A method, system, device and storage medium for recommending boarding points

Abstract

The embodiments of the present application disclose a method, system, device and storage medium for recommending a boarding point. The method includes: obtaining the original starting point of the user; determining whether the original starting point is a parent point POI, and when the original starting point is a parent point POI, recalling at least one child point POI of the parent point POI; obtaining corresponding candidate boarding points based on the parent point POI and all the recalled child point POIs, merging the candidate boarding points of the parent point POI and the candidate boarding points of the child point POI to obtain a candidate boarding point set; calculating the relevant scores of each candidate boarding point in the candidate boarding point set and sorting each candidate boarding point based on the relevant scores; and obtaining at least one recommended boarding point based on the sorting results. The present application can improve the recommended candidate set of POIs with parent-child relationship attributes by using the child point association point library of POI as a supplementary recall, so that the recommended boarding points are more accurate and stable, and the user experience is improved.

Description

Technical Field

[0001] The present application relates to the field of transportation, and in particular to a method, system, device and storage medium for recommending a boarding point. Background Art

[0002] With the rapid development of online taxi services and the popular use of mobile phones, more and more people are using online taxi services on their mobile phones, and the requirements for location recommendation technology are getting higher and higher. When recommending boarding points in a planar POI scenario, the candidate boarding points of the parent POI and the child POI of the POI scenario are usually recalled separately, so that when searching for the parent POI or the child POI, the recommended points presented by the two are not related. The existence of this problem will affect the accuracy of location recommendation, reduce user location perception and travel efficiency. Therefore, it is necessary to propose an application of boarding point recommendation combined with the POI parent-child relationship in planar POI scenarios, so that the recommended boarding points are more accurate and stable, and the user experience is improved. Summary of the invention

[0003] The first aspect of the present application provides a method for recommending a boarding point. The method includes: obtaining the original starting point of the user; determining whether the original starting point is a parent point POI, and when the original starting point is a parent point POI, recalling at least one child point POI of the parent point POI; obtaining corresponding candidate boarding points based on the parent point POI and all the recalled child point POIs, respectively, merging the candidate boarding points of the parent point POI and the candidate boarding points of the child point POI to obtain a candidate boarding point set; calculating the relevant scores of each candidate boarding point in the candidate boarding point set and sorting each candidate boarding point based on the relevant scores; and obtaining at least one recommended boarding point based on the sorting result.

[0004] In some embodiments, the relevant score of the candidate boarding point is calculated based on at least one of the following feature data: first feature data, the first feature data can reflect the distance characteristics of the candidate boarding point from the original starting point; second feature data, the second feature data can reflect the distance characteristics of the candidate boarding point from the user's current location; third feature data, the third feature data can reflect the first attribute characteristics of the parent point POI or child point POI that recalls the candidate boarding point, and the first attribute characteristics at least include: the frequency of the parent point POI or child point POI as a boarding point in the past period of time; and fourth feature data, the fourth feature data can reflect the second attribute characteristics of the candidate boarding point, and the second attribute characteristics at least include: the frequency of the candidate boarding point as a boarding point in the past period of time.

[0005] In some embodiments, the method for sorting each of the candidate boarding points based on the relevant scores includes: obtaining a sorting model, which is a machine learning model; inputting the feature data of each of the candidate boarding points into the sorting model respectively, and outputting the sorting results of each of the candidate boarding points through the sorting model.

[0006] In some embodiments, the ranking model includes at least one of the following models: Lambda rank model, Lambda Mart model, CNN model and LTR model.

[0007] In some embodiments, the method for obtaining the corresponding candidate boarding point based on the parent point POI or the child point POI includes at least one of the following: recalling all boarding points within a first distance range from the parent point POI or the child point POI as the candidate boarding points; or taking the N boarding points closest to the parent point POI or the child point POI as the candidate boarding points, where N is a positive integer.

[0008] In some embodiments, the method for recalling at least one child POI of the parent POI includes: recalling the child POI based on parent-child relationship attributes; the method for determining the parent-child relationship attributes at least includes: the parent POI and the child POI have a semantic inclusion relationship and / or the parent POI and the child POI have an inclusion relationship in map range.

[0009] In some embodiments, the relevant score of the candidate boarding point is obtained based on the frequency of the candidate boarding point being used as a boarding point within a period of time and the user's current location.

[0010] A second aspect of the present application provides a boarding point recommendation system, comprising: a first acquisition unit, used to acquire an original starting point of a user; a first judgment unit, used to judge whether the original starting point is a parent point POI, and when the original starting point is a parent point POI, recall at least one child point POI of the parent point POI; a first processing unit, used to obtain corresponding candidate boarding points based on the parent point POI and all the recalled child point POIs, respectively, and merge the candidate boarding points of the parent point POI and the candidate boarding points of the child point POIs to obtain a candidate boarding point set; a first sorting unit, used to calculate the relevant score of each candidate boarding point in the candidate boarding point set and sort each candidate boarding point based on the relevant score; and a first recommendation unit, used to obtain at least one recommended boarding point based on the sorting result.

[0011] In some embodiments, the relevant score of the candidate boarding point is calculated based on at least one of the following feature data: first feature data, the first feature data can reflect the distance characteristics of the candidate boarding point from the original starting point; second feature data, the second feature data can reflect the distance characteristics of the candidate boarding point from the user's current location; third feature data, the third feature data can reflect the first attribute characteristics of the parent point POI or child point POI that recalls the candidate boarding point, and the first attribute characteristics at least include: the frequency of the parent point POI or child point POI as a boarding point in the past period of time; and fourth feature data, the fourth feature data can reflect the second attribute characteristics of the candidate boarding point, and the second attribute characteristics at least include: the frequency of the candidate boarding point as a boarding point in the past period of time.

[0012] In some embodiments, the first sorting unit is used to: obtain a sorting model, which is a machine learning model; input feature data of each candidate boarding point into the sorting model respectively, and output a sorting result of each candidate boarding point through the sorting model.

[0013] In some embodiments, the ranking model includes at least one of the following models: Lambda rank model, Lambda Mart model, CNN model and LTR model.

[0014] In some embodiments, the method by which the first processing unit obtains the corresponding candidate boarding point based on the parent point POI or the child point POI includes at least one of the following: recalling all boarding points within a first distance range from the parent point POI or the child point POI as the candidate boarding points; or taking the N boarding points closest to the parent point POI or the child point POI as the candidate boarding points, where N is a positive integer.

[0015] In some embodiments, the method for the first judgment unit to recall at least one child POI of the parent point POI includes: recalling the child POI based on the parent-child relationship attribute; the method for determining the parent-child relationship attribute at least includes: the parent point POI and the child point POI have a semantic inclusion relationship and / or the parent point POI and the child point POI have an inclusion relationship in the map range.

[0016] In some embodiments, the relevant score of the candidate boarding point is obtained based on the frequency of the candidate boarding point being used as a boarding point within a period of time and the user's current location.

[0017] The third aspect of the present application provides a boarding point recommendation device, comprising: at least one processor and at least one memory; the at least one memory is used to store computer instructions; the at least one processor is used to execute at least part of the computer instructions to implement the operations described in some embodiments of the present application.

[0018] A fourth aspect of the present application provides a computer-readable storage medium, which stores computer instructions. When the computer instructions are executed by a processor, the operations described in some embodiments of the present application are implemented.

[0019] The fifth aspect of the present application provides a method for recommending a boarding point, including: obtaining the original starting point of the user; determining whether the original starting point is a parent point POI; obtaining at least one candidate boarding point based on the determination result; obtaining a ranking result of each of the candidate boarding points; and recommending at least one recommended boarding point to the user based on the ranking result.

[0020] In some embodiments, obtaining the ranking results of each candidate boarding point includes: sending the original starting point and the judgment result of whether the original starting point is the parent point POI to the server; receiving at least one candidate boarding point and its ranking result returned by the server.

[0021] The sixth aspect of the present application provides a boarding point recommendation system, including: a second acquisition unit, used to acquire the user's original starting point; a second judgment unit, used to judge whether the original starting point is a parent point POI; a second processing unit, used to obtain at least one candidate boarding point based on the judgment result; a second sorting unit, used to obtain the sorting result of each of the candidate boarding points; a second recommendation unit, used to recommend at least one recommended boarding point to the user based on the sorting result.

[0022] In some embodiments, the second processing unit further includes: a sending unit for sending the original starting point and a determination result of whether the original starting point is a parent point POI to the server; and a receiving unit for receiving at least one candidate boarding point returned by the server.

[0023] The seventh aspect of the present application provides a boarding point recommendation device, comprising at least one processor and at least one memory; the at least one memory is used to store computer instructions; the at least one processor is used to execute at least part of the computer instructions to implement the operations described in some embodiments of the present application.

[0024] An eighth aspect of the present application provides a computer-readable storage medium, which stores computer instructions. When the computer instructions are executed by a processor, the operations described in some embodiments of the present application are implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] 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. Among them:

[0026] Figure 1 is a schematic diagram of an application scenario of a boarding point recommendation system according to some embodiments of the present application;

[0027] Figure 2 is a schematic block diagram of a boarding point recommendation system according to some embodiments of the present application;

[0028] Figure 3 is an exemplary flow chart of a method for recommending a boarding point according to some embodiments of the present application;

[0029] Figure 4 is a schematic block diagram of a boarding point recommendation system according to other embodiments of the present application;

[0030] Figure 5 It is an exemplary flow chart of a method for recommending a boarding point according to other embodiments of the present application. DETAILED DESCRIPTION

[0031] 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 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.

[0032] 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 "include" and "comprise" 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.

[0033] Although the present application makes various references to certain modules in the system according to embodiments of the present application, any number of different modules may be used and run on the vehicle client and / or server. The modules are illustrative only, and different aspects of the system and method may use different modules.

[0034] 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, various steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or a certain step or several steps of operations may be removed from these processes.

[0035] The embodiments of the present application can be applied to different transportation service systems, including but not limited to one or a combination of land, rivers, lakes, oceans, aviation, etc. For example, rickshaws, means of transportation, cars (e.g., small cars, buses, large transport vehicles, etc.), rail transit (e.g., trains, motor vehicles, high-speed railways, subways, etc.), ships, airplanes, aircraft, hot air balloons, unmanned vehicles, express delivery, etc., which use management and / or distribution transportation systems. 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.

[0036] Figure 1 1 is a schematic diagram of an application scenario of a pickup point recommendation system according to some embodiments of the present application. The pickup point recommendation system 100 can determine the pickup point and recommend it to the passenger, guiding the passenger to choose a suitable pickup point. The pickup point recommendation system 100 can be an online service platform for Internet services. For example, the pickup point recommendation system 100 can be an online transportation service platform for transportation services. In some embodiments, the pickup point recommendation system 100 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. In some embodiments, the pickup point recommendation system 100 can also be applied to services such as chauffeur services, express delivery, and take-out. The pickup point recommendation system 100 can 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.

[0037] In some embodiments, the server 110 can be used to process relevant information and / or data for determining the recommended boarding point. The server 110 can be an independent server or a server group. The server group can be centralized or distributed (e.g., the server 110 can be a distribution system). In some embodiments, the server 110 can be regional or remote. For example, the server 110 can access information and / or data stored in the user terminal 130 and the storage device 140 through the network 120. In some embodiments, the server 110 can be directly connected to the user terminal 130 and the storage device 140 to access the information and / or data stored therein. In some embodiments, the server 110 can 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, etc.

[0038] 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 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 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.

[0039] The network 120 may facilitate the exchange of data and / or information. In some embodiments, one or more components in the pickup point recommendation system 100 (e.g., server 110, user terminal 130, storage device 140) may send data and / or information to other components in the pickup point recommendation system 100 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 pickup point recommendation system 100 can be connected to the network 120 to exchange data and / or information.

[0040] In some embodiments, the user may obtain the recommended boarding point through the user terminal 130. In some embodiments, the user terminal 130 may include one of a mobile device 130-1, a tablet computer 130-2, a laptop computer 130-3, a motor vehicle built-in device 130-4, etc., or any combination thereof. In some embodiments, the mobile device 130-1 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 lighting device, a control device for smart appliances, a smart monitoring device, etc., or any combination thereof. 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.

[0041] The storage device 140 may store data and / or instructions. In some embodiments, the storage device 140 may store data obtained from the user terminal 130. In some embodiments, the storage device 140 may store information and / or instructions for execution or use by the server 110 to perform the exemplary methods described in this application. In some embodiments, the storage device 140 may include a large-capacity memory, a removable memory, a volatile read-write memory (e.g., a random access memory RAM), a read-only memory (ROM), etc., 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, etc., or any combination thereof.

[0042] In some embodiments, the storage device 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 pickup point recommendation system 100 may access data or instructions stored in the storage device 140 through the network 120. In some embodiments, the storage device 140 may be directly connected to or communicate with one or more components of the pickup point recommendation system 100 (e.g., the server 110, the user terminal 130). In some embodiments, the storage device 140 may be part of the server 110.

[0043] Figure 2 is a schematic block diagram of a boarding point recommendation system according to some embodiments of the present application. Figure 2 As shown, in some embodiments, the boarding point recommendation system 200 may include: a first acquisition unit 201, used to acquire the original starting point of the user; a first judgment unit 203, used to judge whether the original starting point is a parent point POI, and when the original starting point is a parent point POI, recall at least one child point POI of the parent point POI. The parent point POI may refer to one or more sheet-like areas, such as Beijing University of Posts and Telecommunications. The child point POI may refer to one or more specific points, such as the East Gate and West Gate of Beijing University of Posts and Telecommunications; a first processing unit 205, used to obtain corresponding candidate boarding points based on the parent point POI and all the recalled child point POIs, and merge the candidate boarding points of the parent point POI and the candidate boarding points of the child point POI to obtain a candidate boarding point set; a first sorting unit 207, used to calculate the relevant scores of each of the candidate boarding points in the candidate boarding point set and sort each of the candidate boarding points based on the relevant scores; and a first recommendation unit 209, used to obtain at least one recommended boarding point based on the sorting result.

[0044] In some embodiments, the relevant score of the candidate boarding point is calculated based on at least one of the following feature data: first feature data, the first feature data can reflect the distance characteristics of the candidate boarding point from the original starting point; second feature data, the second feature data can reflect the distance characteristics of the candidate boarding point from the user's current location; third feature data, the third feature data can reflect the first attribute characteristics of the parent point POI or child point POI that recalls the candidate boarding point, and the first attribute characteristics at least include: the frequency of the parent point POI or child point POI as a boarding point in the past period of time; and fourth feature data, the fourth feature data can reflect the second attribute characteristics of the candidate boarding point, and the second attribute characteristics at least include: the frequency of the candidate boarding point as a boarding point in the past period of time.

[0045] In some embodiments, the first sorting unit 207 can also be used to: obtain a sorting model, which is a machine learning model; input the feature data of each candidate boarding point into the sorting model respectively, and output the sorting results of each candidate boarding point through the sorting model.

[0046] In some embodiments, the ranking model includes at least one of the following models: Lambda rank model, Lambda Mart model, CNN model and LTR model.

[0047] In some embodiments, the method by which the first processing unit 205 obtains the corresponding candidate boarding point based on the parent point POI or the child point POI includes at least one of the following: recalling all boarding points within a first distance range from the parent point POI or the child point POI as the candidate boarding points; or taking the N boarding points closest to the parent point POI or the child point POI as the candidate boarding points, where N is a positive integer.

[0048] In some embodiments, the method for the first judgment unit 203 to recall at least one child POI of the parent POI may include: recalling the child POI based on the parent-child relationship attribute. The method for determining the parent-child relationship attribute at least includes: the parent POI and the child POI have a semantic inclusion relationship and / or the parent POI and the child POI have a map range inclusion relationship.

[0049] In some embodiments, the relevant score of the candidate boarding point can be obtained based on the frequency of the candidate boarding point being used as a boarding point within a period of time and the user's current location.

[0050] It should be understood that Figure 2The system and its units shown can be implemented in various ways. For example, in some embodiments, the system and its units can be implemented by hardware, software or a combination of software and hardware. Among them, the hardware part can be implemented by 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, for example, 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 units 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).

[0051] It should be noted that the above description of the system and its units is only for convenience of description and does not limit the present application to the scope of the embodiments. It is understandable that, after understanding the principle of the system, those skilled in the art may arbitrarily combine the modules or form a subsystem to connect with other modules without deviating from the principle. For example, in some embodiments, Figure 2 The first acquisition unit 201, the first judgment unit 203, the first processing unit 205, the first sorting unit 207, and the first recommendation unit 209 disclosed in the system may be different units in a system, or one unit may realize the functions of two or more of the above units. For another example, each unit may share a storage device 140, or each unit may have its own storage device 140. Such variations are all within the protection scope of this application.

[0052] Figure 3 It is an exemplary flow chart shown according to some embodiments of the present application, used to illustrate the implementation steps of the boarding point recommendation method.

[0053] In some embodiments of the present application, a method for recommending a boarding point is provided. The method may be executed by the server 110. The method 300 may include the following steps:

[0054] Step 301 : Acquire the original starting point of the user; in some embodiments, this step may be performed by the first acquisition unit 201 in the system 200 .

[0055] In some embodiments, the original starting point may be a query word input by the user, or may be the current location of the user obtained through positioning technology. For example, when the user inputs a query word in the user terminal 130, the user terminal 130 may send the query word to the server 110 through the network 120, and the processing device 112 may receive the query word and process it.

[0056] In some embodiments, the way in which a user inputs a query word may include, but is not limited to, any combination of one or more of typing input, handwriting input, selection input, voice input, scanning input, etc. Specifically, typing input may include English input, Chinese input, etc., depending on the language. Selection input may include selecting a query word from a selection list, etc. Scanning input may include scanning a barcode input, scanning a QR code input, scanning text input, scanning an image input, etc. For example, the query word may be Chinese characters directly handwritten by the user. For another example, the query word may be text or letters recognized based on the user's scanned image input. For another example, the query word may be text or letters recognized based on the voice input of the user.

[0057] In some embodiments, the current location of the user obtained by the user terminal 130 through the positioning technology may include longitude and latitude information, and then the original starting point of the user may be determined according to the longitude and latitude information. In some embodiments, the original starting point may include the name of the departure place. 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, etc. or any combination thereof.

[0058] In some embodiments, the user may select the original departure point based on the record list. For example, the user terminal 130 may provide the user with a record list of original departure points, and the user may click one of the record lists to input the original departure point. In some embodiments, the record list may be a list of location information obtained based on the historical input information of the current user.

[0059] In some embodiments, the user can input the original starting point based on the map. For example, the user can drag the map in the user terminal 130 to make a pin stick to the selected location to input the original starting point.

[0060] Step 303 , determining whether the original starting point is a parent POI, and when the original starting point is a parent POI, recalling at least one child POI of the parent POI; in some embodiments, this step may be performed by the first determining unit 203 in the system 200 .

[0061] In some embodiments, the parent point POI may refer to one or more sheet-like areas, such as Beijing University of Posts and Telecommunications. The child point POI may refer to one or more specific points, such as the east gate and west gate of Beijing University of Posts and Telecommunications. The first judgment unit 203 may determine whether the original starting point is a parent point POI or a child point POI by judging the area corresponding to the original starting point on the map. For example, if the user's original starting point is "Beijing University of Posts and Telecommunications", and "Beijing University of Posts and Telecommunications" corresponds to a sheet-like area on the map, the first judgment unit 203 may determine that "Beijing University of Posts and Telecommunications" is the parent point POI.

[0062] In some embodiments, the parent point POI and the child point POI may have a parent-child relationship attribute. The first judgment unit 203 may recall the child point POI based on the parent-child relationship attribute. The parent-child relationship attribute may be an inclusion relationship between the parent point POI and the child point POI, specifically, the parent point POI includes the child point POI. A parent point POI may have one or more child point POIs with which it has a parent-child relationship attribute.

[0063] In some embodiments, the first judgment unit 203 may determine the parent-child relationship attribute between the parent point POI and the child point POI based on the existence of a semantic inclusion relationship between the parent point POI and the child point POI. In some embodiments, the existence of a semantic inclusion relationship between the parent point POI and the child point POI may mean that the parent point POI and the child point POI are semantically in a whole-part relationship. Specifically, the child point POI may be a part of the parent point POI semantically. For example, "East Gate of Beijing University of Posts and Telecommunications" is semantically a part of "Beijing University of Posts and Telecommunications", and "Beijing University of Posts and Telecommunications" and "East Gate of Beijing University of Posts and Telecommunications" have a parent-child relationship attribute.

[0064] In some embodiments, the first judgment unit 203 may also determine the parent-child relationship attribute between the parent POI and the child POI based on the existence of a containment relationship between the parent POI and the child POI on the map range. In some embodiments, the existence of a containment relationship between the parent POI and the child POI on the map range may mean that the position of the child POI on the map falls within the area of ​​the parent POI on the map. For example, the position point of "East Gate of Beijing University of Posts and Telecommunications" on the map is within the area of ​​"Beijing University of Posts and Telecommunications" on the map, and "Beijing University of Posts and Telecommunications" and "East Gate of Beijing University of Posts and Telecommunications" have a parent-child relationship attribute.

[0065] In some embodiments, the first judgment unit 203 may also determine one or more child POIs of the parent POI based on the parent-child relationship attributes between the parent POI and the child POI. In some embodiments, when the original starting point is the parent POI, the first judgment unit 203 may recall at least one child POI of the parent POI. For example, when the user's original starting point is "Beijing University of Posts and Telecommunications", the first judgment unit 203 may determine that "Beijing University of Posts and Telecommunications" is the parent POI, and may recall its child POI "East Gate of Beijing University of Posts and Telecommunications".

[0066] Step 305: obtain corresponding candidate boarding points based on the parent point POI and all the recalled child point POIs, and merge the candidate boarding points of the parent point POI and the candidate boarding points of the child point POI to obtain a candidate boarding point set; in some embodiments, this step can be performed by the first processing unit 205 in the system 200.

[0067] In some embodiments, the method for obtaining the corresponding candidate boarding point based on the parent POI or the child POI may include recalling all boarding points within a first distance range from the parent POI or the child POI as the candidate boarding points. In some embodiments, the method for obtaining the corresponding candidate boarding point based on the parent POI or the child POI may also include taking the N boarding points closest to the parent POI or the child POI as the candidate boarding points, where N is a positive integer.

[0068] In some embodiments, the first processing unit 205 may recall the candidate boarding point set A of the parent point POI based on the parent point POI. In some embodiments, the first processing unit 205 may obtain the candidate boarding point set A near the parent point POI based on the historical order behavior data of the parent point POI input by the user and the basic point library. In some embodiments, the basic point library may be a point library in a map database including Google Maps, Amap, Baidu Maps, etc. In some embodiments, the first processing unit 205 may also recall the candidate boarding point set A based on the first distance from the parent point POI, and the candidate boarding point set A includes at least one candidate boarding point. For example, all boarding points within a range of 50m from the parent point POI may be recalled as the candidate boarding point set A. In some embodiments, the first processing unit 205 may also use the N boarding points closest to the parent point POI as the candidate boarding point set A of the parent point POI, where N is a positive integer. For example, the first processing unit 205 may recall the 10 boarding points closest to the parent point POI as the candidate boarding point set A.

[0069] In some embodiments, the first processing unit 205 may recall the candidate boarding point set B of all sub-point POIs based on at least one sub-point POI obtained in step 303. In some embodiments, the first processing unit 205 may obtain the candidate boarding point set B near the sub-point POI based on the historical order behavior data of the sub-point POI obtained and the basic point library. In some embodiments, the first processing unit 205 may also recall one or more candidate boarding point sets B based on the first distance from the sub-point POI. For example, all boarding points within 50m of the first sub-point POI may be recalled, and all boarding points within 50m of the second sub-point POI may be recalled, and so on, and the boarding points recalled from all sub-point POIs are used as the candidate boarding point set B. In some embodiments, the first processing unit 205 may also use the N boarding points closest to the obtained sub-point POI as its candidate boarding point set B, where N is a positive integer. For example, the first processing unit 205 may recall the five boarding points closest to the first sub-point POI, recall the five boarding points closest to the second sub-point POI, and so on, and use the boarding points recalled from all sub-point POIs as the candidate boarding point set B.

[0070] In some embodiments, the first processing unit 205 may merge the candidate boarding point set A and the candidate boarding point set B to obtain the candidate boarding point set. In some embodiments, the candidate boarding point set A and the candidate boarding point set B may be merged by taking the intersection of the two sets, that is, eliminating duplicate candidate boarding points.

[0071] Step 307 , calculating the correlation score of each candidate boarding point in the candidate boarding point set and sorting each candidate boarding point based on the correlation score; in some embodiments, this step can be performed by the first sorting unit 207 in the system 200 .

[0072] In some embodiments, the relevant scores of the candidate boarding points can be calculated from at least one of the following relevant feature data: first feature data, second feature data, third feature data, and fourth feature data.

[0073] In some embodiments, the first feature data may be data that can reflect the distance characteristics from the candidate boarding point to the original starting point. In some embodiments, the distance includes but is not limited to spherical distance or straight-line distance. The spherical distance may be the length of the shortest line between two points on a sphere, that is, the length of a minor arc of a great circle passing through the two points between the two points. In some embodiments, the larger the first feature data, the more the candidate boarding point deviates from the original starting point. The smaller the first feature data, the less the candidate boarding point deviates from the original starting point.

[0074] In some embodiments, the second characteristic data may be data that can reflect the distance characteristics from the candidate boarding point to the user's current location. In some embodiments, the user's current location may be a location obtained in real time by a positioning system, which may be different from the original starting point when the user places an order due to user movement and other reasons. The larger the second characteristic data, the higher the walking cost for the user to walk from the current location to the candidate boarding point. The larger the second characteristic data, the smaller the walking cost for the user to walk from the current location to the candidate boarding point.

[0075] In some embodiments, the third data feature may be a data feature that can reflect the first attribute feature of the parent POI or child POI that recalls the candidate boarding point. In some embodiments, the first attribute feature at least includes: the historical heat of the parent POI or child POI, that is, the frequency of the parent POI or child POI as a boarding point in the past period of time. In some embodiments, the frequency of the parent POI or child POI as a boarding point in the past period of time can be obtained from the historical orders in the past period of time. In some embodiments, the first attribute feature may also include: the number of candidate boarding points recalled by the parent POI or child POI, the number of associations between the parent POI or child POI and the candidate boarding point in history, etc. In some embodiments, the more the number of candidate boarding points recalled by the parent POI or child POI, the more the number of candidate boarding points participating in the sorting. In some embodiments, the more the number of associations between the parent POI or child POI and the candidate boarding point in history, the higher the heat weight of the candidate boarding point, and the higher the score of the candidate boarding point.

[0076] In some embodiments, the fourth data feature may be a data feature that can reflect the second attribute feature of the candidate boarding point. In some embodiments, the second attribute feature includes at least: the historical popularity of the candidate boarding point, that is, the frequency of the candidate boarding point as a boarding point in the past period of time. In some embodiments, the frequency of the candidate boarding point as a boarding point in the past period of time can be obtained from statistics of historical orders in the past period of time. In some embodiments, the second attribute feature may also include: the global popularity, local popularity, etc. of the candidate boarding point. In some embodiments, the global popularity may be the number of orders in which historical passengers use the candidate boarding point as the actual boarding point in historical orders in the past period of time. In some embodiments, the local popularity may be the number of orders in which historical passengers depart from the original departure point and arrive at the candidate boarding point in historical orders in the past period of time.

[0077] In some embodiments, the method for ranking each of the candidate boarding points based on the correlation score includes: obtaining a ranking model, wherein the ranking model is a machine learning model. For example, trained ranking model parameters can be obtained from the storage device 140 to obtain the ranking model. The feature data of each of the candidate boarding points is respectively input into the ranking model, and the ranking results of each of the candidate boarding points are output through the ranking model.

[0078] In some embodiments, after the user initiates a ride order at the user terminal 130, the first processing unit 205 can determine a set of candidate boarding points based on the original starting point of the order information. The first sorting unit 207 can calculate the above-mentioned relevant feature data of each candidate boarding point in the candidate boarding point set, and input the relevant feature data of the candidate boarding point set into the trained sorting model, and output the sorting result using the sorting model. In some embodiments, the sorting model may include a Lambda rank model, a Lambda Mart model, a CNN model, an LTR model, etc. In some embodiments, the sorting result may be a recommended boarding point and its score, for example, "boarding point A, 90 points", "boarding point B, 80 points"... In some embodiments, the sorting result may also be the TOP N boarding points arranged in descending order of score values.

[0079] In some embodiments, the Lambda rank model is an empirical algorithm that directly defines the gradient of the loss function, namely the Lambda gradient. In some embodiments, the Lambda Mart model is a combination of Lambda gradient and MART, which is suitable for sorting scenarios, differentiable loss functions, incremental learning, combined features, feature selection, etc. In some embodiments, a CNN (convolutional neural network) model can also be used for sorting. The CNN model is essentially an input-to-output mapping that can learn a large number of mapping relationships between inputs and outputs without requiring any precise mathematical expressions between inputs and outputs. In some embodiments, an LTR (Learning to rank) model can also be used for sorting. The LTR model is a supervised learning sorting method. Among them, the steps of the sorting method may include training data acquisition, feature extraction, model training, test data prediction, and effect evaluation.

[0080] In other embodiments, the sorting model can also be trained by the following steps: obtaining multiple historical orders; processing each of the multiple historical orders to obtain a training sample; using the multiple training samples to train the sorting model, thereby obtaining a trained sorting model. In some embodiments, the historical orders include historical original departure points and historical boarding points. Specifically, the processing process may include: recalling at least one candidate boarding point based on the historical original departure point; obtaining relevant feature data of each candidate boarding point as input data for the training sample; determining the mark of each candidate boarding point based on whether the distance between the candidate boarding point and the historical boarding point is less than a first threshold; combining the marks of each candidate boarding point to obtain a reference standard for the training sample.

[0081] In some embodiments, the model can also be optimized. The optimization process can be a process of adjusting the parameters of the sorting model. The process of adjusting the parameters of the sorting model can be based on the comparison of the output results of the sorting model with the labeled results. When the output sorting results deviate greatly from the labeled results, a certain penalty is given to the sorting model. When the output sorting results are highly consistent with the labeled results, a certain reward is given to the sorting model, thereby obtaining the final sorting model as a boarding point recommendation model. For example, candidate boarding point A is a negative sample and is marked as "0". After model training, the top five candidate boarding points in the sorting results include station A. At this time, it is necessary to give the sorting model a certain penalty and continue to train the sorting model to achieve the tuning effect. If the top five candidate boarding points in the model sorting results are all positive samples marked as "1", the sorting model training effect is better and can be put into use.

[0082] Step 309 , based on the sorting results, obtain at least one recommended boarding point; in some embodiments, this step can be performed by the first recommendation unit 209 in the system 200 .

[0083] In some embodiments, the first recommendation unit 209 may use the first N candidate boarding points in the sorting result as recommended boarding points, or may use the candidate boarding points with scores greater than a threshold as recommended boarding points, and so on.

[0084] In some embodiments, the obtained recommended boarding points may be presented in a list format on a display interface of the user terminal 130 .

[0085] It should be noted that the above description of the relevant process is only for example and explanation, and does not limit the scope of application of the present application. For those skilled in the art, various modifications and changes can be made to the process under the guidance of the present application. However, these modifications and changes are still within the scope of the present application.

[0086] In other embodiments of the present application, a device for recommending boarding points is provided, the device comprising at least one processor and at least one memory; the at least one memory is used to store computer instructions; the at least one processor is used to execute at least part of the computer instructions to implement the operations described above.

[0087] In some further embodiments of the present application, a computer-readable storage medium is provided, wherein the storage medium stores computer instructions, and when the computer instructions are executed by a processor, the operations described above are implemented.

[0088] Figure 4 is a schematic block diagram of a boarding point recommendation system according to some other embodiments of the present application. Figure 4 As shown, in some embodiments, the boarding point recommendation system 400 may include: a second acquisition unit 401, used to acquire the original starting point of the user. A second judgment unit 403, used to judge whether the original starting point is a parent point POI. A second processing unit 405, used to obtain at least one candidate boarding point based on the judgment result. A second sorting unit 407, used to obtain the sorting result of each of the candidate boarding points. A second recommendation unit 409, used to recommend at least one recommended boarding point to the user based on the sorting result.

[0089] In some embodiments, the second processing unit 405 further includes: a sending unit for sending the original starting point and a determination result of whether the original starting point is a parent point POI to the server, and a receiving unit for receiving at least one candidate boarding point returned by the server.

[0090] It should be noted that the above description of the system and its units is only for convenience of description and does not limit the present application to the scope of the embodiments. It is understandable that, after understanding the principle of the system, those skilled in the art may arbitrarily combine the units or form a subsystem to connect with other units without deviating from the principle. For example, in some embodiments, Figure 2 The second acquisition unit 401, the second judgment unit 403, the second processing unit 405, the second sorting unit 407, and the second recommendation unit 409 disclosed in the system may be different units in a system, or one unit may realize the functions of two or more of the above units. For another example, each unit may share a storage device 140, or each unit may have its own storage device 140. Such variations are all within the protection scope of this application.

[0091] Figure 5It is an exemplary flow chart according to some other embodiments of the present application, used to illustrate the implementation steps of the boarding point recommendation method. In some other embodiments of the present application, a boarding point recommendation method is provided, which can be executed by the user terminal 130, and the method 500 can include the following steps:

[0092] Step 501 : Acquire the original starting point of the user; in some embodiments, this step may be performed by the second acquisition unit 401 in the system 400 .

[0093] In some embodiments, the original starting point may be a query word input by the user, or may be the current location of the user obtained by positioning technology. In some embodiments, the way in which the user inputs the query word may include but is not limited to any combination of one or more of typing input, handwriting input, selection input, voice input, scanning input, etc. In some embodiments, the current location of the user obtained by the user terminal 130 through positioning technology may include longitude and latitude information, and then the original starting point of the user may be determined based on the longitude and latitude information. In some embodiments, the user can select the original starting point based on the record list. For example, the user terminal 130 can provide the user with a list of original starting point records, and the user can click on one of them in the record list to enter the original starting point. In some embodiments, the user can enter the original starting point based on a map. For example, the user can drag the map in the user terminal 130 to make a pin stick to the selected location and enter the original starting point.

[0094] Step 503 , determining whether the original starting point is a parent point POI; in some embodiments, this step may be performed by the second determining unit 403 in the system 400 .

[0095] In some embodiments, the parent point POI may refer to one or more sheet-like areas. The child point POI may refer to one or more specific points. The second judgment unit 403 may determine whether the original starting point is a parent point POI or a child point POI by judging the area corresponding to the original starting point on the map. For example, if the user's original starting point is "Beijing University of Posts and Telecommunications", "Beijing University of Posts and Telecommunications" corresponds to a sheet-like area on the map, the second judgment unit 403 may determine that "Beijing University of Posts and Telecommunications" is the parent point POI.

[0096] In some embodiments, the judgment result may be provided by the server. For example, the user terminal 130 sends the original starting point to the server, and receives the judgment result of whether the original starting point is the parent point POI returned by the server. In some embodiments, the judgment result may also be obtained by the processor of the user terminal 130. The specific process of obtaining the judgment result can be found in Figure 3 Related description.

[0097] Step 505 , obtaining at least one candidate boarding point based on the judgment result; in some embodiments, this step can be performed by the second processing unit 405 in the system 400 .

[0098] In some embodiments, the second processing unit 405 can obtain at least one candidate boarding point based on the judgment result in step 503. In some embodiments, the candidate boarding point can be provided by the server, or obtained by the processor of the user terminal 130. The candidate boarding point can be a candidate boarding point of a parent point POI, or a candidate boarding point of a child point POI. The method of obtaining at least one candidate boarding point can refer to the method of this specification. Figure 3 The relevant description of step 305 is similarly obtained and will not be repeated here.

[0099] Step 507 , obtaining the ranking results of each of the candidate boarding points; in some embodiments, this step may be performed by the second ranking unit 407 in the system 400 .

[0100] In some embodiments, obtaining the ranking results of each candidate boarding point may include: sending the original starting point and a judgment result of whether the original starting point is a parent point POI to the server, and receiving at least one candidate boarding point and its ranking result returned by the server.

[0101] In some embodiments, the candidate boarding points and their ranking results returned by the server may be provided by the server, or may be implemented by a processor of the user terminal 130. For details on how to obtain the ranking results, please refer to the specification. Figure 3 The relevant description of step 307 is similarly obtained and will not be repeated here.

[0102] Step 509 : Based on the sorting result, recommend at least one recommended boarding point to the passenger; in some embodiments, this step may be performed by the second recommendation unit 409 in the system 400 .

[0103] In some embodiments, the second recommendation unit 409 may use the first N candidate boarding points in the sorting results as recommended boarding points, for example, displaying the first 5 candidate boarding points in the sorting results on the display interface; in another embodiment, candidate boarding points with scores greater than a threshold may be used as recommended boarding points, and the threshold may be 80 points, 90 points, 95 points, etc.

[0104] In some embodiments, the arrangement, display, display position, etc. of the recommended boarding points on the display interface or any combination thereof may be adjusted to improve the user's perception of the recommended boarding points.

[0105] In some embodiments, the arrangement may include up-down arrangement and left-right arrangement. For example, when a user enters a query word in an input box of a user terminal, the ranking result output by the model is presented to the user in up-down arrangement. For example, based on the ranking result, the second recommendation unit 409 presents it to the user in left-right arrangement.

[0106] In some embodiments, the display mode may include thumbnail display and full display. In some embodiments, when the recommended boarding point information in the sorting result contains a length greater than the display box, the recommended boarding point may be presented to the user terminal in thumbnail display. For example, when the recommended boarding point information in the sorting result is long, only the first part of the recommended boarding point information may be displayed in the display box, and the part exceeding the display box may be omitted. In some embodiments, the full display may be presenting the sorting result to the user in its entirety. For example, when the recommended boarding point information in the sorting result is greater than the length of the display box, the font size may be adjusted to display it in its entirety.

[0107] In some embodiments, the display position may include below the input box, above the input box, and to the right of the input box. For example, after the user enters a query word in 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 enters a query word in the user terminal, the ranking result is presented to the user on the right side of the input box.

[0108] It should be noted that the above description of the relevant process is only for example and explanation, and does not limit the scope of application of the present application. For those skilled in the art, various modifications and changes can be made to the process under the guidance of the present application. However, these modifications and changes are still within the scope of the present application.

[0109] In other embodiments of the present application, a device for recommending boarding points is provided, the device comprising at least one processor and at least one memory; the at least one memory is used to store computer instructions; the at least one processor is used to execute at least part of the computer instructions to implement the operations described above.

[0110] In some further embodiments of the present application, a computer-readable storage medium is provided, wherein the storage medium stores computer instructions, and when the computer instructions are executed by a processor, the operations described above are implemented.

[0111] It should be noted that the above description is only for the convenience of description and does not limit the present application to the scope of the embodiments. It is understandable that, after understanding the principle of the present application, those skilled in the art can make various modifications and changes in form and details to the implementation of the above process without departing from this principle. However, these changes and modifications do not depart from the scope of the present application.

[0112] The beneficial effects that may be brought about by the embodiments of the present application include but are not limited to: (1) determining the recalled candidate boarding points by judging the parent-child relationship attributes of POIs, so that the candidate boarding points recalled by the parent point POI can include the candidate boarding points recalled by its child point POI, thereby improving the coverage rate of the candidate boarding points; (2) sorting the candidate boarding point set through a sorting model, making the recommended boarding points more accurate and stable, thereby improving the user experience.

[0113] 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.

[0114] The above content describes the present application and / or some other examples. According to the above content, the present application can also make different variations. The subject matter disclosed in the present application can be realized in different forms and examples, and the present application can be applied to a large number of applications. All applications, modifications and changes required for protection in the following claims belong to the scope of the present application.

[0115] 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 "one embodiment", "an embodiment", "an alternative embodiment", "another embodiment" or "another embodiment" mentioned twice or more in different positions in this specification do not necessarily refer to the same embodiment. In addition, some features, structures or characteristics in one or more embodiments of the present application can be appropriately combined.

[0116] Those skilled in the art will appreciate that the contents disclosed in this application may be subject to many variations and improvements. For example, the various system components described above are all implemented by hardware devices, but may also be implemented only by software solutions. For example: installing the system on an existing server. In addition, the provision of location information disclosed herein may be implemented by a firmware, a combination of firmware / software, a combination of firmware / hardware, or a combination of hardware / firmware / software.

[0117] All or part of the software may sometimes be communicated over a network, such as the Internet or other communications network. Such communications enable software to be loaded from one computer device or processor to another. For example, from a management server or host computer of a radiation therapy system to a hardware platform of a computer environment, or other computer environment implementing the system, or a system of similar functionality associated with providing information required to determine the parameters of the wheelchair target structure. Therefore, another medium capable of transmitting software elements may also be used as a physical connection between local devices, such as light waves, radio waves, electromagnetic waves, etc., transmitted through cables, optical cables or air. Physical media such as cables, wireless connections or optical cables and the like used to carry carriers may also be considered as media that carry software. As used herein, unless limited to tangible "storage" media, other terms referring to computer or machine "readable media" refer to media that participate in the process of executing any instructions by the processor.

[0118] The computer program coding required for the operation of each part of the present 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, for example, a local area network (LAN) or a wide area network (WAN), or connected to an external computer (for example, via the Internet), or in a cloud computing environment, or used as a service such as software as a service (SaaS).

[0119] 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.

[0120] 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.

[0121] In some embodiments, numbers describing attributes and quantities are used. It should be understood that such numbers used to describe 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.

[0122] Each patent, patent application, patent application disclosure, and other materials, such as articles, books, instructions, publications, documents, objects, 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.

[0123] 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, characterized in that: The method comprises: Get the user's original starting point; Determine whether the original starting point is a parent point POI, and when the original starting point is a parent point POI, recall at least one child point POI of the parent point POI; Based on the parent point POI and all the recalled child points POI, corresponding candidate boarding points are obtained respectively, and the candidate boarding points of the parent point POI and the candidate boarding points of the child point POI are combined to obtain a candidate boarding point set; Calculate the relevant scores of each of the candidate boarding points in the candidate boarding point set and sort each of the candidate boarding points based on the relevant scores; wherein the relevant scores of the candidate boarding points are calculated based on the following feature data: first feature data, where the first feature data can reflect the distance feature from the candidate boarding point to the original departure point; Second feature data, where the second feature data can reflect the distance feature from the candidate boarding point to the user's current location; The third feature data can reflect the first attribute feature of the parent point POI or the child point POI of the candidate boarding point, and the first attribute feature includes: The frequency of the parent POI or the child POI being used as a boarding point in the past period of time, the number of candidate boarding points recalled by the parent POI or the child POI, and the number of associations between the parent POI or the child POI and the candidate boarding points in history; and fourth feature data, the fourth feature data being able to reflect a second attribute feature of the candidate boarding point, the second attribute feature comprising: a frequency of the candidate boarding point being a boarding point in the past period of time, a global heat of the candidate boarding point, and a local heat of the candidate boarding point; The method for ranking each of the candidate boarding points based on the relevant scores includes: obtaining a ranking model, which is a machine learning model; inputting feature data of each of the candidate boarding points into the ranking model respectively, and outputting ranking results of each of the candidate boarding points through the ranking model; Based on the sorting result, at least one recommended boarding point is obtained.

2. The method according to claim 1, characterized in that The sorting model includes at least one of the following models: Lambda rank model, Lambda Mart model, CNN model and LTR model.

3. The method according to claim 1, characterized in that The method for obtaining the corresponding candidate boarding point based on the parent point POI or the child point POI includes at least one of the following: Recalling all the boarding points within a first distance range from the parent POI or the child POI as the candidate boarding points; or The N boarding points closest to the parent point POI or the child point POI are used as the candidate boarding points, where N is a positive integer.

4. The method according to claim 1, characterized in that: The method for recalling at least one child POI of the parent POI includes: Recalling the child point POI based on the parent-child relationship attribute; The method for determining the parent-child relationship attribute at least includes: the parent point POI and the child point POI have a semantic inclusion relationship and / or the parent point POI and the child point POI have a map range inclusion relationship.

5. The method according to claim 1, characterized in that The relevant score of the candidate boarding point is obtained based on the frequency of the candidate boarding point being used as a boarding point within a period of time and the current location of the user.

6. A boarding point recommendation system, characterized in that: include: A first acquisition unit, used to acquire the original starting point of the user; A first judgment unit, configured to judge whether the original starting point is a parent point POI, and when the original starting point is a parent point POI, recall at least one child point POI of the parent point POI; A first processing unit, configured to obtain corresponding candidate boarding points based on the parent point POI and all the recalled child point POIs, respectively, and merge the candidate boarding points of the parent point POI and the candidate boarding points of the child point POIs to obtain a candidate boarding point set; The first sorting unit is used to calculate the relevant scores of each candidate boarding point in the candidate boarding point set and sort each candidate boarding point based on the relevant scores; wherein the relevant scores of the candidate boarding points are calculated based on the following feature data: first feature data, where the first feature data can reflect the distance feature from the candidate boarding point to the original departure point; Second feature data, where the second feature data can reflect the distance feature from the candidate boarding point to the user's current location; The third feature data can reflect the first attribute feature of the parent point POI or the child point POI of the candidate boarding point, and the first attribute feature includes: The frequency of the parent POI or the child POI being used as a boarding point in the past period of time, the number of candidate boarding points recalled by the parent POI or the child POI, and the number of associations between the parent POI or the child POI and the candidate boarding points in history; and fourth feature data, the fourth feature data being able to reflect a second attribute feature of the candidate boarding point, the second attribute feature comprising: a frequency of the candidate boarding point being a boarding point in the past period of time, a global heat of the candidate boarding point, and a local heat of the candidate boarding point; The first sorting unit is further used to obtain a sorting model, which is a machine learning model; input the feature data of each candidate boarding point into the sorting model respectively, and output the sorting result of each candidate boarding point through the sorting model; and a first recommendation unit, configured to obtain at least one recommended boarding point based on the sorting result.

7. The system according to claim 6, characterized in that The sorting model includes at least one of the following models: Lambda rank model, Lambda Mart model, CNN model and LTR model.

8. The system according to claim 6, characterized in that The method for the first processing unit to obtain the corresponding candidate boarding point based on the parent point POI or the child point POI includes at least one of the following: Recalling all the boarding points within a first distance range from the parent POI or the child POI as the candidate boarding points; or The N boarding points closest to the parent point POI or the child point POI are used as the candidate boarding points, where N is a positive integer.

9. The system according to claim 6, characterized in that The method for the first judgment unit to recall at least one child POI of the parent POI includes: Recalling the child point POI based on the parent-child relationship attribute; The method for determining the parent-child relationship attribute at least includes: the parent point POI and the child point POI have a semantic inclusion relationship and / or the parent point POI and the child point POI have a map range inclusion relationship.

10. The system according to claim 6, characterized in that The relevant score of the candidate boarding point is obtained based on the frequency of the candidate boarding point being used as a boarding point within a period of time and the current location of the user.

11. A device for recommending boarding points, characterized in that: The apparatus comprises at least one processor and at least one memory; The at least one memory is used to store computer instructions; The at least one processor is configured to execute at least part of the computer instructions to implement the operations of the method as claimed in any one of claims 1 to 5.

12. A computer-readable storage medium, characterized in that: The storage medium stores computer instructions, which, when executed by a processor, implement the operations of the method as claimed in any one of claims 1 to 5.

Images