Site determination method and device, electronic equipment and computer readable storage medium

Abstract

The embodiment of the invention discloses a station determination method and device, electronic equipment and a computer readable storage medium. The method comprises the steps of obtaining online car-hailing historical order data; determining a plurality of gathering point position sets according to the distribution of boarding point positions and / or getting-off point positions in the online car-hailing historical order data; screening point locations in the aggregated point location set based on a preset screening strategy, and determining a corresponding candidate point set; determining a reference point location according to the candidate point locations in the candidate point set; and determining the fixed station according to the position relationship between the reference point location and the route point location on the fixed route, thereby setting the fixed station for the fixed route based on the actual riding demand of the passenger through the method, gathering the car sharing demand to the fixed station, and improving the journey sharing rate.

Description

Technical Field

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

[0002] In the common carpooling mode, the platform often recommends multiple dynamic stations to passengers in real time based on the convenience of the passengers' order points / end POIs. Although this station recommendation method can improve the efficiency of carpooling trips to a certain extent, it has a certain ceiling on the improvement of the trip completion rate when the order demand is relatively scattered. Summary of the invention

[0003] In view of this, an object of embodiments of the present invention is to provide a site determination method, device, electronic device and computer-readable storage medium to improve the completion rate of an itinerary.

[0004] In a first aspect, an embodiment of the present invention is to provide a site determination method, which is applied to online bus booking, and the method includes:

[0005] Get historical order data of online ride-hailing services;

[0006] Determine a plurality of aggregation point sets according to the distribution of pick-up point locations and / or drop-off point locations in the historical order data of the online car-hailing service;

[0007] Screening the points in the clustered point set based on a preset screening strategy to determine a corresponding candidate point set;

[0008] Determine a reference point according to the candidate points in the candidate point set;

[0009] The fixed site is determined according to the positional relationship between the reference point and the route point on the fixed route.

[0010] Optionally, screening the points in the clustered point set based on a preset screening strategy to determine the corresponding candidate point set includes:

[0011] Extracting points whose heat values ​​reach a preset heat value from the gathering point set to determine a preselected point set;

[0012] The points in the pre-selected point set are clustered based on the distances between the points to determine a candidate point set corresponding to the pre-selected point set.

[0013] Optionally, extracting points whose heat values ​​reach a preset heat value from the gathering point set and determining the preselected point set includes:

[0014] Extracting points whose heat values ​​reach a preset heat value from the aggregation point set, and determining an initial point set;

[0015] The points in the initial point set are thinned out by distance to determine a pre-selected point set.

[0016] Optionally, determining a reference point according to candidate points in the candidate point set includes:

[0017] Sorting the candidate points in the candidate point set according to the heat values;

[0018] The candidate point with the highest heat value is determined as the reference point.

[0019] Optionally, determining a reference point according to candidate points in the candidate point set includes:

[0020] Determine at least one recommended point corresponding to the candidate point set, the recommended point being a point whose sum of distances from each candidate point in the candidate point set is less than a preset distance value;

[0021] The reference point position corresponding to the candidate point set is determined according to each of the recommended points.

[0022] Optionally, determining the reference point position corresponding to the candidate point set according to each of the recommended points includes:

[0023] A reference point is determined from the recommended points based on the sum of distances and / or heat values ​​corresponding to the recommended points.

[0024] Optionally, determining the fixed site according to the positional relationship between the reference point and the route point on the fixed route includes:

[0025] Determine the route point closest to the reference point on the fixed route as an available site;

[0026] Determining matching parameters between the available site and each candidate point in the candidate point set;

[0027] evaluating the available sites according to the matching parameters;

[0028] In response to the available site meeting a preset condition, the available site is determined as a fixed site.

[0029] Optionally, the matching parameter includes at least one of a distance parameter, a convenience parameter and a security parameter;

[0030] The preset condition includes at least one of a distance parameter being less than a preset distance, a convenience parameter being greater than a preset convenience parameter value, and a safety factor being greater than a preset safety factor value;

[0031] Among them, the distance parameter is used to characterize the arrival distance between the candidate point and the available site, the convenience parameter is used to characterize the convenience of the candidate point to reach the available site, and the safety parameter is used to characterize the safety factor of the candidate point to reach the available site.

[0032] Optionally, determining at least one fixed site in the fixed route according to each of the candidate point sets further includes:

[0033] The position of each of the fixed sites is adjusted based on a preset constraint condition, where the constraint condition is determined according to at least one of the distance between the fixed sites, the flow of people at the fixed sites, and a threshold value of the number of fixed sites.

[0034] In a second aspect, an embodiment of the present invention is intended to provide a site recommendation method, which is applied to online bus booking, and the method includes:

[0035] Get historical order data of online ride-hailing services;

[0036] Generate fixed routes based on historical order data of online ride-hailing services;

[0037] Determine a plurality of aggregation point sets according to the distribution of pick-up point locations and / or drop-off point locations in the historical order data of the online car-hailing service;

[0038] Screening the points in the clustered point set based on a preset screening strategy to determine a corresponding candidate point set;

[0039] Determine a reference point according to the candidate points in the candidate point set;

[0040] Determine a fixed site according to a positional relationship between the reference point and a route point on the fixed route;

[0041] Storing the fixed sites corresponding to each candidate point set in a site library;

[0042] In response to receiving a ride request, a fixed station in a station library is recommended to a passenger based on a ride point in the ride request.

[0043] In a third aspect, an embodiment of the present invention is to provide a station determination device, which is applied to online bus booking, and the device includes:

[0044] A data acquisition unit, used to acquire historical order data of online ride-hailing services;

[0045] A point analysis unit is used to determine a plurality of clustered point sets according to the distribution of the pickup point locations and / or the drop-off point locations in the historical order data of the online car-hailing service; and to screen the points in the clustered point sets based on a preset screening strategy to determine a corresponding candidate point set;

[0046] The site determination unit is used to determine a reference point according to the candidate points in the candidate point set; and determine a fixed site according to the positional relationship between the reference point and the route points on the fixed route.

[0047] In a fourth aspect, an embodiment of the present invention is to provide a station recommendation system, which is applied to online bus booking, and the system includes:

[0048] Data acquisition module, used to obtain historical order data of online ride-hailing services;

[0049] A route determination module, used to generate a fixed route based on the historical order data of the online car-hailing service;

[0050] A station determination module is used to determine a plurality of clustered point sets according to the distribution of the pickup point locations and / or the drop-off point locations in the historical order data of the online car-hailing service; screen the points in the clustered point set based on a preset screening strategy to determine a corresponding candidate point set; determine a reference point according to the candidate points in the candidate point set; and determine a fixed station according to the positional relationship between the reference point and the route points on the fixed route;

[0051] The station recommendation module is used to store the fixed stations corresponding to each candidate point set in a station library; in response to receiving a ride request, recommend the fixed stations in the station library to the passenger based on the ride point in the ride request.

[0052] In a fifth 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.

[0053] In a sixth 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.

[0054] In a seventh 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.

[0055] The technical solution of the embodiment of the present invention is achieved by obtaining historical order data of online ride-hailing vehicles; determining multiple aggregation point sets based on the distribution of pick-up point locations and / or alighting point locations in the historical order data of online ride-hailing vehicles; screening the points in the aggregation point set based on a preset screening strategy to determine a corresponding candidate point set; determining reference points based on the candidate points in the candidate point set; determining fixed stations based on the positional relationship between the reference points and the route points on the fixed route, and being able to set fixed stations for fixed routes based on the actual passenger demand, thereby gathering carpooling demand at the fixed stations and improving the carpooling rate of the trip. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] 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:

[0057] Figure 1 is a schematic diagram of an online bus booking service system according to an embodiment of the present invention;

[0058] Figure 2 is a flow chart of a site determination method according to an embodiment of the present invention;

[0059] Figure 3 is a flowchart of determining a candidate point set according to an embodiment of the present invention;

[0060] Figure 4 is a flow chart of determining a reference point according to an embodiment of the present invention;

[0061] Figure 5 is a flow chart of determining a fixed site according to an embodiment of the present invention;

[0062] Figure 6 is a schematic diagram of determining a fixed site corresponding to a candidate point set according to an embodiment of the present invention;

[0063] Figure 7 is a schematic diagram of determining a fixed site of a fixed route according to an embodiment of the present invention;

[0064] Figure 8 is a schematic diagram of a site recommendation method according to an embodiment of the present invention;

[0065] Fig. 9 is a schematic diagram of a site determination device according to an embodiment of the present invention;

[0066] Fig.10 is a schematic diagram of a site recommendation system according to an embodiment of the present invention;

[0067] Fig.11 is a schematic diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0068] 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.

[0069] 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.

[0070] 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".

[0071] 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.

[0072] The solutions described in this specification and the embodiments, if they involve information acquisition, will collect data under 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 (who can be a passenger, driver or any other type of user) refuses to process personal information other than the necessary information required for basic functions, which will not affect the user's use of basic functions.

[0073] In the normal carpooling mode, the platform often recommends multiple dynamic sites in real time based on the passenger's ordering point / terminal POI point. The platform selects the point that makes the trip most efficient based on the convenience. However, although this system recommends multiple dynamic sites to achieve carpooling, it can improve the efficiency of pick-up and drop-off during the trip, but when the order demand is relatively scattered and the transportation capacity is insufficient, there is a certain ceiling for improving the success rate of the trip. Therefore, it is hoped to find some high-frequency routes, similar to bus routes, to gather as much demand as possible in time and space, which can further improve route efficiency, reduce operating costs, and ensure passengers' travel experience. At the same time, it is necessary to set reasonable fixed sites for high-frequency routes according to passengers' travel needs to improve the success rate of the trip.

[0074] In view of this, the present embodiment aims to provide a method for determining bus stops for an online-hailing bus, so as to set reasonable fixed stops for the fixed routes traveled by the online-hailing bus that performs carpooling tasks, thereby improving the carpooling success rate of the trip.

[0075] Figure 1 Schematic diagram of the online bus booking service system according to an embodiment of the present invention. Figure 1 As shown, the online bus booking service system of this embodiment includes a server 1, a passenger terminal 2, and a driver terminal 3. The server 1, the passenger terminal 2, and the driver terminal 3 are connected to each other through a network 4 to achieve information and data interaction. It should be understood that although Figure 1 Only a certain number of online car-hailing servers 1, passenger terminals 2 and driver terminals 3 are shown, but this does not mean that their respective numbers are limited. The system can include multiple servers, passenger terminals and driver terminals.

[0076] Server 1 should be understood as a device that provides data processing, database, and communication facilities. For example, server 1 may refer to a single physical server with related communication and data storage and database facilities, or may refer to a collection of networked or clustered processors, related networks, and storage devices, and operates software and one or more database systems and application software that supports the services provided by the server. Server 1 can be a monolithic server or a distributed server across multiple computers or computer data centers, or it can be various types of cloud servers. In some embodiments, each server may include hardware, software, or an embedded logic component or a combination of two or more such components for performing appropriate functions supported or implemented by the server.

[0077] The passenger terminal 2 and the driver terminal 3 are communication terminals capable of running computer programs. These communication terminals may be terminal devices such as mobile phones, tablet computers, PDAs, wearable devices, and vehicle-mounted terminals integrated with vehicles. The passenger client 21 may be run on the passenger terminal 2. The driver client 31 may be run on the driver terminal 3. At the same time, the server 1 runs the server application 11. Both the passenger terminal 2 and the driver terminal 3 have a communication module, which is capable of wired or wireless communication. In some embodiments, the passenger terminal 2 and the driver terminal 3 include at least one remote communication module, such as a communication circuit for WLAN, GPRS, 2G / 3G / 4G / 5G remote communication. The passenger terminal 2 and the driver terminal 3 also have a display device and an input device, and the display device may be a liquid crystal display, an LED display, or a projection device. The input device may include, for example, a touch screen, a button, a pressure sensor, etc. The passenger terminal 2 and the driver terminal 3 receive the passenger's ride request through the input device and interact with the passenger or the driver through the display device.

[0078] The online car-hailing bus service of this embodiment is developed on the basis of the online car-hailing carpooling service. Compared with the existing ordinary carpooling model, the online car-hailing bus can simultaneously accommodate more passengers with similar ride needs for carpooling, so that passengers can enjoy services similar to ordinary carpooling at a lower service price, thereby improving the utilization efficiency of vehicles. At the same time, the online car-hailing bus has the concept of fixed routes and fixed stations, and integrates the logic of existing carpooling services. On the one hand, the online car-hailing bus service forms a ride order based on the passenger's ride request, inheriting the mechanism of online initiation of the carpooling service based on passenger requests. On the other hand, the online car-hailing bus service limits the boarding and alighting locations to fixed stations along the fixed route as much as possible. Setting a fixed route can facilitate passengers along the fixed route to quickly reach their destination, thereby improving the operational efficiency of the carpooling service and the travel experience of passengers. The advantage of setting a fixed station is that it is more likely to pick up and drop off multiple passengers at a time at a fixed station, thereby improving the success rate and travel efficiency. Moreover, in the case of setting a fixed station, in addition to initiating a request online, passengers can also directly initiate a ride request by scanning a code at a fixed station. At the same time, the online bus-hailing business still has a high degree of flexibility. The server can match ride orders based on the location of the passenger who initiated the request and the location of the online bus driver, using a logic similar to carpooling.

[0079] exist Figure 1 In the online bus-hailing service system shown, the passenger terminal 2 can initiate a ride request to the server 1 through the passenger client 21. After receiving the ride request, the server 1 matches the appropriate fixed route and the boarding and alighting stations of the fixed route based on the location information in the ride request, and sends the ride request to the driver terminal 3 that goes to the boarding station on the fixed route, thereby forming a ride order. The driver terminal 3 guides the online bus to the boarding station through the driver client 31, and sends the passenger to the alighting station along the predetermined driving route through multiple fixed stations. In this process, the driver terminal 3 of the online bus is still in the order-taking state, and can continuously match new ride requests, and pick up passengers at the corresponding boarding station and send them to the alighting station. The server 1 matches the ride requests near the fixed route with the online bus on the fixed route according to the actual distribution of the received ride requests, so that the online bus runs between different stations according to the planned route to pick up passengers and provide services to passengers along the route.

[0080] Figure 2 is a flow chart of a site determination method according to an embodiment of the present invention. Figure 2 As shown, in this embodiment, fixed sites are set for fixed routes by the following method.

[0081] In step S210, historical order data of online ride-hailing services is obtained.

[0082] In this embodiment, the online car-hailing order data may include one or more service data of multiple service types such as carpooling service data, express service data, and private car service data in the online car-hailing service. These online car-hailing order data can cover the ride demands generated at different times and in different spaces. By obtaining the historical order data of online car-hailing services, it is possible to fully understand the ride demands of passengers.

[0083] In step S220, multiple aggregation point sets are determined based on the distribution of pick-up point locations and / or alighting point locations in the historical order data of the online car-hailing service.

[0084] In this embodiment, by analyzing the location distribution of the pickup point and / or the drop-off point in the historical order data of the online car-hailing service, multiple demand grids and the clustered point sets corresponding to each demand grid can be determined. The demand grid usually corresponds to a certain geographical area such as a business district or a community. In each demand grid, there are multiple pickup point locations and / or drop-off point locations that are clustered and distributed.

[0085] Optionally, in this embodiment, knowledge and techniques from multiple fields such as geographic information systems (GIS), statistics, spatial analysis, and data visualization can be combined to analyze the location distribution of pick-up points and / or alighting points in the historical order data of online ride-hailing vehicles through multiple specific methods such as point density analysis, kernel density estimation, spatial fit test, heat map analysis, and spatial interpolation, so as to determine the demand grids where ride demand is concentrated and the set of aggregation points corresponding to each demand grid.

[0086] In step S230, the points in the clustered point set are screened based on a preset screening strategy to determine a corresponding candidate point set.

[0087] In this embodiment, considering that there are many points in the clustered point set and the demands corresponding to different points are different, in order to facilitate the setting of sites based on each clustered point set and improve the efficiency of site determination, the points in the clustered point set will be screened based on the point heat to determine the candidate point set corresponding to the clustered point set.

[0088] Optionally, in this embodiment, Figure 3 The method shown determines a set of candidate points, specifically including:

[0089] In step S310, points whose heat values ​​reach a preset heat value in the clustered point set are extracted to determine a pre-selected point set.

[0090] In this embodiment, the preset heat value can be set according to factors such as the capacity of the points in the clustered point set, the density of the points, etc. For example, the larger the point capacity and the greater the point density, the greater the preset heat value. However, it should be understood that the setting of the preset heat value can be set according to the specific application scenario, and this is not limited here.

[0091] Optionally, in the case where there are a large number of points in the clustered point set or other scenarios where the site needs to be quickly determined, in this embodiment, when determining the pre-selected point set, the points in the clustered point set can be screened by combining the point heat and a preset thinning method to determine the pre-selected point set. The purpose of thinning is to eliminate some points in the clustered point set, which is conducive to improving the efficiency of site determination.

[0092] Furthermore, in this embodiment, when determining the pre-selected point set, the points whose heat values ​​reach the preset heat value in the clustered point set can be first extracted to determine the initial point set; and then the points in the initial point set are distance-thinned to determine the pre-selected point set. Distance thinning between points (also called point thinning or point simplification) is a technology for reducing the number of data points, which can reduce the amount of data while maintaining the overall characteristics of the data, thereby saving storage space or improving processing speed.

[0093] In step S320, the points in the pre-selected point set are clustered based on the distances between the points to determine a candidate point set corresponding to the pre-selected point set.

[0094] Optionally, in this embodiment, the points in the pre-selected point set can be clustered based on the point positions and the distances between the points through a K-Means clustering algorithm, a mean shift (Mean Shift) clustering algorithm, a DBSCAN clustering algorithm, a Gaussian mixture model (GMMs) or other clustering methods to determine a candidate point set corresponding to the pre-selected point set.

[0095] In step S240, a reference point is determined according to the candidate points in the candidate point set.

[0096] Optionally, the reference point in this embodiment can be a candidate point in the candidate point set, or it can be a non-candidate point determined based on the attribute information of each candidate point in the candidate point set, wherein the attribute information includes at least one of the factors that affect the arrival at the fixed route, such as the heat value and the distance from the fixed route.

[0097] In an optional implementation, in this embodiment, when determining the reference point, each candidate point in the candidate point set can be sorted according to the heat value, and the sorting order can be in ascending or descending order of heat value; after the sorting is completed, the candidate point with the highest heat value is determined as the reference point.

[0098] In another optional implementation, in this embodiment, the distances between the candidate points in the candidate point set can be first determined, and then the sum of the distances between each candidate point and other candidate points is calculated, and the candidate points are sorted in order from the smallest to the largest sum of distances, and then the candidate point with the smallest sum of distances is determined as the reference point.

[0099] In another optional implementation, in this embodiment, the Figure 4 The method shown determines the reference point, which specifically includes the following steps.

[0100] In step S410, at least one recommended point corresponding to the candidate point set is determined.

[0101] Optionally, the recommended point in this embodiment is a point whose total distance from each candidate point in the candidate point set is less than a preset distance value. The recommended point may be a point in the candidate point set or a point outside the candidate point set.

[0102] Furthermore, when determining the recommended points, in this embodiment, preset algorithms such as KD tree (K-Dimensional Tree), approximate nearest neighbor search, ball tree algorithm, space partitioning methods, etc. can be used to determine at least one recommended point whose distance from each candidate point in the candidate point set is less than a preset distance value. At this time, the recommended point determined can be a point outside the candidate point set, or a point that overlaps with the position of a candidate point in the candidate point set.

[0103] Further optionally, when determining at least one recommended point from the candidate point set, in this embodiment, the distances between the candidate points in the candidate point set can be determined first, and then the sum of the distances between each candidate point and other candidate points can be calculated, and the candidate points can be sorted in order of the sum of the distances from the smallest to the largest, and then a preset number of candidate points at the front of the sorting result can be determined as recommended points. Alternatively, in this embodiment, after determining the sum of the distances between each candidate point in the candidate point set and other candidate points, the candidate points whose sum of distances is less than the preset distance can be determined as recommended points.

[0104] In step S420, the reference point positions corresponding to the candidate point set are determined according to the recommended points.

[0105] Optionally, after determining at least one recommended point corresponding to the candidate point set, this embodiment determines a reference point from each recommended point based on the sum of distances and / or heat values ​​corresponding to each recommended point.

[0106] In an optional implementation, in this embodiment, the reference point is determined from the recommended points based only on the sum of distances corresponding to each recommended point, and the recommended point with the smallest sum of distances is determined as the reference point, that is, the recommended point with the smallest sum of distances from each candidate point in the candidate point set is determined as the reference point. In this case, the present embodiment can also use the method of determining Fermat points to determine the recommended points, and the Fermat point is the point with the smallest sum of distances from all points in the candidate point set. When solving the Fermat point, in this embodiment, iterative methods, numerical methods, geometric construction methods, etc. can be used to determine the Fermat point. For example, when using the iterative method, an optimization algorithm (such as gradient descent, Newton's method, etc.) is used to iteratively find the point that minimizes the sum of distances to all candidate points; when using the numerical method, the optimization toolbox in the mathematical software (such as MATLAB, Python's SciPy library, etc.) is used to solve the Fermat points corresponding to all candidate points. Afterwards, the determined Fermat point is determined as the recommended point corresponding to the candidate point set, and the recommended point is determined as the reference point corresponding to the candidate point set. Therefore, in this embodiment, the above method can determine the reference point with the smallest sum of distances to each candidate point in the candidate point set.

[0107] In another optional implementation, in this embodiment, a reference point is determined from each recommended point based only on the heat value corresponding to each recommended point, and the recommended point with the highest heat value is selected as the reference point. Optionally, when the location of the recommended point is not a point in the historical data of the online car-hailing service, the heat value of the recommended point can be represented by the heat average of the points within a certain range of the recommended point. Afterwards, the heat values ​​of different recommended points are compared, and the recommended point with the largest heat value is determined as the reference point of the corresponding candidate point set. Therefore, in this embodiment, the above method can determine the reference point with a reasonable sum of distances to each candidate point in the candidate point set and the highest heat.

[0108] In another optional implementation, in this embodiment, a reference point is determined from each recommended point based on the sum of distances and heat values ​​corresponding to each recommended point. When determining the reference point, in this embodiment, a distance weight is set in advance for the distance sum, and a heat weight is set for the heat value; and a corresponding distance score is set for each distance sum according to the numerical distribution of each distance sum, and a corresponding heat score is set for each heat value according to the numerical distribution of the heat value; then, the distance sum and heat value of each recommended point are weighted and summed according to the distance weight, distance score, heat weight, and heat score to obtain a reference score for each recommended point; finally, the recommended point with the highest reference score is selected as the reference point of the corresponding candidate point set. Therefore, in this embodiment, the above method can determine the reference point with the best comprehensive sum of distances and heat values ​​of each candidate point in the candidate point set.

[0109] In step S250, a fixed site is determined based on a positional relationship between a reference point and a route point on the fixed route.

[0110] In this embodiment, the fixed route is a predetermined route for online-hailing buses, and the fixed route can be determined by analyzing and processing the high-heat routes corresponding to the high-heat grid pairs in the online-hailing historical order data. Among them, the starting grid and the end grid in the high-heat grid pair are the geographical areas where the starting point and the end point are located in the historical orders, respectively, and the demand for rides between the starting grid and the end grid is dense. The high-heat route is a route with high popularity from the starting grid to the end grid.

[0111] Optionally, taking into account that the locations where ride demand is concentrated may be different in different time periods, in order to fully improve the utilization efficiency of online-hailing buses, the fixed routes in different time periods may be different in this embodiment. The fixed routes corresponding to each time period may be determined based on the above method according to the online-hailing historical data for the corresponding time period.

[0112] Furthermore, after the reference points and known fixed routes corresponding to the candidate point set are determined based on the aforementioned method, the fixed sites corresponding to the candidate point set are determined according to the positional relationship between the reference points and the route points on the fixed route.

[0113] Figure 5 FIG. 1 is a flow chart of determining a fixed site according to an embodiment of the present invention. Figure 5 As shown, in this embodiment, the fixed site is determined by the following method.

[0114] In step S510, the route point closest to the reference point on the fixed route is determined as an available site.

[0115] Optionally, this embodiment may determine the route point on the fixed route with the smallest straight-line distance or arrival distance to the reference point as an available site. Preferably, in order to improve the availability of available sites, this embodiment determines the route point on the fixed route with the smallest arrival distance to the reference point as an available site.

[0116] In step S520, matching parameters between the available sites and each candidate point in the candidate point set are determined.

[0117] In this embodiment, the matching parameters include at least one of a distance parameter, a convenience parameter, and a safety parameter; wherein the distance parameter is used to characterize the arrival distance between the candidate point and the available site, and the arrival distance may be a walking distance, a cycling distance, a public transportation distance, etc. The convenience parameter is used to characterize the convenience of the candidate point in reaching the available site, and the convenience parameter may be determined based on factors affecting the convenience of travel, such as the road width, flatness, and other road conditions, the traffic congestion coefficient, and the number of public transportation facilities on the roads through which the candidate point reaches the available site. The safety parameter is used to characterize the safety factor of the candidate point in reaching the available site, and the safety factor may be determined based on safety-related factors, such as the road traffic accident rate on the roads through which the candidate point reaches the available site, and the number of monitoring facilities on the road.

[0118] In step S530, available sites are evaluated according to the matching parameters.

[0119] In this embodiment, the available sites are evaluated by comparing the matching parameters with preset conditions, wherein the preset conditions include at least one of a distance parameter being less than a preset distance, a convenience parameter being greater than a preset convenience parameter value, and a safety factor being greater than a preset safety factor value.

[0120] In step S540, it is determined whether the available sites meet the preset conditions.

[0121] In this embodiment, when it is determined that the available site meets the preset condition, step S550 is continued to be executed. When it is determined that the available site does not meet the preset condition, step S560 is continued to be executed.

[0122] In step S550, in response to the available site meeting a preset condition, the available site is determined to be a fixed site.

[0123] In this embodiment, when the available site meets the preset conditions, it indicates that the distance, convenience and / or safety of each candidate point in the candidate point set corresponding to the current available site to reach the available site can meet the passengers' travel needs. At this time, the available site can be determined as a fixed site corresponding to each candidate point in the corresponding candidate point set.

[0124] In step S560, in response to the available site not meeting the preset condition, the available site is modified.

[0125] In this embodiment, when the available site does not meet the preset conditions, it indicates that the current available site does not meet the passenger's riding needs, and the available site needs to be modified.

[0126] When correcting the available stations, the positions of the available stations can be adjusted according to the location distribution and / or heat distribution of each candidate point in the candidate point set. For example, the available stations can be moved in a direction closer to the areas where the candidate points are concentrated and / or have higher heat, and the moved available stations can be used to replace the original available stations to meet the travel needs of more different locations as much as possible.

[0127] Figure 6 FIG. 1 is a schematic diagram of determining a fixed site corresponding to a candidate point set according to an embodiment of the present invention. Figure 6 As shown, in this embodiment, after obtaining the historical order data 61 of online car-hailing, a heat map analysis is performed on the pick-up points and / or drop-off points in the historical order data 61 of online car-hailing to determine multiple demand grids with concentrated ride demand in the target geographical area (such as a city) and a collection of clustered points 62 corresponding to each demand grid. Then, for each collection of clustered points 62, the points in the collection of clustered points 62 are sequentially subjected to heat value screening, distance thinning and clustering processing to obtain a candidate point set 63 corresponding to the collection of clustered points. Afterwards, for each candidate point set 63, a reference point 64 corresponding to the candidate point set is determined according to each candidate point in the candidate point set 63, and then an available point 651 is determined based on the positional relationship between the reference point 64 and the route point on the fixed route 65, and the available point 651 is evaluated, and finally the available point 651 that meets the preset conditions is determined as the fixed station corresponding to the corresponding candidate point set. Among them, the method of determining the cluster point set, candidate point set, reference point, available point, evaluating the available point and determining the fixed site corresponding to the candidate point set according to the evaluation results has been introduced in detail in the above content and will not be repeated here.

[0128] Optionally, in this embodiment, after the fixed stations corresponding to each candidate point set are determined, the fixed stations corresponding to all candidate point sets may be used as fixed stations on the fixed route and applied to the fixed route.

[0129] Alternatively, in order to improve the availability of fixed stations, in this embodiment, after determining the fixed stations corresponding to each candidate point set, the position of each fixed station can be adjusted based on preset constraints, and the constraints are determined according to at least one of the distance between the fixed stations, the flow of people at the fixed stations, and the threshold value of the number of fixed stations (i.e., the maximum number of fixed stations that can be set on a fixed route). When adjusting the position of each fixed station based on the preset conditions, the fixed stations corresponding to each candidate point set can be adjusted by merging the fixed stations whose distance is less than the distance threshold, determining the position in the middle of the fixed stations as the final fixed station, merging the fixed stations corresponding to the candidate point set with less flow of people into the nearest fixed station with more flow of people, etc., so that more riding needs can be met while reducing operating costs.

[0130] Figure 7 Schematic diagram of determining fixed sites of a fixed route according to an embodiment of the present invention. Figure 7 As shown, in this embodiment, after determining the fixed sites 71, 72, 73 and 74 corresponding to each candidate point set, since the distance between the fixed sites 72 and 73 is less than the distance threshold, the fixed sites 72 and 73 will be merged to the middle position of the two points, and a new fixed site 72' will be obtained. Finally, the fixed sites 71, 72' and 74 are used as fixed sites on a fixed route. Therefore, by setting fixed sites on a fixed route through the above method, the carpooling rate of the trip can be improved and the riding needs of different passengers can be met, and the problem of increased operating costs caused by frequent starts of vehicles between points that are very close can also be avoided.

[0131] Furthermore, after the fixed stations in the fixed route are determined based on the above method, each fixed station will be stored in the station library so as to recommend the fixed stations to the passengers later. Furthermore, in this embodiment, in response to receiving the passenger's ride request, the fixed stations in the station library are recommended to the passenger based on the ride point in the ride request.

[0132] Optionally, when recommending fixed stations to passengers, the nearest fixed stations can be recommended to passengers in real time based on the boarding points in the passengers' boarding requests, so that passengers can quickly reach the fixed stations to board, which is conducive to improving the utilization efficiency of fixed stations and enhancing passengers' travel experience.

[0133] The technical solution of this embodiment is to obtain historical order data of online ride-hailing vehicles; determine multiple aggregation point sets based on the distribution of pick-up point locations and / or alighting point locations in the historical order data of online ride-hailing vehicles; filter the points in the aggregation point set based on a preset filtering strategy to determine the corresponding candidate point set; determine reference points based on the candidate points in the candidate point set; determine fixed stations based on the positional relationship between the reference points and route points on the fixed route, and can set fixed stations for fixed routes based on the actual passenger demand, thereby aggregating carpooling demand at fixed stations and improving the success rate of the trip.

[0134] Figure 8 FIG. 1 is a schematic diagram of a site recommendation method according to an embodiment of the present invention. Figure 8 As shown, the site recommendation method in this embodiment is applied to online bus booking, and site recommendation is achieved in the following way.

[0135] In step S810, historical order data of online ride-hailing services is obtained.

[0136] In step S820, a fixed route is generated based on the historical order data of the online car-hailing service.

[0137] In step S830, multiple aggregation point sets are determined based on the distribution of pick-up point locations and / or alighting point locations in the historical order data of the online car-hailing service.

[0138] In step S840, the points in the clustered point set are screened based on a preset screening strategy to determine a corresponding candidate point set.

[0139] In step S850, a reference point is determined according to the candidate points in the candidate point set.

[0140] In step S860, a fixed site is determined based on the positional relationship between the reference point and the route point on the fixed route.

[0141] In step S870, the fixed sites corresponding to each candidate point set are stored in a site library.

[0142] In step S880, in response to receiving a ride request, a fixed station in a station library is recommended to the passenger based on the ride point in the ride request.

[0143] Among them, the processing methods in steps S810-S880 in this embodiment have been introduced in the above content and will not be repeated here.

[0144] Therefore, in this embodiment, the above method can realize setting fixed routes and fixed stops for fixed routes based on actual passenger riding needs, gather different carpooling needs at fixed stops, and improve the rate of itinerary sharing. At the same time, by recommending fixed stops to users when passengers have ride requests, passengers can be guided to quickly get on and off at suitable ride stops, which can provide convenience for ride travel and further improve passenger experience.

[0145] Fig. 9 Schematic diagram of a site determination device according to an embodiment of the present invention. Fig. 9 As shown, the station determination device in this embodiment is applied to online-hailing buses, and the station determination device includes a data acquisition unit 91, a point analysis unit 92 and a station determination unit 93. Among them, the data acquisition unit 91 is used to obtain the historical order data of the online-hailing bus. The point analysis unit 92 is used to determine multiple clustered point sets based on the distribution of the pickup point locations and / or the alighting point locations in the historical order data of the online-hailing bus; the points in the clustered point sets are screened based on a preset screening strategy to determine the corresponding candidate point sets. The station determination unit 93 is used to determine the reference point based on the candidate points in the candidate point set; and determine the fixed station based on the positional relationship between the reference point and the route point on the fixed route.

[0146] Fig.10 Schematic diagram of a site recommendation system according to an embodiment of the present invention. Fig.10 As shown, the site recommendation system in this embodiment is applied to online-booked buses, including a data acquisition module 101, a route determination module 102, a site determination module 103, and a site recommendation module 104. Among them, the data acquisition module 101 is used to obtain the historical order data of online-booked buses. The route determination module 102 is used to generate a fixed route based on the historical order data of online-booked buses. The site determination module 103 is used to determine multiple clustering point sets according to the distribution of the pickup point location and / or the drop-off point location in the historical order data of online-booked buses; filter the points in the clustering point set based on the preset screening strategy to determine the corresponding candidate point set; determine the reference point according to the candidate points in the candidate point set; and determine the fixed site according to the positional relationship between the reference point and the route point on the fixed route. The site recommendation module 104 is used to store the fixed sites corresponding to each candidate point set in the site library; in response to receiving a ride request, recommend the fixed sites in the site library to the passenger based on the ride point in the ride request.

[0147] Fig.11 Schematic diagram of an electronic device according to an embodiment of the present invention. Fig.11 As shown, Fig.11The electronic device shown is a general data processing device, which includes a general computer hardware structure, which includes at least a processor 111 and a memory 112. The processor 111 and the memory 112 are connected via a bus 113. The memory 112 is suitable for storing instructions or programs executable by the processor 111. The processor 111 can be an independent microprocessor or a collection of one or more microprocessors. Thus, the processor 111 executes the instructions stored in the memory 112, 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 113 connects the above-mentioned multiple components together, and at the same time connects the above-mentioned components to the display controller 114 and the display device and the input / output (I / O) device 115. The input / output (I / O) device 115 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 115 is connected to the system through an input / output (I / O) controller 116.

[0148] 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.

[0149] 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.

[0150] These computer program instructions may be stored in a computer-readable memory that can direct 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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 site determination method, applied to online bus booking, characterized in that: The method comprises: Get historical order data of online ride-hailing services; Determine a plurality of aggregation point sets according to the distribution of pick-up point locations and / or drop-off point locations in the historical order data of the online car-hailing service; Screening the points in the clustered point set based on a preset screening strategy to determine a corresponding candidate point set; Determine a reference point according to the candidate points in the candidate point set; The fixed site is determined according to the positional relationship between the reference point and the route point on the fixed route.

2. The method according to claim 1, characterized in that The screening of points in the clustered point set based on a preset screening strategy to determine a corresponding candidate point set includes: Extracting points whose heat values ​​reach a preset heat value from the gathering point set to determine a preselected point set; The points in the pre-selected point set are clustered based on the distances between the points to determine a candidate point set corresponding to the pre-selected point set.

3. The method according to claim 2, characterized in that The extracting points whose heat values ​​reach a preset heat value from the gathering point set and determining the pre-selected point set comprises: Extracting points whose heat values ​​reach a preset heat value from the aggregation point set, and determining an initial point set; The points in the initial point set are thinned out by distance to determine a pre-selected point set.

4. The method according to claim 1, characterized in that: Determining the reference point according to the candidate points in the candidate point set includes: Sorting the candidate points in the candidate point set according to the heat values; The candidate point with the highest heat value is determined as the reference point.

5. The method according to claim 1, characterized in that Determining the reference point according to the candidate points in the candidate point set includes: Determine at least one recommended point corresponding to the candidate point set, the recommended point being a point whose sum of distances from each candidate point in the candidate point set is less than a preset distance value; The reference point position corresponding to the candidate point set is determined according to each of the recommended points.

6. The method according to claim 5, characterized in that Determining the reference point corresponding to the candidate point set according to each of the recommended points includes: A reference point is determined from the recommended points based on the sum of distances and / or heat values ​​corresponding to the recommended points.

7. The method according to claim 1, characterized in that Determining the fixed site according to the positional relationship between the reference point and the route point on the fixed route includes: Determine the route point closest to the reference point on the fixed route as an available site; Determining matching parameters between the available site and each candidate point in the candidate point set; evaluating the available sites according to the matching parameters; In response to the available site meeting a preset condition, the available site is determined as a fixed site.

8. The method according to claim 7, characterized in that The matching parameter includes at least one of a distance parameter, a convenience parameter and a security parameter; The preset condition includes at least one of a distance parameter being less than a preset distance, a convenience parameter being greater than a preset convenience parameter value, and a safety factor being greater than a preset safety factor value; Among them, the distance parameter is used to characterize the arrival distance between the candidate point and the available site, the convenience parameter is used to characterize the convenience of the candidate point to reach the available site, and the safety parameter is used to characterize the safety factor of the candidate point to reach the available site.

9. The method according to claim 1, characterized in that: The step of determining at least one fixed site in the fixed route according to each of the candidate point sets further comprises: The position of each of the fixed sites is adjusted based on a preset constraint condition, where the constraint condition is determined according to at least one of the distance between the fixed sites, the flow of people at the fixed sites, and a threshold value of the number of fixed sites.

10. A site recommendation method, applied to online bus booking, characterized in that: The method comprises: Get historical order data of online ride-hailing services; Generate a fixed route based on the historical order data of the online car-hailing service; Determine a plurality of aggregation point sets according to the distribution of pick-up point locations and / or drop-off point locations in the historical order data of the online car-hailing service; Screening the points in the clustered point set based on a preset screening strategy to determine a corresponding candidate point set; Determine a reference point according to the candidate points in the candidate point set; Determine a fixed site according to a positional relationship between the reference point and a route point on the fixed route; Storing the fixed sites corresponding to each candidate point set in a site library; In response to receiving a ride request, a fixed station in a station library is recommended to a passenger based on a ride point in the ride request.

11. A station determination device, applied to online bus booking, characterized in that: The device comprises: A data acquisition unit, used to acquire historical order data of online ride-hailing services; A point analysis unit is used to determine a plurality of clustered point sets according to the distribution of the pickup point locations and / or the drop-off point locations in the historical order data of the online car-hailing service; and to screen the points in the clustered point sets based on a preset screening strategy to determine a corresponding candidate point set; The site determination unit is used to determine a reference point according to the candidate points in the candidate point set; and determine a fixed site according to the positional relationship between the reference point and the route points on the fixed route.

12. A station recommendation system, applied to online bus booking, characterized in that: The system comprises: Data acquisition module, used to obtain historical order data of online ride-hailing services; Route determination module, used to generate fixed routes based on historical order data of online ride-hailing; A station determination module is used to determine a plurality of clustered point sets according to the distribution of the pickup point locations and / or the drop-off point locations in the historical order data of the online car-hailing service; screen the points in the clustered point set based on a preset screening strategy to determine a corresponding candidate point set; determine a reference point according to the candidate points in the candidate point set; and determine a fixed station according to the positional relationship between the reference point and the route points on the fixed route; The station recommendation module is used to store the fixed stations corresponding to each candidate point set in a station library; in response to receiving a ride request, recommend the fixed stations in the station library to the passenger based on the ride point in the ride request.

13. 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 10 is implemented.

14. 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 10.

15. 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 10 is implemented.

Images