New Energy Vehicle Charging Management Method, System and Medium for Public Parking Spaces

Abstract

The present invention discloses a new energy vehicle charging management method, system and medium for public parking spaces, belonging to the technical field of new energy vehicle charging. The method includes: if receiving a reservation information of a target vehicle, acquiring historical charging data based on the reservation information; acquiring a body image of the target vehicle, performing image recognition on the body image to obtain vehicle information of the target vehicle, and if it is queried that the vehicle information is bound to a mobile terminal, acquiring the historical charging data of the target vehicle; acquiring the current SOC of the target vehicle, predicting the termination SOC and the parking duration, calculating an ideal charging power in combination with the charging limit power, and if the remaining available power in the charging area is less than the ideal charging power, reducing the charging power of low-priority vehicles to increase the remaining available power; sending a reminder to the charging vehicles in the charging area whose current SOC is greater than a first threshold. Through the present invention, the charging power can be reasonably allocated, thereby improving the charging efficiency of new energy vehicles.

Description

Technical Field

[0001] The present invention belongs to the technical field of new energy vehicle charging, and particularly relates to a new energy vehicle charging management method, system and medium for public parking spaces. Background Art

[0002] With the rapid development of new energy vehicles, the construction of charging infrastructure has become increasingly important. However, there are many problems in the current charging management of public parking spaces, such as low utilization rate of charging piles and non-charging vehicles occupying charging spaces, which seriously restrict the convenient use of new energy vehicles. To solve the above problems, the following technical solutions have been proposed in the prior art.

[0003] For example, the Chinese patent document with the publication number CN116409188A discloses a V2X-based charging space management method, system and its charging space. This invention can identify the vehicle license plate of the vehicle to be driven into the parking space based on the principle of image recognition, determine whether the vehicle to be driven into the parking space is a new energy vehicle according to the vehicle license plate, and further determine whether the vehicle is a new energy vehicle supporting charging. For new energy vehicles supporting charging, it is released and can enter the charging space for charging operations. Another example is the Chinese patent document with the publication number CN116834594A, which discloses a charging management method, device, electronic device and medium based on charging spaces. When it is determined that the driving-in vehicle is of fuel type, the target space is determined according to the idle spaces corresponding to ordinary spaces; when the driving-in vehicle is a new energy vehicle and does not need charging, the target space is determined according to the idle spaces corresponding to ordinary spaces; when the driving-in vehicle is a new energy vehicle and needs charging, the target space is determined according to the idle spaces corresponding to charging spaces, so as to achieve precise allocation of spaces.

[0004] The above methods distinguish between fuel vehicles and new energy vehicles to manage charging spaces. There are still the following problems at present. For new energy vehicles charging in the same charging area, the output power allocated to each charging gun is unbalanced, so there will be a situation where vehicles eager to charge have a slower charging speed. Summary of the Invention

[0005] To solve the above problems, the present invention provides a new energy vehicle charging management method, system and medium for public parking spaces to solve the problems in the above background art.

[0006] To achieve the above invention purpose, the present invention proposes a new energy vehicle charging management method for public parking spaces, including:

[0007] Dividing the parking lot into an entrance area and a charging area. If the parking lot receives a reservation message of a target vehicle, the historical charging data of the target vehicle is obtained based on the reservation message;

[0008] After the target vehicle passes through the entry area, obtain a body image of the target vehicle, perform image recognition on the body image to obtain vehicle information of the target vehicle, and if it is queried that the vehicle information is bound to a mobile terminal, obtain the historical charging data of the target vehicle;

[0009] After the target vehicle starts charging in the charging area, obtain the current SOC of the target vehicle, and predict the termination SOC and parking duration based on the historical charging data;

[0010] Calculate the ideal charging power by combining the current SOC, the termination SOC, the charging limit power, and the parking duration. If the remaining available power in the charging area is less than the ideal charging power, search for low-priority vehicles that meet the preset conditions in the charging area and reduce the charging power of the low-priority vehicles to increase the remaining available power;

[0011] Send a reminder to the charging vehicles in the charging area whose current SOC is greater than the first threshold, and the first threshold fluctuates according to the number of waiting vehicles.

[0012] Further, adjust the first threshold based on the following steps:

[0013] Obtain an environmental photo of the charging area, define the vehicles outside the charging area in the environmental photo with their vehicle tail lights lit as the waiting vehicles, count the first number of the waiting vehicles, count the second number of the vehicles that have made reservations to charge in the charging area, add the first number and the second number to obtain the total number of waiting vehicles, establish a comparison table between the total number and the first threshold. In the comparison table, the larger the total number, the smaller the first threshold. Adjust the first threshold based on the comparison table and the current total number of waiting vehicles.

[0014] Further, after the parking lot receives the reservation information, the following steps are also included:

[0015] Define the charging areas with vacant parking spaces in the parking lot as idle areas, obtain the historical charging data of the idle areas, where the historical charging data includes the number of charging vehicles per minute in the past, analyze the historical charging data to generate various charging rules in the idle areas. Define the time point when the reservation information is received as the current time point, obtain the daily charging data of each idle area between the preset time point and the current time point on the same day, and determine the charging rules that appear in each idle area on the same day based on the daily charging data, which is defined as the pre-set rule;

[0016] Retrieve the historical charging data that occurred every day between the preset time point and the current time point and belongs to the previous rule, obtain the estimated arrival time point in the reservation information, and calculate the recommended value of the idle area based on the first formula , and the first formula is: , where K is the number of charging vehicles in the idle area at the current time point, 、 are respectively the number of charging vehicles at the estimated arrival time point on the nth day in the previous rule and the number of charging vehicles at the current time point, N is the number of dates belonging to the previous rule, M is the upper limit of the number of charging vehicles in the idle area, repeat this step to calculate the recommended value of each idle area;

[0017] Take the idle area with the largest recommended value as the recommended area, generate the driving route from the entry area to the recommended area, and push it to the mobile terminal.

[0018] Furthermore, generating multiple charging rules for the idle area includes the following steps:

[0019] Establish a coordinate system with time as the horizontal axis and the number of charging vehicles as the vertical axis, and draw multiple first curves in the coordinate system. The first curve is the curve of the number of charging vehicles in the idle area changing with time every day;

[0020] Extract two of the first curves, calculate the similarity between the two first curves. If the similarity is greater than the second threshold, then divide the two first curves into the same charging rule. Define the first curve that has been divided into the charging rule as the second curve, extract another first curve and compare it with the second curve. If the similarities are all greater than the second threshold, then divide the extracted first curve into the same charging rule as the second curve. If it is less than or equal to the second threshold, re-extract the first curve until the extraction of the first curve is completed. Extract two from the first curves that have not been divided into the charging rule and calculate the similarity, and repeat this step until all the first curves are divided into the charging rule.

[0021] Furthermore, calculating the similarity of the first curve includes the following steps:

[0022] Obtain the intervals where the change trends of the two first curves are the same, which are defined as comparison intervals. Calculate the difference in the number of charging vehicles at the same time points of the two first curves within the comparison intervals. Define the coordinate points where the difference is less than the third threshold as comparison points, and define the intervals where the comparison points continuously appear as similar intervals. Obtain the first length of the abscissa of each similar interval, accumulate the first lengths to obtain the second length, obtain the third length of the abscissa of the first curve, and use the ratio of the second length to the third length as the similarity.

[0023] Further, predicting the termination SOC and parking duration based on the historical charging data includes the following steps:

[0024] The historical charging data includes the parking duration, starting SOC, ending SOC, charging electricity price, and charging date information during the stay in the charging area. The charging date information includes the charging date of the vehicle, weekday information, start time point, and end time point. The vehicle information includes the license plate number and vehicle model. Train and establish a neural network model based on the historical charging data, and use the starting SOC, charging date information, and vehicle model of the target vehicle as input features and input them into the neural network model. The neural network model outputs the termination SOC and parking duration.

[0025] Further, the preset conditions include that the current SOC of the charging vehicle is greater than the fourth threshold, and the current charging duration of the charging vehicle is greater than the fifth threshold.

[0026] Further, perform image recognition on the vehicle body image based on the CNN model.

[0027] The present invention also provides a new energy vehicle charging management system for public parking spaces, which is used to implement the above-mentioned new energy vehicle charging management method for public parking spaces. The system includes:

[0028] A query unit. If the parking lot receives the reservation information of the target vehicle, based on the reservation information, obtain the historical charging data of the target vehicle. After the target vehicle passes through the entry area, obtain the vehicle body picture of the target vehicle, perform image recognition on the vehicle body picture, obtain the vehicle information of the target vehicle. If it is queried that the vehicle information is bound to a mobile terminal, obtain the historical charging data of the target vehicle;

[0029] A prediction unit. After the target vehicle starts charging in the charging area, obtain the current SOC of the target vehicle, and predict the termination SOC and parking duration based on the historical charging data;

[0030] An adjustment unit calculates an ideal charging power by combining the current SOC, the termination SOC, the charging limit power, and the parking duration. If the remaining available power in the charging area is less than the ideal charging power, it searches for low-priority vehicles that meet the preset conditions in the charging area and reduces the charging power of the low-priority vehicles to increase the remaining available power;

[0031] A reminder unit sends a reminder to the charging vehicles in the charging area whose current SOC is greater than the first threshold, and the first threshold floats according to the number of waiting vehicles.

[0032] The present invention also discloses a computer storage medium storing program instructions, wherein when the program instructions run, they control the device where the computer storage medium is located to execute the method described above.

[0033] Compared with the prior art, the beneficial effects of the present invention are at least as follows:

[0034] The present invention obtains historical charging data based on the reservation information of the target vehicle, or after the target vehicle enters the parking lot, it recognizes the vehicle pictures, and indirectly obtains historical charging data through the obtained vehicle information; on the basis of being able to obtain the vehicle historical charging data, it combines artificial intelligence technology to predict the parking duration of the vehicle in the parking lot and the possible charging power required. When the parking duration of the target vehicle is short and the required charging power is large, it will search for vehicles with a relatively large remaining power or vehicles that have been charged for a long time in the charging area, reduce their charging power, and as much as possible increase the charging power of the newly charged vehicles without exceeding the charging gun limit power, realizing the reasonable distribution of charging power. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a flowchart of the steps for the charging management of new energy vehicles in public parking spaces according to the present invention;

[0036] Figure 2 It is a schematic structural diagram of the system for the charging management of new energy vehicles in public parking spaces according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0037] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0038] It can be understood that the terms "first", "second", etc. used in this application may be used herein to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, without departing from the scope of this application, the first xx script may be referred to as the second xx script, and similarly, the second xx script may be referred to as the first xx script.

[0039] As Figure 1 shown, a new energy vehicle charging management method for public parking spaces includes:

[0040] S1: Divide the parking lot into an entrance area and a charging area. If the parking lot receives a reservation information of a target vehicle, obtain the historical charging data of the target vehicle based on the reservation information.

[0041] The entrance area is the entrance channel set in the parking lot, and the target vehicle is the vehicle that needs to enter the parking lot for charging. If the management system of the parking lot receives the reservation information of the target vehicle, it indicates that the vehicle information of the target vehicle has been bound to the mobile terminal in the management system. The mobile terminal is, for example, a mobile phone, and the management system is allowed to record the behavior data of the vehicle. Then, before this, the system may have recorded the charging behavior data of the vehicle multiple times. Therefore, the management system retrieves the historical charging behavior data according to the vehicle information, that is, the historical charging data.

[0042] S2: After the target vehicle passes through the entrance area, obtain the body image of the target vehicle, perform image recognition on the body image, obtain the vehicle information of the target vehicle. If it is queried that the vehicle information is bound to a mobile terminal, obtain the historical charging data of the target vehicle.

[0043] In this embodiment, the CNN deep learning algorithm is used to recognize the body image to obtain the vehicle information of the target vehicle. The vehicle information includes the license plate number and the vehicle model. In the absence of reservation information, only the vehicle information can be used to attempt to obtain the historical charging data. If the historical charging data is not obtained, it indicates that the target vehicle may enter this parking lot for the first time, or the vehicle information has not been bound to the mobile terminal. In both cases, the management system does not retain the behavior data of the target vehicle after it enters the parking lot to protect the user privacy.

[0044] S3: After the target vehicle starts charging in the charging area, obtain the current SOC of the target vehicle, and predict the termination SOC and the parking duration based on the historical charging data.

[0045] S4: Calculate the ideal charging power by combining the current SOC, the termination SOC, the charging limit power, and the parking duration. If the remaining available power in the charging area is less than the ideal charging power, search for low-priority vehicles that meet the preset conditions in the charging area and reduce the charging power of the low-priority vehicles to increase the remaining available power.

[0046] After connecting the charging gun to the vehicle, the current SOC of the target vehicle, that is, the current remaining battery level, can be obtained. In the field of new energy vehicles, SOC represents the remaining battery level of the vehicle's power battery. Combining the previously obtained historical charging data, predict the possible charging duration of the target vehicle in the charging area and the possible remaining battery level when charging ends. Artificial intelligence methods can be used for prediction. Then, subtract the current remaining battery level from the possible remaining battery level when charging ends and divide by the parking duration to obtain the ideal charging power, such as 40 kw / h. If the ideal charging power is less than the charging limit power of the charging gun and the remaining available power in the charging area is less than the ideal charging power, low-priority vehicles will be searched for in the charging area. Reduce their charging power to release the remaining available power. Low-priority vehicles include those with the current SOC of the charging vehicle greater than the second threshold, for example, the second threshold is 70%, or those with too long a charging duration, for example, exceeding 2 hours.

[0047] S5: Send a reminder to the charging vehicles in the charging area whose current SOC is greater than the first threshold, and the first threshold floats according to the number of waiting vehicles.

[0048] The first threshold is continuously adjusted according to the actual situation. For example, the first threshold is 95%. When the remaining battery level of the vehicle in the charging area is greater than 95% and the charging vehicle is bound to a mobile terminal, a reminder is sent to the corresponding mobile terminal. The reminder content can be that it is recommended that the vehicle owner move the vehicle in time to avoid wasting charging resources.

[0049] In addition, during the vehicle charging process in the charging area of this embodiment, the charging current, charging voltage, and battery temperature of the charging gun are also obtained. When the charging current, charging voltage, and battery temperature exceed the preset range, the power supply is cut off and an alarm is generated.

[0050] The present invention obtains historical charging data based on the reservation information of the target vehicle, or after the target vehicle enters the parking lot, the vehicle pictures are recognized, and the historical charging data is indirectly obtained through the obtained vehicle information; on the basis of being able to obtain the vehicle historical charging data, artificial intelligence technology is combined to predict the stay duration of the vehicle in the parking lot and the possible charging power required. When the stay duration of the target vehicle is short and the required charging power is large, vehicles with a relatively large current remaining battery level or those that have been charging for a long time will be searched for in the charging area, and their charging power will be reduced. Without exceeding the charging limit power of the charging gun, the charging power of the newly charging vehicle is increased as much as possible, realizing the reasonable distribution of charging power.

[0051] Particularly noteworthy is that through the present invention, the charging power can be reasonably allocated, thereby improving the charging efficiency of new energy vehicles.

[0052] This embodiment adjusts the first threshold based on the following steps:

[0053] Obtain environmental photos of the charging area. Define the vehicles outside the charging area with their taillights lit as waiting vehicles. Count the first number of waiting vehicles, count the second number of vehicles that have reserved to charge in the charging area, add the first number and the second number to obtain the total number of waiting vehicles. Establish a comparison table between the total number and the first threshold. In the comparison table, the larger the total number, the smaller the first threshold. Adjust the first threshold based on the comparison table and the current total number of waiting vehicles.

[0054] The environmental photos include photos of the charging area and its nearby areas. Then, perform image recognition on the photos to obtain the vehicles outside the charging area. In addition, the taillights of the vehicles in the waiting state are usually lit. Then, count the first number of vehicles identified as waiting vehicles in the environmental photos, and the second number of vehicles that have been reserved in the management system and need to charge in this charging area, so as to obtain the total number of vehicles that need to charge in the charging area in the future. Determine the specific first threshold to be set according to the corresponding relationship between the total number and the first threshold in the comparison table. For example, in the comparison table, when the total number is 2, the first threshold is 80%, and when the total number is 5, the first threshold is 70%.

[0055] After this embodiment receives the reservation information in the parking lot, it further includes the following steps:

[0056] Define the charging areas with vacant parking spaces in the parking lot as idle areas. Obtain the historical charging data of the idle areas. The historical charging data includes the number of charging vehicles per minute in the past. Analyze the historical charging data to generate various charging rules for the idle areas. Define the time point when the reservation information is received as the current time point. Obtain the daily charging data of each idle area between the preset time point and the current time point on the same day. Determine the charging rules that appear in each idle area on the same day based on the daily charging data, and define them as the pre-set rules.

[0057] For medium and large parking lots, there are often multiple charging areas, which are relatively scattered and generally established by different suppliers. In order to find a charging area with available parking spaces, users need to constantly explore in the parking lot, which not only wastes users' time but also exacerbates the congestion in the parking lot. Therefore, after receiving the reservation information of the target vehicle in the parking lot, the present invention determines the seat idle areas with available parking spaces in each charging area, and then obtains the historical charging data of the idle areas. The historical charging data includes the number of charging vehicles in the idle areas per minute in the past, such as at 14:00, the number of charging vehicles is 3, and at 14:01, the number of charging vehicles is 3. Then, analyze the historical charging data to generate the charging rules of each idle area every day. Through the charging rules, it can be understood which time periods of the charging area are busier and which are more idle, so as to facilitate subsequent analysis.

[0058] The preset time point is a time point set manually, such as 6 am. After the parking lot receives the reservation information, determine the current time point when the reservation information is received, such as 10 am, obtain the current day's charging data of each idle area between 6 am and 10 am on the current day, and then compare the current day's charging data with the historical charging data of each idle area between 6 am and 10 am in the past respectively, so as to obtain the dates with the same charging rules as the current day. The corresponding charging rules are defined as the pre-set rules. Through this step, the charging rules that appear currently in each idle area are obtained.

[0059] Retrieve the historical charging data between the preset time point and the current time point every day in the past and belonging to the pre-set rules, obtain the estimated arrival time point in the reservation information, and calculate the recommended value of the idle area based on the first formula , the first formula is: , where K is the number of charging vehicles in the idle area at the current time point, 、 are respectively the number of charging vehicles at the estimated arrival time point and the number of charging vehicles at the current time point on the nth day in the pre-set rules, N is the number of dates belonging to the pre-set rules, and M is the upper limit of the number of charging vehicles in the idle area. Repeat this step to calculate the recommended value of each idle area;

[0060] Take the idle area with the largest recommended value as the recommended area, generate the driving route from the entrance area to the recommended area, and push it to the mobile terminal.

[0061] The first formula is for calculating the recommended value of an idle area. Before using the first formula, first obtain the dates belonging to the previous rule, count their number as the value of N, then obtain the estimated arrival time of the customer from the reservation information, and obtain the number of charging vehicles at the estimated arrival time and the current time for each day in the dates belonging to the previous rule, and then substitute them into the first formula for calculation. The denominator in the first formula represents the fluctuation of the number of charging vehicles between two time points, and the larger the upper limit of the number of charging vehicles in the idle area, the larger the calculated recommended value. After calculating the recommended values of all idle areas through the first formula, the idle area with the largest recommended value is used as the recommended area and pushed to the mobile terminal of the target vehicle. At the same time, a suggestion message is generated. The suggestion message may include the following content, for example: It is recommended that you go to charging area A, and there are expected to be 3 idle parking spaces when you arrive.

[0062] Through this step, after the customer makes a reservation for charging, the system can recommend a suitable charging location for the customer according to the reservation time and the charging situation of each charging area when arriving, so as to further improve the charging management level of public parking spaces.

[0063] The steps for generating multiple charging rules in the idle area in this embodiment include the following:

[0064] Establish a coordinate system with time as the horizontal axis and the number of charging vehicles as the vertical axis, and draw multiple first curves in the coordinate system. The first curve is the curve of the number of charging vehicles changing with time in the idle area every day;

[0065] Extract two first curves, calculate the similarity between the two first curves. If the similarity is greater than the second threshold, then divide the two first curves into the same charging rule. Define the first curve that has been divided into a charging rule as the second curve, and extract another first curve and compare it with the second curve. If the similarities are all greater than the second threshold, then divide the extracted first curve into the same charging rule as the second curve. If it is less than or equal to the second threshold, then re-extract the first curve until the extraction of the first curve is completed. Extract two from the first curves that have not been divided into charging rules and calculate the similarity, and repeat this step until all first curves are divided into charging rules.

[0066] For the same free area, draw the first curve of each day in the coordinate system in the past, randomly select two first curves, and calculate the similarity between the two first curves. The calculation method will be introduced later. If the similarity between the two first curves is greater than the second threshold, that is, the two first curves are very similar, indicating that the charging patterns of these two days are also very close. Therefore, store them as a charging pattern. For convenience of description, define these two first curves as the second curves. Then, randomly select another first curve and compare it with the two second curves respectively to obtain the similarity. If the newly selected first curve is very similar to both second curves, then classify this first curve into the corresponding charging pattern. Continue to select until all the first curves in this free area are traversed. The first curves that have not been classified into charging patterns are re-classified using this step.

[0067] The steps for calculating the similarity of the first curves in this embodiment include the following:

[0068] Obtain the intervals where the changing trends of the two first curves are the same, and define them as comparison intervals. Calculate the difference in the number of charging vehicles at the same time points within the comparison intervals. Define the coordinate points where the difference is less than the third threshold as comparison points, and define the intervals where the comparison points continuously appear as similar intervals. Obtain the first lengths of the abscissas of each similar interval, and accumulate the first lengths to obtain the second length. Obtain the third length of the abscissa of the first curve, and use the ratio of the second length to the third length as the similarity.

[0069] Curves with the same change refer to time periods when the number of charging vehicles remains unchanged, or when it increases and decreases simultaneously. After screening out this time period, for the difference in the number of charging vehicles at the same time points, if the difference is less than the third threshold, then the quantities of the two points are considered close, and are defined as comparison points here. If the comparison points continuously appear, it indicates that in the rising and falling intervals, the two curves are also rising or falling at the same rate. In the horizontal interval, the number of vehicles charging at the current time is close. Set such an interval as the similarity interval. It can be known that the longer the length of the similar interval, the higher the similarity between the two curves. Compare the second length of the similar interval with the total third length of the first curve, and use the ratio as the similarity. Then, the larger the ratio, the higher the similarity.

[0070] Specifically, when comparing which charging pattern the current day belongs to, first draw the curve of the change in the charging quantity between the current preset time point and the current time point. Select one first curve from each charging pattern divided in the past as a representative curve, intercept the part between the preset time point and the current time point from the representative curve, compare this part with the curve of the change in the charging quantity of the current day, and use the first curve with the highest similarity as the corresponding charging pattern.

[0071] This embodiment predicts the termination SOC and parking duration based on historical charging data, including the following steps:

[0072] The historical charging data includes the parking duration, starting SOC, ending SOC, charging electricity price, and charging date information during the stay in the charging area. The charging date information includes the charging date of the vehicle, weekday information, start time point, and end time point. The vehicle information includes the license plate number and vehicle model. Based on the historical charging data, a neural network model is trained and established. The starting SOC, charging date information, and vehicle model of the target vehicle are used as input features and input into the neural network model, and the neural network model outputs the termination SOC and parking duration.

[0073] The parking duration is, for example, 1 hour or 2 hours. The charging electricity price is the electricity price set by the supplier in the charging area, which generally fluctuates with the time of day. The weekday information indicates whether the charging date is a weekday, and is represented by 0 or 1 when used as an input feature. In this embodiment, a BP neural network model is used for training and use. The BP neural network belongs to a type of artificial intelligence algorithm and has the characteristics of simple structure and strong interpretability. In other embodiments, an RBF neural network or a SOM self-organizing network can also be used as the prediction model.

[0074] In this embodiment, the preset conditions include that the current SOC of the charging vehicle is greater than the second threshold, and the current charging duration of the charging vehicle is greater than the third threshold.

[0075] As Figure 2 shown, the present invention also provides a new energy vehicle charging management system for public parking spaces. This system is used to implement the above-mentioned new energy vehicle charging management method for public parking spaces. The system includes:

[0076] A query unit. If the parking lot receives the reservation information of the target vehicle, it obtains the historical charging data of the target vehicle based on the reservation information. After the target vehicle passes through the entry area, it obtains the body picture of the target vehicle, performs image recognition on the body picture to obtain the vehicle information of the target vehicle. If it is queried that the vehicle information is bound to a mobile terminal, it obtains the historical charging data of the target vehicle;

[0077] A prediction unit. After the target vehicle starts charging in the charging area, it obtains the current SOC of the target vehicle and predicts the termination SOC and parking duration based on the historical charging data;

[0078] An adjustment unit. It calculates the ideal charging power by combining the current SOC, termination SOC, charging limit power, and parking duration. If the remaining available power in the charging area is less than the ideal charging power, it searches for low-priority vehicles that meet the preset conditions in the charging area and reduces the charging power of the low-priority vehicles to increase the remaining available power;

[0079] A reminder unit sends a reminder to a charging vehicle in a charging area whose current SOC is greater than a first threshold, and the first threshold fluctuates according to the number of waiting vehicles.

[0080] The present invention also discloses a computer storage medium storing program instructions, wherein when the program instructions run, they control the device where the computer storage medium is located to execute the above method.

[0081] It should be understood that although the steps in the flowcharts of the embodiments of the present invention are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in each embodiment may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same moment, but can be executed at different moments, and the execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least a part of other steps or sub-steps or stages of other steps.

[0082] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combinations of these technical features do not conflict, they should all be considered as the scope described in this specification.

[0083] The above embodiments only represent several implementation manners of the present invention, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several deformations and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the appended claims.

[0084] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, and improvements made within the spirit and principle of the present invention should all be included in the protection scope of the present invention.

Claims

1. A new energy vehicle charging management method for public parking spaces, characterized in that: include: The parking lot is divided into an entry area and a charging area, and if the parking lot receives reservation information of a target vehicle, historical charging data of the target vehicle is obtained based on the reservation information; After the target vehicle passes through the entry area, a body picture of the target vehicle is obtained, image recognition is performed on the body picture, and vehicle information of the target vehicle is obtained. If it is found that the vehicle information is bound to a mobile terminal, the historical charging data of the target vehicle is obtained; After the target vehicle starts charging in the charging area, obtaining the current SOC of the target vehicle, and predicting the termination SOC and parking duration based on the historical charging data; Calculate the ideal charging power by combining the current SOC, the termination SOC, the charging limit power and the parking time. If the remaining available power in the charging zone is less than the ideal charging power, search for a low-priority vehicle that meets a preset condition in the charging zone, and reduce the charging power of the low-priority vehicle to increase the remaining available power. Sending a reminder to a charging vehicle in the charging area whose current SOC is greater than a first threshold, wherein the first threshold fluctuates according to the number of waiting vehicles; After the parking lot receives the reservation information, the following steps are also included: The charging area with vacant parking spaces in the parking lot is defined as an idle area, and historical charging data of the idle area is obtained, wherein the historical charging data includes the number of vehicles charged per minute in the past, and the historical charging data is analyzed to generate multiple charging rules under the idle area, and the time point when the reservation information is received is defined as the current time point, and the charging data of each idle area on the day between the preset time point and the current time point is obtained, and the charging law of each idle area on the day is determined based on the charging data on the day, and defined as the preceding law; The historical charging data between the preset time point and the current time point in the past every day and belonging to the pre-regulation is captured, the estimated arrival time point in the reservation information is obtained, and the recommended value α of the idle area is calculated based on a first formula, the first formula being: Where K is the number of charging vehicles in the idle area at the current time point, H n , R n are the number of charging vehicles at the estimated arrival time on the nth day in the preceding rule and the number of charging vehicles at the current time, N is the number of dates belonging to the preceding rule, M is the upper limit of charging vehicles in the idle area, repeat this step to calculate the recommended value for each idle area; The vacant area with the largest recommendation value is used as a recommended area, a driving route from the entry area to the recommended area is generated, and the driving route is pushed to a mobile terminal.

2. The method according to claim 1, characterized in that: The first threshold is adjusted based on the following steps: Obtain an environmental photo of the charging area, define vehicles in the environmental photo that are outside the charging area and whose taillights are on as the waiting vehicles, count a first number of the waiting vehicles, count a second number of vehicles that have made reservations to charge in the charging area, add the first number to the second number to obtain a total number of waiting vehicles, and establish a comparison table between the total number and the first threshold value, wherein in the comparison table, a larger the total number, a smaller the first threshold value, and adjust the first threshold value based on the comparison table and the current total number of waiting vehicles.

3. The method according to claim 1, characterized in that Generating a plurality of charging rules in the idle area comprises the following steps: Establishing a coordinate system with time as the horizontal axis and the number of charged vehicles as the vertical axis, and drawing a plurality of first curves in the coordinate system, wherein the first curves are curves showing the number of charged vehicles in the idle area changing with time every day; Extract two first curves, calculate the similarity between the two first curves, if the similarity is greater than a second threshold, classify the two first curves into the same charging law, define the first curve that has been classified into the charging law as the second curve, extract another first curve, and compare it with the second curve, if the similarity is greater than the second threshold, classify the extracted first curve into the same charging law as the second curve, if it is less than or equal to the second threshold, re-extract the first curve until the extraction of the first curve is completed, extract two from the first curves that have not been classified into the charging law and calculate the similarity, repeat this step until all the first curves are classified into the charging law.

4. The method according to claim 3, characterized in that: Calculating the similarity of the first curve comprises the following steps: An interval in which the two first curves have the same change trend is obtained, which is defined as a comparison interval. A difference in the number of charging vehicles at the same time point of the two first curves within the comparison interval is calculated. A coordinate point in which the difference is less than a third threshold is defined as a comparison point. An interval in which the comparison point appears continuously is defined as a similarity interval. A first length of the horizontal coordinate of each similar interval is obtained, the first lengths are accumulated to obtain a second length, a third length of the horizontal coordinate of the first curve is obtained, and a ratio of the second length to the third length is used as the similarity.

5. The method according to claim 1, characterized in that Predicting the termination SOC and parking duration based on the historical charging data includes the following steps: The historical charging data includes the parking duration, starting SOC, ending SOC, charging electricity price and charging date information in the charging area. The charging date information includes the charging date, working day information, starting time point and ending time point of the vehicle. The vehicle information includes the license plate number and vehicle model. A neural network model is trained and established based on the historical charging data. The starting SOC, charging date information and vehicle model of the target vehicle are input into the neural network model as input features. The neural network model outputs the ending SOC and parking duration.

6. The method according to claim 1, characterized in that The preset conditions include that the current SOC of the charging vehicle is greater than a fourth threshold, and the current charging time of the charging vehicle is greater than a fifth threshold.

7. The method according to claim 1, characterized in that Image recognition is performed on the vehicle body image based on the CNN model.

8. A new energy vehicle charging management system for public parking spaces, used to implement the method according to any one of claims 1 to 7, characterized in that: include: The query unit, if the parking lot receives the reservation information of the target vehicle, obtains the historical charging data of the target vehicle based on the reservation information, obtains the body picture of the target vehicle after the target vehicle passes through the entry area, performs image recognition on the body picture, and obtains the vehicle information of the target vehicle, and if it is found that the vehicle information is bound to a mobile terminal, obtains the historical charging data of the target vehicle, and after the parking lot receives the reservation information, defines the charging area with vacant parking spaces in the parking lot as an idle area, obtains the historical charging data of the idle area, and the historical charging data includes the number of vehicles charged per minute in the past. The amount of charging is analyzed, and a plurality of charging rules under the idle area are generated. The time point when the reservation information is received is defined as the current time point, and the charging data of each idle area between the preset time point and the current time point on the day are obtained. Based on the charging data of the day, the charging rule that occurs in each idle area on the day is determined and defined as the preceding rule. The historical charging data between the preset time point and the current time point and belonging to the preceding rule are captured every day in the past, and the estimated arrival time point in the reservation information is obtained. The recommended value α of the idle area is calculated based on the first formula, and the first formula is: Where K is the number of charging vehicles in the idle area at the current time point, H n , R n are the number of charging vehicles at the estimated arrival time on the nth day in the preceding rule and the number of charging vehicles at the current time, N is the number of days belonging to the preceding rule, M is the upper limit of charging vehicles in the idle area, repeat this step, calculate the recommended value of each idle area, take the idle area with the largest recommended value as the recommended area, generate the driving route from the entry area to the recommended area, and push it to the mobile terminal; A prediction unit, after the target vehicle starts charging in the charging area, obtains the current SOC of the target vehicle, and predicts the termination SOC and parking duration based on the historical charging data; an adjusting unit, which calculates an ideal charging power in combination with the current SOC, the termination SOC, the charging limit power and the parking duration, and if the remaining available power in the charging zone is less than the ideal charging power, searches for a low-priority vehicle that meets a preset condition in the charging zone, and reduces the charging power of the low-priority vehicle to increase the remaining available power; The reminder unit sends a reminder to a charging vehicle in the charging area whose current SOC is greater than a first threshold, wherein the first threshold fluctuates according to the number of waiting vehicles.

9. A computer storage medium, characterized in that: The computer storage medium stores program instructions, wherein when the program instructions are executed, the device where the computer storage medium is located is controlled to execute the method according to any one of claims 1 to 7.

Images