CN112991008A

CN112991008A - Position recommendation method and device and electronic equipment

Info

Publication number: CN112991008A
Application number: CN202110240716.9A
Authority: CN
Inventors: 尹辉
Original assignee: Beijing Didi Infinity Technology and Development Co Ltd
Current assignee: Beijing Didi Infinity Technology and Development Co Ltd
Priority date: 2021-03-04
Filing date: 2021-03-04
Publication date: 2021-06-18

Abstract

The embodiment of the invention discloses a position recommendation method, a position recommendation device and electronic equipment.

Description

Position recommendation method and device and electronic equipment

Technical Field

The invention relates to the technical field of computers, in particular to a position recommendation method and device and electronic equipment.

Background

In the field of logistics, network appointment and the like needing to reach a target address, a target recommended position is often required to be determined according to the target address provided by a user so as to be reached by a task executing party. For example, in the field of network reservation, a server needs a destination address provided by a passenger to determine a destination recommended position for the passenger to get on or off the vehicle, but the destination recommended position recommended by the server sometimes does not meet the requirements of the passenger, for example, the passenger needs to spend much cost (for example, a long distance, etc.) to reach the destination recommended position, which results in poor passenger experience.

Disclosure of Invention

In view of this, embodiments of the present invention provide a position recommendation method and apparatus, and an electronic device, so as to improve accuracy of a target recommendation point, reduce a cost spent by a user to reach a target address from a pushed target recommendation point or reach the target recommendation point from the target address, and further improve a user experience.

In a first aspect, an embodiment of the present invention provides a location recommendation method, where the method includes:

acquiring target task information;

determining at least one candidate position set according to the target task information, wherein candidate positions in the candidate position set are point positions and/or grids, and the grids are geographical areas with preset sizes;

clustering candidate positions in at least one candidate position set, and determining a clustering center set corresponding to each candidate position set;

determining at least one target recommendation position according to each cluster center set;

and pushing at least one target recommendation position to a target user terminal.

In a second aspect, an embodiment of the present invention provides a position recommendation apparatus, where the apparatus includes:

an information acquisition unit configured to acquire target task information;

a candidate position set determining unit configured to determine at least one candidate position set according to the target task information, wherein candidate positions in the candidate position set are point locations and/or grids, and the grids are geographical areas with a predetermined size;

the clustering center determining unit is configured to cluster candidate positions in at least one candidate position set and determine clustering center sets corresponding to the candidate position sets respectively;

a target recommendation position determination unit configured to determine at least one target recommendation position according to each of the cluster center sets;

the pushing unit is configured to push at least one target recommendation position to a target user terminal.

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, where the one or more computer program instructions are executed by the processor to implement the method according to the first aspect of the embodiment of the present invention.

In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, in which a computer program is stored, and the computer program, when executed by a processor, implements the method according to the first aspect of the embodiment of the present invention.

In a fifth aspect, embodiments of the present invention provide a computer program product, which when run on a computer causes the computer to perform the method according to the first aspect of embodiments of the present invention.

According to the embodiment of the invention, the target task information is obtained, at least one candidate position set is determined according to the target task information, the candidate positions in the at least one candidate position set are clustered, the clustering center sets corresponding to the candidate position sets respectively are determined, at least one target recommendation position is determined according to the clustering center sets, and the at least one target recommendation position is pushed to the target user terminal, so that the position recommendation accuracy can be improved, the cost for a user to reach a target address from a pushed target recommendation point or reach the target recommendation point from the target address is reduced, and the user experience is further improved.

Drawings

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

FIG. 1 is a flow chart of a method of location recommendation in accordance with an embodiment of the present invention;

FIG. 2 is a schematic diagram of a candidate position determination method according to an embodiment of the invention;

FIG. 3 is a schematic diagram of a terminal interface according to an embodiment of the invention;

FIG. 4 is a flow chart of another location recommendation method of an embodiment of the present invention;

FIG. 5 is a flow chart of yet another location recommendation method of an embodiment of the present invention;

FIG. 6 is a flow chart of yet another position recommendation method of an embodiment of the present invention;

FIG. 7 is a schematic diagram of a position recommendation device of an embodiment of the present invention;

fig. 8 is a schematic diagram of an electronic device of an embodiment of the invention.

Detailed Description

The present invention will be described below based on examples, but the present invention is not limited to only these examples. In the following detailed description of the present invention, certain specific details are set forth. It will be apparent to one skilled in the art that the present invention may be practiced without these specific details. Well-known methods, procedures, components and circuits have not been described in detail so as not to obscure the present invention.

Further, those of ordinary skill in the art will appreciate that the drawings provided herein are for illustrative purposes and are not necessarily drawn to scale.

Unless the context clearly requires otherwise, throughout the description, the words "comprise", "comprising", and the like are to be construed in an inclusive sense as opposed to an exclusive or exhaustive sense; that is, what is meant is "including, but not limited to".

In the description of the present invention, it is to be understood that the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. In addition, in the description of the present invention, "a plurality" means two or more unless otherwise specified.

In the following embodiments, a network appointment as an example is mainly described in detail, it should be understood that the embodiments of the present invention are not limited to being applied to a network appointment application scenario, and other application scenarios that require a target recommendation point to be determined based on a target location, such as a logistics field, may all adopt the location recommendation method of the present embodiment.

Fig. 1 is a flowchart of a location recommendation method according to an embodiment of the present invention. As shown in fig. 1, the position recommendation method according to the embodiment of the present invention includes the following steps:

step S110, target task information is obtained. Optionally, the target task information includes a target address and/or target user information. Alternatively, for example, the destination address may be a Point of Interest (POI) or a destination POI, such as a school, a cell, an office building, a park, etc., in the case of a car appointment.

And step S120, determining at least one candidate position set according to the target task information. And the candidate positions in the candidate position set are point positions and/or grids. The grid is a geographical area of a predetermined size. Optionally, in this embodiment, the at least one candidate location set includes a first candidate location set determined by all historical tasks corresponding to the target address, and/or a second candidate location set determined by all historical tasks corresponding to the target address by the target user. Taking a network appointment application scene as an example, the historical tasks corresponding to the target address are also the historical tasks taking the target address as a task starting point or a task ending point, and the target user takes the target address as the historical task starting point or the historical task ending point in the historical tasks corresponding to the target address, namely all the historical tasks of the target user.

In an alternative implementation, the target task information includes a target address. Step S120 may specifically include: and acquiring historical recommendation points and/or historical task execution points of the historical tasks corresponding to the target addresses to determine a first candidate position set. Taking a network appointment application scene as an example, the recommended point is a recommended getting-on/off point in the corresponding historical task, and the historical task execution point is an actual getting-on/off point of the corresponding historical task.

In an optional implementation manner, taking the determination of the getting-on recommended point of the networked car as an example, the historical recommended points and/or the historical task execution points of the historical tasks with the starting addresses as the target addresses are obtained, all the obtained historical recommended points and/or historical task execution points are determined as candidate positions, or the historical recommended points and/or historical task execution points with the heat degree exceeding a predetermined heat degree threshold are determined as candidate positions, so as to determine the first candidate position set.

In another optional implementation manner, taking the determination of the getting-on recommended point of the networked taxi appointment as an example, the historical recommended points and/or the historical task execution points of the historical tasks with the starting addresses as the target addresses are obtained, the historical recommended points and/or the historical task execution points are mapped into grids, and the grids with the historical recommended points and/or the historical task execution points are determined as candidate positions to determine the first candidate position set. In an actual application scenario, the historical tasks corresponding to the target addresses are too many, that is, the historical recommendation points and/or the historical task execution points are too many or the distances between some historical recommendation points and/or the historical task execution points are particularly close, and if all the historical recommendation points and/or the historical task execution points are used as candidate positions, the calculation amount of position recommendation is large, and the efficiency is low. Therefore, the embodiment reduces the calculation amount of position recommendation and improves the position recommendation efficiency by adopting a mode of mapping each historical recommendation point and/or each historical task execution point to the grid and taking the grid as the candidate position.

Fig. 2 is a schematic diagram of a candidate position determination method according to an embodiment of the present invention. As shown in fig. 2, history recommended points and/or history task execution points in the history task information with the address P as a target position are acquired, each history recommended point and/or history task execution point is mapped into a grid with a predetermined size, and the grid with the history recommended points and/or history task execution points is determined as a candidate position, such as grid 21-grid 29. Alternatively, the representation of the grid may be determined according to a geocoding algorithm, such as a GeoHash code.

In another alternative implementation, the target task information includes target user information and a target address. Step S120 may specifically include: and acquiring historical recommendation points and/or historical task execution points of the historical tasks of the target user at the target address to determine a second candidate position set. Taking the determination of the recommended boarding point in the online taxi appointment application scene as an example, the historical recommendation points and/or the historical task execution points of the historical tasks with the target position as the task starting point in the historical tasks of the target user are obtained, all the obtained historical recommendation points and/or the historical task execution points are determined as candidate positions, or the historical recommendation points and/or the historical task execution points with the heat degree exceeding a preset heat degree threshold are determined as candidate positions, so that a second candidate position set is determined.

Generally, a single user has fewer corresponding historical tasks, and therefore, it is not necessary to map each historical recommendation point and/or historical task execution point to the grid to determine the grid satisfying the condition as the candidate location, but if there are more historical tasks of the target user, the second candidate location set may also be determined in a manner of mapping each historical recommendation point and/or historical task execution point to the grid to determine the grid satisfying the condition as the candidate location, which is not limited in this embodiment.

Step S130, clustering candidate positions in at least one candidate position set, and determining a clustering center set corresponding to each candidate position set. In this embodiment, the candidate positions in each candidate position set are clustered respectively, and a cluster center set corresponding to each candidate position set is obtained. For example, each candidate position in the first candidate position set is clustered to obtain at least one clustering center, so as to determine a first clustering center set corresponding to the first candidate position set, and each candidate position in the second candidate position set is clustered to determine a second clustering center set corresponding to the second candidate position set.

In an optional implementation manner, step S130 may specifically include: and respectively carrying out density clustering on the candidate positions in each candidate position set according to the heat information of the candidate positions so as to determine each clustering center set. The popularity information is used for representing the recommended times of the corresponding candidate positions. Alternatively, the popularity information of each candidate location may be determined according to the recommended times of each candidate location in a predetermined time period (e.g., one week, one month, etc.), or may be determined according to a weighted value of the recommended times of each candidate location in each time period, for example, if the recommended times of a candidate location in the first 30 days is X1, the recommended times of the candidate location in the first 30-60 days is X2, and the recommended times of the candidate location in the first 60-90 days is X3, the popularity information X of the candidate location is r 1X 1+ r 2X 2+ r 3X 3. Optionally, the weights r1, r2, and r3 are sequentially decreased in size. It should be understood that the present embodiment does not limit the specific determination method of the heat information of the candidate position, and other ways of determining the heat information may be applied to the present embodiment.

Optionally, in this embodiment, if the candidate location is a point location, the heat information of the candidate location may be determined according to the recommended times of the point location or according to the total recommended times in a predetermined range around the point location. If the candidate position is a grid, the heat information of the grid may be determined according to the heat of all the historical recommendation points and/or the historical task execution points in the grid, and the heat determination manner of each historical recommendation point and each historical task execution point is as described above and is not described herein again. Optionally, the heat information of the grid is a sum of heats of all the historical recommended points and/or the historical task execution points in the grid, or a heat average, a maximum, a weighted average, and the like, which is not limited in this embodiment.

In this embodiment, based on density clustering, the candidate positions in the candidate position set are clustered by using the heat information of each candidate position, and one or more corresponding clustering centers are determined to obtain a corresponding clustering center set. The cluster center is generally the highest candidate position in a certain range. In some cases, the distance between the cluster center and the target address may be too far, or the target address needs to be reached through a road crossing, etc., which results in a higher motion cost parameter, and therefore, the cluster center needs to be adjusted. In an optional implementation manner, in response to detecting that the motion cost parameter of the cluster center and the target address in the cluster center set is greater than the cost threshold, the cluster center is adjusted until the motion cost parameter of the cluster center and the target address is less than or equal to the cost threshold. The motion cost parameter of the cluster center and the target address is used to represent the cost to be spent on reaching the target address from the cluster center (or the cost to be spent on reaching the cluster center from the target address), and the motion cost parameter may be represented by a distance between the cluster center and the target address, a road crossing state, and the like, or represented by the motion time, the motion distance, and/or whether the user reaches the cluster center in the corresponding historical task, or represented by a road crossing, which is not limited in this embodiment. Therefore, the risk that the cost for the pushed target recommendation position to reach the target address is too high can be further reduced, and the user experience is further improved.

And step S140, determining at least one target recommendation position according to each clustering center set.

In an optional implementation manner, at least one target recommended position is determined by using a first cluster center set corresponding to the first candidate position set. In an optional implementation manner, at least one target recommendation position is determined according to the heat information of each cluster center in the first cluster center set. Optionally, information of each cluster center in the first cluster center set (for example, information of coordinates of the cluster center, coordinates of a target address, and the like) is input into a pre-trained model to sort each cluster center, and at least one target recommendation position is determined based on a sorting result. For example, the information of each cluster center is processed by using a GBDT model or other network models to obtain a score of each cluster center, each cluster center is sorted from large to small based on the corresponding score, and a predetermined number of cluster centers in the obtained sorting sequence are determined as the target recommended position. It should be understood that, in other alternative implementations, N (N is greater than or equal to 1) cluster centers with the highest degree of heat in the first cluster center may also be determined as the target recommendation position, or the target recommendation position may be determined according to a distance between each cluster center and the target address, or a movement time, a movement distance, and the like of the user reaching the cluster center in the corresponding historical task, which is not limited in this embodiment.

In another optional implementation manner, if the target user has more historical tasks corresponding to the target address, at least one target recommendation position may be determined by using the second cluster center set corresponding to the second candidate position set. In an alternative implementation manner, information of each cluster center in the second cluster center set may be input into a pre-trained model (e.g., GNDT model, etc.) to sort the cluster centers, and determine at least one target recommendation position based on the sorting result, or determine at least one target recommendation position according to heat information of each cluster center in the second cluster center set, which is not limited in this embodiment. Optionally, the N (N is greater than or equal to 1) cluster centers with the highest heat in the second cluster center may be determined as the target recommended position. It should be understood that, in other alternative implementations, the target recommended position may also be determined according to a distance between each cluster center and the target address, or a movement time, a movement distance, and the like of the user reaching the cluster center in the corresponding historical task, which is not limited in this embodiment. Therefore, personalized recommendation can be performed according to the historical tasks of the target user, and the accuracy of the target recommendation position and the user experience are further improved.

In yet another optional implementation manner, at least one target recommendation position is determined by using the first cluster center set corresponding to the first candidate position set and the second cluster center set corresponding to the second candidate position set. Optionally, in response to that the second cluster center set is not empty, the target recommendation position is determined at least according to the second cluster center in the second cluster center set, so as to perform personalized recommendation on the target user, and further improve the user experience. Or determining the target recommendation position according to the intersection of the second cluster center set and the first cluster center set, or determining at least one candidate recommending position according to the second center set, determining at least one candidate recommending position according to the first center set, determining the target address according to the distance between each candidate recommending position and the target address, or the target recommendation position is determined from each candidate recommendation position by the movement time, the movement distance and the like of the user reaching the candidate recommendation position in the corresponding historical task, therefore, the target recommendation position can be determined based on the user personalized information and the general information (namely, the recommendation information corresponding to most users), the situation that the target recommendation position has large deviation when the historical tasks of the user are few can be avoided, the risk that the pushed target recommendation position reaches the target address with too large cost is further reduced, and the accuracy of user recommendation and the user experience can be improved.

Optionally, in response to that the second cluster center set corresponding to the second candidate position set is empty, the target recommended position is determined according to the first cluster center in the first cluster center set. The specific method for determining the target recommended position according to the first cluster center set is similar to the above embodiment, and is not described herein again.

And S150, pushing at least one target recommended position to a target user terminal and/or a task execution terminal. Taking a network appointment scene as an example, assuming that the target recommended position is a get-off recommended position, at least one get-off recommended position can be pushed to the passenger terminal and/or the driver terminal to be displayed on a navigation interface of the passenger terminal and/or the driver terminal, so that the passenger and/or the driver can determine a get-off point.

Fig. 3 is a schematic diagram of a terminal interface according to an embodiment of the present invention. As shown in fig. 3, the terminal interface 3 may be an interface of a target user terminal or a task execution end interface, and if the target recommended position determined through the above steps S110 to S150 is the position 31, the longitude and latitude coordinates or the GeoHash code of the position 31 is sent to the corresponding terminal, so as to display the position 31 on the navigation interface of the terminal, thereby enabling the target user and/or the task execution party to determine a task starting point or a task ending point.

According to the embodiment of the invention, the target task information is obtained, the at least one candidate position set is determined according to the target task information, the candidate positions in the at least one candidate position set are clustered, the clustering center sets corresponding to the candidate position sets respectively are determined, the at least one target recommendation position is determined according to the clustering center sets, and the at least one target recommendation position is pushed to the target user terminal, so that the accuracy of position recommendation can be improved, and the user experience is further improved.

Fig. 4 is a flowchart of another location recommendation method according to an embodiment of the present invention. The embodiment of the invention determines the target recommendation position by adopting the historical task information corresponding to the target address. As shown in fig. 4, the position recommendation method according to the embodiment of the present invention includes the following steps:

step S210, target task information is obtained. Optionally, the target task information includes a target address. Alternatively, for example, the destination address may be a Point of Interest (POI) or a destination POI, such as a school, a cell, an office building, a park, etc., in the case of a car appointment.

Step S220, a first candidate position set is determined according to the historical task information corresponding to the target address. And the candidate positions in the first candidate position set are point positions and/or grids.

In an optional implementation manner, step S220 may specifically include: and acquiring historical recommendation points and/or historical task execution points of the historical tasks corresponding to the target addresses to determine a first candidate position set. Taking a network appointment application scenario as an example, for example, the recommended point is a point for getting on or off a vehicle recommended in the corresponding historical task, and the historical task execution point is a point for actually getting on or off the vehicle corresponding to the historical task.

In another optional implementation manner, taking the determination of the getting-on recommended point of the networked taxi appointment as an example, the historical recommended points and/or the historical task execution points of the historical tasks with the starting addresses as the target addresses are obtained, the historical recommended points and/or the historical task execution points are mapped into grids, and the grids with the historical recommended points and/or the historical task execution points are determined as candidate positions to determine the first candidate position set. Thus, the position recommendation calculation amount can be reduced, and the position recommendation efficiency can be improved.

Step S230, clustering candidate positions in the first candidate position set, and determining a first cluster center set corresponding to the first candidate position set.

In an optional implementation manner, step S230 may specifically include: and performing density clustering on the candidate positions in the first candidate position set according to the heat information of the candidate positions to determine a first clustering center set. Optionally, in this embodiment, based on density clustering, the candidate position with the highest heat degree in a certain range is determined as a clustering center, and candidate positions in the first candidate position set are clustered to obtain a first clustering center set corresponding to the first candidate position set. In an optional implementation manner, in response to detecting that the motion cost parameter of the cluster center and the target address in the first cluster center set is greater than the cost threshold, the cluster center is adjusted until the motion cost parameter of the cluster center and the target address is less than or equal to the cost threshold.

Step S240, determining at least one target recommendation position according to the first clustering center set. In an optional implementation manner, at least one target recommendation position is determined according to the heat information of each cluster center in the first cluster center set. Optionally, N (N is greater than or equal to 1) cluster centers with the highest heat in the first cluster center are determined as the target recommended position. It should be understood that, in other alternative implementations, the target recommended position may also be determined according to a distance between each cluster center and the target address, or a movement time, a movement distance, and the like of the user reaching the cluster center in the corresponding historical task, which is not limited in this embodiment.

And step S250, pushing at least one target recommended position to a target user terminal and/or a task execution terminal. Taking a network appointment scene as an example, assuming that the target recommended position is a get-off recommended position, at least one get-off recommended position can be pushed to the passenger terminal and/or the driver terminal to be displayed on a navigation interface of the passenger terminal and/or the driver terminal, so that the passenger and/or the driver can determine a get-off point.

The detailed implementation of steps S210-S250, steps S110-S150 are similar, and are not specifically described herein, it should be understood that the related implementation based on the first candidate location set in steps S110-S150 can be applied to this embodiment.

In the embodiment, target task information including a target address is acquired, a first candidate position set is determined according to historical task information corresponding to the target address, candidate positions in the first candidate position set are clustered, a first clustering center set corresponding to the first candidate position set is determined, at least one target recommendation position is determined according to the first clustering center set, and the at least one target recommendation position is pushed to a target user terminal and/or a task execution terminal, so that the position recommendation accuracy can be improved, the cost spent by a user for reaching the target address from a pushed target recommendation point or reaching the target recommendation point from the target address is reduced, and the user experience is further improved.

Fig. 5 is a flowchart of another position recommendation method according to an embodiment of the present invention. Embodiments of the present invention may be employed when a predetermined number of historical tasks of a target user at a target location are reached. The position recommendation method provided by the embodiment of the invention comprises the following steps:

step S310, target task information is acquired. Optionally, the target task information includes a target address and target user information. Alternatively, for example, the destination address may be a Point of Interest (POI) or a destination POI, such as a school, a cell, an office building, a park, etc., in the case of a car appointment.

Step S320, determining a second candidate location set according to the historical task information corresponding to the target user at the target address. And the candidate positions in the candidate position set are point positions and/or grids.

In an optional implementation manner, step S320 may specifically include: and acquiring historical recommendation points and/or historical task execution points of the historical tasks of the target user at the target address to determine a second candidate position set. Taking the determination of the recommended boarding point in the online taxi appointment application scene as an example, the historical recommendation points and/or the historical task execution points of the historical tasks with the target position as the task starting point in the historical tasks of the target user are obtained, all the obtained historical recommendation points and/or the historical task execution points are determined as candidate positions, or the historical recommendation points and/or the historical task execution points with the heat degree exceeding a preset heat degree threshold are determined as candidate positions, so that a second candidate position set is determined.

Step S330, clustering candidate positions in the second candidate position set, and determining second clustering center sets corresponding to the second candidate position set respectively.

In an optional implementation manner, step S330 may specifically include: and performing density clustering on the candidate positions in the second candidate position set respectively according to the heat information of the candidate positions to determine a second clustering center set. Optionally, in this embodiment, based on density clustering, the candidate position with the highest heat degree in a certain range is determined as a clustering center, and candidate positions in the second candidate position set are clustered to obtain a second clustering center set corresponding to the second candidate position set. In an alternative implementation manner, in response to detecting that the motion cost parameter of the cluster center and the target address in the second cluster center set is greater than the cost threshold, the cluster center is adjusted until the motion cost parameter of the cluster center and the target address is less than or equal to the cost threshold. The motion cost parameter may be represented by a distance between a cluster center and a target address, or represented by a motion time, a motion distance, and/or whether a path is crossed when a user arrives at the cluster center in a corresponding historical task, which is not limited in this embodiment.

Step S340, determining at least one target recommendation position according to the second cluster center set.

In an optional implementation manner, at least one target recommended position is determined by using a second clustering center set corresponding to the second candidate position set. In an optional implementation manner, at least one target recommendation position is determined according to the heat information of each clustering center in the second clustering center set. It should be understood that, in other alternative implementations, the target recommended position may also be determined according to a distance between each cluster center and the target address, or a movement time, a movement distance, and the like of the user reaching the cluster center in the corresponding historical task, which is not limited in this embodiment.

And step S350, pushing at least one target recommended position to a target user terminal and/or a task execution terminal. Taking a network appointment scene as an example, assuming that the target recommended position is a get-off recommended position, at least one get-off recommended position can be pushed to the passenger terminal and/or the driver terminal to be displayed on a navigation interface of the passenger terminal and/or the driver terminal, so that the passenger and/or the driver can determine a get-off point.

The detailed implementation of steps S310-S350, steps S110-S150 are similar, and are not specifically described herein, it should be understood that the related implementation based on the first candidate location set in steps S110-S150 can be applied to this embodiment.

In the embodiment, target task information including a target address and target user information is acquired, a second candidate position set is determined according to historical task information corresponding to the target address of a target user, candidate positions in the second candidate position set are clustered, a second clustering center set corresponding to the second candidate position set is determined, at least one target recommendation position is determined according to the second clustering center set, and the at least one target recommendation position is pushed to a target user terminal and/or a task execution terminal, so that personalized recommendation can be performed on the target user, and the user experience is further improved.

Fig. 6 is a flowchart of another position recommendation method according to an embodiment of the present invention. The position recommendation method provided by the embodiment of the invention comprises the following steps:

step S410, target task information is acquired. Optionally, the target task information includes a target address and target user information. Alternatively, for example, the destination address may be a Point of Interest (POI) or a destination POI, such as a school, a cell, an office building, a park, etc., in the case of a car appointment.

Step S420, determining a first candidate location set according to the historical task information corresponding to the target address. And the candidate positions in the first candidate position set are point positions and/or grids.

In an optional implementation manner, the first candidate location set is determined by obtaining a history recommendation point and/or a history task execution point of a history task corresponding to the target address. Taking a network appointment application scenario as an example, for example, the recommended point is a point for getting on or off a vehicle recommended in the corresponding historical task, and the historical task execution point is a point for actually getting on or off the vehicle corresponding to the historical task. Optionally, taking the determination of the getting-on recommended point of the networked taxi appointment as an example, the historical recommended points and/or the historical task execution points of the historical tasks with the start addresses as the target addresses are obtained, all the obtained historical recommended points and/or the historical task execution points are determined as candidate positions, or the historical recommended points and/or the historical task execution points with the heat degrees exceeding a predetermined heat degree threshold are determined as candidate positions, so as to determine the first candidate position set.

Step S430, clustering candidate positions in the first candidate position set, and determining a first cluster center set corresponding to the first candidate position set. Optionally, density clustering is performed on the candidate positions in the first candidate position set according to the heat information of the candidate positions to determine a first clustering center set. Optionally, in this embodiment, based on density clustering, the candidate position with the highest heat degree in a certain range is determined as a clustering center, and candidate positions in the first candidate position set are clustered to obtain a first clustering center set corresponding to the first candidate position set. In an optional implementation manner, in response to detecting that the motion cost parameter of the cluster center and the target address in the first cluster center set is greater than the cost threshold, the cluster center is adjusted until the motion cost parameter of the cluster center and the target address is less than or equal to the cost threshold.

Step S440, determining a second candidate position set according to the historical task information corresponding to the target user at the target address. And the candidate positions in the candidate position set are point positions and/or grids.

In an optional implementation manner, the present embodiment determines the second candidate location set by acquiring historical recommendation points and/or historical task execution points of the historical task of the target user at the target address. Taking the determination of the recommended boarding point in the online taxi appointment application scene as an example, the historical recommendation points and/or the historical task execution points of the historical tasks with the target position as the task starting point in the historical tasks of the target user are obtained, all the obtained historical recommendation points and/or the historical task execution points are determined as candidate positions, or the historical recommendation points and/or the historical task execution points with the heat degree exceeding a preset heat degree threshold are determined as candidate positions, so that a second candidate position set is determined.

Step S450, clustering candidate positions in the second candidate position set, and determining second clustering center sets corresponding to the second candidate position set respectively. Optionally, in this embodiment, density clustering is performed on the candidate positions in the second candidate position set according to the heat information of the candidate positions, so as to determine a second clustering center set. Optionally, in this embodiment, based on density clustering, the candidate position with the highest heat degree in a certain range is determined as a clustering center, and candidate positions in the second candidate position set are clustered to obtain a second clustering center set corresponding to the second candidate position set. In an alternative implementation manner, in response to detecting that the motion cost parameter of the cluster center and the target address in the second cluster center set is greater than the cost threshold, the cluster center is adjusted until the motion cost parameter of the cluster center and the target address is less than or equal to the cost threshold. The motion cost parameter may be represented by a distance between a cluster center and a target address, or represented by a motion time, a motion distance, and/or whether a path is crossed when a user arrives at the cluster center in a corresponding historical task, which is not limited in this embodiment.

It should be understood that the present invention does not limit the execution sequence of steps S420-S430 and steps S440-S450, and steps S420-S430 may be executed before steps S440-S450, after steps S440-S450, or simultaneously with steps S440-S450.

Step S460, determining whether the second cluster center set is empty, executing step S470 when the second cluster center set is empty, and executing step S480 when the second cluster center set is not empty.

Step S470, in response to that the second cluster center set corresponding to the second candidate position set is empty, determining a target recommended position according to the first cluster center in the first cluster center set. The specific method for determining the target recommended position according to the first cluster center set is similar to the above embodiment, and is not described herein again.

Step S480, in response to that the second cluster center set is not empty, determining a target recommended position according to at least a second cluster center in the second cluster center set.

In an optional implementation manner, the target recommendation position is determined according to a second clustering center in the second clustering center set, so as to perform personalized recommendation on the target user, and further improve the user experience.

In another alternative implementation, the target recommendation position is determined according to the second cluster center set and the first cluster center set. Optionally, the target recommendation position is determined according to an intersection of the second cluster center set and the first cluster center set. Optionally, at least one candidate recommended position is determined according to the second center set, at least one candidate recommended position is determined according to the first center set, and a target recommended position is determined from the candidate recommended positions according to the distance between each candidate recommended position and the target address, or the movement time and the movement distance of the user reaching the candidate recommended position in the corresponding historical task, so that the target recommended position can be determined based on the user personalized information and the general information, the situation that the target recommended position has large deviation when the historical tasks of the user are few can be avoided, and the accuracy of user recommendation and the user experience are further improved.

Fig. 7 is a schematic diagram of a position recommendation device according to an embodiment of the present invention. As shown in fig. 7, the position recommendation apparatus 7 of the embodiment of the present invention includes an information acquisition unit 71, a candidate position set determination unit 72, a clustering center determination unit 73, a target recommendation position determination unit 74, and a push unit 75.

The information acquisition unit 71 is configured to acquire target task information. The candidate location set determining unit 72 is configured to determine at least one candidate location set according to the target task information, where the candidate locations in the candidate location set are points and/or grids, and the grids are geographical areas with a predetermined size. The cluster center determining unit 73 is configured to cluster candidate positions in at least one of the candidate position sets, and determine a cluster center set corresponding to each of the candidate position sets. The target recommendation position determining unit 74 is configured to determine at least one target recommendation position according to each of the cluster center sets. The pushing unit 75 is configured to push at least one of the target recommended positions to a target user terminal.

In an optional implementation manner, the target task information includes target user information and a target address. The candidate location set determination unit comprises a first set determination subunit and/or a second set determination subunit. The first set determining subunit is configured to acquire historical recommendation points and/or historical task execution points of a historical task corresponding to the target address to determine a first candidate position set. The second set determination subunit is configured to acquire historical recommendation points and/or historical task execution points of the historical task of the target user at the target address to determine a second candidate position set.

In an alternative implementation, the target recommended position determination unit includes a first position determination subunit. The first position determination subunit is configured to determine at least one target recommended position according to a second clustering center in the second clustering center set in response to the second clustering center set corresponding to the second candidate position set not being empty.

In an alternative implementation, the target recommended position determination unit includes a second position determination subunit. A second position determining subunit, configured to determine at least one target recommended position according to a first cluster center in the first cluster center set in response to that a second cluster center corresponding to the second candidate position set is empty.

In an optional implementation manner, the first set determining subunit includes a point location determining module and a first set determining module. The point location determination module is configured to obtain a historical recommendation point and/or a historical task execution point of a historical task corresponding to the target address. The first set determination module is configured to map each historical recommendation point and/or historical task execution point into a grid, determine the grid with the historical recommendation points and/or historical task execution points as candidate positions, and determine the first set of candidate positions.

In an optional implementation manner, the cluster center determining unit includes a cluster center set determining subunit. The cluster center set determining subunit is configured to perform density clustering on the candidate positions in each candidate position set according to heat information of the candidate positions to determine each cluster center set, wherein the heat information is used for representing recommended times of the corresponding candidate positions.

In an optional implementation manner, the cluster center determining unit further includes a cluster center set updating subunit. The cluster center set updating subunit is configured to adjust the cluster centers in response to detecting that the motion cost parameters of the cluster centers and the target addresses in each cluster center set are greater than a cost threshold value, so as to obtain each updated cluster center set.

In an optional implementation manner, the target recommended position determining unit includes a target recommended position determining subunit. And the target recommendation position determining subunit is configured to determine at least one target recommendation position according to the heat information of each clustering center in each clustering center set.

Fig. 8 is a schematic diagram of an electronic device of an embodiment of the invention. As shown in fig. 8, the electronic device 8 is a general-purpose data processing apparatus comprising a general-purpose computer hardware structure including at least a processor 81 and a memory 82. The processor 81 and the memory 82 are connected by a bus 83. The memory 82 is adapted to store instructions or programs executable by the processor 81. Processor 81 may be a stand-alone microprocessor or a collection of one or more microprocessors. Thus, the processor 81 implements the processing of data and the control of other devices by executing instructions stored by the memory 82 to perform the method flows of embodiments of the present invention as described above. The bus 83 connects the above components together, and also connects the above components to a display controller 84 and a display device and an input/output (I/O) device 85. Input/output (I/O) devices 85 may be a mouse, keyboard, modem, network interface, touch input device, motion sensing input device, printer, and other devices known in the art. Typically, the input/output devices 85 are coupled to the system through an input/output (I/O) controller 86.

As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, apparatus (device) or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may employ a computer program product embodied on one or more computer-readable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations of methods, apparatus (devices) and computer program products according to embodiments of the application. It will be understood that each flow in the flow diagrams can be implemented by computer program instructions.

These computer program instructions may be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows.

These computer program instructions may also be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows.

Another embodiment of the invention relates to a computer program product for causing a computer to perform some or all of the above method embodiments when the computer program product runs on a computer.

Another embodiment of the invention is directed to a non-transitory storage medium storing a computer-readable program for causing a computer to perform some or all of the above-described method embodiments.

That is, as can be understood by those skilled in the art, all or part of the steps in the method for implementing the embodiments described above may be accomplished by specifying the relevant hardware through a program, where the program is stored in a storage medium and includes several instructions to enable a device (which may be a single chip, a chip, or the like) or a processor (processor) to execute all or part of the steps of the method described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

The embodiment of the invention discloses a TS1 and a position recommendation method, wherein the method comprises the following steps:

acquiring target task information;

and pushing at least one target recommendation position to a target user terminal and/or a task execution terminal.

TS2, the method of TS1, the target task information including target user information and target address;

determining at least one candidate location set according to the target task information comprises:

acquiring historical recommendation points and/or historical task execution points of historical tasks corresponding to the target addresses to determine a first candidate position set; and/or

And acquiring historical recommendation points and/or historical task execution points of the historical tasks of the target user at the target address to determine a second candidate position set.

TS3, the method of TS2, wherein determining at least one target recommended location from each of the sets of cluster centers comprises:

and in response to that the second clustering center set corresponding to the second candidate position set is not empty, determining at least one target recommendation position according to a second clustering center in the second clustering center set.

TS4, the method of TS2 or TS3, the determining at least one target recommended position from each of the sets of cluster centers comprising:

and in response to that the second clustering center set corresponding to the second candidate position set is empty, determining at least one target recommendation position according to a first clustering center in the first clustering center set.

The TS5, the method according to TS2, the determining a first candidate location set according to a historical recommendation point and/or a historical task execution point of a historical task corresponding to the target address includes:

acquiring a historical recommendation point and/or a historical task execution point of a historical task corresponding to the target address;

mapping each historical recommendation point and/or historical task execution point into a grid, and determining the grid with the historical recommendation points and/or historical task execution points as candidate positions to determine the first candidate position set.

The TS6, clustering the candidate locations in at least one of the candidate location sets according to the method of any one of TS1-TS5, and determining a cluster center set corresponding to each of the candidate location sets includes:

and performing density clustering on the candidate positions in each candidate position set according to the heat information of the candidate positions to determine each clustering center set, wherein the heat information is used for representing the recommended times of the corresponding candidate positions.

TS7, clustering candidate positions in at least one of the candidate position sets according to the method described in TS6, and determining a cluster center set corresponding to each of the candidate position sets further includes:

and adjusting the cluster centers to obtain updated cluster center sets in response to detecting that the motion cost parameters of the cluster centers and the target addresses in the cluster center sets are larger than a cost threshold.

TS8, the method of any one of TS1-TS7, the determining at least one target recommended location from each of the sets of cluster centers comprising:

and determining at least one target recommendation position according to the heat information of each clustering center in each clustering center set.

The embodiment of the invention also discloses a TS9 and a position recommending device, wherein the device comprises:

an information acquisition unit configured to acquire target task information;

TS10, the apparatus of TS9, the target task information including target user information and target address;

the candidate position set determination unit includes:

a first set determining subunit, configured to acquire a historical recommendation point and/or a historical task execution point of a historical task corresponding to the target address to determine a first candidate position set; and/or

A second set determination subunit configured to acquire a historical recommendation point and/or a historical task execution point of a historical task of the target user at the target address to determine a second candidate location set.

TS11, the apparatus of TS10, the target recommended position determination unit comprising:

a first position determination subunit configured to determine at least one target recommended position according to a second clustering center in a second clustering center set in response to a second clustering center set corresponding to the second candidate position set not being empty.

TS12, the device according to TS10 or TS11, the target recommended position determining unit comprising:

a second position determining subunit, configured to determine at least one target recommended position according to a first cluster center in the first cluster center set in response to that a second cluster center corresponding to the second candidate position set is empty.

TS13, the apparatus of TS10, the first set determining sub-unit comprising:

the point location determining module is configured to obtain a historical recommendation point and/or a historical task execution point of a historical task corresponding to the target address;

and the first set determination module is configured to map each historical recommendation point and/or historical task execution point into a grid, and determine the grid with the historical recommendation points and/or historical task execution points as candidate positions to determine the first candidate position set.

TS14, the apparatus according to any one of TS9-TS13, the cluster center determining unit comprising:

the clustering center set determining subunit is configured to perform density clustering on the candidate positions in each candidate position set according to heat information of the candidate positions to determine each clustering center set, wherein the heat information is used for representing recommended times of corresponding candidate positions.

TS15, the apparatus according to TS14, the cluster center determining unit further comprising:

and the clustering center set updating subunit is configured to adjust the clustering centers to obtain updated clustering center sets in response to detecting that the motion cost parameters of the clustering centers and the target addresses in the clustering center sets are greater than a cost threshold.

TS16, the device according to any one of TS9-TS15, the target recommended position determination unit comprising:

and the target recommendation position determining subunit is configured to determine at least one target recommendation position according to the heat information of each clustering center in each clustering center set.

The embodiment of the invention also discloses TS17 and an electronic device, which comprises a memory and a processor, wherein the memory is used for storing one or more computer program instructions, and the one or more computer program instructions are executed by the processor to realize the method according to any one of TS1-TS 8.

The embodiment of the invention also discloses a TS18 and a computer readable storage medium, wherein a computer program is stored in the computer readable storage medium, and when the computer program is executed by a processor, the method of any one of TS1-TS8 is realized.

The embodiment of the invention also discloses a TS19 and a computer program product, wherein when the computer program product runs on a computer, the computer is caused to execute the method according to any one of TS1-TS 8.

The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for location recommendation, the method comprising:

acquiring target task information;

2. The method of claim 1, wherein the target task information includes target user information and a target address;

3. The method of claim 2, wherein determining at least one target recommendation location from each of the cluster center sets comprises:

4. The method of claim 2 or 3, wherein determining at least one target recommendation location from each of the cluster center sets comprises:

5. The method of claim 2, wherein determining the first candidate location set according to the historical recommendation points and/or the historical task execution points of the historical task corresponding to the target address comprises:

6. The method according to any one of claims 1-5, wherein clustering candidate locations in at least one of the candidate location sets, and determining a cluster center set corresponding to each of the candidate location sets comprises:

7. A location recommendation device, the device comprising:

an information acquisition unit configured to acquire target task information;

8. An electronic device comprising a memory and a processor, wherein the memory is configured 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 of any of claims 1-6.

9. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1 to 6.

10. A computer program product, characterized in that, when the computer program product is run on a computer, it causes the computer to perform the method according to any of claims 1-6.