Vehicle occupancy recognition method, recognition device, electronic equipment and storage medium

Abstract

The application provides a vehicle occupancy identification method, an identification device, an electronic device and a storage medium. The method is applied to the technical field of parking space identification. The method comprises the following steps: determining a geographic fence of a target parking space, acquiring charging pile state information of the target parking space, and corresponding vehicle state information and historical charging records; determining the parking-in state of the vehicle according to the geographic fence and the vehicle state information; determining the electrical state of the charging pile according to the charging pile state information; and determining the vehicle occupancy state of the target parking space according to the parking-in state, the electrical state and the historical charging records. According to the geographic fence of the parking space, the charging pile state information, the vehicle state information and the historical charging records, the occupancy state of the parking space is comprehensively determined, the accuracy of the occupancy determination is improved, no additional hardware device needs to be deployed, the application cost is controlled, the technical effects of optimizing the utilization of charging parking space resources, improving the charging service experience and the operation efficiency are achieved.

Description

Technical Field

[0001] This application relates to the field of parking space recognition technology, and more specifically, to a vehicle occupancy recognition method, recognition device, electronic device and storage medium in the field of parking space recognition. Background Technology

[0002] With the popularization of new energy vehicles, the demand for public charging stations continues to increase. However, the phenomenon of gasoline vehicles occupying charging spaces is quite common, which can easily cause new energy vehicle owners to be unable to charge after arriving at the charging station, wasting travel time and seriously reducing the charging experience.

[0003] In related technologies, external hardware such as cameras, ground locks, and geomagnetic detectors are used to achieve occupancy recognition. However, this method is not only costly to deploy and wire, but also difficult to maintain later, and it is hard to adapt to scenarios where hardware installation is limited. Summary of the Invention

[0004] This application provides a vehicle occupancy identification method, identification device, electronic device, and storage medium. The method comprehensively determines the occupancy status of a parking space based on the geographic fence of the parking space, the status information of the charging pile, the status information of the vehicle, and historical charging records. This improves the accuracy of occupancy identification and eliminates the need for additional identification equipment deployment, which helps control application costs and achieves the technical effects of optimizing charging parking space resources and improving the charging service experience and operational efficiency.

[0005] Firstly, a vehicle occupancy identification method is provided, which is applied to a target parking space where a charging pile is configured. The method includes: determining the geofence of the target parking space and obtaining the status information of the charging pile of the target parking space, as well as the status information and historical charging records of the corresponding vehicle; determining the vehicle's parking status based on the geofence and the vehicle's status information; determining the electrical status of the charging pile based on the charging pile status information; and determining the vehicle occupancy status of the target parking space based on the parking status, electrical status, and historical charging records.

[0006] According to the vehicle occupancy identification method of this application embodiment, during the vehicle occupancy identification process, the target parking space equipped with charging piles is continuously monitored. First, the geofence of the target parking space is determined, and the status information of the charging pile, the corresponding vehicle status information, and historical charging records are obtained. Then, the vehicle's parking status is determined based on the obtained geofence and vehicle status information. Simultaneously, the electrical status of the charging pile is determined based on the obtained charging pile status information. Finally, the vehicle occupancy status of the target parking space is determined based on the parking space's geofence, charging pile status information, vehicle status information, and historical charging records. Therefore, this method comprehensively determines the parking space occupancy status based on the parking space's geofence, charging pile status information, vehicle status information, and historical charging records, improving the accuracy of occupancy determination. Furthermore, it eliminates the need for additional identification equipment deployment, helping to control application costs and achieving the technical effects of optimizing the utilization of charging parking space resources and improving the charging service experience and operational efficiency.

[0007] In conjunction with the first aspect, in some possible implementation methods, determining the geofence of the target parking space includes: constructing a baseline fence based on the coordinates of the target parking space; collecting the actual contour information of the target parking space, and correcting the baseline fence based on the actual contour information to obtain the geofence.

[0008] By first constructing a baseline fence and then modifying and optimizing it based on the actual contour, the geofence is made to fit precisely with the actual physical parking space boundary, overcoming the spatial matching deviation problem and providing an accurate and reliable spatial benchmark for subsequent occupancy determination.

[0009] In combination with the first aspect and the above implementation methods, in some possible implementation methods, the vehicle occupancy identification method further includes: setting an isolation buffer zone for the geofence when the distance between the target parking space and the adjacent parking space is less than a preset distance threshold, wherein the isolation buffer zone represents the invalid vehicle identification area.

[0010] By setting up an isolation buffer zone when the distance between parking spaces is small, the spatial recognition range of the target parking space and the adjacent parking spaces can be isolated and divided, avoiding positioning errors when crossing the fence in dense parking spaces, improving spatial differentiation ability, and reducing neighbor interference for subsequent occupancy status determination.

[0011] In conjunction with the first aspect, in some possible implementations, the vehicle's state information includes positioning information, vehicle speed information, and heading angle information. The vehicle's parking status is determined based on the geofence and the vehicle's state information, including: determining the relative positional relationship between the vehicle and the target parking space based on the geofence and positioning information; determining the vehicle's stationary determination result based on the vehicle speed information; determining the vehicle's attitude determination result based on the heading angle information and the orientation marker of the target parking space; and determining the vehicle's parking status based on the relative positional relationship, the stationary determination result, and the attitude determination result.

[0012] By combining multi-dimensional vehicle status information and geofencing to determine parking space occupancy status, the system reduces misidentification caused by relying on a single piece of information, improves the reliability of vehicle parking space occupancy status determination, and provides accurate parking space occupancy status determination for subsequent parking space occupancy status determination.

[0013] Combining the first aspect and the above implementation methods, in some possible implementation methods, the vehicle occupancy status of the target parking space is determined based on the parking status, electrical status, and historical charging records, including: determining the geofence parking score and the vehicle stationary time score based on the parking status; determining the charging pile idle status score based on the electrical status; determining the vehicle's score for having no recent charging records based on historical charging records; and determining the vehicle occupancy status of the target parking space based on the geofence parking score, the vehicle stationary time score, the charging pile idle status score, and the vehicle's score for having no recent charging records.

[0014] By using multi-dimensional scoring to quantify the vehicle occupancy status, we can avoid errors caused by bias in single-dimensional information, improve the anti-interference ability of occupancy recognition, and make the occupancy status judgment results more objective and reliable.

[0015] Combining the first aspect and the above implementation methods, in some possible implementation methods, the vehicle occupancy status of the target parking space is determined based on the geofence entry score, vehicle stationary time score, charging pile idle status score, and vehicle no recent charging record score. This includes: weighting and fusing the geofence entry score, vehicle stationary time score, charging pile idle status score, and vehicle no recent charging record score to obtain the target total score; determining that the target parking space is in a vehicle occupancy status when the target total score exceeds a preset score threshold; and determining that the target parking space is in a non-vehicle occupancy status when the target total score is less than or equal to the preset score threshold.

[0016] The system performs weighted fusion of scores from multiple dimensions and compares them with preset score thresholds to output the parking space occupancy results. This allows for adjustable weights for each evidence dimension, improving the controllability and robustness of the judgment process and making the quantitative judgment results of parking space occupancy status more stable and accurate.

[0017] In combination with the first aspect and the above implementation methods, in some possible implementation methods, the vehicle occupancy identification method further includes: determining the actual state of the target parking space based on the vehicle occupancy status and electrical status; and updating the actual map label of the target parking space based on the actual state.

[0018] The actual status of a parking space is obtained based on its occupancy and electrical status, and the map markers are updated accordingly. This enables the real-time mapping of parking space usage to the map, facilitating accurate parking information for users, reducing unnecessary trips, and improving the user experience of charging services.

[0019] Secondly, a vehicle occupancy identification device is provided, which is applied to a target parking space where a charging pile is configured. The device includes: a first determining module for determining the geofence of the target parking space; an acquiring module for acquiring the charging pile status information of the target parking space, as well as the corresponding vehicle status information and historical charging records; a second determining module for determining the vehicle's parking status based on the geofence and the vehicle's status information, and determining the electrical status of the charging pile based on the charging pile status information; and an occupancy identification module for determining the vehicle's occupancy status in the target parking space based on the parking status, electrical status, and historical charging records.

[0020] Thirdly, an electronic device is provided, comprising: a memory for storing a computer program; and a processor for executing the computer program to implement the steps of the vehicle occupancy recognition method as described in the first aspect or any possible implementation thereof.

[0021] Fourthly, a computer-readable storage medium is provided, characterized in that the computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, it implements the steps of the vehicle occupancy recognition method as described in the first aspect or any possible implementation of the first aspect. Attached Figure Description

[0022] Figure 1 This is a schematic flowchart of a vehicle occupancy identification method provided in an embodiment of this application.

[0023] Figure 2 This is a schematic flowchart illustrating a vehicle occupancy recognition method provided in a specific embodiment of this application.

[0024] Figure 3 This is a schematic diagram of the structure of a vehicle occupancy recognition device provided in an embodiment of this application.

[0025] Figure 4 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0026] The technical solutions in this application will be clearly and thoroughly described below with reference to the accompanying drawings. In the description of the embodiments of this application, unless otherwise stated, " / " means "or," for example, A / B can mean A or B. "And / or" in the text is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Furthermore, in the description of the embodiments of this application, "multiple" refers to two or more than two.

[0027] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature.

[0028] With the increasing popularity of new energy vehicles, the demand for public charging stations is growing. However, in public charging scenarios, gasoline vehicles commonly occupy charging spaces, causing new energy vehicle users to be unable to charge after arriving at the station, wasting time and travel, and seriously affecting the user charging experience. Market research and user feedback have revealed that the core pain point of poor user charging experience in existing public charging scenarios is: finding that the parking space is occupied by a gasoline vehicle after arriving at the station.

[0029] Existing technical solutions to this problem have significant flaws and cannot meet practical application needs. Most related technologies rely on additional hardware to determine whether a gasoline vehicle is occupying a charging space. This involves combining image recognition with charging parameters to determine the vehicle's occupancy status, often requiring the deployment of visual hardware such as surveillance cameras. Other solutions use hardware such as ground locks and geomagnetic detectors to trigger the determination of parking space occupancy and then synchronize this information to a relevant platform. These hardware-dependent solutions are costly to deploy and difficult to maintain, requiring wiring and equipment installation. They are unsuitable for older residential areas or temporary charging points where additional hardware cannot be installed. Furthermore, the hardware is prone to damage and susceptible to environmental factors (such as camera obstruction or ground lock malfunction), leading to poor stability in the determination. In addition, the judgment logic of these solutions is simplistic, merely integrating the electrical status of the charging pile with coarse positioning data. This fails to effectively eliminate interference scenarios such as fully charged electric vehicles not moved, temporary parking, or vehicles waiting to be charged, resulting in low accuracy in determining gasoline vehicle occupancy and users still experiencing problems charging at charging stations.

[0030] To address at least one of the aforementioned technical problems, this application proposes a vehicle occupancy identification method. During the vehicle occupancy identification process, the target parking space equipped with a charging pile is continuously monitored. First, the geofence of the target parking space is determined, and the status information of the charging pile, as well as the corresponding vehicle status information and historical charging records, are obtained. Then, the vehicle's parking status is determined based on the obtained geofence and vehicle status information. Simultaneously, the electrical status of the charging pile is determined based on the obtained charging pile status information. Finally, the vehicle occupancy status of the target parking space is determined based on the parking status, electrical status, and historical charging records. Therefore, this method comprehensively determines the parking space occupancy status based on the geofence, charging pile status information, vehicle status information, and historical charging records, improving the accuracy of occupancy determination. Furthermore, it requires no additional hardware equipment, making deployment convenient, which helps control application costs and expands the scope of application. This achieves the technical effect of optimizing the utilization of charging parking space resources and improving the charging service experience and operational efficiency.

[0031] In some embodiments of this application, the vehicle occupancy identification method is applied to target parking spaces configured with charging piles. These target parking spaces include charging parking spaces set up in various public charging scenarios. By reusing existing reported data from charging piles and vehicles, and without relying on additional hardware devices, the method is used to identify the occupancy status of charging parking spaces by gasoline vehicles.

[0032] Figure 1 This is a schematic flowchart of a vehicle occupancy identification method provided in an embodiment of this application.

[0033] For example, such as Figure 1 As shown, the vehicle occupancy detection method includes the following steps: S101. Determine the geofence of the target parking space and obtain the status information of the charging piles in the target parking space, as well as the status information and historical charging records of the corresponding vehicles.

[0034] Specifically, the geofence of the target parking space can be pre-defined, the installation location information of the charging pile can be obtained, the parking space distribution information can be obtained based on the high-precision map, and the national standard parking space size can be used as a benchmark to initially divide each parking space and construct quadrilateral geofences for each. At the same time, a corresponding mapping relationship can be constructed to bind the geofence information of each parking space with the charging pile number, and finally the target parking space geofence used for vehicle parking determination can be obtained.

[0035] During the process of identifying the target parking space, the geofence information is determined based on the charging pile number. At the same time, the charging pile status information is collected. The charging pile status information can be reported to the back-end service platform through the charging network communication link. The charging pile status information can include operating data such as charging pile electrical parameters, plug-in signal, and charging and discharging status.

[0036] The system identifies the vehicle corresponding to the target parking space as the vehicle parked within that space. The vehicle's status information and historical charging records can be obtained through communication between the charging station and the vehicle. Additionally, the relative positional relationship between the vehicle and the target parking space can be identified based on the vehicle's real-time reported location information and the geofence of the target parking space to determine if it is the correct vehicle for that space. Then, the vehicle's status information and historical charging records are obtained through communication with the vehicle. Vehicle status information may include operating status such as vehicle speed, or it may include vehicle location information, with no specific limitations. Historical charging records may include vehicle identification, charging station number, charging start time, charging end time, charging duration, and charging amount. By retrieving these historical charging records, it is possible to identify whether the vehicle has recently engaged in charging activities, facilitating the differentiation of interference scenarios.

[0037] The acquisition of the above information does not require the deployment of additional hardware such as monitoring, ground locks, and geomagnetic sensors. It only utilizes existing electrical data of charging piles, vehicle positioning data, and map platforms, which greatly reduces deployment and maintenance costs. It is suitable for various public charging scenarios such as old residential areas and temporary charging points, and can be quickly promoted.

[0038] S102. Determine the vehicle's parking status based on the geofence and vehicle status information.

[0039] Specifically, the geofence information for parking spaces can include: the coordinates of the center point of the geofence, its length, width, and other information. At the same time, the determination of vehicle entry is based on the location information reported by the vehicle. For example, the center coordinates of the geofence are matched with the center coordinates of the vehicle, and an corresponding error range is set. If the center coordinates of the vehicle fall within the range of the center coordinates of the geofence, then the vehicle is determined to be in the parking space.

[0040] S103. Determine the electrical status of the charging pile based on the charging pile status information.

[0041] Specifically, the charging pile status information may include the charging pile's electrical status data and operational status data. The electrical status of the charging pile is obtained by parsing this data, and it indicates whether the charging pile is idle and ready to charge. Taking the charging pile status information, which includes electrical parameters, order status, connection status, and device status, as an example, the specific conditions for determining whether a charging pile is in an idle and ready-to-charge state are as follows: 1. Electrical parameters: No charging current output, nor charging voltage output; 2. Order Status: No charging orders have been generated, and there are no charging start records. 3. Connection status: No charging gun connection signal, no vehicle BMS (Battery Management System) handshake signal; 4. Equipment status: No fault alarm information, no equipment offline records, and no ongoing maintenance work orders; the equipment is in normal working condition. 5. For interference scenarios that are prone to misidentification, such as charging guns being plugged in but not charging, or charging guns not being unplugged after completion, it is necessary to collect additional correlation data between the charging gun connection status and the charging completion record for subsequent interference elimination and to avoid misjudgment.

[0042] If the collected charging pile status information meets all of the above conditions, the charging pile is considered to be in an idle and charging state; otherwise, the vehicle is considered not to be in an idle and charging state.

[0043] This embodiment uses charging pile status information to confirm whether there is currently no electric vehicle charging at the charging pile or no electric vehicle preparing to charge, providing reliable support for the subsequent fusion judgment of gasoline vehicle occupancy.

[0044] S104. Determine the vehicle occupancy status of the target parking space based on the parking status, electrical status, and historical charging records.

[0045] Specifically, based on the obtained parking status and electrical status, combined with the vehicle's historical charging records and spatiotemporal constraints, a multi-layered progressive timing judgment logic is constructed to complete the condition verification layer by layer, thereby realizing the identification of the vehicle's occupancy status in the target parking space.

[0046] For example, the system first performs a basic judgment step, which jointly verifies the vehicle's dwell time and the electrical status of the charging pile. If both conditions are met simultaneously, such as the vehicle being fully in place and the stationary dwell time exceeding a preset threshold, and the charging pile being in an idle state, the system determines that the vehicle is suspected of being occupied by a gasoline vehicle. If the above two conditions cannot be met simultaneously, the system directly determines that there is no suspected gasoline vehicle occupying the charging pile.

[0047] Next, the interference elimination process begins. The historical charging records of the vehicle stored in the background are retrieved for verification. The charging events within the last 30 minutes are checked. If there is a charging completion record or a charging reservation record for the vehicle within the last 30 minutes, the interference scenario of the electric vehicle being fully charged but not moved or waiting to be charged is eliminated. At this time, the suspected gasoline vehicle occupying the space is removed.

[0048] Finally, in the precise judgment stage, if the vehicle has no charging behavior record and has not established BMS handshake or other communication interaction with the charging pile of the current target parking space, under the premise that interference has been eliminated and no interference scenario has been triggered, then it is finally determined that the charging parking space is occupied by a gasoline vehicle or a non-charging vehicle.

[0049] In some embodiments of this application, determining the geofence of a target parking space includes: constructing a reference fence based on the coordinates of the target parking space; collecting the actual contour information of the target parking space; and correcting the reference fence based on the actual contour information to obtain the geofence.

[0050] Specifically, the first step is to construct a baseline fence based on the coordinates of the target parking space. For example, based on the coordinates of the target parking space, an initial baseline fence is constructed using the national standard size of 2.5m × 5m for public charging parking spaces as a reference. This baseline fence serves as the initial template for the parking space fence, generating a rectangular fence to initially define the area where the parking space is located.

[0051] Next, staff members carry positioning terminals, such as mobile phones or handheld GNSS (Global Navigation Satellite System) data acquisition devices, to each inflection point of the ground markings of the physical parking space. They record the coordinates of each inflection point in sequence, and then string all the coordinates together to obtain the electronic coordinates of the inflection points of the parking space's outer contour. This yields the actual boundary contour information of the target parking space, which can reflect whether the parking space is a standard rectangle or an irregularly shaped parking space formed by site constraints. The data acquisition process does not require the deployment of physical sensing hardware.

[0052] Furthermore, the baseline fence is corrected based on the actual contour information to obtain the geofence. The baseline fence is adjusted and reshaped using the actual contour information of the parking space collected. For standard rectangular parking spaces, the fence boundary is regularized. For irregular parking spaces, the polygon boundary is reconstructed according to the actual inflection point coordinates. This ensures that the generated fence contour strictly matches the actual contour of the corresponding physical charging parking space, resulting in an independent polygonal precise geofence at the single parking space level. This geofence is essentially the parking space boundary contour outlined by electronic coordinates.

[0053] After the geofence is built, each corrected and accurate geofence is bound to a unique charging pile number and a unique parking space ID (Identifier), forming a mapping relationship between parking space, fence, and charging pile, ensuring that the location determination of a single parking space is independent and accurate.

[0054] By first constructing a baseline fence and then modifying and optimizing it based on the actual contour, the geofence is made to fit precisely with the actual physical parking space boundary, overcoming the spatial matching deviation problem and providing an accurate and reliable spatial benchmark for subsequent occupancy determination.

[0055] In some embodiments of this application, the vehicle occupancy identification method further includes: setting an isolation buffer zone for a geofence when the distance between the target parking space and the adjacent parking space is less than a preset distance threshold, wherein the isolation buffer zone represents an invalid vehicle identification area.

[0056] In other words, for scenarios with densely packed charging stations, such as commercial areas and residential communities, isolation buffer zones are set up to avoid misidentification of multiple fences caused by overlapping geofences of adjacent parking spaces and positioning errors. Specifically, a distance threshold between adjacent parking spaces can be preset. Then, the fence distance between the target parking space and its surrounding adjacent parking spaces is calculated and compared with the preset distance threshold. When the distance between adjacent parking spaces is less than the preset distance threshold, the current area is determined to be a dense charging station cluster prone to interference, and an isolation buffer zone needs to be added to optimize recognition accuracy. The preset distance threshold can be calibrated according to the actual situation and is used to determine whether the distance between adjacent parking spaces meets the requirements of a dense charging station cluster.

[0057] When the distance between the target parking space and the adjacent parking space is less than the preset distance threshold, it is considered to be in a dense pile cluster scenario. At this time, an isolation buffer with a width of 0.5m to 1m can be set between the geofences of two adjacent parking spaces. The width of the isolation buffer is evenly divided between the geofence buffers on both sides. For example, when the isolation buffer is 1m, each of the two adjacent parking spaces has an isolation buffer of 0.5m. The overall isolation buffer completely covers the error interference range on both sides.

[0058] The isolation buffer zone represents the invalid vehicle identification area. When determining vehicle placement, in special scenarios where part of the vehicle's body coordinates fall into the isolation buffer zone, the system automatically ignores the coordinate data within the buffer zone and only makes a judgment based on the landing point of the vehicle's main body coordinates. For example, if the main body of the vehicle falls into geofence A, but part of the area falls into the isolation buffer zone of geofence B, then the vehicle is considered to be in parking space A.

[0059] By adding an isolation buffer zone, the problem of chaotic parking space determination in dense pile cluster scenarios is effectively solved, interference from adjacent parking spaces is eliminated, and the accuracy of vehicle occupancy determination in scenarios with densely arranged multiple parking spaces is further improved.

[0060] In some embodiments of this application, the vehicle's status information includes positioning information, vehicle speed information, and heading angle information. Determining the vehicle's parking status based on the geofence and the vehicle's status information includes: determining the relative positional relationship between the vehicle and the target parking space based on the geofence and positioning information; determining the vehicle's stationary determination result based on the vehicle speed information; determining the vehicle's attitude determination result based on the heading angle information and the orientation indicator of the target parking space; and determining the vehicle's parking status based on the relative positional relationship, the stationary determination result, and the attitude determination result.

[0061] Specifically, vehicle status information is reported to the cloud in real time via the vehicle's onboard GPS (Global Positioning System) and built-in sensors. The vehicle's status information, including location information, speed information, and heading angle information, is continuously obtained by calling the cloud interface.

[0062] First, taking the vehicle's location information as the center point coordinates as an example, the vehicle's corresponding model file is queried to retrieve the vehicle's overall length and width parameters. Using the received vehicle center coordinates as the center point, the vehicle's front direction is the local positive X-axis direction, and the left side of the vehicle is the local positive Y-axis direction. Under this local coordinate system, the positions of the four corners of the vehicle are calculated. A two-dimensional rotation transformation is performed based on the heading angle to align the vehicle's attitude to the world coordinate system, eliminating angular deviations caused by the vehicle's own orientation. The current vehicle outline information is formed by the four corner points. Next, the coordinate information of the target parking space's geofence is matched with the vehicle outline information to determine the relative positional relationship between the vehicle and the target parking space. For example, the ratio of the overlap area between the vehicle outline and the target parking space's geofence to the area of ​​the target parking space's geofence is calculated, and the relative positional relationship between the vehicle and the target parking space is determined based on this ratio. For example, firstly, based on the coordinate information of the geofence of the target parking space and the vehicle outline information, it is identified whether the vehicle is completely within the geofence of the target parking space, or the vehicle partially crosses out of the geofence of the target parking space, or the vehicle is outside the geofence of the target parking space. In the case where the vehicle partially crosses out of the geofence of the target parking space, the isolation buffer rule is combined. If the coordinates of part of the vehicle body fall into the isolation buffer between parking spaces, the coordinate influence of the buffer area is ignored, and the overlap ratio of the main outline of the vehicle body is used as the judgment basis to completely determine the relative positional relationship between the vehicle and the target parking space.

[0063] Simultaneously, the system determines whether a vehicle is stationary based on its speed information. For example, if a vehicle is detected to have reached zero speed and remain stationary, the system further calculates the duration of its continuous stationary position and compares the actual stationary position with a preset time threshold of 3-5 minutes. Only when the duration of the vehicle's continuous stationary position exceeds the preset threshold is the vehicle considered stationary, thus filtering out non-occupied scenarios such as temporary parking, reversing, and U-turns.

[0064] By calling the pre-stored orientation identifiers corresponding to each target parking space through the charging pile number, the heading angle data reported by the vehicle is compared with the orientation identifier to verify whether the vehicle is parked in the correct orientation. If the vehicle's heading angle is consistent with the orientation of the parking space, the vehicle's parking posture is determined to be compliant, thereby eliminating non-standard parking scenarios such as vehicles parking horizontally or at an angle, and ensuring accurate determination of parking status.

[0065] Finally, by combining the relative positional relationship between the vehicle and the parking space, the results of determining the vehicle's stationary state, and the results of determining the vehicle's parking posture, a multi-dimensional fusion judgment is made to accurately determine the vehicle's valid parking status. This eliminates various interference scenarios such as abnormal parking, short-term stops, and non-standard parking, providing a reliable preliminary judgment basis for the accurate identification of the vehicle's parking space occupancy status in the future.

[0066] In some embodiments of this application, determining the vehicle occupancy status of a target parking space based on the parking status, electrical status, and historical charging records includes: determining a geofence parking score and a vehicle stationary time score based on the parking status; determining a charging pile idle status score based on the electrical status; determining a score for the vehicle having no recent charging records based on historical charging records; and determining the vehicle occupancy status of the target parking space based on the geofence parking score, the vehicle stationary time score, the charging pile idle status score, and the score for the vehicle having no recent charging records.

[0067] Specifically, based on the vehicle's parking status and the charging pile's electrical status, and combined with the vehicle's historical charging records, scores for each dimension are calculated. Each dimension is scored using a segmented threshold, with each item ranging from 0 to 1.

[0068] The geofence placement score is used to evaluate the vehicle's placement accuracy. Specifically, it is determined based on the relative position information between the vehicle and the target parking space, and the vehicle's attitude assessment results. For example, the position score is calculated based on the percentage overlap between the vehicle's outline and the geofence of the target parking space. A pre-set upper and lower threshold for this percentage can be used. When the overlap percentage is greater than or equal to the upper threshold, the geofence placement score is 1; when the overlap percentage is between the upper and lower thresholds, the geofence placement score is linearly mapped to the overlap percentage, taking a value between 0 and 1; when the overlap percentage is below the lower threshold, the geofence placement score is 0. Simultaneously, an attitude score is calculated based on the vehicle's attitude assessment results, i.e., the degree of directional matching between the vehicle's heading angle and the orientation marker. The geofence placement score is calculated by combining the position score and the attitude score. Alternatively, if the vehicle is determined to be within the target parking space based on its parking status (including cases where the vehicle is completely within the target parking space and cases where the vehicle is partially within the isolation area of ​​an adjacent parking space) and the vehicle's parking posture is compliant, the vehicle is considered to have successfully entered the parking space, and the geofence entry score is 1; otherwise, if the vehicle is considered not to have successfully entered the parking space, the geofence entry score is 0.

[0069] The vehicle stationary duration score is used to determine the duration of the vehicle's stationary state. For example, the actual stationary duration of the vehicle can be compared with a preset time threshold. When the actual stationary duration is greater than or equal to the preset time threshold, the vehicle stationary duration score is 1; when the actual stationary duration is less than the preset time threshold, the vehicle stationary duration score is 0.

[0070] The system identifies whether a charging pile is idle based on its electrical status. For example, if there is no charging power output, no BMS handshake signal, no charging order, and the equipment is not faulty or offline, the target parking space is considered to be in an idle state, and the charging pile idle state score is 1; otherwise, the charging pile is considered not to be idle, and the charging pile idle state score is 0.

[0071] Based on the vehicle's historical charging records, assess whether there are situations such as "the vehicle is fully charged but not moved" or "the charging gun is plugged in and waiting to be charged". For example, focus on examining the vehicle's charging completion record and reservation record within the past 30-minute time window. If the vehicle has no charging completion record or no charging reservation record in the past 30 minutes, the vehicle has no recent charging record and scores 1; otherwise, the vehicle has no recent charging record and scores 0.

[0072] The final score is calculated based on the geofence entry score, vehicle stationary time score, charging pile idle status score, and vehicle no recent charging record score. For example, the final score is calculated by summation. The final score is compared with a preset total score threshold. If the final score is greater than the preset total score threshold, it is determined that the vehicle is occupied by a gasoline vehicle; otherwise, it is considered that the vehicle is not occupied by a gasoline vehicle, so as to obtain the vehicle occupancy status of the target parking space.

[0073] This embodiment uses a multi-dimensional scoring method to quantify and evaluate the vehicle occupancy status, avoiding errors caused by single-dimensional information bias, improving the anti-interference capability of occupancy recognition, and making the occupancy status judgment result more objective and reliable.

[0074] In some embodiments of this application, the vehicle occupancy status of a target parking space is determined based on the geofence entry score, vehicle stationary time score, charging pile idle status score, and vehicle no recent charging record score. This includes: weighting and fusing the geofence entry score, vehicle stationary time score, charging pile idle status score, and vehicle no recent charging record score to obtain a target total score; determining that the target parking space is in a vehicle occupancy status when the target total score exceeds a preset score threshold; and determining that the target parking space is in a non-vehicle occupancy status when the target total score is less than or equal to the preset score threshold.

[0075] Specifically, confidence weights are configured for different distribution dimensions. Each weight is pre-set based on the importance of the data in each dimension. The weight for the geofence placement score is 0.4, the weight for the vehicle stationary time score is 0.2, the weight for the charging pile idle status score is 0.3, and the weight for the vehicle having no recent charging records is 0.1.

[0076] Next, the score of each dimension is multiplied by its corresponding confidence weight and then summed. The calculation formula is: Target total score = Geofence entry score × 0.4 + Vehicle stationary time score × 0.2 + Charging pile idle status score × 0.3 + Vehicle no recent charging record score × 0.1. The weighted target total score is calculated according to the above formula.

[0077] The calculated target total score is compared with a preset score threshold, which can be set according to the actual situation. For example, if the preset score threshold is set to 0.7, the target parking space is determined to be occupied by a vehicle when the target total score is greater than 0.7; and the target parking space is determined to be in a non-occupied state when the target total score is less than or equal to 0.7.

[0078] This embodiment adopts a weighted decision fusion strategy. When a single data source has a slight error (such as a brief GPS drift), it will not affect the overall judgment result, thereby improving the controllability and robustness of the judgment process and making the quantitative judgment result of parking space occupancy status more stable and accurate.

[0079] In some embodiments of this application, the vehicle occupancy identification method further includes: determining the actual state of the target parking space based on the vehicle occupancy status and electrical status; and updating the actual map identifier of the target parking space based on the actual state.

[0080] Specifically, the status of the target parking space is divided into four actual states: available, charging, occupied by a gasoline vehicle, and faulty. The charging state is determined based on the electrical status of the charging pile at the target parking space, such as: the charging pile is detecting charging power output, there is a charging order in the charging pile operator's backend, and a vehicle is in the parking space. The occupied state is determined based on the above vehicle occupancy results. The faulty state is determined by the charging pile reporting a hardware fault signal or by an abnormal timeout in the charging pile's data communication. The available state is when no vehicle is detected in the geofence and the conditions for determining the charging, gasoline vehicle occupied, or faulty state are not met.

[0081] Next, the real-time status of the parking spaces is pushed to the map server through a dedicated data interface, realizing a complete business loop of "occupancy determination - map display - experience optimization". Through multi-dimensional optimization strategies, the charging parking spaces can be visualized and intelligently managed, such as: visualization display, intelligent filtering, dynamic early warning and route replanning, and data accumulation functions.

[0082] The visualization involves the map platform assigning unique icons to each charging parking space, using different colors to distinguish four parking space statuses: green for available, blue for charging, red for occupied by gasoline vehicles, and gray for malfunction. Users can click on the parking space icon to view detailed information such as the start time of occupancy, the estimated probability of vacancy, the geographic boundary of the parking space, the number of times the space has been occupied in the past 7 days, and the duration of each occupancy.

[0083] The intelligent filtering means that when a user searches for charging stations on the map platform, the map system will filter out parking spaces occupied by gasoline vehicles and those that are faulty by default, and will prioritize pushing the nearest, normally available, and less occupied charging spaces to the user.

[0084] Dynamic warnings and route replanning mean that as the user navigates to the target charging parking space, the map platform monitors the dynamic changes in the parking space status in real time. If the target parking space is detected to be occupied by a gasoline car, an occupancy warning will immediately pop up, and the system will automatically replan the driving route for the user and recommend the nearest available charging parking space, without requiring manual operation from the user.

[0085] Data accumulation and iterative optimization involve linking the map platform with the charging pile operator's backend to continuously accumulate various parking space status data and gasoline vehicle occupancy data, generating high-frequency occupancy location heatmaps, providing data support for subsequent parking space geofence calibration and charging pile location optimization.

[0086] As a result, users can filter available parking spaces in advance via the map, receive parking space occupancy warnings during navigation, and automatically replan their routes, solving the core pain point of "unable to charge after reaching a charging station," reducing unnecessary trips, and improving user satisfaction; at the same time, the parking space occupancy details displayed on the map can help users make quick decisions and further optimize the experience.

[0087] As one embodiment of this application, such as Figure 2 As shown, this vehicle occupancy detection method is applied to the system to detect the occupancy status of target parking spaces in real time. The specific scheme is as follows: S201, Process Startup: System initialization, complete the construction of precise geofences for single parking spaces (including on-site coordinate calibration, isolation buffer zone setting, and occlusion area calibration), and bind each fence to the corresponding charging pile number and parking space ID; S202, Data Acquisition: Synchronously collect vehicle positioning data (GPS / BeiDou), vehicle speed data, heading angle data, as well as real-time electrical status data of charging piles (current, voltage, orders, connection signals, etc.) and vehicle historical charging records; S203, Vehicle Positioning Determination: Determine whether the vehicle has completely entered the precise geofence, whether the vehicle speed is 0 and has been stationary for more than 3-5 minutes, and whether it is in the correct orientation. If yes, proceed to the next step; otherwise, return to the data collection stage for continuous monitoring. S204 Charging Pile Status Determination: Determine whether the charging pile is in an idle state with no current, no orders, no connection, and no fault. If yes, proceed to the next step; otherwise, determine it as "non-fuel vehicle occupying the space" and update the map status to "charging / fault". S205. Interference scenario elimination: Check if the vehicle has a charging completion record or charging reservation record in the past 30 minutes. If so, it is determined as "electric vehicle fully charged and not moved / plugged in and waiting to charge"; at the same time, check if the charging pile has a charging gun connection signal. If there is a connection signal but no current or order, it is determined as "not charging but plugged in". In both cases, the determination of gasoline vehicle occupying the space is excluded. If not, proceed to the next step. S206. Determination of "Occupied by Gasoline Vehicle": A weighted decision fusion (or rule-based reasoning fusion) strategy is adopted, combined with multi-source data for comprehensive determination. If the weighted score is >0.7 (or all rules are met), it is determined as "Occupied by Gasoline Vehicle", otherwise it returns to the data collection stage. S207, Map Linkage Optimization: The location determination results (idle / available / charging / gasoline vehicle occupying / fault) are pushed to the map server in real time to achieve visualization, intelligent filtering, dynamic warning and route replanning; S208. Data Accumulation and Optimization: The background system accumulates the occupancy data and generates a high-frequency occupancy heat map, which is used for subsequent fence calibration and charging pile location optimization to form a closed-loop iteration. S209, Process End: The vehicle leaves the parking space (location is off the fence, vehicle speed > 0), the system updates the parking space status to "available", returns to the data collection stage, and continues to monitor the next vehicle entry.

[0088] This embodiment is based on precise geofencing for single parking spaces. It achieves accurate occupancy determination through multi-source data fusion (including charging gun status collection), focusing on eliminating interfering scenarios such as electric vehicles that are fully charged but not moved, or charging guns being plugged in but not charging. Furthermore, it optimizes the user charging experience through map integration. The entire process is hardware-independent, and the robustness of the determination is improved through interference elimination and collaborative verification, forming a complete closed loop of "construction-monitoring-determination-optimization-iteration". This embodiment has the following technical effects: 1. Lower cost and easier deployment: No additional hardware such as monitoring, ground locks, and geomagnetic sensors are required. It only utilizes existing charging pile electrical data, vehicle positioning data, and map platform, which greatly reduces deployment and maintenance costs. It is suitable for various public charging scenarios such as old residential areas and temporary charging points, and can be quickly promoted.

[0089] 2. Higher accuracy in parking space determination: By using precise geofencing for single parking spaces (matching parking space outlines and calibrating GPS drift), combined with multi-source data fusion determination (weighted decision-making and multi-pile collaboration), it effectively eliminates scenarios such as interference from adjacent parking spaces, GPS drift, temporary parking, and electric vehicles that are fully charged but not moved. The accuracy rate of determination is much higher than that of existing coarse fencing solutions.

[0090] 3. Significantly improved user charging experience: A complete closed-loop optimization is formed, allowing users to filter available parking spaces in advance via the map, receive parking space occupancy warnings during navigation and automatically replan the route, completely solving the core pain point of "unable to charge after arriving at the charging station", reducing unnecessary trips and improving user satisfaction; at the same time, the parking space occupancy details displayed on the map can help users make quick decisions, further optimizing the experience.

[0091] 4. Enhanced robustness: Employing a weighted decision fusion strategy, a slight error in a single data source (such as a brief GPS drift) will not affect the overall judgment result; there are specialized optimization schemes for complex scenarios such as dense pile groups and underground parking garages, making it more adaptable to different application environments.

[0092] 5. Avoiding existing patent risks: Existing hardware-dependent solutions are mostly protected by related patents. This invention avoids hardware-related patent restrictions through an innovative design that is hardware-free, precise fencing, and multi-source fusion, while forming its own core technology barrier.

[0093] Therefore, this method can be widely applied to various public charging scenarios such as residential areas, business districts, office buildings, and highway service areas, improving the success rate of users charging at charging stations, reducing users' unnecessary trips, and eliminating the need for hardware installation, thus reducing the deployment cost per location and eliminating subsequent hardware maintenance costs, which can also improve the operational efficiency of charging stations.

[0094] Figure 3 This is a schematic diagram of the structure of a vehicle occupancy recognition device provided in an embodiment of this application.

[0095] For example, such as Figure 3 As shown, the vehicle occupancy identification device is applied to the target parking space where charging piles are configured. The vehicle occupancy identification device 300 may include: a first determining module 301, an acquiring module 302, a second determining module 303, and an occupancy identification module 304.

[0096] The first determining module 301 is used to determine the geofence of the target parking space; the acquiring module 302 is used to acquire the charging pile status information of the target parking space, as well as the corresponding vehicle status information and historical charging records; the second determining module 303 is used to determine the vehicle's parking status based on the geofence and vehicle status information, and to determine the electrical status of the charging pile based on the charging pile status information; the occupancy identification module 304 is used to determine the vehicle's occupancy status of the target parking space based on the parking status, electrical status, and historical charging records.

[0097] According to one embodiment of this application, the first determining module 301 determines the geofence of the target parking space, specifically used for: constructing a reference fence based on the coordinate position of the target parking space; collecting the actual contour information of the target parking space, and correcting the reference fence based on the actual contour information to obtain the geofence.

[0098] According to one embodiment of this application, the first determining module 301 is further configured to: set an isolation buffer zone for the geofence when the distance between the target parking space and the adjacent parking space is less than a preset distance threshold, wherein the isolation buffer zone represents an invalid vehicle identification area.

[0099] According to one embodiment of this application, the vehicle's status information includes positioning information, vehicle speed information, and heading angle information. The second determining module 303 determines the vehicle's parking status based on the geofence and the vehicle's status information. Specifically, it is used to: determine the relative positional relationship between the vehicle and the target parking space based on the geofence and positioning information; determine the vehicle's stationary determination result based on the vehicle speed information; determine the vehicle's attitude determination result based on the heading angle information and the orientation indicator of the target parking space; and determine the vehicle's parking status based on the relative positional relationship, the stationary determination result, and the attitude determination result.

[0100] According to one embodiment of this application, the parking space occupancy identification module 304 determines the vehicle occupancy status of the target parking space based on the parking status, electrical status, and historical charging records. Specifically, it is used to: determine the geofence parking score and the vehicle stationary time score based on the parking status; determine the charging pile idle status score based on the electrical status; determine the vehicle no recent charging record score based on the historical charging records; and determine the vehicle occupancy status of the target parking space based on the geofence parking score, the vehicle stationary time score, the charging pile idle status score, and the vehicle no recent charging record score.

[0101] According to one embodiment of this application, the parking space occupancy identification module 304 determines the vehicle occupancy status of the target parking space based on the geofence entry score, vehicle stationary time score, charging pile idle status score, and vehicle no recent charging record score. Specifically, it is used to: perform weighted fusion of the geofence entry score, vehicle stationary time score, charging pile idle status score, and vehicle no recent charging record score to obtain a target total score; when the target total score exceeds a preset score threshold, it is determined that the target parking space is in a vehicle occupancy status; when the target total score is less than or equal to the preset score threshold, it is determined that the target parking space is in a non-vehicle occupancy status.

[0102] According to one embodiment of this application, the occupancy identification module 304 is further configured to: determine the actual state of the target parking space based on the vehicle occupancy status and electrical status; and update the actual map identifier of the target parking space based on the actual state.

[0103] This application also provides an electronic device 400, please refer to... Figure 4 The electronic device 400 includes a memory 401 and a processor 402. The memory 401 is used to store computer programs, and the processor 402 is used to execute the computer programs stored in the memory 401, so that the vehicle occupancy identification method in any embodiment of this application is implemented during execution.

[0104] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the vehicle occupancy recognition method in any embodiment of this application.

[0105] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0106] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0107] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A method for identifying vehicle occupancy, characterized in that, The method, applied to target parking spaces for configuring charging piles, includes: Determine the geofence of the target parking space, and obtain the charging pile status information of the target parking space, as well as the corresponding vehicle status information and historical charging records; The vehicle's positioning status is determined based on the geofence and the vehicle's status information; The electrical status of the charging pile is determined based on the charging pile status information; The vehicle occupancy status of the target parking space is determined based on the parking status, the electrical status, and the historical charging records.

2. The method according to claim 1, characterized in that, The process of determining the geofence of the target parking space includes: Construct a baseline fence based on the coordinates of the target parking space; The actual contour information of the target parking space is collected, and the reference fence is corrected based on the actual contour information to obtain the geofence.

3. The method according to claim 2, characterized in that, The method further includes: When the distance between the target parking space and the adjacent parking space is less than a preset distance threshold, an isolation buffer zone is set for the geofence, wherein the isolation buffer zone represents an invalid vehicle identification area.

4. The method according to claim 1, characterized in that, The vehicle's status information includes location information, vehicle speed information, and heading angle information. Determining the vehicle's positioning status based on the geofence and the vehicle's status information includes: The relative positional relationship between the vehicle and the target parking space is determined based on the geofence and the location information; The vehicle's stationary determination result is determined based on the vehicle speed information; The attitude determination result of the vehicle is determined based on the heading angle information and the orientation indicator of the target parking space; The vehicle's parking status is determined based on the relative positional relationship, the static determination result, and the attitude determination result.

5. The method according to claim 4, characterized in that, Determining the vehicle occupancy status of the target parking space based on the parking status, the electrical status, and the historical charging records includes: The geofence placement score and vehicle stationary time score are determined based on the placement status. The charging pile idle status score is determined based on the electrical status. Based on the historical charging records, a score is determined for the vehicle having no recent charging records. The vehicle occupancy status of the target parking space is determined based on the geofence entry score, the vehicle stationary time score, the charging pile idle status score, and the vehicle's no recent charging record score.

6. The method according to claim 5, characterized in that, The process of determining the vehicle occupancy status of the target parking space based on the geofence entry score, the vehicle stationary time score, the charging pile idle status score, and the vehicle's lack of recent charging records score includes: The target total score is obtained by weighting and fusing the geofence placement score, the vehicle stationary time score, the charging pile idle state score, and the vehicle no recent charging record score. When the target total score exceeds a preset score threshold, it is determined that the target parking space is occupied by a vehicle. When the target total score is less than or equal to the preset score threshold, the target parking space is determined to be in a non-occupied state.

7. The method according to claim 5, characterized in that, The method further includes: The actual state of the target parking space is determined based on the vehicle occupancy status and the electrical status. Update the actual map identifier of the target parking space based on the actual status.

8. A vehicle occupancy detection device, characterized in that, The device, used for configuring charging stations in target parking spaces, includes: The first determining module is used to determine the geofence of the target parking space; The acquisition module is used to acquire the charging pile status information of the target parking space, as well as the corresponding vehicle status information and historical charging records; The second determining module is used to determine the vehicle's parking status based on the geofence and the vehicle's status information, and to determine the charging pile's electrical status based on the charging pile's status information. The parking space occupancy identification module is used to determine the vehicle occupancy status of the target parking space based on the parking status, the electrical status, and the historical charging records.

9. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor, configured to implement the steps of the vehicle occupancy identification method as described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, it implements the steps of the vehicle occupancy identification method as described in any one of claims 1 to 7.

Images