Pick-up point determination method, computer storage medium and computer program product

Abstract

The embodiment of the application provides a method for determining a pickup point, a computer storage medium and a computer program product, wherein the method for determining the pickup point comprises the following steps: generating a basic pickup point along a corresponding road according to road data in road network data and a preset distance interval; determining the heat of the basic pickup point according to the order pickup points of historical travel orders of the road in a preset time period; obtaining the basic pickup point with heat meeting a preset heat standard as a candidate basic pickup point; comparing the candidate basic pickup point with a pre-screened experience pickup point, and generating a recommended pickup point on the road according to a comparison result. Through the embodiment of the application, a stable and more accurate pickup point can be provided.

Description

Technical Field

[0001] This application relates to the field of geographic information technology, and in particular to a method for determining a boarding point, a computer storage medium, and a computer program product. Background Technology

[0002] With the development of intelligent transportation technology, more and more people are relying on ride-hailing platforms for transportation. In this travel scenario, ride-hailing platforms intelligently recommend pick-up points based on passenger locations. The pick-up point needs to be a location where drivers and passengers can easily meet and where parking is convenient, in order to improve travel efficiency.

[0003] Existing ride-hailing platforms typically use clustering algorithms to determine pick-up points, identifying locations with a high frequency of pick-ups within a set of orders. However, the inventors discovered that clustering algorithms have a degree of randomness; even for the same set of orders within the same geographical area, different calculations yield different results. This makes it impossible to uniformly name pick-up points and leads to unstable (constantly changing) pick-up points recommended to users, resulting in a poor user experience. Summary of the Invention

[0004] In view of this, embodiments of this application provide a boarding point determination scheme to at least partially solve the above-mentioned problems.

[0005] According to a first aspect of the embodiments of this application, a method for determining a pick-up point is provided, comprising: generating basic pick-up points along corresponding roads based on road data in road network data and preset distance intervals; determining the popularity of basic pick-up points based on the order pick-up points of historical travel orders on the roads within a preset time period; obtaining candidate basic pick-up points whose popularity meets a preset popularity standard; comparing the candidate basic pick-up points with pre-screened experience pick-up points, and generating recommended pick-up points on the roads based on the comparison results.

[0006] According to a second aspect of the embodiments of this application, a pick-up point determination device is provided, comprising: a generation module, configured to generate basic pick-up points along corresponding roads based on road data in road network data and preset distance intervals; a popularity module, configured to determine the popularity of basic pick-up points based on the order pick-up points of historical travel orders on the roads within a preset time period; an acquisition module, configured to acquire candidate basic pick-up points whose popularity meets a preset popularity standard; and a determination module, configured to compare the candidate basic pick-up points with pre-screened experienced pick-up points, and generate recommended pick-up points on the roads based on the comparison results.

[0007] According to a third aspect of the present application, an electronic device is provided, comprising: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus; the memory is used to store at least one executable instruction, wherein the executable instruction causes the processor to perform an operation corresponding to the boarding point determination method described in the first aspect.

[0008] According to a fourth aspect of the embodiments of this application, a computer storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the boarding point determination method as described in the first aspect.

[0009] According to a fifth aspect of the embodiments of this application, a computer program product is provided, including computer instructions that instruct a computing device to perform an operation corresponding to the boarding point determination method described in the first aspect.

[0010] According to the pick-up point determination scheme provided in this application embodiment, based on the generated basic pick-up points on the road, candidate basic pick-up points and experienced pick-up points are compared and filtered, and the final recommended pick-up point is determined based on the comparison results. On the one hand, the basic pick-up points generated according to the preset distance interval are relatively stable and will not change repeatedly due to randomness issues; on the other hand, filtering based on the popularity of pick-up points selects the more popular, i.e., frequently used pick-up points, from the stable basic pick-up points. Furthermore, combining with experienced pick-up points, the selected more popular pick-up points can be further assisted in determining and correcting, resulting in more optimized pick-up points. Therefore, this application embodiment can provide stable and more accurate pick-up points. This also facilitates the unified naming of pick-up points and improves the user experience. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings.

[0012] Figure 1A This is a flowchart illustrating the steps of a method for determining a boarding point according to Embodiment 1 of this application;

[0013] Figure 1B for Figure 1A A schematic diagram of a scenario example in the illustrated embodiment;

[0014] Figure 2 This is a flowchart illustrating the steps of a method for determining a boarding point according to Embodiment 2 of this application;

[0015] Figure 3 This is a structural block diagram of a vehicle loading point determination device according to Embodiment 3 of this application;

[0016] Figure 4 This is a schematic diagram of the structure of an electronic device according to Embodiment 4 of this application. Detailed Implementation

[0017] To enable those skilled in the art to better understand the technical solutions in the embodiments of this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art should fall within the protection scope of the embodiments of this application.

[0018] The specific implementation of the embodiments of this application will be further described below with reference to the accompanying drawings.

[0019] Example 1

[0020] Reference Figure 1A The diagram shows a flowchart of a method for determining a boarding point according to Embodiment 1 of this application.

[0021] The method for determining the boarding point in this embodiment includes the following steps:

[0022] Step S102: Based on the road data in the road network data and the preset distance interval, generate the base entry point along the corresponding road.

[0023] The road network data contains a wealth of road data and information, including but not limited to: length, width, number of lanes, specific lane information, information on buildings on both sides of the lanes, POI (point of interest) information, intersection information, gap information, etc. Each road has its own corresponding road data.

[0024] To obtain relatively stable boarding point data, this embodiment also pre-sets the distance interval for determining boarding points. This distance interval can be set by those skilled in the art according to actual needs in practical applications, such as 30 meters. A smaller distance interval results in a higher density and more accurate boarding points, but also a greater data processing burden. Conversely, a larger distance interval results in a lower density of boarding points, but also a lighter data processing burden. Therefore, it is necessary to set an appropriate distance interval to achieve a balance between boarding point density and data processing burden. In one feasible approach, multiple interval levels can be set to correspond to different distance intervals. For example, there can be five levels: 1B, 2B, 3B, 4B, and 5B. Assuming 1B = 30 meters, then 2B = 60 meters, 3B = 90 meters, and so on. Specifically, for example, if road A is 3000 meters long, assuming level 1B is used, i.e., a distance interval of 30 meters, 3000 / 30 + 1 = 101 boarding points will be generated. Since the pick-up point needs to take into account the start or end point of the road, it needs to be "+1". However, in practical applications, considering the two sides of the road, a pick-up point at the corresponding position on the other side of the road can also be added.

[0025] The process of generating pick-up points on the road based on distance intervals is also called spraying points; that is, pick-up points are generated one by one on the road. In this embodiment of the application, the pick-up points generated by spraying points are called basic pick-up points.

[0026] Step S104: Determine the popularity of the basic pick-up point based on the order pick-up points of the historical travel orders of the road within the preset time period.

[0027] Typically, each travel order corresponds to a pick-up point, which is the actual pick-up location for the passenger. In this embodiment, the popularity of the basic pick-up point is obtained based on the basic pick-up point and the order pick-up point.

[0028] In practical applications, the corresponding base pick-up point can be determined based on its distance from different base pick-up points, thus determining the popularity of each base pick-up point. For example, if the distance between adjacent base pick-up points is 30 meters, a 15-meter boundary can be used to assign the popularity gained from the order pick-up point to the corresponding base pick-up point. For instance, for base pick-up points X and Y, if order pick-up point 1 is 10 meters from X and 20 meters from Y; order pick-up point 2 is 5 meters from X and 25 meters from Y; order pick-up point 3 is 12 meters from X and 18 meters from Y; order pick-up point 4 is 20 meters from X and 10 meters from Y; and order pick-up point 5 is 22 meters from X and 8 meters from Y, then the popularity of order pick-up points 1, 2, and 3 is assigned to base pick-up point X, meaning the popularity of base pick-up point X is 3; and the popularity of order pick-up points 4 and 5 is assigned to base pick-up point Y, meaning the popularity of base pick-up point Y is 2.

[0029] Therefore, the popularity of determining the basic boarding point based on the order boarding point makes this popularity relatively objective; at the same time, by mapping the order boarding point to the basic boarding point, since the basic boarding point is a stable boarding point, subsequent processing of the boarding point is based on the stable boarding point, thus ensuring the overall stability of the solution.

[0030] Furthermore, in this step, the preset time period can be appropriately set by those skilled in the art according to actual needs, such as one month, several months, or one year before the current date, etc., and this application embodiment does not limit this.

[0031] Step S106: Obtain base stations that meet the preset heat standards as candidate base stations.

[0032] The heat index can be set based on the heat index of the boarding point or processed before being set accordingly.

[0033] Based on this popularity value, those base stations that meet the preset popularity criteria (the popularity value can be the standard, or the popularity value can be a parameter to determine further criteria) can be selected from the base stations, which are then called candidate base stations.

[0034] Step S108: Compare the candidate basic boarding points with the pre-screened experienced boarding points, and generate recommended boarding points on the road based on the comparison results.

[0035] In this embodiment, experienced boarding points are pre-screened and set. These experienced boarding points can be set manually, selecting those POIs with a higher probability of actually boarding or a higher number of boarding times, and associating them with or mapping them to basic boarding points. However, this method is not limited to manual setting; big data statistics or other appropriate methods are also applicable.

[0036] Candidate boarding points are based on actual travel data, which can ensure that relatively objective boarding points are selected; experience-based boarding points are based on experience or statistical results and can serve as an auxiliary and supplementary measure to candidate boarding points.

[0037] Based on this, the candidate base pick-up points are compared with pre-screened experienced pick-up points to obtain comparison results. For example, the candidate base pick-up points and experienced pick-up points may completely overlap, partially overlap and partially miss each other, or completely miss each other. Based on this, corresponding recommended pick-up points on the road can be generated.

[0038] For example, for a given road, pick-up points that overlap with candidate pick-up points and experienced pick-up points are first identified as recommended pick-up points. Then, for the non-overlapping pick-up points, those skilled in the art can make appropriate settings according to actual needs, such as identifying the remaining candidate pick-up points as recommended pick-up points, or identifying the remaining experienced pick-up points as recommended pick-up points, etc. Each road has at least one recommended pick-up point. These recommended pick-up points can then be provided to ride-hailing platforms and recommended to passengers after they place a ride order.

[0039] The above process will be illustrated below with a specific example, such as... Figure 1B As shown.

[0040] exist Figure 1B In the example shown, assuming road X is 300M long, 300 / 30+1 = 11 basic boarding points are generated on road X at 30M intervals. Let these basic boarding points be boarding points A, B, C...K. Further assume that the calculated popularity values ​​of these 11 boarding points are 100, 10, 90, 12, 15, 95, 20, 50, 28, 130, and 10, respectively. Figure 1B In this example, the above information is represented by a line graph. The horizontal axis of the line graph represents the baseline boarding point, and the vertical axis represents the popularity value corresponding to each boarding point. We assume the experienced boarding points (shown as dashed rectangles in the graph) are boarding points A, C, H, and J. In this example, a popularity value of 80 is simply used as the popularity standard. However, those skilled in the art should understand that in practical applications, the setting of the popularity standard may be more complex and accurate. In this case, baseline boarding points A, C, F, and J are selected as candidate boarding points (shown as dashed circles in the graph). Among these candidate boarding points, A, C, and J overlap with the experienced boarding points and can be directly determined as recommended boarding points. However, boarding point F does not overlap with boarding point H. In this example, we simply assume that the experienced boarding point is selected over the candidate boarding points. Therefore, boarding point H is selected, while boarding point F is ignored. Finally, boarding points A, C, H, and J are determined as recommended boarding points. Similarly, if a candidate boarding point is selected as superior to an experienced boarding point, then boarding point H is ignored, boarding point F is selected, and finally boarding points A, C, F, and J will be used as recommended boarding points.

[0041] As can be seen, this embodiment uses the generated basic pick-up points on the road as a foundation, compares and filters them with candidate basic pick-up points and experienced pick-up points, and determines the final recommended pick-up point based on the comparison results. On the one hand, the basic pick-up points generated according to the preset distance interval are relatively stable and will not change repeatedly due to randomness. On the other hand, filtering based on the popularity of pick-up points selects the more popular, frequently used pick-up points from the stable basic pick-up points. Combining this with experienced pick-up points allows for further confirmation and correction of the selected more popular pick-up points, resulting in a more optimized pick-up point. Therefore, this embodiment can provide stable and more accurate pick-up points. This also facilitates the unified naming of pick-up points and improves the user experience.

[0042] The boarding point determination method of this embodiment can be executed by any suitable electronic device with data processing capabilities, including but not limited to: servers, mobile terminals (such as mobile phones, PADs, etc.) and PCs.

[0043] Example 2

[0044] Reference Figure 2 The flowchart illustrates the steps of a method for determining a boarding point according to Embodiment 2 of this application.

[0045] The method for determining the boarding point in this embodiment includes the following steps:

[0046] Step S202: Based on the road data in the road network data and the preset distance interval, generate base entry points along the corresponding roads.

[0047] In this step, based on road network data, boarding points, or basic boarding points, are generated uniformly for each road. These basic boarding points can be used to measure and represent the location of the boarding point; therefore, they can be used as a scale or resolution to approximate the actual boarding point location. By uniformly generating basic boarding points first, the difficulty of implementing the solution can be greatly reduced, and the feasibility and stability of the boarding points can be improved.

[0048] In one example, let's define the distance interval as B, also known as scale B, taking 30 meters as an example. Given a road X, determine the number of segments. For example, if road X is 120 meters long with 30-meter scales, then road X needs to be divided into 120 / 30 = 4 segments. Determine the final dividing point as the base driving point. As another example, if road Y is 130 meters long with 30-meter scales, then road Y needs to be divided into 130 / 30 = 4.33 segments. In this case, rounding is performed, resulting in 4 segments. Then, divide the 130 meters evenly into 4 segments and determine the final dividing point as the base driving point.

[0049] It should be noted that in some cases, such as when two or more roads intersect, if the intersection is used as a base pick-up point, it will belong to at least two roads. In this situation, to improve the accuracy of the pick-up point, it can be determined whether any base pick-up point is associated with multiple roads; if so, the base pick-up point associated with multiple roads will only be used as the base pick-up point for the road with the highest road grade among the multiple roads. The road grade can be appropriately set by those skilled in the artery, based on factors such as whether the road is a major road, its traffic volume, and its popularity. Of course, using other indicators to set the road grade is also applicable. This ensures that the pick-up point consistently belongs to a specific road. It should be noted that multiple roads involving the base pick-up point should ideally use the same distance interval to generate the base pick-up points to ensure overall consistency.

[0050] Step S204: Determine the popularity of the basic pick-up point based on the order pick-up points of the historical travel orders of the road within the preset time period.

[0051] The specific time setting of the preset time period can be appropriately set by those skilled in the art according to actual needs.

[0052] In one feasible approach, this step can be implemented as follows: obtaining multiple order pick-up points from historical travel orders for the road within a preset time period; determining order pick-up points whose distance to the base pick-up point meets a set distance condition; and determining the popularity of the base pick-up point, where popularity is equal to the number of times the order pick-up point whose distance to the base pick-up point meets the set distance condition appears in historical travel orders. The set distance condition can also be appropriately set by those skilled in the art according to actual needs. Optionally, order pick-up points within a distance of half the set distance interval (i.e., the distance interval when generating the base pick-up point) from each base pick-up point can be determined as order pick-up points whose distance meets the set distance condition. This makes the popularity statistics of the base pick-up point more objective and accurate, while simultaneously ensuring the stability of the pick-up points.

[0053] Step S206: Obtain base stations that meet the preset heat standards as candidate base stations.

[0054] If a particular boarding point has a high concentration of passengers, it indicates that most passengers have chosen to board at that boarding point, and that boarding point can be considered a candidate boarding point.

[0055] In one feasible implementation, it can be determined whether the popularity of the base boarding point is greater than a preset popularity threshold, and whether the popularity of the base boarding point is higher than that of other base boarding points, wherein the distance from the base boarding point to the base boarding point is within a preset distance range; when the determination results are both yes, the base boarding point is determined as a candidate base boarding point. The preset popularity threshold and preset distance range can be appropriately set by those skilled in the art according to actual needs. Furthermore, it can also be combined with determining whether the popularity difference between the base boarding point and its adjacent base boarding points is greater than a preset difference threshold; then, when the popularity of the base boarding point is greater than the preset popularity threshold, the popularity of the base boarding point is higher than that of other base boarding points, and the popularity difference between the base boarding point and its adjacent base boarding points is greater than the preset difference threshold, the base boarding point is determined as a candidate base boarding point. By judging the popularity of the base boarding point itself and whether its popularity is higher than that of other base boarding points, candidate base boarding points within a certain range can be accurately determined, and by combining the judgment of the popularity difference with adjacent base boarding points, it can be ensured that the determination of candidate base boarding points is more consistent with the actual boarding point situation.

[0056] For example, if a base pick-up point A has a popularity score of 100 (H=100) based on historical travel orders, and its popularity score is 20% higher than other base pick-up points in the vicinity (P=20%), and there are no higher popularity peaks within 3 base pick-up points near base pick-up point A (M=3), then base pick-up point A can be selected as a candidate base pick-up point.

[0057] It is evident that when determining candidate base station entry points, considering the heat H of the base station entry point itself, the relative amount P that it needs to be higher than the adjacent base station entry points, and the minimum distance M between two heat peaks can make the determination of candidate base station entry points more objective and consistent with the actual distribution of entry points.

[0058] Step S208: Compare the candidate basic boarding points with the pre-screened experienced boarding points, and generate recommended boarding points on the road based on the comparison results.

[0059] To obtain stable and reasonable final recommended boarding points, empirical boarding points can also be considered. One feasible approach is to manually set these points, such as identifying prominent or high-traffic Points of Interest (POIs) like street-facing gates, bus stops, subway entrances, and road intersections based on expert experience. These POIs are then mapped to base boarding points as empirical boarding points. In other words, multiple preset POIs can be obtained; then, the base boarding points closest to each preset POI are determined; and these determined base boarding points are used as empirical boarding points. However, this is not the only approach; those skilled in the art can use other methods to obtain or determine empirical boarding points, such as directly selecting from base boarding points or obtaining POIs through big data statistics and mapping them to base boarding points, etc. Whether candidate base boarding points are obtained based on popularity values ​​or empirically set points, they may be limited by their respective perspectives, leading to the risk of overfitting in the selected candidate boarding points. Therefore, combining the two approaches allows for mutual verification.

[0060] In one feasible approach, candidate boarding points that overlap with empirical boarding points can be identified as boarding points with the highest credibility level. That is, to reflect the verification results, the credibility of the previous two groups of candidate boarding points can be divided into different levels, and boarding points that simultaneously satisfy both can be identified as preferred candidates, providing strong support for the determination of subsequent recommended boarding points.

[0061] However, some boarding points may not simultaneously satisfy both requirements. In such cases, we can separately identify the remaining candidate boarding points that do not overlap with the experienced boarding points, and the remaining experienced boarding points that do not overlap with the candidate boarding points. According to a preset rule, the remaining candidate boarding points or the remaining experienced boarding points are designated as the boarding points with the second-highest credibility level. Based on this, the boarding points with the highest credibility level and the second-highest credibility level can be identified as recommended boarding points on the road. The preset rule can be set by those skilled in the art according to actual needs; for example, a second-highest level can be set for the remaining candidate boarding points or the remaining experienced boarding points. This ensures both a reasonable number of recommended boarding points and a sufficient number of boarding points.

[0062] Furthermore, there may be no boarding point that simultaneously satisfies both conditions. In such cases, one feasible approach is to determine the recommended boarding point if no candidate boarding point overlaps with the experienced boarding point, or to determine the recommended boarding point based on the experienced boarding point. For example, the credibility level of the boarding point can be determined based on the weights corresponding to the candidate boarding point and the experienced boarding point. The specific weights can be set by those skilled in the art according to actual needs. If the focus is more on popularity statistics, a larger weight can be assigned to the candidate boarding point; conversely, if the focus is more on human experience, a larger weight can be assigned to the experienced boarding point. Optionally, the sum of the two weights can be 1 to facilitate data calculation and processing. This method of boarding point selection is relatively simple and has low implementation costs.

[0063] In another feasible approach, if no candidate boarding points overlap with experienced boarding points, the credibility level of the corresponding boarding point is determined based on the travel popularity of the candidate boarding points. Since both candidate and experienced boarding points are partial boarding points within the base boarding point network and each has corresponding travel popularity, the credibility level can be determined based on their travel popularity; for example, higher travel popularity corresponds to a higher credibility level. However, this approach is not limited to this. It can also be based on their travel popularity, combined with assigning weights to whether the boarding point belongs to a candidate or experienced boarding point, i.e., combining the travel popularity of the weighted points to determine the credibility level. Using this method, based on travel popularity, makes the determination of the credibility level more objective.

[0064] For example, three confidence levels can be defined, from highest to lowest: Level 1, Level 2, and Level 3. A boarding point where the experienced boarding point and the candidate boarding point overlap is classified as Level 1. Furthermore, if there are no Level 1 boarding points, or if a boarding point is not Level 1, Level 2 and Level 3 boarding points can be determined using the above method. It's possible that the candidate boarding point is Level 2 and the experienced boarding point is Level 3, or vice versa.

[0065] Once the credibility level of the selected pick-up points is determined, the recommended pick-up points for each road can be identified.

[0066] However, in some cases, the base pick-up points on a certain road are relatively sparse, resulting in an even sparser distribution of recommended pick-up points. In such cases, optionally, the following optional step S210 can also be performed.

[0067] Step S210: Determine the total heat of the road, and based on the road width and / or the total heat of the road, determine whether the road needs to add recommended pick-up points; if so, add recommended pick-up points on the road based on the road width and the total heat of the road.

[0068] The total heat of the road is the sum of the heat of the base vehicle points on the road.

[0069] The wider the road, the less likely it is to have sufficient recommended pick-up points; similarly, the higher the total popularity of a road, the less likely it is to have sufficient recommended pick-up points. Therefore, the need to add more recommended pick-up points can be determined based on the road width and / or the road's total popularity. Specific judgment criteria can be appropriately set by those skilled in the art based on actual conditions. For example, if the road's total width exceeds a certain width threshold and / or the road's total popularity exceeds a certain popularity threshold, then it is determined that the road needs to add more pick-up points. In this case, the road width and total popularity can be combined to determine how to add more recommended pick-up points to the road. Specific supplementary rules can include adding previously filtered-out experienced pick-up points or candidate pick-up points.

[0070] However, this is not the only feasible approach. In a preferred method, a first supplementary interval can be determined based on the road width of the road to be supplemented with recommended boarding points, a preset normalized width, and the distance interval. The average road popularity of the road to be supplemented with recommended boarding points can be determined based on the total popularity and road length of the road. A second supplementary interval can be determined based on the average road popularity. A target supplementary interval can be determined based on the first and second supplementary intervals. Based on the target supplementary interval, boarding points can be added as recommended boarding points on the road to be supplemented with recommended boarding points. In specific supplementation, a different distance interval than when the basic boarding points were generated can be used to supplement recommended boarding points on the road to be supplemented, thereby improving the fault tolerance rate of boarding point supplementation and covering a wider range. The preset normalized width is used to ensure that different road widths correspond to different supplementary intervals. In specific implementation, this normalized width can be the road width of the widest road in the road network data, or it can be a preset road width threshold. The road width threshold can be set according to the actual road conditions in the road network, or according to big data statistics. For example, it can be set to 24 meters. In this case, even if the actual width of the widest road is greater than 24 meters, 24 meters is still used as the road width threshold to simplify the algorithm and effectively control the road width in the road network based on data processing.

[0071] However, this is not the only approach. When determining the target replenishment interval, one can directly determine the target replenishment interval corresponding to the road of the recommended pick-up point based on the road width of the road to be replenished, according to a pre-defined mapping relationship between multiple road widths and target replenishment intervals. Alternatively, one can determine the corresponding interval level of the road of the recommended pick-up point based on the road width of the road to be replenished, according to a pre-defined mapping relationship between multiple road widths and interval levels, and then finally determine the target replenishment interval corresponding to the road of the recommended pick-up point based on the mapping relationship between the interval level and the distance interval. In some cases, if the road width of the recommended pick-up point cannot strictly correspond to the road width in the mapping relationship, the road width closest to the road of the recommended pick-up point in the mapping relationship can be used to determine the target replenishment interval, or the interval level can be determined first, and then the target replenishment interval can be determined.

[0072] For example, multiple distance intervals of different levels are first set. These multiple distance intervals are applicable both when generating basic pick-up points and when supplementing recommended pick-up points. Assume that S levels are pre-set; for example, when S=5, there are 5 corresponding distance intervals: 1B, 2B, 3B, 4B, and 5B. In this example, assume 1B=30M, 2B=60M, 3B=90M, 4B=120M, and 5B=150M. However, it should be noted that this is only an illustrative example. In practical applications, those skilled in the art can set corresponding distance intervals according to actual needs, and the differences between the distance intervals do not necessarily have to be equal.

[0073] Then, the first supplementary interval is determined. For example, road width is represented by W, which can approximate the road grade. A wider road can be understood as making it easier to get on and off vehicles, allowing for more basic and recommended pick-up points. Optionally, the interval grade can be determined using the following formula, and then the first supplementary interval can be determined based on this interval grade;

[0074] W_Score=FLOOR((1-W / MAX(W))*S)+1

[0075] Where W_Score represents the interval level corresponding to the road width W, FLOOR represents rounding down, W represents the road width of the road to be supplemented with recommended pick-up points, W>0, MAX(W) represents the width of the widest road in the road network, and S represents the scale used when generating the base pick-up points (i.e., the level corresponding to the preset distance interval). For example, this scale can be divided into 5 levels as described above, i.e., S=5.

[0076] For example, if W = 3M, MAX(W) = 24M, and S = 5B, then the corresponding W_Score is 5, which is 5B. The distance interval corresponding to 5B is 150M. Based on this, the first supplementary interval can be determined to be 150M.

[0077] For example, if W = 24M, MAX(W) = 24M, and S = 5B, then the corresponding W_Score is 1, or 1B. The distance interval corresponding to 1B is 30M. Based on this, the first supplementary interval can be determined to be 30M.

[0078] Those skilled in the art will readily recognize that replacing S with a distance interval and adaptively adjusting and replacing 1 in the formula can also yield the same first supplementary interval. However, using the above formula simplifies calculations, reduces computational costs, and is applicable regardless of how S and the distance interval are set, offering greater flexibility and higher compatibility.

[0079] Next, a second supplementary interval can be determined. For example, the average road heat, denoted by h, reflects the usage of the recommended pick-up points per unit length of the road as a pick-up area. Roads with higher heat are more likely to have their recommended pick-up points used, allowing for more base pick-up points and recommended pick-up points.

[0080] in:

[0081] Average road heat h = Total road heat H / Road length L

[0082] Wherein, the total road heat H is the sum of the heat of all boarding points on the road.

[0083] Alternatively, h can be normalized first, that is:

[0084] h=(h-min(h)) / (max(h)-min(h))

[0085] Wherein, min(h) represents the minimum average heat per unit length on the road, and max(h) represents the maximum average heat per unit length on the road.

[0086] Based on this, alternatively, the interval level can be determined using the following formula, and then the second supplementary interval can be determined based on the interval level:

[0087] H_Score = CEIL((1-he)*S)

[0088] Where H_Score represents the interval level corresponding to the average road heat h of the road to be supplemented pick-up points; CEIL represents rounding up; e is a very small number, ranging from (0, 10). -10The interval is defined as follows: [ ] to prevent mismatch between interval levels when h=1; S represents the scale used when generating the base pick-up points on the road to be supplemented (i.e., the level corresponding to the preset distance interval). For example, this scale can be divided into 5 levels as described above, i.e., S=5.

[0089] Once H_Score is determined, the second supplementary interval can be determined by referring to the method described above for determining the first supplementary interval.

[0090] Then, after obtaining the first and second replenishment intervals, the target replenishment interval can be determined. Optionally, the interval level can be determined first using the following formula, and then the target replenishment interval can be determined based on the interval level. The formula is:

[0091] b=Round(W_Score*w1+H_Score*w2)

[0092] Where b represents the interval level of the road for which supplementary recommended pick-up points are to be added; w1 and w2 are weights, w1 + w2 = 1; Round is for rounding to the nearest integer; W_Score represents the interval level corresponding to the first supplementary interval, and H_Score represents the interval level corresponding to the second supplementary interval. Generally, w2 can be set to be greater than w1 to make the supplementary recommended pick-up points more consistent with the actual situation.

[0093] Once b is determined, the target supplementary interval can be determined by referring to the aforementioned method for determining the first or second supplementary interval.

[0094] After determining the target supplementary interval, for the selected recommended pick-up points, the road can be segmented according to these existing recommended pick-up points. Within each segment (L1), pick-up points are selected according to the distance interval corresponding to the interval level b (still based on the basic pick-up points). The number of pick-up points to be selected is ROUND(L1 / b). These selected pick-up points are the supplementary recommended pick-up points for this road.

[0095] For example, if the interval between two recommended pick-up points is 5 base pick-up points (L1=5), and the calculated road interval level is b=3, then ROUND(5.0 / 3)=2 more base pick-up points need to be selected. The selection order is, for example, starting with the pick-up point with the higher popularity value, and selecting in sequence. Based on the original recommended pick-up points and the supplementary recommended pick-up points, the final recommended pick-up points are formed.

[0096] It should be noted that if a road previously only had basic pick-up points, such as no pick-up points whose popularity met the preset popularity standard, then the aforementioned method would not be effective in obtaining recommended pick-up points for that road. In this case, the aforementioned interval level b can be used to select recommended pick-up points from the basic pick-up points for that road, thus avoiding the situation where effective recommended pick-up points cannot be obtained on roads with fewer people.

[0097] In addition, in one feasible approach, the basic boarding points that have not been selected after the above multiple screenings and determinations, i.e. the remaining basic boarding points, can also be retained, but with a relatively low weight, as a last-line backup boarding point to deal with unforeseen circumstances.

[0098] In the above scheme, firstly, because the generated base boarding points are relatively fixed, using them as the scale basis for generating all recommended boarding points makes the scheme more stable overall. Secondly, selecting relatively stable boarding points that meet the popularity criteria and boarding points that follow human experience to select candidate boarding points, since the selected boarding points are also expressed through the base boarding points, their locations are also stable. Furthermore, it greatly disperses the distribution of boarding points, reducing the sensitivity of boarding point naming, making the naming relatively fixed, and making recommendations simpler. Moreover, stable boarding points and naming can bring a better user experience and improve operational efficiency, as the maintained boarding point data will be passed down according to the location coordinates and will not change with iterations.

[0099] The boarding point determination method of this embodiment can be executed by any suitable electronic device with data processing capabilities, including but not limited to: servers, mobile terminals (such as mobile phones, PADs, etc.) and PCs.

[0100] Example 3

[0101] Reference Figure 3 The diagram shows a structural block diagram of a vehicle boarding point determination device according to Embodiment 3 of this application.

[0102] The pick-up point determination device in this embodiment includes: a generation module 302, used to generate basic pick-up points along corresponding roads based on road data in road network data and preset distance intervals; a popularity module 304, used to determine the popularity of basic pick-up points based on the historical travel orders of the roads within a preset time period; an acquisition module 306, used to acquire basic pick-up points whose popularity meets preset popularity standards as candidate basic pick-up points; and a determination module 308, used to compare the candidate basic pick-up points with pre-screened experience pick-up points, and generate recommended pick-up points on the roads based on the comparison results.

[0103] Optionally, the heat index module 304 is used to obtain multiple order pick-up points of historical travel orders for the road within a preset time period; determine the order pick-up points whose distance to the base pick-up point meets a set distance condition; and determine the heat index of the base pick-up point, wherein the heat index is equal to the number of times the order pick-up point whose distance to the base pick-up point meets the set distance condition appears in the historical travel orders.

[0104] Optionally, the acquisition module 306 is used to determine whether the popularity of the base loading point is greater than a preset popularity threshold, and to determine whether the popularity of the base loading point is higher than that of other base loading points, wherein the distance from the other base loading points to the base loading point is within a preset distance range; when the determination results are both yes, the base loading point is determined as a candidate base loading point.

[0105] Optionally, the acquisition module 306 is further configured to determine whether the heat difference between the base loading point and its adjacent base loading points is greater than a preset difference threshold; when the heat of the base loading point is greater than the preset heat threshold, the heat of the base loading point is higher than other base loading points, and the heat difference between the base loading point and its adjacent base loading points is greater than the preset difference threshold, the base loading point is determined as a candidate base loading point.

[0106] Optionally, the determining module 308 is used to compare the candidate base boarding points with pre-screened experienced boarding points, and determine the candidate base boarding points that overlap with the experienced boarding points as the boarding points with the highest credibility level; determine the remaining candidate base boarding points that do not overlap with the experienced boarding points, and the remaining experienced boarding points that do not overlap with the candidate base boarding points; determine the remaining candidate base boarding points or the remaining experienced boarding points as the boarding points with the second highest credibility level according to preset rules; and determine the boarding points with the highest credibility level and the boarding points with the second highest credibility level as recommended boarding points on the road.

[0107] Optionally, the pick-up point determination device in this embodiment further includes: a supplementary module 310, used to determine the total heat of the road, wherein the total heat of the road is the sum of the heat of the basic pick-up points on the road; determine whether the road needs to add recommended pick-up points based on the road width and / or the total heat of the road; if so, add recommended pick-up points on the road based on the road width and the total heat of the road.

[0108] Optionally, the supplementary module 310 is configured to: determine a first supplementary interval based on the road width of the road to be supplemented recommended pick-up points, a preset normalized width, and the distance interval; determine the average road heat based on the total heat and road length of the road to be supplemented recommended pick-up points; determine a second supplementary interval based on the average road heat; determine a target supplementary interval based on the first supplementary interval and the second supplementary interval; and add pick-up points as recommended pick-up points on the road to be supplemented recommended pick-up points based on the target supplementary interval and the base pick-up points.

[0109] Optionally, the generation module 302 is also used to determine whether there is a base entry point associated with multiple roads; if so, the base entry point is used only as the base entry point of the road with the highest road level among the multiple roads.

[0110] The boarding point determination device of this embodiment is used to implement the corresponding boarding point determination methods in the foregoing multiple method embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here. In addition, the functional implementation of each module in the boarding point determination device of this embodiment can refer to the description of the corresponding part in the foregoing method embodiments, which will also not be repeated here.

[0111] Example 4

[0112] Reference Figure 4 The diagram shows a structural schematic of an electronic device according to Embodiment 4 of this application. The specific embodiments of this application do not limit the specific implementation of the electronic device.

[0113] like Figure 4 As shown, the electronic device may include: a processor 402, a communications interface 404, a memory 406, and a communications bus 408.

[0114] in:

[0115] The processor 402, communication interface 404, and memory 406 communicate with each other via communication bus 408.

[0116] Communication interface 404 is used to communicate with other electronic devices or servers.

[0117] The processor 402 is used to execute program 410, which can specifically execute the relevant steps in the above-described method embodiment for determining the boarding point.

[0118] Specifically, program 410 may include program code that includes computer operation instructions.

[0119] Processor 402 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application. The smart device includes one or more processors, which may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0120] Memory 406 is used to store program 410. Memory 406 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0121] Specifically, program 410 can be used to cause processor 402 to perform the operation corresponding to the boarding point determination method described in the aforementioned method embodiment one or embodiment two.

[0122] The specific implementation of each step in procedure 410 can be found in the corresponding steps and units described in the above-described method embodiment for determining the vehicle loading point, and will not be repeated here. Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the devices and modules described above can be referred to the corresponding process descriptions in the aforementioned method embodiments, and will not be repeated here.

[0123] This application also provides a computer program product, including computer instructions that instruct a computing device to perform an operation corresponding to any of the boarding point determination methods in the above-described multiple method embodiments.

[0124] It should be noted that, depending on the implementation needs, the various components / steps described in the embodiments of this application can be broken down into more components / steps, or two or more components / steps or parts of the operation of components / steps can be combined into new components / steps to achieve the purpose of the embodiments of this application.

[0125] The methods described in the embodiments of this application can be implemented in hardware, firmware, or as software or computer code that can be stored in a recording medium (such as a CD-ROM, RAM, floppy disk, hard disk, or magneto-optical disk), or as computer code downloaded over a network that is originally stored in a remote recording medium or a non-transitory machine-readable medium and will be stored in a local recording medium. Thus, the methods described herein can be processed by software stored on a recording medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware (such as an ASIC or FPGA). It is understood that the computer, processor, microprocessor controller, or programmable hardware includes storage components (e.g., RAM, ROM, flash memory, etc.) capable of storing or receiving software or computer code that, when accessed and executed by the computer, processor, or hardware, implements the boarding point determination method described herein. Furthermore, when a general-purpose computer accesses code used to implement the boarding point determination method shown herein, the execution of the code transforms the general-purpose computer into a dedicated computer for executing the boarding point determination method shown herein.

[0126] Those skilled in the art will recognize that the units and method steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the embodiments of this application.

[0127] The above embodiments are only used to illustrate the embodiments of this application, and are not intended to limit the embodiments of this application. Those skilled in the art can make various changes and modifications without departing from the spirit and scope of the embodiments of this application. Therefore, all equivalent technical solutions also fall within the scope of the embodiments of this application, and the patent protection scope of the embodiments of this application should be defined by the claims.

Claims

1. A method for determining a boarding point, comprising: Based on the road data in the road network data and the preset distance intervals, generate base entry points along the corresponding roads; The popularity of the basic pick-up point is determined based on the historical travel orders for the road within a preset time period. Based on the popularity of the base points that meet the preset popularity standard, the base points are selected as candidate base points. The candidate boarding points are compared with pre-screened experienced boarding points. Based on the comparison results, recommended boarding points on the road are generated. The candidate boarding points are based on actual travel data, while the experienced boarding points are based on experience or statistical results and serve as an aid and supplement to the candidate boarding points.

2. The method according to claim 1, wherein, The step of determining the popularity of the basic pick-up point based on the historical travel orders of the road within a preset time period includes: Obtain multiple pick-up points for historical travel orders on the road within a preset time period; Determine the pick-up point for orders whose distance to the base pick-up point meets the set distance conditions; The popularity of a base pick-up point is determined, which is equal to the number of times a pick-up point for an order that meets a set distance condition appears in historical travel orders.

3. The method according to claim 2, wherein, The criteria for selecting candidate foundation loading points based on the obtained heat intensity meeting a preset heat intensity standard include: Determine whether the heat of the base loading point is greater than a preset heat threshold, and determine whether the heat of the base loading point is higher than that of other base loading points, wherein the distance from the other base loading points to the base loading point is within a preset distance range; When all the judgment results are yes, the foundation boarding point is determined as a candidate foundation boarding point.

4. The method according to claim 3, wherein, The method further includes: determining whether the heat difference between the base loading point and its adjacent base loading points is greater than a preset difference threshold; The step of determining the base station as a candidate base station when all judgment results are yes includes: determining the base station as a candidate base station when the popularity of the base station is greater than a preset popularity threshold, the popularity of the base station is higher than other base stations, and the difference in popularity between the base station and its adjacent base stations is greater than a preset difference threshold.

5. The method according to any one of claims 1-4, wherein, The step of generating recommended pick-up points on the road based on the comparison results includes: Candidate boarding points that overlap with the experienced boarding points are identified as boarding points with the highest confidence level. Determine the remaining candidate base boarding points that do not overlap with the experienced boarding points, and the remaining experienced boarding points that do not overlap with the candidate base boarding points; according to a preset rule, determine the remaining candidate base boarding points or the remaining experienced boarding points as the boarding points with the second highest confidence level. The pick-up point with the highest credibility level and the pick-up point with the second highest credibility level are determined as recommended pick-up points on the road.

6. The method according to claim 1, wherein, The method further includes: Determine the total heat of the road, which is the sum of the heat of the base vehicle points on the road; Based on the road width and / or the total heat of the road, determine whether the road needs additional recommended pick-up points; If necessary, recommended pick-up points may be added to the road based on its width and total popularity.

7. The method according to claim 6, wherein, The step of adding recommended pick-up points on the road based on the road width and the total heat of the road includes: The first supplementary interval is determined based on the road width, the preset normalized width, and the preset distance interval. Based on the total heat of the road and the length of the road, the average heat of the road is determined, and a second supplementary interval is determined based on the average heat of the road; The target replenishment interval is determined based on the first replenishment interval and the second replenishment interval; Based on the target supplementary interval, additional boarding points are added on the road as recommended boarding points.

8. The method according to claim 1, wherein, include: The method further includes; Determine if there are any base entry points that are associated with multiple roads; If so, the base entry point will be used only as the base entry point for the road with the highest road grade among the multiple roads.

9. A computer storage medium having a computer program stored thereon, which, when executed by a processor, implements the boarding point determination method as described in any one of claims 1-8.

10. A computer program product comprising computer instructions that instruct a computing device to perform an operation corresponding to the boarding point determination method as described in any one of claims 1-8.

Images