Method, device, storage medium and electronic equipment for monitoring shared vehicle
By recognizing images of shared vehicle parking areas, the system automatically determines the degree of abnormal parking of abnormal vehicles and their managers, and notifies the target managers to handle the issue. This solves the problem of existing technologies being unable to quickly manage abnormally parked vehicles, and achieves real-time and efficient operation of shared vehicles.
Patent Information
- Application Number
- CN202510122747.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-01-26
- Publication Date
- 2026-08-04
AI Technical Summary
In existing technologies, relying on site managers to patrol and notify parking areas is not a quick way to sort out abnormally parked shared vehicles, which affects the normal operation of shared vehicles.
By acquiring images of shared vehicle parking areas and using AI devices to identify parking results, the degree of abnormal parking of abnormal vehicles and their management is determined, and the target management is automatically notified for handling.
It enables real-time monitoring and rapid handling of abnormally parked vehicles, reducing the impact on shared vehicle operations and improving the real-time nature of monitoring and processing efficiency.
Smart Images

Figure CN122511070A_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of shared vehicle technology, and in particular to a method, device, storage medium and electronic equipment for monitoring shared vehicles. Background Technology
[0002] Shared vehicles provide users with a convenient way to travel in the city. However, in areas where shared vehicles are frequently used, there are often abnormal parking situations such as vehicle congestion or vehicles not being parked properly.
[0003] Currently, the relevant technologies mainly rely on site managers to conduct on-site inspections of the parking areas for shared vehicles. When abnormally parked shared vehicles are found, the relevant vehicle managers are notified to tidy them up.
[0004] However, the technology relies on site managers to patrol and notify parking areas, which is time-consuming and cannot quickly address abnormally parked shared vehicles, thus affecting the normal operation of shared vehicles. Summary of the Invention
[0005] In view of this, this disclosure provides a monitoring method, device, storage medium and electronic device for shared vehicles. The main purpose is to improve the technical problem that the current reliance on site managers to patrol and notify parking areas is lagging and cannot quickly sort out abnormally parked shared vehicles, thus affecting the normal operation of shared vehicles.
[0006] In a first aspect, this disclosure provides a method for monitoring shared vehicles, the method comprising:
[0007] Obtain parking recognition results by recognizing images of shared vehicle parking areas;
[0008] If it is determined that a vehicle is parked abnormally based on the parking identification result, then the management party corresponding to the abnormally parked vehicle and the degree of abnormal parking corresponding to the management party are determined based on the parking identification result.
[0009] Based on the degree of abnormal parking corresponding to each of the aforementioned management parties, the target management party that needs to be notified is determined from among the management parties.
[0010] Send a notification message about abnormal parking of shared vehicles to the management platform corresponding to the target management party.
[0011] Secondly, this disclosure provides a monitoring device for shared vehicles, the device comprising:
[0012] The acquisition module is configured to acquire parking recognition results obtained by recognizing images of parking areas of shared vehicles;
[0013] The determination module is configured to, if it is determined that there is an abnormal parking of a vehicle based on the parking identification result, determine the management party corresponding to the abnormally parked vehicle and the degree of abnormal parking corresponding to the management party based on the parking identification result;
[0014] The determination module is configured to determine the target management party that needs to be notified from the management parties based on the degree of abnormal parking corresponding to each management party;
[0015] The sending module is configured to send a notification message about abnormal parking of shared vehicles to the management platform corresponding to the target manager.
[0016] Thirdly, this disclosure provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the shared vehicle monitoring method described in the first aspect.
[0017] Fourthly, this disclosure provides an electronic device, including a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein the processor executes the computer program to implement the shared vehicle monitoring method described in the first aspect.
[0018] Fifthly, this disclosure provides a computer program product, including a computer program that, when executed by a processor, implements the shared vehicle monitoring method described in the first aspect.
[0019] By employing the above technical solution, this disclosure provides a method, device, storage medium, and electronic device for monitoring shared vehicles. Compared with existing related technologies, this disclosure first obtains parking identification results by recognizing images of parking areas of shared vehicles; then, if it is determined that there is abnormal parking of a vehicle based on the parking identification results, the management party corresponding to the abnormally parked vehicle and the degree of abnormal parking corresponding to each management party are determined according to the parking identification results; then, based on the degree of abnormal parking corresponding to each management party, the target management party to be notified is determined from among the management parties; finally, a notification message of abnormal parking of shared vehicles is sent to the management platform corresponding to the target management party. By applying the technical solution of this disclosure, this disclosure can identify the parking area image of shared vehicles and obtain the parking identification results of the shared vehicles corresponding to the parking area. When abnormally parked vehicles are detected in the parking area based on the parking identification results, the management party corresponding to the abnormally parked vehicle and the degree of abnormal parking for each management party are determined according to the parking identification results. Then, the target management party is determined according to the degree of abnormal parking and instructed to handle the abnormally parked vehicles in a timely manner. This realizes real-time monitoring of abnormally parked vehicles in the parking area without relying on site management personnel to patrol and notify the parking area, improving the real-time performance of shared vehicle monitoring. This enables the target management party to quickly handle abnormally parked vehicles and reduces the impact on the normal operation of shared vehicles.
[0020] The above description is merely an overview of the technical solution disclosed herein. In order to better understand the technical means of this disclosure and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this disclosure more apparent and understandable, specific embodiments of this disclosure are described below. Attached Figure Description
[0021] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.
[0022] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0023] Figure 1 A flowchart illustrating a method for monitoring shared vehicles provided in an embodiment of this disclosure is shown.
[0024] Figure 2 A flowchart illustrating a method for monitoring shared vehicles provided in an embodiment of this disclosure is shown.
[0025] Figure 3 A flowchart illustrating an example provided by an embodiment of this disclosure is shown;
[0026] Figure 4 A schematic diagram of the structure of a monitoring device for shared vehicles provided in an embodiment of this disclosure is shown. Detailed Implementation
[0027] To better understand the above-mentioned objectives, features, and advantages of this disclosure, the solutions disclosed herein will be further described below. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.
[0028] To address the technical issues of current methods that rely on site managers to patrol and notify parking areas, which are often delayed and unable to quickly handle abnormally parked shared vehicles, thus affecting the normal operation of shared vehicles, this embodiment provides a method for monitoring shared vehicles, such as... Figure 1 As shown, the method includes:
[0029] Step 101: Obtain the parking recognition result obtained by recognizing the parking area image of the shared vehicle.
[0030] In some embodiments, cameras and other devices can be installed in the parking areas of shared vehicles. The number of cameras is configured according to the area size of the parking area, and the installation position of each camera is determined based on the location of the parking area to ensure that the field of view of each camera covers the parking area, thereby capturing a complete image of the parking area. This image can include pictures or videos. For example, for smaller parking areas, only one camera may be installed; for larger parking areas, multiple cameras may be installed to capture images from multiple angles, thus obtaining a complete image of the parking area. Image recognition is then performed on the captured images to obtain the parking identification results, facilitating real-time monitoring of shared vehicles within the parking area and reducing the cost of manual monitoring. Accordingly, the camera configuration installed in the parking area can meet the image quality requirements of the algorithm. The parking area may include popular parking areas, such as parking spots around subway entrances, shopping malls, office buildings, and other popular locations.
[0031] In some embodiments, devices with artificial intelligence (AI) capabilities (such as AI edge devices, AI cloud services, etc.) can be used to perform image recognition on the collected parking area images to obtain parking recognition results. Accordingly, the parking recognition results may include, but are not limited to, the abnormal parking recognition results of shared vehicles in the parking area images (such as whether there is a backlog of shared vehicles, whether shared vehicles are not neatly arranged, etc.), vehicle identification information, etc. (such as the management information corresponding to the shared vehicles, etc.).
[0032] Step 102: If the parking identification results determine that there is an abnormal parking of a vehicle, then determine the management party corresponding to the abnormally parked vehicle and the degree of abnormal parking of each management party based on the parking identification results.
[0033] In specific application scenarios, if shared vehicles are parked in undesignated areas or violate other parking rules, they can be marked as abnormally parked vehicles. Examples include parking on sidewalks, driveways, green belts, or other non-designated parking areas, or situations where vehicles are piled up, improperly arranged, stacked, or obstructing passageways, affecting urban traffic order and aesthetics. The management entity can be any organization or institution that manages and maintains the shared vehicles, and can be used to handle issues related to the deployment, maintenance, dispatch, and parking of these vehicles.
[0034] In some embodiments, if the parking identification result indicates abnormal parking, the management unit corresponding to the abnormally parked shared vehicle can be obtained based on the parking identification result identified by the AI device. Since multiple management units may correspond to abnormally parked shared vehicles in the same parking area, and the number of abnormal vehicles corresponding to each management unit may differ, the degree of abnormal parking for each management unit can be obtained based on the parking identification result, thereby enabling real-time monitoring of vehicle parking conditions in the parking area. Specifically, the degree of abnormal parking can be used to indicate the extent to which a shared vehicle deviates from a preset parking standard. It can be determined based on factors such as the number of abnormal vehicles, the irrationality of the parking location, and the degree of inconvenience caused to the public, such as general abnormality, moderate abnormality, and severe abnormality.
[0035] Step 103: Based on the degree of abnormal parking corresponding to each management party, determine the target management party that needs to be notified.
[0036] In some embodiments, based on the degree of abnormal parking for each management entity, the management entity with the highest level of abnormal parking can be identified as the target management entity. The target management entity can then be used to promptly handle abnormally parked vehicles. For example, if a management entity's abnormal parking level is generally abnormal, with a small number of abnormal vehicles, it does not need to be identified as a target management entity requiring notification. However, if a management entity's abnormal parking level is severely abnormal, with a large number of abnormal vehicles, seriously affecting traffic order and the city's aesthetics, it can be identified as a target management entity requiring notification so that abnormal vehicle intervention can be carried out in a timely manner.
[0037] Step 104: Send a notification message about the abnormal parking of shared vehicles to the management platform corresponding to the target management party.
[0038] In some embodiments, after identifying the target manager, a notification message can be promptly sent to the management platform corresponding to the target manager. If there are multiple target managers, a notification message indicating abnormal parking of shared vehicles can be sent to the management platform corresponding to each target manager, informing them of the shared vehicles parked abnormally and the degree of abnormal parking. Upon receiving the notification message, the target manager can promptly arrange relevant management personnel to handle the abnormally parked vehicles based on the degree of abnormal parking and other information. For example, the abnormally parked shared vehicles can be moved to designated parking areas, the number of vehicles deployed in the parking area can be reduced, and the shared vehicles can be arranged neatly. This will improve the parking situation in the parking area in a timely manner and reduce the negative impact of improper parking of shared vehicles.
[0039] By applying the technical solution of this disclosure embodiment, this embodiment can obtain the parking identification result of the shared vehicles corresponding to the parking area by recognizing the parking area image of the shared vehicles. When abnormally parked vehicles are detected in the parking area according to the parking identification result, the management party corresponding to the abnormally parked vehicle and the degree of abnormal parking corresponding to each management party are determined according to the parking identification result. Then, the target management party is determined according to the degree of abnormal parking, and the target management party is instructed to handle the abnormally parked vehicles in a timely manner. This realizes real-time monitoring of abnormally parked vehicles in the parking area without relying on site management personnel to patrol and notify the parking area, which improves the real-time performance of shared vehicle monitoring and enables the target management party to quickly handle abnormally parked vehicles, reducing the impact on the normal operation of shared vehicles.
[0040] To further illustrate, as Figure 1 The specific implementation process of the method shown in this embodiment is provided as follows: Figure 2 The specific method shown includes:
[0041] Step 201: Obtain the parking recognition result obtained by recognizing the parking area image of the shared vehicle.
[0042] For example, such as Figure 3 As shown, cameras and AI edge devices with computing power can be installed in the parking areas of shared vehicles near subway entrances. After the cameras capture video streams or images of the parking area, they can be transmitted to the AI edge devices in real time. The AI edge devices then use these devices to identify the parking area images and obtain parking recognition results. This eliminates the need to transmit the video streams or images captured by the cameras to the cloud via the internet, thus reducing bandwidth or data costs. As another possible implementation, after the cameras capture images in the parking area, they can also upload the images to an AI cloud service for image recognition to obtain parking recognition results.
[0043] Correspondingly, after AI edge devices or AI cloud services identify shared vehicles in parking area images, obtain parking identification results, and determine whether there are abnormal parking situations such as siltation, the parking identification results can be transmitted to the cloud judgment service. The cloud judgment service will then notify and distribute the abnormal parking vehicles to at least one management party, such as: management party 1, management party 2, and management party 3.
[0044] Correspondingly, the cloud-based determination service can determine the number of shared vehicles corresponding to each management party based on the parking identification results, and then determine the management party that needs to be notified. This enables the management party to notify relevant personnel to handle abnormally parked vehicles, realizing automatic determination of the management party of abnormally parked vehicles, reducing the cost of manual inspection and notification of parking areas, improving the efficiency of management parties in handling abnormal vehicles, and thus reducing the impact on the operation of shared vehicles.
[0045] Optionally, step 201 may specifically include: performing AI image recognition on the parking area image to obtain the number of parked vehicles corresponding to each management unit; and determining the parking recognition result based on the number of parked vehicles corresponding to each management unit.
[0046] For example, AI edge devices or models in AI cloud services can be used to perform AI image recognition on parking area images to identify the number of shared vehicles corresponding to each management unit in the parking area image, and then determine the parking recognition result of the parking area based on the number of parked vehicles corresponding to each management unit. The model for performing AI image recognition on parking area images may include, but is not limited to, visual algorithm models with object detection capabilities, such as YOLOv5 and YOLOv8.
[0047] In some embodiments, the parking identification result is determined based on the number of parked vehicles corresponding to each management entity. Specifically, this may include: if the total number of parked vehicles corresponding to each management entity is greater than the parking capacity of the parking area, then an abnormal parking identification result indicating vehicle congestion is determined.
[0048] The parking capacity of a parking area can be preset based on factors such as the location and area of the parking area, for example, 50 vehicles or 100 vehicles.
[0049] In some embodiments, the number of parked vehicles corresponding to each management unit can be identified through AI edge devices or AI cloud services, and the total number of parked vehicles corresponding to each management unit can be calculated. Then, the total number of parked vehicles corresponding to each management unit is compared with the parking capacity of the parking area. If the total number of parked vehicles is greater than the parking capacity of the parking area, it can be determined that there is vehicle congestion in the parking area, and the relevant management unit needs to be notified in time to deal with the situation and restore normal operation. If the total number of parked vehicles is not greater than the parking capacity of the parking area, it can be determined that there is no vehicle congestion in the parking area, and the management unit does not need to be notified for intervention.
[0050] In specific application scenarios, each management platform can collect images of parking areas in real time or collect the location information of each shared vehicle, obtain the number of vehicles parked in the corresponding parking area for each management, compare it with the parking capacity of the parking area, and determine whether there is any abnormal parking situation such as congestion through the management platform itself.
[0051] Optionally, step 201 may further include: performing AI image recognition on the parking area image to obtain the placement positions of the parked vehicles; and determining the parking recognition result based on the placement positions of the parked vehicles.
[0052] For example, AI image recognition can be used to obtain information such as the shape and position of each shared vehicle in the parking area image. Specifically, the position of each shared vehicle's components (such as the seat and handlebars) can be identified to indicate the placement position of each shared vehicle. Then, based on the distance and orientation between the placement positions of each parked vehicle, it can be determined whether the parked vehicles are neatly arranged, so as to improve the aesthetics of the vehicle placement.
[0053] Optionally, the parking recognition result can be determined based on the placement position of each parked vehicle. Specifically, this may include: obtaining the coordinate points of each parked vehicle in the parking area image; fitting a target straight line based on the coordinate points of each parked vehicle; calculating the deviation between each coordinate point and the target straight line; and if the sum of the deviations is greater than a third preset threshold, then an abnormal parking recognition result indicating that the vehicles are not neatly placed can be determined.
[0054] One possible implementation is to use rectangles to identify each shared vehicle, with the center point of the rectangle defined as the coordinate point of the corresponding shared vehicle in the parking area. Then, through line fitting, the coordinate points of each shared vehicle are fitted to a target straight line, and the deviation between the coordinate points of each shared vehicle and the target straight line is obtained. The sum of the deviations of each shared vehicle is calculated. If the total deviation exceeds a third preset threshold, the abnormal parking identification result for that parking area is determined to be that the vehicles are not neatly arranged, requiring notification to the relevant management for intervention. The third preset threshold can be a pre-set threshold used to evaluate whether multiple shared vehicles in the parking area image are neatly arranged, enabling analysis of the distribution of abnormally parked vehicles.
[0055] Optionally, step 201 may further include: performing AI image recognition on the parking area image to obtain the appearance feature information corresponding to each parked vehicle; comparing the appearance feature information with the appearance feature information of shared vehicles corresponding to different management parties; determining the management party corresponding to each parked vehicle based on the comparison results, and determining the parking recognition result based on the management party corresponding to each parked vehicle.
[0056] The appearance features of shared vehicles can include information such as color, structure, text, and patterns. For example, AI edge devices or AI cloud services can be used to perform AI image recognition on images of shared vehicles in parking areas, obtaining the color information of each shared vehicle in the image and comparing it with the colors of shared vehicles belonging to each management entity. If a vehicle in the image is found to have a color matching a particular management entity's shared vehicle, the identified vehicle can be marked as belonging to that entity. Thus, by recognizing the appearance features of each shared vehicle, the management entity corresponding to each vehicle can be determined, thereby determining the parking identification result for each management entity.
[0057] Step 202: If it is determined that there are vehicles parked abnormally based on the parking identification results, then obtain the number of abnormally parked vehicles corresponding to the management based on the parking identification results.
[0058] In some embodiments, a preset time interval for detecting parked vehicles can be set based on information such as the location, area, and peak parking times of each parking area. Then, abnormally parked vehicles are identified based on the preset time interval. The number of shared vehicles corresponding to each management party is then identified through models in AI edge devices or AI cloud services. Alternatively, the parking identification results can be received through cloud-based judgment services. Based on the management party information corresponding to each shared vehicle in the parking identification results, the number of abnormally parked vehicles corresponding to each management party can be determined. This allows for the selection of management parties that need intervention, and timely notification to intervene in abnormally parked vehicles to reduce the impact on vehicle operation.
[0059] Step 203: Determine the degree of abnormal parking based on the number of abnormally parked vehicles.
[0060] In some embodiments, a score can be used to represent the degree of abnormal parking in a parking area. For example, a score of 0-9 can be used to rate the degree of abnormal parking. A score of 0 to 3 corresponds to a general degree of abnormal parking, involving a small number of vehicles; a score of 4 to 6 corresponds to a moderate degree of abnormal parking, which may lead to minor traffic congestion or public safety issues; a score of 7 to 9 corresponds to a severe degree of abnormal parking, which may easily lead to serious traffic congestion or public safety issues and affect the aesthetics of the city.
[0061] Step 204: Based on the degree of abnormal parking corresponding to each management party, determine the target management party that needs to be notified.
[0062] The target management party can be at least one management party that needs to intervene in abnormally parked vehicles.
[0063] In some embodiments, the degree of abnormal parking of the target management party can be determined based on geographical location, parking time, weather conditions and other factors. For example, the management party with the highest degree of abnormal parking can be selected as the target management party, or the management party with a moderate or severe degree of abnormal parking can be selected as the target management party. Then, the target management party is notified to handle its abnormally parked vehicles and restore them to normal parking status, thereby reducing the impact on traffic order, improving the aesthetics of the city, and reducing the impact on the operation of shared vehicles.
[0064] Optionally, step 204 may specifically include: identifying management entities whose number of abnormally parked vehicles exceeds a first preset threshold as target management entities; or, determining the percentage of abnormal vehicles corresponding to each management entity based on the number of abnormally parked vehicles, and identifying management entities whose percentage of abnormal vehicles exceeds a second preset threshold as target management entities.
[0065] In some embodiments, when the number of abnormally parked vehicles in a parking area by a certain management entity exceeds a first preset threshold, that management entity can be identified as the target management entity that needs to handle abnormal vehicles. Alternatively, the total number of abnormally parked vehicles in the parking area can be obtained, the proportion of abnormal vehicles for each management entity can be calculated, and by comparing the proportion of abnormal vehicles for each management entity with a second preset threshold, the management entity with the proportion of abnormal vehicles greater than the second preset threshold can be identified as the target management entity, thereby achieving automatic identification of the target management entity and effectively improving the efficiency of abnormal vehicle handling.
[0066] In specific application scenarios, different parking areas may have different sizes. A first preset threshold and a second preset threshold can be set according to the size of each parking area. The first preset threshold can be a preset number of vehicles to evaluate whether the number of abnormal vehicles detected by the management is abnormal, such as 50 vehicles or 80 vehicles. For example, if the first preset threshold is 50 vehicles, and two management entities are detected with 2 and 80 abnormally parked vehicles respectively, then the management entity with 80 abnormally parked vehicles should be identified as the target management entity and should be the primary handling entity for abnormally parked vehicles, and should intervene in abnormally parked vehicles in a timely manner.
[0067] Correspondingly, the second preset threshold can be a preset percentage for evaluating whether the proportion of abnormal vehicles of the management party is abnormal, such as 30% or 50%. For example, if the second preset threshold is 30%, and two management parties with abnormal parking percentages of 10% and 80% are detected, the management party with an abnormal parking percentage of 80% should be identified as the target management party and the main party handling abnormal parking vehicles, and should intervene in abnormal parking vehicles in a timely manner.
[0068] Step 205: Send a notification message about the abnormal parking of shared vehicles to the management platform corresponding to the target manager.
[0069] In some embodiments, a cloud-based determination service can send a notification message to a selected target manager, requesting them to take measures to resolve the abnormal parking issues of shared vehicles. For example, the notification message may include, but is not limited to, the location, number, duration, and intervention suggestions of the abnormally parked vehicles for the target manager. Correspondingly, upon receiving the notification message from the cloud-based determination service, the target manager's management platform can quickly organize relevant management personnel to go to the site to organize and manage the vehicles.
[0070] Optionally, step 205 may specifically include: generating time limit information for abnormal handling based on the degree of abnormal parking and the weather information of the parking area; and sending a notification message containing the time limit information to the management platform.
[0071] In some embodiments, weather information corresponding to parking areas can be collected via AI edge devices and then uploaded to the cloud. Alternatively, weather information for each parking area can be collected directly through a cloud-based judgment service. The cloud-based judgment service can then combine this information with the abnormal parking information of shared vehicles from each target management entity to determine the time limit for handling abnormal vehicles for each entity. Finally, a notification message carrying the time limit information is sent to the management platform of each target management entity. For example, for a target management entity with a moderate level of abnormal parking, if the weather in the parking area is detected as sunny, the time limit for handling abnormal vehicles can be determined to be 1 hour; for a target management entity with a moderate level of abnormal parking, if the weather in the parking area is detected as rainy, the time limit for handling abnormal vehicles can be determined to be 2 hours.
[0072] In some embodiments, the management platform corresponding to the target management entity can send notification messages to relevant management personnel, quickly organizing them to go to the parking area to evacuate and redistribute abnormally parked vehicles. Management personnel can adjust the allocation of nearby parking resources based on the actual situation on site, such as adding temporary parking spaces or optimizing the existing parking space layout. Specifically, the management platform corresponding to the target management entity can notify relevant management personnel via SMS, telephone, work orders, etc., enabling them to promptly handle abnormally parked vehicles and complete the relevant vehicle handling work within the specified time limit, minimizing the impact on vehicle operations.
[0073] In some embodiments, the system continuously monitors the progress of interventions by the target management party regarding abnormally parked vehicles and collects intervention result data. The cloud-based judgment service can adjust relevant strategy configurations, such as intervention time limits, first preset thresholds, and second preset thresholds, based on the intervention result data from multiple interventions to optimize the management efficiency of shared vehicles. Simultaneously, it can receive reports from users via the app or other channels regarding abnormal parking of shared vehicles, allowing for timely data updates and processing. This effectively manages and controls the problem of abnormal parking of shared vehicles, ensuring urban traffic order and the rational use of public space, thereby improving the user experience.
[0074] This disclosure provides a scheme for monitoring abnormally parked vehicles in a parking area. Based on the parking identification results, the number of abnormally parked vehicles corresponding to each management entity can be obtained. By comparing the number of abnormally parked vehicles with a first preset threshold, the target management entity can be determined. Furthermore, based on the degree of abnormal parking and the weather information of the parking area, time limit information for abnormal handling can be generated, and a notification message containing the time limit information can be sent to the management platform. This enables automatic identification of the target management entity and notifies the target management entity to handle abnormally parked vehicles in a timely manner according to the time limit information, effectively improving the efficiency of abnormal vehicle handling and reducing the impact on vehicle operation.
[0075] Furthermore, embodiments of this disclosure provide a monitoring device for shared vehicles, such as... Figure 4 As shown, the device includes: an acquisition module 31, a determination module 32, and a transmission module 33.
[0076] The acquisition module 31 is configured to acquire the parking recognition result obtained by recognizing the parking area image of the shared vehicle;
[0077] The determination module 32 is configured to, if it is determined that there is an abnormal parking of a vehicle based on the parking recognition result, determine the management party corresponding to the abnormally parked vehicle and the degree of abnormal parking corresponding to each management party based on the parking recognition result;
[0078] Module 32 is configured to determine the target management party that needs to be notified based on the degree of abnormal parking corresponding to each management party.
[0079] The sending module 33 is configured to send a notification message about abnormal parking of shared vehicles to the management platform corresponding to the target manager.
[0080] In some embodiments, the determining module 32 is specifically configured to obtain the number of abnormally parked vehicles corresponding to the management based on the parking identification results; and determine the degree of abnormal parking based on the number of abnormally parked vehicles.
[0081] In some embodiments, the determining module 32 is specifically configured to acquire the management party whose number of abnormally parked vehicles is greater than a first preset threshold as the target management party; or, based on the number of abnormally parked vehicles, determine the proportion of abnormal vehicles corresponding to each management party, and acquire the management party whose proportion of abnormal vehicles is greater than a second preset threshold as the target management party.
[0082] In some embodiments, the determining module 32 is specifically configured to perform AI image recognition on the parking area image to obtain the number of parked vehicles corresponding to each management unit; and determine the parking recognition result based on the number of parked vehicles corresponding to each management unit.
[0083] In some embodiments, the determining module 32 is specifically configured to determine an abnormal parking identification result of vehicle congestion if the total number of parked vehicles corresponding to each management party is greater than the parking capacity of the parking area.
[0084] In some embodiments, the determining module 32 is specifically configured to perform AI image recognition on the parking area image to obtain the placement positions of the parked vehicles respectively; and determine the parking recognition result based on the placement positions of the parked vehicles respectively.
[0085] In some embodiments, the determining module 32 is specifically configured to acquire the coordinate points of the parked vehicles in the parking area image; fit the target straight line based on the coordinate points corresponding to the parked vehicles; calculate the deviation between the coordinate points and the target straight line; if the sum of the deviations is greater than a third preset threshold, then it is determined that there is an abnormal parking recognition result where the vehicles are not neatly arranged.
[0086] In some embodiments, the determining module 32 is specifically configured to perform AI image recognition on the parking area image to obtain the appearance feature information corresponding to each parked vehicle; compare the appearance feature information with the appearance feature information of shared vehicles corresponding to different management parties; determine the management party corresponding to each parked vehicle based on the comparison results; and determine the parking recognition result based on the management party corresponding to each parked vehicle.
[0087] In some embodiments, the sending module 33 is specifically configured to generate time limit information for abnormal handling based on the degree of abnormal parking and the weather information of the parking area; and send a notification message containing the time limit information to the management platform.
[0088] It should be noted that other corresponding descriptions of the functional units involved in the shared vehicle monitoring device provided in this disclosure embodiment can be found by referring to... Figures 1 to 2 The corresponding description in [the document] will not be repeated here.
[0089] Based on the above, Figures 1 to 2 As illustrated in the example, correspondingly, embodiments of this disclosure also provide a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the above-described... Figures 1 to 2 The example method shown.
[0090] Based on the above, Figures 1 to 2 As illustrated, correspondingly, this disclosure also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described... Figures 1 to 2 The example method shown.
[0091] Based on this understanding, the technical solutions of the embodiments of this disclosure can be embodied in the form of a software product. The software product can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, mobile hard drive, etc.) and includes several instructions to cause a computer device (such as a personal computer, server, or network device, etc.) to execute the methods of various implementation scenarios of this disclosure.
[0092] Based on the above, Figures 1 to 2 The method shown, and Figure 4 To achieve the above objectives, this disclosure also provides an electronic device, comprising a storage medium and a processor; the storage medium for storing a computer program; and the processor for executing the computer program to implement the above-described virtual device embodiments. Figures 1 to 2 The method shown.
[0093] Optionally, the aforementioned electronic device may also include a user interface, a network interface, a camera, radio frequency (RF) circuitry, sensors, audio circuitry, a Wi-Fi module, etc. The user interface may include a display screen, an input unit, etc.
[0094] Furthermore, this disclosure also provides a shared vehicle, such as a shared bicycle (or shared electric bicycle), a shared electric bicycle (or shared electric vehicle), a shared electric scooter, a shared car, a shared motorcycle, a shared truck, a shared van, a shared golf cart, etc. The shared vehicle may include, for example... Figure 4 The apparatus shown may include a computer-readable storage medium, an electronic device, or a computer program product that implements the shared vehicle side method.
[0095] Those skilled in the art will understand that the physical device structure provided in this embodiment does not constitute a limitation on the physical device, and may include more or fewer components, or combine certain components, or have different component arrangements.
[0096] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages the hardware and software resources of the aforementioned physical device, supporting the operation of information processing programs and other software and / or programs. The network communication module is used to enable communication between the various components within the storage medium, as well as communication with other hardware and software in the information processing physical device.
[0097] Through the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platforms, or it can be implemented by hardware. This disclosure provides a scheme for monitoring abnormally parked vehicles in a parking area. Based on the parking identification results, the number of abnormally parked vehicles corresponding to each management entity can be obtained. By comparing the number of abnormally parked vehicles with a first preset threshold, the target management entity can be determined. Furthermore, based on the degree of abnormal parking and the weather information of the parking area, time limit information for abnormal handling can be generated, and a notification message containing the time limit information can be sent to the management platform. This achieves automatic identification of the target management entity and notifies it to promptly handle abnormally parked vehicles according to the time limit information, effectively improving the efficiency of abnormal vehicle handling and reducing the impact on vehicle operation.
[0098] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the term "comprising" or any other variations thereof is intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.
[0099] The above are merely specific embodiments of this application, enabling those skilled in the art to understand or implement this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to these embodiments, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.
Claims
1. A monitoring method of a shared vehicle, characterized by, include: Obtain parking recognition results by recognizing images of shared vehicle parking areas; If it is determined that a vehicle is parked abnormally based on the parking identification result, then the management party corresponding to the abnormally parked vehicle and the degree of abnormal parking corresponding to the management party are determined based on the parking identification result. Based on the degree of abnormal parking corresponding to each of the aforementioned management parties, the target management party that needs to be notified is determined from among the management parties. Send a notification message about abnormal parking of shared vehicles to the management platform corresponding to the target management party.
2. The method of claim 1, wherein, Based on the parking identification results, the degree of abnormal parking corresponding to each management party is determined, including: Based on the parking identification results, the number of abnormally parked vehicles corresponding to each management entity is obtained; The degree of abnormal parking is determined based on the number of abnormally parked vehicles.
3. The method of claim 2, wherein, Based on the degree of abnormal parking corresponding to each of the aforementioned management entities, the target management entities that need to be notified are determined, including: The management entities whose number of abnormally parked vehicles exceeds a first preset threshold are identified as the target management entities; or, Based on the number of abnormally parked vehicles, the percentage of abnormal vehicles corresponding to each management party is determined, and management parties with an abnormal vehicle percentage greater than a second preset threshold are selected as the target management parties.
4. The method of claim 1, wherein, The parking recognition results obtained by identifying images of shared vehicle parking areas include: The parking area image is subjected to artificial intelligence (AI) image recognition to obtain the number of parked vehicles corresponding to each management unit; The parking identification result is determined based on the number of parked vehicles corresponding to each management entity.
5. The method of claim 4, wherein, The parking identification result is determined based on the number of parked vehicles corresponding to each management entity, including: If the total number of parked vehicles corresponding to each management entity is greater than the parking capacity of the parking area, then an abnormal parking identification result of vehicle congestion is determined.
6. The method of claim 1, wherein, The parking recognition results obtained by identifying images of shared vehicle parking areas include: AI image recognition is performed on the parking area image to obtain the placement positions of the parked vehicles. The parking recognition result is determined based on the placement position of each parked vehicle.
7. The method of claim 6, wherein, The parking recognition result is determined based on the placement positions of the parked vehicles, including: Obtain the coordinates of the parked vehicles in the parking area image; The target straight line is obtained by fitting the coordinate points corresponding to the parked vehicles; Calculate the deviation between the coordinate points and the target line; If the sum of the deviations is greater than the third preset threshold, then it is determined that there is an abnormal parking result where the vehicle is not neatly arranged.
8. The method of claim 1, wherein, The parking recognition results obtained by identifying images of shared vehicle parking areas include: AI image recognition is performed on the parking area image to obtain the appearance feature information of each parked vehicle; The appearance feature information is compared with the appearance feature information of shared vehicles corresponding to different management parties; Based on the comparison results, the management entity corresponding to each parked vehicle is determined, and the parking identification result is determined based on the management entity corresponding to each parked vehicle.
9. The method according to any one of claims 1 to 8, characterized in that, Send a notification message about abnormal parking of shared vehicles to the management platform corresponding to the target manager, including: Based on the degree of abnormal parking and the weather information of the parking area, generate time limit information for abnormal handling; Send the notification message containing the time limit information to the management platform.
10. A monitoring device of a shared vehicle, characterized by, include: The acquisition module is configured to acquire parking recognition results obtained by recognizing images of parking areas of shared vehicles; The determination module is configured to, if it is determined that there is an abnormal parking of a vehicle based on the parking identification result, determine the management party corresponding to the abnormally parked vehicle and the degree of abnormal parking corresponding to the management party based on the parking identification result; The determination module is configured to determine the target management party that needs to be notified from the management parties based on the degree of abnormal parking corresponding to each management party; The sending module is configured to send a notification message about abnormal parking of shared vehicles to the management platform corresponding to the target manager.
11. A computer readable storage medium having stored thereon a computer program, characterized in that When the computer program is executed by a processor, it implements the method of any one of claims 1 to 9.
12. An electronic device comprising a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 9.
13. A computer program product comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 9.