Method, device, equipment and medium for recommending ridesharing stations based on hierarchical filtering

Abstract

The method, device, equipment and medium for recommending ride-sharing stations based on hierarchical filtering provided by the present invention relate to the field of shared transportation technology. The present invention draws a first filtering area covering all route points according to the national site data and the route points of the initial itinerary path of any ride-sharing, thereby obtaining a first site set; then insert any site of the first site set into the initial itinerary path, construct a new itinerary path, traverse and calculate the on-the-way coefficients of all sites in the first site set, and obtain a second site set; then select any two sites in the second site set for combination, construct a simulated new path, and obtain a third site set by calculating the on-the-way coefficient; finally, determine whether the new passenger boarding site obtained belongs to the third site set, and if so, output the corresponding alighting site. The present invention can effectively reduce the generation of a large number of invalid site combinations, avoid redundant calculations and waste of resources, and can calculate the recommended alighting site for the ride-sharing more quickly.

Description

Technical Field

[0001] The present invention relates to the field of shared transportation technology, and in particular to a method, device, equipment and medium for recommending ridesharing stations based on hierarchical filtering. Background Art

[0002] With the rapid development of the sharing economy, ride-sharing services, as a green travel mode, have been favored by more and more users. Ride-sharing services can not only effectively utilize idle social capacity, reduce energy consumption and carbon emissions, but also alleviate urban traffic pressure. However, how to further improve the convenience and user experience of ride-sharing services in practical applications is still a problem that needs continuous exploration and optimization. In the traditional ride-sharing matching system, passengers usually need to manually enter their own pick-up and drop-off points, and the system will match the driver's itinerary based on this information. This method played an important role in early applications, but it also gradually exposed its shortcomings. If passengers set the pick-up and drop-off points by themselves, the accuracy and flexibility of the matching results will be limited, and the setting locations may be unreasonable or not meet actual needs, and the best solution cannot be achieved, affecting the user experience.

[0003] In order to solve the above problems, existing systems have tried to recommend eligible alighting stations after passengers choose the boarding station. With this improvement, passengers can choose the most convenient alighting point for themselves from multiple recommended alighting stations, and then travel by subway, shared bicycles and other transportation methods. This not only improves the flexibility of matching, but also optimizes the user experience, allowing passengers to find a suitable alighting location more conveniently. However, this method still faces efficiency challenges in practical applications, because it is necessary to combine and match all possible matching stations, that is, it is necessary to combine and match the stations in the administrative area where the starting point and the administrative area where the end point are located. Therefore, there will be a large number of invalid station combination calculations, and the recommendation efficiency is slow, especially during peak hours, which is easy to cause system response delays and affect the overall service quality.

[0004] In view of this, the applicant filed this application after studying the existing technology. Summary of the invention

[0005] The present invention aims to provide a method, device, equipment and medium for recommending ride-sharing stations based on hierarchical filtering, so as to address the shortcomings of existing methods, improve the service quality and efficiency of ride-sharing, reduce the calculation of invalid combinations, improve the efficiency of algorithm recommendation, and provide passengers with a better service experience.

[0006] In order to solve the above technical problems, the present invention is implemented through the following technical solutions:

[0007] A method for recommending ridesharing stations based on hierarchical filtering, comprising:

[0008] S1, obtaining the trip data of the national ride-sharing service, and obtaining a national site set after preprocessing; wherein the national site set includes the latitude and longitude of the site;

[0009] S2, selecting an initial travel path of any hitchhiking car, and drawing a first filtering area covering all the waypoints according to the waypoints of the initial travel path, so as to obtain all the stopover sites in the first filtering area, i.e., a first site set; wherein the first site set is a subset of the national site set;

[0010] S3, inserting any one station in the first station set into the initial travel path, constructing a new travel path for the rideshare, and calculating the co-ordination coefficient of the new travel path and the initial travel path, traversing and calculating the co-ordination coefficients of all stations in the first station set, and then obtaining all stations in the first station set whose co-ordination coefficients meet the preset standard, i.e., the second station set;

[0011] S4, selecting any two stations in the second station set for combination as the boarding station and the alighting station respectively, constructing a new path, i.e., simulating the new path, calculating the co-ordination coefficient of the simulated new path and the initial travel path, and then obtaining all stations in the second station set whose co-ordination coefficients meet the preset standard, i.e., the third station set;

[0012] S5, based on the acquired new passenger boarding point, determine whether the new passenger boarding point belongs to the third point set, if it does, output the alighting point corresponding to the new passenger boarding point, that is, all the alighting points recommended for the ride-sharing.

[0013] Preferably, S2 is specifically:

[0014] According to the initial travel path, a list of waypoints of the rideshare travel path is obtained;

[0015] According to the list of waypoints and the preset maximum value of the trip percentage, the minimum filtered straight-line distance of the ride-sharing trip is obtained by binary search, and then the filtering area is drawn according to the minimum filtered straight-line distance to obtain the percentage of the minimum filtered straight-line distance of the ride-sharing and the trip mileage; wherein, the preset maximum value of the trip percentage is obtained by statistically analyzing the percentage data of the minimum filtered straight-line distance of a large number of ride-sharing trips to the trip mileage, and selecting the maximum value of the percentage as the preset maximum value of the trip percentage;

[0016] According to the percentage of the minimum filtered straight-line distance of the ride-sharing car to the travel mileage and the initial travel path, the filtered straight-line distance required for the ride-sharing car travel path is obtained;

[0017] According to the conversion coefficient between kilometers and latitude, the filtering straight-line distance required for the ride-sharing route is converted into the corresponding latitude degree, thereby generating a polygonal area, namely, the polygonal filtering area; the polygonal filtering area is calculated as follows:

[0018] ;

[0019] ;

[0020] in, is the filtering straight line distance; is the conversion factor between kilometers and latitude; is the latitude after conversion; filtering an area for said polygon; To generate a regional function around the geometric object L;

[0021] L is a linear geometry object, which represents the position and shape of the path in geographic space;

[0022] ;

[0023] Among them, the LineString function is a linear geometric object drawing function. is the longitude of the nth waypoint, is the latitude of the nth waypoint;

[0024] The national site set is traversed to determine whether a site is within the polygonal filtering area, and all sites within the filtering area are obtained, namely, the first site set.

[0025] Preferably, the filtering straight-line distance required for the ride-sharing route is:

[0026] = * ;

[0027] in, is the filtering straight line distance; is the mileage of the ride, that is, the mileage of the initial journey path, The percentage of the minimum filtering straight-line distance for ride-sharing to the trip mileage.

[0028] Preferably, the calculation formula of the co-route coefficient between the new travel path and the initial travel path is:

[0029] ;

[0030] in, is the co-route coefficient, is the mileage of the new travel route.

[0031] Preferably, the mileage of the new travel path and the mileage of the initial travel path are the mileages of corresponding paths recommended by the GPS navigation system by default.

[0032] The present invention also provides a device for recommending rideshare sites based on hierarchical filtering, comprising:

[0033] A station data acquisition unit is used to acquire the trip data of the national ride-sharing service, and obtain a national station set after preprocessing; wherein the national station set includes the latitude and longitude of the station;

[0034] The first layer filtering unit is used to obtain a first site set, select an initial travel path of any rideshare, and draw a first filtering area covering all waypoints according to the waypoints of the initial travel path, so as to obtain all the stop-by sites in the first filtering area, i.e., a first site set; wherein the first site set is a subset of the national site set;

[0035] The second layer filtering unit is used to obtain a second site set, insert any site in the first site set into the initial travel path, construct a new travel path for the rideshare, calculate the co-travel coefficient of the new travel path and the initial travel path, traverse and calculate the co-travel coefficients of all sites in the first site set, and then obtain all sites in the first site set whose co-travel coefficients meet the preset standard, i.e., the second site set;

[0036] The third-layer filtering unit is used to obtain a third site set, select any two sites in the second site set for combination, respectively as a boarding site and an alighting site, construct a new path, i.e., simulate a new path, calculate a co-location coefficient between the simulated new path and the initial travel path, and then obtain all sites in the second site set whose co-location coefficients meet a preset standard, i.e., a third site set;

[0037] The station recommendation unit is used to determine whether the new passenger boarding station belongs to the third station set based on the acquired new passenger boarding station. If it does, output the alighting station corresponding to the new passenger boarding station, that is, all the alighting stations recommended for the ride-sharing.

[0038] The present invention also provides a ride-sharing site recommendation device based on hierarchical filtering, including a processor and a memory, wherein a computer program is stored in the memory, and the computer program can be executed by the processor to implement a ride-sharing site recommendation method based on hierarchical filtering as described above.

[0039] The present invention also provides a computer-readable storage medium, on which computer-readable instructions are stored. When the computer-readable instructions are executed by a processor of a device where the computer-readable storage medium is located, the method for recommending ride-sharing stations based on hierarchical filtering as described above is implemented.

[0040] In summary, compared with the prior art, the present invention has the following beneficial effects:

[0041] The present invention is based on hierarchical filtering technology, by screening out the first site set that is on the way with the initial itinerary path of the ride, and then inserting each site in the first site set into the initial itinerary path to form a new path, and calculating the sites on the way with the new path and the initial itinerary path, thereby obtaining a second site set, and then performing two-by-two combination matching according to the second site set to obtain a third site set. The present invention can effectively reduce the generation of a large number of invalid site combinations, avoid redundant calculations and waste of resources, and can more quickly calculate the recommended get-off site for the ride under limited computing resources. In addition, while ensuring efficiency, the present invention greatly optimizes and improves the overall experience of users. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0043] Figure 1 A schematic diagram of a method for recommending ridesharing stations based on hierarchical filtering provided in Example 1 of the present invention.

[0044] Figure 2 A schematic diagram of the process of preprocessing site data provided in the first embodiment of the present invention.

[0045] Figure 3 A schematic diagram of a flow chart of the filtering area provided in the first embodiment of the present invention.

[0046] Figure 4 A schematic diagram of the three-layer filtering process provided in Example 1 of the present invention.

[0047] Figure 5 A schematic diagram of the site recommendation process provided in the first embodiment of the present invention.

[0048] Figure 6 This is a visualization diagram of the experimental results of trip B provided in Example 1 of the present invention.

[0049] Figure 7A schematic diagram of a ride-sharing station recommendation device based on hierarchical filtering provided in Embodiment 2 of the present invention.

[0050] The present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the invention claimed for protection, but merely represents the selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0052] Embodiment 1

[0053] Embodiment 1 of the present invention provides a method for recommending ridesharing stations based on hierarchical filtering, which can be implemented by a ridesharing station recommendation device based on hierarchical filtering (hereinafter referred to as recommendation device), and in particular, executed by one or more processors in the recommendation device.

[0054] In this embodiment, the recommendation device may be an electronic device equipped with a processor, which has a computer program of the ride-sharing site recommendation method based on hierarchical filtering and can be executed, such as a computer, a smart phone, a smart tablet, a workstation, etc., which is not limited here.

[0055] like Figure 1 As shown, a method for recommending ridesharing stations based on hierarchical filtering includes steps S1 to S5.

[0056] S1, obtain the travel data of hitchhiking across the country, and obtain the national site set after preprocessing; wherein, the national site set includes the latitude and longitude of the site.

[0057] Specifically, Figure 2 As shown in the figure, from the national ride-sharing trip data, the longitude and latitude of the station are used as the unique identifier, and the information of all boarding stations and all alighting stations are merged and deduplicated to obtain the national station set. .

[0058] Among them, the definition , Indicates sites, Indicates the total number of sites nationwide.

[0059] Of course, it is also possible to obtain the ride data of a specific province, city or region according to the actual situation to reduce the amount of data calculation. The above situation is also within the protection scope of the present invention and does not affect the implementation of the present invention.

[0060] S2, selecting an initial travel path of any hitchhiking car, and drawing a first filtering area covering all the waypoints according to the waypoints of the initial travel path, so as to obtain all the stopover sites in the first filtering area, i.e., a first site set; wherein the first site set is a subset of the national site set;

[0061] Specifically, the S2 specifically includes S21 to S25:

[0062] S21, obtaining a list of waypoints of the ride-sharing route according to the initial route.

[0063] Specifically, define a list of waypoints , all the waypoints of the itinerary can be obtained through existing open GPS navigation systems, such as the driving route planning interface of the AutoNavi system open platform.

[0064] in, is the longitude of the nth waypoint; is the latitude of the nth waypoint.

[0065] S22, according to the list of waypoints and the preset maximum value of the trip percentage, the minimum filtered straight-line distance of the ride-sharing trip is obtained through a binary search method, and then a filtering area is drawn according to the minimum filtered straight-line distance to obtain the percentage of the minimum filtered straight-line distance of the ride-sharing and the trip mileage; wherein, the preset maximum value of the trip percentage is obtained by statistically analyzing a large number of percentage data of the minimum filtered straight-line distance of the ride-sharing trips to the trip mileage, and selecting the maximum value of the percentage as the preset maximum value of the trip percentage.

[0066] In this embodiment, binary search is a search algorithm for finding a specific element in an ordered array. The search process starts from the middle element of the array. If the middle element is exactly the element to be found, the search process ends; if a specific element is greater than or less than the middle element, the search is performed in the half of the array that is greater than or less than the middle element, and the comparison starts from the middle element as at the beginning.

[0067] S23, according to the percentage of the minimum filtered straight-line distance of the ride-sharing and the travel mileage and the initial travel path, the filtered straight-line distance required for the ride-sharing travel path is obtained.

[0068] Specifically, the filtered straight-line distance required for the ride-sharing route is:

[0069] = * ;

[0070] in, is the filtering straight line distance; is the mileage of the ride, that is, the mileage of the initial journey path, The percentage of the minimum filtering straight-line distance for ride-sharing to the trip mileage.

[0071] S24, according to the conversion coefficient between kilometers and latitude, the filtering straight-line distance required for the ride-sharing route is converted into the corresponding latitude degree, thereby generating a polygonal area, i.e., the polygonal filtering area; the polygonal filtering area is calculated as follows:

[0072] ;

[0073] ;

[0074] in, is the filtering straight line distance; is the conversion factor between kilometers and latitude; is the latitude after conversion; filtering an area for said polygon; To generate a regional function around the geometric object L;

[0075] L is a linear geometry object, which represents the position and shape of the path in geographic space;

[0076] ;

[0077] The LineString function is a linear geometry object drawing function, which is used to describe the geometry of line segments and curves.

[0078] The filtered straight-line distance is converted from kilometers to units suitable for longitude and latitude. Since the latitude is almost fixed around the world, that is, each degree of latitude is approximately equal to 110.574 kilometers, the conversion factor is Set to 110.574 to convert the filtered straight-line distance from kilometers to the corresponding latitude degrees.

[0079] Specifically, the polygon filtering area The drawing process is as follows Figure 3 shown.

[0080] S25, traversing the national site set, determining whether a site is within the polygonal filtering area, and obtaining all sites within the filtering area, namely, the first site set.

[0081] Specifically, Figure 4 The schematic diagram of the three-layer filtering process is shown in FIG. The sites in the national site set are traversed to see whether they are within the polygonal filtering area, and the site set within the polygonal filtering area is obtained, that is, the first site set. ,in Indicates the site information obtained by the first layer of filtering. Indicates the total number of sites obtained by first-level filtering.

[0082] S3, insert any station in the first station set into the initial travel path, construct a new travel path for the ride-sharing, and calculate the co-ordination coefficient of the new travel path and the initial travel path, traverse and calculate the co-ordination coefficients of all stations in the first station set, and then obtain all stations in the first station set whose co-ordination coefficients meet the preset standards, i.e., the second station set.

[0083] In this embodiment, the initial travel path is the starting point-end point of the driver's trip. Through the driving route planning interface of the open platform of GPS navigation system such as AutoNavi, the mileage information of the default path recommended by AutoNavi is obtained to obtain the mileage of the initial travel path.

[0084] In this embodiment, a site of the first site set is selected and inserted into the itinerary to obtain a new itinerary path, which is the starting point-site-end point. Then, through the driving route planning interface of the AutoNavi GPS navigation system open platform, the mileage information of the default path recommended by AutoNavi is obtained, that is, the mileage of the new itinerary path.

[0085] Then, the co-route coefficient between the new travel path and the initial travel path is calculated, and the calculation formula is:

[0086] ;

[0087] in, is the co-route coefficient, is the mileage of the initial travel path, is the mileage of the new travel route.

[0088] If the calculated co-location coefficient meets the set co-location coefficient standard, it is a co-location station, and then all stations whose co-location coefficients meet the preset standard in the first station set are obtained, that is, the second station set. = , Indicates the first Site information, Indicates the total number of sites obtained by second-level filtering.

[0089] S4, select any two stations in the second station set for combination, respectively as the boarding station and the alighting station, construct a new path, i.e. simulate the new path, calculate the co-ordination coefficient of the simulated new path and the initial travel path, and then obtain all stations in the second station set whose co-ordination coefficients meet the preset standards, i.e., the third station set.

[0090] In this embodiment, the second site set in S3 = , any two station combinations are matched, one as the boarding station and the other as the alighting station, and inserted into the initial trip path , get a simulated new path, then calculate the simulated new path and the initial travel path Then select the site combination that meets the set standard of the co-location coefficient, that is, the third site set.

[0091] In this embodiment, the standard that the co-location coefficient meets can be set according to actual conditions and is not limited here.

[0092] S5, based on the acquired new passenger boarding point, determine whether the new passenger boarding point belongs to the third point set, if it does, output the alighting point corresponding to the new passenger boarding point, that is, all the alighting points recommended for the ride-sharing.

[0093] In this embodiment, if Figure 5 As shown in the flow chart of site recommendation, when a hitchhiking driver publishes a trip, after layered filtering to obtain the stop combination (i.e., the third stop set) of the trip, as long as the boarding stop selected by the passenger is among the boarding stops of any stop combination, the corresponding alighting stop information will be recommended to the passenger. If there are multiple stop combinations that meet the requirements, multiple alighting stop information will be recommended to the passenger. Assuming the third stop set =[( ),( ),( ), ], the new passenger boarding station is , then the alighting station recommended by the method of the present invention is , .

[0094] If there is no matching stop combination, the passenger will be informed that there is no matching stop. The set stop coefficient may also be appropriately lowered to expand the range of stop combinations, which is not limited here.

[0095] In another specific embodiment, the ride-sharing trip data of an online car-hailing operating company is selected as the research object. As shown in Table 1, the data is selected from June 1, 2024 to July 31, 2024.

[0096] Table 1: Rideshare trip data

[0097] Fields Example Departure area Jimei District, Xiamen Departure station address Line 1, Jimei Software Park Station, Exit 4 Departure station longitude 24.61362821 Departure station latitude 118.04858481 Arrival Area Jimei District, Xiamen Arrival site address Building 08, Zone D, Jimei Software Park Arrival point longitude 24.61004709 Arrival site latitude 118.03814959

[0098] After preprocessing the data, the site data information is shown in Table 2.

[0099] Table 2: Site data information

[0100] Fields Example Site Address Line 1, Jimei Software Park Station, Exit 4 Site longitude 24.61362821 Site Latitude 118.04858481

[0101] After counting the percentage of the minimum filtered straight-line distance of a large number of trips in advance, the binary search method is used to reverse the calculation and the maximum percentage is selected as the standard. The results are shown in Table 3.

[0102] Table 3: Partial data of the trip

[0103]

[0104] In this embodiment, according to the statistical results, 50% is finally selected as the standard.

[0105] The evaluation indicators are shown in Table 4.

[0106] Table 4: Evaluation indicators

[0107]

[0108] The set on-the-go coefficient standard is 80%, and the comparison method is the traditional method (i.e., calculating all combinations of sites in the starting area and the arrival area of ​​the trip to obtain the on-the-go site combination). The comparison of the time complexity of the two methods and the number of third-party (AutoNavi) API calls is shown in Table 5.

[0109] Time complexity of layered filtering:

[0110] 1) The first layer of filtering draws the filtering area based on the passing points, and the time complexity is , is the number of waypoints; get the sites in the filter area, that is, the first site set, the time complexity , is the number of all sites. The total time complexity is . API call count: 1.

[0111] 2) The second layer of filtering is to obtain the stops along the way in the filtering area, i.e. the second stop set. The time complexity is , The number of sites in the filtering area. Number of API calls Second-rate.

[0112] 3) The third layer of filtering is to obtain the combination of sites along the way, that is, the third site set. The time complexity is ), The number of stops along the way in the filtering area. API call times Second-rate.

[0113] in, .

[0114] Traditional method:

[0115] Get the combination of stops along the way, time complexity ), The number of all sites. Number of API calls Second-rate.

[0116] Table 5: Comparison results of the two methods ( )

[0117]

[0118] We select three trips with different mileages to display the experimental results. The experimental results are shown in Table 6. The results of the stops along the way for trip B are shown in Table 6. Figure 6 shown.

[0119] Table 6: Experimental results

[0120]

[0121] The symbol '-' in the table indicates that the method does not have this process.

[0122] Experimental results analysis:

[0123] Through the analysis of experimental results, the calculation of hitchhiking stop combinations based on the hierarchical filtering method shows significant improvements in various evaluation indicators compared with the traditional method:

[0124] (1) Under different mileages, the method of the present invention can filter the stations in just over 10 seconds, and the number of station combination matches is significantly reduced, from 12,210 to 210 for trip A, from 12,210 to 702 for trip B, and from 18,090 to 3,782 for trip C. At the same time, the total time cost of obtaining the combination of stop-by-trip stations is also significantly reduced, from 1,828.42 seconds to 27.28 seconds for trip A, from 1,972.46 seconds to 88.98 seconds for trip B, and from 3,034.46 seconds to 741.5 seconds for trip C. The results show that the method of the present invention effectively reduces the generation of a large number of invalid combinations when matching the stop-by-trip station combination of the trip, greatly shortening the time cost.

[0125] (2) Under different mileages, the accuracy of trip A, trip B, and trip C increased from 0.43% to 25.24%, 2.82% to 49.00%, and 10.34% to 49.50% respectively. The results show that the matching results of the two methods are consistent, but the accuracy of the method of the present invention is significantly improved when matching the combination of stops along the way. The higher the accuracy, the faster the time to obtain the combination of stops along the way, indicating that this method has the characteristics of fast recommendation.

[0126] In summary, compared with the prior art, the present invention has the following beneficial effects:

[0127] The method of the present invention can preferentially screen out sites that are along the driver's route through the hierarchical filtering technology, and then perform pairwise matching. Compared with the existing all-site combination method, the hierarchical filtering method can more effectively utilize computing resources, effectively reduce the generation of a large number of invalid combinations, avoid redundant calculations and waste of resources, and achieve the purpose of rapid recommendation. In addition, while ensuring efficiency, it can greatly improve the overall user experience.

[0128] Embodiment 2

[0129] like Figure 7 As shown, the second embodiment of the present invention further provides a device for recommending rideshare stations based on hierarchical filtering, comprising:

[0130] The site data acquisition unit 101 is used to acquire the trip data of the national ride-sharing service, and obtain the national site set after preprocessing; wherein the national site set includes the latitude and longitude of the site;

[0131] The first layer filtering unit 102 is used to obtain a first site set, select an initial travel path of any rideshare, and draw a first filtering area covering all waypoints according to the waypoints of the initial travel path, so as to obtain all the stop-by sites in the first filtering area, i.e., a first site set; wherein the first site set is a subset of the national site set;

[0132] The second layer filtering unit 103 is used to obtain a second site set, insert any site in the first site set into the initial travel path, construct a new travel path for the rideshare, calculate the co-ordination coefficient of the new travel path and the initial travel path, traverse and calculate the co-ordination coefficients of all sites in the first site set, and then obtain all sites in the first site set whose co-ordination coefficients meet the preset standard, i.e., the second site set;

[0133] The third layer filtering unit 104 is used to obtain a third site set, select any two sites in the second site set to combine as a boarding site and an alighting site, respectively, to construct a new path, i.e., simulate a new path, calculate the co-ordination coefficient of the simulated new path and the initial travel path, and then obtain all sites in the second site set whose co-ordination coefficients meet the preset standard, i.e., a third site set;

[0134] The station recommendation unit 105 is used to determine whether the new passenger boarding station belongs to the third station set based on the acquired new passenger boarding station. If it does, output the alighting station corresponding to the new passenger boarding station, that is, all the alighting stations recommended for the ride-sharing.

[0135] Embodiment 3

[0136] The third embodiment of the present invention also provides a ride-sharing station recommendation device based on hierarchical filtering, which includes a memory and a processor, wherein a computer program is stored in the memory, and the computer program can be executed by the processor to implement the ride-sharing station recommendation method based on hierarchical filtering as described above.

[0137] Embodiment 4

[0138] The fourth embodiment of the present invention also provides a computer-readable storage medium, on which computer-readable instructions are stored. When the computer-readable instructions are executed by a processor of a device where the computer-readable storage medium is located, the method for recommending ride-sharing stations based on hierarchical filtering as described above is implemented.

[0139] In several embodiments provided in the embodiments of the present invention, it should be understood that the disclosed apparatus and method can also be implemented in other ways. The apparatus and method embodiments described above are merely schematic. For example, the flowcharts in the accompanying drawings show the possible architecture, functions and operations of the apparatus, method and computer program product according to multiple embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, program segment or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0140] In addition, the functional modules in the various embodiments of the present invention may be integrated together to form an independent part, or each module may exist independently, or two or more modules may be integrated to form an independent part.

[0141] If the function is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, an electronic device, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. 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 code. It should be noted that in this article, the term "include", "include" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements that are not explicitly listed, or also includes elements inherent to such process, method, article or device. Without more constraints, an element defined by the phrase "comprising a..." does not exclude the existence of other identical elements in the process, method, article or apparatus comprising the element.

[0142] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The singular forms "a", "said" and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings.

[0143] It should be understood that the term "and / or" used in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0144] The word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.

[0145] The "first\second" mentioned in the embodiments is only to distinguish similar objects, and does not represent a specific order for the objects. It is understandable that the "first\second" can be interchanged with the specific order or sequence where permitted. It should be understood that the objects distinguished by "first\second" can be interchanged where appropriate, so that the embodiments described herein can be implemented in an order other than those illustrated or described herein.

[0146] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for recommending ridesharing stations based on hierarchical filtering, characterized in that: include: S1, obtaining the trip data of the national ride-sharing service, and obtaining a national site set after preprocessing; wherein the national site set includes the latitude and longitude of the site; S2, select the initial travel path of any hitchhiking car, draw a first filtering area covering all the waypoints according to the waypoints of the initial travel path, so as to obtain all the stopover sites in the first filtering area, that is, the first site set; wherein the first site set is a subset of the national site set; S2 is specifically: According to the initial travel path, a list of waypoints of the rideshare travel path is obtained; According to the list of waypoints and the preset maximum value of the trip percentage, the minimum filtered straight-line distance of the ride-sharing trip is obtained by binary search, and then the filtering area is drawn according to the minimum filtered straight-line distance to obtain the percentage of the minimum filtered straight-line distance of the ride-sharing and the trip mileage; wherein, the preset maximum value of the trip percentage is obtained by statistically analyzing the percentage data of the minimum filtered straight-line distance of a large number of ride-sharing trips to the trip mileage, and selecting the maximum value of the percentage as the preset maximum value of the trip percentage; According to the percentage of the minimum filtered straight-line distance of the ride-sharing car to the travel mileage and the initial travel path, the filtered straight-line distance required for the ride-sharing car travel path is obtained; According to the conversion coefficient between kilometers and latitude, the filtering straight-line distance required for the ride-sharing route is converted into the corresponding latitude degree, thereby generating a polygonal area, namely, the polygonal filtering area; the polygonal filtering area is calculated as follows: ； ； in, is the filtering straight line distance; is the conversion factor between kilometers and latitude; is the latitude after conversion; filtering an area for said polygon; To generate a regional function around the geometric object L; L is a linear geometry object, which represents the position and shape of the path in geographic space; ； Among them, the LineString function is a linear geometric object drawing function. is the longitude of the nth waypoint, is the latitude of the nth waypoint; Traversing the national site set, determining whether a site is within the polygonal filtering area, and obtaining all sites within the filtering area, namely, the first site set; S3, inserting any one station in the first station set into the initial travel path, constructing a new travel path for the rideshare, and calculating the co-ordination coefficient of the new travel path and the initial travel path, traversing and calculating the co-ordination coefficients of all stations in the first station set, and then obtaining all stations in the first station set whose co-ordination coefficients meet the preset standard, i.e., the second station set; S4, selecting any two stations in the second station set for combination as the boarding station and the alighting station respectively, constructing a new path, i.e., simulating the new path, calculating the co-ordination coefficient of the simulated new path and the initial travel path, and then obtaining all stations in the second station set whose co-ordination coefficients meet the preset standard, i.e., the third station set; S5, based on the acquired new passenger boarding point, determine whether the new passenger boarding point belongs to the third point set, if it does, output the alighting point corresponding to the new passenger boarding point, that is, all the alighting points recommended for the ride-sharing.

2. A method for recommending rideshare stations based on hierarchical filtering according to claim 1, characterized in that ,The calculation method of filtering straight line distance required for the ride trip path is as follows: = * ； in, is the filtering straight line distance; is the mileage of the ride, that is, the mileage of the initial journey path, The percentage of the minimum filtering straight-line distance for ride-sharing to the trip mileage.

3. A method for recommending rideshare stations based on hierarchical filtering according to claim 2, characterized in that ,The calculation formula of the co-route coefficient between the new travel path and the initial travel path is: ； in, is the co-route coefficient, is the mileage of the new travel route.

4. A method for recommending rideshare stations based on hierarchical filtering according to claim 3, characterized in that ,The mileage of the new travel path and the mileage of the initial travel path are the mileages of the corresponding paths recommended by the GPS navigation system by default.

5. A device for recommending rideshare stations based on hierarchical filtering, characterized in that: include: A station data acquisition unit is used to acquire the trip data of the national ride-sharing service, and obtain a national station set after preprocessing; wherein the national station set includes the latitude and longitude of the station; The first layer filtering unit is used to obtain a first site set, select an initial travel path of any rideshare, and draw a first filtering area covering all waypoints according to the waypoints of the initial travel path, so as to obtain all the stop-by sites in the first filtering area, i.e., a first site set; wherein the first site set is a subset of the national site set; specifically: According to the initial travel path, a list of waypoints of the rideshare travel path is obtained; According to the list of waypoints and the preset maximum value of the trip percentage, the minimum filtered straight-line distance of the ride-sharing trip is obtained by binary search, and then the filtering area is drawn according to the minimum filtered straight-line distance to obtain the percentage of the minimum filtered straight-line distance of the ride-sharing and the trip mileage; wherein, the preset maximum value of the trip percentage is obtained by statistically analyzing the percentage data of the minimum filtered straight-line distance of a large number of ride-sharing trips to the trip mileage, and selecting the maximum value of the percentage as the preset maximum value of the trip percentage; According to the percentage of the minimum filtered straight-line distance of the ride-sharing car to the travel mileage and the initial travel path, the filtered straight-line distance required for the ride-sharing car travel path is obtained; According to the conversion coefficient between kilometers and latitude, the filtering straight-line distance required for the ride-sharing route is converted into the corresponding latitude degree, thereby generating a polygonal area, namely, the polygonal filtering area; the polygonal filtering area is calculated as follows: ； ； in, is the filtering straight line distance; is the conversion factor between kilometers and latitude; is the latitude after conversion; filtering an area for said polygon; To generate a regional function around the geometric object L; L is a linear geometry object, which represents the position and shape of the path in geographic space; ； Among them, the LineString function is a linear geometric object drawing function. is the longitude of the nth waypoint, is the latitude of the nth waypoint; Traversing the national site set, determining whether a site is within the polygonal filtering area, and obtaining all sites within the filtering area, namely, the first site set; The second layer filtering unit is used to obtain a second site set, insert any site in the first site set into the initial travel path, construct a new travel path for the rideshare, calculate the co-travel coefficient of the new travel path and the initial travel path, traverse and calculate the co-travel coefficients of all sites in the first site set, and then obtain all sites in the first site set whose co-travel coefficients meet the preset standard, i.e., the second site set; The third-layer filtering unit is used to obtain a third site set, select any two sites in the second site set for combination, respectively as a boarding site and an alighting site, construct a new path, i.e., simulate a new path, calculate a co-location coefficient between the simulated new path and the initial travel path, and then obtain all sites in the second site set whose co-location coefficients meet a preset standard, i.e., a third site set; The station recommendation unit is used to determine whether the new passenger boarding station belongs to the third station set based on the acquired new passenger boarding station. If it does, output the alighting station corresponding to the new passenger boarding station, that is, all the alighting stations recommended for the ride-sharing.

6. A device for recommending rideshare stations based on hierarchical filtering according to claim 5, characterized in that ,The calculation formula of the co-route coefficient between the new travel path and the initial travel path in the second layer filtering unit is: in, is the co-route coefficient, is the mileage of the initial travel path, is the mileage of the new travel route.

7. A ride-sharing station recommendation device based on hierarchical filtering, characterized in that: It includes a processor and a memory, wherein the memory stores a computer program, and the computer program can be executed by the processor to implement a method for recommending ride-sharing sites based on hierarchical filtering as described in any one of claims 1-4.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor of a device where the computer-readable storage medium is located, implement a method for recommending ride-sharing stations based on hierarchical filtering as described in any one of claims 1 to 4.

Images