Charging pile intelligent planning method and system based on big data

Abstract

The invention is suitable for the technical field of charging pile planning, and especially relates to a charging pile intelligent planning method and system based on big data, and the method comprises the steps: S100, defining elements in a preset planning region, the elements at least comprising a community, an office building and an industrial park, obtaining the video monitoring data of the entrances and exits of the elements, extracting the vehicle features, and obtaining the video monitoring data of the entrances and exits of the elements; wherein the vehicle features at least comprise a license plate, a vehicle logo and a vehicle contour; s200, based on the license plate, counting the total number of the new energy vehicles entering the elements in the video monitoring data by taking a natural day as a unit; and if the total number of the license plates is an odd number, mounting the corresponding license plates in the elements. According to the method, the demand density of the charging piles can be determined through statistics of the supply-demand ratio, the configuration of the charging piles is better optimized, so that data support is provided for charging station site selection, the positions of the charging stations are accurately planned through calculation of the charging amount gaps of the elements, the service coverage rate is increased, and the user satisfaction degree is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of charging pile planning, and in particular to a charging pile intelligent planning method and system based on big data. Background Art

[0002] With the development of new energy vehicle technology, the demand for charging piles is increasing. In addition to private charging piles, the number of commercial charging stations is also booming. The planning of commercial charging stations and charging piles involves many aspects. For example, detailed demand analysis and forecasting are needed to understand the number of electric vehicles in the region, the distribution of charging piles, and the charging habits of users in order to predict charging demand and determine the final site selection. The site selection should give priority to high-density areas, major transportation hubs, public facilities, and commercial areas to meet the charging needs of different users.

[0003] Therefore, “how to calculate the charging capacity gap in a region” is the technical problem that the present invention needs to solve. Summary of the invention

[0004] The purpose of the present invention is to provide a charging pile intelligent planning method and system based on big data, so as to solve the problem of "how to calculate the charging capacity gap in a region" raised in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions: A charging pile intelligent planning method based on big data, the method comprising: S100: defining elements in a preset planning area, wherein the elements at least include: a residential area, an office building, and an industrial park, acquiring video surveillance data at the entrances and exits of the elements, and extracting vehicle features, wherein the vehicle features at least include: a license plate, a vehicle logo, and a vehicle outline; S200: Based on the license plate, the total number of new energy vehicles entering the element in the video surveillance data is counted in units of natural days. If the total number is an odd number, the corresponding license plate is mounted in the element, and the total number of license plates is calculated; S300: using existing resources, determining the number of private charging piles in the element, and calculating the supply-demand ratio, wherein the supply-demand ratio is the quotient of the number divided by the total number of license plates, locating at least two candidate locations based on a preset site selection rule, and marking the planned site selection of the charging station based on the deviation of the supply-demand ratio from the candidate location; S400: Compare the vehicle logo and vehicle outline with the existing database, read out the battery pack power corresponding to each vehicle feature, and accumulate the total battery pack power, collect the total charging capacity of the private charging pile within the preset time period in the element, calculate the charging capacity gap of the element, and correct the configuration of the charging station.

[0006] Furthermore, the S100 includes: Mark the candidate points in the preset planning area and define the audience range corresponding to each candidate point; The portion of the planned area that is outside the audience range is deleted, and the audience range is divided into a plurality of elements.

[0007] Furthermore, the S100 further includes: Identify vehicle posture, extract a single-frame frontal image of a vehicle passing a preset position from video surveillance data, and separate the vehicle from the background; The image obtained after stripping is input into a trained deep convolutional neural network, and the output result is filled into a pre-constructed comparison table, which at least includes: a license plate column, a vehicle logo column and a contour column.

[0008] Further, the S200 includes: Record the time when the vehicle enters the element, count the number of entries into the element each day, and insert the number into the comparison table as a note column; Based on the license plate column, delete the data in the row where the license plate is a fuel truck; Based on the remark column, delete the data in the row where the number of times is an even number; The total number of license plates in the comparison table is accumulated and mounted into the element.

[0009] Further, the S300 includes: The supply-demand ratio is segmented, and different evaluation scores are assigned to the supply-demand ratio of each segment, so as to establish a supply-demand ratio evaluation score ladder diagram; Determine the factors affecting the planning of charging piles, including transportation, catering and entertainment, and generate reference scores; The candidate point with the largest sum of reference score and evaluation score is determined as the planning site.

[0010] Furthermore, the S300 further includes: The difference between the total number and the quantity is defined as the charging pile gap; Based on the configuration, it is determined whether the number of charging piles in the planned site is greater than the charging pile gap, and the determination result is sent to a preset terminal.

[0011] Further, the S400 includes: Establishing a database of vehicle outlines with vehicle logos as the catalog, wherein each vehicle outline in the database corresponds to a set of attribute data, wherein the attribute data at least includes the vehicle model and the battery pack power; Construct a feedback mechanism for vehicle-grid interaction, divide feedback parking spaces, recruit voluntary registrants based on a preset charging platform, predict the peak period of grid demand, issue feedback instructions to the recruited voluntary registrants based on load changes during the peak period, open the feedback parking spaces, and give rewards determined based on the feedback mechanism.

[0012] Furthermore, the system comprises: An extraction module is used to define elements in a preset planning area, wherein the elements include at least: a residential area, an office building, and an industrial park, obtain video surveillance data at the entrances and exits of the elements, and extract vehicle features, wherein the vehicle features include at least: a license plate, a vehicle logo, and a vehicle outline; A mounting module, for counting the total number of new energy vehicles entering the element in the video surveillance data based on the license plate and taking natural days as the unit, and if the total number of occurrences is an odd number, mounting the corresponding license plate into the element and calculating the total number of license plates; A marking module, used to determine the number of private charging piles in the element by using existing resources, and calculate the supply-demand ratio, wherein the supply-demand ratio is the quotient of the number divided by the total number of license plates, locate at least two candidate locations based on a preset site selection rule, and mark the planned site selection of the charging station based on the deviation of the supply-demand ratio from the candidate location; The correction module is used to compare the vehicle logo and vehicle outline with the existing database, read the battery pack power corresponding to each vehicle feature, and accumulate the total battery pack power, collect the total charging capacity of the private charging pile within a preset time period in the element, calculate the charging capacity gap of the element, and correct the configuration of the charging station.

[0013] Furthermore, the extraction module includes: A delineation unit, used to mark the candidate points in a preset planning area and delineate the audience range corresponding to each candidate point; A division unit, used for deleting the portion of the planned area outside the audience range and dividing the audience range into a plurality of elements; A stripping unit, used for identifying the posture of a vehicle, extracting a single-frame front image of a vehicle passing a preset position from the video surveillance data, and stripping the vehicle from the background; The output unit is used to input the stripped image into the trained deep convolutional neural network, and fill the output result into a pre-built comparison table, which at least includes: a license plate column, a vehicle logo column and a contour column.

[0014] Furthermore, the mounting module includes: An insertion unit, used to record the time when the vehicle enters the element, and count the number of times the vehicle enters the element every day, and insert the number of times as a note column into the comparison table; A deleting unit, configured to delete the data in the row where the license plate is a fuel truck based on the license plate column, and to delete the data in the row where the number of times is an even number based on the remarks column; The accumulation unit is used to accumulate the total number of license plates in the comparison table and mount the total number into the element.

[0015] Compared with the prior art, the present invention has the following beneficial effects: 1. By defining the characteristics of elements and vehicles, it is possible to reasonably configure charging piles according to the usage of new energy vehicles in each element. By obtaining video surveillance data, it is possible to count the number of new energy vehicles in the element and accurately predict demand, optimize resource allocation, and improve charging investment efficiency. By counting the supply-demand ratio, it is possible to determine the demand density of charging piles and better optimize the configuration of charging piles, thereby providing data support for the site selection of charging stations. By calculating the charging capacity gap of the elements, it is possible to further optimize the configuration of charging stations, improve service coverage, and enhance user satisfaction. 2. By establishing a feedback mechanism, it helps to balance the grid load, reduce grid pressure, greatly improve the stability and balance of the grid, and indirectly ensure the safety of electricity use for residents in the planned area. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A flowchart of a charging pile intelligent planning method based on big data provided by an embodiment of the present invention; Figure 2 A first sub-process flowchart of a charging pile intelligent planning method based on big data provided by an embodiment of the present invention; Figure 3 A second sub-process flowchart of the charging pile intelligent planning method based on big data provided by an embodiment of the present invention; Figure 4 A third sub-flow chart of the charging pile intelligent planning method based on big data provided by an embodiment of the present invention; Figure 5 A fourth sub-flow chart of the charging pile intelligent planning method based on big data provided by an embodiment of the present invention; Figure 6 A block diagram of the composition of a charging pile intelligent planning system based on big data provided by an embodiment of the present invention; Figure 7 A block diagram of the components of the extraction module in the charging pile intelligent planning system based on big data provided by an embodiment of the present invention; Figure 8 A block diagram of the components of the mounting module in the charging pile intelligent planning system based on big data provided by an embodiment of the present invention; Fig. 9 A block diagram of the composition of the marking module in the charging pile intelligent planning system based on big data provided by an embodiment of the present invention; Fig.10 A block diagram of the composition of the correction module in the charging pile intelligent planning system based on big data provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with 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 intended to limit the present invention.

[0018] In Example 1, Figure 1 The implementation process of the charging pile intelligent planning method based on big data provided by an embodiment of the present invention is shown, and is described in detail below: S100: defining elements in a preset planning area, wherein the elements include at least residential areas, office buildings and industrial parks, acquiring video surveillance data at the entrances and exits of the elements, and extracting vehicle features, wherein the vehicle features include at least license plates, vehicle logos and vehicle outlines.

[0019] First, it is necessary to determine the location of the candidate points within the preset planning area. The preset planning area can be based on the city or the district. The candidate points are the locations where charging stations can be built. Elements are defined within the audience range of the candidate points. The elements are residential areas, office buildings, etc. The video surveillance data at the entrances and exits of the elements is obtained to determine the number of new energy vehicles in the elements and extract vehicle features, where the vehicle features are the unique features of each vehicle. By extracting vehicle features, the number of times each vehicle enters the element can be counted to avoid repeated counting, thereby improving the accuracy of the number of new energy vehicles.

[0020] Among vehicle characteristics, the license plate is the vehicle license plate number, the vehicle logo is the brand of the vehicle, and the vehicle outline is the shape of the vehicle, which are used to determine the model of the vehicle.

[0021] S200: Based on the license plate, the total number of new energy vehicles entering the element in the video surveillance data is counted in units of natural days. If the total number is an odd number, the corresponding license plate is mounted in the element and the total number of license plates is calculated.

[0022] Taking natural days as the unit, by utilizing video surveillance data, we can find vehicles with new energy license plates and count the number of new energy vehicles entering the element.

[0023] For example, when vehicle A enters a community and only appears once in the video surveillance data, and vehicle A enters the community; that is, vehicle A did not leave the community that day, it can be identified as a vehicle of a community user, where a natural day is one day.

[0024] S300: Using existing resources, determine the number of private charging piles in the element and calculate the supply-demand ratio, where the supply-demand ratio is the quotient of the number divided by the total number of license plates. Based on preset site selection rules, locate at least two candidate locations, and mark the planned site selection of the charging station based on the deviation of the supply-demand ratio from the candidate locations.

[0025] Utilize existing resources to calculate the number of private charging stations within the element. The existing resources here can be obtained from the power supply department or through manual statistics.

[0026] Continuing with the above example, after calculating how many new energy vehicles there are in the community, continue to determine the number of private charging piles, and divide the number of private charging piles by the number of new energy vehicles to get the supply-demand ratio. Based on the preset site selection rules, determine the candidate points in the planning area, and according to the supply-demand ratio, deviate from the candidate points and select the planning site from the candidate points.

[0027] Among them, the preset site selection rules are the locations that can be used for the construction of charging stations, and the candidate locations are the locations of the charging stations after preliminary screening; in actual use, not all vacant land in the planning area can be used for the construction of charging stations, which also requires coordination with specific urban planning, charging resource allocation, power grid construction, etc.; after preliminary screening, multiple locations that meet the hard conditions and can be used for the construction of charging stations will be selected, which are the candidate locations.

[0028] S400: Compare the vehicle logo and vehicle outline with the existing database, read out the battery pack power corresponding to each vehicle feature, and accumulate the total battery pack power, collect the total charging capacity of the private charging pile within the preset time period in the element, calculate the charging capacity gap of the element, and correct the configuration of the charging station.

[0029] The vehicle characteristics are compared with the existing database to find out the brand and model of each new energy vehicle, and the battery pack power of the new energy vehicle is read from the database, and the sum of the battery pack power of all new energy vehicles in the element is calculated, and then the total power consumption of the private charging piles in the element within the preset time period is obtained from the power supply department, so as to determine the total charging capacity of the private charging piles. The preset time period can be a natural day or a week.

[0030] By subtracting the total charge from the total degree of the battery pack in the element, the charge gap can be calculated. In other words, car owners corresponding to the charge gap generally do not charge within this element.

[0031] In Example 2, Figure 2 The implementation process of the charging pile intelligent planning method based on big data provided by an embodiment of the present invention is shown, and S100 is described in detail below, as follows: S101: Mark the candidate points in a preset planning area and define the audience range corresponding to each candidate point.

[0032] Candidate points are marked in the planning area, and the audience range of each candidate point is determined. The audience range here can be an approximate number.

[0033] S102: deleting the portion of the planned area that is outside the audience range, and dividing the audience range into a plurality of elements.

[0034] Divide the planning area into the audience range and the part outside the part, and only divide the audience range part into several elements.

[0035] In Example 3, Figure 2 The implementation process of the charging pile intelligent planning method based on big data provided by an embodiment of the present invention is shown, and S100 is further described in detail below, as follows: S103: Identify the vehicle posture, extract a single-frame front image of the vehicle passing through a preset position from the video surveillance data, and separate the vehicle from the background.

[0036] Through convolutional neural networks or mobile tracking technology, the vehicle posture is identified and a single-frame frontal image of the vehicle passing through a preset position is captured, where the preset position may be a gate entering an element or a preset threshold line, and the vehicle is separated from the background.

[0037] The advantage of doing this is that it can reduce the processing burden of video surveillance data and improve the accuracy of vehicle feature recognition.

[0038] S104: Input the stripped image into a trained deep convolutional neural network, and fill the output result into a pre-built comparison table, wherein the comparison table at least includes: a license plate column, a vehicle logo column, and a contour column.

[0039] The frontal image obtained after peeling is input into the trained deep convolutional neural network to obtain the output result, which should include the license plate number, vehicle logo, vehicle outline and vehicle registration information, etc. The output result is filled into the pre-built comparison table.

[0040] In Example 4, Figure 3 The implementation process of the charging pile intelligent planning method based on big data provided by an embodiment of the present invention is shown, and S200 is described in detail below, as follows: S201: Record the time when the vehicle enters the element, count the number of times the vehicle enters the element every day, and insert the number of times as a note column into the comparison table.

[0041] The time when the vehicle enters the element is recorded, and the number of times the vehicle enters the element each day is counted, and the number is inserted into the comparison table as a note.

[0042] If a vehicle enters and exits an element during a fixed time period every day, then the vehicle is also the vehicle of a user within the element. By recording the number of times, the number of new energy vehicles within the element and the frequency of use can be more intuitively displayed.

[0043] S202: Based on the license plate column, delete the data in the row where the license plate is a fuel truck, and based on the remarks column, delete the data in the row where the number of times is an even number.

[0044] In the license plate column, delete the license plate of the gasoline vehicle and the data in its row. Based on the remarks column, delete the data with an even number of times and the data in its row. What remains is the data of the new energy vehicle with an odd frequency of occurrence.

[0045] S203: Accumulate the total number of license plates in the comparison table and mount the total number into the element.

[0046] Record the total number of license plates remaining in the comparison table and determine the total number corresponding to each element.

[0047] In Example 5, Figure 4 The implementation process of the charging pile intelligent planning method based on big data provided by an embodiment of the present invention is shown, and S300 is described in detail below, as follows: S301: Segmenting the supply-demand ratio, assigning different evaluation scores to the supply-demand ratio of each segment, and establishing a supply-demand ratio evaluation score ladder diagram.

[0048] The supply-demand ratio is segmented, and the evaluation score corresponding to each segment is determined. The larger the supply-demand ratio, the higher the evaluation score, which means that the element has a greater demand for charging piles. According to the segmentation, the supply-demand ratio and the evaluation score are summarized to establish an evaluation score ladder chart.

[0049] S302: Determine the influencing factors of charging pile planning, where the influencing factors include: transportation, catering and entertainment, and generate a reference score.

[0050] A reference score is generated based on the traffic, living facilities and entertainment near the candidate point. If the traffic near the candidate point is smooth and the living facilities are complete, the reference score corresponding to the candidate point should be higher.

[0051] S303: Determine the candidate point with the largest sum of the reference score and the evaluation score as the planning site.

[0052] The reference score and the evaluation score are superimposed, and the candidate point with the largest superposition result is determined as the planning site.

[0053] In Example 6, Figure 4 The implementation process of the charging pile intelligent planning method based on big data provided by an embodiment of the present invention is shown, and S300 is further described in detail below, as follows: S304: defining the difference between the total number and the number as a charging pile gap; The difference between the total number of license plates in an element and the number of charging piles in the element is defined as the charging pile gap, where the total number of license plates in the element is the number of new energy vehicles in the element, and the charging pile gap is the number of users who have not installed charging piles.

[0054] S305: Based on the configuration, determine whether the number of charging piles in the planned site is greater than the charging pile gap, and send the determination result to a preset terminal.

[0055] If the number of charging piles is greater than the charging pile gap, it means that the charging station can meet the charging needs of the elements in the preset area. If it is not greater, it means that the number of charging piles in the charging station is small. Regardless of the result, the judgment result should be sent to the preset terminal, where the preset terminal can be the management terminal of the planner.

[0056] In Example 7, Figure 5 The implementation process of the charging pile intelligent planning method based on big data provided by an embodiment of the present invention is shown, and S400 is further described in detail below, as follows: S401: Establishing a database of vehicle outlines with vehicle logos as catalogs, wherein each vehicle outline in the database corresponds to a set of attribute data, wherein the attribute data at least includes a vehicle model and a battery pack power.

[0057] After extracting the vehicle features of the car logo and car outline, the car logo is retrieved to determine the car outline, thereby determining the vehicle attribute data, and then determining the battery pack power of the new energy vehicle. By determining the battery pack power and calculating the charging capacity gap, it can provide decision support for the planning of the number of charging piles in the site selection.

[0058] S402: Construct a feedback mechanism for vehicle-grid interaction, divide feedback parking spaces, recruit voluntary registrants based on a preset charging platform, predict the peak period of grid demand, issue feedback instructions to the recruited voluntary registrants based on the load changes during the peak period, open the feedback parking spaces, and give rewards determined based on the feedback mechanism.

[0059] Construct a feedback mechanism for vehicle-grid interaction, where the feedback mechanism is to guide new energy vehicles back to the planned site (charging station) through the preset charging platform during periods of high electricity load, and transmit the electric energy stored in the new energy vehicles back to the power grid in the form of reverse flow.

[0060] First of all, it is necessary to determine the feedback parking spaces in the planning and site selection, and it is also necessary to determine the registered users, that is, the voluntary registrants, in the preset charging platform. The preset charging platform is not limited. According to the public data of the power supply department, the peak period of electricity demand is determined, and feedback instructions are issued to the voluntary registrants in advance, so that the voluntary registrants can go to the feedback parking spaces for reverse power exchange. During the trough period, the voluntary registrants can still charge through the feedback parking spaces; of course, the voluntary registrants should be given corresponding rewards after the reverse power exchange.

[0061] In actual use, the feedback parking spaces require the use of special two-way charging piles. Volunteer registrants only need to keep the charging gun connected to the new energy vehicle and use the preset charging platform to achieve reverse power exchange.

[0062] Figure 6 The structure diagram of the charging pile intelligent planning system based on big data provided by an embodiment of the present invention is shown. The charging pile intelligent planning system based on big data 1 includes: The extraction module 11 is used to define elements in a preset planning area, wherein the elements include at least: a residential area, an office building and an industrial park, obtain video surveillance data at the entrance and exit of the elements, and extract vehicle features, wherein the vehicle features include at least: a license plate, a vehicle logo and a vehicle outline; The mounting module 12 is used to count the total number of new energy vehicles entering the element in the video surveillance data based on the license plate and in units of natural days. If the total number is an odd number, the corresponding license plate is mounted in the element and the total number of license plates is calculated; The marking module 13 is used to determine the number of private charging piles in the element by using existing resources, and calculate the supply-demand ratio, where the supply-demand ratio is the quotient of the number divided by the total number of license plates, locate at least two candidate locations based on a preset site selection rule, and mark the planned site selection of the charging station based on the deviation of the supply-demand ratio from the candidate location; The correction module 14 is used to compare the vehicle logo and vehicle outline with the existing database, read the battery pack power corresponding to each vehicle feature, and accumulate the total battery pack power, collect the total charging capacity of the private charging pile within the preset time period in the element, calculate the charging capacity gap of the element, and correct the configuration of the charging station.

[0063] Figure 7The structure diagram of the charging pile intelligent planning system based on big data provided by an embodiment of the present invention is shown, and the extraction module 11 includes: The delineation unit 111 is used to mark the candidate points in the preset planning area and delineate the audience range corresponding to each candidate point; A division unit 112, configured to delete the portion of the planned area outside the audience range and divide the audience range into a plurality of elements; The stripping unit 113 is used to identify the vehicle posture, intercept a single frame front image of the vehicle passing through a preset position from the video monitoring data, and strip the vehicle from the background; The output unit 114 is used to input the stripped image into the trained deep convolutional neural network, and fill the output result into a pre-built comparison table, which at least includes: a license plate column, a vehicle logo column and a contour column.

[0064] Figure 8 The structure diagram of the charging pile intelligent planning system based on big data provided by an embodiment of the present invention is shown, and the mounting module 12 includes: Insertion unit 121, used to record the time when the vehicle enters the element, count the number of times the vehicle enters the element every day, and insert the number of times as a note column into the comparison table; A deleting unit 122, configured to delete the data in the row where the license plate is a fuel truck based on the license plate column, and to delete the data in the row where the number of times is an even number based on the remarks column; The accumulation unit 123 is used to accumulate the total number of license plates in the comparison table and mount the total number into the element.

[0065] Fig. 9 The structure diagram of the charging pile intelligent planning system based on big data provided by an embodiment of the present invention is shown, and the marking module 13 includes: An establishing unit 131 is used to segment the supply-demand ratio, assign different evaluation scores to the supply-demand ratio of each segment, and establish a supply-demand ratio evaluation score ladder diagram; A generating unit 132 is used to determine the influencing factors of charging pile planning, wherein the influencing factors include: transportation, catering and entertainment, and generate a reference score; A planning unit 133, configured to determine the candidate point with the largest sum of the reference score and the evaluation score as the planning site; A comparison unit 134, configured to compare the total capacity of the charging piles in the planned site based on the configuration; A definition unit 135, configured to define a difference between the total number and the quantity as a charging pile gap; The judgment unit 136 is used to judge whether the total capacity of the charging piles is greater than the charging pile gap, and send the judgment result to a preset terminal.

[0066] Fig.10 The structural block diagram of the charging pile intelligent planning system based on big data provided by an embodiment of the present invention is shown, and the correction module 14 includes: A corresponding unit 141 is used to establish a database of vehicle profiles with vehicle logos as the directory, wherein each vehicle profile in the database corresponds to a set of attribute data, wherein the attribute data at least includes a vehicle model and a battery pack power; The open unit 142 is used to build a feedback mechanism for vehicle-grid interaction, divide feedback parking spaces, recruit voluntary registrants based on a preset charging platform, predict the peak period of grid demand, issue feedback instructions to the recruited voluntary registrants based on the load changes during the peak period, open the feedback parking spaces, and give rewards determined based on the feedback mechanism.

[0067] The extraction module 11 is mainly used to complete step S100, the mounting module 12 is mainly used to complete step S200, the marking module 13 is mainly used to complete step S300, and the correction module 14 is mainly used to complete step S400; The demarcation unit 111 is mainly used to complete step S101, the division unit 112 is mainly used to complete step S102, the stripping unit 113 is mainly used to complete step S103, and the output unit 114 is mainly used to complete step S104; The inserting unit 121 is mainly used to complete step S201, the deleting unit 122 is mainly used to complete step S202, and the accumulating unit 123 is mainly used to complete step S203; The establishing unit 131 is mainly used to complete step S301, the generating unit 132 is mainly used to complete step S302, the planning unit 133 is mainly used to complete step S303, the comparing unit 134 is mainly used to complete step S304, the defining unit 135 is mainly used to complete step S305, and the judging unit 136 is mainly used to complete step S306; The corresponding unit 141 is mainly used to complete step S401, and the open unit 142 is mainly used to complete step S402.

[0068] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0069] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

[0070] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A charging pile intelligent planning method based on big data, characterized in that: The method comprises: S100: defining elements in a preset planning area, wherein the elements at least include: a residential area, an office building, and an industrial park, acquiring video surveillance data at the entrances and exits of the elements, and extracting vehicle features, wherein the vehicle features at least include: a license plate, a vehicle logo, and a vehicle outline; S200: Based on the license plate, the total number of new energy vehicles entering the element in the video surveillance data is counted in units of natural days. If the total number is an odd number, the corresponding license plate is mounted in the element, and the total number of license plates is calculated; S300: using existing resources, determining the number of private charging piles in the element, and calculating the supply-demand ratio, wherein the supply-demand ratio is the quotient of the number divided by the total number of license plates, locating at least two candidate locations based on a preset site selection rule, and marking the planned site selection of the charging station based on the deviation of the supply-demand ratio from the candidate location; S400: Compare the vehicle logo and vehicle outline with the existing database, read out the battery pack power corresponding to each vehicle feature, and accumulate the total battery pack power of the element, collect the total charging capacity of the private charging pile within the preset time period in the element, calculate the charging capacity gap of the element, and correct the configuration of the charging station.

2. The intelligent planning method for charging piles based on big data according to claim 1 is characterized in that: The S100 includes: Mark the candidate points in the preset planning area and define the audience range corresponding to each candidate point; The portion of the planned area that is outside the audience range is deleted, and the audience range is divided into a plurality of elements.

3. The intelligent planning method for charging piles based on big data according to claim 1 is characterized in that: The S100 further includes: Identify vehicle posture, extract a single-frame frontal image of a vehicle passing a preset position from video surveillance data, and separate the vehicle from the background; The image obtained after stripping is input into a trained deep convolutional neural network, and the output result is filled into a pre-constructed comparison table, which at least includes: a license plate column, a vehicle logo column and a contour column.

4. The intelligent planning method for charging piles based on big data according to claim 2 is characterized in that: The S200 includes: Record the time when the vehicle enters the element, count the number of entries into the element each day, and insert the number into the comparison table as a note column; Based on the license plate column, delete the data in the row where the license plate is a fuel truck; Based on the remark column, delete the data in the row where the number of times is an even number; The total number of license plates in the comparison table is accumulated and mounted into the element.

5. The intelligent planning method for charging piles based on big data according to claim 1 is characterized in that: The S300 includes: The supply-demand ratio is segmented, and different evaluation scores are assigned to the supply-demand ratio of each segment, so as to establish a ladder diagram of supply-demand ratio evaluation scores; Determine the factors affecting the planning of charging piles, including transportation, catering and entertainment, and generate reference scores; The candidate point with the largest sum of reference score and evaluation score is determined as the planning site.

6. The intelligent planning method for charging piles based on big data according to claim 5 is characterized in that: The S300 further includes: The difference between the total number and the quantity is defined as the charging pile gap; Based on the configuration, it is determined whether the number of charging piles in the planned site is greater than the charging pile gap, and the determination result is sent to a preset terminal.

7. The charging pile intelligent planning method based on big data according to claim 1 is characterized in that: The S400 includes: Establishing a vehicle profile database with vehicle logos as catalogs, wherein each vehicle profile in the database corresponds to a set of attribute data, wherein the attribute data at least includes: vehicle model and battery pack power; Construct a feedback mechanism for vehicle-grid interaction, divide feedback parking spaces, recruit voluntary registrants based on a preset charging platform, predict the peak period of grid demand, issue feedback instructions to the recruited voluntary registrants based on load changes during the peak period, open the feedback parking spaces, and give rewards determined based on the feedback mechanism.

8. The intelligent planning system of charging piles based on big data is characterized by: The system comprises: An extraction module is used to define elements in a preset planning area, wherein the elements include at least: a residential area, an office building, and an industrial park, obtain video surveillance data at the entrances and exits of the elements, and extract vehicle features, wherein the vehicle features include at least: a license plate, a vehicle logo, and a vehicle outline; A mounting module, for counting the total number of new energy vehicles entering the element in the video surveillance data based on the license plate and taking natural days as the unit, and if the total number of occurrences is an odd number, mounting the corresponding license plate into the element and calculating the total number of license plates; A marking module, used to determine the number of private charging piles in the element by using existing resources, and calculate the supply-demand ratio, wherein the supply-demand ratio is the quotient of the number divided by the total number of license plates, locate at least two candidate locations based on a preset site selection rule, and mark the planned site selection of the charging station based on the deviation of the supply-demand ratio from the candidate location; The correction module is used to compare the vehicle logo and vehicle outline with the existing database, read the battery pack power corresponding to each vehicle feature, and accumulate the total battery pack power, collect the total charging capacity of the private charging pile within a preset time period in the element, calculate the charging capacity gap of the element, and correct the configuration of the charging station.

9. According to the big data-based charging pile intelligent planning system of claim 8, the extraction module comprises: A delineation unit, used to mark the candidate points in a preset planning area and delineate the audience range corresponding to each candidate point; A division unit, used for deleting the portion of the planned area outside the audience range and dividing the audience range into a plurality of elements; A stripping unit, used to identify the vehicle posture, extract a single-frame front image of the vehicle passing through a preset position from the video surveillance data, and strip the vehicle from the background; The output unit is used to input the stripped image into the trained deep convolutional neural network, and fill the output result into a pre-built comparison table, which at least includes: a license plate column, a vehicle logo column and a contour column.

10. According to the big data-based charging pile intelligent planning system of claim 8, the mounting module comprises: An insertion unit, used to record the time when the vehicle enters the element, and count the number of times the vehicle enters the element every day, and insert the number of times as a note column into the comparison table; A deleting unit, configured to delete the data in the row where the license plate is a fuel truck based on the license plate column, and to delete the data in the row where the number of times is an even number based on the remarks column; The accumulation unit is used to accumulate the total number of license plates in the comparison table and mount the total number into the element.

Images