Delivery personnel standard riding identification method and computer program product

By obtaining the riding trajectory of the delivery personnel to match the road network, identifying and correcting violations of cycling norms in real time, the coverage and accuracy of identifying and correcting violations in the existing technology are solved, and the safety of cycling and delivery are improved The safety awareness of personnel is suitable for smart traffic management.

CN119067549APending Publication Date: 2024-12-03BEIJING SANKUAI ONLINE TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411186564.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-27
Publication Date
2024-12-03

Smart Images

  • Figure CN119067549A_ABST
    Figure CN119067549A_ABST
Patent Text Reader

Abstract

The invention discloses a delivery personnel standard riding identification method. The method comprises the following steps: acquiring a riding track of a delivery personnel in a delivery platform order process; matching the riding track with a road network, and determining a current driving road of the delivery personnel; the riding behavior of the delivery personnel is judged based on the riding track of the delivery personnel and the attribute characteristics of the current driving road, so that whether the delivery personnel violate riding specifications or not is determined, and the violation of the riding specifications comprises one or more of red light running, retrograde driving and forbidden driving; and under the condition that the riding behavior violates the riding standard, prompting is carried out on the delivery personnel terminal equipment through voice and / or through the identifier in the delivery page of the platform order. According to the method, the riding track of the delivery personnel can be obtained in real time and matched with the road network, behaviors violating riding specifications are effectively recognized, and riding safety is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The embodiments of the present application relate to the field of Internet technology, and in particular to a method for identifying standardized riding of delivery personnel and a computer program product. Background Art

[0002] With the rapid development of Internet technology, online ordering and shopping have become a normal part of life, which has brought about a huge demand for delivery. In the instant delivery scenario, delivery personnel generally use two-wheeled vehicles such as electric vehicles and motorcycles to deliver goods. In the process of order delivery, delivery personnel may ignore riding safety and violate riding regulations, which may pose a safety hazard to delivery personnel and other pedestrians and vehicles. At present, the industry's main solution to violations of riding regulations is to use violation cameras installed on the road by traffic control departments and make judgments based on computer vision methods. However, this solution is limited by the number of violation cameras and the degree of local traffic informatization. Therefore, it cannot guarantee the accuracy and timeliness of the judgment, and it is difficult to promote and implement on a larger scale to cover more delivery personnel. Summary of the invention

[0003] The embodiment of the present application provides a method, device, equipment and computer-readable storage medium for identifying the standardized riding of a delivery person. The technical solution is as follows:

[0004] In a first aspect, an embodiment of the present application provides a method for identifying standardized riding of delivery personnel, the method comprising: obtaining the riding trajectory of the delivery personnel in the process of delivering platform orders; matching the riding trajectory with the road network to determine the current driving road of the delivery personnel; judging the riding behavior of the delivery personnel based on the attribute characteristics of the delivery personnel's riding trajectory and the current driving road to determine whether the delivery personnel has violated the riding regulations, wherein the violation of the riding regulations includes one or more of running a red light, driving in the wrong direction, and prohibited driving; in the case where the riding behavior violates the riding regulations, prompting the delivery personnel on the terminal device through voice and / or through the logo in the delivery page of the platform order.

[0005] In one possible implementation, the delivery personnel's riding trajectory is matched with the road network to determine the delivery personnel's current driving road, including: determining the matching relationship between the historical riding trajectory and the road based on the historical riding trajectory of multiple delivery personnel and the road information of the road network; comparing the delivery personnel's riding trajectory with the historical riding trajectory for similarity to determine the delivery personnel's current driving road.

[0006] In one possible implementation, the following method is used to determine whether the delivery personnel has run a red light: when there is an intersection on the current driving road, the time when the delivery personnel enters and exits the intersection is determined based on the delivery personnel's riding trajectory and the current driving road; the time when the delivery personnel enters and exits the intersection is compared with the traffic light time template of the intersection to determine whether the delivery personnel has run a red light.

[0007] In one possible implementation, the traffic light time template is determined in the following manner: obtaining the starting point time information of the changes in the motion states of multiple vehicles, merging the starting point time information with similar times, and obtaining several starting point time periods; performing maximum likelihood estimation on the starting point time periods to obtain the change cycle range of the traffic lights at the intersection; using the change cycle of the traffic lights at the intersection during the peak period to fill and smooth the change cycle of the traffic lights at the intersection during the off-peak period, and determining the traffic light time template for the intersection.

[0008] In one possible implementation, the following method is used to determine whether the delivery personnel is driving in the wrong direction: the riding direction is determined based on the riding trajectory of the delivery personnel, the road direction is obtained based on the current driving road, and when the riding direction is inconsistent with the road direction, a preliminary result of the reverse driving judgment is obtained; based on the historical riding trajectories of multiple delivery personnel on the current road and / or the cost value of the delivery personnel changing routes, the preliminary result of the reverse driving judgment is corrected to determine whether the delivery personnel is driving in the wrong direction.

[0009] In one possible implementation, the preliminary result of the wrong-traffic judgment is corrected according to the historical riding trajectories of multiple delivery personnel on the current road, including: for each point in the riding trajectory of the delivery personnel, obtaining the historical riding trajectory points of multiple delivery personnel at the current road point; based on the coordinates of the historical riding trajectory points, determining the coordinate stability of the point in the riding trajectory; for the coordinate stability of each point in the riding trajectory, determining a first correction confidence for the preliminary result of the wrong-traffic judgment; and correcting the preliminary result of the wrong-traffic judgment according to the first correction confidence.

[0010] In one possible implementation, the preliminary result of the reverse traffic judgment is corrected according to the cost value of the delivery personnel's route change, including: determining, for the delivery personnel's riding trajectory, a planned riding path and a first required time from the current driving road of the riding trajectory to the delivery destination of the platform order, and determining an estimated riding path and a second required time along the riding trajectory to the delivery destination of the platform order; determining the cost value of the delivery personnel's route change by comparing the similarity of the planned riding path and the estimated riding path, as well as the difference between the first required time and the second required time; determining a second correction confidence based on the cost value of the delivery personnel's route change; and correcting the preliminary result of the reverse traffic judgment according to the second correction confidence.

[0011] In one possible implementation, the following method is used to determine whether the delivery personnel is prohibited from driving: based on the current driving road of the delivery personnel, the road label of the current driving road is obtained to determine the traffic attributes; based on the traffic attributes of the current driving road, it is determined whether the delivery personnel is prohibited from driving.

[0012] In a possible implementation, the method further includes: displaying statistical results of the delivery personnel's riding behavior violating riding regulations and corresponding safety promotion content on a page of the delivery personnel's terminal device.

[0013] On the other hand, the embodiment of the present application further provides a delivery personnel standard riding identification device, the device comprising: a trajectory acquisition module: used to obtain the delivery personnel's riding trajectory in the process of delivering platform orders; a road network matching module: used to match the riding trajectory with the road network to determine the current driving road of the delivery personnel; a riding identification module: used to judge the delivery personnel's riding behavior based on the delivery personnel's riding trajectory and the attribute characteristics of the current driving road to determine whether the delivery personnel has violated the riding regulations, wherein the violation of the riding regulations includes one or more of running a red light, driving against the flow, and prohibited driving;

[0014] The prompt module is used to give a prompt through voice and / or an icon in the delivery page of the platform order on the delivery personnel's terminal device when the riding behavior violates the riding regulations.

[0015] On the other hand, an embodiment of the present application also provides a computer program or a computer program product, in which at least one computer instruction is stored, and the at least one computer instruction is loaded and executed by a processor so that the computer implements any of the above-mentioned methods for identifying standardized riding of delivery personnel.

[0016] The technical solution provided in the embodiment of the present application can effectively identify violations of riding regulations and improve riding safety by acquiring the riding trajectory of delivery personnel in real time and matching it with the road network. Use historical data to correct judgments, reduce misjudgments, and improve accuracy. At the same time, reminders and safety promotion are carried out through terminal devices to enhance the safety awareness of delivery personnel, correct violations in a timely manner, ensure the safe driving of delivery personnel, and reduce the risk of accidents. This method does not rely on fixed violation cameras, has wide applicability, and is conducive to smart transportation and urban safety management. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 It is a schematic flowchart of a method for identifying standardized riding of delivery personnel provided in an embodiment of the present application. DETAILED DESCRIPTION

[0019] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0020] A method for identifying standardized riding of delivery personnel provided in an embodiment of the present application can be implemented in the following implementation environment, which includes but is not limited to: a terminal device and a server.

[0021] The terminal device may be at least one of a smart phone, a smart watch, a wearable device, an integrated electronic module, a tablet computer, an MP3 (Moving Picture Experts Group Audio Layer III) player, an MP4 (Moving Picture Experts Group Audio Layer IV) player, and a laptop computer. The terminal device is used to obtain data such as the location information of the delivery personnel and send the data to the server.

[0022] The terminal device may generally refer to one of a plurality of terminal devices. This embodiment is only illustrated by taking the terminal device as an example. Those skilled in the art may know that the number of the terminal devices may be more or less. For example, the terminal device may be only one, or the terminal device may be more. The embodiment of this application does not limit the number and type of the terminal devices.

[0023] The server is a single server, or a server cluster consisting of multiple servers, or any one of a cloud computing platform and a virtualization center, which is not limited in the embodiments of the present application. The server is connected to the terminal device through a wired network or a wireless network. The server is used to process data and exchange information with the terminal device. Of course, the server may also have other functions, which are not limited in the embodiments of the present application.

[0024] Based on the above implementation environment, the embodiment of the present application provides a method for identifying the standardized riding of delivery personnel. Figure 1 As an example, the flowchart of a method for identifying a standardized riding of a delivery person provided in an embodiment of the present application is shown in FIG. Figure 1 The terminal device in the process can be implemented independently, or through data interaction between the terminal device and the server. Figure 1 As shown, the method comprises the following steps:

[0025] In step 100, the riding trajectory of the delivery personnel in the process of delivering the platform order is obtained.

[0026] In an exemplary embodiment of the present application, the delivery personnel carry a terminal device, such as a smart phone, in which an application is installed and running. The application can help the delivery personnel to accept platform orders, display information about the goods involved in the platform orders during the delivery process, perform other operations on the orders, and receive and display information sent by the platform. The present application embodiment does not limit this. The goods involved in the platform orders can be food, medicine, fresh food, clothing, etc., and the present application embodiment does not limit the types of delivery.

[0027] The delivery personnel's riding trajectory can be obtained by one or a combination of the following methods:

[0028] Application: The application of the terminal device collects riding trajectory data during the delivery process by requesting access to location services.

[0029] Satellite positioning network: Through the terminal equipment carried by the delivery personnel or dedicated satellite positioning equipment, their geographic location information can be tracked in real time to obtain the riding trajectory.

[0030] Mobile network: Track the mobile phone signal of the delivery personnel through the mobile network signal of the terminal device carried by the delivery personnel, so as to obtain their approximate movement trajectory.

[0031] Vehicle-mounted sensors: Sensors installed on the vehicles driven by delivery personnel, such as accelerometers and gyroscopes, can record the movement data of the vehicle and then calculate the riding trajectory.

[0032] IoT devices: If the delivery personnel’s vehicle is equipped with an IoT device, riding trajectory data can also be collected through the IoT device.

[0033] In step 200, the riding trajectory is matched with the road network to determine the current driving road of the delivery person.

[0034] In an optional implementation, the step may include:

[0035] Based on the historical riding trajectories of multiple delivery personnel and the road information of the road network, the matching relationship between the historical riding trajectories and the roads is determined. The similarity between the delivery personnel's riding trajectory and the historical riding trajectory is compared to determine the current driving road of the delivery personnel.

[0036] Among them, establishing a matching relationship between historical cycling trajectories and road networks may include:

[0037] Road network data preparation: Obtain detailed road network data from map service providers, including road geometry information and attribute information such as road type, direction, speed limit, etc.

[0038] Data feature extraction: Feature extraction of multiple historical riding trajectories and road network data during the platform order delivery process. For historical riding trajectories, extract the spatial features (such as longitude and latitude), time features (such as timestamps), and dynamic features (such as speed and acceleration) of the trajectory points, such as the spatial distribution of the trajectory points, speed, direction, and road connection relationships. For road network data, extract the geometric features (such as road width and curvature), topological features (such as connectivity and road grade), and attribute features (such as road type) of the road network.

[0039] Matching model training: Use machine learning algorithms (such as random forests, support vector machines, or neural networks) to train historical riding trajectories and road network data to establish a matching model so that the model can learn the mapping relationship between trajectory points and road network links. It should be noted that in the process of training the model in this application, it is necessary to evaluate the importance of each feature, rank the feature importance, and select features with higher importance. Based on the results of the feature selection algorithm, determine the feature subset. The determination of the feature subset needs to be determined through multiple iterations and cross-validation.

[0040] Model validation: Evaluate the accuracy of the model through cross-validation methods to ensure that the model has good generalization ability. Use an independent test set to verify the matching effect of the model and ensure the reliability of the matching relationship.

[0041] Through the above steps, a matching relationship between historical riding trajectories and road network links is established. This model can provide a reference for real-time trajectory matching, thereby improving the accuracy of determining the current driving route of the delivery personnel.

[0042] The implementation process of comparing the delivery personnel's riding trajectory with the historical riding trajectory for similarity and determining the delivery personnel's current driving route may include:

[0043] Real-time trajectory feature extraction: The riding trajectory collected in real time is segmented and features are extracted for each segment. Ensure that the real-time trajectory features match the historical trajectory features in terms of dimension and format.

[0044] Similarity calculation: The spatial similarity between the real-time trajectory and the historical trajectory is calculated using a distance metric (such as Euclidean distance, Manhattan distance) or a similarity metric (such as cosine similarity).

[0045] Matching decision: According to the temporal continuity of the segmented riding trajectory and the spatial similarity between the segmented riding trajectory and the historical trajectory, several segments of historical trajectories with similar heights are selected. Based on the road network links of these historical trajectories, the nearest neighbor algorithm, clustering or pattern recognition technology is used to determine the road network link that is most likely to correspond to the real-time riding trajectory.

[0046] Real-time update: Since the location of the delivery personnel may change, the matching results need to be updated in real time to maintain the accuracy of the current road network links.

[0047] It should be noted that the calculation process of matching the riding trajectory with the road network can be completed in the terminal device; the trajectory data can also be sent to the server through the terminal device and completed by the server; or the trajectory data can be pre-processed by the terminal device and then sent to the server and completed by the server. This application is not limited here.

[0048] This method establishes a matching relationship between historical riding trajectories and road network links. The model can provide a reference for real-time trajectory matching, thereby improving the accuracy of determining the current road traveled by the delivery personnel. In the process of comparing the similarity between the delivery personnel's riding trajectory and the historical riding trajectory and determining the current road traveled by the delivery personnel, the steps of real-time trajectory feature extraction, similarity calculation, matching decision and real-time update are comprehensively considered to ensure the accuracy and real-time nature of the matching results.

[0049] In step 300: the delivery personnel's riding behavior is judged based on the delivery personnel's riding trajectory and the attribute characteristics of the current driving road to determine whether the delivery personnel has violated the riding regulations, wherein the violation of the riding regulations includes one or more of running a red light, driving in the wrong direction, and prohibited driving.

[0050] The following describes the different ways of determining violations of riding regulations.

[0051] In an optional implementation, the following method can be used to determine whether the delivery person has run a red light:

[0052] When there is an intersection on the current road, the time when the delivery person enters and exits the intersection is determined based on the delivery person's riding trajectory and the current road. The time when the delivery person enters and exits the intersection is compared with the traffic light time template of the intersection to determine whether the delivery person has run a red light.

[0053] Specifically, firstly, based on the road network links and road attributes of the current road traveled by the delivery personnel, it is determined whether there is an intersection on the current road traveled, such as a crossroads, a turning intersection, etc.

[0054] Then analyze the riding trajectory data to determine whether the delivery person has entered the intersection: Use the road network data to identify the center line of the road that intersects the riding trajectory. If it is determined that the center line intersects with the riding trajectory point or is about to intersect, it is determined that there may be a delivery person entering the intersection. If the riding trajectory intersects the intersection, it is determined that the delivery person has entered the intersection.

[0055] Calculate the time it takes for the delivery person to enter and exit the intersection. Retrieve the traffic light information for the intersection, including the traffic light time template. Compare the time it takes for the delivery person to enter and exit the intersection with the traffic light time template.

[0056] Determine red light running: If the delivery personnel enters or exits the intersection during a red light, it is considered to be a red light running. If the delivery personnel enters or exits the intersection during a green light, it is considered to be complying with traffic regulations.

[0057] The signal light time template refers to the timestamp of the switching point from red to green at the road intersection within a certain period, which is calculated based on the change in the vehicle's motion state. The signal light time template can be determined in the following ways:

[0058] First, the starting point time information of the motion state changes of multiple vehicles is obtained, and the starting point time information with similar time is merged to obtain several starting point time periods.

[0059] The vehicle can be a motor vehicle, a two-wheeled vehicle such as a motorcycle or electric vehicle, a delivery person's vehicle, or a combination of the above vehicle types. First, data collection is performed to collect the motion state change data of multiple vehicles in different time periods, including the starting point time information and timestamp of the vehicle passing through the intersection, where the starting point time information refers to the time when the vehicle goes from stationary to moving. Then, data preprocessing is performed. Cleaning and preprocessing data can include removing outliers, filling in missing data, etc. to ensure data quality and consistency. The data is standardized for subsequent analysis.

[0060] Since the reaction time of vehicle drivers to traffic lights varies from person to person and is affected by various factors such as road conditions and the vehicle's own reasons, it is not accurate enough to use only one time point to characterize the starting point. The present application merges the starting point time information of similar time periods to obtain several starting point time periods, thereby narrowing the range of the starting point time. For example, the starting point time of the vehicle is processed to obtain the time interval [15:55:29, 15:55:34] and the time interval [15:55:22, 15:55:32]. The intersection of the two intervals is [15:55:29, 15:55:32]. The actual starting point time interval can be shortened to 3 seconds, thereby obtaining a more accurate vehicle starting point. It should be understood that the above-mentioned interval merging is only an example, and the actual situation will be more complicated.

[0061] The maximum likelihood estimation is performed on the start-point time period to obtain the change cycle range of the intersection signal light. For mining and calculation of the change cycle range, the following methods can be used: the start-point time period is represented by a start time point, and the center point, minimum or maximum value, geometric center of the time interval, etc. of the start-point time period can be taken, and then the difference between the time stamps of the adjacent start time points of the vehicle passing through the intersection is calculated.

[0062] Set the change period of the traffic light to T, and the range of T is between 30 seconds and 360 seconds. Enumerate the values ​​of T, use the normal distribution assumption, and use the maximum likelihood estimation based on the difference sequence to find the minimum T, which is the change period of the traffic light.

[0063] Then, the change cycle of the traffic lights at the intersection during the peak period is used to fill and smooth the change cycle of the traffic lights at the intersection during the off-peak period, and the traffic light time template of the intersection is determined.

[0064] If the cycle of traffic lights cannot be mined during the off-peak period, or the mined cycle is significantly different from the peak period, the cycle data of the peak period can be used to fill the cycle data of the off-peak period. The filling process takes into account the possible differences between the peak period and the off-peak period, such as traffic flow, weather conditions, etc. For the cycle data with low confidence in the off-peak period, the cycle data of the peak period can be used for smoothing. Smoothing can be achieved through linear interpolation, spline interpolation or other data smoothing techniques. The cycle data of the peak period and the off-peak period are merged to form a complete traffic light time template, thereby ensuring that the traffic light time template has a clear traffic light change cycle in each time period.

[0065] After determining the time when the delivery personnel enters and exits the intersection, as well as the traffic light time template at the intersection, data comparison can be used to determine whether the delivery personnel has run a red light.

[0066] Generally speaking, if the delivery personnel enters or exits the intersection during a red light, it is judged as running a red light. If the delivery personnel enters or exits the intersection during a green light, it is judged as complying with traffic rules. It should be noted that in an optional solution and scenario of the present application, since the traffic light is estimated based on vehicle data, the determination of running a red light also needs to be verified with confidence to ensure the accuracy and reliability of the judgment.

[0067] Confidence reflects the reliability and accuracy of the judgment. The following is an explanation and implementation process of confidence: When it is determined that the delivery person has run a red light, the latest data of the time information of the vehicle starting point at the current intersection is used to verify the matching degree with the previously obtained signal light time template. When the matching degree is higher than or equal to a certain threshold, it is confirmed that the delivery person has run a red light. When the matching degree is lower than a certain threshold, it is confirmed that the delivery person has not run a red light. The introduction of confidence calculation can verify the predicted data with actual data and evaluate the accuracy of the prediction.

[0068] Optionally, the application program of the delivery personnel's terminal displays the countdown of the current traffic light at the intersection based on the confidence level. For intersections with a confidence level higher than or equal to a certain threshold, the countdown of the traffic light is displayed on the terminal so that the delivery personnel can better comply with traffic regulations.

[0069] Optionally, in the case where the delivery person runs a red light, after the delivery person passes the road intersection, the terminal device prompts through voice and / or through an identification on the delivery page of the platform order. The identification can be text, an icon, a logo, or a combination. The identification can be displayed at the current intersection of the navigation map on the delivery page, or at a specific location on the delivery page.

[0070] Through the above steps, it is possible to achieve real-time monitoring and judgment of the red light running behavior of delivery personnel, improve the awareness of delivery personnel to comply with traffic rules, and thus improve riding safety. At the same time, this method takes into account the temporal dynamics of real-time trajectories and the statistical characteristics of historical trajectories. Through machine learning algorithms and feature selection techniques, the matching accuracy is improved, providing effective technical support for the standardized riding identification method of delivery personnel. By real-time monitoring of the riding behavior of delivery personnel, the system can promptly detect violations and issue prompts to delivery personnel through terminal devices to improve riding safety.

[0071] In an optional implementation, the following method can be used to determine whether the delivery person is driving in the wrong direction:

[0072] The riding direction is determined based on the riding trajectory of the delivery personnel, and the road direction is obtained based on the current driving road. When the riding direction is inconsistent with the road direction, a preliminary result of the reverse driving judgment is obtained; based on the historical riding trajectories of multiple delivery personnel on the current road and / or the cost value of the delivery personnel changing routes, the preliminary result of the reverse driving judgment is corrected to determine whether the delivery personnel is driving in the reverse direction.

[0073] Determine the riding direction: Analyze the rider’s riding trajectory data based on the points in the rider’s riding trajectory, including location information, timestamp, speed, etc., to determine their riding direction.

[0074] Road direction determination: Determine the direction of the road, that is, the legal driving direction of the road, based on the road attribute information of the current road.

[0075] Reverse traffic judgment: Compare the riding direction and the road direction. If the two are inconsistent, it is preliminarily judged as reverse traffic, and the preliminary result of reverse traffic judgment is obtained.

[0076] Real-time updates: Since the location of delivery personnel changes over time, retrograde behavior needs to be updated in real time to maintain the accuracy of judgment.

[0077] Optionally, after obtaining the preliminary result of the wrong-travel judgment, the preliminary result of the wrong-travel judgment can be corrected according to the historical riding trajectories of multiple delivery personnel on the current road, so as to determine whether the delivery personnel are riding in the wrong direction.

[0078] Based on the historical riding trajectories of multiple delivery personnel on the current road, the preliminary results of the reverse traffic judgment are corrected, including:

[0079] For each point in the delivery personnel's riding trajectory, obtain the historical riding trajectory points of multiple delivery personnel at the current road point. According to the current driving road information of the current delivery personnel, retrieve the coordinate values ​​of the riding trajectory points of multiple delivery personnel passing through the current driving road during the delivery platform order process.

[0080] Based on the coordinates of the points in the historical riding trajectory, determine the coordinate stability of the point in the riding trajectory. Based on the coordinates of the points in the historical riding trajectory, calculate the point distribution range and concentration level of each point in the historical trajectory of the road section. Among them, the distribution range reflects the degree of dispersion of the historical trajectory points of the point in space, and the concentration level reflects the degree of aggregation of the historical trajectory points of the point in space. The coordinate stability of the point can be calculated by one or more of the following methods: standard deviation: calculate the standard deviation of the point coordinates. The smaller the standard deviation, the more stable the point coordinates; interquartile range: calculate the interquartile range of the point coordinates. The smaller the interquartile range, the more stable the point coordinates; coefficient of variation: calculate the coefficient of variation of the point coordinates. The smaller the coefficient of variation, the more stable the point coordinates. It should be noted that the present application does not limit the calculation method of coordinate stability.

[0081] According to the coordinate stability of each point in the riding trajectory, the first correction confidence of the preliminary result of the reverse traffic judgment is determined. The preliminary result of the reverse traffic judgment is corrected according to the first correction confidence. This can be achieved by the following steps:

[0082] Assuming that the delivery personnel is in the forward state, for each point in the riding trajectory, the trajectory stability of the delivery personnel is first calculated. The trajectory stability index is used to measure the continuity and consistency of the points on the delivery personnel's driving path, reflecting the continuity of the delivery personnel's driving path and whether it is consistent with the preset path. High stability means that the delivery personnel's driving trajectory path is relatively smooth and continuous. Then the reverse confidence, matching distance and historical feature probability are calculated. Among them, the reverse confidence: calculates the possibility of the current trajectory going in reverse. Matching distance: based on the matching distance between the trajectory point and the road network data, judges whether the delivery personnel's position deviates from the predetermined route. Historical feature probability: based on historical data, calculates the probability of the delivery personnel performing specific behaviors in the current situation (for example, the probability of forward or reverse driving). The historical data reflects the point distribution characteristics of the historical delivery personnel's trajectory on this section, thereby providing pattern recognition support for the current delivery personnel's behavior.

[0083] The above index parameters are comprehensively evaluated to obtain the point correction confidence. For example, a weight coefficient can be equipped for each index parameter. The weight coefficient and the operation relationship can be determined, corrected and optimized according to the real data. For each subsequent point of the section, the calculation is performed in the above manner to obtain several point correction confidences. According to the mean of all point correction confidences, the first correction confidence is obtained. The first correction confidence combines the influence of trajectory stability, retrograde confidence, matching distance and historical feature probability, with the aim of generating a comprehensive judgment index for subsequent decision-making.

[0084] The preliminary result of the reverse driving judgment is corrected according to the first correction confidence. When the first correction confidence is greater than the threshold, the system considers that the delivery person is driving in the forward direction and outputs the forward driving judgment result. When the first correction confidence is less than or equal to the threshold, it is considered that there is a risk of reverse driving and outputs the reverse driving judgment result.

[0085] This method comprehensively determines whether the delivery personnel are traveling forward or at risk of traveling backward by calculating trajectory stability, reverse confidence, matching distance, and historical feature probability. The entire process makes full use of real-time trajectory data and historical data to ensure the reliability and accuracy of the judgment process.

[0086] Optionally, after obtaining the preliminary result of the reverse driving judgment, the preliminary result of the reverse driving judgment may be corrected according to the cost value of the delivery person changing the route, so as to determine whether the delivery person is driving in the reverse direction, which may include:

[0087] For the delivery personnel's riding trajectory, determine the planned riding path and the first required time from the current driving road of the riding trajectory to the delivery destination of the platform order, and determine the estimated riding path and the second required time along the riding trajectory to the delivery destination of the platform order; determine the cost of the delivery personnel's route change by comparing the similarity of the planned riding path and the estimated riding path, as well as the difference between the first required time and the second required time; determine the second correction confidence based on the cost of the delivery personnel's route change; and correct the preliminary result of the retrograde judgment according to the second correction confidence.

[0088] In an optional implementation, after obtaining the preliminary result of the reverse driving judgment, the planned path estimation can be performed first: determine the optimal cycling planned path for the delivery personnel from the current driving road to the delivery destination. Calculate the time required for the optimal cycling planned path, including the waiting time for traffic lights, road speed limits, etc.

[0089] Actual route estimation: It assumes that the delivery personnel actually ride along the current cycling trajectory to reach the delivery destination and the time required, and also takes into account factors such as traffic light waiting time and road speed limit.

[0090] Compare the similarity of the planned path and the actual path. The path similarity can be calculated by calculating the Euclidean distance, direction difference, etc. between the two, and normalizing them to obtain the path similarity. And calculate the difference between the time required for the planned path and the time required for the actual path. The difference can be obtained by the ratio of the difference between the two and the overall delivery time of the delivery personnel to deliver the platform order, which is not limited in this application.

[0091] Cost calculation: Consider the path similarity and time difference comprehensively to determine the cost of different routes for the delivery personnel. The cost reflects whether the delivery personnel actually took a shorter or faster route because of the reverse. The cost can be a value between 0 and 1, and the higher the value, the greater the possibility of the reverse. Combined with the form and value range of the first correction confidence, the cost is mapped to the second correction confidence, so that the higher the value of the second correction confidence, the smaller the possibility of the reverse. The preliminary result of the reverse judgment is corrected according to the second correction confidence.

[0092] The preliminary result of retrograde judgment may be corrected by using both the first correction confidence and the second correction confidence, or by using only one of the correction confidences.

[0093] This solution can bring at least the following beneficial effects: Improve the safety of delivery personnel: By correcting the preliminary results of the reverse judgment, it can be more accurately judged whether the delivery personnel have reverse behavior, which helps to reduce reverse behavior and ensure road safety. Improve the intelligence of the system: Through the calculation of cost values ​​and the application of correction confidence, the system can more intelligently analyze and handle complex situations in the delivery process, and improve the system's adaptability and predictive capabilities. Optimize delivery route planning: If the delivery personnel choose to go against the flow because the planned route is unreasonable, the system can automatically report this situation, thereby optimizing subsequent route planning and improving the accuracy and convenience of planning.

[0094] The following methods can be used to determine whether the delivery personnel are prohibited from driving:

[0095] According to the current driving road of the delivery personnel, the road label of the current driving road is obtained to determine the traffic attribute; based on the traffic attribute of the current driving road, it is determined whether the delivery personnel are prohibited from driving.

[0096] In an optional implementation, the determination of the prohibited driving may include: matching the riding trajectory with the road network in the manner mentioned above to determine the current driving road of the delivery personnel.

[0097] According to the current road, the corresponding road label and traffic attributes are queried in the map database. Road labels refer to identifiers with specific meanings assigned to each road. These labels can be numbers, letters, or a combination of the two, and are used to uniquely identify a road in a map database or geographic information system. Road labels can contain one or more of the following information: road name: such as "Changjiang Road", "Zhongshan Road", etc.; road type: such as expressways, urban trunk roads, rural roads, pedestrian streets, etc.; road numbers: such as national highway numbers, provincial highway numbers, etc.; geographic codes: such as postal codes, administrative division codes, etc. Road labels are part of road attributes and are used to quickly retrieve and identify roads.

[0098] Access attributes refer to the rules and restrictions for the use of a road, which define which types of vehicles or traffic participants can travel or use the road, and how these roads should be used. Access attributes generally include the following: Vehicle type: whether different types of vehicles such as motorcycles, bicycles, private cars, trucks, buses, etc. are allowed to pass. Direction of travel: whether two-way traffic is allowed, or only one-way traffic. Speed ​​limit: the maximum speed limit for driving on the road. Lane use: which lanes can be used by which types of vehicles. Time restrictions: whether passage is allowed during certain time periods, for example, some roads may be closed at night or only allow passage during specific time periods. Special rules: such as prohibiting left turns, right turns, or prohibiting parking during certain time periods. In this application, the road name and road type can be determined based on the road label of the current road, and then the access attributes can be determined, for example, whether the road is a road that prohibits motorcycles or electric vehicles.

[0099] The delivery personnel's driving trajectory is matched with the relevant road communication attributes to determine whether it complies with regulations. If the delivery personnel's driving trajectory shows that they are driving on a road where cycling is prohibited, it is determined to be prohibited.

[0100] In step 400: when the riding behavior violates the riding regulations, the delivery personnel terminal device prompts through voice and / or through the logo in the delivery page of the platform order. The logo includes text, logo or a combination thereof.

[0101] The page of the delivery personnel's terminal device displays the real-time and statistical results of the delivery personnel's riding behavior violating the riding regulations, as well as the corresponding safety promotion content, so as to achieve real-time display and reminder of management.

[0102] Optionally, a pre-warning is given on the delivery personnel's terminal. This includes:

[0103] Real-time information feedback: Based on the delivery personnel’s direction of travel, the countdown information of the traffic lights at the next intersection can be provided in real time to help the delivery personnel reasonably plan the driving speed and route.

[0104] Risk warning: Delivery personnel can be informed through voice and / or signs whether there are high-risk areas ahead (such as areas with frequent traffic accidents, construction areas, etc.) so that they can prepare in advance or adjust their routes.

[0105] Optionally, real-time identification is performed on the delivery personnel's terminal. Including:

[0106] Full-time identification: The ability to identify the safety and compliance behaviors of delivery personnel in real time over a larger spatial range and longer time frame.

[0107] Real-time compliance check: During the delivery process, check in real time whether the delivery personnel's behavior complies with traffic rules and safety standards, and conduct safety education. If the delivery personnel is judged to have run a red light, a voice prompt can be given at the terminal at an appropriate time when the delivery personnel passes the intersection. If the delivery personnel is judged to have gone against the traffic or is prohibited from driving, a reminder can be given through text or graphic logos on the current delivery page of the delivery personnel's terminal, and / or a voice prompt can be given at the terminal.

[0108] Optionally, offline identification, post-event management and safety education are performed on the delivery personnel’s terminal, including:

[0109] Offline process analysis: Offline process analysis can be used to analyze the delivery personnel behavior using the full trajectory data of the delivery location service.

[0110] Display statistical results on the terminal: After a period of time after data collection is completed, for example, the next day (T+1 day) or within a week, a report on the identification results of the delivery personnel's safety and compliance behavior is generated. According to the identification results, corresponding governance measures are taken.

[0111] This real-time governance solution can greatly improve the safety awareness and compliance of delivery personnel, reduce the occurrence of traffic accidents and violations, and thus ensure the safety and smoothness of road traffic.

[0112] The solution provided by this application includes at least the following technical effects:

[0113] In terms of optimization of red light running recognition: by integrating multiple trajectory data information and combining light state information, red light running behavior can be identified more accurately. By using algorithms to mine traffic light cycles, even if the amount of trajectory data is small, high accuracy and generalization capabilities can be maintained. Compared with the periodic pattern mining algorithms commonly used in the industry, the method of this proposal requires less trajectory data, so the computational cost is lower and the stability is stronger. In terms of reverse and prohibited driving control, especially in riding scenarios with a high degree of freedom, this application adopts a multi-round matching and correction method to effectively improve the accuracy of identifying reverse behavior.

[0114] The solution of this application can not only identify violations, but also output the severity of the violations, providing more refined data support for subsequent governance measures. At the same time, by utilizing the integration capabilities of end intelligence, real-time security management and control is achieved, and violations can be identified instantly while delivery personnel are driving, as well as offline identification and T+1 governance. Compared with the commonly used solutions in the industry, the timeliness is greatly improved, allowing control measures to respond to violations more quickly.

[0115] To sum up, this application has proposed innovative technical solutions in terms of red light running identification, wrong-way traffic control, no-travel control, and control timeliness, which not only improves the accuracy and stability of identification, but also enhances the real-time and refinement of control, which is of great practical significance for improving the level of traffic safety management.

[0116] The present application also provides a device for identifying a delivery person's standard riding, the device comprising:

[0117] Trajectory collection module: is configured to obtain the riding trajectory of the delivery personnel in the process of delivering platform orders.

[0118] Trajectory matching module: It is configured to match the riding trajectory with the road network to determine the current driving road of the delivery personnel.

[0119] Violation identification module: configured to judge the delivery personnel's riding behavior based on the delivery personnel's riding trajectory and the attribute characteristics of the current road, so as to determine whether the delivery personnel has violated the riding regulations, wherein the violation of riding regulations includes one or more of running a red light, driving in the wrong direction, and prohibited driving.

[0120] Violation prompt module: It is configured to prompt the delivery personnel through voice and / or through the logo in the delivery page of the platform order on the terminal device when the riding behavior violates the riding regulations.

[0121] The device can obtain the delivery personnel's riding trajectory in real time and match it with the road network, effectively identifying behaviors that violate riding regulations and improving riding safety.

[0122] An electronic device provided by an exemplary embodiment of the present application may be a portable mobile terminal. Generally, the electronic device includes: a processor and a memory. The processor may include one or more processing cores, such as a 4-core processor, an 8-core processor, and the like. The processor may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor may also include a main processor and a coprocessor, the main processor being a processor for processing data in an awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in a standby state. In some embodiments, the processor may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0123] The memory may include one or more computer-readable storage media, which may be non-transitory. The memory may also include high-speed random access memory, and non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory is used to store at least one instruction, which is used to be executed by the processor to implement the method for identifying the standardized riding of delivery personnel provided in the method embodiment of the present application.

[0124] In some embodiments, the electronic device may optionally include: a peripheral device interface and at least one peripheral device. The processor, the memory and the peripheral device interface may be connected via a bus or a signal line. Each peripheral device may be connected to the peripheral device interface via a bus, a signal line or a circuit board. Specifically, the peripheral device includes: at least one of a radio frequency circuit, a display screen, a camera assembly, an audio circuit, a positioning assembly and a power supply.

[0125] The display screen is used to display the UI (User Interface). The UI may include graphics, text, icons, videos and any combination thereof. When the display screen is a touch display screen, the display screen also has the ability to collect touch signals on the surface of the display screen or above the surface. The touch signal can be input to the processor as a control signal for processing. At this time, the display screen can also be used to provide virtual buttons and / or virtual keyboards, also known as soft buttons and / or soft keyboards. In some embodiments, the display screen can be one, arranged on the front panel of the electronic device; in other embodiments, the display screen can be at least two, respectively arranged on different surfaces of the electronic device or in a folding design; in other embodiments, the display screen can be a flexible display screen, arranged on a curved surface or a folding surface of the electronic device. Even, the display screen can also be set to a non-rectangular irregular shape, that is, a special-shaped screen. The display screen can be made of materials such as LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode) and the like.

[0126] The audio circuit may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, and convert the sound waves into electrical signals and input them into a processor for processing, or input them into a radio frequency circuit to achieve voice communication. For the purpose of stereo acquisition or noise reduction, there may be multiple microphones, which are respectively arranged in different parts of the electronic device. The microphone may also be an array microphone or an omnidirectional acquisition microphone. The speaker is used to convert electrical signals from the processor or radio frequency circuit into sound waves. The speaker may be a traditional film speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can not only convert electrical signals into sound waves audible to humans, but also convert electrical signals into sound waves inaudible to humans for purposes such as ranging. In some embodiments, the audio circuit may also include a headphone jack.

[0127] The positioning component is used to locate the current geographic location of the electronic device to achieve navigation or LBS (Location Based Service). The positioning component can be a positioning component based on the US GPS (Global Positioning System), China's Beidou system or Galileo system.

[0128] In some embodiments, the electronic device further includes one or more sensors, including but not limited to: an acceleration sensor, a gyroscope sensor, a pressure sensor, a fingerprint sensor, an optical sensor, and a proximity sensor.

[0129] Those skilled in the art will appreciate that the above structure does not constitute a limitation on the electronic device, and may include more or fewer components, or combine certain components, or adopt different component arrangements.

[0130] The server provided in the embodiment of the present application may have relatively large differences due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) and one or more memories, wherein the one or more memories store at least one program code, and the at least one program code is loaded and executed by the one or more processors to implement the delivery personnel standardized riding identification method provided in the above-mentioned various method embodiments. Of course, the server may also have components such as a wired or wireless network interface, a keyboard, and an input and output interface for input and output, and the server may also include other components for realizing device functions, which will not be repeated here.

[0131] In an exemplary embodiment, a computer-readable storage medium is also provided, in which at least one program code is stored. The at least one program code is loaded and executed by a processor to enable a computer to implement any of the above-mentioned methods for identifying standardized riding of delivery personnel.

[0132] Optionally, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, etc.

[0133] In an exemplary embodiment, a computer program or a computer program product is also provided, in which at least one computer instruction is stored, and the at least one computer instruction is loaded and executed by a processor so that the computer implements any of the above-mentioned methods for identifying the standardized riding of delivery personnel.

[0134] It should be understood that the "plurality" mentioned in this article refers to two or more. "And / or" describes the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects are in an "or" relationship.

[0135] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0136] The above description is only an exemplary embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for identifying the standardized riding of delivery personnel, characterized in that: The method comprises: Obtain the riding trajectory of delivery personnel in the process of delivering orders on the platform; Match the riding trajectory with the road network to determine the delivery personnel’s current driving route; The delivery personnel's riding behavior is judged based on the delivery personnel's riding trajectory and the attribute characteristics of the current road to determine whether the delivery personnel has violated the riding regulations, wherein the violation of the riding regulations includes one or more of running a red light, driving against the flow, and prohibited driving; If the riding behavior violates the riding regulations, the delivery personnel will be prompted through voice and / or through the logo on the delivery page of the platform order on the terminal device.

2. The method according to claim 1, characterized in that The step of matching the delivery personnel's riding trajectory with the road network to determine the delivery personnel's current driving road includes: Based on the historical riding trajectories of multiple delivery personnel and the road information of the road network, the matching relationship between the historical riding trajectories and the roads is determined; The delivery personnel's riding trajectory is compared with the historical riding trajectory for similarity to determine the delivery personnel's current driving route.

3. The method according to claim 2, characterized in that Use the following methods to determine whether the delivery personnel have run a red light: If there is an intersection on the current road, determine the time when the delivery person enters the intersection and the time when he leaves the intersection based on the delivery person's riding trajectory and the current road; The entry and exit times of the intersection are compared with the traffic light time template of the intersection to determine whether the delivery personnel have run a red light.

4. The method according to claim 3, characterized in that The signal light time template is determined in the following manner: Acquire the starting point time information of the motion state changes of multiple vehicles, merge the starting point time information with similar time, and obtain several starting point time periods; Perform maximum likelihood estimation on the start point time period to obtain the change cycle range of the intersection traffic lights; The change cycle of the traffic lights at the intersection during the peak period is used to fill and smooth the change cycle of the traffic lights at the intersection during the off-peak period, and the traffic light time template of the intersection is determined.

5. The method according to claim 1, characterized in that Use the following methods to determine whether the delivery personnel are driving in the wrong direction: The riding direction is determined based on the riding trajectory of the delivery personnel, and the road direction is obtained based on the current driving road. If the riding direction is inconsistent with the road direction, a preliminary result of the reverse driving judgment is obtained; According to the historical riding trajectories of multiple delivery personnel on the current road and / or the cost value of the delivery personnel changing routes, the preliminary result of the wrong-way judgment is corrected to determine whether the delivery personnel are riding in the wrong direction.

6. The method according to claim 5, characterized in that Based on the historical riding trajectories of multiple delivery personnel on the current road, the preliminary results of the reverse traffic judgment are corrected, including: For each point in the delivery personnel's riding trajectory, obtain the historical riding trajectory points of multiple delivery personnel at the current road point; Based on the coordinates of the historical riding track point, determine the coordinate stability of the point in the riding track; According to the coordinate stability of each point in the riding trajectory, a first correction confidence for the preliminary result of the retrograde judgment is determined; The preliminary result of retrograde judgment is corrected according to the first correction confidence.

7. The method according to claim 5, characterized in that According to the cost value of the delivery personnel changing the route, the preliminary result of the reverse judgment is corrected, including: For the delivery personnel's riding trajectory, determine the planned riding route and the first required time from the current driving road of the riding trajectory to the delivery destination of the platform order, and determine the estimated riding route and the second required time along the riding trajectory to the delivery destination of the platform order; By comparing the similarity between the planned cycling route and the estimated cycling route, and the difference between the first required time and the second required time, the cost of changing the route of the delivery person is determined; Determining a second correction confidence based on the delivery personnel route change cost value; The preliminary result of the retrograde judgment is corrected according to the second correction confidence.

8. The method according to claim 1, characterized in that Use the following methods to determine whether the delivery personnel are prohibited from driving: According to the current driving road of the delivery personnel, the road label of the current driving road is obtained to determine the traffic attribute; Based on the traffic attributes of the current road, determine whether the delivery personnel are prohibited from driving.

9. The method according to any one of claims 1 to 8, characterized in that: The method further comprises: The page of the delivery personnel's terminal device displays the statistical results of the delivery personnel's riding behavior violating the riding regulations, as well as the corresponding safety promotion content.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.