Loading and unloading position mining method and device, computer equipment and storage medium
By obtaining and analyzing the vehicle driving trajectory and order basic tables, filtering and sorting candidate loading and unloading positions, the problem of low accuracy of loading and unloading points is solved, and the user experience and 30m fixed-point rate is improved.
Patent Information
- Application Number
- CN202411452904.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-16
- Publication Date
- 2025-01-03
Smart Images
Figure CN119250671A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of transportation technology, and in particular to a method, device, computer equipment and storage medium for mining loading and unloading locations. Background Art
[0002] With the continuous expansion of scenarios such as freight and passenger transport, general map data is increasingly unable to meet the application needs of freight participants. Building a professional logistics map based on freight has become an important driving force for the development of the logistics industry. The loading and unloading stop location is an important part of the logistics map.
[0003] Currently, in freight and passenger transport scenarios, the 30m fixed-point rate is usually used as an evaluation indicator. The calculation caliber is the distance between the user's order point and the actual loading and unloading point. The smaller the distance, the better the recommendation effect, and the driver and passenger are more likely to meet. However, the 30m fixed-point rate indicator is heavily dependent on the accuracy of the driver's operating position. In the loading and unloading scenario, because it is a fixed-price model, the driver's correct proportion of the time points for clicking loading completion and unloading completion is a certain ratio, because it is not strongly correlated with pricing, resulting in the problem of low accuracy of loading and unloading points. The actual loading and unloading point will not only affect the statistical results of the real indicator at the indicator level, but also at the feature level, the drift of the true value point of loading and unloading makes the personalized recommendation unreasonable, which is easy to cause user complaints and reduce user experience. Summary of the invention
[0004] Based on this, it is necessary to provide a method, device, computer equipment and storage medium for mining loading and unloading locations in order to solve at least one problem existing in the above-mentioned prior art.
[0005] In a first aspect, a method for mining a loading and unloading location is provided, comprising the following steps:
[0006] Obtaining the driving trajectory of the target vehicle and the order base table, wherein the order base table includes the arrival time and arrival position at the loading / unloading place, and the completion time and completion position when the loading / unloading is completed;
[0007] intercepting a first driving trajectory segment within a first preset time range of the arrival time and a second driving trajectory segment within a second preset time range of the completion time from the driving trajectory;
[0008] respectively calculating the dwell time of each stationary point in the first driving trajectory segment and the second driving trajectory segment, and when the dwell time is greater than a preset time threshold, taking the stationary point as a candidate stationary point;
[0009] The arrival location, the completion location and the candidate station point are used as candidate loading / unloading locations, and the candidate loading / unloading locations are sorted by a preset sorting model, and the actual loading / unloading location is determined based on the sorting result.
[0010] In one embodiment, respectively calculating the dwell time of each stationary point in the first driving trajectory segment and the second driving trajectory segment, and when the dwell time is greater than a preset time threshold, taking the stationary point as a candidate stationary point, includes:
[0011] Determine each stationary point in the first driving trajectory segment and the second driving trajectory segment;
[0012] Determining the speed of the target vehicle when passing each of the stationary points;
[0013] When the driving speed is greater than a preset speed threshold, filtering the corresponding stationary point;
[0014] Calculate the dwell time of the target vehicle at each remaining station;
[0015] The remaining stationary points whose stay time is longer than the preset time threshold are used as the candidate stationary points.
[0016] In one embodiment, calculating the dwell time of the target vehicle at each remaining station includes:
[0017] Traversing the stationary point driving trajectory of the target vehicle arriving at each of the remaining stationary points within a third preset time range, the stationary point driving trajectory including a start time and an end time;
[0018] The difference between the start time and the end time is used as the duration of stay at the remaining stop.
[0019] In one embodiment, the step of sorting the candidate loading / unloading locations by using a preset sorting model and determining the actual loading / unloading location based on the sorting result includes:
[0020] intercepting a driving trajectory string corresponding to each of the candidate loading / unloading locations in the driving trajectory;
[0021] Based on the driving trajectory string, each of the candidate loading / unloading locations is scored by a preset sorting model, and the candidate loading / unloading locations are sorted in descending order of the score;
[0022] The candidate loading / unloading position ranked first is used as the actual loading / unloading position.
[0023] In one embodiment, the step of scoring each of the candidate loading / unloading locations based on the driving trajectory string by a preset sorting model, and sorting the candidate loading / unloading locations in descending order of scores, includes:
[0024] Extracting features from the driving trajectory string to obtain a feature vector corresponding to each of the candidate loading / unloading locations;
[0025] Performing weighted summation on the feature vectors corresponding to each candidate loading / unloading location to obtain a score for each candidate loading / unloading location;
[0026] The candidate loading / unloading locations are sorted in descending order of the scores.
[0027] In one embodiment, before taking the candidate loading / unloading location with the highest score as the actual loading / unloading location, the process includes:
[0028] Based on the ranking results, determining the candidate loading / unloading location with the highest score, and performing feasibility determination on the candidate loading / unloading location with the highest score;
[0029] When the candidate loading / unloading location with the highest score does not meet the feasibility determination condition, calling the fallback strategy, determining the fallback loading / unloading location, and using the fallback loading / unloading location as the actual loading / unloading location; or
[0030] When the sorting result is not obtained within a preset time range, the bottom-line strategy is called to determine the bottom-line loading / unloading position, and the bottom-line loading / unloading position is used as the actual loading / unloading position.
[0031] In one embodiment, before obtaining the driving trajectory of the target vehicle and the order base table, the following steps are included:
[0032] Configure tracking conditions based on tracking requirements;
[0033] When the tracking condition is triggered, the tracking generates the arrival time and arrival position of the loading / unloading place, and the completion time and completion position when the loading / unloading is completed;
[0034] The arrival time and arrival position at the loading / unloading place, and the completion time and completion position when the loading / unloading is completed are recorded in the order basic table.
[0035] In a second aspect, a loading and unloading location excavation device is provided, comprising:
[0036] An information acquisition unit, used to acquire the driving trajectory of the target vehicle and an order base table, wherein the order base table includes the arrival time and arrival position at the loading / unloading place, and the completion time and completion position when the loading / unloading is completed;
[0037] A driving trajectory judgment and interception unit, used to intercept a first driving trajectory segment within a first preset time range of the arrival time and a second driving trajectory segment within a second preset time range of the completion time in the driving trajectory;
[0038] a candidate stationary point determination unit, configured to respectively calculate the dwell time of each stationary point in the first driving trajectory segment and the second driving trajectory segment, and when the dwell time is greater than a preset time threshold, use the stationary point as a candidate stationary point;
[0039] The real loading / unloading position determining unit is used to take the arrival position, the completion position and the candidate station point as candidate loading / unloading positions, sort the candidate loading / unloading positions by a preset sorting model, and determine the real loading / unloading position based on the sorting result.
[0040] In a third aspect, a computer device is provided, comprising a memory, a processor, and computer-readable instructions stored in the memory and running on the processor, wherein the processor implements the above-mentioned method for mining loading and unloading locations when executing the computer-readable instructions.
[0041] In a fourth aspect, a readable storage medium is provided, on which computer-readable instructions are stored. When the computer-readable instructions are executed by a processor, the method for mining loading and unloading locations as described above is implemented.
[0042] The above-mentioned loading and unloading location mining method, device, computer equipment and storage medium, the method implementation includes: obtaining the driving trajectory and order basic table of the target vehicle, the order basic table includes the arrival time and arrival position at the loading / unloading place, and the completion time and completion position when the loading / unloading is completed; intercepting a first driving trajectory segment within a first preset time range of the arrival time, and a second driving trajectory segment within a second preset time range of the completion time in the driving trajectory; calculating the residence time of each station in the first driving trajectory segment and the second driving trajectory segment respectively, when the residence time is greater than the preset time threshold, taking the station as a candidate station; taking the arrival position, the completion position and the candidate station as candidate loading / unloading positions, and scoring them according to preset rules, and taking the candidate loading / unloading position with the highest score as the actual loading / unloading position. In an embodiment of the present application, by obtaining the driving trajectory of the target vehicle, the arrival time and arrival position at the loading / unloading site, and the completion time and completion position when the loading / unloading is completed, the candidate points are screened, and a comprehensive judgment and mining is performed to select the candidate position with the highest score as the actual loading / unloading point, which can improve the accuracy of the actual loading / unloading position and improve the user experience. BRIEF DESCRIPTION OF THE DRAWINGS
[0043] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments of the present application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0044] Figure 1 It is a schematic diagram of a process of a method for excavating a loading and unloading location in an embodiment of the present application;
[0045] Figure 2 It is a structural schematic diagram of a loading and unloading position excavation device in one embodiment of the present application;
[0046] Figure 3 It is a schematic diagram of a computer device in one embodiment of the present application. DETAILED DESCRIPTION
[0047] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0048] In one embodiment, if Figure 1As shown, a method for mining a loading and unloading location is provided, comprising the following steps:
[0049] In step S110, the driving trajectory of the target vehicle and the order base table are obtained, wherein the order base table includes the arrival time and arrival position at the loading / unloading place, and the completion time and completion position when the loading / unloading is completed;
[0050] In an embodiment of the present application, the basic driving information of the vehicle driven by the target vehicle can be obtained through a positioning system, such as a Beidou system, a GPS system, etc., as well as the basic driving information reported by the driver at preset intervals, such as 3 seconds. The basic driving information may specifically include driving trajectory information such as location information and speed information. When the target vehicle arrives at the loading / unloading site, or when the loading / unloading operation is completed, the arrival and completion buttons can be clicked through pre-installed applications, official accounts, applets, etc. to trigger the acquisition of buried point information, which may include the arrival time and arrival position at the loading / unloading site, and the completion time and completion position when the loading / unloading is completed. And record it in the order basic table. By combining the driving trajectory and the order basic table with the driver ID, the driver's complete driving information in the entire process of receiving orders-pickup-delivery-completion can be obtained.
[0051] The completion location and the arrival location may be specific address abbreviations or longitude and latitude information, and the arrival time and the completion time may be specific time information.
[0052] In step S120, a first driving trajectory segment within a first preset time range of the arrival time and a second driving trajectory segment within a second preset time range of the completion time are intercepted from the driving trajectory;
[0053] In an embodiment of the present application, the driving trajectory may include the driving trajectory of the driver in the entire process of receiving orders, picking up goods, delivering goods, and completing. It may specifically include information such as time, location, and speed. Then, when the arrival time and arrival location at the loading / unloading site, as well as the completion time and completion location when loading / unloading are completed, the driving trajectory segments within the preset time range before and after the arrival time and the driving trajectory segments within the preset time range before and after the completion time can be intercepted in the driving trajectory, for example, the driving trajectory segments within the time range of 10 minutes before and after. Exemplarily, if the arrival time is 9 o'clock, the driving trajectory segments between 8:50 and 9:10 can be obtained.
[0054] It should be noted that the first driving trajectory segment and the second driving trajectory segment can be divided into multiple points, i.e., stationary points, according to a preset division rule, and the stationary points are used to represent the locations where the target vehicle may stay, for example, according to a preset duration per interval, or a preset distance per interval, etc.
[0055] It should be noted that the speed of the target vehicle passing each stationary point can be determined, and the point information with a speed greater than a preset threshold, such as greater than 3 m / s, can be filtered out, and the remaining points can be retained as stationary points to reduce noise.
[0056] In step S130, the dwell time of each stationary point in the first driving trajectory segment and the second driving trajectory segment is calculated respectively, and when the dwell time is greater than a preset time threshold, the stationary point is used as a candidate stationary point;
[0057] In the embodiment of the present application, a plurality of stationary points may be set in the driving trajectory segment, for example, a stationary point may be set at a preset distance interval, such as 10 meters. After the first driving trajectory segment and the second driving trajectory segment are intercepted, for each stationary point, the driving trajectory within a preset time range before and after reaching the stationary point may be traversed, which needs to meet the requirements of a distance of less than 20 meters and a time of less than 5 minutes, and the difference between the time corresponding to the last point of the trajectory and the time corresponding to the first point of the trajectory may be used as the length of stay.
[0058] If the dwell time is longer than the preset time threshold, for example, longer than 2 minutes, the stop point can be used as a candidate stop point. It should be noted that one candidate stop point can be selected for the arrival position and one candidate stop point can be selected for the completion position. That is, one candidate stop point is selected from the trajectory segment of the arrival position and one candidate stop point is also selected from the trajectory segment of the completion position, and four candidate loading / unloading positions can be obtained.
[0059] In step S140, the arrival location, the completion location and the candidate station point are used as candidate loading / unloading locations, and the candidate loading / unloading locations are sorted by a preset sorting model, and the actual loading / unloading location is determined based on the sorting result.
[0060] In the embodiment of the present application, the preset sorting model may specifically include a feature extraction network and a scoring model, which may extract the arrival location, the completion location, and the type corresponding to the candidate station point, the distance between the candidate loading / unloading location and other candidate loading / unloading locations, the number of candidate loading / unloading locations within a preset range nearby, the length of stay, the number of points with a driving speed lower than a preset speed nearby, the number of tracks within a preset distance nearby, and other features through a feature extraction network, such as a convolutional neural network CNN. Then, each feature is assigned a corresponding weight through the scoring model, and its score is calculated. The scores are sorted in order from large to small, or from small to large, to obtain a sorted list. Based on the sorted list, the candidate loading / unloading location with the highest score is determined as the actual loading / unloading location.
[0061] In an embodiment of the present application, the preset sorting model can be trained in the following manner. Specifically, sample data can be collected to construct a training sample data set and a test data set, and each sample can be manually annotated. Then, the preset sorting model is iteratively trained based on the training sample data set. When the preset convergence conditions are met, such as when the number of iterations reaches the preset maximum number of iterations, such as 1000 times, or when the loss value is less than a preset threshold, the trained preset sorting model can be obtained. The preset sorting model trained by the test set can also be evaluated and optimized.
[0062] It should be noted that when labeling the above training samples, about 1,600 labels can be manually labeled offline. Since it is difficult to obtain real labels, 10-fold cross validation can be used to train the model to prevent overfitting. The final model achieved good results, greatly improving the accuracy of simply using driver tracking information as the true value. At the same time, the true value was used to update the features of the recommendation model, improving the final recommended 30m fixed point rate indicator.
[0063] In an embodiment of the present application, a method for mining loading and unloading locations is provided, including: obtaining a driving trajectory and an order base table of a target vehicle, the order base table including an arrival time and an arrival position at a loading / unloading location, and a completion time and a completion position when loading / unloading is completed; intercepting a first driving trajectory segment within a first preset time range of the arrival time, and a second driving trajectory segment within a second preset time range of the completion time in the driving trajectory; calculating the stay time of each station point in the first driving trajectory segment and the second driving trajectory segment, respectively, and when the stay time is greater than a preset time threshold, taking the station point as a candidate station point; taking the arrival position, the completion position, and the candidate station point as candidate loading / unloading locations, and scoring them according to preset rules, and taking the candidate loading / unloading location with the highest score as the actual loading / unloading location. In an embodiment of the present application, by obtaining the driving trajectory of the target vehicle, the arrival time and arrival position at the loading / unloading site, and the completion time and completion position when the loading / unloading is completed, the candidate points are screened, and a comprehensive judgment and mining is performed to select the candidate position with the highest score as the actual loading / unloading point, which can improve the accuracy of the actual loading / unloading position and improve the user experience.
[0064] In an embodiment of the present application, respectively calculating the dwell time of each stationary point in the first driving trajectory segment and the second driving trajectory segment, and when the dwell time is greater than a preset time threshold, taking the stationary point as a candidate stationary point, includes:
[0065] Determine each stationary point in the first driving trajectory segment and the second driving trajectory segment;
[0066] Determining the speed of the target vehicle when passing each of the stationary points;
[0067] When the driving speed is greater than a preset speed threshold, filtering the corresponding stationary point;
[0068] Calculate the dwell time of the target vehicle at each remaining station;
[0069] The remaining stationary points whose stay time is longer than the preset time threshold are used as the candidate stationary points.
[0070] Optionally, multiple stationary points may be set in each driving trajectory segment, for example, one stationary point is set at each preset distance, such as 10 meters. Or one stationary point is set at each preset time interval, such as every 3 minutes. Then, multiple stationary points may be set in each driving trajectory segment, and for each stationary point, the driving trajectory within the preset time range before and after reaching the stationary point can be traversed, which needs to meet the requirements of less than 20 meters and within 5 minutes. The difference between the time corresponding to the last point of the trajectory and the time corresponding to the first point of the trajectory can be used as the stay time of the stationary point.
[0071] If the stay time is longer than a preset time threshold, for example, longer than 2 minutes, the station point can be used as a candidate station point.
[0072] If each driving trajectory segment determines multiple stationary points with a stay time greater than a preset time threshold, the multiple stationary points can be screened again, and finally an optimal candidate stationary point can be retained for the arrival position, and an optimal candidate stationary point can also be retained for the completion position. The screening condition can be that the target vehicle has the longest stay time at the optimal candidate stationary point and has the shortest distance from the arrival position or the completion position.
[0073] In one embodiment of the present application, calculating the duration of stay of the target vehicle at each remaining stop includes:
[0074] Traversing the stationary point driving trajectory of the target vehicle arriving at each of the remaining stationary points within a third preset time range, the stationary point driving trajectory including a start time and an end time;
[0075] The difference between the start time and the end time is used as the duration of stay at the remaining stop.
[0076] Optionally, for each stop point in each driving trajectory segment, the time when the target vehicle arrives at the stop point can be determined, and the driving trajectory within a preset range before and after the time can be intercepted based on the time. The driving trajectory may include a starting point and an end point, and the difference between the time corresponding to the starting point and the time corresponding to the end point is used as the length of stay at the stop point.
[0077] The preset time range may be a specific time number, such as 5 minutes. For example, if the target vehicle arrives at the station at 8:10, the driving trajectory between 8:05 and 8:15 may be intercepted. It should be noted that the driving speed of the target vehicle at the station may be less than 2 m / s.
[0078] In an embodiment of the present application, the step of sorting the candidate loading / unloading locations by using a preset sorting model and determining the actual loading / unloading location based on the sorting result includes:
[0079] intercepting a driving trajectory string corresponding to each of the candidate loading / unloading locations in the driving trajectory;
[0080] Based on the driving trajectory string, each of the candidate loading / unloading locations is scored by a preset sorting model, and the candidate loading / unloading locations are sorted in descending order of the score;
[0081] The candidate loading / unloading position ranked first is used as the actual loading / unloading position.
[0082] Optionally, the preset sorting model may include a feature extraction network and a scoring model. The feature extraction network may be a neural network, such as a convolutional neural network CNN, and the scoring model may be a regression model, a neural network model, a decision tree, etc. For each candidate loading / unloading location, its corresponding driving trajectory string may be intercepted in the driving trajectory. For example, a driving trajectory string of each candidate loading / unloading location within a preset time range before and after the target vehicle arrives at the location, such as within 10 minutes, and the speed is less than a preset speed threshold, such as 3 meters / second, may be intercepted. The driving trajectory string may specifically include speed information, location information, etc. Through the feature extraction network, a variety of different feature vectors can be extracted, such as the type of candidate loading / unloading location (such as arrival location, completion location, candidate station point), the distance between it and other candidate loading / unloading locations, the number of other candidate loading / unloading locations within a distance range of 10 meters, 20 meters, 30 meters, etc., the length of time the target vehicle stays here, the number of points where the target vehicle's driving speed is less than 0 meters / second, 1 meter / second, 2 meters / second, and 3 meters / second, and the number of trajectories within a distance range of 10, 20, 30 meters, etc., and their corresponding statistics. And input into the scoring model for scoring, then based on the score of each candidate loading / unloading location, and sorting in order from high to low or from low to high, a sorted list is obtained. Based on the sorted list, the candidate loading / unloading location with the highest score can be obtained and used as the real loading / unloading location.
[0083] In an embodiment of the present application, the step of scoring each of the candidate loading / unloading locations based on the driving trajectory string by a preset sorting model, and sorting the candidate loading / unloading locations in descending order of scores, includes:
[0084] Extracting features from the driving trajectory string to obtain a feature vector corresponding to each of the candidate loading / unloading locations;
[0085] Performing weighted summation on the feature vectors corresponding to each candidate loading / unloading location to obtain a score for each candidate loading / unloading location;
[0086] The candidate loading / unloading locations are sorted in descending order of the scores.
[0087] Optionally, through the feature extraction network, the feature vector corresponding to each trajectory string can be extracted, each feature vector can be scored, and then a corresponding weight is assigned to it based on the feature vector, and the weighted sum is calculated, which can be used as the score of each candidate loading / unloading location. Then, the candidate loading / unloading locations can be sorted in descending order according to the score.
[0088] In an embodiment of the present application, before taking the candidate loading / unloading location with the highest score as the actual loading / unloading location, the process includes:
[0089] Based on the ranking results, determining the candidate loading / unloading location with the highest score, and performing feasibility determination on the candidate loading / unloading location with the highest score;
[0090] When the candidate loading / unloading location with the highest score does not meet the feasibility determination condition, calling the fallback strategy, determining the fallback loading / unloading location, and using the fallback loading / unloading location as the actual loading / unloading location; or
[0091] When the sorting result is not obtained within a preset time range, the bottom-line strategy is called to determine the bottom-line loading / unloading position, and the bottom-line loading / unloading position is used as the actual loading / unloading position.
[0092] Optionally, a fallback strategy can be set, which can be used to determine the fallback loading / unloading location, for example, taking the arrival location as the real loading / unloading location, or taking the completion location as the real loading / unloading location. Specifically, when the model outputs the sorting results, the real loading / unloading location with the highest score can be selected from the sorting results, and it is further determined whether the score of the real loading / unloading location with the highest score is greater than a preset score, such as 90 points. If so, it is used as the real loading / unloading location. Otherwise, it can be considered that the model judgment is wrong. At this time, the fallback loading / unloading location can be determined based on the fallback strategy, and the fallback loading / unloading location can be used as the real loading / unloading location.
[0093] If the sorting result is not obtained within the preset time range due to incorrect input data or model failure, the bottom-line loading / unloading position can be determined directly according to the bottom-line strategy, and the bottom-line loading / unloading position can be used as the actual loading / unloading position.
[0094] In one embodiment of the present application, obtaining the driving trajectory of the target vehicle and the order base table includes:
[0095] Configure tracking conditions based on tracking requirements;
[0096] When the tracking condition is triggered, the tracking generates the arrival time and arrival position of the loading / unloading place, and the completion time and completion position when the loading / unloading is completed;
[0097] The arrival time and arrival position at the loading / unloading place, and the completion time and completion position when the loading / unloading is completed are recorded in the order basic table.
[0098] Optionally, a tracking condition can be set based on tracking requirements. When the tracking condition is triggered, for example, when the driver clicks "arrived", the current time and location can be collected as the arrival time and arrival location. When the driver clicks "finished", the current time and location can be collected as the completion time and completion location. Then, the arrival time and arrival location at the loading / unloading place, as well as the completion time and completion location when loading / unloading are completed, can be recorded in the order basic table and stored in association with the driver ID for subsequent use.
[0099] In an embodiment of the present application, by obtaining the driving trajectory of the target vehicle, the arrival time and arrival position at the loading / unloading site, and the completion time and completion position when the loading / unloading is completed, the candidate points are screened, and a comprehensive judgment and mining is performed to select the candidate position with the highest score as the actual loading / unloading point, which can improve the accuracy of the actual loading / unloading position and improve the user experience.
[0100] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
[0101] In one embodiment, a loading and unloading position excavation device is provided, and the loading and unloading position excavation device corresponds to the loading and unloading position excavation method in the above embodiment. Figure 2 As shown, the loading / unloading location mining device includes an information acquisition unit 10, a driving trajectory judgment and interception unit 20, a candidate stationary point determination unit 30 and a real loading / unloading location determination unit 40. The functional modules are described in detail as follows:
[0102] The information acquisition unit 10 is used to acquire the driving trajectory of the target vehicle and the order base table, wherein the order base table includes the arrival time and arrival position at the loading / unloading place, and the completion time and completion position when the loading / unloading is completed;
[0103] A driving trajectory judgment and interception unit 20, used to intercept a first driving trajectory segment within a first preset time range of the arrival time and a second driving trajectory segment within a second preset time range of the completion time in the driving trajectory;
[0104] a candidate stationary point determination unit 30, configured to respectively calculate the dwell time of each stationary point in the first driving trajectory segment and the second driving trajectory segment, and when the dwell time is greater than a preset time threshold, use the stationary point as a candidate stationary point;
[0105] The actual loading / unloading location determining unit 40 is used to take the arrival location, the completion location and the candidate station point as candidate loading / unloading locations, sort the candidate loading / unloading locations by a preset sorting model, and determine the actual loading / unloading location based on the sorting result.
[0106] In the embodiment of the present application, the candidate stationary point determination unit 30 is further configured to:
[0107] Determine each stationary point in the first driving trajectory segment and the second driving trajectory segment;
[0108] Determining the speed of the target vehicle when passing each of the stationary points;
[0109] When the driving speed is greater than a preset speed threshold, filtering the corresponding stationary point;
[0110] Calculate the dwell time of the target vehicle at each remaining station;
[0111] The remaining stationary points whose stay time is longer than the preset time threshold are used as the candidate stationary points.
[0112] In the embodiment of the present application, the candidate stationary point determination unit 30 is further configured to:
[0113] Traversing the stationary point driving trajectory of the target vehicle arriving at each of the remaining stationary points within a third preset time range, the stationary point driving trajectory including a start time and an end time;
[0114] The difference between the start time and the end time is used as the duration of stay at the remaining stop.
[0115] In one embodiment of the present application, the real loading / unloading position determination unit 40 is further used to:
[0116] intercepting a driving trajectory string corresponding to each of the candidate loading / unloading locations in the driving trajectory;
[0117] Based on the driving trajectory string, each of the candidate loading / unloading locations is scored by a preset sorting model, and the candidate loading / unloading locations are sorted in descending order of the score;
[0118] The candidate loading / unloading position ranked first is used as the actual loading / unloading position.
[0119] In one embodiment of the present application, the real loading / unloading position determination unit 40 is further used to:
[0120] Extracting features from the driving trajectory string to obtain a feature vector corresponding to each of the candidate loading / unloading locations;
[0121] Performing weighted summation on the feature vectors corresponding to each candidate loading / unloading location to obtain a score for each candidate loading / unloading location;
[0122] The candidate loading / unloading locations are sorted in descending order according to the scores. In one embodiment of the present application, the device further includes: a bottom-up unit, which is used to:
[0123] Based on the ranking results, determining the candidate loading / unloading location with the highest score, and performing feasibility determination on the candidate loading / unloading location with the highest score;
[0124] When the candidate loading / unloading location with the highest score does not meet the feasibility determination condition, calling the fallback strategy, determining the fallback loading / unloading location, and using the fallback loading / unloading location as the actual loading / unloading location; or
[0125] When the sorting result is not obtained within a preset time range, the bottom-line strategy is called to determine the bottom-line loading / unloading position, and the bottom-line loading / unloading position is used as the actual loading / unloading position.
[0126] In one embodiment of the present application, the device further includes a buried point data acquisition unit, which is used to:
[0127] Configure tracking conditions based on tracking requirements;
[0128] When the tracking condition is triggered, the tracking generates the arrival time and arrival position of the loading / unloading place, and the completion time and completion position when the loading / unloading is completed;
[0129] The arrival time and arrival position at the loading / unloading place, and the completion time and completion position when the loading / unloading is completed are recorded in the order basic table.
[0130] In the embodiment of the present application, by obtaining the driving trajectory of the target vehicle, the arrival time and arrival position at the loading / unloading place, and the completion time and completion position when loading / unloading is completed, the candidate station points are screened, and comprehensive judgment and mining are performed to select the candidate position with the highest score as the real loading and unloading point, which can improve the accuracy of the real loading / unloading position and improve the user experience. In the embodiment of the present application, by obtaining the driving trajectory of the target vehicle, the arrival time and arrival position at the loading / unloading place, and the completion time and completion position when loading / unloading is completed, the candidate station points are screened, and comprehensive judgment and mining are performed to select the candidate position with the highest score as the real loading and unloading point, which can improve the accuracy of the real loading / unloading position and improve the user experience.
[0131] The specific definition of the loading and unloading location mining device can be found in the definition of the loading and unloading location mining method above, which will not be repeated here. Each module in the above-mentioned loading and unloading location mining device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.
[0132] In one embodiment, a computer device is provided. The computer device may be a terminal device, and its internal structure diagram may be as follows: Figure 3 As shown. The computer device includes a processor, a memory, and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a readable storage medium. The readable storage medium stores computer-readable instructions. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer-readable instructions are executed by the processor, a method for mining loading and unloading locations is implemented. The readable storage medium provided in this embodiment includes a non-volatile readable storage medium and a volatile readable storage medium.
[0133] In an embodiment of the present application, a computer device is provided, including a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor. When the processor executes the computer-readable instructions, the steps of the loading and unloading location mining method as described above are implemented.
[0134] In an embodiment of the application, a readable storage medium is provided, wherein the readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the method for mining loading and unloading locations as described above are implemented.
[0135] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing related hardware through computer-readable instructions, and the computer-readable instructions can be stored in a non-volatile readable storage medium or a volatile readable storage medium. When the computer-readable instructions are executed, they may include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.
[0136] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.
[0137] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.
Claims
1. A method for excavating a loading and unloading location, characterized in that: The method comprises: Obtaining the driving trajectory of the target vehicle and the order base table, wherein the order base table includes the arrival time and arrival position at the loading / unloading place, and the completion time and completion position when the loading / unloading is completed; intercepting a first driving trajectory segment within a first preset time range of the arrival time and a second driving trajectory segment within a second preset time range of the completion time from the driving trajectory; respectively calculating the dwell time of each stationary point in the first driving trajectory segment and the second driving trajectory segment, and when the dwell time is greater than a preset time threshold, taking the stationary point as a candidate stationary point; The arrival location, the completion location and the candidate station point are used as candidate loading / unloading locations, the candidate loading / unloading locations are sorted by a preset sorting model, and the actual loading / unloading location is determined based on the sorting result.
2. The method for excavating a loading and unloading location according to claim 1, characterized in that: The step of respectively calculating the dwell time of each stationary point in the first driving trajectory segment and the second driving trajectory segment, and taking the stationary point as a candidate stationary point when the dwell time is greater than a preset time threshold, comprises: Determine each stationary point in the first driving trajectory segment and the second driving trajectory segment; Determining the speed of the target vehicle when passing each of the stationary points; When the driving speed is greater than a preset speed threshold, filtering the corresponding stationary point; Calculate the dwell time of the target vehicle at each remaining station; The remaining stationary points whose stay time is longer than the preset time threshold are used as the candidate stationary points.
3. The method for excavating a loading and unloading location according to claim 1, characterized in that: The calculating the stay time of the target vehicle at each remaining stop includes: Traversing the stationary point driving trajectory of the target vehicle arriving at each of the remaining stationary points within a third preset time range, the stationary point driving trajectory including a start time and an end time; The difference between the start time and the end time is used as the duration of stay at the remaining stop.
4. The method for excavating a loading and unloading location according to claim 1, characterized in that: The step of sorting the candidate loading / unloading locations by using a preset sorting model and determining the actual loading / unloading location based on the sorting result includes: intercepting a driving trajectory string corresponding to each of the candidate loading / unloading locations in the driving trajectory; Based on the driving trajectory string, each of the candidate loading / unloading locations is scored by a preset sorting model, and the candidate loading / unloading locations are sorted in descending order of the score; The candidate loading / unloading position ranked first is used as the actual loading / unloading position.
5. The method for excavating a loading and unloading location according to claim 4, characterized in that: The step of scoring each of the candidate loading / unloading locations based on the driving trajectory string by a preset sorting model, and sorting the candidate loading / unloading locations in descending order of scores, includes: Extracting features from the driving trajectory string to obtain a feature vector corresponding to each of the candidate loading / unloading locations; Performing weighted summation on the feature vectors corresponding to each candidate loading / unloading location to obtain a score for each candidate loading / unloading location; The candidate loading / unloading locations are sorted in descending order of the scores.
6. The method for excavating a loading and unloading location according to claim 4, characterized in that: Before taking the candidate loading / unloading location with the highest score as the actual loading / unloading location, the following steps are performed: Based on the ranking results, determining the candidate loading / unloading location with the highest score, and performing feasibility determination on the candidate loading / unloading location with the highest score; When the candidate loading / unloading location with the highest score does not meet the feasibility determination condition, calling the fallback strategy, determining the fallback loading / unloading location, and using the fallback loading / unloading location as the actual loading / unloading location; or When the sorting result is not obtained within a preset time range, the bottom-line strategy is called to determine the bottom-line loading / unloading position, and the bottom-line loading / unloading position is used as the actual loading / unloading position.
7. The method for excavating a loading and unloading location according to claim 1, characterized in that: Before obtaining the driving trajectory of the target vehicle and the order base table, the following steps are included: Configure tracking conditions based on tracking requirements; When the tracking condition is triggered, the tracking generates the arrival time and arrival position of the loading / unloading place, and the completion time and completion position when the loading / unloading is completed; The arrival time and arrival position at the loading / unloading place, and the completion time and completion position when the loading / unloading is completed are recorded in the order basic table.
8. A method for excavating a loading and unloading location, characterized in that: The method comprises: An information acquisition unit, used to acquire the driving trajectory of the target vehicle and an order base table, wherein the order base table includes the arrival time and arrival position at the loading / unloading place, and the completion time and completion position when the loading / unloading is completed; A driving trajectory judgment and interception unit, used to intercept a first driving trajectory segment within a first preset time range of the arrival time and a second driving trajectory segment within a second preset time range of the completion time in the driving trajectory; a candidate stationary point determination unit, configured to respectively calculate the dwell time of each stationary point in the first driving trajectory segment and the second driving trajectory segment, and when the dwell time is greater than a preset time threshold, use the stationary point as a candidate stationary point; The real loading / unloading position determining unit is used to take the arrival position, the completion position and the candidate station point as candidate loading / unloading positions, sort the candidate loading / unloading positions by a preset sorting model, and determine the real loading / unloading position based on the sorting result.
9. A computer device comprising a memory, a processor, and computer-readable instructions stored in the memory and executed on the processor, characterized in that: When the processor executes the computer-readable instructions, the method for mining loading and unloading locations according to any one of claims 1 to 7 is implemented.
10. A readable storage medium having computer readable instructions stored thereon, characterized in that: When the computer-readable instructions are executed by a processor, the method for mining loading and unloading locations according to any one of claims 1 to 7 is implemented.