Point location recommendation method and device, electronic equipment and computer readable storage medium

Abstract

The embodiment of the invention discloses a point location recommendation method and device, electronic equipment and a computer readable storage medium. The method comprises the steps that a travel request of a user is received; in response to the condition that a riding point in the travel request is a highway section point location, recalling a point location recommendation list, the point location recommendation list comprising at least one candidate point location, the candidate point location being a highway section point location or a non-highway section point location, candidate point locations of expressway section point locations in the point location recommendation list are determined based on historical get-off point locations of expressway sections; and the point location recommendation list is transmitted to the user, so that the point location recommendation effect can be optimized, and the driver and passenger experience is improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a point recommendation method, device, electronic device and computer-readable storage medium. Background Art

[0002] In the current online car-hailing scenario, when users enter highway toll stations and other highway sections as boarding points, they are usually recalled and recommended based on the available points on non-highway sections near the boarding points. If the user does not obtain the stop information near the highway toll station in advance when placing the order, or the user does not communicate with the driver to confirm a reasonable boarding point when placing the order, it will easily lead to problems such as detours in the pick-up distance and failure to deliver the vehicle smoothly, as well as safety hazards. This will cause unnecessary waste of time and money for both the driver and passengers, and affect the driver and passenger experience.

[0003] Therefore, it is necessary to optimize the location recommendation method of the boarding point in a targeted manner to deliver passengers safely, efficiently and accurately, thereby improving the driver and passenger experience. Summary of the invention

[0004] In view of this, an object of the embodiments of the present invention is to provide a point recommendation method, device, electronic device and computer-readable storage medium to optimize the point recommendation effect and enhance the driver and passenger experience.

[0005] In a first aspect, an embodiment of the present invention is to provide a method for recommending a point, the method comprising:

[0006] Receive travel requests from users;

[0007] In response to the boarding point in the travel request being a highway section point, recalling a point recommendation list, the point recommendation list including at least one candidate point, the candidate point being a highway section point or a non-highway section point, the candidate point in the point recommendation list being a highway section point being determined based on historical alighting points of the highway section;

[0008] The recommended list of points is presented to the user.

[0009] Furthermore, the method further comprises:

[0010] Acquire at least one historical stop information on the expressway section, wherein the historical stop information includes a get-off point;

[0011] Determine the alighting point as an available point;

[0012] The available points are added to a global point library, so as to make point recommendations based on the global point library.

[0013] Further, determining the alighting point as an available point includes:

[0014] Acquire an environmental image of the alighting point;

[0015] Verifying the alighting point based on the environmental image and determining a verification result;

[0016] In response to the verification result indicating that the alighting point is available, the alighting point is determined to be an available point.

[0017] Further, the step of verifying the alighting point based on the environmental image and determining the verification result includes:

[0018] Identify a landmark in the environment image, where the landmark includes at least one of a traffic sign, a specific environmental feature, and an auxiliary facility;

[0019] In response to identifying the landmark, determining that a corresponding drop-off point is available;

[0020] In response to not identifying the landmark, it is determined that the corresponding drop-off point is unavailable.

[0021] Furthermore, the method further comprises:

[0022] In response to the candidate point selected by the user being a highway point, prompt information of the candidate point is displayed, where the prompt information is used to prompt that there is a safety risk at the candidate point.

[0023] Furthermore, the recall point recommendation list includes:

[0024] Determine the target geographical range corresponding to the boarding point;

[0025] Recalling the expressway section points and non-expressway section points within the target geographical range and determining the recall results;

[0026] A list of recommended locations is determined based on the recall results.

[0027] Furthermore, determining a recommended list of points according to the recall result includes:

[0028] Sorting the candidate points in the recall result based on a preset sorting model to determine a sorting result;

[0029] Generate a point recommendation list based on a preset number of candidate points in the sorting results.

[0030] Furthermore, the method further comprises:

[0031] The name of the boarding point is identified, and the type of the boarding point is determined, where the type of the boarding point is a high-speed road section point or a non-high-speed road section point.

[0032] Furthermore, the step of displaying the recommended point list to the user includes:

[0033] The candidate points that are highway section points in the point recommendation list are preferentially displayed to the user.

[0034] In a second aspect, an embodiment of the present invention is intended to provide a point recommendation device, the device comprising:

[0035] A trigger unit, used for receiving a user's travel request;

[0036] a recommendation unit, configured to, in response to the boarding point in the travel request being a highway section point, recall a point recommendation list, wherein the point recommendation list includes at least one candidate point, wherein the candidate point is a highway section point or a non-highway section point, and the candidate point in the point recommendation list that is a highway section point is determined based on historical alighting points of the highway section;

[0037] The display unit is used to display the recommended point list to the user.

[0038] In a third aspect, an embodiment of the present invention aims to provide a computer program product, wherein the computer program product comprises a computer program / instructions, and when the computer program / instructions are executed by a processor, the method as described in any one of the above items is implemented.

[0039] In a fourth aspect, an embodiment of the present invention aims to provide an electronic device, comprising a memory and a processor, wherein the memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement a method as described in any one of the above items.

[0040] In a fifth aspect, an embodiment of the present invention aims to provide a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method as described in any one of the above items is implemented.

[0041] The technical solution of the embodiment of the present invention can recommend both highway section points and non-highway section points to users and optimize the point recommendation effect by recalling a point recommendation list including highway section points and non-highway section points when the boarding point in the user's travel request is a highway section point, and showing the point recommendation list to the user, so as to facilitate users to select suitable points from the recommended points as boarding points and improve the driver and passenger experience. In addition, since the candidate points for highway section points in the point recommendation list are determined based on the historical get-off points of the highway section, the highway section points recommended to the user are more in line with the actual travel situation, which can further optimize the point recommendation effect and improve the driver and passenger experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The above and other objects, features and advantages of the present invention will become more apparent through the following description of the embodiments of the present invention with reference to the accompanying drawings, in which:

[0043] Figure 1 It is a schematic diagram of the recommended points in the prior art;

[0044] Figure 2 is a flow chart of a point recommendation method according to an embodiment of the present invention;

[0045] Figure 3 is a flow chart of a recall point recommendation list according to an embodiment of the present invention;

[0046] Figure 4 is a flow chart of determining available points in a global point library according to an embodiment of the present invention;

[0047] Figure 5 is a flow chart of determining available points according to an embodiment of the present invention;

[0048] Figure 6 is a flow chart of determining a recommended point list according to an embodiment of the present invention;

[0049] Figure 7 is a schematic diagram of displaying prompt information according to an embodiment of the present invention;

[0050] Figure 8 is a schematic diagram of a point recommendation process according to an embodiment of the present invention;

[0051] Fig. 9 is a schematic diagram of a point recommendation device according to an embodiment of the present invention;

[0052] Fig.10 is a schematic diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0053] The present application is described below based on embodiments, but the present application is not limited to these embodiments. In the detailed description of the present application below, some specific details are described in detail. It is possible for those skilled in the art to fully understand the present application without the description of these details. In order to avoid confusing the essence of the present application, known methods, processes, flows, components and circuits are not described in detail.

[0054] In addition, persons of ordinary skill in the art will appreciate that the drawings provided herein are for illustration purposes and are not necessarily drawn to scale.

[0055] Unless the context clearly requires otherwise, the words "include", "comprising" and similar words throughout the application should be interpreted as including rather than exclusive or exhaustive; that is, the meaning is "including but not limited to".

[0056] In the description of this application, it should be understood that the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of this application, unless otherwise specified, the meaning of "plurality" is two or more.

[0057] The solutions described in this specification and the embodiments, if they involve information acquisition, will collect data on the premise of legality and compliance, ensure the legitimacy of the data source, and take appropriate technical and management measures to ensure data security. If it involves the processing of personal information, it will be processed on the premise of having a legal basis (such as obtaining the consent of the subject of personal information, or it is necessary for the performance of a contract, etc.), and will only be processed within the prescribed or agreed scope. The user's refusal to process personal information other than the necessary information required for basic functions will not affect the user's use of basic functions.

[0058] In this embodiment, the point recommendation method is described by taking the boarding point as the alighting point and the expressway point corresponding to the boarding point as the expressway toll station as an example. However, it should be understood that the point recommendation method in this embodiment can also be applied to the point recommendation process when the boarding point is the boarding point or the waypoint, and the boarding point is other types of expressway points, such as expressway service areas, expressway temporary parking areas, etc., and the application scenario of the method is not limited here.

[0059] In real life, highway toll stations usually generate travel needs due to commuting, appointment exemptions, etc. If the location recommendations are unreasonable, it is easy to cause problems and safety hazards such as detours and failure to deliver the passengers smoothly, which will cause unnecessary waste of time and money for both drivers and passengers and affect the driver and passenger experience.

[0060] Figure 1 It is a schematic diagram of the recommended points in the prior art. Figure 1 As shown in the figure, assuming that the user inputs the drop-off point as expressway toll station A, the recommended point determined based on the input drop-off point is B, and the recommended point B is located on a non-expressway section near expressway toll station A. After the driver sends the user to the recommended point B along route L1, the user still cannot reach expressway toll station A smoothly. At this time, the driver needs to turn back and send the user from the recommended point B to the stop position C near expressway toll station A along the new navigation route L2, which will result in a relatively long detour distance, resulting in a poor driver and passenger experience.

[0061] In view of this, an embodiment of the present invention aims to provide a point recommendation method, so that when the user's boarding point is a highway point, the available stopping locations near the highway point can be directly recommended to the user, thereby optimizing the point recommendation effect, facilitating the user to quickly reach the expected boarding point, and improving the driver and passenger experience.

[0062] Figure 2FIG. 1 is a flow chart of a method for recommending a point in an embodiment of the present invention. Figure 2 As shown, in this embodiment, point recommendation is achieved through the following method.

[0063] In step S210 , a travel request from a user is received.

[0064] In this embodiment, the user initiates a travel request through a terminal device. The travel request includes travel-related information such as a boarding point. The boarding point may be a boarding point, an alighting point, a passing point, etc.

[0065] Optionally, the boarding point in the user's travel request may be a point entered by the user in the search box on the order issuance page, or may be a point selected by the user from historical boarding point records.

[0066] Further optionally, in this embodiment, the boarding point in the user's travel request can be obtained by any of the following methods, for example, receiving the boarding point indicated by text, voice, image, etc. directly input by the user; or receiving the boarding point input by the user by interacting with presented text, voice, image, etc. options; or other means of implementing user input using existing technologies or future technologies, which are not limited in this embodiment.

[0067] Furthermore, after receiving the user's travel request, this embodiment will identify the type of boarding point in the travel request to determine whether to trigger the recommendation of expressway points. Specifically, in this embodiment, when the type of the boarding point is determined to be an expressway point, the recommendation of the expressway point is triggered; and when the type of the boarding point is determined to be a non-expressway point, the recommendation of the expressway point is not triggered, and only the recommendation of the non-expressway point is triggered, that is, the point recommendation is performed based on the conventional point recommendation process. Therefore, in this embodiment, it is possible to flexibly select a suitable point recommendation method according to the type of the boarding point, thereby optimizing the point recommendation effect, and making the recommended points more in line with user needs, thereby improving the user experience.

[0068] Optionally, in this embodiment, it is possible to determine whether the type of the boarding point is a highway section point based on keywords in the boarding point in the travel request and / or the geographical information of the boarding point.

[0069] When determining the type of the boarding point through the keywords of the boarding point, the keywords of the boarding point can be matched with the highway section keywords (such as toll station) in the preset vocabulary. If the keywords of the boarding point are in the preset vocabulary, the type of the boarding point is determined to be a highway section point; when the keywords of the boarding point are not in the preset vocabulary, it is determined that the type of the boarding point is not a highway section point, that is, the type of the boarding point is a non-highway section point.

[0070] When determining the type of the boarding point through the geographical information of the boarding point, the geographic information system (GIS) technology can be used to match the latitude and longitude information of the boarding point with the location information of the highway section point on the map. If the match is successful, the type of the boarding point is determined to be a highway section point; if the match is unsuccessful, the type of the boarding point is determined to be a non-highway section point.

[0071] Furthermore, in this embodiment, it is considered that the boarding point usually has a corresponding name, such as the boarding point is xx expressway toll station, and the keywords in the name can reflect the type of the boarding point. Therefore, in this embodiment, after receiving the user's travel request, the name of the boarding point will be identified to determine the type of the boarding point. Specifically, in this embodiment, the keywords in the name of the boarding point can be automatically extracted and identified based on models such as deep learning and natural language processing through keyword recognition technology, and the identified keywords can be matched with the expressway section keywords (such as toll station) in the preset word library. When the expressway section keywords consistent with the boarding point keywords are matched in the preset word library, that is, the keywords of the boarding point are located in the preset word library, the type of the boarding point is determined to be an expressway section point; and when the expressway section keywords consistent with the boarding point keywords are not matched in the preset word library, that is, the keywords of the boarding point are not located in the preset word library, the type of the boarding point is determined to be a non-expressway section point. Therefore, in this embodiment, the type of the boarding point can be determined by automatically identifying the boarding point, so as to trigger the corresponding point recommendation process based on the type of the boarding point.

[0072] In step S220, in response to the boarding point in the travel request being a highway section point, a point recommendation list is recalled. The point recommendation list includes at least one candidate point, the candidate point is a highway section point or a non-highway section point, and the candidate point in the point recommendation list that is a highway section point is determined based on the historical get-off points of the highway section.

[0073] In this embodiment, when the boarding point in the travel request is a highway section point, the highway section points and non-highway section points will be recalled at the same time to recall the point recommendation list corresponding to the boarding point.

[0074] Optionally, in this embodiment, by Figure 3 The method shown recalls the recommended list of points, and specifically includes the following steps.

[0075] In step S310, the target geographical range corresponding to the boarding point is determined.

[0076] In this embodiment, in order to facilitate users to quickly reach their desired location, the points recommended to users are all points within a certain range from the boarding point. The target geographic range is used to represent the maximum geographic range covered by the recommended points when recommending points based on the boarding point.

[0077] At the same time, considering that different boarding points have different recommendation factors such as location, surrounding environment, traffic conditions, and recommendation purpose, for example, when the boarding point is located in a busy area, the maximum geographical range covered by the recommended points is relatively small; while for those located in remote areas, the maximum geographical range covered by the recommended points is relatively large. Therefore, in this embodiment, when recalling the list of recommended points, the target geographical range corresponding to the boarding point will be determined first.

[0078] In step S320, the highway section points and non-highway section points within the target geographical range are recalled to determine the recall result.

[0079] In this embodiment, the process of recalling the highway section points and non-highway section points within the target geographical range is the process of querying all available points within the target geographical range from the global point library. Among them, the global point library is a database that stores a large number of available points and related information of each available point (such as location information, heat value, etc.). The available points stored in the global point library include highway section points and non-highway section points. The highway section points include toll stations (i.e. places located at the entrances and exits of highways or specific sections where tolls are collected), service areas (i.e. places on highways that provide rest and supply services), interchanges (i.e. places where highways intersect with other roads), temporary parking areas (i.e. places on both sides of highways or specific sections where vehicles are temporarily parked), and other available parking locations on sections near highways. Non-highway section points include available parking locations on non-highway roads such as intersections, bus stops, school gates, and community gates that are far away from highways. Therefore, in this embodiment, the available stop locations of highway section points and non-highway section point types are stored in the global point library, which can easily query the recommended points matching the boarding points from the global point library to realize point recommendation.

[0080] Optionally, in order to improve the efficiency of point recommendation, the global point library used in the present embodiment for point recommendation is a pre-established database. At the same time, the highway section points in the global point library are available points (i.e., available parking positions) determined in advance based on vehicle parking information on different highway sections.

[0081] In an optional implementation, in this embodiment, Figure 4 The method shown determines the available points in the global point library that are points on a highway section, and specifically includes the following steps.

[0082] In step S410, at least one historical stop information on the expressway section is obtained, and the historical stop information includes a get-off point.

[0083] In this embodiment, the alighting point in the historical stop information on the expressway section is an available stop location on the adjacent expressway section, such as a stop area before entering a toll station, a parking lot in a service area, and other areas where you can stop.

[0084] In step S420, the alighting point is determined as an available point.

[0085] Optionally, since the alighting point is a location where a stop actually occurred, in this embodiment, the alighting point in the historical stop information can be directly determined as an available point.

[0086] Alternatively, considering that stopping at the alighting point is somewhat random, in this embodiment, the alighting points in the historical stopping information will be verified first, and the alighting points that pass the verification will be determined as available points, so as to further improve the reliability of the available points, thereby facilitating the subsequent recommendation of universally available points to users.

[0087] Figure 5 is a flow chart of determining available points according to an embodiment of the present invention. Figure 5 As shown, in this embodiment, the available points are determined by the following method.

[0088] In step S510, an environmental image of the alighting point is acquired.

[0089] In this embodiment, the environmental image of the alighting point may be an environmental image within a predetermined range of the highway section acquired by a high-speed image acquisition system, a ground monitoring camera, a satellite remote sensing image, or the like.

[0090] In step S520, the alighting point is verified based on the environment image and a verification result is determined.

[0091] In this embodiment, considering that the parking area of ​​the expressway usually has obvious traffic signs, environmental features, auxiliary facilities, etc., the get-off point can be verified by identifying the signs in the environmental image.

[0092] Optionally, the landmarks include at least one of traffic signs (including parking signs - such as a stop sign with the letter "P" or a specific pattern, boundary lines of parking areas, parking space lines, etc.), specific environmental features (such as green belts, isolation fences, street lights, etc.), and auxiliary facilities (such as surveillance cameras, signs, lighting equipment, etc.).

[0093] When performing verification, in this embodiment, deep learning models such as target detection and recognition or semantic segmentation can be used to identify markers in the environment image, so as to determine the parking area on the highway section according to the recognition result, thereby determining whether the get-off point is available. Specifically, in this embodiment, in response to the identification of the marker, it indicates that there is a parking area in the area corresponding to the get-off point, and the corresponding get-off point is determined to be available; conversely, in response to the failure to identify the marker, it indicates that there is no parking area in the area corresponding to the get-off point, and the corresponding get-off point is determined to be unavailable.

[0094] In step S530, it is determined whether the inspection result indicates that the alighting point is available.

[0095] In this embodiment, when the verification result indicates that the alighting point is unavailable, step S540 is continued to be executed; when the verification result indicates that the alighting point is available, step S550 is continued to be executed.

[0096] In step S540, in response to the verification result indicating that the alighting point is unavailable, the alighting point is determined to be an unavailable point.

[0097] In step S550, in response to the verification result indicating that the alighting point is available, the alighting point is determined to be an available point.

[0098] Therefore, in this embodiment, the available points are verified by the above method, so as to quickly and accurately determine whether there is a parking area in the area where the get-off point is located and whether the get-off point is available, so that the available get-off point can be used for subsequent point recommendations, and more convenient and safe parking points can be recommended, thereby achieving the technical effect of optimizing the point recommendation effect and improving the driver and passenger experience.

[0099] In another optional implementation, since the location corresponding to the same highway section point may be a location area with a certain geographical range in addition to a location point, in this embodiment, when determining the available points of the highway section points in the global point library, after obtaining at least one historical stop information on the highway section, the safe area may be mined based on the historical stop information, and then the available points in the safe area may be mined. The safe area is a parking area.

[0100] Furthermore, when mining the safe area based on the historical stop information, the safe area corresponding to the same expressway section (such as a toll station) can be determined based on at least one historical stop information corresponding to the same expressway section. The safe area is the parking area surrounded by the get-off points corresponding to all the historical stop information. Afterwards, the safe area is verified based on the environmental image. Specifically, the above-mentioned verification method can be used to verify based on the environmental image related to the safe area. When no marker is identified in the safe area, it is determined that there is no parking area in the safe area. On the contrary, when the marker is identified in the safe area, it is determined that there is a parking area in the safe area, and the parking area is determined as an available point.

[0101] In step S430, the available points are added to the global point library to make point recommendations based on the global point library.

[0102] In this embodiment, after determining the available points corresponding to the expressway section, that is, the expressway section points, based on the above method, these expressway section points will be added to the global point library, so that when point recommendations are made later, the available points that are compatible with the boarding point can be queried from the global point library in a timely manner to realize point recommendations.

[0103] Optionally, when it is difficult to determine the available points on the highway section based on the vehicle stop information on the highway section or the number of available points determined is small, this embodiment can also combine manual excavation to determine the available points corresponding to the highway section to better meet the travel needs of the highway section points.

[0104] Optionally, the global point library in this embodiment will be continuously updated to improve the real-time performance of the global point library, so that the recommended points determined based on the global points are more real-time and can better meet the travel needs of users, which is conducive to further optimizing the point recommendation effect and improving the user experience. Furthermore, in this embodiment, the global point library can be updated regularly or based on preset trigger conditions (such as when a user travel request is detected) to trigger the update, so as to effectively improve the real-time performance of the global point library, so as to facilitate the rapid and accurate recall of the point recommendation list corresponding to the boarding point in the user's travel request.

[0105] Furthermore, when recalling highway section points and non-highway section points within the target geographical range corresponding to the boarding point in the user's travel request based on the global point library, it is determined whether the available points are within the target geographical range by comparing the location information of the available points in the global point library with the target geographical range, so as to determine the candidate points corresponding to the boarding point based on accessibility.

[0106] Furthermore, when the location represented by the location information of the available point is within the target geographical range, it indicates that the available point is within the target geographical range, and the available point is determined as a candidate point and added to the recall result. Thus, in this embodiment, all highway section points and non-highway section points within the target geographical range can be recalled.

[0107] Optionally, when there are only expressway points or non-expressway points within the target geographic range, correspondingly, the recall result obtained by the recall in this embodiment only includes expressway points or non-expressway points. When there are both expressway points and non-expressway points within the target geographic range, the recall result in this embodiment includes expressway points and non-expressway points.

[0108] In step S330, a recommended point list is determined according to the recall result.

[0109] Optionally, in this embodiment, the recommended points in the recall results may be used as candidate points in the point recommendation list, or some recommended points may be screened from the recall results as candidate points in the point recommendation list.

[0110] In an optional implementation, in this embodiment, a point recommendation list can be determined based on the number of recommended points in the recall results. When the number of recommended points in the recall results is small, that is, the number of recommended points does not reach a preset quantity threshold, all recommended points in the recall results are determined as candidate points in the point recommendation list, and a corresponding point recommendation list is determined; when the number of recommended points in the recall results is large, that is, the number of recommended points exceeds the quantity threshold, the recall results will be screened, and a preset number of recommended points screened out will be determined as candidate points in the point recommendation list, and a corresponding point recommendation list will be determined.

[0111] Optionally, when filtering the recall results to determine the recommended point list, in this embodiment, the recommended points in the recall results can be filtered according to the attribute information of the recommended points, and the attribute information may include at least one of the information such as the distance between the recommended point and the boarding point, the popularity value of the recommended point, and the convenience of reaching the recommended point. Therefore, in this embodiment, the recommended points in the recall results are filtered by the above method, and the recommended points that are closer to the boarding point, have higher popularity values, are more convenient to reach, and are easier to be selected by users can be filtered out, so that the recommended point list can better meet the travel needs of users and optimize the point recommendation effect.

[0112] In another optional implementation, in this embodiment, Figure 6 The method shown determines a list of recommended points, and specifically includes the following steps.

[0113] In step S610, the candidate points in the recall result are sorted based on a preset sorting model to determine the sorting result, and the candidate points are high-speed section points or non-high-speed section points.

[0114] Optionally, the sorting model in this embodiment can adopt machine learning models such as logistic regression model (LR model), gradient boosting decision tree (GBDT), etc. When determining the sorting result through the sorting model, the input of the sorting model is the feature vector of each candidate point, and the feature vector of each candidate point is determined according to the attribute information of the corresponding candidate point. The arrangement result output by the model is a candidate point sequence formed by arranging from high to low according to the correlation between each candidate point and the boarding point. The stronger the correlation between the candidate point and the boarding point, the higher the ranking in the candidate point sequence.

[0115] It should be noted that the sorting model in this embodiment can be selected according to the actual usage scenario, and the sorting logic of the sorting model can also be adjusted according to the actual usage scenario, which is not limited here.

[0116] In step S620, a point recommendation list is generated according to a preset number of candidate points at the top of the sorting results.

[0117] Optionally, in order to increase the probability of selecting candidate points that are highly correlated with the boarding point, the order of recommendation of each candidate point in the point recommendation list in this embodiment is consistent with the order of arrangement of each candidate point in the sorting result. Furthermore, in order to avoid the influence of too many candidate points on the user's selection efficiency, in this embodiment, only a preset number of candidate points at the front of the sorting result are selected to generate the point recommendation list. Therefore, by determining the point recommendation list through the above method, the candidate points that are more matched with the boarding point in the user's travel request can be recommended to the user, which is convenient for the user to quickly select the appropriate recommended point and improve the user experience.

[0118] In step S230, a list of recommended points is displayed to the user.

[0119] Optionally, in this embodiment, when the point recommendation list is displayed to the user, candidate points in the point recommendation list that are highway points will be displayed to the user first. In this way, when the user expects the boarding point to be a highway point, recommended points with shorter detour distance and lower time and money costs can be recommended to the user, thereby optimizing the point recommendation effect and improving the driver and passenger experience.

[0120] Optionally, considering that highway section points usually have characteristics such as large traffic volume and limited stop time, which will bring certain risks to the user's safe riding, in order to facilitate the user to perceive the actual situation of the recommended highway section positioning, in this embodiment, when the candidate points of the highway section points are revealed to the user, the prompt information of the candidate points will also be displayed to the user, and the prompt information is used to prompt the candidate points to have safety risks. Therefore, in this embodiment, by displaying the prompt information of the candidate points of the type of highway section points, it is convenient for users to quickly perceive the safety risks of the recommended points, and make the final point selection based on the safety risks and travel needs, which is conducive to further improving the user experience.

[0121] In an optional implementation, in this embodiment, prompt information of a candidate point of type a highway section point can be displayed while displaying the candidate point in the point recommendation list; prompt information of the candidate point can also be displayed to the user when the user selects a candidate point of type a highway section point, that is, the point recommendation method in this embodiment also includes: in response to the user selecting a candidate point as a highway section point, displaying prompt information of the candidate point.

[0122] Figure 7 Schematic diagram of displaying prompt information according to an embodiment of the present invention. Figure 7 As shown, in this embodiment, when the candidate points in the point recommendation list are displayed on the display page P7, each candidate point has a corresponding display control 71. At the same time, for the candidate points of the type of expressway points, such as xx toll station, the corresponding prompt information will be displayed in the display control 71 of the candidate point. The prompt information can remind the user that the candidate point has a safety risk by using similar terms such as "There is a safety risk in taking a car at this location, please confirm and go there".

[0123] Optionally, the prompt information of the candidate points in this embodiment can be displayed in the form of labels, pop-up windows or other display methods. Furthermore, the prompt information of the candidate points in this embodiment is displayed in the form of labels at the same time as the corresponding candidate points, that is, the display time of the prompt information is consistent with the display time of the corresponding candidate points, so that the risk warning of the recommended highway section points can be clearly and effectively displayed to the user, so that the user can effectively confirm the highway section points when selecting the recommended points, thereby improving the user experience.

[0124] Further optionally, when the candidate points in the point recommendation list are displayed on the map, in this embodiment, prompt information of the highway section points will also be displayed on the map to convey the risk information of the recommended highway section points to the user from different dimensions.

[0125] It should be noted that the display position and display method of the prompt information given in this embodiment are only examples, which can be set according to actual usage scenarios and are not limited here.

[0126] The technical solution of this embodiment can recommend both highway and non-highway points to users by recalling a point recommendation list including highway points and non-highway points when the boarding point in the user's travel request is a highway point, and revealing the point recommendation list to the user, thereby optimizing the point recommendation effect, thereby facilitating users to select suitable points from the recommended points as boarding points and improving the driver and passenger experience. In addition, since the candidate points for highway points in the point recommendation list are determined based on the historical get-off points of the highway, the highway points recommended to users are more in line with the actual travel situation, which can further optimize the point recommendation effect and improve the driver and passenger experience.

[0127] Figure 8 FIG. 1 is a schematic diagram of the point recommendation process of an embodiment of the present invention. Figure 8 As shown, in this embodiment, the point recommendation process is described as an example when the boarding point is the alighting point and the alighting point is a highway toll station, including the following processing steps.

[0128] In step S810, a safe area is mined based on historical docking information.

[0129] In this embodiment, the safety area corresponding to the expressway toll station is mined based on the historical stop information occurring within a certain distance of the expressway toll station. The method for determining the safety area adopts the method described above, which will not be repeated here.

[0130] In step S820, the safety area is verified based on the environment image.

[0131] In this embodiment, the safe area determined by excavation is verified based on the environmental image corresponding to the expressway toll station. The verification method has been introduced in the above content and will not be repeated here.

[0132] In step S830, available points in the safety area are added to the global point library.

[0133] In step S840, the user sends a travel request.

[0134] In step S850, it is determined whether a highway section point recommendation is triggered.

[0135] In this embodiment, after receiving a travel request sent by the user, if it is determined that the boarding point in the travel request is not a highway point, it is determined that the highway point recommendation is not triggered, and step S860 is continued; when it is determined that the boarding point in the travel request is a highway point, it is determined that the highway point recommendation is triggered, and step S870 is continued.

[0136] In step S860, a conventional point recommendation process is executed.

[0137] In this embodiment, the conventional point recommendation process includes a recall operation and a sorting operation. The processing methods of recall and sorting are similar to the aforementioned methods and will not be repeated here. It should be noted that when executing the conventional point recommendation process, in this embodiment, only candidate points of non-highway section points are recalled, and candidate points of high-speed section points are not recalled.

[0138] In step S870, the recommended point list is recalled.

[0139] In this embodiment, when the boarding point is a highway section point, the highway section points and non-highway section points within the target geographical range corresponding to the boarding point will be recalled at the same time, and a point recommendation list corresponding to the boarding point will be obtained by recalling. Among them, the method of recalling the point recommendation list has been detailed in the above content and will not be repeated here.

[0140] In step S880, a list of recommended points is displayed.

[0141] In this embodiment, when the point recommendation list is displayed to the user, the candidate points in the point recommendation list that are high-speed road points will be displayed to the user first. At the same time, when the candidate point is a high-speed road point, in this embodiment, prompt information of the candidate point will also be displayed to the user to remind the user that the candidate point has a safety risk.

[0142] In step S890, the user selects a boarding point based on demand.

[0143] Therefore, in this embodiment, the global point library including highway section points is constructed by the above method, which can enrich the recommended points in the global point library, meet the recommendation requirements of different types of boarding points, and optimize the point recommendation effect. At the same time, by recalling the recommended points of highway section points and non-highway section points at the same time when the boarding point in the travel request is a highway section point, it is possible to recommend highway section points and non-highway section points to the user at the same time, further optimize the point recommendation effect, meet the point recommendation under the user's specific travel needs, and reduce the driver's detour distance, saving time and economic costs for both drivers and passengers, thereby improving the experience of both drivers and passengers. In addition, by prompting the user that the candidate point has a safety risk when it is a highway section point, it is convenient for the user to perceive the actual situation of the highway section point in time, and select a more suitable recommended point as the final boarding point based on the prompt information and travel needs, which can further improve the user's travel experience.

[0144] Fig. 9 Schematic diagram of a point recommendation device according to an embodiment of the present invention. Fig. 9 As shown, the point recommendation device in this embodiment includes a trigger unit 91, a recommendation unit 92 and a display unit 93. The trigger unit 91 is used to receive a user's travel request. The recommendation unit 92 is used to respond to the boarding point in the travel request being a highway point, and recall a point recommendation list, the point recommendation list includes at least one candidate point, the candidate point is a highway point or a non-highway point, and the candidate point in the point recommendation list that is a highway point is determined based on the historical get-off point of the highway. The display unit 93 is used to show the point recommendation list to the user.

[0145] Fig.10 Schematic diagram of an electronic device according to an embodiment of the present invention. Fig.10The electronic device shown is a general data processing device, which includes a general computer hardware structure, which at least includes a processor 101 and a memory 102. The processor 101 and the memory 102 are connected via a bus 103. The memory 102 is suitable for storing instructions or programs executable by the processor 101. The processor 101 can be an independent microprocessor or a collection of one or more microprocessors. Thus, the processor 101 executes the instructions stored in the memory 102, thereby executing the method flow of the embodiment of the present invention as described above to realize the processing of data and the control of other devices. The bus 103 connects the above-mentioned multiple components together, and at the same time connects the above-mentioned components to the display controller 104 and the display device and the input / output (I / O) device 105. The input / output (I / O) device 105 can be a mouse, a keyboard, a modem, a network interface, a touch input device, a somatosensory input device, a printer, and other devices known in the art. Typically, the input / output device 105 is connected to the system through an input / output (I / O) controller 106.

[0146] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, devices (equipment) or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present application may adopt a computer program product implemented on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0147] The present application is described with reference to flowcharts of methods, apparatuses (devices) and computer program products according to embodiments of the present application. It should be understood that each process in the flowchart can be implemented by computer program instructions.

[0148] These computer program instructions may be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device that implements the process Figure 1 A function specified in a process or multiple processes.

[0149] These computer program instructions may also be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce the instructions for implementing the process Figure 1 A device that specifies functions in a process or multiple processes.

[0150] Another embodiment of the present invention relates to a non-volatile storage medium for storing a computer-readable program, wherein the computer-readable program is used for a computer to execute part or all of the above method embodiments.

[0151] That is, those skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by specifying relevant hardware through a program, and the program is stored in a storage medium, including several instructions for a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0152] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A point recommendation method, characterized in that: The method comprises: Receive travel requests from users; In response to the boarding point in the travel request being a highway section point, recalling a point recommendation list, the point recommendation list including at least one candidate point, the candidate point being a highway section point or a non-highway section point, the candidate point in the point recommendation list being a highway section point being determined based on historical alighting points of the highway section; The recommended list of points is presented to the user.

2. The method according to claim 1, characterized in that The method further comprises: Acquire at least one historical stop information on the expressway section, wherein the historical stop information includes a get-off point; Determine the alighting point as an available point; The available points are added to a global point library, so as to make point recommendations based on the global point library.

3. The method according to claim 2, characterized in that Determining the alighting point as an available point includes: Acquire an environmental image of the alighting point; Verifying the alighting point based on the environmental image and determining a verification result; In response to the verification result indicating that the alighting point is available, the alighting point is determined to be an available point.

4. The method according to claim 3, characterized in that The verifying the alighting point based on the environment image and determining the verification result comprises: Identify a landmark in the environment image, where the landmark includes at least one of a traffic sign, a specific environmental feature, and an auxiliary facility; In response to identifying the landmark, determining that a corresponding drop-off point is available; In response to not identifying the landmark, it is determined that the corresponding drop-off point is unavailable.

5. The method according to claim 1, characterized in that The method further comprises: In response to the candidate point selected by the user being a highway point, prompt information of the candidate point is displayed, where the prompt information is used to prompt that there is a safety risk at the candidate point.

6. The method according to claim 1, characterized in that The recommended list of recall points includes: Determine the target geographical range corresponding to the boarding point; Recalling the expressway section points and non-expressway section points within the target geographical range and determining the recall results; A list of recommended locations is determined based on the recall results.

7. The method according to claim 6, characterized in that Determining a recommended list of points according to the recall result includes: Sorting the candidate points in the recall result based on a preset sorting model to determine a sorting result; Generate a point recommendation list based on a preset number of candidate points in the sorting results.

8. The method according to claim 1, characterized in that: The method further comprises: The name of the boarding point is identified, and the type of the boarding point is determined, where the type of the boarding point is a high-speed road section point or a non-high-speed road section point.

9. The method according to claim 1, characterized in that: The step of providing the recommended point list to the user includes: The candidate points that are highway section points in the point recommendation list are preferentially displayed to the user.

10. A point recommendation device, characterized in that: The device comprises: A trigger unit, used for receiving a user's travel request; a recommendation unit, configured to, in response to the boarding point in the travel request being a highway section point, recall a point recommendation list, wherein the point recommendation list includes at least one candidate point, wherein the candidate point is a highway section point or a non-highway section point, and the candidate point in the point recommendation list that is a highway section point is determined based on historical alighting points of the highway section; The display unit is used to display the recommended point list to the user.

11. A computer program product, characterized in that The computer program product comprises a computer program / instructions, and when the computer program / instructions are executed by a processor, the method according to any one of claims 1 to 9 is implemented.

12. An electronic device comprising a memory and a processor, characterized in that: The memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method according to any one of claims 1 to 9.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

Images