine the recommended position point according to the initial position point.

[0222] In some embodiments, the target point of interest profile determination unit includes:

[0223] A profile set determination subunit, configured to determine a profile set according to the initial position point, where the profile set includes point of interest profiles within a predetermined range of the initial position point;

[0224] A distance determination subunit, configured to determine the distance between the center of each point of interest profile in the profile set and the initial position point; and

[0225] A target point of interest profile determination subunit, configured to determine the point of interest profile with the smallest distance from the initial position point as the target point of interest profile.

[0226] In some embodiments, the candidate points of interest include at least one of the following:

[0227] Points of interest on the edge of the target point of interest profile;

[0228] Points of interest within the target point of interest profile;

[0229] Points of interest obtained by other recall methods.

[0230] In some embodiments, the score determination unit includes:

[0231] A weight adjustment subunit, configured to adjust the weights of the candidate points of interest;

[0232] A score determination subunit, configured to determine the scores of the candidate points of interest according to the adjusted weights.

[0233] In some embodiments, the weight adjustment subunit includes:

[0234] An initial weight determination module, configured to determine the initial weights of the candidate points of interest;

[0235] A position relationship determination module, configured to determine the position relationship between the initial position point and the target point of interest profile;

[0236] A first intermediate weight acquisition module, configured to, in response to the initial position point not being within the target point of interest profile, adjust the initial weights of the candidate points of interest according to the distances between the initial position point and the candidate points of interest to obtain first intermediate weights;

[0237] A profile type determination module, configured to, in response to the initial position point being within the target point of interest profile, determine the type of the target point of interest profile;

[0238] A second intermediate weight acquisition module, configured to, in response to the type of the target interest point profile being a predetermined type, adjust the initial weight according to the floors, popularity, and interest point types of the candidate interest points to obtain a second intermediate weight; and

[0239] A third intermediate weight acquisition module, configured to, in response to the type of the target interest point profile not being a predetermined type, adjust the initial weight of the candidate interest points according to the distances between the initial position point and the candidate interest points to obtain a third intermediate weight.

[0240] In some embodiments, the weight adjustment subunit further includes:

[0241] A fourth intermediate weight acquisition module, configured to adjust the second intermediate weight according to the distances between the initial position point and the candidate interest points to obtain a fourth intermediate weight.

[0242] In some embodiments, the weight adjustment subunit further includes:

[0243] A fifth intermediate weight acquisition module, configured to adjust the first intermediate weight, the third intermediate weight, and the fourth intermediate weight according to at least one of the positions, types, and historical orders of the candidate interest points to obtain a fifth intermediate weight.

[0244] In some embodiments, the scoring determination unit is specifically configured to:

[0245] Determine the scores of the candidate interest points according to the fifth intermediate weight.

[0246] In some embodiments, the name determination unit is specifically configured to:

[0247] Determine the name of the interest point with the highest score as the main body of the name of the recommended position point.

[0248] In the embodiments of the present invention, by receiving a data acquisition request, the data acquisition request includes an initial position point, determining a target interest point profile according to the initial position point, obtaining at least one candidate interest point according to the target interest point profile, determining the scores of the candidate interest points, determining the name of the recommended position point according to the scores and pushing it to the user terminal for display. Thereby, the name of the recommended position point can be made more matching with the user's expectation, reducing the operation difficulty of the user and improving the user experience and the order success rate.

[0249] Figure 10 It is a schematic diagram of an electronic device according to an embodiment of the present invention. Figure 10The electronic device shown is a general-purpose data processing device, which includes a general computer hardware structure, and at least includes a processor 101 and a memory 102. The processor 101 and the memory 102 are connected by a bus 103. The memory 102 is adapted to store 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, by executing the instructions stored in the memory 102, the processor 101 executes the method flow of the embodiment of the present invention as described above to implement data processing and 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 a display controller 104, a display device, and an 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 body sensing input device, a printer, and other devices well known in the art. Typically, the input / output (I / O) device 105 is connected to the system through an input / output (I / O) controller 106.

[0250] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a device (equipment), or a computer program product. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can be implemented as a computer program product on one or more computer-readable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer-usable program code.

[0251] The present invention 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.

[0252] 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, so that the instructions stored in the computer-readable memory produce a manufactured article including an instruction device, and the instruction device implements the process Figure 1 the functions specified in one process or multiple processes.

[0253] These computer program instructions can also be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices produce a device for implementing the functions specified in Figure 1 one process or multiple processes.

[0254] 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 a 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.

[0255] The foregoing are only the preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, various modifications and changes can be made to the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A location push method, characterized in that: The method comprises: receiving a data acquisition request, wherein the data acquisition request includes an initial position point; Determine the target interest point outline according to the initial position point; Acquire at least one candidate interest point according to the target interest point outline; Determine the score of each candidate point of interest; Determining the name of the recommended location point according to the score; and Sending the name of the recommended location point to the user terminal; The step of determining the score of each candidate interest point includes: Adjusting the weight of the candidate interest point according to the positional relationship between the initial position point and the contour of the target interest point and the type of the contour of the target interest point; Determine the score of each candidate point of interest according to the adjusted weight; The adjusting the weight of the candidate interest point according to the positional relationship between the initial position point and the target interest point contour and the type of the target interest point contour comprises: Determining an initial weight of each of the candidate interest points; Determine the positional relationship between the initial position point and the contour of the target interest point; In response to the initial position point not being within the target interest point contour, adjusting the initial weights of the candidate interest points according to the distances between the initial position point and each of the candidate interest points to obtain a first intermediate weight; In response to the initial position point being within the target interest point contour, the initial weight of the candidate interest point is adjusted according to the type of the target interest point contour.

2. The method according to claim 1, characterized in that The method further comprises: The recommended position point is determined according to the initial position point.

3. The method according to claim 1, characterized in that Determining the target interest point contour according to the initial position point comprises: Determine a contour set according to the initial position point, the contour set including the contours of the points of interest within a predetermined range of the initial position point; Determine the distance between the center of each interest point contour in the contour set and the initial position point; and The interest point contour having the shortest distance from the initial position point is determined as the target interest point contour.

4. The method according to claim 1, characterized in that: The candidate points of interest include at least one of the following: Interest points on the edge of the target interest point contour; Points of interest within the target point of interest outline; Points of interest obtained through other recall methods.

5. The method according to claim 1, characterized in that The adjusting the initial weight of the candidate interest point according to the type of the target interest point contour comprises: In response to the type of the target POI profile being a predetermined type, adjusting the initial weight according to the floor, heat and POI type of each candidate POI to obtain a second intermediate weight; and In response to the type of the target interest point contour being not a predetermined type, the initial weights of the candidate interest points are adjusted according to the distances between the initial position point and each of the candidate interest points to obtain a third intermediate weight.

6. The method according to claim 5, characterized in that The adjusting the weight of the candidate interest point according to the positional relationship between the initial position point and the target interest point contour and the type of the target interest point contour further comprises: The second intermediate weight is adjusted according to the distance between the initial position point and each of the candidate interest points to obtain a fourth intermediate weight.

7. The method according to claim 6, characterized in that The adjusting the weight of the candidate interest point according to the positional relationship between the initial position point and the target interest point contour and the type of the target interest point contour further comprises: The first intermediate weight, the third intermediate weight and the fourth intermediate weight are adjusted according to at least one of the location, the type and the historical order of the candidate point of interest to obtain a fifth intermediate weight.

8. The method according to claim 7, characterized in that The step of determining the score of each candidate interest point is as follows: The score of each of the candidate interest points is determined according to the fifth intermediate weight.

9. The method according to claim 1, characterized in that: The name of the recommended location point determined according to the score is specifically: The name of the highest-scoring point of interest is determined as the main body of the name of the recommended location point.

10. A position push device, characterized in that: The device comprises: A request receiving unit, configured to receive a data acquisition request, wherein the data acquisition request includes an initial position point; A target interest point contour determining unit, used to determine the target interest point contour according to the initial position point; a candidate interest point acquisition unit, configured to acquire at least one candidate interest point according to the target interest point outline; A score determination unit, used to determine the score of each candidate interest point; a name determination unit, configured to determine a name of the recommended location point according to the score; and A name sending unit, used for sending the name of the recommended location point to the user terminal; Wherein, the score determination unit includes: A weight adjustment subunit, configured to adjust the weight of the candidate interest point according to the positional relationship between the initial position point and the contour of the target interest point and the type of the contour of the target interest point; A score determination subunit, used to determine the score of each of the candidate interest points according to the adjusted weight; Wherein, the weight adjustment subunit is used for: Determining an initial weight of each of the candidate interest points; Determine the positional relationship between the initial position point and the contour of the target interest point; In response to the initial position point not being within the target interest point contour, adjusting the initial weights of the candidate interest points according to the distances between the initial position point and each of the candidate interest points to obtain a first intermediate weight; In response to the initial position point being within the target interest point contour, the initial weight of the candidate interest point is adjusted according to the type of the target interest point contour.

11. 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 to 9.

12. 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 9.

Images