CN111859185A

CN111859185A - Method, system and device for recommending boarding points and storage medium

Info

Publication number: CN111859185A
Application number: CN202010598097.6A
Authority: CN
Inventors: 张彦; 黄晓东; 刘伯龙; 束纬寰; 马利
Original assignee: Beijing Didi Infinity Technology and Development Co Ltd
Current assignee: Beijing Didi Infinity Technology and Development Co Ltd
Priority date: 2020-06-28
Filing date: 2020-06-28
Publication date: 2020-10-30

Abstract

The embodiment of the application discloses a boarding point recommendation method, a system, a device and a storage medium. The method comprises the following steps: acquiring an original starting point and a destination; recalling at least one candidate site based on the original starting point; calculating relevant characteristic data of each candidate station; ranking each of the candidate sites based on the relevant feature data; and obtaining at least one recommended boarding point based on the sequencing result. According to the method and the device, the plurality of candidate sites are sequenced based on the relevant feature data of the candidate sites, so that more suitable recommended boarding points are obtained, the driver and passenger experience can be considered, the transport capacity cost of a driver and a platform is reduced, and the travel efficiency is improved.

Description

Method, system and device for recommending boarding points and storage medium

Technical Field

The present application relates to the field of transportation, and in particular, to a pick-up point recommendation method, system, device, and storage medium.

Background

With the development of internet technology, online taxi appointment becomes a common travel mode for people, people can send a taxi taking request by inputting a taxi getting-on point and a taxi getting-off point or positioning the current position at a user terminal, and a driver can send passengers in front according to user order information. However, in real life, the current position of the boarding point or location input by the passenger may be the inside of a building, a construction site, a parking-prohibited road section, or a place where other vehicles cannot reach. If these places are used as the boarding points of the users, the drivers often have many detours and can not smoothly pick up and deliver passengers, so that the passenger experience is poor, and the transport capacity cost of the drivers is greatly increased. Therefore, it is necessary to provide a pick-up point recommendation method.

Disclosure of Invention

A first aspect of the present application provides a pick-up point recommendation method. A first aspect of the present application provides a pick-up point recommendation method. The pick-up point recommendation method comprises the following steps: acquiring an original starting point and a destination; recalling at least one candidate site based on the original starting point; calculating relevant feature data of each candidate station, wherein the relevant feature data of the candidate stations comprises at least one of the following: first feature data capable of reflecting walking costs of the original starting point to the candidate site; the second characteristic data can reflect the frequency of getting on the vehicle from the candidate station by the passenger taking the position within the preset range from the original starting point as the starting point within the past preset time; third feature data capable of reflecting the frequency of the passenger getting on the vehicle from the candidate station within a past preset time; and fourth feature data capable of reflecting the cost of driving a driver from the candidate stop to the destination or capable of reflecting the cost of driving a driver from the candidate stop to the destination in combination with the cost of walking passengers from the original origin to the candidate stop; ranking each of the candidate sites based on the relevant feature data; and obtaining at least one recommended boarding point based on the sequencing result.

In some embodiments, the second characteristic data is associated with an estimated walking cost; the estimated walking cost is estimated based on the frequency of getting on the vehicle from the candidate station at the departure point of the passengers taking the position within the preset range from the original departure point as the departure point within the past preset time, the estimated walking distance between the original departure point and the candidate station and the geometric distance between the original departure point and the candidate station.

In some embodiments, the method for ranking each candidate station based on the relevant feature data comprises: and respectively inputting the characteristic data of each candidate station into a trained sequencing model, and receiving the sequencing result of each candidate station output by the sequencing model.

In some embodiments, the method of recalling at least one candidate site based on the original origin comprises at least one of: recalling all the sites within a preset distance range from the original starting point as the candidate sites; or taking N sites closest to the original starting point as the candidate sites, wherein N is a positive integer.

A second aspect of the present application provides a pick-up point recommendation system, comprising: a first acquisition unit configured to acquire an original starting point and a destination; a recall unit for recalling at least one candidate site based on the original starting point; a processing unit, configured to calculate relevant feature data of each candidate station, where the relevant feature data of the candidate station includes at least one of: first feature data capable of reflecting walking costs of the original starting point to the candidate site; the second characteristic data can reflect the frequency of getting on the vehicle from the candidate station by the passenger taking the position within the preset range from the original starting point as the starting point within the past preset time; third feature data capable of reflecting the frequency of the passenger getting on the vehicle from the candidate station within a past preset time; and fourth feature data capable of reflecting the cost of driving a driver from the candidate stop to the destination or capable of reflecting the cost of driving a driver from the candidate stop to the destination in combination with the cost of walking passengers from the original origin to the candidate stop; the first sequencing unit is used for sequencing each candidate station based on the relevant characteristic data; and the first recommending unit is used for obtaining at least one recommended boarding point based on the sequencing result.

In some embodiments, the second characteristic data is associated with an estimated walking cost; the estimated walking cost is estimated based on the frequency of the historical passengers taking the position within the preset range from the original starting point as the starting point within the past preset time to get on the vehicle from the starting point to the candidate station, the estimated walking distance between the original starting point and the candidate station and the geometric distance between the original starting point and the candidate station.

In some embodiments, the first ordering unit is to: and respectively inputting the relevant characteristic data of each candidate station into a trained ranking model, and receiving the ranking result of each candidate station output by the ranking model.

In some embodiments, the recall unit is to: recalling all the sites within a preset distance range from the original starting point as the candidate sites; or taking N sites closest to the original starting point as the candidate sites, wherein N is a positive integer.

A third aspect of the present application provides a pick-up point recommendation device, comprising the device including at least one processor and at least one memory; the at least one memory is for storing computer instructions; the at least one processor is configured to execute at least some of the computer instructions to implement the operations described above.

A fourth aspect of the present application provides a computer-readable storage medium storing computer instructions that, when executed by a processor, perform the operations as described above.

A fifth aspect of the present application provides a pick-up point recommendation method, including: acquiring an original starting point and a destination of a passenger; acquiring at least one candidate station related to the original starting point and a ranking result thereof, wherein the ranking result is obtained based on the related feature data of each candidate station, and the related feature data of the candidate station comprises at least one of the following: first feature data capable of reflecting walking costs of the original starting point to the candidate site; the second characteristic data can reflect the frequency of getting on the vehicle from the candidate station by the passenger taking the position within the preset range from the original starting point as the starting point within the past preset time; third feature data capable of reflecting the frequency of the passenger getting on the vehicle from the candidate station within a past preset time; and fourth feature data capable of reflecting the cost of driving a driver from the candidate stop to the destination or capable of reflecting the cost of driving a driver from the candidate stop to the destination in combination with the cost of walking passengers from the original origin to the candidate stop; and recommending at least one recommended boarding point to the passenger based on the sequencing result.

In some embodiments, the obtaining at least one candidate station related to the original starting point and the ranking result thereof comprises: sending the original starting point to a server; and receiving at least one candidate site returned by the server side and a sequencing result thereof.

A sixth aspect of the present application provides a pick-up point recommendation system, the system comprising: a second acquisition unit for acquiring an original starting point and a destination of the passenger; a third obtaining unit, configured to obtain at least one candidate station related to the original starting point and a ranking result thereof, where the ranking result is obtained based on relevant feature data of each candidate station, and the relevant feature data of the candidate station includes at least one of the following: first feature data capable of reflecting walking costs of the original starting point to the candidate site; the second characteristic data can reflect the frequency of getting on the vehicle from the candidate station by the passenger taking the position within the preset range from the original starting point as the starting point within the past preset time; third feature data capable of reflecting the frequency of the passenger getting on the vehicle from the candidate station within a past preset time; and fourth feature data capable of reflecting the cost of driving a driver from the candidate stop to the destination or capable of reflecting the cost of driving a driver from the candidate stop to the destination in combination with the cost of walking passengers from the original origin to the candidate stop; and the second recommending unit is used for recommending at least one recommended boarding point to the passenger based on the sorting result.

In some embodiments, the third obtaining unit is further configured to: sending the original starting point to a server; and receiving at least one candidate site returned by the server side and the sequencing result thereof.

A seventh aspect of the present application provides a pick-up point recommendation device, the device comprising at least one processor and at least one memory; the at least one memory is for storing computer instructions; the at least one processor is configured to execute at least some of the computer instructions to implement the operations described above.

An eighth aspect of the present application provides a computer-readable storage medium storing computer instructions that, when executed by a processor, perform the operations as described above.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings used in the description of the embodiments will be briefly introduced below. It is obvious that the drawings in the following description are only examples or embodiments of the application, from which the application can also be applied to other similar scenarios without inventive effort for a person skilled in the art. Wherein:

FIG. 1 is a schematic diagram of an application scenario of a pick-up point recommendation system according to some embodiments of the present application;

FIG. 2 is a schematic block diagram of a pick-up point recommendation system shown in accordance with some embodiments of the present application;

FIG. 3 is an exemplary flow chart of a pick-up point recommendation method according to some embodiments of the present application;

FIG. 4 is a schematic block diagram of a pick-up point recommendation system in accordance with further embodiments of the present application;

FIG. 5 is an exemplary flow chart of a pick-up point recommendation method according to other embodiments of the present application.

Detailed Description

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings used in the description of the embodiments will be briefly introduced below. It is obvious that the drawings in the following description are only examples or embodiments of the application, from which the application can also be applied to other similar scenarios without inventive effort for a person skilled in the art. Unless otherwise apparent from the context, or otherwise indicated, like reference numbers in the figures refer to the same structure or operation.

As used in this application and the appended claims, the terms "a," "an," "the," and/or "the" are not intended to be inclusive in the singular, but rather are intended to be inclusive in the plural unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that steps and elements are included which are explicitly identified, that the steps and elements do not form an exclusive list, and that a method or apparatus may include other steps or elements.

Although various references are made herein to certain modules in a system according to embodiments of the present application, any number of different modules may be used and run on a vehicle client and/or server. The modules are merely illustrative and different aspects of the systems and methods may use different modules.

Flow charts are used herein to illustrate operations performed by systems according to embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in the exact order in which they are performed. Rather, various steps may be processed in reverse order or simultaneously. Meanwhile, other operations may be added to the processes, or a certain step or several steps of operations may be removed from the processes.

The embodiment of the application can be applied to different traffic service systems, including but not limited to one or a combination of land, river, lake, sea, air and the like. For example, a human powered vehicle, a transportation means, an automobile (e.g., a small car, a bus, a large transportation vehicle, etc.), a rail transportation (e.g., a train, a motor car, a high-speed rail, a subway, etc.), a ship, an airplane, an aircraft, a hot air balloon, an unmanned vehicle, a transportation system to which management and/or distribution is applied, a delivery/reception express, etc., and the like. The application scenarios of the different embodiments of the present application include, but are not limited to, one or a combination of several of a web page, a browser plug-in, a client, a customization system, an intra-enterprise analysis system, an artificial intelligence robot, and the like. It should be understood that the application scenarios of the system and method of the present application are merely examples or embodiments of the present application, and those skilled in the art can also apply the present application to other similar scenarios without inventive effort based on these figures. For example, other similar guided user parking systems.

Fig. 1 is a schematic view of an application scenario of a pick-up point recommendation system according to some embodiments of the present application. In some embodiments, the pick-up point recommendation system 100 may determine pick-up points and recommend to the passenger, directing the passenger to select the appropriate pick-up point. In some embodiments, the pick-up point recommendation system 100 may be an online service platform for internet services. For example, the pick-up point recommendation system 100 may be an online transportation service platform for a transportation service. In some embodiments, the pick-up recommendation system 100 may be applied to taxi appointment services, such as taxi calls, express calls, special calls, mini-bus calls, car pool, bus service, driver hiring and pick-up services, and the like. In some embodiments, the pick-up point recommendation system 100 may also be applied to designated driving, express delivery, take-away, and the like. The pick-up point recommendation system 100 may be an online service platform including a server 110, a network 120, a user terminal 130, and a storage device 140. The server 110 may include a processing device 112.

In some embodiments, the server 110 may be used to process information and/or data related to determining pick-up point recommendations. The server 110 may be a stand-alone server or a group of servers. The set of servers can be centralized or distributed (e.g., server 110 can be a distributed system). The server 110 may be regional or remote in some embodiments. For example, server 110 may access information and/or data stored in user terminal 130, storage device 140, through network 120. In some embodiments, server 110 may be directly connected to user terminal 130, storage device 140 to access information and/or material stored therein. In some embodiments, the server 110 may execute 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, and the like.

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 of the functions described herein. For example, the processing device 112 may receive a car use request signal sent by the user terminal 130 and provide the user with a pick-up point recommendation. 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 processing device). By way of 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 Processor (GPU), a Physical Processor (PPU), a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), a programmable logic circuit (PLD), a controller, a micro-controller unit, a Reduced Instruction Set Computer (RISC), a microprocessor, or the like, or any combination thereof.

In some embodiments, network 120 may facilitate the exchange of data and/or information. In some embodiments, one or more components (e.g., server 110, user terminal 130, storage device 140) in the pick-up point recommendation system 100 may send data and/or information to other components in the pick-up point recommendation system 100 via the network 120. In some embodiments, network 120 may be any type of wired or wireless network. For example, network 120 may include a cable network, a wired network, a fiber optic network, a telecommunications network, an intranet, the internet, a Local Area Network (LAN), a Wide Area Network (WAN), a Wireless Local 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, the like, or any combination thereof. In some embodiments, network 120 may include one or more network access points. For example, the network 120 may include wired or wireless network access points, such as base stations and/or Internet switching points 120-1, 120-2, …, through which one or more components of the pick-up recommendation system 100 may connect to the network 120 to exchange data and/or information.

In some embodiments, the user may obtain the pick-up point recommendation through the user terminal 130. In some embodiments, the user terminal 130 may include one or any combination of a mobile device 130-1, a tablet computer 130-2, a laptop computer 130-3, an in-vehicle device 130-4, and the like. In some embodiments, the mobile device 130-1 may include a smart home device, a wearable device, a smart mobile device, a virtual reality device, an augmented reality device, and the like, or any combination thereof. In some embodiments, the smart furniture device may include a smart lighting device, a control device for a smart appliance, a smart monitoring device, or the like, or any combination thereof. In some embodiments, user terminal 130 may include a location-enabled device to determine the location of the user and/or user terminal 130.

Storage device 140 may store data and/or instructions. In some embodiments, storage device 140 may store the profile retrieved from user terminal 130. In some embodiments, storage device 140 may store information and/or instructions for execution or use by server 110 to perform the example methods described herein. In some embodiments, storage device 140 may also store historical orders, historical vehicle usage records for each passenger, and the like. In some embodiments, storage device 140 may include mass storage, removable storage, volatile read-and-write memory (e.g., random access memory, RAM), read-only memory (ROM), the like, or any combination thereof. In some embodiments, the storage device 140 may be implemented on a cloud platform. For example, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, and the like, or any combination thereof.

In some embodiments, storage device 140 may be connected to network 120 to communicate with one or more components of system 100 (e.g., server 110, user terminal 130, etc.). One or more components of the pick-up point recommendation system 100 may access data or instructions stored in the storage device 140 via the network 120. In some embodiments, the storage device 140 may be directly connected to or in communication with one or more components (e.g., the server 110, the user terminal 130) in the pick-up point recommendation system 100. In some embodiments, the storage device 140 may be part of the server 110.

FIG. 2 is a schematic block diagram of a pick-up point recommendation system shown in accordance with some embodiments of the present application. As shown in fig. 2, in some embodiments, the pick-up point recommendation system 200 may include: a pick-up point recommendation system 200 comprising: a first acquisition unit 201 for acquiring an original starting point and a destination; a recalling unit 203, configured to recall at least one candidate site based on the original starting point; a processing unit 205, configured to calculate relevant feature data of each candidate station; a first sorting unit 207, configured to sort the candidate stations based on the relevant feature data; and a first recommending unit 209 for obtaining at least one recommended boarding point based on the sorting result.

In some embodiments, the relevant feature data of the candidate site includes at least one of: first feature data capable of reflecting walking costs of the original starting point to the candidate site; the second characteristic data can reflect the frequency of getting on the vehicle from the candidate station by the passenger taking the position within the preset range from the original starting point as the starting point within the past preset time; third feature data capable of reflecting the frequency of the passenger getting on the vehicle from the candidate station within a past preset time; and fourth feature data capable of reflecting the driving cost of the driver from the candidate stop to the destination or capable of comprehensively reflecting the driving cost of the driver from the candidate stop to the destination and the walking cost of the passenger from the original starting point to the candidate stop.

In some embodiments, the second characteristic data is associated with an estimated walking cost; the estimated walking cost is estimated based on the frequency of passengers getting on the vehicle from the departure point to the candidate station by taking the position within the preset range from the original departure point as the departure point in the past preset time, the estimated walking distance between the original departure point and the candidate station and the geometric distance between the original departure point and the candidate station.

In some embodiments, the first ranking unit 207 is configured to input the relevant feature data of each candidate station into a trained ranking model, and receive a ranking result of each candidate station output by the ranking model.

In some embodiments, the system 200 further comprises a training module to: acquiring a plurality of historical orders, wherein the historical orders comprise a historical original starting point, a historical destination, a billing starting point and at least one recommended site; processing each of the plurality of historical orders to obtain a training sample as follows: acquiring relevant characteristic data of each recommended site as input data of a training sample; determining the mark of each recommended station based on whether the distance between the recommended station and the charging starting point is smaller than a preset threshold value or not; combining the marks of all recommended sites and the related characteristic data to obtain the training sample; and training by using a plurality of training samples to obtain the sequencing model.

In some embodiments, the ranking model comprises at least one of the following models: lambda rank model, Lambda Mart model, LTR model.

In some embodiments, the recall unit 203 is to: recalling all the sites within a preset distance range from the original starting point as the candidate sites; or taking N sites closest to the original starting point as the candidate sites, wherein N is a positive integer.

It should be understood that the system and its elements shown in FIG. 2 may be implemented in a variety of ways. For example, in some embodiments, the system and its elements may be implemented in hardware, software, or a combination of software and hardware. Wherein the hardware portion may be implemented using dedicated logic; the software portions may be stored in a memory for execution by a suitable instruction execution system, such as a microprocessor or specially designed hardware. Those skilled in the art will appreciate that the methods and systems described above may be implemented using computer executable instructions and/or embodied in processor control code, such code being provided, for example, on a carrier medium such as a diskette, CD-or DVD-ROM, a programmable memory such as read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The system and its elements of the present application may be implemented not only by hardware circuits such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., but also by software executed by various types of processors, for example, or by a combination of the above hardware circuits and software (e.g., firmware).

It should be noted that the above description of the system and its elements is merely for convenience of description and is not intended to limit the present application to the scope of the illustrated embodiments. It will be appreciated by those skilled in the art that, given the teachings of the present system, any combination of modules or sub-system configurations may be used to connect to other modules without departing from such teachings. For example, in some embodiments, the first obtaining unit 201, the recalling unit 203, the processing unit 205, the first sorting unit 207, and the first recommending unit 209 disclosed in fig. 2 may be different units in a system, or may be a unit that implements the functions of two or more units described above. For another example, each unit may share one storage device 140, and each unit may have its own storage device 140. Such variations are within the scope of the present application.

FIG. 3 is an exemplary flow chart diagram illustrating implementation steps of a pick-up point recommendation method according to some embodiments of the present application.

In still other embodiments of the present application, a pick-up point recommendation method is provided, which may be performed by the server 110, and the method 300 may include the steps of:

Step 301, acquiring an original starting point and a destination; in some embodiments, this step may be performed by the first acquisition unit 201 in the system 200.

In some embodiments, the original starting point may be a query term input by a user, or may be a current position of the user obtained by a positioning technique. For example, when the user inputs a query term at the user terminal 130, the user terminal 130 may transmit the query term to the server 110 via the network 120, and the processing device 112 may receive the query term and process the query term.

In some embodiments, the manner in which the user enters the query term may include, but is not limited to, any combination of one or more of typing, handwriting, selection, voice, scanning, and the like. Specifically, the typing input may include english input, chinese input, and the like depending on the language. The selection input may include selecting a query term from a selection list, and the like. The scan input may include a scan barcode input, a scan two-dimensional code input, a scan text input, a scan picture input, and the like. For example, the query term may be a Chinese character directly handwritten by the user. As another example, the query term may be a word or letter identified from a user scanned picture input. For another example, the query term may be a word or letter recognized from a voice input by the user.

In some embodiments, the current location of the user obtained by the user terminal 130 through the positioning technology may include latitude and longitude information, and thus an original starting point of the user may be determined according to the latitude and longitude information. In some embodiments, the original starting point may include a starting place name. In some embodiments, the positioning technology may include Global Positioning System (GPS) technology, beidou navigation system technology, global navigation satellite system (GLONASS) technology, galileo positioning system (galileo) technology, quasi-zenith satellite system (QAZZ) technology, base station positioning technology, Wi-Fi positioning technology, and the like, or any combination thereof.

In some embodiments, the destination may be a drop-off point designated by a user. In some embodiments, the destination may be an exit point entered by the user through the user terminal 130. For example, the user may input the information of the lower point by text, image, or voice input, retrieving the "POI name", or the like. The user may input the departure point information, which may include a destination name, which may include an abbreviation, a colloquial name, an official name, and the like. For example, enter "Wangfu well" corresponding to Wangfu well department of general merchandise.

Step 303, recalling at least one candidate site based on the original starting point; in some embodiments, this step may be performed by recall unit 203 in system 200.

In some embodiments, a method of recalling at least one candidate site based on the original origin may comprise: recalling all the sites within a preset distance range from the original starting point as the candidate sites; or taking N sites closest to the original starting point as the candidate sites, wherein N is a positive integer.

In some embodiments, the stations may be actual geographic locations in a road network structure that may be used as stops or pickup points for vehicles. In some embodiments, the system may mark the pick-up points commonly used by historical passengers as stops for storage in the storage device 140 based on historical orders or historical taxi taking records. In other embodiments, the system may also designate geographic locations suitable for parking or driving as stations based on the road network structure. For example, a geographical location with a high degree of identification and less likely to be congested may be selected as a station and stored in the storage device 140. Sites stored in storage device 140 may be recalled by recall unit 203 according to a rule.

In some embodiments, recall unit 203 may recall one or more candidate sites based on a distance from an original origin. For example, all sites within a distance of 500m from the original origin may be recalled as candidate sites. In some embodiments, the recalling unit 203 may also recall N candidate sites based on the closest distance from the original starting point, where N is a positive integer. For example, the 15 sites closest to the original origin may be recalled as candidate sites for recall.

In some embodiments, the original starting point may be a query term input by a user through a user terminal, and the query term may include one or more keywords related to the original starting point. One or more candidate sites may be recalled based on one or more keywords. In some embodiments, the recalled candidate sites may include one or more names associated with the original starting point.

In some embodiments, the processing device 112 may determine one or more candidate sites by processing the obtained query terms. For example, the processing device 112 may further recall one or more candidate sites by establishing a database in which the association of the query term with the site is established. In some embodiments, the database may be a map database including Google maps, high-end maps, Baidu maps, and the like. As another example, processing device 112 may input the query term into a trained recall model and output the candidate sites using the recall model. In some embodiments, the recall model may be a Lambda rank model, a Lambda Mart model, or the like ranking model.

Step 305, calculating relevant characteristic data of each candidate station; in some embodiments, this step may be performed by processing unit 205 in system 200.

In some embodiments, the relevant feature data of the candidate station may include one or more of first feature data, second feature data, third feature data, and fourth feature data.

In some embodiments, the first characteristic data may be a walking score. In some embodiments, the first feature data can reflect walking costs of the original origin to the candidate site. In some embodiments, the walk is associated with an estimated walk cost.

In some embodiments, the estimated walking cost may be estimated based on local heat, walking EDA, and geometric distance between the original origin and the candidate site.

The local heat is the frequency of passengers getting on the vehicle from the departure point to the candidate station, where the position within the preset range from the original starting point is taken as the departure point, for example, a circle is drawn by taking the original starting point as the center of the circle and the preset distance as the radius, and the frequency of passengers getting on the vehicle from the departure point to the candidate station is taken as any position within the circle. In some embodiments, the number of orders that passengers get on the candidate station from the circle in the past preset time in the circle with the original starting point as the center and the preset distance as the radius may be counted, and the frequency is positively correlated to the number of orders. In some embodiments, the number a of orders that the passenger departed from the circle in the historical orders within the past preset time may also be counted, for example, 2000, and it is understood that the number a of orders includes the total number of orders that arrive at different other places from the circle; and counting the number of orders B, such as 800, of the historical orders, which are sent out from the circle by the passenger and arrive at the candidate site, and determining the frequency (such as the frequency of 800/2000-0.4) based on the amount of orders A and the amount of orders B. The past preset time may be the past week, month, year, etc.

The walk EDA is the estimated walk distance between the original origin and the candidate site. In some embodiments, the pedestrial EDA may be characterized based on the length of the walkable path from the original starting point to the candidate station. Wherein, all the passing points on the walkable path are reachable by walking. In some embodiments, when the walkable path between the original start point and the candidate station is multiple, the length of the shortest one of the walkable paths may be used to characterize the walker EDA. In some embodiments, the pedestrial EDA may be characterized by a number of steps or a length.

In some embodiments, the geometric distance may be understood as a distance between the original starting point and the candidate station obtained based on a geometric calculation method. In some embodiments, the geometric distance includes, but is not limited to, a straight line distance or a spherical distance between two points. The spherical distance may be the length of the shortest connecting line between two points on the spherical surface, that is, the length of a minor arc between the two points of a great circle passing through the two points.

In some embodiments, the calculation formula for the estimated walking cost may be: when the local heat is 0, estimateWalking cost min (EDA, 2 × r); when the local heat is larger than a preset value, estimating the walking cost to be min (EDA, r); when the local heat is between 1 and the preset value, the estimated walking cost is min (EDA, [2.5-0.5 × log% ₁₀(max (historical heat, 10))]X r). The preset value may be 500, 1000, 2000 or other values, and may be adjusted according to actual conditions. EDA is the estimated walking distance between the original starting point and the candidate station; and r is the geometric distance between the original starting point and the candidate station.

In some embodiments, the walk score may be negatively correlated with the estimated walk cost. In some embodiments, the walking score may be of a fixed numerical interval. When the estimated walking cost is 0, the walking is divided into the maximum value; the walking score is closer to 0 as the estimated walking cost is larger. The maximum value may be an arbitrarily set integer, and may be, for example, 1, 10, or 100. For example only, the calculation formula for the walking score may be: max (-p × p/250000+1.0, 0.0) × 100, where p is the estimated walking cost.

In some embodiments, the second characteristic data may be historical heat. For example, the historical popularity can reflect the frequency of getting-on from the candidate station by a passenger who starts at a position within a preset range from the original starting point within a past preset time. In some embodiments, the number of orders for passengers in a preset area to get on the candidate station from a departure point in a circle with a preset distance as a radius and an original start point as a center of the circle in the historical orders in the past preset time may be counted, and the frequency is positively related to the number of orders. In some embodiments, the number a of orders placed by passengers in the area in the historical orders within the past preset time may also be counted, such as 10000, and it is understood that the number a of orders includes all orders with other places as boarding places; and counting the order number B of the passengers in the area with the candidate station as the boarding point, for example, 20 in the historical orders, and determining the frequency (for example, the frequency is 20/10000-0.002) based on the order number a and the order number B. The past preset time may be the past week, month, year, etc. The preset area may be a certain cell range, a certain administrative district range, a certain city range, etc.

In some embodiments, the second characteristic data may be associated with an estimated walking cost. In some embodiments, the second characteristic data may be characterized by a historical heat score, and the historical heat score may be positively correlated with the historical heat score of the candidate site. In some embodiments, the historical heat score may be a fixed numerical interval. When the historical heat is 0, the historical heat is divided into 0; when the historical heat degree is larger, the historical heat degree is higher until the maximum value is reached. The maximum value may be an arbitrarily set integer, and may be, for example, 5, 10, or 20. For example only, the historical heat scores may be calculated as: min (log)₁₀max (historical popularity of candidate sites, 1.0), 5).

In some embodiments, the third characteristic data may be personalized heat. For example, the personalized popularity can reflect the frequency of the passengers getting on the vehicle from the candidate station within a past preset time. In some embodiments, the number of orders of the candidate station as the pick-up point of the passenger who made the order request in the historical orders in the past preset time may be counted, and the frequency is positively related to the number of orders. In some embodiments, the number of orders a sent by the passenger in the historical orders within the past preset time may also be counted, for example, 20, and it is understood that the number of orders a includes the total number of orders that the passenger uses other places as the boarding points; and counting the order number B of the passenger with the candidate station as the boarding point, such as 5, in the historical orders, and determining the frequency (such as the frequency of 5/20-0.25) based on the order number a and the order number B. The past preset time may be the past week, month, year, etc.

In some embodiments, the third feature data may be characterized by a personalized score, which may be positively correlated with a personalized heat of the candidate site. In some embodiments, the personalized partition may be of a fixed numerical range. When the personalized heat degree is 0, the personalization is 0; when the personalized heat degree is higher, the personalized score is higher until the maximum value is reached. The maximum value may be an arbitrarily set integer, and may be, for example, an integer3. 5 or 10, etc. By way of example only, the calculation formula for the personalized score may be: min (log)₁₀(1+ personalized heat of candidate site), 3) × walking score. In this formula, the personalization score is also positively correlated with the walking score, and the higher the walking score is, the higher the personalization score is.

In some embodiments, the personalized heat can be historical orders of boarding behaviors of users in half a year mined in an off-line manner, the historical orders are clustered to generate personalized boarding cluster clusters, the personalized boarding positions of the users are filled into the database in an off-line manner, and the database is queried to obtain the personalized heat.

In some embodiments, the fourth characteristic data may reflect the cost of driving the driver from the candidate site to the destination. In some embodiments, the fourth characterization data may synthetically reflect the cost of the driver's walking from the candidate site to the destination and the cost of the passenger's walking from the original origin to the candidate site. In some embodiments, the fourth data characteristic may be characterized by a forward road score.

In some embodiments, the forward road score may be negatively correlated to a distance traveled by the candidate station to the destination and positively correlated to a walking score. In some embodiments, the forward-route score is higher when the distance between the candidate station and the destination is smaller, and the forward-route score reaches the maximum value when the distance between the candidate station and the destination is shortest; the higher the passenger walking score, the higher the forward road score. The maximum value may be an arbitrarily set integer, and may be, for example, 30, 50, or 100. For example only, the calculation formula of the forward road score may be: max ([100- (vehicle travel distance from candidate station to destination-n)/max (n, 1) × 100] × walking score/100, 0). And n is the shortest driving distance to the destination in all the candidate stations. When the vehicle-traveling distance from the candidate station to the destination is equal to the shortest vehicle-traveling distance from the candidate station to the destination, the forward-road score reaches the maximum value.

In other embodiments, a route may be generated based on the current position of the driver to the destination, and the fourth data characteristic may reflect the distance of the candidate stop to the route.

Step 307, ranking each candidate station based on the relevant feature data; in some embodiments, this step may be performed by a first ordering unit 207 in the system 200.

In some embodiments, the method for ranking each candidate station based on the relevant feature data comprises: and respectively inputting the relevant characteristic data of each candidate station into a trained ranking model, and receiving the ranking result of each candidate station output by the ranking model. For example, trained ranking model parameters may be retrieved from the storage device 140 to obtain a ranking model.

In some embodiments, after the user initiates a riding order (e.g., a carpool order) at the user terminal 130, the server 110 may recall the candidate site based on the order information, and calculate corresponding related feature data according to the above-mentioned related feature data calculation method; and inputting the relevant characteristic data of the recalled candidate sites into the trained ranking model, and outputting a ranking result by using the ranking model. In some embodiments, the ranking model may include a Lambda rank model, a LambdaMart model, a LTR model, and the like. In some embodiments, the ranking results may output a recommended pick-up point and its score.

In some embodiments, the ranking model may be trained by: acquiring a plurality of historical orders; processing each of a plurality of historical orders to obtain a training sample; and training by using a plurality of training samples to obtain the sequencing model. In some embodiments, the historical order includes a historical original starting point, a historical boarding point (i.e., a starting billing point, also a location where the driver clicks "passenger arrived" with a manual slide app after receiving the passenger), a historical destination, and at least one recommendation site. Specifically, the processing procedure may include: acquiring relevant characteristic data of each recommended site as input data of a training sample; determining the mark of each recommended station based on whether the distance between the recommended station and the historical vehicle points is smaller than a preset threshold value; and combining the relevant characteristic data and marks of each recommended site to obtain the training sample. In some embodiments, the system may obtain corresponding relevant feature data in each historical order from an online log of the taxi-taking software, and integrate the order data corresponding to the order number and the order number together to generate a corresponding training sample.

In some embodiments, the recommended sites may refer to recommended boarding points given by the system recorded in the historical order, for example, relevant sites obtained based on order data (e.g., original starting point, current location of passenger, etc.) are recommended to the user by the system, and these relevant sites may be recorded in the historical order as recommended sites.

In some embodiments, the marking may be based on whether a geometric distance (e.g., a spherical distance) between a billing start point (where the user actually gets on the bus) and a station (one of the recommended stations) is less than a preset threshold. For example, less than 30 meters is a positive sample, labeled "1", and more than 30 meters is a negative sample, labeled "0".

In some embodiments, an initial ranking model is trained based on the training samples. In some embodiments, the process of adjusting the initial ranking model parameter may be based on a comparison between an output result of the ranking model and a marking result, and when a deviation between the output ranking result and the marking result is large, a certain penalty is given to the ranking model, and when an agreement between the output ranking result and the marking result is high, a certain reward is given to the ranking model, so as to obtain a final ranking model for site ranking. For example, the recommended site a is a negative sample and is marked as "0", after model training, the top five recommended sites in the ranking result include the site a, and at this time, a certain penalty needs to be given to the ranking model, and training is continued on the ranking model, so that the tuning effect is achieved.

In some embodiments, the test data is input into a final ranking model, which outputs ranked sites and their scores. For example, the ranking model outputs the top five ranked recommended sites and their scores. And comparing the output result with the marking result to verify the training effect of the sequencing model. For example, if five recommended sites output by the ranking model are all marked as positive samples "1", the ranking model has a good training effect and can be put into use; if the number of negative samples "0" is large (e.g., greater than a certain threshold), the ranking model needs to be retrained.

Step 309, obtaining at least one recommended boarding point based on the sorting result; in some embodiments, this step may be performed by the first recommending unit 209 in the system 200.

In some embodiments, the first recommending unit 209 may use the top N stations in the ranking result as recommended boarding points.

In some embodiments, the obtained recommended pick-up points may be presented in a list on a display interface of the user terminal 130.

It should be noted that the above description of the flow is for illustration and description only and does not limit the application scope of the present application. Various modifications and alterations to the flow may occur to those skilled in the art, given the benefit of this disclosure. However, such modifications and variations are intended to be within the scope of the present application.

In other embodiments of the present application, there is provided a pick-up point recommendation device comprising at least one processor and at least one memory; the at least one memory is for storing computer instructions; the at least one processor is configured to execute at least some of the computer instructions to implement the operations described above.

In still other embodiments of the present application, a computer-readable storage medium is provided that stores computer instructions that, when executed by a processor, implement the operations described above.

FIG. 4 is a schematic block diagram of a pick-up point recommendation system in accordance with further embodiments of the present application.

As shown in FIG. 4, in some embodiments, the pick-up point recommendation system 400 may include: a second obtaining unit 401 for obtaining an original starting point and destination of the passenger; a third obtaining unit 403, configured to obtain at least one candidate site related to the original starting point and a ranking result thereof; and a second recommending unit 405 for recommending at least one recommended boarding point to the passenger based on the sorting result.

In some embodiments, the third obtaining unit 403 is further configured to: sending the original starting point to a server; and receiving at least one candidate site returned by the server side and the sequencing result thereof.

It should be noted that the above description of the system and its modules is merely for convenience of description and should not limit the present application to the scope of the illustrated embodiments. It will be appreciated by those skilled in the art that, given the teachings of the present system, any combination of modules or sub-system configurations may be used to connect to other modules without departing from such teachings. For example, in some embodiments, the second obtaining unit 401, the third obtaining unit 403, and the second recommending unit 405 disclosed in fig. 4 may be different units in a system, or may be a unit that implements the functions of two or more units described above. For another example, each unit may share one storage device 140, and each unit may have its own storage device 140. Such variations are within the scope of the present application.

FIG. 5 is an exemplary flowchart illustrating implementation steps of a pick-up point recommendation method according to further embodiments of the present application.

In still other embodiments of the present application, a pick-up point recommendation method is provided, which may be performed by the user terminal 130, and the method 500 may include the steps of:

Step 501, obtaining an original starting point and a destination of a passenger; in some embodiments, this step may be performed by the second acquisition unit 401 in the system 400.

In some embodiments, the original starting point may be a boarding point entered by the user at the user terminal 130. In some embodiments, the destination may be an exit point entered by the user at the user terminal 130.

In some embodiments, the manner in which the user enters the entry point or the exit point may include, but is not limited to, any combination of one or more of typing input, handwriting input, selection input, voice input, scanning input, and the like. For example, the user directly hand-writes the chinese name of the original starting point on the display interface of the user terminal 130. For example, the user inputs an english abbreviation of the destination by voice at the user terminal 130. For another example, the user scans a street view picture of the input destination or the like at the user terminal 130.

Step 503, obtaining at least one candidate site related to the original starting point and a sequencing result thereof; in some embodiments, this step may be performed by the third obtaining unit 403 in the system 400.

In some embodiments, the at least one candidate site and the ranking result thereof may be provided by the server. For example, the user terminal 130 sends the original starting point to the server; and receiving at least one candidate site returned by the server side and a sequencing result thereof. In some embodiments, the at least one candidate station and the ranking result thereof may also be processed by a processor of the user terminal 130. The process of obtaining the ranking result may specifically refer to the related description of fig. 3.

Step 505, recommending at least one recommended boarding point to the passenger based on the sequencing result; in some embodiments, this step may be performed by the second recommendation unit 405 in the system 400.

In some embodiments, the second recommending unit 405 may take the top N sites in the ranking results as recommended boarding sites, for example, display the top 5 sites in the ranking results on a display interface; in another embodiment, sites with scores greater than a certain threshold may be considered recommended pick-up points, which may be 80 points, 90 points, 95 points, etc.

In some embodiments, the perception of the user on the recommended boarding point may be further improved by adjusting the arrangement, display position, and the like, or any combination thereof, of the recommended boarding point on the display interface.

In some embodiments, the arrangement may include an up-down arrangement and a left-right arrangement. For example, when a user inputs a query word in an input box of a user terminal, the sorted results output by the model are presented to the user in an up-down arrangement. For example, based on the sorting result, the second recommending unit 405 presents it to the user in a left-right arrangement.

In some embodiments, the display modes may include a thumbnail display and a full display. In some embodiments, when the recommended pick-up point information in the ranking result contains a length greater than that of the display box, the recommended pick-up point may be presented to the user terminal in an abbreviated display. For example, when the recommended upper vehicle point information in the ranking result is long, only the front part information of the recommended upper vehicle point may be displayed in the display frame, and the part beyond the display frame may be omitted. In some embodiments, the complete display may be a complete presentation of the ranking results to the user. For example, when the recommended boarding point information in the sorting result is larger than the length of the display frame, the recommended boarding point information can be completely displayed by adjusting the size of the font.

In some embodiments, the display position may include below the input box, above the input box, to the right of the input box, and so on. For example, after the user inputs the query word at the user terminal, the ranking result output based on the ranking model is presented to the user below the input box. For another example, after the user inputs the query term at the user terminal, the query term is presented to the user at the right side of the input box based on the ranking result.

It should be noted that the above description is merely for convenience and should not be taken as limiting the scope of the present application. It will be understood by those skilled in the art that various changes and modifications in form and detail may be made in the implementation of the above-described processes without departing from the principles of the present application. However, such changes and modifications do not depart from the scope of the present application.

The beneficial effects that may be brought by the embodiments of the present application include, but are not limited to: (1) by sequencing and recommending the candidate sites recalled based on the original starting points, recommended boarding points which are convenient to reach for drivers and passengers can be provided for users, so that the driver experience is improved, the driver transport cost is reduced, and the efficiency is improved; (2) by selecting the relevant characteristic data of the appropriate candidate sites, the ranking result obtained by more accurately calculating the scores of the candidate sites is more suitable.

It is to be noted that different embodiments may produce different advantages, and in different embodiments, any one or combination of the above advantages may be produced, or any other advantages may be obtained.

The foregoing describes the present application and/or some other examples. The present application can be modified in various ways in light of the above. The subject matter disclosed herein can be implemented in various forms and examples, and the present application can be applied to a wide variety of applications. All applications, modifications and variations that are claimed in the following claims are within the scope of this application.

Also, this application uses specific language to describe embodiments of the application. Reference throughout this specification to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic described in connection with at least one embodiment of the present application is included in at least one embodiment of the present application. Therefore, it is emphasized and should be appreciated that two or more references to "an embodiment," or "one embodiment," or "an alternative embodiment," or "another embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, some features, structures, or characteristics of one or more embodiments of the present application may be combined as appropriate.

Those skilled in the art will appreciate that various modifications and improvements may be made to the disclosure herein. For example, the different system components described above are implemented by hardware devices, but may also be implemented by software solutions only. For example: the system is installed on an existing server. Further, the location information disclosed herein may be provided via a firmware, firmware/software combination, firmware/hardware combination, or hardware/firmware/software combination.

All or a portion of the software may sometimes communicate over a network, such as the internet or other communication network. Such communication enables loading of software from one computer device or processor to another. Thus, another medium capable of transferring software elements may also be used as a physical connection between local devices, such as optical, electrical, electromagnetic waves, etc., propagating through cables, optical cables, or the air. The physical medium used for the carrier wave, such as an electric, wireless or optical cable or the like, may also be considered as the medium carrying the software. As used herein, unless limited to a tangible "storage" medium, other terms referring to a computer or machine "readable medium" refer to media that participate in the execution of any instructions by a processor.

Computer program code required for the operation of various portions of the present application may be written in any one or more programming languages, including an object oriented programming language such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C + +, C #, VB.NET, Python, and the like, a conventional programming language such as C, Visual Basic, Fortran 2003, Perl, COBOL 2002, PHP, ABAP, a dynamic programming language such as Python, Ruby, and Groovy, or other programming languages, and the like. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any network, such as a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet), or in a cloud computing environment, or as a service using, for example, software as a service (SaaS).

Additionally, the order in which elements and sequences of the processes described herein are processed, the use of alphanumeric characters, or the use of other designations, is not intended to limit the order of the processes and methods described herein, unless explicitly claimed. While various presently contemplated embodiments of the invention have been discussed in the foregoing disclosure by way of example, it is to be understood that such detail is solely for that purpose and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements that are within the spirit and scope of the embodiments herein. For example, although the system components described above may be implemented by hardware devices, they may also be implemented by software-only solutions, such as installing the described system on an existing server or mobile device.

Similarly, it should be noted that in the preceding description of embodiments of the application, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of one or more of the embodiments. This method of disclosure, however, is not intended to require more features than are expressly recited in the claims. Indeed, the embodiments may be characterized as having less than all of the features of a single embodiment disclosed above.

Numbers describing attributes, quantities, etc. are used in some embodiments, it being understood that such numbers used in the description of the embodiments are modified in some instances by the use of the modifier "about", "approximately" or "substantially". Unless otherwise indicated, "about", "approximately" or "substantially" indicates that the number allows a variation of ± 20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximations that may vary depending upon the desired properties of the individual embodiments. In some embodiments, the numerical parameter should take into account the specified significant digits and employ a general digit preserving approach. Notwithstanding that the numerical ranges and parameters setting forth the broad scope of the range are approximations, in the specific examples, such numerical values are set forth as precisely as possible within the scope of the application.

Each patent, patent application publication, and other material, such as articles, books, specifications, publications, documents, articles, and the like, cited in this application is hereby incorporated by reference in its entirety. Except where the application is filed in a manner inconsistent or contrary to the present disclosure, and except where the claim is filed in its broadest scope (whether present or later appended to the application) as well. It is noted that the descriptions, definitions and/or use of terms in this application shall control if they are inconsistent or contrary to the statements and/or uses of the present application in the material attached to this application.

Finally, it should be understood that the embodiments described herein are merely illustrative of the principles of the embodiments of the present application. Other variations are also possible within the scope of the present application. Thus, by way of example, and not limitation, alternative configurations of the embodiments of the present application can be viewed as being consistent with the teachings of the present application. Accordingly, embodiments of the present application are not limited to those explicitly described and depicted herein.

Claims

1. A pick-up point recommendation method implemented by at least one processor, the method comprising:

acquiring an original starting point and a destination;

recalling at least one candidate site based on the original starting point;

calculating relevant feature data of each candidate station, wherein the relevant feature data of the candidate stations comprises at least one of the following:

first feature data capable of reflecting walking costs of the original starting point to the candidate site;

the second characteristic data can reflect the frequency of getting on the vehicle from the candidate station by the passenger taking the position within the preset range from the original starting point as the starting point within the past preset time;

third feature data capable of reflecting the frequency of the passenger getting on the vehicle from the candidate station within a past preset time; and

Fourth feature data capable of reflecting the cost of travel of the driver from the candidate stop to the destination or capable of synthetically reflecting the cost of travel of the driver from the candidate stop to the destination and the cost of walking of the passenger from the original origin to the candidate stop;

ranking each of the candidate sites based on the relevant feature data;

and obtaining at least one recommended boarding point based on the sequencing result.

2. The method of claim 1, wherein the second characterization data is associated with an estimated cost of walking;

the estimated walking cost is estimated based on the frequency of passengers getting on the vehicle from the departure point to the candidate station by taking the position within the preset range from the original departure point as the departure point in the past preset time, the estimated walking distance between the original departure point and the candidate station and the geometric distance between the original departure point and the candidate station.

3. The method of claim 1, wherein the ranking each of the candidate stations based on the relevant characteristics data comprises:

and respectively inputting the characteristic data of each candidate station into a trained sequencing model, and receiving the sequencing result of each candidate station output by the sequencing model.

4. The method of claim 1, wherein the method of recalling at least one candidate site based on the original origin comprises at least one of:

recalling all the sites within a preset distance range from the original starting point as the candidate sites; or

And taking N sites with the nearest distance to the original starting point as the candidate sites, wherein N is a positive integer.

5. A pick-up point recommendation system, comprising:

a first acquisition unit configured to acquire an original starting point and a destination;

a recall unit for recalling at least one candidate site based on the original starting point;

a processing unit, configured to calculate relevant feature data of each candidate station, where the relevant feature data of the candidate station includes at least one of:

the first sequencing unit is used for sequencing each candidate station based on the relevant characteristic data; and

and the first recommending unit is used for obtaining at least one recommended boarding point based on the sequencing result.

6. The system of claim 5, wherein the second characterization data is associated with an estimated cost of walking;

the estimated walking cost is estimated based on the frequency of the historical passengers taking the position within the preset range from the original starting point as the starting point within the past preset time to get on the vehicle from the starting point to the candidate station, the estimated walking distance between the original starting point and the candidate station and the geometric distance between the original starting point and the candidate station.

7. The system of claim 5, wherein the first sequencing unit is to:

8. The system of claim 5, wherein the recall unit is configured to:

9. A pick-up point recommendation device, the device comprising at least one processor and at least one memory;

the at least one memory is for storing computer instructions;

the at least one processor is configured to execute at least some of the computer instructions to implement the operations of any of claims 1 to 4.

10. A computer-readable storage medium storing computer instructions which, when executed by a processor, perform operations according to any one of claims 1 to 4.

11. A pick-up point recommendation method implemented by at least one processor, the method comprising:

acquiring an original starting point and a destination of a passenger;

acquiring at least one candidate station related to the original starting point and a ranking result thereof, wherein the ranking result is obtained based on the related feature data of each candidate station, and the related feature data of the candidate station comprises at least one of the following:

and recommending at least one recommended boarding point to the passenger based on the sequencing result.

12. The method of claim 11, wherein the obtaining at least one candidate station related to the original starting point and the ranking thereof comprises:

sending the original starting point to a server;

and receiving at least one candidate site returned by the server side and a sequencing result thereof.

13. A pick-up point recommendation system, comprising:

a second acquisition unit for acquiring an original starting point and a destination of the passenger;

a third obtaining unit, configured to obtain at least one candidate station related to the original starting point and a ranking result thereof, where the ranking result is obtained based on relevant feature data of each candidate station, and the relevant feature data of the candidate station includes at least one of the following:

And the second recommending unit is used for recommending at least one recommended boarding point to the passenger based on the sorting result.

14. The system of claim 13, wherein the third obtaining unit is further configured to:

sending the original starting point to a server; and

15. A pick-up point recommendation device, the device comprising at least one processor and at least one memory;

the at least one memory is for storing computer instructions;

the at least one processor is configured to execute at least some of the computer instructions to implement the operations of claim 11 or 12.

16. A computer-readable storage medium, characterized in that the storage medium stores computer instructions, which when executed by a processor, implement the operations of claim 11 or 12.