CN114579890B

CN114579890B - Method, device and equipment for recommending getting-on point name and storage medium

Info

Publication number: CN114579890B
Application number: CN202210446238.1A
Authority: CN
Inventors: 王国杰; 冀晨光; 朱桐; 靖宝
Original assignee: Alibaba China Co Ltd
Current assignee: Alibaba China Co Ltd
Priority date: 2022-04-26
Filing date: 2022-04-26
Publication date: 2022-07-29
Anticipated expiration: 2042-04-26
Also published as: CN114579890A

Abstract

The embodiment of the disclosure discloses a method, a device, equipment and a storage medium for recommending a boarding point name, wherein the method comprises the following steps: acquiring a plurality of candidate points of which the position relation with the vehicle-entering point meets a preset relation from the available map points; if the popularity of the candidate point meets a preset condition, determining the candidate point as a popularity candidate point, otherwise, determining the candidate point as a common candidate point; determining the recommendation scores of the known candidate points based on a known score algorithm, and determining the recommendation scores of the common candidate points based on a common score algorithm, wherein the recommendation scores of the known candidate points are all larger than the recommendation scores of the common candidate points; and determining the name of the boarding point according to the name of the candidate point with the highest recommended score. The technical scheme can improve the significance of the names of the boarding points, reduce the communication cost and the operation cost of drivers and passengers, make drivers and passengers smoother, and optimize the experience of drivers and passengers.

Description

Method, device and equipment for recommending getting-on point name and storage medium

Technical Field

The embodiment of the disclosure relates to the technical field of internet, in particular to a method, a device, equipment and a storage medium for recommending a boarding point name.

Background

With the rapid development of wireless communication technology and computer technology, various APPs (applications) running on smart terminals such as smart phones and tablet computers emerge like spring shoots after rain, and travel APPs are one of the APPs. The passenger inputs the starting place and the destination place through the passenger end of the travel APP installed on the intelligent terminal, the passenger end sends the travel order carrying the starting place and the destination place to the service side, and the server side sends the order to the driver end of the travel APP near the starting place so as to find the vehicle capable of carrying the travel of the passenger for the passenger.

At present, in order to facilitate quick on-line meeting of passengers and drivers, before calling a vehicle to pick up, the passengers usually select a boarding Point according to their own position, and a trip APP gives a name to the boarding Point through Point of Interest (POI) data or road network data near the position according to the current position of the user. However, the existing naming strategy considers a few factors, and often has the problems of wrong name recommendation of the boarding points, invisible naming, insignificant naming, naming by indoor POIs and the like, so that the driver and the passenger are difficult and time-consuming in communication, and even may fail, the order is cancelled, and the driver and the passenger experience is poor.

Disclosure of Invention

The embodiment of the disclosure provides a method, a device, equipment and a storage medium for recommending a boarding point name.

In a first aspect, a method for recommending a boarding point name is provided in an embodiment of the present disclosure.

Specifically, the method for recommending the boarding point name includes the following steps:

acquiring a plurality of candidate points of which the position relation with the vehicle-entering point meets a preset relation from the available map points;

if the unknown degree of the candidate point meets a preset condition, determining the candidate point as an unknown candidate point, otherwise, determining the candidate point as a common candidate point;

determining the recommendation scores of the known candidate points based on a known score algorithm, and determining the recommendation scores of the common candidate points based on a common score algorithm, wherein the recommendation scores of the known candidate points are all larger than the recommendation scores of the common candidate points;

and determining the name of the boarding point according to the name of the candidate point with the highest recommended score.

In one possible embodiment, the method further comprises:

filtering out unavailable map points in the map points according to a preset filtering rule to obtain the available map points; the filtering rules include at least one of:

filtering map points with searching frequency lower than a first preset frequency in a first preset time period;

filtering map points with names containing preset keywords;

filtering map points of a first preset category;

filtering map points which are located indoors and do not belong to a second preset category;

and filtering out map points with searching frequency lower than a second preset frequency in a preset grid area in a second preset time period, wherein the preset grid area comprises grid areas with the number of the map points exceeding the preset number.

In a possible implementation, the obtaining, from the available map points, a plurality of candidate points whose positional relationships with the boarding point satisfy a predetermined relationship includes:

obtaining an interest point POI with a distance between the interest point POI and a vehicle getting-on point within a first preset distance from the available map points as candidate points;

and obtaining an interest area AOI (automatic object identifier) with a distance between a target boundary and a vehicle-entering point within a second preset distance from available map points as candidate points, wherein the target boundary is the nearest boundary to the vehicle-entering point in the AOI.

In a possible implementation manner, the determining that the candidate point is a known candidate point if the degree of awareness of the candidate point satisfies a preset condition includes:

if the popularity degree of the candidate point meets a preset condition corresponding to a preset popularity level, determining the candidate point as the popularity candidate point of the preset popularity level;

the preset condition corresponding to the preset known level comprises the following steps: the type of the candidate point is a known type with a preset known level, the candidate point is a candidate point with a visible boarding point, the position of the candidate point, the position of the boarding point and/or the relative position relation between the candidate point and the boarding point meet the position condition corresponding to the preset known level, the distance between the candidate point and the boarding point is within the distance range corresponding to the preset known level, and the search frequency of the candidate point is within the preset frequency range corresponding to the preset known level within a third preset time period; and when the vehicle-loading point is positioned in the AOI, the density of the candidate point in the grid area with the preset size is less than or equal to a preset threshold value.

In one possible embodiment, the determining the recommendation score of the known candidate point based on a known score algorithm includes:

obtaining a recommendation score multiplying power of the known candidate points based on a corresponding relation between the preset known level and the recommendation score multiplying power, wherein the recommendation score multiplying power is used for limiting a scoring range of the known candidate points of the preset known level;

determining a spare recommendation score of the known candidate points based on known scoring parameters and corresponding parameter weights thereof, wherein the known scoring parameters comprise: the distance between the known candidate point and the vehicle-entering point, and the stability and the reliability of the known candidate point; the range of the spare recommendation score of the known candidate point is more than or equal to 0 and less than or equal to 1;

removing the known candidate points with the spare recommendation score less than or equal to 0.01;

and taking the product of the recommendation score multiplying power of the known candidate points and the spare recommendation scores of the rest known candidate points as the recommendation scores of the rest known candidate points.

In one possible embodiment, the method further comprises:

and if the known candidate point and the getting-on point are located in the same AOI, determining the recommended score multiplying power of the known candidate point as a preset maximum multiplying power.

In one possible embodiment, the determining the recommendation score of the common candidate point based on a common score algorithm includes:

obtaining a scoring range of the common candidate points based on the corresponding relation between the scene where the common candidate points are located and the scoring range;

determining a spare recommendation score of the common candidate point based on a common scoring parameter and a corresponding parameter weight thereof, wherein the common scoring parameter comprises: the distance between the common candidate point and the boarding point, the stability of the common candidate point, the reliability of the common candidate point, whether the common candidate point is a known type with a preset known level, whether the common candidate point is on street or not, and the search frequency in a fourth preset time period; the range of the spare recommendation score is more than or equal to 0 and less than or equal to 1;

and converting the standby recommendation score of the common candidate point into a recommendation score in the scoring range of the common candidate point.

In one possible embodiment, the method further comprises:

acquiring a road intersected with a target connecting line, wherein the target connecting line comprises a connecting line between the upper vehicle point and the candidate point;

and if two parallel roads with opposite driving directions exist in the intersected roads, determining that the relative position relationship between the upper vehicle point and the candidate point is a road crossing relationship.

In one possible embodiment, the method further comprises:

acquiring an orientation angle of the candidate point, wherein the orientation angle is an angle which is perpendicular to the AOI of the candidate point or outward of a building block boundary;

moving the candidate point along the direction of the orientation angle by a third preset distance to obtain an outward-pulling point of the candidate point;

if a building entity exists between the pull-out point and the boarding point, determining the candidate point as a candidate point invisible to the boarding point;

and if no building entity exists between the pull-out point and the boarding point, determining that the candidate point is a visible candidate point of the boarding point.

In a possible implementation manner, the determining the name of the boarding point according to the name of the candidate point with the highest recommendation score includes:

if the boarding point is on the same side as the candidate point with the highest recommended score and the distance between the boarding point and the candidate point with the highest recommended score is within a fourth preset distance, naming the name of the boarding point as the name of the candidate point with the highest recommended score; if the vehicle-entering point and the candidate point with the highest recommended score are on the same side and the distance exceeds the fourth preset distance, determining the name of the vehicle-entering point based on the name of the candidate point with the highest recommended score and the position of the vehicle-entering point at the candidate point with the highest recommended score; if the relative position relationship between the boarding point and the candidate point with the highest recommended score is a road-crossing relationship, naming the boarding point as the opposite of the candidate point with the highest recommended score;

and when the vehicle getting-on point and the candidate point with the highest recommended score are positioned in the same AOI, naming the vehicle getting-on point by using the name of the AOI, the name of the road where the vehicle getting-on point is positioned and the name of the candidate point with the highest recommended score.

In a second aspect, an apparatus for recommending a boarding point name is provided in the embodiments of the present disclosure.

Specifically, the boarding point name recommendation device includes:

the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is configured to acquire a plurality of candidate points which satisfy a preset relation with a boarding point in the position relation from available map points;

the first determining module is configured to determine the candidate point as a known candidate point if the known degree of the candidate point meets a preset condition, and otherwise, determine the candidate point as a common candidate point;

the scoring module is configured to determine the recommendation scores of the known candidate points based on a known score algorithm and determine the recommendation scores of the common candidate points based on a common score algorithm, wherein the recommendation scores of the known candidate points are all larger than the recommendation score of the common candidate points;

and the naming module is configured to determine the name of the boarding point according to the name of the candidate point with the highest recommended score.

In a possible embodiment, the apparatus further comprises:

the filtering module is configured to filter unavailable map points in the map points according to a preset filtering rule to obtain the available map points; the filtering rules include at least one of:

filtering map points with names containing preset keywords;

filtering map points of a first preset category;

In one possible implementation, the first obtaining module is configured to:

In one possible implementation, the first determining module is configured to:

the preset condition corresponding to the preset known level comprises the following steps: the type of the candidate point is a known type with a preset known level, the candidate point is a candidate point with a visible boarding point, the position of the candidate point, the position of the boarding point and/or the relative position relation between the candidate point and the boarding point meet the position condition corresponding to the preset known level, the distance between the candidate point and the boarding point is within the distance range corresponding to the preset known level, and the search frequency of the candidate point is within the preset frequency range corresponding to the preset known level within a third preset time period; when the vehicle-entering point is located inside the AOI, the density of the candidate points in the grid area with the preset size is smaller than or equal to a preset threshold value.

In one possible embodiment, the part of the scoring module that determines the recommendation score of the known candidate point based on a known score algorithm is configured to:

determining a spare recommendation score of the known candidate point based on a known scoring parameter and a corresponding parameter weight thereof, wherein the known scoring parameter comprises: the distance between the known candidate point and the vehicle-entering point, and the stability and the reliability of the known candidate point; the range of the spare recommendation score of the known candidate point is more than or equal to 0 and less than or equal to 1;

In one possible implementation, the scoring module is further configured to:

In one possible embodiment, the section of the scoring module that determines the recommendation score for the generic candidate point based on a generic score algorithm is configured to:

In a possible embodiment, the apparatus further comprises:

the second acquisition module is configured to acquire a road intersected with a target connecting line, wherein the target connecting line comprises a connecting line between the upper vehicle point and the candidate point;

and the second determining module is configured to determine that the relative position relationship between the upper vehicle point and the candidate point is a road crossing relationship if two parallel roads with opposite driving directions exist in the intersected roads.

In a possible embodiment, the apparatus further comprises:

a third obtaining module, configured to obtain an orientation angle of the candidate point, where the orientation angle is an angle that is perpendicular to an AOI where the candidate point is located or an angle that is outward from a floor boundary;

the pull-out module is configured to move the candidate point by a third preset distance along the direction of the orientation angle to obtain a pull-out point of the candidate point;

a third determination module configured to determine that the candidate point is a candidate point where a boarding point is invisible if a building entity exists between the pull-out point and the boarding point; and if no building entity exists between the pull-out point and the boarding point, determining that the candidate point is a visible candidate point of the boarding point.

In one possible implementation, the naming module is configured to:

In a third aspect, the disclosed embodiment provides an electronic device, including a memory for storing one or more computer instructions for supporting a pick-up point name recommendation apparatus to execute the above pick-up point name recommendation method, and a processor configured to execute the computer instructions stored in the memory. The pick-up point name recommending device can also comprise a communication interface, and the pick-up point name recommending device is used for communicating with other equipment or a communication network.

In a fourth aspect, the disclosed embodiments provide a computer-readable storage medium for storing computer instructions for a pick-up point name recommendation device, which includes computer instructions for executing the above pick-up point name recommendation method to the pick-up point name recommendation device.

In a fifth aspect, the present disclosure provides a computer program product, which includes a computer program/instructions, where the computer program/instructions, when executed by a processor, implement the steps in the above-mentioned boarding point name recommendation method.

The technical scheme provided by the embodiment of the disclosure can have the following beneficial effects:

according to the technical scheme, the candidate points can be divided into the known candidate points and the common candidate points based on the known degree of the candidate points near the boarding point, the recommendation score of the known candidate points is larger than that of the common candidate points when the candidate points are classified, and the name of the candidate point with the highest recommendation score is determined to be the name of the boarding point.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of embodiments of the disclosure.

Drawings

Other features, objects, and advantages of embodiments of the disclosure will become more apparent from the following detailed description of non-limiting embodiments when taken in conjunction with the accompanying drawings. The following is a description of the drawings.

Fig. 1 shows a flowchart of a pick-up point name recommendation method according to an embodiment of the present disclosure.

Fig. 2 shows a schematic view of a scene in which a boarding point is located according to an embodiment of the present disclosure.

Fig. 3 is a block diagram illustrating a structure of a pick-up point name recommending apparatus according to an embodiment of the present disclosure.

Fig. 4 shows a block diagram of an electronic device according to an embodiment of the present disclosure.

Fig. 5 is a schematic block diagram of a computer system suitable for implementing a pick-up point name recommendation method according to an embodiment of the present disclosure.

Detailed Description

Hereinafter, exemplary embodiments of the disclosed embodiments will be described in detail with reference to the accompanying drawings so that they can be easily implemented by those skilled in the art. Also, for the sake of clarity, parts not relevant to the description of the exemplary embodiments are omitted in the drawings.

In the disclosed embodiments, it is to be understood that terms such as "including" or "having," etc., are intended to indicate the presence of the disclosed features, numbers, steps, behaviors, components, parts, or combinations thereof, and are not intended to preclude the possibility that one or more other features, numbers, steps, behaviors, components, parts, or combinations thereof may be present or added.

It should be further noted that the embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict. The embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.

As mentioned above, with the rapid development of wireless communication technology and computer technology, various APPs operating on smart terminals such as smart phones and tablet computers emerge as spring shoots after rain, and travel APPs are one of them. The passenger inputs the starting place and the destination place through the passenger end of the travel APP installed on the intelligent terminal, the passenger end sends the travel order carrying the starting place and the destination place to the service side, and the server side sends the order to the driver end of the travel APP near the starting place so as to find the vehicle capable of carrying the travel of the passenger for the passenger. At present, in order to facilitate quick on-line meeting of passengers and drivers, the passengers usually select boarding points according to their own positions before calling the vehicles for pickup, and a trip APP gives names to the boarding points through POI data or road network data near the positions according to the current positions of the users. However, the existing naming strategy considers a few factors, and usually the name of the POI closest to the boarding point is directly found to name the boarding point, so that problems of wrong naming of the boarding point, invisible naming, insignificant naming, naming by using an indoor POI and the like often occur, which causes difficulty and time-consuming communication for drivers and passengers, and even possibility and failure of the drivers and passengers, order cancellation, and poor driver and passenger experience.

In order to solve the above problems, the present disclosure provides a boarding point name recommendation scheme, which divides candidate points near a boarding point into a known candidate point and a common candidate point based on the degree of awareness of the candidate points, makes the recommended value of the known candidate point greater than the recommended value of the common candidate point when the candidate point is scored, and determines the name of the boarding point by the name of the candidate point with the highest recommended value.

Fig. 1 shows a flowchart of a pick-up point name recommendation method according to an embodiment of the present disclosure, which includes the following steps S101-S104, as shown in fig. 1:

in step S101, a plurality of candidate points whose positional relationship with the boarding point satisfies a predetermined relationship are acquired from the available map points;

in step S102, if the degree of awareness of the candidate point satisfies a preset condition, determining that the candidate point is a known candidate point, otherwise, determining that the candidate point is a common candidate point;

in step S103, determining a recommendation score of the known candidate point based on a known score algorithm, and determining a recommendation score of the common candidate point based on a common score algorithm, where the recommendation scores of the known candidate points are all greater than the recommendation score of the common candidate point;

in step S104, the name of the boarding point is determined based on the name of the candidate point with the highest recommended score.

In an embodiment of the present disclosure, the pick-up point name recommendation method may be applied to a computer, a computing device, an electronic device, a server, a service cluster, and the like, which may perform pick-up point name recommendation.

In an embodiment of the present disclosure, the boarding point refers to a pre-boarding position, such as a mall doorway, a road gap, and the like, where a service platform automatically recommends that a passenger easily arrives and a driver conveniently parks according to the position of the passenger in a travel service.

In one embodiment of the present disclosure, the available map point refers to a POI and AOI (Area of Interest) existing on a map and used for naming a boarding point name, where the POI and AOI are terms in map data, and the POI generally refers to all geographical objects that can be abstracted as points, especially some geographical entities closely related to people's life, such as schools, banks, restaurants, gas stations, hospitals, supermarkets, etc.; each POI contains four pieces of information: name, category, address, latitude and longitude coordinates. The AOI refers to regional geographic entities in the map data, especially some geographic entities with hot search and high user cognition, such as university area, hospital area, etc., and each AOI also contains four aspects of information: name, address, category, latitude and longitude coordinates.

In an embodiment of the present disclosure, after the boarding point is obtained, a plurality of available map points near the boarding point may be found from the available map points as candidate points, and the predetermined relationship is used to define a distance relationship between the candidate points and the boarding point.

In an embodiment of the present disclosure, the candidate points may be classified into a known candidate point and a common candidate point according to the degree of awareness, and if the candidate point is known or seen by most people in the vicinity of the boarding point and belongs to a significant location point, the candidate point may be determined as the known candidate point, otherwise, the candidate point is the common candidate point.

In an embodiment of the present disclosure, scores of a known candidate point and a common candidate point may be respectively calculated according to different score algorithms, and recommendation scores within a score range of the known candidate point calculated by the known score algorithm are all greater than recommendation scores within a score range of the common candidate point calculated by the common score algorithm; therefore, after the recommended value of each candidate point is calculated, the recommended value of the known candidate point near the boarding point is larger than that of the common candidate point, and therefore when the known candidate point exists near the boarding point, the boarding point is necessarily named by the name of the known candidate point with the highest recommended value, the significance of the name of the boarding point is improved, the specific position of the boarding point can be well and accurately described, the communication cost and the operation cost of drivers and conductors are reduced, the drivers and conductors can more smoothly, and the driver and conductor experience is optimized.

Here, when there is no known candidate point near the boarding point and all the candidate points are common candidate points, the boarding point may be named by the name of the common candidate point with the highest recommended score, or a better name may be recommended for the boarding point.

In the embodiment, a known candidate point name is selected when a known candidate point exists, and a common candidate point name is selected when no known candidate point exists, so that the upper vehicle point name recommendation is divided into the known candidate point name and the common candidate point name, and the scoring ranges of the two candidate point names are different, so that the problem of threshold boundary sensitivity caused by uneven distribution of scoring data is effectively solved; meanwhile, the strategy of scoring by using different scoring rules can solve the head problem, provide rich operation and maintenance scenes and facilitate iteration operation and maintenance.

In a possible implementation manner, before step S101, the method for recommending a pick-up name may further include the following steps:

filtering map points with searching frequency lower than a first preset frequency in a preset time period;

filtering map points with names containing preset keywords;

filtering map points of a first preset category;

and filtering map points with searching frequency lower than a second preset frequency in a preset grid area, wherein the preset grid area comprises map grid areas with the number of the map points exceeding the preset number.

In this embodiment, the map points refer to all POIs and AOIs existing on the map, and some POIs and AOIs are not used for naming the names of the boarding points, for example, map points that are known by few people, fuzzy in name, too small in POI reference area, located indoors, and the like are not used for naming the names of the boarding points, so that the map points need to be filtered.

In this embodiment, map points with a searching frequency lower than a first preset frequency within a preset time period may be filtered, the preset time period may be one week or one month before the current time, the first preset frequency may be set to a lower value, such as 100 or 1000, and if the searching frequency of the map points within the preset time period is lower than the first preset frequency, it is indicated that the map points are rarely searched and used by people, and usually, a user does not use the map points as a marker to perform positioning and use, and then the map points such as the points may be directly filtered.

In this embodiment, the map points with names containing preset keywords may also be filtered, a filtering blacklist may be set, and as long as the names of the map points contain the preset keywords in the blacklist, the map points are filtered. For example, the blacklist may include unconventional names: lavatory/toilet and related names; names referring to fuzzy: parking lot/entrance/exit, etc.; names referring to too small: newsstand/public telephone/bank ATM (Automated Teller Machine), etc.

In this embodiment, map points of a first preset category may also be filtered out, and the first preset category may include, for example: map points of regional categories such as Beijing; map points of road facilities such as traffic lights, signboards, and the like; indoor map points of related types such as stairs, charging rentals, etc.

In this embodiment, map points that are located indoors and do not belong to the second preset category may also be filtered out; the second preset category may be map points with large logos (identifiers) set by experience, for example, map points with large logos in schools; for example, map points in a basement or high-rise room can be filtered out, but larger map points of the logos in schools can be retained.

In this embodiment, map points with a searching frequency lower than the second preset frequency in the predetermined grid area within the second preset time period may be filtered out. The map is cut into mutually disjoint network-shaped lattices according to a certain shape such as a triangle, a quadrangle, a hexagon and the like, the geographic area covered by the network-shaped lattices can be called a grid area, the predetermined grid area comprises grid areas with the number of map points exceeding a preset number, which indicates that the density of the map points in the predetermined grid area is large, for the area with the large density of the map points, in order to avoid using the map points which are not hot spots to name the upper vehicle points, the map points which are searched for at a lower frequency than a second preset frequency in a second preset time period can be filtered, the second preset time period can be the same as or different from the first preset time period, and no limitation is made herein.

In this embodiment, the open-source mesh system h3 may be used to divide the preset area into several hexagonal meshes, resulting in several hexagonal mesh areas. The h3 grid system has 16 levels of grid regions, the size of each level of grid region is different, in the 15 th level of the smallest grid region in the h3 grid system, the average size of each grid is 0.9 square meters, the average side length is 0.509713 meters, each liter of the subsequent level, the size of the grid region of the level can be 7 times that of the grid region of the lower level, and the side length of the grid region of the 0 th level of the smallest grid region in the grid system can reach more than 1000 kilometers. For example, in this embodiment, the number of POIs in a 12-level grid region may be counted, a 12-level preset grid region where the number of POIs exceeds a preset number is obtained, and map points whose search frequency is lower than a second preset frequency within a second preset time period are filtered from the preset grid regions; meanwhile, the number of POIs in the 10-level grid area is counted, the 10-level preset grid areas with the number of the POIs exceeding the preset number are obtained, and map points with the searching frequency lower than the second preset frequency in the second preset time period are filtered out of the preset grid areas.

In this embodiment, the present disclosure may be performed in the following order: filtering map points with searching frequency lower than first preset frequency in a first preset time period; filtering map points with names containing preset keywords; filtering map points of a first preset category; filtering map points which are located indoors and do not belong to a second preset category; filtering map points with searching frequency lower than a second preset frequency in a preset grid area within a second preset time period, wherein the preset grid area comprises grid areas with the number of the map points exceeding the preset number; and sequentially filtering the points of the unavailable map points to obtain the available map points.

The embodiment refines the filtering strategy of the unavailable map points, pre-filters various candidate points which are searched at low frequency, indoors, invisible and fuzzy in reference and are not suitable for naming, reduces the number of the candidate points needing to be scored subsequently and improves the naming efficiency.

In an embodiment of the present disclosure, in the step S101 of the above-mentioned boarding point name recommendation method, that is, the step of acquiring a plurality of candidate points whose positional relationships with the boarding point satisfy a predetermined relationship from the available map points, may be implemented as the following steps:

and acquiring the interest area AOI with the distance between the boundary and the upper vehicle point within a second preset distance from the available map points as candidate points.

In this embodiment, the available map points include two types, i.e., POI and AOI, the position of the POI is a point position, so that for the POI, POI whose distance from the boarding point is within a first preset distance can be selected as candidate points; the AOI position is an area position and comprises a plurality of boundary positions, so that for the AOI, the AOI with the distance between the boundary closest to the upper vehicle point and the upper vehicle point within a second preset distance can be selected as a candidate point.

In this embodiment, the first preset distance and the second preset distance may be the same or different, and because of the higher stability and significance of the AOI compared to the POI distance, it is preferable that the second preset distance is greater than the first preset distance, for example, the first preset distance may be 80 meters, and the second preset distance may be 100 m.

In an embodiment of the present disclosure, in the step S102 of the method for recommending a name of a boarding pass, that is, if the degree of awareness of the candidate point satisfies a preset condition, determining that the candidate point is a known candidate point may include the following steps:

In this embodiment, the preset known level may be a plurality of known levels set by human experience, for example, the preset known level may have 11 known levels, where the highest known level, i.e., the first level, is a notable gate and a known bank, the second level is a subway gate, the third level is a medium known gate, the fourth level is a notable gate-to-face, the fifth level is a bus stop, the sixth level is a main branch and a virtual door, the seventh level is an intersection, the eighth level is an intersection extension, the ninth level is a building number, the tenth level is a main branch-to-face, and the eleventh level is a significantly large side.

In this embodiment, there are 5 preset conditions, each preset known level corresponds to 5 preset conditions, and since the levels of the preset conditions are different, the relevant parameters in the 5 conditions are also different, for example, the following example may be used to describe the 5 preset conditions corresponding to the 11 preset known levels described above:

the first level is a remarkable gate and a well-known bank, wherein the remarkable gate corresponds to 5 preset conditions: 1. the famous type is a door type; 2. a candidate point which is visible as the boarding point; 3. the spatial position relation between the candidate point and the boarding point is positioned on the same side of the road; 4. the distance between the car and the car-loading point is less than 35 meters; 5. the searching frequency is more than or equal to 300 times in 1 day. The known bank corresponds to 5 preset conditions as follows: 1. the famous type is a bank category; 2. a candidate point which is visible as the boarding point; 3. the spatial position relation between the candidate point and the boarding point is positioned on the same side of the road; 4. the distance between the car and the car-loading point is less than 35 meters; 5. the searching frequency is more than or equal to 1000 times in 1 day.

The second level is a subway entrance, and the subway entrance corresponds to 5 preset conditions as follows: 1. the famous type is the subway entrance category; 2. a candidate point which is visible as the boarding point; 3. the spatial position relation between the candidate point and the boarding point is positioned on the same side of the road; 4. the distance between the car and the car-loading point is less than 35 meters; 5. the searching frequency is more than or equal to 1000 times in 1 day. It should be noted here that, since the search frequency of the subway entrance is very large, the search frequency of the subway entrance level may not be limited.

The third level is a medium-known gate, and the medium-known gate corresponds to 5 preset conditions: 1. the famous type is a door type; 2. a candidate point which is visible as the boarding point; 3. the spatial position relation between the candidate point and the boarding point is positioned on the same side of the road; 4. the distance between the car and the car-loading point is less than 35 meters; 5. the searching frequency is more than or equal to 100 times and less than 300 times in 1 day. It should be noted here that when the search frequency does not meet the condition 5, the width of the road in front of the door is larger than 3m, or the door of which the door category belongs to a hospital/clinic/school, etc. can also be determined as a medium-known door.

The fourth level is opposite to the significant gate, and the 5 preset conditions corresponding to the opposite to the significant gate are as follows: 1. the famous type is a door type; 2. a candidate point which is visible as the boarding point; 3. the spatial position relation between the candidate point and the boarding point is road crossing, and the boarding point is positioned in the 30-degree radiation range of the candidate point; 4. the distance between the vehicle and the boarding point is within the range of [15, 60) meters; 5. the searching frequency is more than or equal to 300 times in 1 day.

The fifth level is a bus stop, and the bus stop corresponds to 5 preset conditions: 1. the known type is a bus station category; 2. a candidate point which is visible as the boarding point; 3. the spatial position relation between the candidate point and the boarding point is positioned on the same side of the road; 4. the distance between the car and the car-loading point is less than 35 meters; 5. the searching frequency is more than or equal to 1000 times in 1 day. It should be noted here that, since the bus stops are searched frequently, the frequency of searching at the bus stop level may not be limited.

The sixth level is a main branch store and a virtual door, and the main branch store corresponds to 5 preset conditions as follows: 1. the known type is a general branch category for catering/shopping/leisure/medical/life services, the name of which satisfies the general branch structure, such as XX bank (YY branch); 2. a candidate point which is visible as the boarding point; 3. the spatial position relation between the candidate point and the boarding point is that the candidate point is positioned on the same side of the road and is a street-approaching commercial tenant; 4. the distance between the car and the car-loading point is less than 35 meters; 5. the frequency of searching the general stores is more than or equal to 1000 times in 1 day. The 5 preset conditions corresponding to the virtual door are as follows: 1. the well-known types are hospital/clinic/school and the like; 2. a candidate point which is visible as the boarding point; 3. the spatial position relation between the candidate point and the boarding point is positioned on the same side of the road; 4. the distance between the car and the car-loading point is less than 35 meters; 5. the search frequency within 1 day is more than or equal to 1000 times or the search frequency is more than or equal to 100 times and less than 300 times when the virtual door has the orientation angle information.

The seventh level is an intersection, and the 5 preset conditions corresponding to the intersection are as follows: 1. the well-known type is the intersection type; 2. a candidate point which is visible as the boarding point; 3. the spatial position relation between the candidate point and the boarding point is positioned on the same side of the road; 4. the distance between the car and the car-loading point is less than 35 meters; 5. the frequency of searching within 1 day is more than or equal to 1000. Here, since the search frequency of the intersection is large, the search frequency of the intersection level may not be limited.

The eighth level is the intersection extension, and the 5 preset conditions corresponding to the intersection extension are as follows: 1. the well-known type is the intersection type; 2. a candidate point which is visible as the boarding point; 3. the spatial position relation between the candidate point and the vehicle-loading point is that the candidate point is positioned on the same side of the road and the candidate point is positioned on the intersection connecting road; 4. the distance between the vehicle and the boarding point is in the range of [15, 60) meters; 5. the frequency of searching within 1 day is more than or equal to 1000. Here, since the search frequency of the intersection is large, the search frequency of the intersection level may not be limited.

The ninth level is a building number, and the 5 preset conditions corresponding to the building number are as follows: 1. the well-known type is the building number category; 2. a candidate point which is visible as the boarding point; 3. the spatial position relation between the candidate point and the boarding point is that the candidate point and the boarding point are positioned on the same side of a road and the boarding point is positioned inside the AOI; 4. the distance between the boundary nearest to the upper vehicle and the upper vehicle point is less than 35 meters; 5. the searching frequency in 1 day is more than or equal to 10 times; at this time, when the boarding point is located inside the interest plane AOI, the 6 th condition that the density in the 10-level H3 grid area where the candidate point is located is less than or equal to 10 is also included; here, since the search frequency of the building number is small, the search frequency of the building number level may not be limited.

The tenth level is the opposite of the general branch store, and the 5 preset conditions corresponding to the opposite of the general branch store are as follows: the well-known type is a general branch category for catering/shopping/leisure/medical/life services, the name of which satisfies a general branch structure, such as XX bank (YY branch); 2. a candidate point which is visible as the boarding point; 3. the spatial position relation between the candidate point and the boarding point is road crossing, and the boarding point is positioned in the 30-degree radiation range of the candidate point; 4. the distance between the vehicle and the boarding point is in the range of [15,40) meters; 5. the searching frequency of the general store is equal to or more than 50000 times within 1 day.

The eleventh level is the side of the notable gate, and the 5 preset conditions corresponding to the side of the notable gate are: 1. the famous type is a door type; 2. a candidate point which is visible as the boarding point; 3. the spatial position relation between the candidate point and the boarding point is positioned on the same side of the road; 4. the distance between the vehicle and the boarding point is in the range of [35, 60) meters; 5. the searching frequency is more than or equal to 300 times in 1 day.

In this embodiment, according to the eleven levels, which preset known level each candidate point belongs to may be sequentially determined from high to low, and if the candidate point satisfies a preset condition corresponding to one of the preset known levels, it is determined that the candidate point belongs to a known candidate point of the preset known level; and if the candidate point does not meet the preset conditions corresponding to the eleven preset known levels, determining the common candidate point of the candidate point.

In the embodiment, the map data and the spatial structure are combined, data depth mining is carried out, and the characteristics of invisible positions, cross-road relations and the like are introduced, so that the division of the naming strategy scene is more clear, the optimization is simpler, and the interpretability of the scene is stronger.

In a possible embodiment, the step S103 of the above-mentioned method for recommending a roll call name, namely determining a recommendation score of the known candidate point based on a known score algorithm, may include the following steps:

obtaining a recommendation score multiplying power of the known candidate points based on a corresponding relation between the preset known level and the recommendation score multiplying power, wherein the recommendation score multiplying power is used for indicating a scoring range of the known candidate points of the preset known level;

determining a spare recommendation score of the known candidate point based on a known scoring parameter and a corresponding parameter weight thereof, wherein the known scoring parameter comprises: the distance between the known candidate point and the vehicle-entering point, and the stability and the reliability of the known candidate point; the range of the spare recommendation score is greater than 0 and less than or equal to 1;

and taking the product of the recommendation score multiplying power of the known candidate points and the standby recommendation score of the known candidate points as the recommendation score of the known candidate points.

In this embodiment, in order to distinguish the recommendation scores of the known candidate points of each preset known level, the recommendation scores of the known candidate points with higher known levels are made higher, different recommendation score magnifications may be set for different preset known levels, and the corresponding relationship between the preset known levels and the recommendation score magnifications is pre-stored, so that when candidate points near the boarding point are obtained and determined as known candidate points, the recommendation score magnifications of the known candidate points may be obtained first, for example, still by taking the above-mentioned 11 preset known levels as an example, the recommendation score magnifications corresponding to the first level, i.e., the notable gate and the known bank, may be set to be 10 ²² Since the alternative recommended score range of the known candidate points is greater than 0.01 and less than or equal to 1, the score range of the first-level known candidate points is 10 ²⁰ ~10 ²² (ii) a The second level, namely the recommended score multiplying power corresponding to the subway entrance is 10 ²⁰ The second level of known candidate points has a score range of 10 ¹⁸ ~10 ²⁰ (ii) a The third level is mediumThe recommendation score multiplying power corresponding to the known gate is 10 ¹⁸ The third level of known candidate points have a score of 10 ¹⁶ ~10 ¹⁸ (ii) a The fourth level, namely the corresponding recommended score multiplying power of the opposite side of the remarkable gate is 10 ¹⁶ The fourth level of known candidate points have a score of 10 ¹⁴ ~10 ¹⁶ (ii) a The recommendation score multiplying power corresponding to the fifth level, namely the bus station point is 10 ¹⁴ The scoring range of the known candidate points of the fifth level is 10 ¹² ~10 ¹⁴ (ii) a The recommendation score multiplying power corresponding to the total branch store and the virtual door at the sixth level is 10 ¹² The scoring range of the known candidate points of the sixth level is 10 ¹⁰ ~10 ¹² (ii) a The recommended score multiplying power corresponding to the seventh level, namely the intersection, is 10 ¹⁰ The scoring range of the known candidate points of the seventh level is 10 ⁸ ~10 ¹⁰ (ii) a The eighth level is that the recommended value multiplying power corresponding to the intersection extension is 10 ⁸ The scoring range of the known candidate points of the eighth level is 10 ⁶ ~10 ⁸ (ii) a The ninth level is that the recommended score multiplying power corresponding to the building number is 10 ⁶ The ninth level of known candidate points has a score of 10 ⁴ ~10 ⁶ (ii) a The tenth level is that the corresponding recommended score multiplying power of the total branch shop to the opposite side is 10 ⁴ The score range of the known candidate points at the tenth level is 10 ² ~10 ⁴ (ii) a The eleventh level is that the recommended score multiplying power corresponding to the significant gate side is 10 ² The scoring range of the known candidate points of the eleventh level is 10 ² 1. The scoring ranges of the known candidate points of the preset known levels are not overlapped.

In this embodiment, the distance between the known candidate point and the boarding point may be normalized, and the value after normalization is smaller as the distance is farther, and the value range after normalization is [0, 1 ]; the stability of the known candidate point refers to whether a boarding point is named by the name of the known candidate point in a finished taxi taking order or not, the stability is determined based on the used times, the more the used times are, the higher the stability is, and the value of the stability can be [0, 1 ]; the credibility of the known candidate point refers to the credibility of POI data of the known candidate point, in general, the credibility of AOI is higher, the credibility of POI or AOI collected by professionals is higher than that of POI or AOI collected by crowdsourcing users, the credibility of POI or AOI not updated for a long time is lower than that of POI or AOI just updated in a short time, and the value range of the credibility is [0, 1 ]. The sum of the weights of the above three scoring parameters is 1, preferably, the weight corresponding to the confidence level may be set to be a larger value, and the spare recommendation score of the known candidate point may be obtained by performing weighted calculation on the three scoring parameters according to the respective weights, where the range of the spare recommendation score is [0, 1 ].

In this embodiment, only known candidate points with a spare recommendation score within a range of (0.01, 1) are selected, and the known candidate points with the spare recommendation score smaller than or equal to 0.01 are removed, so that the range of the spare recommendation scores of the remaining known candidate points is between (0.01, 1), and the product of the recommendation score multiplying power of the known candidate points and the spare recommendation scores of the remaining known candidate points is used as the recommendation score of the known candidate points, so that the finally obtained recommendation scores of all levels of known candidate points are within corresponding scoring ranges and do not overlap, and the highest-score known candidate point selected after sorting is always the highest-score known candidate point near the boarding point and has the highest significance.

In addition, the known candidate points of each preset known level are scored in different scoring ranges, so that not only can a strict priority strategy be conveniently realized, but also the long-tailed condition can be flexibly processed in the same level.

In a possible implementation manner, the pick-up point name recommendation method may further include the following steps:

In this embodiment, if the known candidate point and the pick-up point are located in the same AOI, the recommendation score magnification of the known candidate point is determined as the predetermined maximum magnification, for example, 10, regardless of which preset known level the known candidate point is located in ²⁴ 。

In a possible embodiment, the step S103 of the above-mentioned method for recommending a name of a boarding point, namely determining a recommendation score of the common candidate point based on a common score algorithm, may include the following steps:

In this embodiment, the common candidate points can be divided into the following four scenarios: in a scene 1, a vehicle getting-on point and the common candidate point are located in the same AOI, and the scoring range of the scene is [0.8, 1.0 ]; scene 2, the common candidate point is located at the invisible position of the boarding point, and the scoring range of the scene is [0, 0.1 ]; a scene 3, wherein the ordinary candidate points and the boarding points cross the road, and the scoring range of the scene is [0, 0.5 ]; scene 4, other than the above-mentioned 3 scenes, has a rating range of [0.1, 0.8 ].

In this embodiment, the distance between the common candidate point and the boarding point may be normalized, and the value after normalization is smaller as the distance is farther, and the value range after normalization is [0, 1 ]; the stability of the common candidate point refers to whether a boarding point is named by the name of the common candidate point in a completed taxi taking order or not, the stability is determined based on the used times, the more the used times are, the higher the stability is, and the value of the stability can be [0, 1 ]; the credibility of the common candidate point refers to the credibility of POI data of the common candidate point, in general, the credibility of AOI is higher, the credibility of POI or AOI collected by professionals is higher than that of POI or AOI collected by crowdsourcing users, the credibility of POI or AOI not updated for a long time is lower than that of POI or AOI just updated in a short time, and the value range of the credibility is [0, 1 ]. The sum of the weights of the above three scoring parameters is 1; if the name type is the preset name type, the value is 1, and if the name type is not the preset name level, the value is 0; if the street is present, the value is 1, and if the street is not present, the value is 0; the higher the search frequency in the fourth preset time period is, the greater the heat is, and the value range of the heat is [0, 1 ]. Preferably, the weight corresponding to the confidence level may be set to be a larger value, and the spare recommendation score of the common candidate point may be obtained by performing weighted calculation on the above 6 scoring parameters according to the respective weights, where the spare recommendation score ranges from [0, 1 ].

In this embodiment, according to the scene where the common candidate point is located, the spare recommendation score of the common candidate point may be converted into a recommendation score within the scoring range of the scene where the common candidate point is located. For example, if the scene where the normal candidate point is located is scene 1, the range of the backup recommendation score of the normal candidate point in the scene is [0, 1], and [0, 1] can be compressed and converted to [0.8, 1.0 ]. If the scene where the common candidate point is located is scene 3, the range of the spare recommendation score of the common candidate point in the scene is [0, 1], and the spare recommendation score multiplied by 0.5 can be compressed and converted into the scoring range [0, 0.5 ].

In this embodiment, even if there is no known candidate point near the boarding point, a normal candidate point that is most prominent in the scene may be selected, and an appropriate normal candidate point may be selected from the most prominent scene based on the characteristics of the normal candidate point, such as distance, stability, reliability, saliency, and visibility.

In the embodiment, the scoring standard of the scene where each common candidate point is located is mined, orientation angles are mined, invisible identification and cross-road identification are introduced, naming score is comprehensively evaluated in consideration of naming stability, continuity, confidence degree of data and the like, so that naming is relatively strict and interpretable, in addition, the scene where each common candidate point is located corresponds to different scoring ranges, not only can a strict scene priority strategy be conveniently realized, but also the long tail condition can be flexibly processed in the same level.

In a possible embodiment, the method may further comprise the steps of:

In this embodiment, the above method needs to determine the relative position relationship between the upper vehicle point and the candidate point, at this time, all roads around the upper vehicle point may be recalled first, roads that do not intersect with the target connecting line among the roads at the point are filtered, and roads that intersect with the target connecting line are obtained, and if there are two parallel roads in opposite driving directions, it indicates that the relative position relationship between the upper vehicle point and the candidate point is the cross-road relationship. For example, fig. 2 shows a schematic view of a scene where a boarding point is located according to an embodiment of the present disclosure, as shown in fig. 2, if a target connection line 23 between the first boarding point 21 and the candidate point 22 exists in a road intersecting the target connection line 23, and a first road 24 and a second road 25 are parallel but traveling directions are opposite, a relative position relationship between the first boarding point 21 and the candidate point 22 is a cross-road relationship, and it is obvious from fig. 2 that the relative relationship between the first boarding point 21 and the candidate point 22 needs to be cross-road.

In a possible embodiment, the method may further comprise the steps of:

In this embodiment, since passengers usually drive outside the POI, when determining whether the candidate point is a candidate point visible to the boarding point, the POI needs to be pulled outside to the pull-out point for determination. For example, as shown in fig. 2, the orientation angle of the candidate point 22 is a direction indicated by an arrow 26, which is perpendicular to the AOI boundary where the candidate point 22 is located and faces outwards, and it should be noted here that the AOI or floor boundary refers to the boundary closest to the candidate point. As shown in fig. 2, the candidate point 22 is moved a third preset distance in the direction of the heading angle to reach the pull-out point 27, and a building entity exists between the pull-out point 27 and the second boarding point 28, and then the candidate point 22 is determined to be a candidate point where the boarding point is not visible, as can be seen from fig. 2, the passenger cannot see the candidate point 22 at the second boarding point 28, and the second boarding point 28 is required to turn to see the candidate point 22.

In a possible embodiment, in step S104 of the above method for recommending a name of a boarding point, that is, determining the name of the boarding point according to the name of the candidate point with the highest recommendation score, the method may further include the following steps:

if the vehicle-entering point and the candidate point with the highest recommended score are on the same side and the distance is within a fourth preset distance, naming the candidate point with the highest recommended score to determine the name of the vehicle-entering point; if the vehicle-entering point and the candidate point with the highest recommended score are on the same side and the distance exceeds the fourth preset distance, determining the name of the vehicle-entering point based on the name of the candidate point with the highest recommended score and the position of the vehicle-entering point at the candidate point with the highest recommended score; if the relative position relationship between the vehicle-entering point and the candidate point with the highest recommended score is a road-crossing relationship, recommending the vehicle-entering point name as the opposite of the candidate point with the highest recommended score;

and when the vehicle-entering point and the candidate point are positioned in the same AOI, naming the vehicle-entering point by using the name of the AOI, the name of the road where the vehicle-entering point is positioned and the name of the candidate point.

In this embodiment, if the pick-up point and the candidate point are on the same side and are within 35 meters of each other, the pick-up point can be directly named by the name of the candidate point; if the distance exceeds 35 meters, the pick-up point can be named using [ candidate point name ] + [ azimuth ] + [ side ], such as the northwest side of the first-opening square (northern seven doors).

In this embodiment, if the boarding point crosses the candidate point, the boarding point is named as [ candidate point name ] + [ opposite ], for example, XX school opposite.

In this embodiment, when the boarding point and the candidate point are located in the same AOI, the boarding point is named by using the name of the AOI, the name of the road on which the boarding point is located, and the name of the candidate point, and may be named as [ AOI name ] + [ road name ] + [ candidate point name ], such as across the first opening square-funnean west road-XX hospital.

In the embodiment, the candidate point name and the surrounding environment can be named in a combined manner, the significance and the accurate determination of the naming are considered, and the name of the vehicle-entering point is ensured to be more reasonable.

The following are embodiments of the disclosed apparatus that may be used to perform embodiments of the disclosed methods.

Fig. 3 is a block diagram illustrating a structure of a pick-up point name recommending apparatus according to an embodiment of the present disclosure, which may be implemented as part of or all of an electronic device by software, hardware, or a combination of the two. As shown in fig. 3, the pick-up point name recommending apparatus includes:

a first acquisition module 301 configured to acquire, from available map points, a plurality of candidate points whose positional relationships with a boarding point satisfy a predetermined relationship;

a first determining module 302, configured to determine that the candidate point is a known candidate point if the degree of awareness of the candidate point satisfies a preset condition, and otherwise, determine that the candidate point is a common candidate point;

a scoring module 303 configured to determine a recommendation score of the known candidate point based on a known score algorithm, and determine a recommendation score of the common candidate point based on a common score algorithm, where the recommendation scores of the known candidate points are all greater than the recommendation score of the common candidate point;

and the naming module 304 is configured to determine the name of the boarding point according to the name of the candidate point with the highest recommended score.

In a possible embodiment, the apparatus further comprises:

filtering map points with names containing preset keywords;

filtering map points of a first preset category;

and filtering map points with the searching frequency lower than the second preset frequency in a preset grid area within a second preset time period, wherein the preset grid area comprises grid areas with the number of the map points exceeding the preset number.

In one possible implementation, the first obtaining module 301 is configured to:

In one possible implementation, the first determining module 302 is configured to:

In one possible implementation, the part of the scoring module 303 that determines the recommendation score of the known candidate point based on a known score algorithm is configured to:

In one possible implementation, the scoring module 303 is further configured to:

In one possible implementation, the part of the scoring module that determines the recommendation score for the generic candidate point based on a generic score algorithm is configured to:

In a possible embodiment, the apparatus further comprises:

In one possible embodiment, the apparatus further comprises:

a third obtaining module, configured to obtain an orientation angle of the candidate point, where the orientation angle is perpendicular to an AOI where the candidate point is located or an angle outward from a building block boundary;

In one possible implementation, the naming module 304 is configured to:

The present disclosure also discloses an electronic device, fig. 4 shows a block diagram of the electronic device according to an embodiment of the present disclosure, and as shown in fig. 4, the electronic device 400 includes a memory 401 and a processor 402; wherein the content of the first and second substances,

the memory 401 is used to store one or more computer instructions that are executed by the processor 402 to implement the above-described method steps.

As shown in fig. 5, the computer system 500 includes a processing unit 501 that can execute various processes in the above-described embodiments according to a program stored in a Read Only Memory (ROM) 502 or a program loaded from a storage section 508 into a Random Access Memory (RAM) 503. In the RAM503, various programs and data necessary for the operation of the computer system 500 are also stored. The processing unit 501, the ROM502, and the RAM503 are connected to each other by a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.

The following components are connected to the I/O interface 505: an input portion 506 including a keyboard, a mouse, and the like; an output portion 507 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage portion 508 including a hard disk and the like; and a communication section 509 including a network interface card such as a LAN card, a modem, or the like. The communication section 509 performs communication processing via a network such as the internet. The driver 510 is also connected to the I/O interface 505 as necessary. A removable medium 511 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 510 as necessary, so that a computer program read out therefrom is mounted into the storage section 508 as necessary. The processing unit 501 may be implemented as a CPU, a GPU, a TPU, an FPGA, an NPU, or other processing units.

In particular, the above described methods may be implemented as computer software programs, according to embodiments of the present disclosure. For example, embodiments of the present disclosure include a computer program product comprising a computer program tangibly embodied on a medium readable thereby, the computer program comprising program code for performing the pick-up point name recommendation method. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 509, and/or installed from the removable medium 511.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowcharts or block diagrams may represent a module, a program segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units or modules described in the embodiments of the present disclosure may be implemented by software or hardware. The units or modules described may also be provided in a processor, and the names of the units or modules do not in some cases constitute a limitation of the units or modules themselves.

As another aspect, the disclosed embodiment also provides a computer-readable storage medium, which may be the computer-readable storage medium included in the apparatus in the foregoing embodiment; or it may be a separate computer readable storage medium not incorporated into the device. The computer readable storage medium stores one or more programs for use by one or more processors in performing the methods described in the embodiments of the present disclosure.

The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention in the embodiments of the present disclosure is not limited to the specific combination of the above-mentioned features, but also encompasses other embodiments in which any combination of the above-mentioned features or their equivalents is made without departing from the inventive concept. For example, the above features and (but not limited to) the features with similar functions disclosed in the embodiments of the present disclosure are mutually replaced to form the technical solution.

Claims

1. A pick-up point name recommendation method comprises the following steps:

if the popularity of the candidate point meets a preset condition, determining the candidate point as a popular candidate point, otherwise, determining the candidate point as a common candidate point;

determining the recommendation scores of the known candidate points based on a known score algorithm, and determining the recommendation scores of the common candidate points based on a common score algorithm, wherein the recommendation scores of the known candidate points are all larger than the recommendation scores of the common candidate points; the known score algorithm and the common score algorithm are different score algorithms;

2. The method of claim 1, wherein the method further comprises:

filtering map points with names containing preset keywords;

filtering map points of a first preset category;

3. The method according to claim 1, wherein the obtaining a plurality of candidate points whose position relationship with the boarding point satisfies a predetermined relationship from the available map points comprises:

and acquiring an interest area AOI (area of interest) with the distance between a target boundary and a boarding point within a second preset distance from the available map points as candidate points, wherein the target boundary is the nearest boundary to the boarding point in the AOI.

4. The method of claim 1, wherein the determining the candidate point as a known candidate point if the degree of awareness of the candidate point satisfies a predetermined condition comprises:

5. The method of claim 4, wherein the determining the recommendation score for the known candidate point based on a known score algorithm comprises:

obtaining a recommendation score multiplying power of the unknown candidate points based on the corresponding relation between the preset unknown levels and the recommendation score multiplying power, wherein the recommendation score multiplying power is used for limiting scoring ranges of the unknown candidate points of the preset unknown levels, different preset unknown levels correspond to different scoring ranges, and the scoring ranges are not overlapped;

6. The method of claim 5, wherein the method further comprises:

7. The method of claim 4, wherein the determining the recommendation score for the common candidate point based on a common score algorithm comprises:

determining a spare recommendation score of the common candidate point based on a common scoring parameter and a corresponding parameter weight thereof, wherein the common scoring parameter comprises: the distance between the common candidate point and the boarding point, the stability of the common candidate point, the reliability of the common candidate point, whether the common candidate point is a known type with a preset known level, whether the common candidate point is on street or not, and the search frequency in a fourth preset time period; the range of the spare recommendation score of the common candidate point is more than or equal to 0 and less than or equal to 1;

8. The method of claim 4, wherein the method further comprises:

9. The method of claim 4, wherein the method further comprises:

10. The method of claim 4, wherein the determining the name of the pick-up point according to the name of the candidate point with the highest recommended score comprises:

11. An pick-up point name recommendation device comprising:

the scoring module is configured to determine the recommendation scores of the known candidate points based on a known score algorithm and determine the recommendation scores of the common candidate points based on a common score algorithm, wherein the recommendation scores of the known candidate points are all larger than the recommendation score of the common candidate points; the known score algorithm and the common score algorithm are different score algorithms;

12. An electronic device comprising a memory and a processor; wherein the memory is to store one or more computer instructions that are executed by the processor to implement the method steps of any one of claims 1 to 10.

13. A computer readable storage medium having stored thereon computer instructions which, when executed by a processor, carry out the method steps of any of claims 1-10.