Boarding point recommendation method and computer storage medium

Abstract

An embodiment of the present application provides a method and computer storage medium for recommending a boarding point. The method includes: obtaining boarding point information searched by a traveler, determining a search scenario for the search based on the boarding point information; determining the type of an area of ​​interest (AOI) corresponding to the boarding point based on the search scenario and the boarding point information; determining a recommendation strategy that matches the type of the AOI from a plurality of pre-stored boarding point recommendation strategies based on the type of the AOI; and determining a recommended boarding point based on the recommendation strategy, the AOI information, and the boarding point information. Through the embodiments of the present application, recommended boarding points are made more accurate and reasonable, improving the traveler's travel experience.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of computer technology, and in particular to a method for recommending a boarding point and a computer storage medium. Background Art

[0002] With the rapid development of the transportation service industry and online platforms, online transportation services have become widely used in our lives. For example, online taxi services have become increasingly popular due to their convenience.

[0003] A traveler sends a taxi request through their device. Upon receiving the request, the server assigns the request to a driver. The driver then arrives at the designated pickup point to pick up the traveler. Typically, the server recommends a default pickup point based on the traveler's request. If the default recommended pickup point isn't the desired pickup point, the traveler will actively search for it or drag the pickup point to find it.

[0004] However, in the scenario where the travel object searches for or drags the boarding point, the scenarios are diverse and complex. If the location coordinates searched by the travel object are directly recommended to the travel object as the boarding point, there may be deviations between the recommended boarding point and the boarding point desired by the travel object due to various reasons, such as the boarding point searched by the travel object does not allow temporary parking or the boarding point is temporarily closed or the boarding point is not the actual intended boarding point of the travel object due to input deviation, etc., resulting in improper positioning of the boarding point and reducing the travel experience of the travel object. Summary of the Invention

[0005] In view of this, an embodiment of the present application provides a boarding point recommendation solution to at least partially solve the above-mentioned problem.

[0006] According to a first aspect of an embodiment of the present application, a method for recommending a boarding point is provided, including: obtaining boarding point information for a travel object search, and determining a search scenario for the search based on the boarding point information; determining a type of an area of ​​interest (AOI) corresponding to the boarding point based on the search scenario and the boarding point information; determining a recommendation strategy that matches the type of the AOI from a plurality of pre-stored boarding point recommendation strategies based on the type of the AOI; and determining a recommended boarding point based on the recommendation strategy, the information of the AOI, and the boarding point information.

[0007] According to the second aspect of an embodiment of the present application, another method for recommending a boarding point is provided, including: receiving boarding point information input by a travel subject through a travel navigation interface; generating a search request based on the boarding point information and sending it to a travel service end; receiving information of a recommended boarding point determined based on the boarding point information returned by the travel service end in response to the search request; updating an electronic map in the travel navigation interface based on the information of the recommended boarding point, and marking the location of the recommended boarding point in the updated electronic map.

[0008] According to the third aspect of an embodiment of the present application, an electronic device is provided, comprising: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other through the communication bus; the memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform operations corresponding to the boarding point recommendation method described in the first aspect or the second aspect.

[0009] According to a fourth aspect of an embodiment of the present application, a computer storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the method for recommending a boarding point as described in the first aspect or the second aspect is implemented.

[0010] According to the boarding point recommendation scheme provided by the embodiment of the present application, when a traveler wants to select a boarding point by himself, the current search scenario of the traveler will be determined based on the boarding point information of the boarding point; then, based on the search scenario and the boarding point information, the type of AOI corresponding to the boarding point will be determined; and based on the AOI type, a recommendation strategy will be determined, and then the corresponding recommended boarding point will be determined. Because the search scenario can better reflect the current status and environment of the traveler, the type of AOI that matches the search scenario can be more effectively determined based on this. Compared with using POI as a reference, using AOI as a reference has more boarding point candidates to choose from, and the boarding point selected thereby is more objective and reasonable. In addition, because different types of AOIs may be adapted to different recommendation strategies, their recommendation efficiency and effectiveness are also different. Therefore, based on the type of AOI, a recommendation strategy adapted to it can be determined to achieve efficient, reasonable, and accurate boarding point recommendations.

[0011] It can be seen that through the embodiments of the present application, the accuracy and rationality of boarding point positioning can be effectively improved when travelers search for boarding points by themselves, thereby improving the travel experience of travelers. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments recorded in the embodiments of the present application. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0013] Figure 1 A flowchart of a method for recommending a boarding point provided in an embodiment of the present application;

[0014] Figure 2 A schematic diagram of an application scenario provided in an embodiment of the present application;

[0015] Figure 3 A flowchart of another method for recommending boarding points provided in an embodiment of the present application;

[0016] Figure 4 A flowchart of another method for recommending a boarding point provided in an embodiment of the present application;

[0017] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0018] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field should fall within the scope of protection of the embodiments of the present application.

[0019] The specific implementation of the embodiment of the present application is further explained below in conjunction with the accompanying drawings of the embodiment of the present application.

[0020] Example 1

[0021] The method for recommending boarding points provided in the first embodiment of the present application is as follows: Figure 1 As shown, Figure 1 This is a flowchart of a method for recommending a boarding point provided in an embodiment of the present application. The method for recommending a boarding point includes the following steps:

[0022] Step S101: Acquire boarding point information for a travel object search, and determine a search scenario for the search based on the boarding point information.

[0023] In this embodiment of the present application, the boarding point refers to the location where a traveler begins boarding a particular mode of transportation. The boarding point information may include any information that identifies the boarding point, including but not limited to: the name of the boarding point, the location of the boarding point, the house number corresponding to the boarding point, etc. Alternatively, the boarding point information may be determined by dragging a corresponding sign to the desired location by the traveler, and then based on information about the dragged location.

[0024] The search scenario in which the travel subject is currently searching for the boarding point can be determined based on the boarding point information. In the embodiment of the present application, the search scenario can characterize the state and environment of the travel subject when searching, so as to provide a basis for the subsequent determination of the AOI. For example, if the boarding point information is XX Park, it can be determined that the travel subject may need to return to his residence or other places after playing in the park, and it can be basically determined that the search scenario is a leisure scenario. For another example, if the boarding point information is XX subway station, it can be determined that the travel subject may have arrived at the subway station in some way, such as by subway, by car, or by walking, and needs to continue traveling, and it can be basically determined that the search scenario is a transportation scene. Among them, AOI (Area Of Interest) is used to represent regional geographical entities in a map, such as schools, shopping malls, parks, office buildings, communities, etc.

[0025] In one feasible approach, determining the search scenario based on the boarding point information can be implemented by: obtaining, based on the boarding point information, information about the AOI where the boarding point is located, or information about AOIs within a preset distance range from the boarding point; and determining the search scenario based on the obtained AOI information. The preset distance range can be appropriately set by those skilled in the art to a smaller range, such as 0-100 meters, based on actual needs, and is not limited in this embodiment of the present application.

[0026] Generally speaking, there are one or more AOIs near the boarding point, such as shopping malls, residential areas, parks, roads, etc. The boarding point itself may also be part of the AOI, such as a gate to a residential area or a park entrance. Based on the boarding point information, the AOIs and AOI information of the boarding point or its vicinity can be determined. AOI information generally includes, but is not limited to, name, type, boundaries, whether it is a large AOI, and other information. The types can be distinguished based on the function of the AOI, for example, business, residential, leisure, transportation, etc. Furthermore, each category can be further subdivided. For example, the leisure category can also include park, theater, shopping mall categories, etc., and the transportation category can also include station, subway, road, etc. The specific type division and sub-type division within a type can be determined by those skilled in the art based on actual needs. The above is only an example.

[0027] Because the boarding point being searched by a traveler is close to the corresponding AOI, the search scenario can be determined based on the AOI information to understand the traveler's current status and surroundings. For example, if the boarding point is close to a shopping mall, the search scenario can be a leisure scenario. The traveler's status may be returning to their residence after shopping and their surroundings are near the mall, etc. It should be noted that if there are multiple AOIs close to the boarding point, the search scenario can be determined based on the information of these multiple AOIs according to corresponding rules. These rules may include, but are not limited to, the closest distance rule, the most common type rule, the most frequently used rule, and so on. For example, if there are three AOIs near boarding point A, namely X, Y, and Z. In one approach, if X is closest to boarding point A, the search scenario can be determined based on X's information. In another approach, if X and Y are both leisure types and Z is residential, the search scenario can be determined based on the most common type, i.e., the leisure type corresponding to X and Y. In yet another approach, if most travelers ultimately choose Y when searching for boarding points, the search scenario can be determined based on Y's information according to the most frequently used rule.

[0028] In a specific feasible solution, determining the search scenario for the search based on the acquired AOI information may be implemented as at least one of the following:

[0029] If the AOI information indicates that the AOI is a traffic AOI (such as a station, a road, etc.), determining that the search scene is a traffic scene;

[0030] If the AOI information indicates that the AOI is a business AOI (such as an office building, office area, etc.), determining that the search scenario is a business scenario;

[0031] If the AOI information indicates that the AOI is a leisure AOI (such as a park, a theater, a shopping mall, etc.), determining that the search scene is a leisure scene;

[0032] If the AOI information indicates that the AOI is a residential AOI (such as a residential community), determining that the search scene is a residential scene;

[0033] If the AOI information indicates that the AOI is a public institution AOI (such as a school, hospital, court, etc.), it is determined that the search scenario is a public institution scenario.

[0034] Through the above method, the search scenario can be determined quickly and efficiently based on the AOI information, and can cover most search scenarios in practical applications.

[0035] However, it should be noted that in other implementations, the system can also pre-set the correspondence between different types of boarding points and different search scenarios. Based on this correspondence, the search scenario corresponding to the boarding point information can be quickly determined. However, determining the search scenario based on AOI information is more accurate and objective.

[0036] In addition, it should be noted that in the embodiments of the present application, unless otherwise specified, "multiple", "plurality" and other quantities related to "multiple" all mean two or more.

[0037] Step S102: Based on the search scene and the boarding point information, determine the type of the area of ​​interest (AOI) that matches the search scene.

[0038] In an embodiment of the present application, after the travel subject inputs the boarding point information for search, a specific POI (Point Of Interest) is not directly determined as the recommended boarding point for the travel subject. Instead, a search scene is first determined, and then a corresponding AOI is determined based on the search scene. The AOI is used as a reference for subsequent processing. Because the AOI has more boarding point candidates to choose from, and the type of the AOI can be effectively matched with the search scene, the boarding points selected based on this subsequent processing will be more objective and reasonable.

[0039] In this step, after the search scene is determined, the type of the corresponding AOI is determined based on the search scene and the boarding point information, and the type of the AOI is adapted to the search scene.

[0040] In one feasible approach, this step can be implemented by obtaining at least one AOI corresponding to the boarding point indicated by the boarding point information; determining, from the at least one AOI, an AOI that matches the search scenario, and determining the type of the matching AOI. In this way, AOIs that do not match the search scenario can be filtered out, making AOI selection more accurate.

[0041] For example, when the search scenario is a business scenario, if there are two AOIs near the boarding point, one of which is a business type and the other is a residential type, the business type AOI will be determined as the AOI that matches the search scenario. Its type is business, such as an office building or an office area. For another example, when the search scenario is a transportation scenario, if there are three AOIs near the boarding point, one of which is a business type, one of which is a station type, and one of which is a road type, the AOIs that match the transportation scenario can include the station type AOI and the road type AOI. Which one is subsequently selected can be determined based on the location of the travel object and the recommendation strategy. If there is only one AOI, since the search scenario is determined based on the AOI information in the early stage, this AOI will usually also match the search scenario.

[0042] It should be noted that the search scene and the AOI type may not be completely consistent. For example, if the search scene is a leisure scene, the matching AOI type may be parks, theaters, shopping malls, etc., which are subtypes of the leisure category. For another example, if the search scene is a transportation scene, the matching AOI type may be stations, subway stations, roads, etc., which are subtypes of the transportation category.

[0043] Step S103: According to the type of the AOI, a recommendation strategy matching the type of the AOI is determined from a plurality of pre-stored boarding point recommendation strategies.

[0044] In this embodiment of the present application, the system pre-stores multiple boarding point recommendation strategies, as well as at least one boarding point recommendation strategy that is adaptable to each AOI type. Each AOI may have more than one adaptable boarding point recommendation strategy, for example, two or more. In this case, these two or more strategies may be used individually or in combination. The specific usage rules can be flexibly configured by those skilled in the art based on actual needs, and this embodiment of the present application does not impose any restrictions on this.

[0045] In one feasible method, multiple boarding point recommendation strategies include: a recommendation strategy based on the closest current location of the travel object, a recommendation strategy based on the road topology relationship corresponding to the current location of the travel object, a recommendation strategy based on the positional relationship between the current location of the travel object and the AOI, a recommendation strategy based on the travel object's preferences, and a recommendation strategy based on the frequency of boarding point selection, or some or all of them. Among them, the recommendation strategy based on the closest current location of the travel object is used to determine one or more candidate boarding points based on the boarding points searched by the travel object, and use the candidate boarding point closest to the current location of the travel object among the one or more candidate boarding points as the recommended boarding point; the recommendation strategy based on the road topology relationship corresponding to the current location of the travel object is used to determine one or more roads near the current location of the travel object, and recommend the boarding point based on the boarding point searched by the travel object and the topological relationship between the current location of the travel object and the one or more roads, such as whether it crosses the road, whether it is on the same side as the current location of the travel object, whether it is located at the intersection of a certain road, etc. Candidate boarding points; a recommendation strategy based on the positional relationship between the current location of the travel object and the AOI is used to recommend candidate boarding points based on the positional relationship between the current location of the travel object and the determined AOI, for example, whether it is located outside or inside the AOI, and the boarding point searched by the travel object; a recommendation strategy based on the preferences of the travel object is used to guide the recommendation of candidate boarding points based on the analysis and statistical results of the historical boarding point data of the travel object; a recommendation strategy based on the frequency of boarding point selection is used to determine the candidate boarding points that are frequently selected near the boarding point searched by the travel object based on the big data analysis results of a large number of travel objects for recommendation. In the above-mentioned multiple recommendation strategies, the current location of the travel object can be obtained in real time by the positioning system of the client used when searching for the travel object, which can be different from the boarding point searched by the travel object, or it can be the same as the boarding point.

[0046] Based on this, further optionally, this step can be implemented in one or more of the following ways:

[0047] Method 1: If the AOI type is a station type, the recommendation strategy matching the AOI type includes: a recommendation strategy based on proximity to the traveler's current location and / or a recommendation strategy based on the road topology corresponding to the traveler's current location. For station-type AOIs, in specific applications, the recommendation strategy based on proximity to the traveler's current location and the recommendation strategy based on the road topology corresponding to the traveler's current location can be used either or in combination. For example, if the AOI is a bus station, multiple bus station platforms can be determined based on the boarding point searched by the traveler, and the platform closest to the traveler's current location that does not cross the road can be recommended. For another example, if the AOI is a subway station, multiple subway entrances can be determined based on the boarding point searched by the traveler, and the subway entrance closest to the traveler's current location that does not cross the road can be recommended. However, those skilled in the art will appreciate that the recommendation strategies corresponding to station types are not limited to the above examples. Other strategies can be selected or combined, such as a recommendation strategy based on the traveler's preferences or a recommendation strategy based on the frequency of boarding point selection.

[0048] Method 2: If the AOI type is a road, the recommendation strategy that matches the AOI type includes: a recommendation strategy based on proximity to the traveler's current location and / or a recommendation strategy based on the frequency of boarding point selection. For example, if the AOI is a street, the point on this street closest to the traveler's current location (such as a POI, etc.) may be recommended; alternatively, based on the traveler's current location, several points on this street with a selection frequency greater than a certain threshold may be selected for recommendation, and so on. However, those skilled in the art will appreciate that the recommendation strategy corresponding to the station type is not limited to the above examples; other strategies may be selected or combined with other strategies, such as a recommendation strategy based on the traveler's preferences, etc.

[0049] Furthermore, when the AOI type is road, any recommendation strategy can take into account road congestion. This means avoiding congested roads, sections, or specific points will be avoided as much as possible. Congestion determination can be based on the current road congestion information contained in the AOI information.

[0050] Method 3: If the AOI type is a building type, the recommendation strategy that matches the AOI type includes: a recommendation strategy based on the positional relationship between the current location of the traveler and the AOI and / or a recommendation strategy based on the proximity of the current location of the traveler. For example, if the AOI is a large shopping mall, residential area, school, etc., it is possible to determine whether the traveler is currently inside or outside the AOI based on the current location of the traveler, obtain multiple candidate boarding points, and then recommend the candidate boarding point with the shortest distance based on the distance between the current location of the traveler and the multiple candidate boarding points. However, those skilled in the art should understand that the recommendation strategy corresponding to the station type is not limited to the above examples, and other strategies can also be selected or combined with other strategies, such as a recommendation strategy based on the traveler's preferences, a recommendation strategy based on the frequency of boarding point selection, and so on.

[0051] Method 4: If the AOI type is an outdoor location, the recommendation strategy matching the AOI type may include: a recommendation strategy based on proximity to the traveler's current location and / or a recommendation strategy based on the traveler's preferences. For example, if the AOI is a park, one or more park gates may be obtained based on the traveler's current location, and the closest gate or gates frequently chosen by the traveler may be recommended. However, those skilled in the art will appreciate that the recommendation strategy for station types is not limited to the examples above; other strategies may be selected or combined with other strategies, such as a recommendation strategy based on the frequency of boarding point selection.

[0052] As can be seen from the above, the correspondence between different types of AOIs and their corresponding recommended strategies can be preset. After the type of AOI is determined, it can be selected and used according to certain selection or combination rules.

[0053] Through the above methods, we can effectively implement different AOI types in different search scenarios and determine effective and reasonable recommendation strategies to facilitate the subsequent accurate and efficient recommendation of boarding points for travel objects.

[0054] Step S104: Determine the recommended boarding point based on the recommendation strategy, AOI information, and boarding point information.

[0055] As previously mentioned, once the recommendation strategy is determined, the recommended boarding points (recommended boarding points) are determined based on the AOI information and the boarding point information entered by the traveler. Furthermore, if more than one recommended boarding point is ultimately determined, to increase traveler participation, information for multiple recommended boarding points can be sent to the traveler's search client, allowing the traveler to select their own boarding point.

[0056] However, the present invention is not limited to this. In order to more accurately recommend a boarding point that meets the needs of travelers, in one feasible method, multiple candidate boarding points can be obtained based on the recommendation strategy, AOI information and boarding point information; the information of the multiple candidate boarding points is input into a deep learning network model for boarding point quality evaluation, and the recommended boarding point is determined based on the quality evaluation results output by the deep learning network model.

[0057] The deep learning network model may be a model obtained through training using training samples and capable of evaluating the quality of a boarding point based on information about the boarding point, including but not limited to a convolutional neural network (CNN) model, a decision tree (DT) model, a random forest (RF) model, a classification and logistic regression (LogisticRegression) model, an artificial neural network (ANN) model, etc. The quality evaluation result output by the deep learning network model may comprehensively represent the degree to which the boarding point is likely to be accepted and recognized by the traveler, for example, it may be a probability of being selected, or a score that comprehensively considers information such as the frequency of selection, the distance from the traveler's current location, and road conditions (such as whether there is congestion, whether it is on the same side as the traveler's current location, whether it is within a relatively close distance to the traveler's current location, etc.).

[0058] Furthermore, after determining the recommended boarding point, the name of the recommended boarding point can optionally be modified based on the name of the boarding point searched by the traveler. A search result is generated based on the modified result and sent to the client used to search for the traveler. For example, if the distance between the recommended boarding point and the searched boarding point is within a preset distance range, the name of the recommended boarding point is modified to the name of the searched boarding point. Alternatively, if the distance between the recommended boarding point and the searched boarding point is outside the preset distance range, the name of the recommended boarding point is modified based on the directional relationship between the recommended boarding point and the searched boarding point. This can significantly enhance the traveler's search and travel experience.

[0059] The preset distance range is a relatively close distance to the boarding point being searched by the traveler, such as within 1-5 meters, and can be appropriately set by those skilled in the art based on actual needs. For example, if the boarding point being searched is named A, the name of the recommended boarding point A1' can be modified to the name of the boarding point being searched; or, if the recommended boarding point is a certain distance away from the boarding point being searched and is located to the north of the boarding point being searched, the name of the recommended boarding point A2' can be modified to "North of A," etc.

[0060] It should be noted that, in this embodiment, the name modification is performed by the server as an example, but in actual application, the name modification operation can also be implemented by the client used for searching the travel object.

[0061] In addition, it should be noted that in the embodiment of the present application, although the boarding point recommendation is mainly based on the AOI, in actual application, it is possible that the boarding point searched by the travel subject happens to be a certain POI. In this case, in order to improve the recommendation speed, if the boarding point information input by the travel subject indicates that the boarding point is a POI, the recommended boarding point can be determined from at least one candidate boarding point corresponding to the POI; or at least one boarding point within a preset distance range from the POI with a selection frequency higher than the preset frequency is determined as a candidate boarding point, and the recommended boarding point is determined from the candidate boarding points. Among them, the preset distance range and the preset frequency can be flexibly set by those skilled in the art according to actual conditions, and the embodiment of the present application does not limit this.

[0062] Among them, when determining the recommended boarding point from at least one candidate boarding point corresponding to the POI, the recommended boarding point can be determined based on the principle of being closest to the current location of the travel object, or based on the travel object's preference principle, or based on the principle of the highest frequency of boarding point selection.

[0063] The following is an example of a scenario to illustrate the above process. Figure 2 shown.

[0064] Figure 2 A schematic diagram of an application scenario provided in an embodiment of the present application is provided. Figure 2 In the example, the travel subject inputs the boarding point information on its client, which is shown as searching for "XX Coffee Shop". Based on the input, the client sends a search request to the server, which carries the information of "XX Coffee Shop". After receiving the search request, the server determines that its search scene is a leisure scene based on "XX Coffee Shop" (the specific determination process can be found in the above description). Assuming that there are "Mall A", "Community B" and "School C" near "XX Coffee Shop", the server will determine "Mall A" as the AOI corresponding to the leisure scene based on the determined leisure scene and "XX Coffee Shop", and the type of this AOI is leisure-mall building. Further, it is assumed that the recommendation strategy corresponding to the type of this AOI is a recommendation strategy based on the positional relationship between the current position of the travel subject and the AOI and a recommendation strategy based on the proximity of the current position of the travel subject. Based on this recommendation strategy, the North Gate 1 and North Gate 2 of "Mall A" are selected as candidate boarding points. Furthermore, if the current location of the passenger is closer to North Gate 1, then based on the recommendation strategy based on the passenger's current location being closest, North Gate 1 will be selected as the final recommended boarding point from North Gate 1 and North Gate 2. The recommended boarding point information is then fed back to the client.

[0065] This enables more accurate and reasonable boarding point recommendations.

[0066] Hereinafter, another specific example will be used to illustrate the method for recommending boarding points in the embodiment of the present application. Figure 3 It includes:

[0067] Step S301: Based on pre-stored POI and AOI data resources, a search is performed according to the boarding point information of the travel object and the current location of the travel object.

[0068] Step S302: Obtain the search result, that is, the POI information or AOI information corresponding to the boarding point information.

[0069] Step S303: Determine whether it is an AOI. If not, proceed to step S304; if it is an AOI, proceed to step S305.

[0070] Step S304: For a POI, search for candidate boarding points near the POI that are selected with high frequency. Then, execute step S307.

[0071] Among them, near the POI means within a preset distance range from the POI, and high selection frequency means that the selection frequency meets a certain frequency threshold. Among them, the preset distance range and frequency threshold can be flexibly set by those skilled in the art according to actual needs.

[0072] Step S305 : For the AOI, determine a search scenario according to the AOI information, and determine matching AOIs and their types based on the search scenario.

[0073] In this example, the process of determining the search scenario is not described in detail, and the relevant implementation can refer to the description in the above embodiment. Figure 3 In the figure, "bus station" and "subway station" are used to represent station-type AOIs, "street" is used to represent road-type AOIs, and "shopping mall / community / school" are used to represent leisure / residential / public institution-type AOIs. These AOIs all involve physical buildings and can be adapted to the same or similar recommendation strategies. For simplicity, Figure 3 The merger is explained in the .

[0074] Step S306: Determine a matching boarding point recommendation strategy based on the AOI type, and obtain candidate boarding points.

[0075] For example:

[0076] (1) For bus stop types, the corresponding recommendation strategy can be to determine the multiple bus stops corresponding to the bus stop and select the bus stop that is close to the travel target and does not cross the road as the candidate boarding point;

[0077] (2) For the subway station type, the corresponding recommendation strategy can be to determine the multiple subway entrances corresponding to the subway station and select the subway entrance that is close to the travel target and does not cross the road as the candidate boarding point;

[0078] (3) For street types, the corresponding recommendation strategy can be to determine the candidate boarding point on the street that is closest to the travel object, and then select candidate boarding points within a certain distance range of the candidate boarding point and with a frequency greater than a frequency threshold;

[0079] (4) For shopping malls, residential areas, and schools, the corresponding recommendation strategy can be: determine whether the traveler is inside or outside the AOI based on the traveler's current location, and based on this, filter out candidate boarding points that are closer to the traveler. Optionally, the candidate boarding points can be further filtered from multiple candidate boarding points based on the similarity between the names of the candidate boarding points and the searched boarding points for the traveler and the traveler's current location to determine the final candidate boarding point.

[0080] Step S307: Obtain model recommendation points.

[0081] While the recommendation strategy can select relatively accurate candidate boarding points, to further improve recommendation accuracy, this example also uses a model for selecting candidate boarding points to generate model-generated candidate boarding points as a supplement to the candidate boarding points determined by the recommendation strategy. This model can be a deep learning network model, such as a CNN model, that takes boarding point information and the user's current location as input and outputs candidate boarding points. This model is trained using large data samples, and its outputted candidate boarding points are likely to be accepted by the majority of users with a high probability.

[0082] Step S308: Obtain the preferred boarding point of the travel subject.

[0083] For a certain travel object, he may often travel at or near a certain boarding point. Therefore, based on his historical travel data, his historical data of searching for a certain boarding point can be determined, and the boarding point he finally selected when searching based on the boarding point can be obtained as a candidate boarding point.

[0084] Step S309: Determine a recommended boarding point based on the candidate boarding points.

[0085] For example, the comprehensive quality of the multiple candidate boarding points obtained by the above-mentioned methods can be comprehensively considered based on the selection frequency of the multiple candidate boarding points, the distance between them and the current location of the travel object, the road congestion situation, etc. to determine the final recommended boarding point.

[0086] Step S310: Modify the name of the recommended boarding point based on the name of the boarding point searched by the travel object.

[0087] For example, the recommended boarding point that is closer to the searched boarding point will have its name changed to the searched boarding point name; the point that is slightly farther away from the searched boarding point will have its name changed to a certain side or direction of the searched boarding point name, etc.

[0088] According to the boarding point recommendation method provided in this embodiment, when a traveler wishes to select a boarding point, the current search scenario of the traveler is determined based on the boarding point information. Based on this search scenario and the boarding point information, the type of AOI corresponding to the boarding point is determined. A recommendation strategy is then determined based on the AOI type, and the corresponding boarding point is then recommended. Because the search scenario better reflects the traveler's current state and environment, it can more effectively determine the AOI type that matches the search scenario. Compared to using POIs as a reference, using AOIs provides a wider range of boarding point candidates, making the resulting boarding point selection more objective and reasonable. Because different AOI types may be adapted to different recommendation strategies, resulting in different recommendation efficiency and effectiveness, a recommendation strategy tailored to the AOI type can be determined to achieve efficient, reasonable, and accurate boarding point recommendations.

[0089] It can be seen that through this embodiment, the accuracy and rationality of boarding point positioning can be effectively improved when travelers search for boarding points by themselves, thereby improving the travel experience of travelers.

[0090] The boarding point recommendation method of the embodiment of the present application can be executed by any appropriate electronic device with data processing capabilities, including but not limited to: a server, a PC, and even a high-performance mobile terminal.

[0091] Example 2

[0092] Another method for recommending boarding points provided in the second embodiment of the present application is as follows: Figure 4 As shown, the boarding point recommendation method is described from the client's perspective, which includes the following steps:

[0093] Step S401: Receive boarding point information input by a travel subject through a travel navigation interface.

[0094] For general travel navigation applications, a corresponding interface is provided for travelers to search for boarding points when needed. Based on this, after the traveler enters the boarding point information through the interface, it can be received by the client of the travel navigation application.

[0095] Step S402: Generate a search request based on the boarding point information and send it to the travel service end.

[0096] After receiving the boarding point information, the client generates a corresponding search request, carries the boarding point information in the search request, and sends it to the travel service end.

[0097] Step S403: Receive information of a recommended boarding point determined based on the boarding point information, which is returned by the travel service end in response to the search request.

[0098] In this step, the travel service end may determine the recommended boarding point based on the boarding point recommendation method described in the aforementioned embodiment 1, and send the information to the client.

[0099] Step S404: updating the electronic map in the travel navigation interface according to the information of the recommended boarding point, and marking the location of the recommended boarding point in the updated electronic map.

[0100] To facilitate object identification, travel navigation apps often display recommended boarding points based on the electronic map displayed within the interface. Therefore, after receiving the recommended boarding point information returned in response to a search request, the client typically re-renders the electronic map within the travel navigation interface to display the recommended boarding points.

[0101] Optionally, in this embodiment, the client can modify the name of the recommended boarding point. In this case, the server can directly send the recommended boarding point information to the client. The client obtains the name of the boarding point from the boarding point information and modifies the name of the recommended boarding point based on the boarding point name, for example, directly using the boarding point name or using the boarding point name plus a directional word. Furthermore, the location of the recommended boarding point is marked on the updated electronic map, and the modified name of the recommended boarding point is displayed.

[0102] It can be seen that through this embodiment, accurate and reasonable recommended boarding points can be provided to travelers, and the names of the recommended boarding points can be modified to names that are easier for travelers to understand, greatly improving the travel experience of travelers.

[0103] Example 3:

[0104] Based on any of the boarding point recommendation methods described in the above embodiments 1 to 2, the present embodiment provides an electronic device. It should be noted that the boarding point recommendation method of the present embodiment can be executed by any appropriate electronic device with the ability to recommend boarding points, including but not limited to: servers, mobile terminals (such as mobile phones, PADs, etc.) and PCs, etc. Figure 5 As shown, Figure 5This is a block diagram of an electronic device provided in an embodiment of the present application. The specific embodiments of the present application do not limit the specific implementation of the electronic device. The electronic device 50 may include: a processor 502, a communications interface 504, a memory 506, and a communication bus 508.

[0105] The processor 502 , the communication interface 504 , and the memory 506 communicate with each other via a communication bus 508 .

[0106] The communication interface 504 is used to communicate with other electronic devices or servers.

[0107] The processor 502 is configured to execute the computer program 510 , and specifically may execute the relevant steps in any of the above-mentioned embodiments of the method for recommending a boarding point.

[0108] Specifically, the computer program 510 may include computer program codes including computer operating instructions.

[0109] The processor 502 may be a CPU, an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application. The one or more processors included in the smart device may be processors of the same type, such as one or more CPUs, or may be processors of different types, such as one or more CPUs and one or more ASICs.

[0110] The memory 506 is used to store the computer program 510. The memory 506 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0111] The specific implementation of each step in procedure 510 can be found in the corresponding descriptions of the corresponding steps and units in any of the aforementioned embodiments of the boarding point recommendation method, and will not be repeated here. Those skilled in the art will clearly understand that for ease and brevity of description, the specific operating processes of the devices and modules described above can be referenced to the corresponding process descriptions in the aforementioned method embodiments, and will not be repeated here.

[0112] Based on the boarding point recommendation method described in the above-mentioned embodiments 1 to 2, an embodiment of the present application provides a computer storage medium, which stores a computer program. When the computer program is executed by a processor, it implements any of the boarding point recommendation methods described in embodiments 1 to 2.

[0113] It should be pointed out that, according to the needs of implementation, the various components / steps described in the embodiments of the present application can be split into more components / steps, or two or more components / steps or partial operations of components / steps can be combined into new components / steps to achieve the purpose of the embodiments of the present application.

[0114] The above-described methods according to the embodiments of the present application can be implemented in hardware, firmware, or as software or computer code that can be stored in a recording medium (such as a CD ROM, RAM, floppy disk, hard disk, or magneto-optical disk), or as computer code originally stored in a remote recording medium or non-transitory machine-readable medium downloaded via a network and then stored in a local recording medium. Thus, the methods described herein can be stored in such software processing on a recording medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware (such as an ASIC or FPGA). It is understood that a computer, processor, microprocessor controller, or programmable hardware includes a storage component (e.g., RAM, ROM, flash memory, etc.) that can store or receive software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the boarding point recommendation method described herein is implemented. In addition, when a general-purpose computer accesses the code for implementing the boarding point recommendation method shown herein, the execution of the code converts the general-purpose computer into a dedicated computer for executing the boarding point recommendation method shown herein.

[0115] Those skilled in the art will appreciate that the various exemplary units and method steps described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the embodiments of this application.

[0116] The above implementation methods are only used to illustrate the embodiments of the present application, and are not intended to limit the embodiments of the present application. Ordinary technicians in the relevant technical field can make various changes and modifications without departing from the spirit and scope of the embodiments of the present application. Therefore, all equivalent technical solutions also fall within the scope of the embodiments of the present application, and the scope of patent protection of the embodiments of the present application should be defined by the claims.

Claims

1. A method for recommending a boarding point, comprising: Obtaining boarding point information for a travel object search, and determining a search scenario for the search based on the boarding point information; Determining a type of an area of ​​interest (AOI) matching the search scene based on the search scene and the boarding point information; Determining, according to the type of the AOI, a recommendation strategy that matches the type of the AOI from a plurality of pre-stored boarding point recommendation strategies; A recommended boarding point is determined according to the recommendation strategy, the AOI information, and the boarding point information.

2. The method according to claim 1, wherein The determining of the search scenario according to the boarding point information includes: According to the boarding point information, obtain information about the AOI where the boarding point is located or information about the AOI within a preset distance range from the boarding point; The search scene of the search is determined according to the acquired AOI information.

3. The method according to claim 2, wherein: The determining of the search scenario according to the acquired AOI information includes at least one of the following: If the AOI information indicates that the AOI is a traffic-related AOI, determining that the search scene is a traffic scene; If the AOI information indicates that the AOI is a business AOI, determining that the search scenario is a business scenario; If the information of the AOI indicates that the AOI is a leisure AOI, determining that the search scene is a leisure scene; If the AOI information indicates that the AOI is a residential AOI, determining that the search scene is a residential scene; If the information of the AOI indicates that the AOI is a public institution AOI, it is determined that the search scene is a public institution scene.

4. The method according to claim 2 or 3, wherein: The determining, based on the search scene and the boarding point information, a type of an area of ​​interest (AOI) matching the search scene includes: Acquire at least one AOI corresponding to the boarding point indicated by the boarding point information; An AOI matching the search scene is determined from the at least one AOI, and a type of the matching AOI is determined.

5. The method according to claim 1, wherein The multiple boarding point recommendation strategies include: a recommendation strategy based on the closest current location of the travel object, a recommendation strategy based on the road topology relationship corresponding to the current location of the travel object, a recommendation strategy based on the positional relationship between the current location of the travel object and the AOI, a recommendation strategy based on the travel object's preferences, and some or all of the recommendation strategies based on the frequency of boarding point selection.

6. The method according to claim 5, wherein: Determining, based on the type of the AOI, a recommendation strategy matching the type of the AOI from a plurality of pre-stored boarding point recommendation strategies includes at least one of the following: If the type of the AOI is a station type, determining a recommendation strategy that matches the type of the AOI includes: a recommendation strategy based on a location closest to the current location of the travel object and / or a recommendation strategy based on a road topology relationship corresponding to the current location of the travel object; If the type of the AOI is a road type, determining a recommendation strategy that matches the type of the AOI includes: a recommendation strategy based on the closest current location of the travel object and / or a recommendation strategy based on the frequency of boarding point selection; If the type of the AOI is a building type, determining a recommendation strategy that matches the type of the AOI includes: a recommendation strategy based on a positional relationship between the current location of the travel object and the AOI and / or a recommendation strategy based on the proximity of the current location of the travel object; If the type of the AOI is an outdoor location type, determining a recommendation strategy that matches the type of the AOI includes: a recommendation strategy based on the closest current location of the travel object and / or a recommendation strategy based on the travel object's preference.

7. The method according to claim 1, wherein The determining of a recommended boarding point according to the recommendation strategy, the AOI information, and the boarding point information includes: Acquire multiple candidate boarding points according to the recommendation strategy, the AOI information, and the boarding point information; The information of the plurality of candidate boarding points is input into a deep learning network model for boarding point quality evaluation, and a recommended boarding point is determined based on a quality evaluation result output by the deep learning network model.

8. The method according to claim 1, wherein After determining the recommended boarding point, the method further includes: Modify the name of the determined recommended boarding point according to the name of the boarding point searched by the travel object; A search result is generated based on the modification result and sent to a client used for searching the travel object.

9. The method according to claim 8, wherein The step of modifying the name of the determined recommended boarding point according to the name of the boarding point searched for by the travel object includes: If the distance between the recommended boarding point and the searched boarding point is within a preset distance range, the name of the recommended boarding point is changed to the name of the searched boarding point; or, If the distance between the recommended boarding point and the searched boarding point exceeds the preset distance range, the name of the recommended boarding point is modified according to the directional relationship between the recommended boarding point and the searched boarding point.

10. The method according to claim 1, wherein The method further comprises: If the boarding point indicated by the boarding point information is a point of interest (POI); A recommended boarding point is determined from at least one candidate boarding point corresponding to the POI; or, at least one boarding point within a preset distance range from the POI with a selection frequency higher than a preset frequency is determined as a candidate boarding point, and a recommended boarding point is determined from the candidate boarding points.

11. A method for recommending a boarding point, comprising: Receive boarding point information input by the travel object through the travel navigation interface; Generate a search request based on the boarding point information and send it to the travel service end; receiving information of a recommended boarding point determined based on the boarding point information and returned by the travel service end in response to the search request; wherein the information of the recommended boarding point is determined by the travel service end according to the boarding point recommendation method according to any one of claims 1-10; The electronic map in the travel navigation interface is updated according to the information of the recommended boarding point, and the location of the recommended boarding point is marked on the updated electronic map.

12. The method according to claim 11, wherein The step of marking the location of the recommended boarding point on the updated electronic map includes: Obtaining a name of the boarding point from the boarding point information, and modifying the name of the recommended boarding point according to the name of the boarding point; The location of the recommended boarding point is marked on the updated electronic map, and the name of the recommended boarding point after the name change is displayed.

13. A computer storage medium having a computer program stored thereon, wherein when the program is executed by a processor, the method for recommending a boarding point according to any one of claims 1 to 12 is implemented.

Images