CN114943305A - Data processing method, data processing device, storage medium and server - Google Patents

Abstract

The embodiments of the present application disclose a data processing method, device, storage medium and server. The method includes: based on order data and driver operation data, constraining the time and position of track points in the driving track data, and determining multiple candidate track points from the driving track data; clustering the multiple candidate track points to obtain multiple track points. Based on the order data and driver operation data, the positions of the cluster center points of the multiple clusters are constrained, and the candidate clusters are determined from the multiple clusters; The duration of stay and the position of each trajectory point in the candidate cluster are constrained, and the target start point or target end point of the order is determined from the trajectory points in the candidate cluster. This solution uses clustering algorithms and strategies to identify the actual loading and unloading points, which can improve the accuracy of mining real location points in freight scenarios.

Description

Data processing method, device, storage medium and server

technical field

The present application relates to the technical field of electronic computers, and in particular, to a data processing method, device, storage medium and server.

Background technique

Most of the existing trajectory mining schemes are about the identification algorithm research of stop points, the research of taxi pick-up and drop-off points in the passenger transportation industry, and the research of long-distance truck loading and unloading points. The research on the identification algorithm of truck loading and unloading points in the same-city freight scene is still vacant. However, the need for the identification of loading and unloading points in the same-city freight industry is becoming more and more urgent.

For the tripartite platform, the representative transportation trajectory of intra-city freight is that the driver confirms the order on the platform, confirms the order with the customer by phone, and then goes to the starting point of the order according to the agreed time. Confirm the actual loading point by phone, then go to the actual loading point and stop for a period of time to load, then go to the end of the order, and also stay for a period of time after reaching the destination, confirm the arrival on the platform and confirm the actual unloading point with the customer by phone, then go to Actual unloading point and stop for a period of time to unload. After the unloading is completed, it will go to the starting point of the next order to prepare for the next round of transportation. It can be seen that increasing the proportion of excavation points as real loading and unloading points is of great significance to improve the efficiency of encounters.

At present, users of the tripartite platform place orders on the platform. For some orders, after the driver accepts the order, the route is planned according to the starting point when the user places the order, and before reaching the starting point, it is necessary to communicate with the user by telephone for manual navigation. The communication cost between the driver and the user's goods is high. In the analysis of driver trajectory data, it is found that firstly, the driver's trajectory comes from the driver's positioning, and about 5% of the trajectory is missing; secondly, the proportion of drivers who confirm that the loading point is the real loading point is 51%, and the driver confirms that the unloading point is the real unloading point. The third is that the proportion of users placing an order at the real loading point is 13%, and the end point of the user's order is the real loading point is 7%. It can be seen that the accuracy of the loading and unloading location information in the order information of the existing solution is poor.

SUMMARY OF THE INVENTION

Embodiments of the present application provide a data processing method, device, storage medium, and server, which can improve the accuracy of real location point mining.

In a first aspect, an embodiment of the present application provides a data processing method, which is applied in a freight shipping scenario, including:

Obtain order data and corresponding driving trajectory data;

Based on the order data and the driver's operation data, constrain the time and position of the trajectory points in the driving trajectory data, and determine a plurality of candidate trajectory points from the driving trajectory data;

Clustering multiple candidate trajectory points to obtain multiple clusters;

Based on the order data and the driver operation data, constrain the positions of the cluster center points of the plurality of clusters, and determine candidate clusters from the plurality of clusters;

Constraining the duration of the driver's stay on each trajectory point in the candidate cluster and the position of each trajectory point in the candidate cluster, and determining the target starting point of the order from the trajectory points in the candidate cluster.

In the second aspect, the embodiment of the present application provides another data processing method, which is applied in a freight transport scenario, including:

Obtain order data and corresponding driving trajectory data;

Based on the order data and the driver's operation data, constrain the time and position of the trajectory points in the driving trajectory data, and determine a plurality of candidate trajectory points from the driving trajectory data;

Clustering multiple candidate trajectory points to obtain multiple clusters;

Based on the order data and the driver operation data, constrain the positions of the cluster center points of the plurality of clusters, and determine candidate clusters from the plurality of clusters;

Constraining the duration of the driver's stay on each track point in the candidate cluster and the position of each track point in the candidate cluster, and determining the target end point of the order from the track points in the candidate cluster.

In a third aspect, the embodiments of the present application provide another data processing device, which is applied in a freight transport scenario, including:

a first acquiring unit, used for acquiring order data and corresponding driving track data;

a first determining unit, configured to constrain the time and position of the trajectory points in the driving trajectory data based on the order data and driver operation data, and determine a plurality of candidate trajectory points from the driving trajectory data;

The first clustering unit is used for clustering multiple candidate trajectory points to obtain multiple cluster clusters;

a second determining unit, configured to constrain the positions of the cluster center points of the multiple clusters based on the order data and the driver operation data, and determine candidate clusters from the multiple clusters;

The third determining unit is configured to constrain the length of stay of the driver on each track point in the candidate cluster and the position of each track point in the candidate cluster, and determine the order from the track points in the candidate cluster target starting point.

In a fourth aspect, the embodiments of the present application provide another data processing device, which is applied in a freight transport scenario, including:

a second acquiring unit, configured to acquire order data and corresponding driving track data;

a fourth determining unit, configured to constrain the time and position of the trajectory points in the driving trajectory data based on the order data and the driver operation data, and determine a plurality of candidate trajectory points from the driving trajectory data;

The second clustering unit is used for clustering multiple candidate trajectory points to obtain multiple cluster clusters;

a fifth determining unit, configured to constrain the positions of the cluster center points of the multiple clusters based on the order data and the driver operation data, and determine candidate clusters from the multiple clusters;

The sixth determination unit is used to constrain the length of stay of the driver on each trajectory point in the candidate cluster and the position of each trajectory point in the candidate cluster, and determine the order from the trajectory points in the candidate cluster target end point.

In a fifth aspect, an embodiment of the present application further provides a computer-readable storage medium, where a plurality of instructions are stored in the storage medium, and the instructions are suitable for being loaded by a processor to execute the foregoing data processing method.

In a sixth aspect, an embodiment of the present application further provides a server, including a processor and a memory, 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 data Approach.

In this embodiment of the present application, based on the order data and driver operation data, the time and position of the trajectory points in the driving trajectory data are constrained, and multiple candidate trajectory points are determined from the driving trajectory data; the multiple candidate trajectory points are clustered to obtain Multiple clusters; based on order data and driver operation data, the positions of the cluster center points of multiple clusters are constrained, and candidate clusters are determined from multiple clusters; The duration of stay on the candidate cluster and the position of each trajectory point in the candidate cluster are constrained, and the target start point or target end point of the order is determined from the trajectory points in the candidate cluster. This solution uses clustering algorithms and strategies to identify the actual loading and unloading points, which can improve the accuracy of mining real location points in freight scenarios.

Description of drawings

In order to illustrate the technical solutions in the embodiments of the present application more clearly, the following briefly introduces the drawings that are used in the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those skilled in the art, other drawings can also be obtained from these drawings without creative effort.

FIG. 1 is a schematic flowchart of a data processing method provided by an embodiment of the present application.

FIG. 2 is a schematic structural diagram of a loading and unloading point excavation system provided by an embodiment of the present application.

FIG. 3 is another schematic flowchart of a data processing method provided by an embodiment of the present application.

FIG. 4 is a schematic structural diagram of a data processing apparatus provided by an embodiment of the present application.

FIG. 5 is a schematic structural diagram of a data processing apparatus provided by an embodiment of the present application.

FIG. 6 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.

FIG. 7 is another schematic structural diagram of an electronic device provided by an embodiment of the present application.

Detailed ways

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the protection scope of the present application.

At present, the identification of loading and unloading points in the freight scene of the industry is basically based on the monitoring data of trucks to analyze changes in vehicle speed, load, and vehicle direction, so as to identify the loading and unloading points, and then identify the specific behavior of drivers, push delivery information for drivers, and realize intelligent delivery. . However, in the scenario where the tripartite freight platform issues orders for intra-city freight services, the data that can generally be obtained include driver positioning information, driver operation information, and other order information. Among them, the proportion of the loading point confirmed by the driver's operation is 51%, while this proportion is only 49% at the unloading point, the proportion of the user's order starting point is the real loading point is 13%, and the user's order ending point is 13%. The ratio for the real loading point is 7%. Therefore, new methods are needed to mine real loading and unloading points based on available data. At the same time, the higher the proportion of digging points that are real loading and unloading points, the higher the proportion of recommending accurate loading and unloading points to users. Experience matters.

In order to improve the efficiency of driver-cargo encounters, reduce the cost of encounters, and allow more drivers and users to choose and store them on the platform, a method of mining actual loading and unloading points is needed, and then a database of actual loading and unloading points is generated to provide users with loading and unloading point recommendations. Serve. Based on this, the embodiments of the present application provide a data processing method, device, storage medium, and server, which can identify and mine real loading and unloading points in combination with user order data, driver operation data, and driving trajectory data, which can improve the process of receiving freight orders. Fixed point rate.

In one embodiment, a data processing method is provided in an application server. Referring to Figure 1, the specific flow of the data processing method may be as follows:

101. Acquire order data and corresponding driving track data.

This solution is used in freight scenarios. Specifically, order data refers to the data related to the freight demand initiated by the user through the freight APP, applet or web page installed in the electronic device, such as basic user information (such as name, contact information), basic freight information (such as freight origin, freight destination) , delivery time, cargo details, etc.).

102. Based on the order data and the driver operation data, constrain the time and position of the trajectory points in the driving trajectory data, and determine a plurality of candidate trajectory points from the driving trajectory data. The driving trajectory data refers to the actual driving route data and driving time data during the freight process.

In one embodiment, based on the order data and the driver's operation data, the time and position of the trajectory points in the driving trajectory data are constrained, and when multiple candidate trajectory points are determined from the driving trajectory data, the following procedures may be specifically included:

Determine the starting point section of the order track according to the driver's operation data, the time of each track point in the driving track data, and the first time constraint;

According to the order data, the driver's operation data, the position of each trajectory point in the starting point road segment, the time of each trajectory point in the starting point road segment, the first distance constraint condition and the second time constraint condition, a plurality of candidates are determined from the starting point road segment track point.

In one embodiment, the driver operation data includes: the time when the driver confirms the receipt of the order and the time when the driver confirms the arrival at the starting point. When determining the starting point section of the order track based on the driver's operation data, the time of each track point in the track data, and the first time constraint, you can specifically select the time corresponding to the time of the driver's confirmation of receiving the order based on the time of each track point in the track data. The track point and the track point within the specified time period determined by the driver before reaching the starting point are used as the starting point section of the order track.

In one embodiment, the order data includes: the starting point of the order, and the driver operation data includes: the time when the driver confirms the receipt of the order, the time when the driver confirms the arrival at the starting point, and the driver confirms the loading point. Determine a plurality of candidate trajectories from the starting point road segment according to the order data, the driver operation data, the position of each trajectory point in the starting point road segment, the time of each trajectory point in the starting point road segment, the first distance constraint condition and the second time constraint condition When clicking, it can specifically include the following processes:

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 driver's confirmed loading point, screen out the trajectory points that satisfy the first distance constraint from the starting point road segment;

Based on the time difference between the time of the selected trajectory points and the time when the driver confirms the loading, and the time difference between the time of the selected trajectory points and the time when the driver confirms the arrival at the starting point, it is determined from the selected trajectory points that the time difference satisfies the second The trajectory points of the time constraints are used as candidate trajectory points.

103. Cluster the multiple candidate trajectory points to obtain multiple clusters.

Specifically, the density-based clustering method DBSCAN can be used to cluster the loading and unloading candidate trajectory points respectively, the minimum sample size n is 2, and the ε-neighborhood radius eps is 0.00009.

104. Based on the order data and the driver operation data, constrain the positions of the cluster center points of the multiple clusters, and determine a candidate cluster from the multiple clusters.

In one embodiment, the order data may include: the origin of the order, and the driver operation data may include: the driver confirms the loading completion point. When constraining the positions of the cluster center points of the multiple clusters based on the order data and the driver operation data, and determining candidate clusters from the multiple clusters, the following processes may be specifically included:

Obtain the first distance between the cluster center point and the starting point of the order, and the second distance between the cluster center point and the point where the driver confirms the completion of loading;

Sorting the plurality of clusters according to the first distance and the second distance, respectively, to obtain the first sorting result and the second sorting result;

According to the first sorting result and the second sorting result, respectively, filter out the clusters that satisfy the first sorting constraint from the plurality of clusters;

The filtered cluster and the cluster where the driver confirms the loading completion point are used as candidate clusters.

105. Constrain the length of stay of the driver on each trajectory point in the candidate cluster and the position of each trajectory point in the candidate cluster, and determine the target starting point of the order from the trajectory points in the candidate cluster.

In one embodiment, when the target starting point of the order is determined from the trajectory points in the candidate cluster, the third distance between each trajectory point in the candidate cluster and the order starting point, the trajectory points in the candidate cluster and the driver can be obtained respectively. Confirm the fourth distance of the loading point, the fifth distance between each trajectory point in the candidate cluster and the driver's confirmed loading completion point; obtain the first ratio of the dwell time to the third distance, and the second ratio of the dwell time to the fourth distance The third ratio of the ratio, the dwell time and the fifth distance. Finally, based on the first ratio, the second ratio and the third ratio, the target origin of the order is determined from the trajectory points within the candidate cluster.

In one embodiment, when determining 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, firstly, based on the first ratio, the second ratio, the all The third ratio and the preset scoring strategy are used to score the track points in the track points in the candidate cluster. Then, according to the scoring result, the trajectory point with the highest score is selected from the trajectory points in the candidate cluster, which is indeed the target starting point of the order.

Similarly, in an embodiment, for the mining and identification of the target end point of the trajectory order, the above-mentioned logic strategy may be referred to. That is, another data processing method is also provided, which can be specifically as follows:

Obtain order data and corresponding driving trajectory data;

Based on the order data and driver operation data, the time and position of the trajectory points in the driving trajectory data are constrained, and multiple candidate trajectory points are determined from the driving trajectory data;

Clustering multiple candidate trajectory points to obtain multiple clusters;

Based on order data and driver operation data, the positions of the cluster center points of multiple clusters are constrained, and candidate clusters are determined from multiple clusters;

Constrain the duration of the driver's stay on each trajectory point in the candidate cluster and the position of each trajectory point in the candidate cluster, and determine the target destination of the order from the trajectory points in the candidate cluster.

Specifically, when mining the target destination, the order data may include: basic user information (such as name, contact information), and basic freight information (such as origin, destination, time, details, etc.). The user operation data may include: the time when the driver confirms the arrival at the end point, the time when the driver confirms the order, the unloading point information confirmed by the driver, and the unloading completion point information confirmed by the driver.

It can be seen from the above that the data processing method provided in this embodiment, based on the order data and driver operation data, constrains the time and position of the trajectory points in the driving trajectory data, and determines a plurality of candidate trajectory points from the driving trajectory data; The candidate trajectory points are clustered to obtain multiple clusters; based on the order data and driver operation data, the positions of the cluster center points of the multiple clusters are constrained, and the candidate clusters are determined from the multiple clusters; The duration of the driver's stay on each trajectory point in the candidate cluster and the position of each trajectory point in the candidate cluster are constrained, and the target start point or target end point of the order is determined from the trajectory points in the candidate cluster. This solution uses clustering algorithms and strategies to identify the actual loading and unloading points, which can improve the accuracy of mining real location points in freight scenarios.

In yet another embodiment of the present application, an actual loading and unloading point excavation system is also provided. Referring to FIG. 2, the system architecture may include: electronic equipment, communication equipment, and server equipment. The communication device service is used to connect the server and the terminal device, and provide a data interaction link; the communication device can be realized by but not limited to the following devices: wireless network (WiFi/4G/5G), wired network, satellite communication, etc.

Specifically, the user can use the electronic device to complete the interactive operation of data sending and receiving through the communication device and the server. Software programs can be run on servers and electronic devices to realize tasks such as data transmission, data reception, data processing, data display, model construction, and model prediction.

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 devices. A freight APP can be installed in the electronic device. Users can place orders through the APP to form a freight order. The driver can accept the freight order through the APP installed in the electronic device, and arrive at the freight starting point to perform the freight operation according to the order information. In this embodiment, a server generally refers to a server facility, which may be a single independent server or a server cluster, and model construction and deployment may be implemented by running a corresponding program in the server.

The server provides basic service capabilities through system software and application software. On this basis, the server provides the mining capabilities of the actual loading and unloading points of freight. In this solution, referring to Figure 3, the server can implement the following functions:

Step 1. Data cleaning and processing

(11) Segmentation of trajectory data: Take the later time of the driver's confirmation of receiving the order and 20 minutes before the driver's confirmation of arriving at the starting point as the starting point of the order trajectory, and take the time 20 minutes after the driver's confirmation of the order and 20 minutes after the driver's confirmation that the unloading is completed. The earlier time is used as the end point of the order track, and then the order data is associated with the track data through the driver ID and time.

Specifically, the driver trajectory data is stored by time, the trajectory data di={driver_id, loactioni, ti}, i=1, 2, ..., m, where driver_id is the driver code, loactioni={loni, lati}, loni is a certain time ti (for example, "2021-12-1713:13:13") is the longitude of the location, and lati is the latitude of the location of ti at a certain time; order data 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 code, o_order_t, o_order_loaction are the time and location of the user's order starting point, o_arrived_t, o_loading_t, o_loading_location, o_loaded_t, o_loaded_location are the confirmation of the driver, respectively Arrival time, loading start time and location, loading completion time and location, d_order_t, d_order_loaction are the time and location of the end point of the user's order, respectively, d_arrived_t, d_unloading_t, d_unloading_location, d_complete_t, d_complete_location are the arrival time confirmed by the driver, Unloading start time and location, order completion time and location. The starting point of the order track is the time when the driver confirms the order receipt and the later time (such as 20 minutes) before the driver confirms the arrival at the starting point. The earlier time (eg 20min) is used as the end point of the order track, and then the order data and track data are associated with the driver ID and time.

(12) Due to the problem of GPS positioning accuracy and signal strength, the trajectory points in some drivers' trajectories drift. Since there is a certain time interval in the trajectory collection data, it can be judged by calculating whether the ratio of the distance between the trajectory points and the distance between the front and rear trajectory points and the straight line distance between the front and rear trajectory points is reasonable. If it exceeds the set ratio, the trajectory data will drift, and it will be regarded as noise data to be eliminated.

(13) The operation position and time of the user and the driver recorded in the order data, excluding the data whose operation time does not match the operation order. For example, the driver confirms that the arrival time at the starting point is later than the confirmed loading start time, which is not in line with the operation sequence logic.

(14) Track loading and unloading classification: filter within a certain distance (such as 500m) from the starting point of the user’s order or the loading point confirmed by the driver, and the time of the track point is different from the loading time and arrival time confirmed by the driver by a specified period of time (such as 10min). ), marked as candidate trajectory points for loading points. In the same way, the screening is within a certain distance (such as 500m) from the end point of the user's order or the unloading point confirmed by the driver, and the track point time is within the specified time period (such as 10min) from the unloading time confirmed by the driver and the arrival time at the end point, and it is marked as the unloading point. candidate trajectory points.

Step 2: Identify the loading and unloading points

(21) Use the density-based clustering method DBSCAN to cluster the candidate trajectory points of loading and unloading respectively. 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, and enters the subsequent scoring stage. .

(22) Since there are some trajectories where drivers find their way, the trajectory points are repeated after a long interval. If the time difference between points in the cluster is used to calculate the dwell time, there is an error. Therefore, assuming that the trajectory collection interval is n seconds, the calculation method of the dwell time can be set as the number of point clusters multiplied by n seconds.

(23) Select the first three points with the closest distance between the cluster center point and the driver's confirmed loading completion point, the closest point between the cluster center point and the user's order starting point, and the driver's confirmed loading completion point as the actual loading point. Candidate points; similarly, the selection of candidate points for the actual unloading point is completed.

(24) Through max{the length of stay at the candidate point/(the distance between the candidate point and the starting point of the user's order), the length of stay at the candidate point/(the distance between the candidate point and the starting point for the driver to confirm the loading), the length of stay at the candidate point/ (The distance between the point and the point where the driver confirms the completion of loading)}, score each candidate point, and take the point with the highest score as the excavation point of the loading point. In the same way, the judgment of the unloading point can be completed, that is, max{the length of stay at the candidate point/(the distance between the candidate point and the end point of the user's order), the length of the stay at the candidate point/(the distance between the candidate point and the driver's confirmed unloading start point), the candidate Point stay time/(distance between the point and the point where the driver confirms the unloading completion)}, score each candidate point according to the same strategy, and take the point with the highest score as the excavation point of the unloading point.

Step three, effect evaluation

(31) Calculate the distance between the manually marked loading and unloading point and the loading and unloading point output by the above mining algorithm.

(32) Calculate the fixed point rate of each distance. Among them, the fixed point rate of the loading place is the ratio of the number of points within a certain distance (such as 30m) between the excavation point of the loading place and the manually marked point of the loading place to the number of all marked points; the fixed point rate of the unloading place is the excavation point of the unloading place. The ratio of the number of points within a certain distance (such as 30m) from the manually marked points of the unloading place to the total number of marked points.

It can be seen that this scheme combines user order data, driving trajectory data and driver operation data to identify and mine the real loading point and unloading point, which can improve the fixed point rate in the process of receiving freight orders.

In yet another embodiment of the present application, a data processing apparatus is also provided. The data processing device can be integrated in the server in the form of software or hardware. As shown in FIG. 4, the data processing apparatus 200 may include: a first obtaining unit 201, a first determining unit 202, a first clustering unit 203, a second determining unit 204, and a third determining unit 205, wherein:

The first obtaining unit 201 is used to obtain order data and corresponding driving track data;

The first determining unit 202 is configured to constrain the time and position of the trajectory points in the driving trajectory data based on the order data and the driver operation data, and determine a plurality of candidate trajectory points from the driving trajectory data;

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

The second determining unit 204 is configured to constrain the positions of the cluster center points of the multiple clusters based on the order data and the driver operation data, and determine candidate clusters from the multiple clusters;

The third determining unit 205 is configured to constrain the length of stay of the driver on each trajectory point in the candidate cluster and the position of each trajectory point in the candidate cluster, and determine the driver from the trajectory points in the candidate cluster. The target starting point for the order.

In one embodiment, the first determining unit 202 is used for:

According to the driver operation data, the time of each trajectory point in the driving trajectory data, and the first time constraint, determine the starting point section of the order trajectory;

According to the order data, the driver operation data, the position of each track point in the starting point road segment, the time of each track point in the starting point road segment, the first distance constraint condition and the second time constraint condition, from the starting point A plurality of candidate trajectory points are determined in the road segment.

In one embodiment, the driver operation data includes: the time when the driver confirms the receipt of the order and the time when the driver confirms the arrival at the starting point; the time according to the driver operation data, the time of each trajectory point in the driving trajectory data, and the first time constraint condition, when determining the starting point segment of the order track, the first determining unit 202 is specifically used for:

Based on the time of each track point in the driving track data, the track point corresponding to the time when the driver confirms the order receipt and the track point within the specified time period before the driver determines to arrive at the starting point are selected as the starting point section of the order track.

In one embodiment, the order data includes: the starting point of the order, and the driver operation data includes: the driver confirms the order receiving time, the driver confirms the arrival time at the starting point, and the driver confirms the loading point; Operation data, the position of each trajectory point in the starting point road segment, the time of each trajectory point in the starting point road segment, the first distance constraint condition and the second time constraint condition, when multiple candidate trajectory points are determined from the starting point road segment , the first determining unit 202 is specifically used for:

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, filter out the road segments that satisfy the first requirement from the starting point. The trajectory point of the distance constraint;

Based on the time difference between the time of the selected trajectory points and the time when the driver confirms the loading, and the time difference between the time of the selected trajectory points and the time when the driver confirms the arrival at the starting point, it is determined from the selected trajectory points that the time difference satisfies the second The trajectory points of the time constraints are used as the candidate trajectory points.

In one embodiment, the order data includes: the starting point of the order, and the driver operation data includes: the driver confirms the loading completion point; the second determining unit 204 is used for:

Obtain the first distance between the cluster center point and the starting point of the order, and the second distance between the cluster center point and the point where the driver confirms the completion of loading;

Sorting the plurality of clusters according to the first distance and the second distance, respectively, to obtain a first sorting result and a second sorting result;

According to the first sorting result and the second sorting result, respectively, filter out the clusters that satisfy the first sorting constraint from the plurality of clusters;

The selected cluster and the cluster where the driver confirms the unloading completion point are used as candidate clusters.

In one embodiment, the third determining unit 205 is used for:

Obtain the third distance between each trajectory point in the candidate cluster and the starting point of the order, the fourth distance between each trajectory point in the candidate cluster and the driver's confirmed loading point, and each trajectory point in the candidate cluster and the driver's confirmed loading point. The fifth distance of the completion point;

obtaining a first ratio of the stay duration to the third distance, a second ratio of the stay duration to the fourth distance, and a third ratio of the stay duration to the fifth distance;

Based on the first ratio, the second ratio, and the third ratio, a target origin of the order is determined from trajectory points within the candidate cluster.

In one embodiment, when determining 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, the third determining unit 205 Further use for:

based on the first ratio, the second ratio, the third ratio and a preset scoring strategy, scoring the track points in the track points in the candidate cluster;

According to the scoring result, the trajectory point with the highest score is selected from the trajectory points in the candidate cluster, which is indeed the target starting point of the order.

As can be seen from the above, the data processing device provided by the embodiment of the present application, based on the order data and the driver operation data, constrains the time and position of the trajectory points in the driving trajectory data, and determines a plurality of candidate trajectory points from the driving trajectory data; Cluster the candidate trajectory points to obtain multiple clusters; based on the order data and driver operation data, constrain the positions of the cluster center points of the multiple clusters, and determine the candidate clusters from the multiple clusters; Constrain the duration of the driver's stay on each trajectory point in the candidate cluster and the position of each trajectory point in the candidate cluster, and determine the target starting point of the order from the trajectory points in the candidate cluster. This scheme uses clustering algorithms and strategies to identify actual loading points, which can improve the accuracy of real location mining in freight scenarios.

In yet another embodiment of the present application, a data processing apparatus is also provided. The data processing device can be integrated in the server in the form of software or hardware. As shown in FIG. 5 , the data processing apparatus 300 may include: a second obtaining unit 301, a fourth determining unit 302, a second clustering unit 303, a fifth determining unit 304 and a sixth determining unit 305, wherein:

The first obtaining unit 301 is used to obtain order data and corresponding driving track data;

The fourth determination unit 302 is configured to constrain the time and position of the trajectory points in the driving trajectory data based on the order data and the driver operation data, and determine a plurality of candidate trajectory points from the driving trajectory data;

The second clustering unit 303 is configured to perform clustering on a plurality of candidate trajectory points to obtain a plurality of clusters;

a fifth determining unit 304, configured to constrain the positions of the cluster center points of the multiple clusters based on the order data and the driver operation data, and determine candidate clusters from the multiple clusters;

The sixth determination unit 305 is configured to constrain the length of stay of the driver on each track point in the candidate cluster and the position of each track point in the candidate cluster, and determine the track point from the candidate cluster. The target starting point for the order.

In one embodiment, the fourth determining unit 302 is used for:

According to the driver operation data, the time of each trajectory point in the driving trajectory data, and the first time constraint, determine the end road section of the order trajectory;

According to the order data, the driver's operation data, the position of each track point in the end road segment, the time of each track point in the end road segment, the first distance constraint condition and the second time constraint condition, from the end point A plurality of candidate trajectory points are determined in the road segment.

In one embodiment, the driver operation data includes: the time when the driver confirms the single and the time when the driver confirms the arrival at the end point; the time according to the driver operation data, the time of each trajectory point in the driving trajectory data, and the first time constraint condition, when determining the end road segment of the order track, the fourth determining unit 302 is specifically used for:

Based on the time of each track point in the driving track data, the track point corresponding to the driver's confirmation of the single time and the track point within the specified time period before the driver's determination to reach the end point are selected as the end road section of the order track.

In one embodiment, the order data includes: the order end point, and the driver operation data includes: the time when the driver confirms the order, the time when the driver confirms the arrival at the end point, and the driver confirms the unloading point; data, the position of each trajectory point in the end road segment, the time of each trajectory point in the end road segment, the first distance constraint and the second time constraint, when multiple candidate trajectory points are determined from the end road segment, The fourth determining unit 302 is specifically configured to:

Based on the distance between each trajectory point in the driving trajectory data and the end point of the order, or the distance between each trajectory point in the driving trajectory data and the driver's confirmed unloading point, filter out the road segments that satisfy the first distance from the end point. Constraint trajectory points;

Based on the time difference between the time of the selected trajectory point and the time when the driver confirms the unloading, and the time difference between the time of the selected trajectory point and the time when the driver confirms the arrival at the end point, it is determined from the selected trajectory points that the time difference satisfies the second time The trajectory points of the constraints are used as the candidate trajectory points.

In one embodiment, the order data includes: the end point of the order, and the driver operation data includes: the driver confirms the unloading completion point; the fifth determining unit 304 is used for:

Obtain the first distance between the cluster center point and the order end point, and the second distance between the cluster center point and the point where the driver confirms the unloading completion;

Sorting the plurality of clusters according to the first distance and the second distance, respectively, to obtain a first sorting result and a second sorting result;

According to the first sorting result and the second sorting result, respectively, filter out the clusters that satisfy the first sorting constraint from the plurality of clusters;

The selected cluster and the cluster where the driver confirms the unloading completion point are used as candidate clusters.

In one embodiment, the sixth determining unit 305 is used for:

Obtain the third distance between each trajectory point in the candidate cluster and the order end point, the fourth distance between each trajectory point in the candidate cluster and the driver's confirmed unloading point, and each trajectory point in the candidate cluster and the driver's confirmed unloading completion point. the fifth distance;

obtaining a first ratio of the stay duration to the third distance, a second ratio of the stay duration to the fourth distance, and a third ratio of the stay duration to the fifth distance;

Based on the first ratio, the second ratio, and the third ratio, a target end point of the order is determined from trajectory points within the candidate cluster.

In one embodiment, when determining the target end point of the order from the trajectory points in the candidate cluster based on the first ratio, the second ratio and the third ratio, the sixth determining unit 305 Further use for:

based on the first ratio, the second ratio, the third ratio and a preset scoring strategy, scoring the track points in the track points in the candidate cluster;

According to the scoring result, the trajectory point with the highest score is selected from the trajectory points in the candidate cluster, which is indeed the target end point of the order.

As can be seen from the above, the data processing device provided by the embodiment of the present application, based on the order data and the driver operation data, constrains the time and position of the trajectory points in the driving trajectory data, and determines a plurality of candidate trajectory points from the driving trajectory data; Cluster the candidate trajectory points to obtain multiple clusters; based on the order data and driver operation data, constrain the positions of the cluster center points of the multiple clusters, and determine the candidate clusters from the multiple clusters; Constrain the duration of the driver's stay on each trajectory point in the candidate cluster and the position of each trajectory point in the candidate cluster, and determine the target destination of the order from the trajectory points in the candidate cluster. This scheme uses clustering algorithms and strategies to identify actual unloading points, which can improve the accuracy of real location point mining in freight scenarios.

In yet another embodiment of the present application, a server is also provided. As shown in FIG. 6 , the server 400 includes a processor 401 and a memory 402 . The processor 401 is electrically connected to the memory 402 .

The processor 401 is the control center of the server 400, and uses various interfaces and lines to connect various parts of the entire server, and executes various functions of the server by running or loading the applications stored in the memory 402 and calling the data stored in the memory 402. function and process data for overall monitoring of the server.

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 executes the instructions stored in the memory 402. application to achieve various functions:

Obtain order data and corresponding driving trajectory data;

Based on the order data and the driver's operation data, constrain the time and position of the trajectory points in the driving trajectory data, and determine a plurality of candidate trajectory points from the driving trajectory data;

Clustering multiple candidate trajectory points to obtain multiple clusters;

Based on the order data and the driver operation data, constrain the positions of the cluster center points of the plurality of clusters, and determine candidate clusters from the plurality of clusters;

Constraining the duration of the driver's stay on each trajectory point in the candidate cluster and the position of each trajectory point in the candidate cluster, and determining the target starting point of the order from the trajectory points in the candidate cluster.

In one embodiment, when the time and position of the trajectory points in the driving trajectory data are constrained based on the order data and driver operation data, and a plurality of candidate trajectory points are determined from the driving trajectory data, the processor 401 may: Do the following:

According to the driver operation data, the time of each trajectory point in the driving trajectory data, and the first time constraint, determine the starting point section of the order trajectory;

According to the order data, the driver operation data, the position of each track point in the starting point road segment, the time of each track point in the starting point road segment, the first distance constraint condition and the second time constraint condition, from the starting point A plurality of candidate trajectory points are determined in the road segment.

In one embodiment, the driver operation data includes: the time when the driver confirms the receipt of the order and the time when the driver confirms the arrival at the starting point; the time according to the driver operation data, the time of each trajectory point in the driving trajectory data, and the first time constraint Conditions, when determining the starting point segment of the order track, the processor 401 may perform the following operations:

Based on the time of each track point in the driving track data, the track point corresponding to the time when the driver confirms the order receipt and the track point within the specified time period before the driver determines to arrive at the starting point are selected as the starting point section of the order track.

In one embodiment, the order data includes: the starting point of the order, and the driver operation data includes: the driver confirms the order receiving time, the driver confirms the arrival time at the starting point, and the driver confirms the unloading point; data, the position of each trajectory point in the starting point road segment, the time of each trajectory point in the starting point road segment, the first distance constraint condition and the second time constraint condition, when multiple candidate trajectory points are determined from the starting point road segment, The processor 401 can perform the following operations:

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 driver's confirmed unloading point, the first distance is selected from the starting point road segment Constraint trajectory points;

Based on the time difference between the time of the selected trajectory point and the time when the driver confirms the unloading, and the time difference between the time of the selected trajectory point and the time when the driver confirms the arrival at the starting point, it is determined from the selected trajectory points that the time difference satisfies the second time The trajectory points of the constraints are used as the candidate trajectory points.

In one embodiment, the order data includes: an order starting point, and the driver operation data includes: the driver confirms the unloading completion point; The position of the cluster center point is constrained, and when a candidate cluster is determined from multiple clusters, the processor 401 may perform the following operations:

Obtain the first distance between the cluster center point and the starting point of the order, and the second distance between the cluster center point and the point where the driver confirms the completion of loading;

Sorting the plurality of clusters according to the first distance and the second distance, respectively, to obtain a first sorting result and a second sorting result;

According to the first sorting result and the second sorting result, respectively, filter out the clusters that satisfy the first sorting constraint from the plurality of clusters;

The filtered cluster and the cluster where the driver confirms the loading completion point are used as candidate clusters.

In one embodiment, when the time and position of the trajectory points in the driving trajectory data are constrained based on the order data and driver operation data, and multiple candidate trajectory points are determined from the driving trajectory data, the processor 401 specifically: You can do the following:

According to the driver operation data, the time of each trajectory point in the driving trajectory data, and the first time constraint, determine the starting point section of the order trajectory;

According to the order data, the driver operation data, the position of each track point in the starting point road segment, the time of each track point in the starting point road segment, the first distance constraint condition and the second time constraint condition, from the starting point A plurality of candidate trajectory points are determined in the road segment.

In one embodiment, the driver's operation data includes: the time when the driver confirms the receipt of the order and the time when the driver confirms the arrival at the starting point; according to the driver's operation data, the time of each trajectory point in the driving trajectory data, and the first time constraint, When determining the starting point segment of the order track, the processor 401 may specifically perform the following operations:

Based on the time of each track point in the driving track data, the track point corresponding to the time when the driver confirms the order receipt and the track point within the specified time period before the driver determines to arrive at the starting point are selected as the starting point section of the order track.

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 executes the instructions stored in the memory 402 applications in , so as to achieve various functions:

Obtain order data and corresponding driving trajectory data;

Based on the order data and the driver's operation data, constrain the time and position of the trajectory points in the driving trajectory data, and determine a plurality of candidate trajectory points from the driving trajectory data;

Clustering multiple candidate trajectory points to obtain multiple clusters;

Based on the order data and the driver operation data, constrain the positions of the cluster center points of the plurality of clusters, and determine candidate clusters from the plurality of clusters;

Constraining the duration of the driver's stay on each track point in the candidate cluster and the position of each track point in the candidate cluster, and determining the target end point of the order from the track points in the candidate cluster.

Memory 402 may be used to store applications and data. The application stored in memory 402 contains instructions executable in the processor. Applications can be composed of various functional modules. The processor 401 executes various functional applications and data processing by executing applications stored in the memory 402 .

In some embodiments, as shown in FIG. 7 , the server 400 further 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 respectively.

The display screen 403 may be used to display information input by the user or information provided to the user and various graphical user interfaces of the server, which may be composed of images, text, icons, videos, and any combination thereof.

The control circuit 404 is electrically connected to the display screen 403 for controlling the display screen 403 to display information.

The radio frequency circuit 405 is used for transmitting and receiving radio frequency signals, so as to construct wireless communication with the electronic device or other servers through wireless communication, and send and receive signals with the electronic device or other servers.

Input unit 406 may be used to receive input numbers, character information, or user characteristic information (eg, fingerprints), and generate keyboard, mouse, joystick, optical, or trackball signal input related to user settings and function control. The input unit 406 may include a fingerprint identification module.

The power supply 407 is used to power various components of the server 400 . In some embodiments, the power supply 407 may be logically connected to the processor 401 through a power management system, so as to implement functions such as managing charging, discharging, and power consumption through the power management system.

Although not shown in FIG. 7 , the server 400 may further include a speaker, a Bluetooth module, a camera, and the like, which will not be repeated here.

As can be seen from the above, the server provided by the embodiment of the present application, based on the order data and driver operation data, constrains the time and position of the trajectory points in the driving trajectory data, and determines multiple candidate trajectory points from the driving trajectory data; The trajectory points are clustered to obtain multiple clusters; based on the order data and driver operation data, the positions of the cluster center points of the multiple clusters are constrained, and candidate clusters are determined from the multiple clusters; The duration of stay on each trajectory point in the candidate cluster and the position of each trajectory point in the candidate cluster are constrained, and the target start point or target end point of the order is determined from the trajectory points in the candidate cluster. This solution uses clustering algorithms and strategies to identify the actual loading and unloading points, which can improve the accuracy of mining real location points in freight scenarios.

In some embodiments, a computer-readable storage medium is also provided, the storage medium having stored therein a plurality of instructions, the instructions being adapted to be loaded by a processor to perform any of the above data processing methods.

Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing relevant hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium can include: Read Only Memory (ROM, Read Only Memory), Random Access Memory (RAM, Random Access Memory), magnetic disk or optical disk, etc.

The data processing method, device, storage medium, and server provided by the embodiments of the present application have been described in detail above. The principles and implementations of the present application are described with specific examples in this paper. The descriptions of the above embodiments are only used to help Understand the method of the present application and its core idea; at the same time, for those skilled in the art, according to the idea of the present application, there will be changes in the specific implementation and application scope. In summary, the content of this specification should not be It is construed as a limitation of this application.

Claims (10)

1. A data processing method is applied to a freight scene, and is characterized by comprising the following steps:

acquiring order data and corresponding driving track data;

constraining the time and the position of a track point in the driving track data based on order data and driver operation data, and determining a plurality of candidate track points from the driving track data;

clustering the candidate track points to obtain a plurality of clustering clusters;

based on the order data and the driver operation data, constraining the positions of cluster center points of the plurality of cluster clusters, and determining candidate clusters from the plurality of cluster clusters;

and restricting the stay time of the driver on each track point in the candidate cluster and the position of each track point in the candidate cluster, and determining the target starting point of the order from the track points in the candidate cluster.

2. The data processing method according to claim 1, wherein the determining a plurality of candidate trajectory points from the travel trajectory data by constraining the time and position of the trajectory points in the travel trajectory data based on the order data and the driver operation data comprises:

determining a starting point road section of the order track according to the driver operation data, the time of each track point in the driving track data and a first time constraint condition;

and determining a plurality of candidate track points from the starting road section according to the order data, the driver operation data, the positions of the track points in the starting road section, the time of the track points in the starting road section, a first distance constraint condition and a second time constraint condition.

3. The data processing method of claim 2, wherein the driver operation data comprises: the driver confirms the order receiving time and the driver confirms the time to reach the starting point;

determining a starting point road section of the order track according to the driver operation data, the time of each track point in the driving track data and a first time constraint condition, wherein the method comprises the following steps:

and selecting track points corresponding to the order taking confirmation time of the driver and track points in a specified time period before the driver confirms to reach the starting point as the starting point road section of the order track based on the time of each track point in the driving track data.

4. The data processing method of claim 2, wherein the order data comprises: an order starting point, the driver operational data comprising: the driver confirms the order receiving time, the driver confirms the arrival starting time and the driver confirms the loading point;

determining a plurality of candidate track points from the starting point road section according to the order data, the driver operation data, the positions of the track points in the starting point road section, the time of the track points in the starting point road section, a first distance constraint condition and a second time constraint condition, and including:

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 loading point confirmed by the driver, selecting track points meeting a first distance constraint condition from the starting point road section;

and determining the track point with the time difference meeting the second time constraint condition from the screened track point based on the time difference between the screened track point and the confirmation loading time of the driver and the time difference between the screened track point and the confirmation arrival starting point time of the driver, and taking the track point as the candidate track point.

5. The data processing method of claim 1, wherein the order data comprises: an order starting point, the driver operational data comprising: the driver confirms the loading completion point;

the constraining the positions of cluster center points of the plurality of clusters based on the order data and the driver operation data, and determining candidate clusters from the plurality of clusters, comprising:

acquiring a first distance between a cluster center point and an order starting point and a second distance between the cluster center point and a loading completion point confirmed by a driver;

sorting the plurality of clustering clusters according to the first distance and the second distance respectively to obtain a first sorting result and a second sorting result;

screening cluster clusters with the ordering meeting the first ordering constraint condition from the plurality of cluster clusters according to the first ordering result and the second ordering result respectively;

and taking the screened cluster and the cluster where the loading completion point is confirmed by the driver as candidate clusters.

6. The data processing method according to any one of claims 1 to 5, wherein the determining the target starting point of the order from the track points in the candidate cluster by constraining the stay time of the driver on the track points in the candidate cluster and the positions of the track points in the candidate cluster comprises:

respectively obtaining a third distance between each track point in the candidate cluster and an order starting point, a fourth distance between each track point in the candidate cluster and a driver cargo confirmation point, and a fifth distance between each track point in the candidate cluster and a driver cargo confirmation completion point;

acquiring a first ratio of the stay time to the third distance, a second ratio of the stay time to the fourth distance, and a third ratio of the stay time to the fifth distance;

and determining a target starting point of the order from the track points in the candidate cluster based on the first ratio, the second ratio and the third ratio.

7. The data processing method of claim 6, wherein determining the target starting point of the order from the track points in the candidate cluster based on the first ratio, the second ratio, and the third ratio comprises:

scoring the track points in the candidate clusters based on the first ratio, the second ratio, the third ratio and a preset scoring strategy;

and according to the scoring result, screening track points with the highest score from the track points in the candidate clusters, and determining the track points as the target starting points of the order.

8. A data processing method is applied to a freight scene, and is characterized by comprising the following steps:

acquiring order data and corresponding driving track data;

constraining the time and the position of a track point in the driving track data based on order data and driver operation data, and determining a plurality of candidate track points from the driving track data;

clustering the candidate track points to obtain a plurality of clustering clusters;

based on the order data and the driver operation data, the positions of cluster center points of the plurality of clusters are restrained, and candidate clusters are determined from the plurality of clusters;

and restricting the stay time of the driver on each track point in the candidate cluster and the position of each track point in the candidate cluster, and determining the target end point of the order from the track points in the candidate cluster.

9. A computer-readable storage medium having stored thereon a plurality of instructions adapted to be loaded by a processor to perform the data processing method of any of claims 1-8.

10. A server, comprising a processor and a memory, wherein the processor is electrically connected to the memory, and the memory is used for storing instructions and data; the processor is configured to perform the data processing method of any one of claims 1-8.

Images