Data processing methods, devices, storage media and servers

Abstract

This application discloses a data processing method, apparatus, storage medium, and server. The method includes: constraining the time and location of trajectory points in driving trajectory data based on order data and driver operation data to determine multiple candidate trajectory points from the driving trajectory data; clustering the multiple candidate trajectory points to obtain multiple clusters; constraining the location of the cluster center points of the multiple clusters based on order data and driver operation data to determine candidate clusters from the multiple clusters; and constraining the driver's dwell time at each trajectory point within the candidate cluster and the location of each trajectory point within the candidate cluster to determine the target start point or target end point of the order from the trajectory points within the candidate cluster. This solution uses clustering algorithms and strategies to identify actual loading and unloading points, which can improve the accuracy of real location point mining in freight scenarios.

Description

Technical Field

[0001] This application relates to the field of electronic computer technology, and in particular to a data processing method, apparatus, storage medium and server. Background Technology

[0002] Existing trajectory mining solutions mostly focus on research into algorithms for identifying stop points, taxi pick-up and drop-off locations in the passenger transport industry, and loading and unloading points for long-haul trucks. However, research on algorithms for identifying loading and unloading points for trucks in intra-city freight scenarios is currently lacking, despite the increasingly urgent need for such identification in the intra-city freight industry.

[0003] For third-party platforms, a typical transportation route for intra-city freight is as follows: the driver confirms the order on the platform, confirms the order with the customer by phone, and then proceeds to the order's origin at the agreed time. The driver first stops near the origin for a period of time to confirm arrival on the platform and confirm the actual loading point with the customer by phone. Then, the driver proceeds to the actual loading point, stays for a while to load the goods, and then continues to the order's destination. Similarly, upon arrival at the destination, the driver stays for a while to confirm arrival on the platform and confirm the actual unloading point with the customer by phone. Then, the driver proceeds to the actual unloading point, stays for a while to unload the goods, and then proceeds to the origin of the next order to begin the next round of transportation. Therefore, increasing the percentage of digging points that are actually loading and unloading points is crucial for improving meeting efficiency.

[0004] Currently, when users place orders on third-party platforms, some orders require drivers to plan routes based on the starting point filled in by the user after accepting the order. However, before reaching the starting point, drivers need to contact the user by phone for manual navigation, resulting in high communication costs when the driver and user meet the goods. Analysis of driver trajectory data revealed three main issues: first, driver trajectories are derived from driver location data, with an approximately 5% missing trajectory rate; second, 51% of drivers confirmed that the loading point was the actual loading point, and 49% confirmed that the unloading point was the actual unloading point; third, 13% of users' order starting points were the actual loading points, and 7% confirmed that the order destination was the actual loading point. Therefore, the accuracy of loading and unloading location information in the existing solution is poor. Summary of the Invention

[0005] This application provides a data processing method, apparatus, storage medium, and server that can improve the accuracy of real location point mining.

[0006] Firstly, embodiments of this application provide a data processing method applied in a freight transportation scenario, including:

[0007] Obtain order data and corresponding driving trajectory data;

[0008] Based on order data and driver operation data, constraints are applied to the time and location of trajectory points in the driving trajectory data to determine multiple candidate trajectory points from the driving trajectory data;

[0009] Multiple candidate trajectory points are clustered to obtain multiple clusters;

[0010] Based on the order data and the driver operation data, the positions of the cluster centers of the multiple clusters are constrained, and candidate clusters are determined from the multiple clusters;

[0011] The driver's dwell time at each trajectory point within the candidate cluster and the position of each trajectory point within the candidate cluster are constrained, and the target starting point of the order is determined from the trajectory points within the candidate cluster.

[0012] Secondly, embodiments of this application provide another data processing method applied in freight scenarios, including:

[0013] Obtain order data and corresponding driving trajectory data;

[0014] Based on order data and driver operation data, constraints are applied to the time and location of trajectory points in the driving trajectory data to determine multiple candidate trajectory points from the driving trajectory data;

[0015] Multiple candidate trajectory points are clustered to obtain multiple clusters;

[0016] Based on the order data and the driver operation data, the positions of the cluster centers of the multiple clusters are constrained, and candidate clusters are determined from the multiple clusters;

[0017] The driver's dwell time at each trajectory point within the candidate cluster and the position of each trajectory point within the candidate cluster are constrained, and the target destination of the order is determined from the trajectory points within the candidate cluster.

[0018] Thirdly, embodiments of this application provide another data processing apparatus, applied in a freight scenario, including:

[0019] The first acquisition unit is used to acquire order data and corresponding driving trajectory data;

[0020] The first determining unit is used to constrain the time and position of trajectory points in the driving trajectory data based on order data and driver operation data, and to determine multiple candidate trajectory points from the driving trajectory data;

[0021] The first clustering unit is used to cluster multiple candidate trajectory points to obtain multiple clusters;

[0022] The second determining unit is used to constrain the position of the cluster center point of the multiple clusters based on the order data and the driver operation data, and determine candidate clusters from the multiple clusters.

[0023] The third determining unit is used to constrain the driver's dwell time at each trajectory point in the candidate cluster and the position of each trajectory point in the candidate cluster, and to determine the target starting point of the order from the trajectory points in the candidate cluster.

[0024] Fourthly, embodiments of this application provide another data processing apparatus, applied in a freight scenario, including:

[0025] The second acquisition unit is used to acquire order data and corresponding driving trajectory data;

[0026] The fourth determining unit is used to constrain the time and position of trajectory points in the driving trajectory data based on order data and driver operation data, and to determine multiple candidate trajectory points from the driving trajectory data;

[0027] The second clustering unit is used to cluster multiple candidate trajectory points to obtain multiple clusters;

[0028] The fifth determining unit is used to constrain the position of the cluster center point of the multiple clusters based on the order data and the driver operation data, and to determine candidate clusters from the multiple clusters;

[0029] The sixth determining unit is used to constrain the driver's dwell time at each trajectory point in the candidate cluster and the position of each trajectory point in the candidate cluster, and to determine the target destination of the order from the trajectory points in the candidate cluster.

[0030] Fifthly, embodiments of this application also provide a computer-readable storage medium storing a plurality of instructions adapted to be loaded by a processor to execute the data processing method described above.

[0031] Sixthly, embodiments of this application also provide a server, including a processor and a memory, wherein the processor is electrically connected to the memory, the memory is used to store instructions and data, and the processor is used to execute the above-described data processing method.

[0032] In this embodiment, based on order data and driver operation data, constraints are imposed on the time and location of trajectory points in the driving trajectory data to determine multiple candidate trajectory points. These candidate trajectory points are then clustered to obtain multiple clusters. Based on the order data and driver operation data, the positions of the cluster centers of these clusters are constrained to determine candidate clusters. Finally, constraints are imposed on the driver's dwell time at each trajectory point within a candidate cluster and the position of each trajectory point within that cluster, determining the target start or end point of the order from the trajectory points within the candidate clusters. This solution uses clustering algorithms and strategies to identify actual loading and unloading points, improving the accuracy of real location point discovery in freight scenarios. Attached Figure Description

[0033] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0034] Figure 1 This is a flowchart illustrating the data processing method provided in the embodiments of this application.

[0035] Figure 2 This is a schematic diagram of the architecture of the loading and unloading point discovery system provided in the embodiments of this application.

[0036] Figure 3 This is another schematic diagram of the data processing method provided in the embodiments of this application.

[0037] Figure 4 This is a schematic diagram of the structure of the data processing device provided in the embodiments of this application.

[0038] Figure 5 This is a schematic diagram of the structure of the data processing device provided in the embodiments of this application.

[0039] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0040] Figure 7 This is another structural schematic diagram of the electronic device provided in the embodiments of this application. Detailed Implementation

[0041] The technical solutions of 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 without creative effort are within the scope of protection of this application.

[0042] Currently, the industry primarily relies on analyzing truck monitoring data to identify loading and unloading points in freight scenarios, focusing on speed, load, and direction changes. This data helps identify specific driver behaviors and provides drivers with cargo matching information, enabling intelligent cargo allocation. However, in the context of same-city freight services placed through third-party freight platforms, the available data typically includes driver location information, driver operation information, and other order information. Among these, the proportion of driver-confirmed loading points that are actually loading points is 51%, while this proportion is only 49% for unloading points. The proportion of user orders originating from actual loading points is 13%, and the proportion of user orders ending at actual loading points is 7%. Therefore, new methods are needed to mine actual loading and unloading points based on available data. Furthermore, a higher percentage of identified loading and unloading points leads to a higher rate of accurate point recommendations for users, which is crucial for providing loading and unloading point recommendations to order placement users, improving truck-cargo meeting efficiency, and enhancing the driver-passenger experience.

[0043] To improve driver-cargo meeting efficiency, reduce meeting costs, and encourage more drivers and users to choose and remain on the platform, a method is needed to identify actual loading and unloading points, thereby generating a database of real loading and unloading points and providing users with loading and unloading point recommendation services. Based on this, embodiments of this application provide a data processing method, apparatus, storage medium, and server that combine user order data, driver operation data, and driving trajectory data to identify and mine real loading and unloading points, thereby improving the on-time rate during freight order acceptance.

[0044] In one embodiment, a data processing method is provided in an application server. (See reference...) Figure 1 The specific process of this data processing method can be summarized as follows:

[0045] 101. Obtain order data and corresponding driving trajectory data.

[0046] This solution is applied to freight scenarios. Specifically, order data refers to the relevant data of freight requests initiated by users through freight apps, mini-programs, or web pages installed on their electronic devices, such as basic user information (e.g., name, contact information) and basic freight information (e.g., freight origin, freight destination, delivery time, cargo details, etc.).

[0047] 102. Based on order data and driver operation data, constraints are applied to the time and location of trajectory points in the driving trajectory data to determine multiple candidate trajectory points. Driving trajectory data refers to the actual driving route data and driving time data during this freight transport process.

[0048] In one embodiment, when determining multiple candidate trajectory points from driving trajectory data by constraining the time and location of trajectory points based on order data and driver operation data, the specific process may include the following:

[0049] Based on the driver's operation data, the time of each trajectory point in the driving trajectory data, and the first time constraint conditions, the starting segment of the order trajectory is determined;

[0050] Based on order data, driver operation data, the location of each trajectory point in the starting road segment, the time of each trajectory point in the starting road segment, the first distance constraint, and the second time constraint, multiple candidate trajectory points are determined from the starting road segment.

[0051] In one embodiment, the driver operation data includes: the driver's confirmation of order acceptance time and the driver's confirmation of arrival at the starting point. When determining the starting segment of the order trajectory based on the driver operation data, the time of each trajectory point in the trajectory data, and the first time constraint condition, specifically, the trajectory point corresponding to the driver's confirmation of order acceptance time and the trajectory points within a specified time period before the driver confirms arrival at the starting point can be selected as the starting segment of the order trajectory based on the time of each trajectory point in the trajectory data.

[0052] In one embodiment, the order data includes: the order origin, and the driver operation data includes: the driver's confirmed order acceptance time, the driver's confirmed arrival time at the origin, and the driver's confirmed loading point. When determining multiple candidate trajectory points from the origin road segment based on the order data, the driver operation data, the positions of each trajectory point in the origin road segment, the times of each trajectory point in the origin road segment, a first distance constraint, and a second time constraint, the specific process may include the following:

[0053] Based on the distance between each trajectory point in the driving trajectory data and the order origin, or the distance between each trajectory point in the driving trajectory data and the driver's confirmed loading point, trajectory points that meet the first distance constraint condition are selected from the origin road segment;

[0054] Based on the time difference between the selected trajectory points and the driver's confirmed loading time, and the time difference between the selected trajectory points and the driver's confirmed arrival time at the starting point, trajectory points whose time differences satisfy the second time constraint are selected as candidate trajectory points.

[0055] 103. Cluster the multiple candidate trajectory points to obtain multiple clusters.

[0056] Specifically, the density-based clustering method DBSCAN can be used to cluster the candidate trajectory points for loading and unloading, with a minimum sample size of n = 2 and an ε-neighborhood radius of eps = 0.00009.

[0057] 104. Based on the order data and the driver operation data, constrain the positions of the cluster centers of multiple clusters, and determine candidate clusters from the multiple clusters.

[0058] In one embodiment, the order data may include: the order origin, and the driver operation data includes: the driver's confirmed loading completion point. When constraining the positions of the cluster centers of the multiple clusters based on the order data and the driver operation data to determine candidate clusters from the multiple clusters, the specific process may include the following:

[0059] Obtain the first distance between the cluster center point and the order start point, and the second distance between the cluster center point and the point where the driver confirms the completion of loading;

[0060] Multiple clusters are sorted according to the first distance and the second distance respectively, resulting in the first sorting result and the second sorting result;

[0061] Based on the first and second sorting results respectively, select the clusters that satisfy the first sorting constraint from multiple clusters;

[0062] The selected clusters, as well as the clusters where the driver confirmed the loading completion point, are used as candidate clusters.

[0063] 105. Constrain the driver's dwell time at each trajectory point within the candidate cluster and the position of each trajectory point within the candidate cluster, and determine the target starting point of the order from the trajectory points within the candidate cluster.

[0064] In one embodiment, when determining the target starting point of the order from the trajectory points within the candidate cluster, the third distance between each trajectory point in the candidate cluster and the order starting point, the fourth distance between each trajectory point in the candidate cluster and the driver-confirmed loading point, and the fifth distance between each trajectory point in the candidate cluster and the driver-confirmed loading completion point can be obtained respectively; a first ratio of the dwell time to the third distance, a second ratio of the dwell time to the fourth distance, and a third ratio of the dwell time to the fifth distance can be obtained. Finally, based on the first ratio, the second ratio, and the third ratio, the target starting point of the order is determined from the trajectory points within the candidate cluster.

[0065] In one embodiment, when determining the target starting point of the order from trajectory points within a candidate cluster based on a first ratio, a second ratio, and a third ratio, firstly, the trajectory points within the candidate cluster are scored based on the first ratio, the second ratio, the third ratio, and a preset scoring strategy. Then, based on the scoring results, the trajectory point with the highest score is selected from the trajectory points within the candidate cluster and confirmed as the target starting point of the order.

[0066] Similarly, in one embodiment, the above-described logical strategy can be used to mine and identify the destination of a trajectory order. That is, another data processing method is also provided, which can be as follows:

[0067] Obtain order data and corresponding driving trajectory data;

[0068] Based on order data and driver operation data, constraints are imposed on the time and location of trajectory points in the driving trajectory data to determine multiple candidate trajectory points from the driving trajectory data;

[0069] Multiple candidate trajectory points are clustered to obtain multiple clusters;

[0070] Based on order data and driver operation data, the location of the cluster center point of multiple clusters is constrained to determine candidate clusters from multiple clusters;

[0071] Constraints are imposed on the driver's dwell time at each trajectory point within the candidate cluster and the position of each trajectory point within the candidate cluster, and the target destination of the order is determined from the trajectory points within the candidate cluster.

[0072] Specifically, when identifying the target destination, order data can include: basic user information (such as name and contact information) and basic freight information (such as freight origin, freight destination, delivery time, cargo details, etc.). User operation data can include: driver's confirmed arrival time at the destination, driver's confirmed order completion time, driver's confirmed unloading point information, and driver's confirmed unloading completion point information.

[0073] As can be seen from the above, the data processing method provided in this embodiment, based on order data and driver operation data, constrains the time and position of trajectory points in the driving trajectory data to determine multiple candidate trajectory points from the driving trajectory data; clusters the multiple candidate trajectory points to obtain multiple clusters; constrains the position of the cluster center points of the multiple clusters based on order data and driver operation data to determine candidate clusters from the multiple clusters; and constrains the driver's dwell time at each trajectory point within the candidate cluster and the position of each trajectory point within the candidate cluster to determine the target start point or target end point of the order from the trajectory points within the candidate cluster. This solution uses clustering algorithms and strategies to identify actual loading and unloading points, which can improve the accuracy of real location point mining in freight scenarios.

[0074] In yet another embodiment of this application, a system for identifying actual loading and unloading points is also provided. (See reference...) Figure 2 The system architecture may include: electronic devices, communication devices, and server devices. Communication devices serve to connect servers and terminal devices, providing data exchange links; these communication devices can be implemented through, but are not limited to, the following: wireless networks (WiFi / 4G / 5G), wired networks, satellite communications, etc.

[0075] Specifically, users can use electronic devices to interact with the server by sending and receiving data through communication devices. Software programs can run on the server and electronic devices to perform tasks such as data sending, data receiving, data processing, data display, model building, and model prediction.

[0076] Electronic devices include, but are not limited to, smart terminal devices such as computers, mobile phones, and tablets, which can receive data from server devices through communication equipment. A freight APP can be installed on this electronic device, allowing users to place orders and generate freight orders. Drivers can accept freight orders through the APP and proceed to the freight origin to perform freight operations based on the order information. In this embodiment, "server" refers to server facilities in general, which can be a single independent server or a server cluster. Model building and deployment can be achieved by running corresponding programs on the server.

[0077] The server provides basic service capabilities through system software and application software. Building upon this, the server offers the ability to identify actual loading and unloading points for freight transport. In this solution, reference is made to... Figure 3 The server can perform the following functions:

[0078] Step 1: Data Cleaning and Processing

[0079] (11) Segmentation of trajectory data: The later of the time when the driver confirms the order acceptance time and the time when the driver confirms the arrival at the starting point 20 minutes before the start time is taken as the starting point of the order trajectory. The earlier of the time when the driver confirms the order 20 minutes after the driver completes the order and the time when the driver confirms the completion of unloading is taken as the ending point of the order trajectory. Then, the order data and trajectory data are associated through the driver ID and time.

[0080] Specifically, driver trajectory data is stored by time. Trajectory data is represented as di = {driver_id, loactioni, ti}, where i = 1, 2, ..., m, and driver_id is the driver's ID. Loactioni = {loni, lati}, where loni is the longitude of the location at a given time ti (e.g., "2021-12-17 13:13:13"), and lati is the latitude of the location at a given time ti. Order data is represented as order = {order_id, driver_id, o_order_t, o_order_loaction, o_arrived_t, o_loading_t, o_loading_location, o_loaded_t, o_loaded_location, d_order_t, d_order_loaction, d_arrived_t, d_unloading_t, d_unloading_location}. d_complete_t, d_complete_location}, where order_id is the driver's code, o_order_t and o_order_loaction are the time and location of the user's order start point, o_arrived_t, o_loading_t, o_loading_location, o_loaded_t, and o_loaded_location are the time and location of the driver's confirmed arrival at the start point, loading start time and location, and loading completion time and location, respectively; d_order_t and d_order_loaction are the time and location of the user's order end point, respectively; and d_arrived_t, d_unloading_t, d_unloading_location, d_complete_t, and d_complete_location are the time and location of the driver's confirmed arrival at the end point, unloading start time and location, and order completion time and location, respectively. The later of the driver's order confirmation time and the time before the driver confirms arrival at the starting point (e.g., 20 minutes) is taken as the starting point of the order trajectory. The earlier of the time after the driver confirms the order (e.g., 20 minutes) and the time after the driver confirms unloading (e.g., 20 minutes) is taken as the ending point of the order trajectory. Then, the order data and trajectory data are associated by the driver ID and time.

[0081] (12) Due to GPS positioning accuracy and signal strength issues, some drivers experience trajectory point drift. Since there is a certain time interval between trajectory data collection, the ratio of the sum of the distances between individual trajectory points and the distances between preceding and following trajectory points to the straight-line distance between preceding and following trajectory points can be used to determine if it is reasonable. If the ratio exceeds the set value, the trajectory data has drifted and will be considered noise data and discarded.

[0082] (13) The user and driver operation locations and times recorded in the order data are excluded if the operation time does not match the operation sequence. For example, if the driver confirms that the arrival time at the starting point is later than the confirmation of the start time of loading, this does not conform to the operation sequence logic.

[0083] (14) Track loading and unloading classification: Select tracks within a certain distance (e.g., 500m) from the user's order start point or the driver's confirmed loading point, and mark them as candidate loading track points if the time difference between the track point and the driver's confirmed loading time and arrival time at the start point is within a specified time (e.g., 10min). Similarly, select tracks within a certain distance (e.g., 500m) from the user's order end point or the driver's confirmed unloading point, and mark them as candidate unloading track points if the time difference between the track point and the driver's confirmed unloading time and arrival time at the end point is within a specified time (e.g., 10min).

[0084] Step 2: Identify loading and unloading points

[0085] (21) The candidate trajectory points for loading and unloading are clustered using the density-based clustering method DBSCAN. The minimum sample size n is 2, the ε-neighborhood radius eps is 0.00009, and the center point of the point cluster is used as the candidate point position to enter the subsequent scoring stage.

[0086] (22) Since some trajectories involve drivers searching for routes and repeating trajectory points after a long interval, calculating the dwell time using the time difference between points within a cluster would result in errors. Therefore, assuming the trajectory acquisition interval is n seconds, the dwell time can be calculated by multiplying the number of point clusters by n seconds.

[0087] (23) Select the three points closest to the cluster center and the driver's confirmed loading completion point, the point closest to the user's order start point, and the driver's confirmed loading completion point as candidate points for actual loading points; similarly, select the candidate points for actual unloading points.

[0088] (24) Each candidate point is scored using max{dwell time at candidate point / (distance between candidate point and user's order start point), candidate point stay time / (distance between waiting point and driver's confirmed loading start point), candidate point stay time / (distance between point and driver's confirmed loading completion point)}, and the point with the highest score is selected as the loading point. Similarly, the unloading point can be determined using max{dwell time at candidate point / (distance between candidate point and user's order end point), candidate point stay time / (distance between waiting point and driver's confirmed unloading start point), candidate point stay time / (distance between point and driver's confirmed unloading completion point)}, and each candidate point is scored using the same strategy, and the point with the highest score is selected as the unloading point.

[0089] Step 3: Effectiveness Evaluation

[0090] (31) Calculate the distance between the manually marked loading and unloading points and the loading and unloading points output by the above mining algorithm.

[0091] (32) Calculate the fixed point rate for each distance. Among them, the fixed point rate for loading site is the ratio of the number of points within a certain range (e.g., 30m) between the loading site excavation point and the loading site manual marking point to the total number of marking points; the fixed point rate for unloading site is the ratio of the number of points within a certain range (e.g., 30m) between the unloading site excavation point and the unloading site manual marking point to the total number of marking points.

[0092] It can be seen that this solution combines user order data, driving trajectory data and driver operation data to identify and mine the real loading and unloading points, which can improve the on-site accuracy rate in the freight order acceptance process.

[0093] In yet another embodiment of this application, a data processing apparatus is also provided. This data processing apparatus can be integrated into a server in the form of software or hardware. Figure 4 As shown, the data processing device 200 may include: a first acquisition unit 201, a first determination unit 202, a first clustering unit 203, a second determination unit 204, and a third determination unit 205, wherein:

[0094] The first acquisition unit 201 is used to acquire order data and corresponding driving trajectory data;

[0095] The first determining unit 202 is used to constrain the time and position of trajectory points in the driving trajectory data based on order data and driver operation data, and to determine multiple candidate trajectory points from the driving trajectory data;

[0096] The first clustering unit 203 is used to cluster multiple candidate trajectory points to obtain multiple clusters;

[0097] The second determining unit 204 is used to constrain the position of the cluster center point of the multiple clusters based on the order data and the driver operation data, and determine candidate clusters from the multiple clusters.

[0098] The third determining unit 205 is used to constrain the driver's dwell time at each trajectory point in the candidate cluster and the position of each trajectory point in the candidate cluster, and to determine the target starting point of the order from the trajectory points in the candidate cluster.

[0099] In one embodiment, the first determining unit 202 is used to:

[0100] Based on the driver's operation data, the time of each trajectory point in the driving trajectory data, and the first time constraint, the starting segment of the order trajectory is determined;

[0101] Based on the order data, the driver operation data, the position of each trajectory point in the starting road segment, the time of each trajectory point in the starting road segment, the first distance constraint, and the second time constraint, multiple candidate trajectory points are determined from the starting road segment.

[0102] In one embodiment, the driver operation data includes: the driver's confirmation of order acceptance time and the driver's confirmation of arrival at the starting point; when determining the starting segment of the order trajectory based on the driver operation data, the time of each trajectory point in the driving trajectory data, and the first time constraint condition, the first determining unit 202 is specifically used for:

[0103] Based on the time of each trajectory point in the driving trajectory data, the trajectory point corresponding to the time when the driver confirms the order acceptance, and the trajectory point within a specified time period before the driver confirms arrival at the starting point are selected as the starting segment of the order trajectory.

[0104] In one embodiment, the order data includes: the order origin; the driver operation data includes: the driver's confirmed order acceptance time, the driver's confirmed arrival time at the origin, and the driver's confirmed loading point; when determining multiple candidate trajectory points from the origin road segment based on the order data, the driver operation data, the positions of each trajectory point in the origin road segment, the times of each trajectory point in the origin road segment, the first distance constraint, and the second time constraint, the first determining unit 202 is specifically used for:

[0105] Based on the distance between each trajectory point in the driving trajectory data and the starting point of the order, or the distance between each trajectory point in the driving trajectory data and the loading point confirmed by the driver, trajectory points that meet the first distance constraint condition are selected from the starting point road segment;

[0106] Based on the time difference between the selected trajectory points and the time the driver confirms the loading time, and the time difference between the selected trajectory points and the time the driver confirms the arrival at the starting point, trajectory points whose time differences satisfy the second time constraint condition are determined from the selected trajectory points and are used as candidate trajectory points.

[0107] In one embodiment, the order data includes: the order origin; the driver operation data includes: the driver confirming the loading completion point; the second determining unit 204 is used for:

[0108] Obtain the first distance between the cluster center point and the order start point, and the second distance between the cluster center point and the point where the driver confirms the completion of loading;

[0109] The multiple clusters are sorted according to the first distance and the second distance respectively to obtain the first sorting result and the second sorting result;

[0110] Based on the first and second sorting results respectively, select the clusters that satisfy the first sorting constraint from multiple clusters;

[0111] The selected clusters, as well as the clusters where the driver confirmed the unloading completion point, are used as candidate clusters.

[0112] In one embodiment, the third determining unit 205 is used to:

[0113] The third distance between each trajectory point in the candidate cluster and the order starting point, the fourth distance between each trajectory point in the candidate cluster and the driver-confirmed loading point, and the fifth distance between each trajectory point in the candidate cluster and the driver-confirmed loading completion point are obtained respectively.

[0114] Obtain a first ratio of the dwell time to the third distance, a second ratio of the dwell time to the fourth distance, and a third ratio of the dwell time to the fifth distance;

[0115] Based on the first ratio, the second ratio, and the third ratio, the target starting point of the order is determined from the trajectory points within the candidate cluster.

[0116] In one embodiment, when determining the target starting point of the order from trajectory points within the candidate cluster based on the first ratio, the second ratio, and the third ratio, the third determining unit 205 is further configured to:

[0117] Based on the first ratio, the second ratio, the third ratio, and the preset scoring strategy, the trajectory points in the candidate cluster are scored;

[0118] Based on the scoring results, the trajectory point with the highest score is selected from the trajectory points in the candidate cluster and confirmed as the target starting point of the order.

[0119] As can be seen from the above, the data processing apparatus provided in this application, based on order data and driver operation data, constrains the time and position of trajectory points in the driving trajectory data to determine multiple candidate trajectory points from the driving trajectory data; clusters the multiple candidate trajectory points to obtain multiple clusters; constrains the position of the cluster center points of the multiple clusters based on order data and driver operation data to determine candidate clusters from the multiple clusters; and constrains the driver's dwell time at each trajectory point within the candidate cluster and the position of each trajectory point within the candidate cluster to determine the target starting point of the order from the trajectory points within the candidate cluster. This solution uses clustering algorithms and strategies to identify actual loading points, which can improve the accuracy of real location point mining in freight scenarios.

[0120] In yet another embodiment of this application, a data processing apparatus is also provided. This data processing apparatus can be integrated into a server in the form of software or hardware. Figure 5 As shown, the data processing device 300 may include: a second acquisition unit 301, a fourth determination unit 302, a second clustering unit 303, a fifth determination unit 304, and a sixth determination unit 305, wherein:

[0121] The first acquisition unit 301 is used to acquire order data and corresponding driving trajectory data;

[0122] The fourth determining unit 302 is used to constrain the time and position of trajectory points in the driving trajectory data based on order data and driver operation data, and to determine multiple candidate trajectory points from the driving trajectory data;

[0123] The second clustering unit 303 is used to cluster multiple candidate trajectory points to obtain multiple clusters;

[0124] The fifth determining unit 304 is used to constrain the position of the cluster center point of the multiple clusters based on the order data and the driver operation data, and to determine candidate clusters from the multiple clusters;

[0125] The sixth determining unit 305 is used to constrain the driver's dwell time at each trajectory point in the candidate cluster and the position of each trajectory point in the candidate cluster, and to determine the target starting point of the order from the trajectory points in the candidate cluster.

[0126] In one embodiment, the fourth determining unit 302 is used to:

[0127] Based on the driver's operation data, the time of each trajectory point in the driving trajectory data, and the first time constraint, the destination segment of the order trajectory is determined;

[0128] Based on the order data, the driver operation data, the location of each trajectory point in the destination road segment, the time of each trajectory point in the destination road segment, the first distance constraint, and the second time constraint, multiple candidate trajectory points are determined from the destination road segment.

[0129] In one embodiment, the driver operation data includes: the driver's confirmation of order completion time and the driver's confirmation of arrival at the destination time; when determining the destination segment of the order trajectory based on the driver operation data, the time of each trajectory point in the driving trajectory data, and the first time constraint condition, the fourth determining unit 302 is specifically used for:

[0130] Based on the time of each trajectory point in the driving trajectory data, the trajectory point corresponding to the time when the driver confirms the completion of the order, and the trajectory point within the specified time period before the driver confirms the arrival at the destination, are selected as the destination segment of the order trajectory.

[0131] In one embodiment, the order data includes: the order destination; the driver operation data includes: the driver's confirmed order completion time, the driver's confirmed arrival time at the destination, and the driver's confirmed unloading point; when determining multiple candidate trajectory points from the destination segment based on the order data, the driver operation data, the positions of each trajectory point in the destination segment, the times of each trajectory point in the destination segment, the first distance constraint, and the second time constraint, the fourth determining unit 302 is specifically used for:

[0132] Based on the distance between each trajectory point in the driving trajectory data and the destination of the order, or the distance between each trajectory point in the driving trajectory data and the unloading point confirmed by the driver, trajectory points that meet the first distance constraint condition are selected from the destination road segment;

[0133] Based on the time difference between the selected trajectory points and the driver's confirmed unloading time, and the time difference between the selected trajectory points and the driver's confirmed arrival time at the destination, trajectory points whose time differences satisfy the second time constraint condition are determined from the selected trajectory points and are used as candidate trajectory points.

[0134] In one embodiment, the order data includes: the order destination; the driver operation data includes: driver confirmation of unloading completion point; the fifth determining unit 304 is used for:

[0135] Obtain the first distance between the cluster center point and the order endpoint, and the second distance between the cluster center point and the point where the driver confirms the unloading completion;

[0136] The multiple clusters are sorted according to the first distance and the second distance respectively to obtain the first sorting result and the second sorting result;

[0137] Based on the first and second sorting results respectively, select the clusters that satisfy the first sorting constraint from multiple clusters;

[0138] The selected clusters, as well as the clusters where the driver confirmed the unloading completion point, are used as candidate clusters.

[0139] In one embodiment, the sixth determining unit 305 is used to:

[0140] The third distance between each trajectory point in the candidate cluster and the order endpoint, the fourth distance between each trajectory point in the candidate cluster and the driver-confirmed unloading point, and the fifth distance between each trajectory point in the candidate cluster and the driver-confirmed unloading completion point are obtained respectively.

[0141] Obtain a first ratio of the dwell time to the third distance, a second ratio of the dwell time to the fourth distance, and a third ratio of the dwell time to the fifth distance;

[0142] Based on the first ratio, the second ratio, and the third ratio, the target endpoint of the order is determined from the trajectory points within the candidate cluster.

[0143] In one embodiment, when determining the target endpoint of the order from trajectory points within the candidate cluster based on the first ratio, the second ratio, and the third ratio, the sixth determining unit 305 is further configured to:

[0144] Based on the first ratio, the second ratio, the third ratio, and the preset scoring strategy, the trajectory points in the candidate cluster are scored;

[0145] Based on the scoring results, the trajectory point with the highest score is selected from the trajectory points within the candidate cluster and confirmed as the target endpoint of the order.

[0146] As can be seen from the above, the data processing apparatus provided in this application, based on order data and driver operation data, constrains the time and position of trajectory points in the driving trajectory data to determine multiple candidate trajectory points from the driving trajectory data; clusters the multiple candidate trajectory points to obtain multiple clusters; constrains the position of the cluster center points of the multiple clusters based on order data and driver operation data to determine candidate clusters from the multiple clusters; and constrains the driver's dwell time at each trajectory point within the candidate cluster and the position of each trajectory point within the candidate cluster to determine the target destination of the order from the trajectory points within the candidate cluster. This solution uses clustering algorithms and strategies to identify actual unloading points, which can improve the accuracy of real location point mining in freight scenarios.

[0147] In yet another embodiment of this application, a server is also provided. For example... Figure 6 As shown, server 400 includes processor 401 and memory 402. Processor 401 and memory 402 are electrically connected.

[0148] The processor 401 is the control center of the server 400. It connects various parts of the server through various interfaces and lines. By running or loading applications stored in the memory 402 and calling data stored in the memory 402, it performs various functions of the server and processes data, thereby monitoring the server as a whole.

[0149] In one embodiment, the processor 401 in the server 400 loads the instructions corresponding to the processes of one or more applications into the memory 402 according to the following steps, and the processor 401 runs the applications stored in the memory 402 to realize various functions:

[0150] Obtain order data and corresponding driving trajectory data;

[0151] Based on order data and driver operation data, constraints are applied to the time and location of trajectory points in the driving trajectory data to determine multiple candidate trajectory points from the driving trajectory data;

[0152] Multiple candidate trajectory points are clustered to obtain multiple clusters;

[0153] Based on the order data and the driver operation data, the positions of the cluster centers of the multiple clusters are constrained, and candidate clusters are determined from the multiple clusters;

[0154] The driver's dwell time at each trajectory point within the candidate cluster and the position of each trajectory point within the candidate cluster are constrained, and the target starting point of the order is determined from the trajectory points within the candidate cluster.

[0155] In one embodiment, when constraining the time and position of trajectory points in the driving trajectory data based on order data and driver operation data, and determining multiple candidate trajectory points from the driving trajectory data, the processor 401 may perform the following operations:

[0156] Based on the driver's operation data, the time of each trajectory point in the driving trajectory data, and the first time constraint, the starting segment of the order trajectory is determined;

[0157] Based on the order data, the driver operation data, the position of each trajectory point in the starting road segment, the time of each trajectory point in the starting road segment, the first distance constraint, and the second time constraint, multiple candidate trajectory points are determined from the starting road segment.

[0158] In one embodiment, the driver operation data includes: the driver's confirmation of order acceptance time and the driver's confirmation of arrival at the starting point; when determining the starting segment of the order trajectory based on the driver operation data, the time of each trajectory point in the driving trajectory data, and the first time constraint condition, the processor 401 may perform the following operations:

[0159] Based on the time of each trajectory point in the driving trajectory data, the trajectory point corresponding to the time when the driver confirms the order acceptance, and the trajectory point within a specified time period before the driver confirms arrival at the starting point are selected as the starting segment of the order trajectory.

[0160] In one embodiment, the order data includes: the order origin; the driver operation data includes: the driver's confirmed order acceptance time, the driver's confirmed arrival time at the origin, and the driver's confirmed unloading point; when determining multiple candidate trajectory points from the origin road segment based on the order data, the driver operation data, the positions of each trajectory point in the origin road segment, the times of each trajectory point in the origin road segment, the first distance constraint, and the second time constraint, the processor 401 may perform the following operations:

[0161] Based on the distance between each trajectory point in the driving trajectory data and the starting point of the order, or the distance between each trajectory point in the driving trajectory data and the unloading point confirmed by the driver, trajectory points that meet the first distance constraint condition are selected from the starting point road segment;

[0162] Based on the time difference between the selected trajectory points and the driver's confirmed unloading time, and the time difference between the selected trajectory points and the driver's confirmed arrival time at the starting point, trajectory points whose time differences satisfy the second time constraint condition are determined from the selected trajectory points and are used as candidate trajectory points.

[0163] In one embodiment, the order data includes: the order origin, and the driver operation data includes: the driver's confirmation of unloading completion point; when constraining the positions of the cluster centers of the multiple clusters based on the order data and the driver operation data to determine candidate clusters from the multiple clusters, the processor 401 may perform the following operations:

[0164] Obtain the first distance between the cluster center point and the order start point, and the second distance between the cluster center point and the point where the driver confirms the completion of loading;

[0165] The multiple clusters are sorted according to the first distance and the second distance respectively to obtain the first sorting result and the second sorting result;

[0166] Based on the first and second sorting results respectively, select the clusters that satisfy the first sorting constraint from multiple clusters;

[0167] The selected clusters, as well as the clusters where the driver confirmed the loading completion point, are used as candidate clusters.

[0168] In one embodiment, when constraining the time and position of trajectory points in the driving trajectory data based on order data and driver operation data, and determining multiple candidate trajectory points from the driving trajectory data, the processor 401 may specifically perform the following operations:

[0169] Based on the driver's operation data, the time of each trajectory point in the driving trajectory data, and the first time constraint, the starting segment of the order trajectory is determined;

[0170] Based on the order data, the driver operation data, the position of each trajectory point in the starting road segment, the time of each trajectory point in the starting road segment, the first distance constraint, and the second time constraint, multiple candidate trajectory points are determined from the starting road segment.

[0171] In one embodiment, the driver operation data includes: the driver's confirmation of order acceptance time and the driver's confirmation of arrival at the starting point; when determining the starting segment of the order trajectory based on the driver operation data, the time of each trajectory point in the driving trajectory data, and the first time constraint condition, the processor 401 may specifically perform the following operations:

[0172] Based on the time of each trajectory point in the driving trajectory data, the trajectory point corresponding to the time when the driver confirms the order acceptance, and the trajectory point within a specified time period before the driver confirms arrival at the starting point are selected as the starting segment of the order trajectory.

[0173] Alternatively, in one embodiment, the processor 401 in the server 400 loads the instructions corresponding to the processes of one or more applications into the memory 402 according to the following steps, and the processor 401 runs the applications stored in the memory 402 to achieve various functions:

[0174] Obtain order data and corresponding driving trajectory data;

[0175] Based on order data and driver operation data, constraints are applied to the time and location of trajectory points in the driving trajectory data to determine multiple candidate trajectory points from the driving trajectory data;

[0176] Multiple candidate trajectory points are clustered to obtain multiple clusters;

[0177] Based on the order data and the driver operation data, the positions of the cluster centers of the multiple clusters are constrained, and candidate clusters are determined from the multiple clusters;

[0178] The driver's dwell time at each trajectory point within the candidate cluster and the position of each trajectory point within the candidate cluster are constrained, and the target destination of the order is determined from the trajectory points within the candidate cluster.

[0179] Memory 402 can be used to store applications and data. The applications stored in memory 402 contain instructions that can be executed in the processor. Applications can be composed of various functional modules. Processor 401 executes various functional applications and data processing by running the applications stored in memory 402.

[0180] In some embodiments, such as Figure 7 As shown, the server 400 also includes: a display screen 403, a control circuit 404, a radio frequency circuit 405, an input unit 406, and a power supply 407. The processor 401 is electrically connected to the display screen 403, the control circuit 404, the radio frequency circuit 405, the input unit 406, and the power supply 407.

[0181] Display screen 403 can be used to display information input by the user or information provided to the user via various graphical user interfaces of the server, which can be composed of images, text, icons, videos and any combination thereof.

[0182] The control circuit 404 is electrically connected to the display screen 403 and is used to control the display screen 403 to display information.

[0183] The radio frequency circuit 405 is used to transmit and receive radio frequency signals to establish wireless communication with electronic devices or other servers, and to transmit and receive signals with electronic devices or other servers.

[0184] The input unit 406 can be used to receive input numeric or character information or user characteristic information (such as fingerprints), and to generate keyboard, mouse, joystick, optical, or trackball signal inputs related to user settings and function control. The input unit 406 may include a fingerprint recognition module.

[0185] Power supply 407 is used to supply power to the various components of server 400. In some embodiments, power supply 407 can be logically connected to processor 401 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system.

[0186] although Figure 7 As not shown in the diagram, server 400 may also include speakers, Bluetooth modules, cameras, etc., which will not be described in detail here.

[0187] As can be seen from the above, the server provided in this application, based on order data and driver operation data, constrains the time and position of trajectory points in the driving trajectory data to determine multiple candidate trajectory points from the driving trajectory data; it clusters these multiple candidate trajectory points to obtain multiple clusters; based on order data and driver operation data, it constrains the position of the cluster center points of the multiple clusters to determine candidate clusters from the multiple clusters; it constrains the driver's dwell time at each trajectory point within the candidate cluster and the position of each trajectory point within the candidate cluster to determine the target start point or target end point of the order from the trajectory points within the candidate cluster. This solution uses clustering algorithms and strategies to identify actual loading and unloading points, which can improve the accuracy of real location point mining in freight scenarios.

[0188] In some embodiments, a computer-readable storage medium is also provided, which stores a plurality of instructions adapted to be loaded by a processor to perform any of the data processing methods described above.

[0189] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, which may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0190] The data processing method, apparatus, storage medium, and server provided in the embodiments of this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A data processing method applied to a freight scene, characterized in that, The method comprises the following steps: obtaining order data and corresponding driving track data; based on the order data and the driver operation data, the time and position of the track points in the driving track data are constrained, and a plurality of candidate track points are determined from the driving track data; the plurality of candidate track points are clustered to obtain a plurality of clustering clusters; based on the order data and the driver operation data, the position of the cluster center point of the plurality of clustering clusters is constrained, and a candidate cluster is determined from the plurality of clustering clusters; the time length of the driver staying at each track point in the candidate cluster and the position of each track point in the candidate cluster are constrained, and the target starting point of the order is determined from the track points in the candidate cluster; the method comprises the following steps: determine the starting point of the order track according to the driver operation data, the time of each track point in the driving track data, and the first time constraint condition; determine a plurality of candidate track points from the starting point section according to the order data, the driver operation data, the position of each track point in the starting point section, the time of each track point in the starting point section, the first distance constraint condition and the second time constraint condition.

2. The data processing method according to claim 1, characterized in that, The driver operation data includes the driver's confirmation of order acceptance time and the driver's confirmation of arrival at the starting point time; the method comprises the following steps: based on the time of each track point in the driving track data, the track point corresponding to the driver's confirmation of order acceptance time and the track point in the specified time period before the driver's determination of arrival at the starting point are selected as the starting point section of the order track.

3. The data processing method of claim 1, wherein, The order data includes the order starting point, and the driver operation data includes the driver's confirmation of order acceptance time, the driver's confirmation of arrival at the starting point time, and the driver's confirmation of loading point; the method comprises the following steps: based on the distance between each track point in the driving track data and the order starting point, or the distance between each track point in the driving track data and the driver's confirmation of loading point, the track points meeting the first distance constraint condition are screened out from the starting point section; based on the time difference between the time of the screened track points and the driver's confirmation of loading time, and the time difference between the time of the screened track points and the driver's confirmation of arrival at the starting point time, the track points meeting the second time constraint condition in time difference are determined from the screened track points as the candidate track points.

4. The data processing method of claim 1, wherein, The order data includes the order starting point, and the driver operation data includes the driver's confirmation of loading completion point; the method comprises the following steps: Obtaining a first distance between the cluster center point and the order starting point, and a second distance between the cluster center point and the driver-confirmed loading completion point; Respectively according to the first distance and the second distance, the plurality of clustering clusters are sorted to obtain a first sorting result and a second sorting result; Respectively according to the first sorting result and the second sorting result, a clustering cluster whose sorting satisfies a first sorting constraint condition is selected from the plurality of clustering clusters; The selected clustering cluster and the clustering cluster in which the driver-confirmed loading completion point is located are taken as candidate clusters.

5. The data processing method according to any one of claims 1 to 4, characterized in that, The constraint on the staying time of the driver at each trajectory point in the candidate cluster and the position of each trajectory point in the candidate cluster is used to determine the target starting point of the order from the trajectory points in the candidate cluster, which includes: Respectively obtaining a third distance between each trajectory point in the candidate cluster and the order starting point, a fourth distance between each trajectory point in the candidate cluster and the driver-confirmed loading point, and a fifth distance between each trajectory point in the candidate cluster and the driver-confirmed loading completion point; Obtaining a first ratio of the staying time to the third distance, a second ratio of the staying time to the fourth distance, and a third ratio of the staying time to the fifth distance; Based on the first ratio, the second ratio, and the third ratio, the target starting point of the order is determined from the trajectory points in the candidate cluster.

6. The data processing method according to claim 5, characterized in that, The determination of the target starting point of the order from the trajectory points in the candidate cluster based on the first ratio, the second ratio, and the third ratio includes: Based on the first ratio, the second ratio, the third ratio, and a preset scoring strategy, a trajectory point in the trajectory points in the candidate cluster is scored; According to the scoring result, the trajectory point with the highest score is selected from the trajectory points in the candidate cluster as the target starting point of the order.

7. A data processing method applied to a freight scene, characterized in that, It includes: Obtaining order data and corresponding driving trajectory data; Based on the order data and the driver operation data, the time and position of the trajectory points in the driving trajectory data are constrained, and a plurality of candidate trajectory points are determined from the driving trajectory data; The plurality of candidate trajectory points are clustered to obtain a plurality of clustering clusters; Based on the order data and the driver operation data, the position of the cluster center point of the plurality of clustering clusters is constrained, and a candidate cluster is determined from the plurality of clustering clusters; The constraint on the staying time of the driver at each trajectory point in the candidate cluster and the position of each trajectory point in the candidate cluster is used to determine the target terminal point of the order from the trajectory points in the candidate cluster; The constraint on the time and position of the trajectory points in the driving trajectory data based on the order data and the driver operation data to determine a plurality of candidate trajectory points from the driving trajectory data includes: According to the driver operation data, the time of each trajectory point in the driving trajectory data, and a first time constraint condition, the starting point of the order trajectory is determined. According to the order data, the driver operation data, the position of each trajectory point in the starting point section, the time of each trajectory point in the starting point section, a first distance constraint condition, and a second time constraint condition, a plurality of candidate trajectory points are determined from the starting point section.

8. A computer-readable storage medium, characterized in that, The storage medium stores a plurality of instructions, which are adapted to be loaded by a processor to execute the data processing method of any one of claims 1-7.

9. A server, characterized by A device comprises a processor and a memory, the processor and the memory being electrically connected, the memory being used to store instructions and data, and the processor being used to execute the data processing method of any one of claims 1-7.

Images