Method and system for recommending boarding point

Through a merge method based on spatial topological relationship and similarity of candidate boarding points, combined with the recommendation model, the problem of extended waiting time for boarding points in online car-hailing is solved, and more efficient boarding points are achieved and user experience is improved. and service quality.

CN111859175BActive Publication Date: 2024-11-22DITU (BEIJING) TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202010151813.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-03-06
Publication Date
2024-11-22
Estimated Expiration
2040-11-22

AI Technical Summary

Technical Problem

In online car-hailing services, drivers and passengers do not know the exact location of each other, which leads to repeated communication to find the boarding point, extending travel time, and wasting time and money.

Method used

By searching the points of interest, the first candidate boarding point set is determined, and based on the spatial topological relationship and the similarity of the candidate boarding point, the recommended boarding point set is obtained, and the training recommended model is used to calculate the score results of the candidate boarding point. Recommend the most suitable place to get on the bus.

Benefits of technology

It improves the accuracy and efficiency of recommended boarding points, reduces waiting time for passengers and drivers, and improves user experience and service quality.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN111859175B_ABST
    Figure CN111859175B_ABST
Patent Text Reader

Abstract

The embodiment of the present application discloses a method and system for recommending a boarding point. The method includes: a method for recommending a boarding point, characterized in that it includes: determining a first candidate boarding point set based on the retrieved interest points; determining at least one related interest point based on the retrieved interest points; determining at least one second candidate boarding point set based on the at least one related interest point; merging the first candidate boarding point set with the at least one second candidate boarding point set to obtain a third candidate boarding point set for the retrieved interest points; and determining a recommended boarding point based on the third candidate boarding point set. The method disclosed in the present application can increase the possibility of recommending a suitable boarding point and improve the service quality of the platform.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of online car-hailing, and in particular to a method and system for recommending a pick-up point. Background Art

[0002] With the emergence of online ride-hailing services, people's travel has become much more convenient. When using online ride-hailing services, drivers and passengers do not know each other's exact location, and may have to repeatedly communicate over the phone to find each other, which prolongs the passengers' travel time. In order to improve the user experience and avoid wasting time and money for passengers and drivers, online ride-hailing services currently provide recommended pick-up points when users choose a pick-up point. Summary of the invention

[0003] One of the embodiments of the present application provides a method for recommending a boarding point. The method for recommending a boarding point includes: determining a first candidate boarding point set based on the retrieved interest points; determining at least one related interest point based on the retrieved interest points; determining at least one second candidate boarding point set based on the at least one related interest point; merging the first candidate boarding point set with the at least one second candidate boarding point set to obtain a third candidate boarding point set for the retrieved interest points; and determining a recommended boarding point based on the third candidate boarding point set.

[0004] In some embodiments, the retrieving the interest point to determine at least one related interest point comprises: determining at least one related interest point based on a spatial topological relationship between the retrieved interest point and other interest points.

[0005] In some embodiments, determining at least one of the related points of interest based on the spatial topological relationship between the retrieved point of interest and other points of interest includes: determining a first area including the retrieved point of interest; acquiring at least one first other point of interest in the first area; and determining the at least one first other point of interest as the related point of interest.

[0006] In some embodiments, determining at least one of the related points of interest based on the spatial topological relationship between the retrieved point of interest and other points of interest includes: acquiring at least one second other point of interest whose distance from the retrieved point of interest is less than a first threshold; and determining the at least one second other point of interest as the related point of interest.

[0007] In some embodiments, determining at least one related point of interest based on the retrieved point of interest also includes: determining at least one third other point of interest based on the similarity between the candidate boarding point set of other points of interest and the first candidate boarding point set; and determining the at least one third other point of interest as the related point of interest.

[0008] In some embodiments, determining the recommended boarding point based on the third candidate boarding point set includes: inputting the candidate boarding points in the third candidate boarding point set into a trained recommendation model; determining a scoring result for each of the candidate boarding points; and determining the recommended boarding point based on the scoring results.

[0009] In some embodiments, determining the scoring result of each of the candidate boarding points includes: obtaining feature data based on the candidate boarding points in the third candidate boarding point set, the feature data including: attribute features of the candidate boarding points, attribute features of the retrieved points of interest, positional relationship features between the candidate boarding points and the retrieved points of interest, and one or more combinations of positional relationship features between the candidate boarding points and the user's location; and calculating the score of each of the candidate boarding points based on the feature data.

[0010] In some embodiments, the acquiring feature data based on the candidate boarding points in the third candidate boarding point set includes: acquiring the location information of the retrieved point of interest; acquiring the location information of the candidate boarding points in the third candidate boarding point set; and determining the location relationship features between the candidate boarding points and the retrieved point of interest based on the location information of the candidate boarding points and the location information of the retrieved point of interest.

[0011] In some embodiments, the step of obtaining characteristic data based on the candidate boarding points in the third set of candidate boarding points also includes: obtaining the positioning information of the user; obtaining the position information of the candidate boarding points in the third set of candidate boarding points; and determining the position relationship characteristics between the candidate boarding points and the user's positioning position based on the position information of the candidate boarding points and the positioning information of the user.

[0012] One of the embodiments of the present application provides a system for recommending boarding points. The system for recommending boarding points may include: a first candidate boarding point set determination module, used to determine a first candidate boarding point set based on retrieved interest points; a related interest point determination module, used to determine at least one related interest point based on the retrieved interest point; a second candidate boarding point set determination module, used to determine at least one second candidate boarding point set based on the at least one related interest point; a third candidate boarding point set determination module, used to merge the first candidate boarding point set with the at least one second candidate boarding point set to obtain a third candidate boarding point set for the retrieved interest point; and a boarding point recommendation module, used to determine a recommended boarding point based on the third candidate boarding point set.

[0013] In some embodiments, the related interest point determination module is used to determine at least one of the related interest points based on the spatial topological relationship between the retrieved interest point and other interest points.

[0014] In some embodiments, the related interest point determination module is used to: obtain at least one second other interest point whose distance from the retrieved interest point is less than a first threshold; and use the at least one second other interest point as the related interest point.

[0015] In some embodiments, the related point of interest determination module is used to: determine at least one third other point of interest based on the similarity between the candidate boarding point set of other points of interest and the first candidate boarding point set; the at least one third other point of interest is used as the related point of interest.

[0016] In some embodiments, the boarding point recommendation module is used to: input the candidate boarding points in the third candidate boarding point set into a trained recommendation model; determine a scoring result for each of the candidate boarding points; and determine a recommended boarding point based on the scoring result.

[0017] In some embodiments, the boarding point recommendation module is used to: obtain feature data based on the candidate boarding points in the third candidate boarding point set, the feature data including: attribute features of the candidate boarding points, attribute features of the retrieved points of interest, positional relationship features between the candidate boarding points and the retrieved points of interest, and one or more combinations of positional relationship features between the candidate boarding points and the user's location; calculate the score of each of the candidate boarding points based on the feature data.

[0018] In some embodiments, the boarding point recommendation module is used to: obtain the location information of the retrieved point of interest; obtain the location information of the candidate boarding points in the third candidate boarding point set; and determine the positional relationship characteristics between the candidate boarding points and the retrieved point of interest based on the location information of the candidate boarding points and the location information of the retrieved point of interest.

[0019] In some embodiments, the boarding point recommendation module is used to: obtain the location information of the user; obtain the location information of the candidate boarding points in the third candidate boarding point set; and determine the positional relationship characteristics between the candidate boarding points and the user's location based on the location information of the candidate boarding points and the location information of the user.

[0020] In some embodiments, the recommendation model is a LambdaMART ranking model.

[0021] One of the embodiments of the present application provides a device for recommending a boarding point, including a memory and a processor, wherein the memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement a method for recommending a boarding point.

[0022] One of the embodiments of the present application provides a computer-readable storage medium, wherein the storage medium stores computer instructions, and the computer program instructions implement a method for recommending a boarding point when executed by a processor. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The present application will be further described in the form of exemplary embodiments, which will be described in detail by way of the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0024] Figure 1 is a schematic diagram of an application scenario of a recommended boarding point system according to some embodiments of the present application;

[0025] Figure 2 is a block diagram of an exemplary processing module of a recommended boarding point system according to some embodiments of the present application;

[0026] Figure 3 is an exemplary flow chart of a method for recommending a boarding point according to some embodiments of the present application;

[0027] Figure 4 is an exemplary flow chart for determining relevant points of interest based on spatial topological relationships according to some embodiments of the present application;

[0028] Figure 5 This is an exemplary flowchart for determining a recommended boarding point according to some embodiments of the present application. DETAILED DESCRIPTION

[0029] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of the present application. For ordinary technicians in this field, the present application can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0030] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0031] As shown in this application and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprises" and "includes" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0032] Flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, the various steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0033] The embodiments of the present application can be applied to different transportation systems, including but not limited to one or a combination of land, sea, aviation, aerospace, etc. For example, taxis, special cars, ride-sharing, buses, drivers, trains, motor vehicles, high-speed railways, ships, airplanes, hot air balloons, unmanned vehicles, express delivery, etc. apply management and / or distribution transportation systems. The application scenarios of different embodiments of the present application include but are not limited to one or a combination of web pages, browser plug-ins, clients, customized systems, internal enterprise analysis systems, artificial intelligence robots, etc. It should be understood that the application scenarios of the system and method of the present application are only some examples or embodiments of the present application. For ordinary technicians in this field, without paying creative labor, the present application can also be applied to other similar scenarios based on these drawings. For example, other similar user-guided parking systems.

[0034] The "passenger", "passenger terminal", "user terminal", "customer", "demander", "service demander", "consumer", "consumer", "user demander", etc. described in this application are interchangeable and refer to the party that needs or orders the service, which can be an individual or a tool. Similarly, the "driver", "driver terminal", "provider", "supplier", "service provider", "service provider", "service provider", "service party", etc. described in this application are also interchangeable and refer to individuals, tools or other entities that provide services or assist in providing services. In addition, the "user" described in this application can be the party that needs or orders the service, or the party that provides the service or assists in providing the service.

[0035] Figure 11 is a schematic diagram of an application scenario of a recommended boarding point system 100 according to some embodiments of the present application. The system 100 for recommending boarding points can recommend boarding points and recommend them to passengers, guiding passengers to choose a suitable boarding point. The system 100 for recommending boarding points can be an online service platform for Internet services. For example, the system 100 for recommending boarding points can be an online transportation service platform for transportation services. In some embodiments, the system 100 for recommending boarding points can be applied to online car-hailing services, such as taxi calls, express calls, special car calls, minibus calls, carpooling, bus services, driver hiring and pick-up services, etc. Specifically, one or more suitable boarding locations can be provided for passengers requesting online car-hailing services, or one or more suitable locations for picking up passengers can be provided for drivers providing services. In some embodiments, the system 100 for recommending boarding points can also be applied to services such as chauffeur service, express delivery, and take-out, for example, providing a service starting point for users who send service requests such as chauffeur service, express delivery, and take-out. The system 100 for recommending boarding points can be an online service platform, including a server 110, a network 120, a user terminal 130, and a database 140. Server 110 may include a processing device 112 .

[0036] In some embodiments, the server 110 may be used to process information and / or data related to the recommended boarding point. For example, the server 110 may recommend a boarding point for a user who sends a service request for an online taxi. The server 110 may also receive a service request from a user terminal 130 and process the service request to recommend a boarding point to the user terminal 130. The server 110 may be an independent server or a server group. The server group may be centralized or distributed (e.g., the server 110 may be a distributed system). In some embodiments, the server 110 may be regional or remote. For example, the server 110 may access information and / or data stored in the user terminal 130 and the database 140 through the network 120. In some embodiments, the server 110 may be directly connected to the user terminal 130 and the database 140 to access the information and / or data stored therein. In some embodiments, the server 110 may be executed on a cloud platform. For example, the cloud platform may include one or any combination of a private cloud, a public cloud, a hybrid cloud, a community cloud, a decentralized cloud, an internal cloud, etc.

[0037] In some embodiments, the server 110 may include a processing device 112. The processing device 112 may process data and / or information related to the service request to perform one or more functions described in the present application. For example, the processing device 112 may receive a vehicle request signal sent by the user terminal 130 and provide a recommended boarding point to the user. In some embodiments, the processing device 112 may include one or more sub-processing devices (e.g., a single-core processing device or a multi-core multi-core processing device). As an example only, the processing device 112 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), an application-specific instruction processor (ASIP), a graphics processing unit (GPU), a physical processing unit (PPU), a digital signal processor (DSP), a field programmable gate array (FPGA), a programmable logic circuit (PLD), a controller, a microcontroller unit, a reduced instruction set computer (RISC), a microprocessor, etc., or any combination thereof.

[0038] The network 120 may facilitate the exchange of data and / or information, which may include a user identifier of a target user terminal, a request time, a service start location, a service destination, a location of the target user terminal when the target user terminal initiates a service request, etc. In some embodiments, one or more components of the system 100 for recommending a pickup point (e.g., server 110, user terminal 130, database 140) may send data and / or information to other components of the system 100 for recommending a pickup point via the network 120. In some embodiments, the network 120 may be any type of wired or wireless network. For example, the network 120 may include a cable network, a wired network, a fiber optic network, a telecommunications network, an intranet, an internet network, a local area network (LAN), a wide area network (WAN), a wireless area network (WLAN), a metropolitan area network (MAN), a public switched telephone network (PSTN), a Bluetooth network, a ZigBee network, a near field communication (NFC) network, etc., or any combination thereof. In some embodiments, the network 120 may include one or more network entry and exit points. For example, the network 120 may include wired or wireless network entry and exit points, such as base stations and / or Internet exchange points 120-1, 120-2, ..., through which one or more components of the system 100 for recommending pickup points can be connected to the network 120 to exchange data and / or information.

[0039] In some embodiments, the user terminal 130 may be a terminal of a device that can display a recommended boarding point page, and may include one of a mobile phone 130-1, a laptop computer 130-2, a mobile device (not shown in the figure), a vehicle-mounted device (not shown in the figure), etc., or any combination thereof. In some embodiments, the mobile device may include a smart home device, a wearable device, a smart action device, a virtual reality device, an augmented reality device, etc., or any combination thereof. In some embodiments, the smart furniture device may include a smart monitoring device, a smart TV, a smart camera, a smart video access control intercom, etc., or any combination thereof. In some embodiments, the wearable device may include a smart bracelet with a display interface, smart glasses, a smart helmet, a smart watch, etc., or any combination thereof. In some embodiments, the smart action device may include a smart phone, a personal digital assistant (PDA), a gaming device, a navigation device, a POS device, etc., or any combination thereof. In some embodiments, the virtual reality device and / or the augmented reality device may include a virtual reality helmet, virtual reality glasses, virtual reality goggles, augmented reality helmets, augmented reality glasses, augmented reality goggles, etc., or any combination thereof. For example, the virtual reality device and / or augmented reality device may include Google Glass, Oculus Rift, HoloLens, or Gear VR, etc. In some embodiments, the user terminal 130 may include a device with a positioning function to determine the location of the user and / or the user terminal 130. In some embodiments, the user may obtain a recommended boarding point through the user terminal 130. In some embodiments, the user terminal 130 may communicate with another positioning device to determine the location of the user terminal 130. In some embodiments, the user terminal 130 may send positioning information to the server 110. The user may be a service requester.

[0040] The database 140 is a source for providing other information to the system 100. The database 140 can be used to provide the system 100 with information related to the service, such as weather conditions, traffic information, legal and regulatory information, news events, life information, life guide information, etc. For another example, the database 140 may also include user information, historical orders, etc. of the taxi platform, and the user information may include user location information, user boarding point information, etc. The database 140 may be implemented in a single central server, multiple servers connected by a communication link, or multiple personal devices. When the database 140 is implemented in multiple personal devices, the personal devices may generate content (e.g., referred to as "user-generated content"), for example, by uploading text, voice, images, and videos to a cloud server. The database 140 may be generated by multiple personal devices and cloud servers. In some embodiments, the database 140 may store information obtained from the user terminal 130, such as location information when the user sends a service request. In some embodiments, the database 140 may store information and / or instructions for execution or use by the server 110 to perform the exemplary method described in this application. In some embodiments, the database 140 may include a mass storage, a removable storage, a volatile read-write storage (e.g., a random access memory RAM), a read-only memory (ROM), etc., or any combination thereof. In some embodiments, the database 140 may be implemented on a cloud platform. For example, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a decentralized cloud, an internal cloud, etc., or any combination thereof.

[0041] In some embodiments, the database 140 may be connected to the network 120 to communicate with one or more components of the system 100 (e.g., the server 110, the user terminal 130, etc.). One or more components of the system 100 for recommending pickup points may access information or instructions stored in the database 140 through the network 120, such as the request time, the service start location, the service destination, the location of the target user terminal when the target user terminal initiates the service request, etc. In some embodiments, the database 140 may be directly connected or communicated with one or more components of the system 100 for recommending pickup points (e.g., the server 110, the user terminal 130). In some embodiments, the database 140 may be a part of the server 110.

[0042] Figure 2 is a module diagram of a recommended boarding point system according to some embodiments of this specification. Figure 2 As shown, the system 100 for recommending boarding points may include a first candidate boarding point set determination module 210 , a related interest point determination module 220 , a second candidate boarding point set determination module 230 , a third candidate boarding point set determination module 240 , and a boarding point recommendation module 250 .

[0043] The first candidate boarding point set determination module 210 can be used to determine the first candidate boarding point set. In some embodiments, the first candidate boarding point set determination module 210 can be used to determine the first candidate boarding point set based on the retrieved interest points. The retrieved interest points can be obtained from the user terminal by the processing device 112. The user terminal can be the service requester terminal 120. In some embodiments, the first candidate boarding point set determination module 210 searches the boarding point library in the database based on the retrieved interest points, and the retrieved boarding points can be used as candidate boarding points of the first candidate boarding point set.

[0044] The related interest point determination module 220 can be used to determine related interest points. In some embodiments, the related interest point determination module 220 can determine at least one related interest point based on the retrieved interest point. In some embodiments, the related interest point determination module 220 can be used to determine one or more related interest points based on the spatial topological relationship between the retrieved interest point and other interest points. In some embodiments, the related interest determination module 220 can determine the first other interest point in the first area where the retrieved interest point is located as a related interest point. For more details, see Figure 4 .

[0045] In some embodiments, the related interest point determination module 220 may be used to determine a second other interest point whose distance from the retrieved interest point is less than a first threshold as a related interest point. For more details, see step 320 and its related description.

[0046] In some embodiments, the relevant interest point determination module 220 can be used to determine relevant interest points based on the similarity of the candidate boarding point set. Specifically, it is determined whether the similarity of the candidate boarding point set of other interest points to the first candidate boarding point set is greater than a threshold, and the second other interest point greater than the threshold is used as a relevant interest point. For more details, please refer to step 320 and its related description.

[0047] The second candidate boarding point set determination module 230 may be used to determine at least one second candidate boarding point set. In some embodiments, the second candidate boarding point set determination module 230 may be used to determine at least one second candidate boarding point set based on the at least one related point of interest. In some embodiments, the second candidate boarding point set determination module 230 searches the boarding point library in the database based on the related points of interest, and uses the retrieved boarding points as candidate boarding points in the second candidate boarding point set. For more details, see step 330 and its related description.

[0048] The third candidate boarding point set determination module 240 may be used to determine the third candidate boarding point set. In some embodiments, the third candidate boarding point set determination module 240 may be used to merge the first candidate boarding point set with the at least one second candidate boarding point set to obtain the third candidate boarding point set for retrieving the point of interest. For more details, see step 340 and its related description.

[0049] The boarding point recommendation module 250 can be used to determine the recommended boarding point. In some embodiments, the boarding point recommendation module 250 can be used to obtain the feature data of the candidate boarding points in the third candidate boarding point set, calculate the scores of the candidate boarding points based on the recommendation model and sort them, and determine the recommended boarding point. For more details, see Figure 5 and its related description.

[0050] The boarding point recommendation module 250 can be used to determine the positional relationship characteristics between the candidate boarding points and the retrieved points of interest. In some embodiments, the boarding point recommendation module 250 can be used to determine the positional relationship characteristics by using the acquired positional information of the retrieved points of interest and the positional information of the candidate boarding points in the third candidate boarding point set. In some embodiments, the positional information of the retrieved points of interest and the candidate boarding points can be obtained in a variety of ways, for example, it can be obtained by querying from a map database. For another example, it can be obtained by querying from the vehicle GPS track data (or GPS log) in the taxi platform.

[0051] The boarding point recommendation module 250 may be used to determine the positional relationship characteristics between the candidate boarding point and the user's location. In some embodiments, the boarding point recommendation module 250 may be used to determine the positional relationship characteristics by using the acquired user's location information and the location information of the candidate boarding points in the third candidate boarding point set. In some embodiments, the user's location information may be acquired in a variety of ways, for example, it may be through the Global Positioning System (GPS), the Global Navigation Satellite System (GLONASS), the Compass Navigation System (COMPASS), the Beidou Navigation Satellite System, the Galileo Positioning System, the Quasi-Zenith Satellite System (QZSS), etc. The location information may include the user's location, altitude, speed or acceleration, or the current time.

[0052] It should be understood that Figure 2The system and its modules shown can be implemented in various ways. For example, in some embodiments, the system and its modules can be implemented by hardware, software or a combination of software and hardware. Among them, the hardware part can be implemented using dedicated logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or a dedicated design hardware. Those skilled in the art will understand that the above-mentioned method and system can be implemented using computer executable instructions and / or included in a processor control code, such as a carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. Such code is provided on the carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The system and its modules of the present application can not only be implemented by hardware circuits such as ultra-large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., but can also be implemented by software such as executed by various types of processors, and can also be implemented by a combination of the above-mentioned hardware circuits and software (for example, firmware).

[0053] It should be noted that the above description of the recommended boarding point system and its modules is for convenience of description only and does not limit the present application to the scope of the embodiments cited. It is understandable that for those skilled in the art, after understanding the principle of the system, it is possible to arbitrarily combine the various modules, or form a subsystem to connect with other modules without deviating from this principle. For example, the first candidate boarding point set determination module 210, the relevant interest point determination module 220, the second candidate boarding point set determination module 230, the third candidate boarding point set determination module 240 and the boarding point recommendation module 250 can be different modules in a system, or a module can realize the functions of two or more of the above modules. Such variations are within the scope of protection of the present application.

[0054] Figure 3 is an exemplary flow chart of recommending boarding points according to some embodiments of the present application. In some embodiments, one or more steps of method 300 may be performed in Figure 1 The system 100 shown in FIG. Figure 3 As shown, the method 300 for recommending a boarding point includes:

[0055] Step 310 , determining a first candidate boarding point set according to the retrieved points of interest. Specifically, step 310 may be performed by the first candidate boarding point set determining module 210 .

[0056] The search point of interest is one or more locations that the user is interested in when preparing to use the service. The user can further search, find and select locations and services based on the above locations. In some embodiments, the search point of interest can be a location entered by the user. For example, the user enters "Forbidden City" as the search point of interest, and further searches for pick-up locations, restaurants, etc. near the Forbidden City. The search point of interest can be input by the user, can be obtained by the user terminal through positioning technology, or can be obtained by other means.

[0057] The first candidate pickup point set is one or more sets, each set including one or more available pickup points. The pickup point can be a location where the user agrees with the service provider to enable the service when using a service related to a transportation tool. For example, when a user uses an online car-hailing service, the pickup point can be the location where the passenger gets on the car.

[0058] The pickup point library contains a large number of pickup points, which can be stored in the database of the storage device. In some embodiments, the pickup points in the pickup point library can be the pickup points collected and sorted by the platform (e.g., the online car-hailing platform). For example, the platform sorts the actual locations where users board the car in historical orders as pickup points and stores them in the pickup point library. In some embodiments, the platform can also filter the actual locations where users board the car in historical orders based on traffic rules, for example, filtering out pickup points located in the middle of the road.

[0059] In some embodiments, the first candidate boarding point set can be determined based on the retrieved points of interest. For example, a search can be performed in the boarding point library of the database, and the boarding points whose distance from the retrieved points of interest is less than a certain threshold are selected as the boarding points in the first candidate boarding point set. For another example, based on the names of the retrieved points of interest, the database can be searched for boarding points whose similarity with the names of the retrieved points of interest is greater than a threshold and are selected as the boarding points in the first candidate boarding point set. The first candidate boarding point set can also be determined in other ways, which are not limited in this embodiment.

[0060] Step 320 , determining at least one related point of interest according to the retrieved point of interest. Specifically, step 320 may be performed by the related point of interest determination module 220 .

[0061] In some embodiments, the relevant points of interest may be places related to the searched points of interest. For example, the relevant points of interest are related to the spatial position of the searched points of interest, the relevant points of interest are related to the candidate boarding points corresponding to the searched points of interest, the relevant points of interest are related to the names of the searched points of interest, etc. Among them, the spatial position correlation of the relevant points of interest and the searched points of interest may be that they belong to a containment relationship in terms of position. For example, the searched point of interest is Peking University, Peking University and the East Gate of Peking University are in a containment and being contained relationship in terms of spatial position relationship, then the East Gate of Peking University is the relevant point of interest of Peking University. The name correlation of the relevant points of interest and the searched points of interest may be that there are upper and lower concepts between the two. For example, the searched point of interest is Beijing Railway Station, Beijing Railway Station and Beijing West Railway Station and Beijing South Railway Station are in a hypernym and hyponym relationship in terms of textual hyponymy, then Beijing West Railway Station and Beijing South Railway Station are the relevant points of interest of Beijing Railway Station. The correlation between the candidate boarding points corresponding to the relevant interest points and the retrieved interest points may be that the relevant interest points are the same as some of the candidate boarding points of the retrieved interest points. For example, the retrieved interest point is Terminal 1 of Capital Airport, and the candidate boarding points of this point are the parking lot of Terminal 1 of Capital Airport and the waiting point of the roundabout of Capital Airport, and the candidate boarding points of Terminal 2 of Capital Airport are the parking lot of Terminal 2 of Capital Airport and the waiting point of the roundabout of Capital Airport. If the candidate boarding points of Terminal 1 of Capital Airport and Terminal 2 of Capital Airport are partially the same, then the relevant interest point of the retrieved interest point may be Terminal 2 of Capital Airport.

[0062] In some embodiments, the relevant interest point determination module 220 can determine the relevant interest points based on the spatial topological relationship between the retrieved interest points and other interest points, wherein the other interest points can be any interest points different from the retrieved interest points. In some embodiments, other interest points can be obtained from a map database. The spatial topological relationship reflects the logical relationship between spatial entities. The spatial topological relationship between interest points includes, but is not limited to, attributes such as subordinate relationships, binding relationships, relative positions, and relative distances. For example, "Terminal 3 of Beijing Capital International Airport" and "Zone C of Terminal 3 of Beijing Capital International Airport (Gate 2 of 4F International / Hong Kong, Macao and Taiwan Departure)" are subordinate relationships. For another example, "Xinzhongguan Shopping Center" and "Zhongguancun Street, Haidian District, Beijing" are binding relationships, and the two interest points are bound based on longitude and latitude. For another example, "Haidian Theater" and "Haidian Culture and Art Building" are left-right adjacent position relationships, and the positions of the two interest points are adjacent. The spatial topological relationship between interest points can be stored in the database as an attribute of the interest point.

[0063] In some embodiments, the related points of interest may be determined based on the spatial topological relationship between the retrieved point of interest and other points of interest, whether they belong to the same area. For more details on determining related points of interest based on whether the retrieved point of interest and other points of interest belong to the same area, see Figure 4 and its related description.

[0064] In some embodiments, the relevant points of interest may be determined based on the distance relationship between the retrieved point of interest and other points of interest. In some embodiments, a second other point of interest whose distance from the retrieved point of interest is less than a first threshold (e.g., 500m, 300m, 200m, 100m, etc.) may be determined as a relevant point of interest. In some embodiments, it may be a straight-line distance, a spherical distance, a walking distance, etc. In some embodiments, the relevant point of interest determination module 220 may be centered on the retrieved point of interest, and at least one point of interest with a radius less than the first threshold may be obtained as the second other point of interest. In some embodiments, all points of interest within a certain radius may be centered on the retrieved point of interest as the second other point of interest.

[0065] In some embodiments, the relevant interest point determination module 220 can determine the relevant interest points based on the similarity between the candidate boarding point set of other interest points and the first candidate boarding point set. The method for determining the candidate boarding point set of other interest points is similar to the method for determining the first candidate boarding point set. For details, please refer to step 310, which will not be repeated here. The similarity between the candidate boarding point set of other interest points and the first candidate boarding point set refers to the degree of correlation between the boarding points in the two sets. For example, the candidate boarding point set of other interest points and the first candidate boarding point set have the same boarding points, the candidate boarding point set of other interest points and the first candidate boarding point set have boarding points belonging to the same area, and the distance between the boarding points in the candidate boarding point set of other interest points and the first candidate boarding point set is less than a preset threshold. In some embodiments, the similarity can be determined based on the number of the same boarding points in the candidate boarding point set of other interest points and the first candidate boarding point set, and the relevant interest points of the retrieved interest points are further determined. For example, a threshold number of the same boarding points is set (eg, 3, 5, etc.), and other points of interest whose number of the same boarding points as the first candidate boarding point set exceeds the threshold number can be determined as related points of interest.

[0066] Step 330 : Determine at least one second candidate boarding point set according to the at least one related point of interest. Specifically, step 330 may be performed by the second candidate boarding point set determination module 230 .

[0067] In some embodiments, the second candidate boarding point set determination module 230 searches the boarding point library in the database based on the relevant points of interest to determine at least one boarding point, and the at least one boarding point is used as the boarding point in the second candidate boarding point set. The method for determining the second candidate boarding point set is similar to the method for determining the first candidate boarding point set, and the details can be referred to step 310, which will not be repeated here.

[0068] Step 340 , merging the first candidate boarding point set with the at least one second candidate boarding point set to obtain a third candidate boarding point set for searching interest points. Specifically, step 340 may be performed by the third candidate boarding point set determination module 240 .

[0069] In some embodiments, the third candidate boarding point set determination module 240 adds the at least one second candidate boarding point set to the first candidate boarding point set to generate a third candidate boarding point set. For example, the first candidate boarding point set A includes candidate boarding points a, b, and c, and the second candidate boarding point set B includes candidate boarding points d and e, then the third candidate boarding point set C includes boarding points a, b, c, d, and e.

[0070] Step 350 : Determine a recommended boarding point based on the third candidate boarding point set. Specifically, step 350 may be performed by the boarding point recommendation module 250 .

[0071] In some embodiments, the boarding point recommendation module 250 inputs the third candidate boarding point set into the recommendation model to obtain the recommended boarding point. For more detailed information on determining the recommended boarding point based on the third candidate boarding point set, see Figure 5 The related descriptions will not be repeated here.

[0072] Figure 4 is an exemplary flow chart of determining relevant points of interest based on spatial topological relationships according to some embodiments of the present application. Figure 4 As shown, the method 400 includes:

[0073] Step 410 , determining a first area including the retrieved interest point. Specifically, step 410 may be performed by the relevant interest point determination module 220 .

[0074] A region may represent a certain geographical range. A region may contain one or more points of interest, or may not contain any points of interest. In some embodiments, the geographical range may be defined by administrative divisions. In some embodiments, the geographical range may be defined by the outline of a region, wherein the outline may be a line connecting the boundary points of the region, and the lines of the outline are connected together to form a closed surface, which surface may represent the range of the region. When the position of a point of interest is within the range surrounded by the outline of a region, the point of interest is considered to belong to the region. In some embodiments, the range of a region may be defined by a coordinate range, including a horizontal coordinate range and a vertical coordinate range.

[0075] In some embodiments, the information of the area may be predefined. The information may include, but is not limited to, the area name, area number, information of points of interest within the area, etc. The point of interest information may refer to the location information of the point of interest, including but not limited to latitude and longitude coordinates, geographic names, etc. The relevant point of interest determination module 220 can determine the first area including the retrieved point of interest based on the information of the point of interest and the information of the area. For example, the location information of the retrieved point of interest and the area to which the point of interest belongs are queried in the database, and the area to which the retrieved point of interest belongs is taken as the first area. For example, the retrieved point of interest is "East Gate of Peking University", and the area to which the point of interest belongs is "Peking University" numbered "100010", then "Peking University" is the first area including the retrieved point of interest.

[0076] Step 420 , obtaining at least one first other point of interest in the first area, and determining the at least one first other point of interest as the related point of interest. Specifically, step 420 may be performed by the related point of interest determination module 220 .

[0077] In some embodiments, the relevant interest point determination module 220 can obtain at least one first other interest point based on the first area. In some embodiments, the relevant interest point determination module 220 can retrieve the map database and obtain other interest points in the first area as the first other interest points. For example, when the first area is determined to be "Peking University" by retrieving the interest point "East Gate of Peking University", the areas to which the interest points "Peking University Library" and "Peking University Gymnasium" belong are both "Peking University", then "Peking University Library" and "Peking University Gymnasium" can be used as the first other interest points. In some embodiments, the relevant interest point determination module 220 can determine the obtained first other interest points as relevant interest points.

[0078] In some embodiments, the relevant interest point determination module 220 can search the database to obtain other interest points that have a parent-child relationship with the first area as the first other interest points. The first area is the parent interest point, and the other interest points are the child interest points of the first area. The parent interest point is an interest point with an AOI (Area Of Interest), which contains a certain area range, such as a school, hospital, park, community, scenic spot, building, etc. The child interest point is an interest point located inside the AOI, and the child interest point is included in the area range of the parent interest point. For example, Peking University has an AOI and can be used as a parent interest point. The teaching buildings, school gates, gymnasiums, supermarkets, etc. inside Peking University are located within the area range of Peking University and are all child interest points of Peking University. For another example, Xishan Forest Park is the parent interest point, and the toilets, children's playgrounds, entrances, exits, etc. inside Xishan Forest Park are all child interest points of Xishan Forest Park. For example, when the first area is Peking University, the retrieval database determines that Peking University has the attribute of a parent point of interest, then all child points of interest with Peking University as the parent point of interest are searched, and the first other point of interest finally obtained can be a collection of one or more of Peking University East Gate, Peking University West Gate, Peking University Library, and Peking University Gymnasium.

[0079] In some embodiments, the first other points of interest retrieved from the map database may be screened, and the remaining first other points of interest after the screening are determined as relevant points of interest. For example, the screening may be performed based on distance, and the first other points of interest whose distance from the retrieved point of interest is greater than a preset threshold may be screened out.

[0080] Figure 5 is an exemplary flow chart for determining a recommended boarding point according to some embodiments of the present application. Figure 5 As shown, the method 500 includes:

[0081] Step 510 , inputting the candidate boarding points in the third candidate boarding point set into the trained recommendation model. Specifically, step 510 may be performed by the boarding point recommendation module 250 .

[0082] In some embodiments, the boarding point recommendation module 250 may input the candidate boarding points and their attributes in the third candidate boarding point set into a trained recommendation model. In some embodiments, the recommendation model may be a ranking model. For example, a ranking model implemented using a ranking algorithm such as LambdaMART, LamdbsRank, or RankNet.

[0083] In some embodiments, the characteristic information of the point of interest includes but is not limited to: attribute characteristics of the candidate boarding points in the third candidate boarding point set, attribute characteristics of the retrieved point of interest, positional relationship characteristics between the candidate boarding points and the retrieved point of interest, and positional relationship characteristics between the candidate boarding points and the user's positioning location, or a combination of one or more of these.

[0084] The attribute characteristics of the candidate boarding points in the third candidate boarding point set include, but are not limited to, the popularity of the boarding point, the type of the boarding point, etc. The popularity of the boarding point refers to the frequency of users boarding at the boarding point. The type of the boarding point may be a characteristic that represents the boarding point, such as belonging to a commercial area, an office building, etc. The attribute characteristics of retrieving points of interest include, but are not limited to, the number of candidate boarding points that can be determined by the points of interest, the popularity of the points of interest, etc. The popularity of the points of interest may be the number of times the point of interest has been used for retrieval. In some embodiments, the attribute characteristics of retrieving points of interest and candidate boarding points may be attribute characteristics within a certain period of time and / or a certain distance. For example, the number of times a certain boarding point is used for boarding within a month, the number of times a certain boarding point is used for boarding within 10m of a certain boarding point within a month, etc.

[0085] The positional relationship characteristics between the candidate boarding point and the retrieved interest point may be the distance between the candidate boarding point and the retrieved interest point, the cross-road relationship, etc. The distance may be a spherical distance, a walking distance, a straight-line distance, etc. The cross-road relationship may be whether it crosses the road, the walking cost caused by the cross-road, etc. In some embodiments, the positional relationship characteristics between the candidate boarding point and the retrieved interest point may be determined based on the position information of the candidate boarding point and the position information of the retrieved interest point. The position information may include, but is not limited to, longitude and latitude coordinates, geographic names, etc. The position information may be obtained from a map database. In some embodiments, the position information stored in the database may be directly read, or may be obtained through an interface.

[0086] The positional relationship characteristics between the candidate boarding point and the user's location may include the distance between the candidate boarding point and the user's location, the cross-road relationship, etc. For details of the distance and the cross-road relationship, please refer to the above paragraph. In some embodiments, the positional relationship characteristics between the candidate boarding point and the user's location may be determined based on the location information of the candidate boarding point and the user's location information.

[0087] The ranking model can be used to predict the correlation ranking of at least two candidate boarding points related to the retrieved interest point. The ranking model can be pre-trained and stored in a storage device, or can be trained online by a processing device. The method for training the ranking model can be any method in the prior art, and this embodiment does not limit it.

[0088] Step 520 , determining the scoring result of each of the candidate boarding points. Specifically, step 520 may be performed by the boarding point recommendation module 250 .

[0089] In some embodiments, the boarding point recommendation module 250 can obtain the scoring results of the trained recommendation model for all the candidate boarding points in the third candidate boarding point set input. The scoring results reflect the degree of relevance between each candidate boarding point and the retrieved interest point. For example, a candidate boarding point with a higher historical click-through rate has a higher score. For another example, a candidate boarding point that is closer to the user's location has a higher score.

[0090] Step 530 , based on the scoring result, determine the recommended boarding point. Specifically, step 530 may be performed by the boarding point recommendation module 250 .

[0091] In some embodiments, the boarding point recommendation module 250 may sort the candidate boarding points based on the obtained scoring results of the candidate boarding points, and determine the recommended boarding point according to the sorting results. For example, the top 3 or top 1 candidate boarding points in the sorting results are selected as the best boarding points.

[0092] In some embodiments, the boarding point recommendation module 250 may determine the candidate boarding point with a score greater than a threshold as a recommended boarding point. In some embodiments, the threshold may be used to determine whether the correlation level between the candidate boarding point and the retrieved point of interest meets the requirements. In some embodiments, the threshold may be a default value stored in a storage device, or may be dynamically determined according to different conditions.

[0093] The embodiment of the present specification also provides a device, which includes at least a processor and a memory. The memory is used to store one or more computer program instructions. When the instructions are executed by the processor, the device implements the above-mentioned method for recommending a boarding point.

[0094] The embodiment of the present specification also provides a computer-readable storage medium. When the computer program instructions are executed by a processor, the computer program instructions implement the aforementioned method for recommending a boarding point.

[0095] The beneficial effects that may be brought about by the embodiments of the present application include but are not limited to: (1) determining the relevant points of interest for the searched points of interest based on the spatial expansion relationship and the similarity of the candidate boarding points, and taking the candidate boarding points of the relevant points of interest as the candidate boarding points for the searched points of interest, which can increase the selection of recommended boarding points; (2) improving the possibility of recommending suitable boarding points; (3) improving the service efficiency and service quality of the platform. It should be noted that different embodiments may produce different beneficial effects. In different embodiments, the beneficial effects that may be produced may be any one or a combination of the above, or any other beneficial effects that may be obtained. The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only an example and does not constitute a limitation of the present application. Although it is not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to the present application. Such modifications, improvements and corrections are suggested in the present application, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of the present application. At the same time, the present application uses specific words to describe the embodiments of the present application. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of the present application. Therefore, it should be emphasized and noted that "an embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different places in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of the present application can be appropriately combined.

[0096] In addition, it will be appreciated by those skilled in the art that various aspects of the present application may be illustrated and described by a number of patentable categories or situations, including any new and useful process, machine, product or combination of substances, or any new and useful improvements thereto. Accordingly, various aspects of the present application may be performed entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. The above hardware or software may all be referred to as "data blocks", "modules", "engines", "units", "components" or "systems". In addition, various aspects of the present application may be represented as a computer product located in one or more computer-readable media, which includes computer-readable program code.

[0097] A computer storage medium may include a propagated data signal containing computer program code, for example, in baseband or as part of a carrier wave. The propagated signal may be in a variety of forms, including electromagnetic, optical, etc., or a suitable combination. A computer storage medium may be any computer-readable medium other than a computer-readable storage medium, which can be connected to an instruction execution system, device or apparatus to communicate, propagate or transmit the program for use. The program code on the computer storage medium may be transmitted via any suitable medium, including radio, cable, fiber optic cable, RF, or similar media, or any combination of the above media.

[0098] The computer program coding required for the operation of each part of the application can be written in any one or more programming languages, including object-oriented programming languages ​​such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB.NET, Python, etc., conventional procedural programming languages ​​such as C language, Visual Basic, Fortran 2003, Perl, COBOL 2002, PHP, ABAP, dynamic programming languages ​​such as Python, Ruby and Groovy, or other programming languages, etc. The program coding can be run completely on the user's computer, or run on the user's computer as an independent software package, or run partly on the user's computer and partly on the remote computer, or run completely on the remote computer or server. In the latter case, the remote computer can be connected to the user's computer through any network form, such as a local area network (LAN) or a wide area network (WAN), or connected to an external computer (e.g., via the Internet), or in a cloud computing environment, or used as a service such as software as a service (SaaS).

[0099] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this application, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this application. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this application. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0100] Similarly, it should be noted that in order to simplify the description of the disclosure of this application and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this application, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the object of this application are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0101] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of the present application are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0102] Each patent, patent application, patent application disclosure, and other materials, such as articles, books, instructions, publications, documents, etc., cited in this application are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the content of this application, documents that limit the broadest scope of the claims of this application (currently or later attached to this application) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the attached materials of this application are inconsistent or conflicting with the content described in this application, the descriptions, definitions, and / or use of terms in this application shall prevail.

[0103] Finally, it should be understood that the embodiments described in this application are only used to illustrate the principles of the embodiments of the present application. Other variations may also fall within the scope of the present application. Therefore, as an example and not a limitation, the alternative configurations of the embodiments of the present application may be considered to be consistent with the teachings of the present application. Accordingly, the embodiments of the present application are not limited to the embodiments explicitly introduced and described in the present application.

Claims

1. A method for recommending a boarding point, It is characterized in that include: Determine a first candidate boarding point set according to the retrieved points of interest; Determine at least one related point of interest based on the retrieved point of interest, wherein the retrieved point of interest is one or more locations that the user is interested in when preparing to use the service, and the related point of interest is a location related to the retrieved point of interest; determining at least one second candidate boarding point set based on the at least one related point of interest; Merging the first candidate boarding point set with the at least one second candidate boarding point set to obtain a third candidate boarding point set for retrieving points of interest; Based on the third candidate boarding point set, a recommended boarding point is determined.

2. The method according to claim 1, It is characterized in that Determining at least one related point of interest according to the retrieved point of interest comprises: Based on the spatial topological relationship between the retrieved interest point and other interest points, at least one of the related interest points is determined.

3. The method according to claim 2, It is characterized in that The determining at least one of the related points of interest based on the spatial topological relationship between the retrieved point of interest and other points of interest comprises: determining a first area including the retrieved point of interest; At least one first other point of interest in the first area is acquired, and the at least one first other point of interest is determined as the related point of interest.

4. The method according to claim 2, It is characterized in that The determining at least one of the related points of interest based on the spatial topological relationship between the retrieved point of interest and other points of interest comprises: At least one second other interest point whose distance from the retrieved interest point is less than a first threshold is obtained, and the at least one second other interest point is determined as the related interest point.

5. The method according to claim 1, It is characterized in that Determining at least one related point of interest according to the retrieved point of interest comprises: Based on the similarity between the candidate boarding point set of other points of interest and the first candidate boarding point set, at least one third other point of interest is determined, and the at least one third other point of interest is determined as the related point of interest.

6. The method according to claim 1, It is characterized in that The determining of the recommended boarding point based on the third candidate boarding point set includes: Inputting the candidate boarding points in the third candidate boarding point set into the trained recommendation model; Determining a scoring result for each of the candidate boarding points; Based on the scoring results, a recommended boarding point is determined.

7. The method according to claim 6, It is characterized in that The step of determining a scoring result for each of the candidate boarding points includes: Acquire feature data based on the candidate boarding point in the third candidate boarding point set, the feature data comprising: attribute features of the candidate boarding point, attribute features of the retrieved interest points, positional relationship features between the candidate boarding point and the retrieved interest points, and positional relationship features between the candidate boarding point and the user's location, or a combination of one or more of these; A score is calculated for each of the candidate boarding points based on the feature data.

8. The method according to claim 7, It is characterized in that The acquiring feature data based on the candidate boarding points in the third candidate boarding point set comprises: Obtaining location information of the retrieved point of interest; Acquire location information of the candidate boarding point in the third candidate boarding point set; Based on the position information of the candidate boarding point and the position information of the retrieved point of interest, a position relationship feature between the candidate boarding point and the retrieved point of interest is determined.

9. The method according to claim 7, It is characterized in that The acquiring feature data based on the candidate boarding points in the third candidate boarding point set comprises: Obtaining location information of the user; Acquire location information of the candidate boarding point in the third candidate boarding point set; Based on the position information of the candidate boarding point and the positioning information of the user, a position relationship feature between the candidate boarding point and the positioning position of the user is determined.

10. The method according to claim 6, It is characterized in that The recommendation model is the LambdaMART ranking model.

11. A system for recommending boarding points, It is characterized in that include: A first candidate boarding point set determining module, used to determine a first candidate boarding point set according to the retrieved interest points; a related point of interest determination module, configured to determine at least one related point of interest based on the retrieved point of interest, wherein the retrieved point of interest is one or more locations that the user is interested in when preparing to use the service, and the related point of interest is a location related to the retrieved point of interest; A second candidate boarding point set determining module, configured to determine at least one second candidate boarding point set according to the at least one related point of interest; A third candidate boarding point set determining module, configured to merge the first candidate boarding point set with the at least one second candidate boarding point set to obtain a third candidate boarding point set for retrieving the point of interest; The boarding point recommendation module is used to determine a recommended boarding point based on the third candidate boarding point set.

12. The system according to claim 11, It is characterized in that The relevant interest point determination module is used for: Based on the spatial topological relationship between the retrieved interest point and other interest points, at least one of the related interest points is determined.

13. The system of claim 12, It is characterized in that The relevant interest point determination module is used for: determining a first area including the retrieved point of interest; At least one first other point of interest in the first area is acquired, and the at least one first other point of interest is determined as the related point of interest.

14. The system of claim 12, It is characterized in that The relevant interest point determination module is used for: At least one second other interest point whose distance from the retrieved interest point is less than a first threshold is obtained, and the at least one second other interest point is determined as the related interest point.

15. The system of claim 11, It is characterized in that The relevant interest point determination module is used for: Based on the similarity between the candidate boarding point set of other points of interest and the first candidate boarding point set, at least one third other point of interest is determined, and the at least one third other point of interest is determined as the related point of interest.

16. The system of claim 11, It is characterized in that The boarding point recommendation module is used for: Inputting the candidate boarding points in the third candidate boarding point set into the trained recommendation model; Determining a scoring result for each of the candidate boarding points; Based on the scoring results, a recommended boarding point is determined.

17. The system of claim 16, It is characterized in that The boarding point recommendation module is used for: Acquire feature data based on the candidate boarding point in the third candidate boarding point set, the feature data comprising: attribute features of the candidate boarding point, attribute features of the retrieved interest points, positional relationship features between the candidate boarding point and the retrieved interest points, and positional relationship features between the candidate boarding point and the user's location, or a combination of one or more of these; A score is calculated for each of the candidate boarding points based on the feature data.

18. The system of claim 17, It is characterized in that The boarding point recommendation module is used for: Obtaining location information of the retrieved point of interest; Acquire location information of the candidate boarding point in the third candidate boarding point set; Based on the position information of the candidate boarding point and the position information of the retrieved point of interest, a position relationship feature between the candidate boarding point and the retrieved point of interest is determined.

19. The system of claim 17, It is characterized in that The boarding point recommendation module is used for: Obtaining location information of the user; Acquire location information of the candidate boarding point in the third candidate boarding point set; Based on the position information of the candidate boarding point and the positioning information of the user, a position relationship feature between the candidate boarding point and the positioning position of the user is determined.

20. The system of claim 16, It is characterized in that The recommendation model is the LambdaMART ranking model.

21. A device for recommending a boarding point, comprising a memory and a processor, It is 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 10.

22. A computer-readable storage medium storing computer instructions, It is characterized in that When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 10 is implemented.