A charging parking space management method and system based on interaction between a ground lock and a charging pile
Patent Information
- Application Number
- CN202611062058.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-07-16
- Publication Date
- 2026-11-03
AI Technical Summary
Charging spaces are often occupied by fuel vehicles or new energy vehicles due to improper parking. The lack of effective automatic identification, billing and cyclical management mechanisms results in low utilization of charging facilities.
Parking space information is collected by geomagnetic sensors and combined with charging pile status information to generate a parking space fusion data set. The decision model is used to calculate the occupancy time and collect the occupancy fee. The model is updated by combining a lightweight classifier to improve detection accuracy and achieve automated management.
This improves the effective utilization rate of charging spaces, and by charging a space occupancy fee, it addresses the issue of parking without charging or leaving vehicles unmoved for extended periods, thereby enhancing the charging experience for new energy vehicle owners and increasing operator revenue.
Smart Images
Figure CN123033290A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of charging parking space management technology, and in particular to a charging parking space management method and system based on the interaction between ground locks and charging piles. Background Technology
[0002] With the continuous growth of the number of new energy vehicles, the supply and demand contradiction of charging spaces is becoming increasingly prominent. On the one hand, public charging pile resources are scarce; on the other hand, due to the lack of effective supervision, charging spaces are often occupied by fuel vehicles or new energy vehicles that are parked but not charging, resulting in a significant reduction in the effective utilization rate of charging facilities, which seriously affects the charging experience of new energy vehicle owners and the revenue of operators.
[0003] Therefore, charging parking spaces with ground locks have appeared on the market. These charging parking spaces usually require car owners to verify their new energy vehicle status by scanning a QR code or other means before the ground lock can be lowered and they can drive in. This can prevent fuel vehicles from occupying the space to some extent. However, there is still a lack of effective automatic identification, billing and cyclical management mechanisms for the irregular parking behavior of new energy vehicles, such as not connecting the charging gun after parking or occupying the parking space for a long time after charging is completed. Summary of the Invention
[0004] To address the shortcomings of existing technologies, this invention provides a charging parking space management method and system based on the interaction between ground locks and charging piles, which solves the technical problem of new energy vehicles occupying charging parking spaces for extended periods without being able to autonomously manage them.
[0005] To address the aforementioned technical problems, this invention provides a charging parking space management method based on the interaction between a parking lock and a charging pile, comprising the following steps:
[0006] S1. Respond to real-time geomagnetic sensor data for any parking space and obtain parking space information including the parking space occupancy status through a decision model (parking space information may include geomagnetic occupancy signals and geomagnetic vacancy signals).
[0007] S2. Synchronously acquire the charging status information of the charging pile corresponding to the parking space. The charging status information includes at least the charging start signal and time, the charging end signal and time, and the charging gun connection status.
[0008] S3. Align the parking space information and charging status information according to a unified time window to generate a parking space fusion data group. When the parking space information is occupied and the charging status is charging, it is marked as a positive sample data group. When the parking space information is unoccupied and the charging status is idle, it is marked as a negative sample data group.
[0009] S4. Continuously generate multiple parking space fusion data sets and determine whether they meet the correction conditions of the decision model;
[0010] S5. If yes, then the judgment parameters of the decision model are corrected based on the current parking space fusion data set, and the deviation rate of the corrected geomagnetic judgment result relative to the initial standard positive and negative samples is calculated; if no, then no operation is performed.
[0011] S6. When the deviation rate exceeds the preset warning threshold, an alarm is triggered.
[0012] Furthermore, S2 also includes: real-time monitoring of the charging gun connection status; when a disconnection signal is detected, a lowering command is generated to control the ground lock to lower and allow the vehicle to leave; (if the ground lock is always in the lowered state, this step can ensure that the ground lock is indeed in the lowered state, preventing the ground lock from rising due to abnormal reasons during charging).
[0013] The total parking time in the parking space is calculated based on the difference between the generation time of the gun removal signal and the time of the charging start signal.
[0014] The charging time for the parking space is calculated based on the difference between the time of the charging end signal and the time of the charging start signal.
[0015] The parking space occupancy time is calculated based on the difference between the total parking time and the charging time.
[0016] The parking space occupancy fee is calculated based on the vehicle occupancy duration and the preset occupancy fee rate.
[0017] Furthermore, S2 also includes:
[0018] Set the free reservation time;
[0019] After detecting that the charging gun is disconnected, a free pre-emptive timer is started;
[0020] Determine if the free reservation timer is greater than the free reservation duration;
[0021] If so, the parking space occupancy fee is calculated by adding up the portion of the free occupancy time exceeding the free occupancy period and the preset occupancy fee rate.
[0022] Furthermore, S2 also includes:
[0023] If the parking lock is equipped with an anti-roll-off protection mechanism, the parking lock will be raised to prevent the vehicle from leaving when the free parking time exceeds the free parking duration.
[0024] Furthermore, S4 includes the following steps:
[0025] Multiple continuously generated parking space fusion data sets are merged into a parking space fusion data set. The generation time of the parking space fusion data set is timed to obtain the parking space fusion data set duration data.
[0026] Determine whether the number of data in the parking space fusion data set is greater than the correction quantity threshold of the decision model; or determine whether the duration of the parking space fusion data set is greater than or equal to the correction duration threshold of the decision model.
[0027] Furthermore, S1 includes the following steps:
[0028] Geomagnetic sensor data is collected, and after feature extraction and normalization, geomagnetic sensor feature vectors are obtained by comparing the geomagnetic sensor data with a preset geomagnetic baseline; or geomagnetic variation data is obtained by comparing the geomagnetic sensor data with a preset geomagnetic baseline. The extracted features include: real-time triaxial magnetic field strength values detected by the geomagnetic sensor; the difference between the real-time triaxial magnetic field strength values and the corresponding axis geomagnetic baselines to obtain the triaxial magnetic field variation; the Euclidean distance between the real-time triaxial magnetic field strength values and the corresponding geomagnetic baselines to obtain the geomagnetic variation data; the original values of the triaxial magnetic field strength; and the magnetic field gradient and short-time fluctuation variance.
[0029] The feature vector from the geomagnetic sensor is input into a pre-trained parking space occupancy classifier to generate corresponding parking space information; alternatively, parking space information is generated by determining whether the geomagnetic change data is less than a preset geomagnetic change threshold, i.e., whether it falls within the standard deviation range of a preset multiple (e.g., 2-3 times) of the geomagnetic baseline. If the determination is yes, the parking space information is a geomagnetic occupancy signal; otherwise, it is a geomagnetic vacancy signal. The pre-trained parking space occupancy classifier can be a lightweight classifier, such as logistic regression, Naive Bayes, decision trees, or linear kernel support vector machines.
[0030] Furthermore, S5 includes the following steps:
[0031] Based on the positive and negative sample data sets, the parking space occupancy status classifier is retrained and updated. During training, the geomagnetic sensor data from the positive and negative sample data sets is used as input, and the corresponding parking space information is used as output to train the prepared lightweight classifier, obtain new parameters for the parking space occupancy status classifier, and update them. For example, algorithms such as stochastic gradient descent (SGD) are used to minimize the cross-entropy loss. The model parameters are updated online to verify whether the accuracy, recall, and other indicators of the updated model have improved. The new weights and biases are sent to the geomagnetic sensor via OTA to replace the original hard-coded thresholds.
[0032] Alternatively, based on the positive and negative sample data sets, a new geomagnetic change threshold that maximizes the F1 score can be calculated through optimization, and this threshold can be updated. The F1 score is the harmonic mean of precision and recall, which comprehensively evaluates the classifier's performance on imbalanced datasets. The optimization calculation can be performed through the following steps:
[0033] Calculate all geomagnetic variation data in the positive sample data set and the negative sample data set, as well as the corresponding parking space information;
[0034] Within the possible range of geomagnetic change data values (e.g., from 0 to a certain upper limit, with a step size of 0.1 or finer), traverse the candidate geomagnetic change thresholds;
[0035] For each candidate geomagnetic variation threshold, the corresponding confusion matrix (TP, FP, TN, FN) is calculated, and then the F1 score is calculated.
[0036] The geomagnetic variation data that maximizes the F1 score is selected as the updated geomagnetic variation threshold.
[0037] Furthermore, method 1 also includes correcting a preset geomagnetic baseline, comprising the following steps:
[0038] Multi-axis (X-axis, Y-axis, and Z-axis) magnetic field data were collected from the geomagnetic sensor while the parking space was continuously vacant.
[0039] The mean vector of the magnetic field strength of each axis is calculated using a sliding window mean filtering algorithm and used as the geomagnetic baseline.
[0040] The present invention also provides a charging parking space management system based on the interaction between ground locks and charging piles, including a geomagnetic sensor, a charging pile, a ground lock, an interface, a storage device, a smart chip, and an alarm.
[0041] The geomagnetic sensor is buried under the parking space to collect triaxial magnetic field change information above the parking space, and transmits the collected triaxial magnetic field change information to the storage device through the interface.
[0042] The charging pile is used to charge the vehicles in the parking space and is connected to the storage device through an interface for information exchange.
[0043] The ground lock is installed on the surface of the parking space to prevent vehicles from entering or exiting when raised and to allow vehicles to enter or exit when lowered. It is connected to the smart chip via an interface to receive control signals from the smart chip and to feed back the execution results to the smart chip. Furthermore, at least one of the ground lock, charging pile, and parking space has a QR code affixed to it for users to scan and enter the identity verification system to complete identity verification.
[0044] The storage device is used to store received data and computer programs, and connects to the smart chip through an interface for information exchange.
[0045] The smart chip is used to run the computer program and execute a charging parking space management method based on the interaction between the ground lock and the charging pile.
[0046] The alarm is connected to the smart chip via an interface to receive control signals from the smart chip and trigger an alarm.
[0047] By employing the above technical solution, the present invention provides a charging parking space management method and system based on the interaction between ground locks and charging piles, which has at least the following beneficial effects:
[0048] 1. This invention obtains parking space information by acquiring and analyzing data from geomagnetic sensors, and obtains charging status information from charging piles. By associating geomagnetic sensor data, parking space information, and charging status information at the same time, the parking duration and charging duration can be calculated, and then the occupancy duration can be calculated. In order to calculate the occupancy fee based on the occupancy duration and the preset occupancy fee rate, the occupancy fee can be used to improve the behavior of parking without charging or not moving the car for a long time after charging, thereby improving the effective utilization rate of electric parking spaces.
[0049] 2. This invention labels the geomagnetic sensor data, parking space information, and charging status information at the same time stamp as positive and negative sample data groups. This allows the truth labels corresponding to the geomagnetic sensor data in the group to be obtained through the labeled positive and negative sample data groups. This enables the decision model to be updated through the positive and negative sample data groups after the preset decision model correction conditions are met, so as to correct the error of geomagnetic sensor detection and maintain the detection accuracy. Attached Figure Description
[0050] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:
[0051] Figure 1 This is a flowchart of the charging parking space management method in this invention;
[0052] Figure 2 This is a schematic diagram of the charging parking space management system in this invention. Detailed Implementation
[0053] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. This will allow for a full understanding of how the present application uses technical means to solve technical problems and achieve technical effects, and to facilitate its implementation.
[0054] This embodiment proposes a charging parking space management method based on the interaction between parking locks and charging piles. It calculates and charges for parking spaces based on the duration of occupancy and a preset occupancy rate. By charging for occupancy, it aims to improve the effective utilization rate of charging parking spaces by addressing behaviors such as parking without charging or leaving vehicles unmoved for extended periods after charging. Figure 1As shown, the method includes the following steps:
[0055] S1. Responding to real-time geomagnetic sensor data for any parking space, and obtaining parking space information including the parking space occupancy status (parking space information may include geomagnetic occupancy signals and geomagnetic vacancy signals) through a decision model, including the following steps:
[0056] S1A.1. Collect geomagnetic sensor data. After feature extraction and normalization, the geomagnetic sensor feature vector is obtained by comparing the data with a preset geomagnetic baseline. Specifically, the extracted features include: real-time triaxial magnetic field strength values detected by the geomagnetic sensor; calculation of the difference between the real-time triaxial magnetic field strength values and the corresponding axis geomagnetic baseline to obtain the triaxial magnetic field change; calculation of the Euclidean distance between the real-time triaxial magnetic field strength values and the corresponding geomagnetic baseline to obtain geomagnetic change data; the raw values of the triaxial magnetic field strength; magnetic field gradient; and short-time fluctuation variance. Furthermore, the temperature of the parking space can be monitored by a temperature sensor and added as an optional feature to the geomagnetic sensor feature vector to compensate for temperature drift. Normalization is used to eliminate the influence of the dimensions of the features. The geomagnetic sensor, temperature sensor, and parking lock can establish communication with the system via an internal NB-IoT communication module using NB-IoT technology to transmit data or control signals.
[0057] S1A.2. Input the feature vector from the geomagnetic sensor into the pre-trained parking space occupancy status classifier to generate corresponding parking space information. The pre-trained parking space occupancy status classifier can be a lightweight classifier, such as logistic regression, Naive Bayes, decision trees, or linear kernel support vector machines. The use of a lightweight classifier also ensures the interpretability of the model. For example, when using a decision tree to determine the parking space status, the judgment process can be represented as something like "if the change in the X-axis magnetic field is greater than threshold 1 and the change in the Z-axis magnetic field is less than threshold 2, then it is determined that there is a car." When using logistic regression, a weight coefficient is assigned to each input feature. The sign and magnitude of the weight coefficient can directly explain the direction and degree of contribution of each factor to the "car / no car" judgment, facilitating the investigation of the root causes of abnormal judgments.
[0058] In another embodiment, steps S1A.1-S1A.2 can be replaced using the following steps:
[0059] S1B.1. Geomagnetic variation data is obtained by comparing geomagnetic sensor data with a preset geomagnetic baseline;
[0060] S1B.2. By determining whether the geomagnetic change data is less than the preset geomagnetic change threshold, that is, whether it falls within the standard deviation range of the preset multiple (such as 2-3 times) of the geomagnetic baseline, the corresponding parking space information is generated. If the determination is yes, the parking space information is a geomagnetic occupied signal; otherwise, it is a geomagnetic idle signal.
[0061] Furthermore, when there are no vehicles in the parking space, the preset geomagnetic baseline is corrected, including the following steps:
[0062] When the parking space is continuously vacant, if the duration of the continuous geomagnetic vacancy signal reaches the preset baseline correction threshold, the multi-axis (X-axis, Y-axis and Z-axis) magnetic field data of the geomagnetic sensor during this period will be collected.
[0063] The mean vector of the magnetic field strength of each axis is calculated using a sliding window mean filtering algorithm, which serves as the geomagnetic baseline.
[0064] Furthermore, before entering a parking space, users can authenticate their electric vehicle by scanning a QR code on the corresponding parking space, ground lock, or charging station to verify their vehicle's identity. Once the authentication is successful, the ground lock will lower, allowing the user to drive into the parking space and charge the vehicle.
[0065] S2. Synchronously acquire the charging status information of the charging pile corresponding to the parking space. The charging status information includes at least the charging start signal and time, the charging end signal and time, and the charging gun connection status. Specific implementation steps include:
[0066] The charging gun connection status is monitored in real time. When a disconnection signal is detected, a lowering command is generated to control the ground lock to lower and allow the vehicle to leave. If the ground lock is always in the lowered state, this step can be used to ensure that the ground lock is indeed in the lowered state and prevent the ground lock from rising due to abnormal reasons during charging.
[0067] The total parking time in the parking space is calculated based on the difference between the generation time of the gun removal signal and the time of the charging start signal.
[0068] The charging time for the parking space is calculated based on the difference between the time of the charging end signal and the time of the charging start signal.
[0069] The parking space occupancy time is calculated based on the difference between the total parking time and the charging time.
[0070] The parking space occupancy fee is calculated based on the vehicle's occupancy duration and a preset occupancy rate. The occupancy rate can be set linearly, such as per minute, or in stages, such as per 15 / 20 / 30 / 60 minutes, with any period less than 15 / 20 / 30 / 60 minutes rounded up to 15 / 20 / 30 / 60 minutes. Since charging stations typically use prepaid, credit payment, or password-free payment methods, the system can be configured to automatically retrieve the current charging amount and parking space occupancy fee upon detecting a disconnection signal, allowing users to quickly leave after disconnecting the charging gun.
[0071] In one embodiment, S2 further includes:
[0072] Set the free hold duration; start the free hold timer after detecting that the charging gun is disconnected; determine whether the free hold timer is greater than the free hold duration;
[0073] If so, the parking space occupancy fee will be calculated by adding the portion of the free occupancy time exceeding the free occupancy duration and the preset occupancy rate. If the parking lock is equipped with an anti-roofing protection mechanism, the parking lock will be raised to prevent the vehicle from leaving when the free occupancy time exceeds the free occupancy duration.
[0074] The free parking space reservation timer stops counting down once the parking space information changes to an empty geomagnetic signal. After a user pays, the current parking space reservation fee is reset to zero, and the remaining reservation fee is added back to the original amount. If payment is not made after the user removes the parking gun or payment is unsuccessful, the remaining reservation fee is added back to the original amount.
[0075] Furthermore, the timer can be reset after a user pays, preventing users from not leaving promptly after payment.
[0076] S3. Align the parking space information and charging status information according to a unified time window to generate a parking space fusion data group. When the parking space information is occupied and the charging status is charging, it is marked as a positive sample data group. When the parking space information is unoccupied and the charging status is idle, it is marked as a negative sample data group.
[0077] S4. Continuously generate multiple parking space fusion data sets and determine whether they meet the correction conditions of the decision model, including the following steps:
[0078] Collect parking space fusion data sets, generate parking space fusion data set sets, and time the generation time of the parking space fusion data set sets to obtain parking space fusion data set set duration data;
[0079] Determine whether the number of data in the parking space fusion data set is greater than the preset decision model correction threshold; or determine whether the duration of the parking space fusion data set is greater than or equal to the preset decision model correction duration threshold.
[0080] S5. If so, then based on the current parking space fusion data set, the judgment parameters of the decision model are corrected, and the deviation rate of the corrected geomagnetic judgment result relative to the initial standard positive and negative samples is calculated, including the following steps:
[0081] Based on the positive and negative sample data sets, the parking space occupancy status classifier is retrained and updated. During training, the geomagnetic sensor data from the positive and negative sample data sets are used as input, and the corresponding parking space information is used as output to train the prepared lightweight classifier, obtain the new parameters of the parking space occupancy status classifier and update them. For example, algorithms such as stochastic gradient descent (SGD) are used to minimize the cross-entropy loss. The model parameters are updated online to verify whether the accuracy, recall and other indicators of the updated model have improved. The new weights and biases are sent to the geomagnetic sensor via OTA to replace the original hard-coded thresholds.
[0082] Alternatively, based on the positive and negative sample data sets, a new geomagnetic change threshold that maximizes the F1 score can be calculated through optimization, and this threshold can be updated. The F1 score is the harmonic mean of precision and recall, which comprehensively evaluates the classifier's performance on imbalanced datasets. The optimization calculation can be performed through the following steps:
[0083] Calculate all geomagnetic variation data and corresponding parking space information in the positive and negative sample data sets; within the possible range of geomagnetic variation data values (e.g., from 0 to a certain upper limit, with a step size of 0.1 or finer), traverse the candidate geomagnetic variation thresholds; for each candidate geomagnetic variation threshold, calculate the corresponding confusion matrix (TP, FP, TN, FN), and then calculate the F1 score; select the geomagnetic variation data that maximizes the F1 score as the updated geomagnetic variation threshold.
[0084] Other standards can also be selected based on business preferences. For example, if it is absolutely impossible to miss a detection (preventing charging when there is a vehicle), then the minimum threshold that makes the recall rate reach more than 99% can be selected; if it is absolutely impossible to lock the vehicle incorrectly (judging that there is no vehicle and raising the ground lock when there is one), then the threshold that makes the accuracy rate the highest can be selected.
[0085] Bias rate = (Number of misclassified samples by the new corrected decision model based on the initial standard samples / Total number of initial standard samples) × 100%.
[0086] If S4 determines otherwise, no operation is performed.
[0087] S6. If the deviation rate exceeds the preset warning threshold, an alarm will be triggered.
[0088] This embodiment also provides a system for implementing the above-described charging parking space management method, including a geomagnetic sensor, a charging pile, a ground lock, an interface, a storage device, a smart chip, and an alarm, such as... Figure 2 As shown.
[0089] In this embodiment, a geomagnetic sensor is buried under the parking space to collect triaxial magnetic field change information above the parking space, and transmits the collected triaxial magnetic field change information to the storage device through an interface; the charging pile is used to charge the vehicle in the parking space, and connects to the storage device through an interface for information exchange.
[0090] The parking lock is installed on the surface of the parking space to prevent vehicles from entering or exiting when raised and to allow vehicles to enter or exit when lowered. It connects to a smart chip via an interface to receive control signals from the smart chip and feeds back the execution results to the smart chip.
[0091] Furthermore, at least one of the ground locks, charging piles, and parking spaces has a QR code affixed for users to scan and enter the identity verification system to complete identity verification; furthermore, ground locks with anti-top-car protection mechanisms can also be used, which can rise when the vehicle is parked in the parking space to prevent the vehicle from leaving without paying, and can also prevent the ground lock from damaging the vehicle chassis when it rises.
[0092] The storage device is used to store received data and computer programs, and connects to the smart chip via an interface for information exchange; the smart chip is used to run the computer program and implement the charging parking space management method; the alarm connects to the smart chip via an interface to receive control signals from the smart chip and trigger an alarm.
[0093] Those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing related hardware. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0094] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. Since the above embodiments are substantially similar to the method embodiments, their descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.
[0095] The above embodiments provide a detailed description of the present invention. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.
Claims
1. A method for managing charging parking spaces based on the interaction between ground locks and charging piles, characterized in that, The method includes the following steps: Responding to real-time geomagnetic sensor data for any parking space, and obtaining parking space information including the occupancy status through a decision model; Synchronously acquire the charging status information of the charging pile corresponding to the parking space. The charging status information includes at least the charging start signal and time, the charging end signal and time, and the charging gun connection status. Parking space information and charging status information are time-aligned according to a unified time window to generate a parking space fusion data group. When the parking space information is occupied and the charging status is charging, it is marked as a positive sample data group. When the parking space information is unoccupied and the charging status is idle, it is marked as a negative sample data group. Continuously generate multiple parking space fusion data sets and determine whether they meet the correction conditions of the decision model; If so, the decision parameters of the decision model are corrected based on the current parking space fusion data set, and the deviation rate of the corrected geomagnetic judgment result relative to the initial standard positive and negative samples is calculated. An alarm will be triggered when the deviation rate exceeds a preset warning threshold.
2. The charging parking space management method according to claim 1, characterized in that, Obtaining the parking space information includes: Collect geomagnetic sensor data, compare the geomagnetic sensor data with a preset geomagnetic baseline, extract features and normalize the data to obtain geomagnetic sensor feature vectors; or obtain geomagnetic change data by comparing the geomagnetic sensor data with a preset geomagnetic baseline. The feature vector of the geomagnetic sensor is input into a pre-trained parking space occupancy status classifier to generate corresponding parking space information; or the corresponding parking space information is generated by judging whether the geomagnetic change data is less than a preset geomagnetic change threshold, wherein if the judgment is yes, the parking space information is a geomagnetic occupancy signal, otherwise it is a geomagnetic vacancy signal.
3. The charging parking space management method according to claim 1, characterized in that, Also includes: The charging gun connection status is monitored in real time. When a disconnection signal is detected, a lowering command is generated and the ground lock is lowered to allow the vehicle to leave. The total parking time in the parking space is calculated based on the difference between the generation time of the gun removal signal and the time of the charging start signal. The charging time for the parking space is calculated based on the difference between the time of the charging end signal and the time of the charging start signal. The parking space occupancy time is calculated based on the difference between the total parking time and the charging time. The parking space occupancy fee is calculated based on the vehicle occupancy duration and the preset occupancy fee rate.
4. The charging parking space management method according to claim 3, characterized in that, Also includes: Set the free reservation time; After detecting that the charging gun is disconnected, a free pre-emptive timer is started; Determine if the free reservation timer is greater than the free reservation duration; If so, the parking space occupancy fee is calculated by adding up the portion of the free occupancy time exceeding the free occupancy period and the preset occupancy fee rate.
5. The charging parking space management method according to claim 4, characterized in that, Also includes: If the parking lock is equipped with an anti-roll-off protection mechanism, the parking lock will be raised to prevent the vehicle from leaving when the free parking time exceeds the free parking duration.
6. The charging parking space management method according to claim 1, characterized in that, Continuously generate multiple fused parking space data sets and determine whether they meet the correction conditions of the decision model, including: Multiple continuously generated parking space fusion data sets are merged into a parking space fusion data set. The generation time of the parking space fusion data set is timed to obtain the parking space fusion data set duration data. Determine whether the number of data in the parking space fusion data set is greater than the correction quantity threshold of the decision model; or determine whether the duration of the parking space fusion data set is greater than or equal to the correction duration threshold of the decision model.
7. The charging parking space management method according to claim 1, characterized in that, Correcting the judgment parameters includes: Based on the positive sample data set and the negative sample data set, the parking space occupancy status classifier is retrained and updated; Alternatively, based on the positive and negative sample data sets, a new geomagnetic change threshold that maximizes the F1 score can be obtained through optimization calculation, and the geomagnetic change threshold can be updated.
8. The charging parking space management method according to claim 2, characterized in that, It also includes correcting a preset geomagnetic baseline, including: Collect multi-axis magnetic field data from geomagnetic sensors while the parking space is continuously vacant. The mean vector of the magnetic field strength of each axis is calculated using a sliding window mean filtering algorithm and used as the geomagnetic baseline.
9. A charging parking space management system based on the interaction between a parking lock and a charging pile, used to execute the charging parking space management method according to any one of claims 1-8, characterized in that, This includes geomagnetic sensors, charging piles, ground locks, interfaces, storage devices, smart chips, and alarms; The geomagnetic sensor is buried under the parking space to collect triaxial magnetic field change information above the parking space, and transmits the collected triaxial magnetic field change information to the storage device through the interface. The charging pile is used to charge the vehicles in the parking space and is connected to the storage device through an interface for information exchange. The ground lock is installed on the surface of the parking space to prevent vehicles from entering or exiting when raised and to allow vehicles to enter or exit when lowered. It is connected to the smart chip through an interface to receive control signals from the smart chip and to feed back the execution results to the smart chip. The storage device is used to store received data and computer programs, and connects to the smart chip through an interface for information exchange. The smart chip is used to run the computer program and execute the charging parking space management method according to any one of claims 1-8; The alarm is connected to the smart chip via an interface to receive control signals from the smart chip and trigger an alarm.