Charging pile site selection methods, devices, equipment and storage media

Abstract

This invention relates to artificial intelligence technology and discloses a method, apparatus, device, and storage medium for selecting charging pile sites. The method includes: based on charging data of electric vehicles within a target area, statistically analyzing the set of vehicles with the highest charging demand and constructing a distribution map of the largest charging vehicles; based on charging records of each charging station, obtaining the user distribution range of each charging station; based on the charging convenience level of users in each region under the combined influence of different charging stations, constructing a user charging convenience map, and obtaining a charging difficulty map based on a preset threshold; obtaining the central area of ​​the charging difficulty map through clustering, acquiring the set of human geographical environment types in the central area, using a pre-constructed charging area scale prediction model for prediction, and selecting the location corresponding to the smallest environmental type as the charging pile site selection area. This invention can improve the effectiveness of charging pile site selection and increase the coordination between charging pile site selection and scale.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, and in particular to a method, apparatus, equipment, and computer-readable storage medium for selecting charging pile sites. Background Technology

[0002] With the rise of environmental awareness, new energy vehicles have developed rapidly. However, the scale and distribution of charging piles have become important factors restricting the development of new energy vehicles. At present, the site selection method of charging piles is affected by multiple factors and has a strong subjective opinion. Usually, places with high vehicle density are selected, which has a low site selection effect and easily leads to unreasonable configuration of charging pile scale, resulting in poor balance of charging pile utilization. Summary of the Invention

[0003] This invention provides a method, apparatus, equipment, and storage medium for selecting charging pile sites. Its main purpose is to improve the effectiveness of charging pile site selection and increase the coordination between the site selection and scale of charging piles.

[0004] To achieve the above objectives, the present invention provides a method for selecting a charging pile site, comprising:

[0005] By using the data points of the preset charging application, the charging data of electric vehicles in the target area is obtained, and the electric vehicles are divided into daytime charging type, nighttime charging type and irregular charging type according to the charging data, and the number of vehicles of each type is counted.

[0006] Based on the preset intersection and union strategy and the number of vehicles of each type, the set of vehicles with the maximum charging demand in the target area is obtained, and a distribution map of the maximum electricity-consuming vehicles is constructed based on the permanent address information of each vehicle in the charging application and the administrative region layer of the target area.

[0007] Based on the maximum electric vehicle distribution map, the charging records of each existing charging station are obtained, and the distribution range of loyal users of each charging station is obtained based on the preset clustering strategy and the permanent address information of each vehicle in the charging records.

[0008] By utilizing the distribution range of loyal users of each charging station and the preset distance ratio-level configuration rules, the distribution map of the largest electric vehicle is configured with layers to obtain a user charging convenience map.

[0009] The user charging convenience map is eroded according to a preset threshold to obtain charging difficulty areas. Based on the vehicle distribution density in the charging difficulty areas, the cluster centers of the charging difficulty areas are obtained, and the human geographical environment type set of the cluster centers within a preset range is obtained.

[0010] Using a pre-trained charging area size prediction model, the size of the charging difficulty area and the set of human geographical environment types are predicted to obtain the predicted charging area size under each human geographical environment type in the set of human geographical environment types.

[0011] The location corresponding to the human geographical environment type with the smallest predicted charging area size is selected as the site selection area for charging piles.

[0012] Optionally, obtaining the distribution range of loyal users of each charging station based on a preset clustering strategy and the permanent address information of each vehicle in the charging records includes:

[0013] Based on the charging records of each charging station and the permanent address information of each vehicle, the distribution range of primary users is filtered out.

[0014] Based on the permanent address information of each vehicle, calculate the distance between each vehicle and the charging station;

[0015] The number of times each vehicle is charged at the charging station within a preset time period is obtained, and the distance and the number of charging times are calculated according to a preset charging dependence formula to obtain the degree of dependence of each vehicle on the charging station.

[0016] The distribution range of the first-level users is eroded according to a preset dependency threshold to obtain the distribution range of the second-level users. Then, according to a preset clustering strategy, each user in the distribution range of the second-level users is clustered to obtain the distribution range of the loyal users of the charging station.

[0017] Optionally, before using the pre-trained charging area size prediction model to predict the size of the charging difficulty area and the set of human geographical environment types, the method further includes:

[0018] Based on the construction scale and average utilization rate of each pre-built charging station, the effective scale label of each charging station is obtained, and the human geographical environment type of each charging station is obtained. The training sample set is constructed using the human geographical environment type, the distribution range of loyal users, and the effective scale label of each charging station.

[0019] The pre-built charging station scale prediction model is used to extract a training sample one by one for network forward propagation calculation to obtain the predicted charging scale, and the loss value between the predicted charging scale and the effective scale label corresponding to the training sample is calculated using a preset cross-entropy algorithm.

[0020] Calculate the model parameters when the loss value is minimized, and perform network inverse update on the model parameters to obtain an optimized charging area size prediction model;

[0021] Determine the convergence of the loss value;

[0022] If the loss value fails to converge, return to the steps described above: using the pre-built charging area size prediction model to extract a training sample sequentially for network forward propagation calculation to obtain the predicted charging area size.

[0023] The optimized charging area size prediction model is iteratively updated;

[0024] When the loss value converges, the finally updated optimized charging area size prediction model is used as the trained charging area size prediction model.

[0025] Optionally, obtaining the set of vehicles with the maximum charging demand in the target area based on a preset intersection and union strategy and the number of vehicles of each type includes:

[0026] Based on the number of vehicles charging during the day and the number of vehicles charging at night, the charging type with the larger number of vehicles is selected as the primary demand type.

[0027] Calculate the union of vehicles with primary demand type and vehicles with intermittent charging type, and use it as the set of vehicles with the maximum charging demand in the target area.

[0028] Optionally, the distribution range of loyal users at each of the charging stations and a preset distance are utilized.

[0029] The scaling-level configuration rules are used to configure layers on the distribution map of the largest electric vehicles to obtain a user charging convenience map, including:

[0030] Based on the preset distance-level configuration rules, the distribution of loyal users at each charging station is determined.

[0031] The area is divided into levels;

[0032] The average level of each user under the influence of each charging station is obtained, and a heat map is applied to the distribution map of the largest electric vehicle based on the average level to obtain a user charging convenience map.

[0033] Optionally, before selecting the location corresponding to the human geographical environment type with the smallest predicted charging area as the site selection area for the charging pile, the method further includes:

[0034] Determine whether the predicted size of the smallest charging area is less than the preset construction limit; when the predicted size of the smallest charging area is less than or equal to the construction limit, it is determined that the charging difficulty area does not need to build charging piles.

[0035] When the predicted size of the smallest charging area is greater than the construction limit, the location corresponding to the human geographical environment type with the smallest predicted size of the charging area is selected as the site selection area for the charging pile.

[0036] Optionally, the step of using a pre-trained charging area size prediction model to predict the size of the charging difficulty area and the set of human geographical environment types, and obtaining the predicted charging area size for each human geographical environment type in the set of human geographical environment types, includes:

[0037] From the set of human geographical environment types, one human geographical environment type is selected in sequence. The pre-trained charging area size prediction model is used to perform feature extraction operations on the range size of the charging difficulty area and the environment type to obtain range quantification parameters and a set of environmental feature sequences.

[0038] A fully connected operation is performed on the range quantization parameters and the set of environmental feature sequences to obtain the predicted scale of the charging area corresponding to the environmental type.

[0039] To address the above problems, the present invention also provides a charging pile site selection device, the device comprising:

[0040] The vehicle statistics module is used to acquire charging data of electric vehicles in the target area by using the data points of the preset charging application, and to classify the electric vehicles into daytime charging type, nighttime charging type and irregular charging type according to the charging data, and to count the number of vehicles of each type. According to the preset intersection and union strategy and the number of vehicles of each type, the module obtains the set of vehicles with the maximum charging demand in the target area, and constructs a distribution map of the maximum electricity-consuming vehicles based on the permanent address information of each vehicle in the charging application and the administrative region layer of the target area.

[0041] The user charging convenience acquisition module is used to acquire the charging records of each existing charging station according to the maximum electric vehicle distribution map, and obtain the distribution range of loyal users of each charging station according to the preset clustering strategy and the permanent address information of each vehicle in the charging records. It also uses the distribution range of loyal users of each charging station and the preset distance ratio-level configuration rules to configure the maximum electric vehicle distribution map into layers to obtain the user charging convenience map.

[0042] The candidate environment type acquisition module is used to erode the user charging convenience map according to a preset threshold to obtain charging difficulty areas, and obtain the cluster center of the charging difficulty areas according to the vehicle distribution density in the charging difficulty areas, and obtain the human geographical environment type set of the cluster center within a preset range.

[0043] The scale prediction module is used to use a pre-trained charging area scale prediction model to predict the size of the charging difficulty area and the set of human geographical environment types, obtain the predicted scale of the charging area under each human geographical environment type in the set of human geographical environment types, and select the location corresponding to the human geographical environment type with the smallest predicted charging area scale as the charging pile site selection area.

[0044] To address the above problems, the present invention also provides an electronic device, the electronic device comprising:

[0045] At least one processor; and,

[0046] A memory communicatively connected to the at least one processor; wherein,

[0047] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the charging pile site selection method described above.

[0048] To address the aforementioned problems, the present invention also provides a computer-readable storage medium storing at least one computer program, which is executed by a processor in an electronic device to implement the charging pile site selection method described above.

[0049] This invention analyzes charging patterns and constructs a maximum vehicle distribution map by intersecting and unifying user charging data from different time periods. This allows for understanding the demand scale and style within different charging stations, avoiding the problem of low utilization rates caused by excessively large-scale charging pile construction. Furthermore, this invention constructs a user charging convenience map for each user at different charging stations, selecting areas with charging difficulties as potential sites based on the ease of charging for each user. Additionally, a pre-trained charging area size prediction model predicts the minimum size based on the environmental type of each location, assuming a similar distribution range of loyal users, thus enabling reasonable planning. Therefore, this invention provides a charging pile site selection method, apparatus, equipment, and storage medium that improves the effectiveness of charging pile site selection and enhances the coordination between charging pile site selection and scale. Attached Figure Description

[0050] Figure 1 This is a flowchart illustrating a charging pile site selection method according to an embodiment of the present invention.

[0051] Figure 2 This is a detailed flowchart illustrating one step of a charging pile site selection method according to an embodiment of the present invention.

[0052] Figure 3 This is a detailed flowchart illustrating one step of a charging pile site selection method according to an embodiment of the present invention.

[0053] Figure 4 This is a functional block diagram of a charging pile site selection device provided in an embodiment of the present invention;

[0054] Figure 5 This is a schematic diagram of the structure of an electronic device for implementing the charging pile site selection method according to an embodiment of the present invention.

[0055] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0056] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0057] This application provides a charging pile site selection method. In this application, the executing entity of the charging pile site selection method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the charging pile site selection method can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0058] Reference Figure 1 The diagram shown is a flowchart illustrating a charging pile site selection method according to an embodiment of the present invention. In this embodiment, the charging pile site selection method includes:

[0059] S1. Using the data points of the preset charging application, obtain the charging data of electric vehicles in the target area, and according to the charging data, classify the electric vehicles into daytime charging type, nighttime charging type and irregular charging type, and count the number of vehicles of each type.

[0060] In this embodiment of the invention, charging data for each electric vehicle within a target area can be obtained through data embedding on the server corresponding to a charging application, mini-program, or webpage. This charging data includes vehicle charging time, charging duration, charging station number, and personal information of the electric vehicle user. The user's personal information may include their permanent address information. This permanent address information can be a home address or office address manually set by the user, or it can be locations frequently visited by the user based on big data statistics.

[0061] It should be understood that the usage rate of charging stations in different locations varies at different times. For example, charging stations in office areas and large shopping malls have a higher usage rate during the day, while charging stations in residential areas have a higher usage rate at night. Considering the usage efficiency of each charging station and the charging styles of users in different areas, this embodiment of the invention statistically analyzes the charging patterns of each electric vehicle based on the charging data of each electric vehicle, and classifies them according to the charging patterns, dividing the electric vehicles of different users into daytime charging type, nighttime charging type, and irregular charging type.

[0062] S2. Based on the preset intersection and union strategy and the number of vehicles of each type, obtain the vehicle set with the maximum charging demand in the target area, and construct the maximum power consumption vehicle distribution map based on the permanent address information of each vehicle in the charging application and the administrative region layer of the target area.

[0063] Considering the scale and usage rate of charging pile construction, this embodiment of the invention analyzes the charging style of users in the target area by counting the number of vehicles with different charging types.

[0064] In detail, in this embodiment of the invention, obtaining the set of vehicles with the maximum charging demand in the target area based on a preset intersection and union strategy and the number of vehicles of each type includes:

[0065] Based on the number of vehicles charging during the day and the number of vehicles charging at night, the charging type with the larger number of vehicles is selected as the primary demand type.

[0066] Calculate the union of vehicles with primary demand type and vehicles with intermittent charging type, and use it as the set of vehicles with the maximum charging demand in the target area.

[0067] For example, in the target area of ​​this embodiment of the invention, there are 100,000 vehicles, of which 20,000 are charged during the day, 30,000 are charged intermittently, and 50,000 are charged at night. It can be estimated that the maximum charging demand in the target area will not exceed 80,000 vehicles. In this embodiment of the invention, the 80,000 vehicles can be marked at various locations on the geographic layer of the target area using a density map to obtain a map of the distribution of vehicles with the maximum power consumption.

[0068] S3. Based on the maximum electric vehicle distribution map, obtain the charging records of each existing charging station, and based on the preset clustering strategy and the permanent address information of each vehicle in the charging records, obtain the distribution range of loyal users of each charging station.

[0069] In this embodiment of the invention, each charging station that has been constructed is first obtained from the distribution map of the largest electric vehicles. In this embodiment of the invention, each charging station is a public facility such as a public parking and charging lot, and private charging areas are not considered.

[0070] Then, the charging records of each charging station are obtained. By viewing these records, the distribution range of loyal users for each charging station can be seen from the maximum electric vehicle distribution map. This distribution range of loyal users can represent the true influence range of the charging station.

[0071] For details, please refer to the following: Figure 2 As shown in this embodiment of the invention, obtaining the distribution range of loyal users of each charging station based on a preset clustering strategy and the permanent address information of each vehicle in the charging records includes:

[0072] S31. Based on the charging records of each charging station and the permanent address information of each vehicle, filter out the distribution range of primary users.

[0073] S32. Calculate the distance between each vehicle and the charging station based on the permanent address information of each vehicle;

[0074] S33. Obtain the number of times each vehicle is charged at the charging station within a preset time period, and calculate the distance and the number of charging times according to the preset charging dependency formula to obtain the degree of dependence of each vehicle on the charging station.

[0075] S34. Perform range erosion on the primary user distribution range according to a preset dependency threshold to obtain the secondary user distribution range, and cluster each user in the secondary user distribution range according to a preset clustering strategy to obtain the loyal user distribution range of the charging station.

[0076] The primary user distribution range obtained in this embodiment of the invention is all historical charging users of the charging station, which has a large degree of randomness and cannot represent the influence coverage of a charging station. Only by looking at the user's dependence on the charging station can an accurate judgment be made. In this embodiment of the invention, the degree of dependence is evaluated by two aspects: distance and preset time period, such as the number of times used within a month. Distance is an inverse proportional parameter and the number of times used is a direct proportional parameter.

[0077] This invention employs range erosion to delete portions with dependency levels below a preset dependency threshold, yielding a secondary user distribution range that indicates user dependence on the charging station. Finally, this invention uses a clustering strategy to cluster the secondary user distribution range, removing special points at the edges of the range and retaining the main body, ultimately obtaining the loyal user distribution range of the charging station.

[0078] S4. Using the distribution range of loyal users of each charging station and the preset distance ratio-level configuration rules, the distribution map of the largest electric vehicle is configured with layers to obtain a user charging convenience map.

[0079] In detail, in this embodiment of the invention, the step of configuring the maximum electric vehicle distribution map into layers using the distribution range of loyal users of each charging station and preset distance ratio-level configuration rules to obtain a user charging convenience map includes:

[0080] Based on the preset distance ratio-level configuration rules, the distribution range of loyal users at each charging station is classified into levels.

[0081] The average level of each user under the influence of each charging station is obtained, and a heat map is applied to the distribution map of the largest electric vehicle based on the average level to obtain a user charging convenience map.

[0082] In this embodiment of the invention, the distance ratio-level configuration rule divides the distribution range of loyal users into levels 5, 4...1 from the inside out. The distance ratio can be defined as 20% of the distance from the center point of the distribution range to the outermost point, serving as a dividing line for each level. Therefore, if a user is within the range of two charging stations, at levels 1 and 2 respectively, the user's charging quality can be 1.5.

[0083] Finally, the average level values ​​are used to create a heat map over the distribution map of the vehicles with the highest electricity consumption, resulting in a user charging convenience map.

[0084] S5. Erode the user charging convenience map according to a preset threshold to obtain charging difficulty areas, and obtain the cluster center of the charging difficulty areas according to the vehicle distribution density in the charging difficulty areas, and obtain the human geographical environment type set of the cluster center within a preset range.

[0085] In this embodiment of the invention, to ensure the charging quality for users, areas with an average charging level of N or higher can be eliminated to obtain charging difficulty areas. Then, new charging stations are constructed within these charging difficulty areas. In this embodiment, N can be 2, and can be changed according to specific circumstances.

[0086] In this embodiment of the invention, in order to ensure the coverage effect of the charging pile site selection, a location within a preset range of the center point of the difficult charging area, such as within 2 kilometers, is selected.

[0087] In this embodiment of the invention, the mean clustering algorithm is used to find the center point of the charging difficulty area. Then, the various environmental types in the center point, such as residential area, business area, undeveloped area, etc., are searched to obtain a set of human geographical environment types.

[0088] S6. Using a pre-trained charging area size prediction model, predict the size of the charging difficulty area and the set of human geographical environment types to obtain the predicted charging area size under each human geographical environment type in the set of human geographical environment types.

[0089] In detail, in this embodiment of the invention, step S6 includes:

[0090] From the set of human geographical environment types, one human geographical environment type is selected in sequence. The pre-trained charging area size prediction model is used to perform feature extraction operations on the range size of the charging difficulty area and the environment type to obtain range quantification parameters and a set of environmental feature sequences.

[0091] A fully connected operation is performed on the range quantization parameters and the set of environmental feature sequences to obtain the predicted scale of the charging area corresponding to the environmental type.

[0092] In this embodiment of the invention, the feature extraction network of the charging area size prediction model is used to perform quantization and convolutional pooling operations on the range of the charging difficulty area and the environment type to obtain the range quantization parameters and the set of environmental feature sequences. Then, through the fully connected layer of the charging area size prediction model, each environmental feature sequence is combined with the range quantization parameters, and the scale of each combined feature is predicted by the function parameters trained in the model to obtain the predicted charging area size of the environment type.

[0093] Further reference Figure 3 As shown in this embodiment of the invention, before using a pre-trained charging area size prediction model to predict the size of the charging difficulty area and the set of human geographical environment types, the method includes:

[0094] S601. Based on the construction scale and average utilization rate of each pre-built charging station, obtain the effective scale label of each charging station, and obtain the human geographical environment type of each charging station. Use the human geographical environment type, the distribution range of loyal users and the effective scale label of each charging station to construct a training sample set.

[0095] S602. Using the pre-built charging station scale prediction model, extract one of the training samples in sequence and perform network forward propagation calculation to obtain the predicted charging scale. Then, use the preset cross-entropy algorithm to calculate the loss value between the predicted charging scale and the effective scale label corresponding to the training sample.

[0096] S603. Calculate the model parameters when the loss value is minimized, and perform network inverse update on the model parameters to obtain an optimized charging area size prediction model.

[0097] S604. Determine the convergence of the loss value;

[0098] If the loss value does not converge, return to step S602 above and iteratively update the optimized charging area size prediction model;

[0099] When the loss value converges, S605, the finally updated optimized charging area size prediction model is used as the trained charging area size prediction model.

[0100] In this embodiment of the invention, after obtaining the distribution range of loyal users of each charging station, the construction scale, average utilization rate and human geographical environment type of each charging station can be obtained. The human geographical environment type includes a type name and various data parameters in the type, such as [Business District Type: Development Price**, Transportation Convenience**, Traffic Flow**, Topographical Factors**] etc.

[0101] Therefore, this embodiment of the invention calculates the effective size of each charging area by constructing the scale and average utilization rate, and sets the effective size as the effective size label. The human geographical environment type and coverage area of ​​each charging area are used as the main sample to construct a training sample set. Then, using a pre-constructed neural network-based charging area size prediction model, the training sample set is trained through loss backpropagation to obtain an optimized charging area size prediction model. During the training process, the model is further optimized through loss backpropagation.

[0102] The training process of the model is monitored using a loss value supervision method. When the loss value converges, a fully trained charging area size prediction model is obtained. This model can predict the effective size of charging stations based on the distribution range of loyal users and the environmental type.

[0103] S7. Select the location corresponding to the human geographical environment type with the smallest predicted charging area as the site selection area for charging piles.

[0104] This invention, through comparison, selects the location with the smallest predicted charging area size corresponding to the environmental type as the charging pile site selection area, which can effectively improve the utilization rate after the charging pile is constructed. In this invention, the charging pile site selection area and the predicted charging area size can be output simultaneously, increasing the coordination between the charging pile site selection and the scale.

[0105] Furthermore, in another embodiment of the present invention, before step S7, the method further includes:

[0106] Determine whether the predicted size of the smallest charging area is less than the preset construction limit;

[0107] When the predicted size of the smallest charging area is less than or equal to the construction quota, it is determined that no charging piles need to be built in the charging difficulty area.

[0108] When the predicted size of the smallest charging area is greater than the construction limit, the location corresponding to the human geographical environment type with the smallest predicted size of the charging area is selected as the site selection area for the charging pile.

[0109] In this embodiment of the invention, the construction quota is the minimum number of charging piles to be constructed in the charging area, such as 5. If the predicted size of the charging area is less than 5, it indicates that the area of ​​the charging difficulty area is very small or contains very few users. Considering the public construction cost, it can be basically ignored.

[0110] This invention analyzes charging patterns and constructs a maximum vehicle distribution map by intersecting and unifying user data from different time periods. This allows for understanding the demand scale and style within different charging stations, avoiding the problem of low utilization rates caused by excessively large-scale charging pile construction. Furthermore, this invention constructs a user charging convenience map for each user at different charging stations, selecting potential sites based on the ease of charging for each user. Additionally, a pre-trained charging area size prediction model predicts the minimum size based on the environmental type of each location, assuming a similar distribution range of loyal users, thus enabling reasonable planning. Therefore, this invention provides a charging pile site selection method that improves the effectiveness of charging pile site selection and enhances the coordination between charging pile site selection and scale.

[0111] like Figure 4 The diagram shown is a functional block diagram of a charging pile site selection device provided in an embodiment of the present invention.

[0112] The charging pile site selection device 100 of the present invention can be installed in an electronic device. Depending on the functions implemented, the charging pile site selection device 100 may include a vehicle statistics module 101, a user charging convenience acquisition module 102, a candidate environment type acquisition module 103, and a scale prediction module 104. The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and are stored in the memory of the electronic device.

[0113] In this embodiment, the functions of each module / unit are as follows:

[0114] The vehicle statistics module 101 is used to obtain the charging data of electric vehicles in the target area by using the data embedding points of the preset charging application, and to divide the electric vehicles into daytime charging type, nighttime charging type and irregular charging type according to the charging data, and to count the number of vehicles of each type. According to the preset intersection and union strategy and the number of vehicles of each type, the set of vehicles with the maximum charging demand in the target area is obtained, and the maximum power consumption vehicle distribution map is constructed according to the permanent address information of each vehicle in the charging application and the administrative region layer of the target area.

[0115] The user charging convenience acquisition module 102 is used to acquire the charging records of each existing charging station according to the maximum electric vehicle distribution map, and obtain the distribution range of loyal users of each charging station according to the preset clustering strategy and the permanent address information of each vehicle in the charging records. It also uses the distribution range of loyal users of each charging station and the preset distance ratio-level configuration rules to perform layer configuration on the maximum electric vehicle distribution map to obtain the user charging convenience map.

[0116] The candidate environment type acquisition module 103 is used to erode the user charging convenience map according to a preset threshold to obtain charging difficulty areas, and obtain the cluster center of the charging difficulty areas according to the vehicle distribution density in the charging difficulty areas, and obtain the human geographical environment type set of the cluster center within a preset range.

[0117] The scale prediction module 104 is used to use a pre-trained charging area scale prediction model to predict the size of the charging difficulty area and the set of human geographical environment types, obtain the predicted scale of the charging area under each human geographical environment type in the set of human geographical environment types, and select the location corresponding to the human geographical environment type with the smallest predicted charging area as the charging pile site selection area.

[0118] In detail, each module in the charging pile site selection device 100 described in this application embodiment adopts the same method as described above during use. Figures 1 to 3 The method used is the same as the charging pile site selection method described in the article and can produce the same technical effect, so it will not be repeated here.

[0119] like Figure 5 The diagram shown is a schematic diagram of the structure of an electronic device 1 for implementing a charging pile site selection method according to an embodiment of the present invention.

[0120] The electronic device 1 may include a processor 10, a memory 11, a communication bus 12 and a communication interface 13, and may also include a computer program, such as a charging pile site selection program, stored in the memory 11 and capable of running on the processor 10.

[0121] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device 1, connecting various components of the electronic device through various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., executing a charging pile location program) and calls data stored in the memory 11 to perform various functions of the electronic device and process data.

[0122] The memory 11 includes at least one type of readable storage medium, including flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of an electronic device, such as a portable hard drive. In other embodiments, the memory 11 can be an external storage device of the electronic device, such as a plug-in portable hard drive, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, etc. Furthermore, the memory 11 can include both internal and external storage units of the electronic device. The memory 11 can be used not only to store application software and various types of data installed on the electronic device, such as the code for a charging station site selection program, but also to temporarily store data that has been output or will be output.

[0123] The communication bus 12 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into an address bus, a data bus, a control bus, etc. The bus is configured to enable communication between the memory 11 and at least one processor 10, etc.

[0124] The communication interface 13 is used for communication between the electronic device 1 and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, Bluetooth interface, etc.), typically used to establish communication connections between the electronic device and other electronic devices. The user interface may be a display, an input unit (such as a keyboard), or, optionally, a standard wired or wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device and to display a visual user interface.

[0125] Figure 5 Only electronic devices with components are shown; it will be understood by those skilled in the art that... Figure 5 The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0126] For example, although not shown, the electronic device 1 may also include a power supply (such as a battery) to power various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management device, thereby enabling functions such as charging management, discharging management, and power consumption management. The power supply may also include one or more DC or AC power supplies, recharging devices, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0127] It should be understood that the embodiments described are for illustrative purposes only and are not limited to this structure in the scope of the patent application.

[0128] The charging pile location selection program stored in the memory 11 of the electronic device 1 is a combination of multiple instructions, which, when run in the processor 10, can achieve the following:

[0129] By using the data points of the preset charging application, the charging data of electric vehicles in the target area is obtained, and the electric vehicles are divided into daytime charging type, nighttime charging type and irregular charging type according to the charging data, and the number of vehicles of each type is counted.

[0130] Based on the preset intersection and union strategy and the number of vehicles of each type, the set of vehicles with the maximum charging demand in the target area is obtained, and a distribution map of the maximum electricity-consuming vehicles is constructed based on the permanent address information of each vehicle in the charging application and the administrative region layer of the target area.

[0131] Based on the maximum electric vehicle distribution map, the charging records of each existing charging station are obtained, and the distribution range of loyal users of each charging station is obtained based on the preset clustering strategy and the permanent address information of each vehicle in the charging records.

[0132] By utilizing the distribution range of loyal users of each charging station and the preset distance ratio-level configuration rules, the distribution map of the largest electric vehicle is configured with layers to obtain a user charging convenience map.

[0133] The user charging convenience map is eroded according to a preset threshold to obtain charging difficulty areas. Based on the vehicle distribution density in the charging difficulty areas, the cluster centers of the charging difficulty areas are obtained, and the human geographical environment type set of the cluster centers within a preset range is obtained.

[0134] Using a pre-trained charging area size prediction model, the size of the charging difficulty area and the set of human geographical environment types are predicted to obtain the predicted charging area size under each human geographical environment type in the set of human geographical environment types.

[0135] The location corresponding to the human geographical environment type with the smallest predicted charging area size is selected as the site selection area for charging piles.

[0136] Specifically, the specific implementation method of the processor 10 for the above instructions can be referred to the description of the relevant steps in the corresponding embodiment of the accompanying drawings, and will not be repeated here.

[0137] Furthermore, if the modules / units integrated in the electronic device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0138] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor of an electronic device, can perform the following:

[0139] By using the data points of the preset charging application, the charging data of electric vehicles in the target area is obtained, and the electric vehicles are divided into daytime charging type, nighttime charging type and irregular charging type according to the charging data, and the number of vehicles of each type is counted.

[0140] Based on the preset intersection and union strategy and the number of vehicles of each type, the set of vehicles with the maximum charging demand in the target area is obtained, and a distribution map of the maximum electricity-consuming vehicles is constructed based on the permanent address information of each vehicle in the charging application and the administrative region layer of the target area.

[0141] Based on the maximum electric vehicle distribution map, the charging records of each existing charging station are obtained, and the distribution range of loyal users of each charging station is obtained based on the preset clustering strategy and the permanent address information of each vehicle in the charging records.

[0142] By utilizing the distribution range of loyal users of each charging station and the preset distance ratio-level configuration rules, the distribution map of the largest electric vehicle is configured with layers to obtain a user charging convenience map.

[0143] The user charging convenience map is eroded according to a preset threshold to obtain charging difficulty areas. Based on the vehicle distribution density in the charging difficulty areas, the cluster centers of the charging difficulty areas are obtained, and the human geographical environment type set of the cluster centers within a preset range is obtained.

[0144] Using a pre-trained charging area size prediction model, the size of the charging difficulty area and the set of human geographical environment types are predicted to obtain the predicted charging area size under each human geographical environment type in the set of human geographical environment types.

[0145] The location corresponding to the human geographical environment type with the smallest predicted charging area size is selected as the site selection area for charging piles.

[0146] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0147] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0148] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0149] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0150] Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be embraced within the invention. No appended diagram markings in the claims should be construed as limiting the scope of the claims.

[0151] The blockchain referred to in this invention is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Essentially, a blockchain is a decentralized database, a chain of data blocks linked together using cryptographic methods. Each data block contains information about a batch of network transactions, used to verify the validity of the information (anti-counterfeiting) and generate the next block. A blockchain can include an underlying blockchain platform, a platform product service layer, and an application service layer.

[0152] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0153] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices recited in a system claim may also be implemented by a single unit or device through software or hardware. The terms "first," "second," etc., are used to indicate names and do not indicate any specific order.

[0154] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for selecting the location of a charging pile, characterized in that, The method includes: By using the data points of the preset charging application, the charging data of electric vehicles in the target area is obtained, and the electric vehicles are divided into daytime charging type, nighttime charging type and irregular charging type according to the charging data, and the number of vehicles of each type is counted. Based on the preset intersection and union strategy and the number of vehicles of each type, the set of vehicles with the maximum charging demand in the target area is obtained, and a distribution map of the maximum electricity-consuming vehicles is constructed based on the permanent address information of each vehicle in the charging application and the administrative region layer of the target area. Based on the maximum electric vehicle distribution map, the charging records of each existing charging station are obtained, and the distribution range of loyal users of each charging station is obtained based on the preset clustering strategy and the permanent address information of each vehicle in the charging records. By utilizing the distribution range of loyal users of each charging station and the preset distance ratio-level configuration rules, the distribution map of the largest electric vehicle is configured with layers to obtain a user charging convenience map. The user charging convenience map is eroded according to a preset threshold to obtain charging difficulty areas. Based on the vehicle distribution density in the charging difficulty areas, the cluster centers of the charging difficulty areas are obtained, and the human geographical environment type set of the cluster centers within a preset range is obtained. Using a pre-trained charging area size prediction model, the size of the charging difficulty area and the set of human geographical environment types are predicted to obtain the predicted charging area size under each human geographical environment type in the set of human geographical environment types. The location corresponding to the human geographical environment type with the smallest predicted charging area size is selected as the site selection area for charging piles.

2. The charging pile site selection method as described in claim 1, characterized in that, The step of obtaining the distribution range of loyal users for each charging station based on a preset clustering strategy and the permanent address information of each vehicle in the charging records includes: Based on the charging records of each charging station and the permanent address information of each vehicle, the distribution range of primary users is filtered out. Based on the permanent address information of each vehicle, calculate the distance between each vehicle and the charging station; The number of times each vehicle is charged at the charging station within a preset time period is obtained, and the distance and the number of charging times are calculated according to a preset charging dependence formula to obtain the degree of dependence of each vehicle on the charging station. The distribution range of the first-level users is eroded according to a preset dependency threshold to obtain the distribution range of the second-level users. Then, according to a preset clustering strategy, each user in the distribution range of the second-level users is clustered to obtain the distribution range of the loyal users of the charging station.

3. The charging pile site selection method as described in claim 1, characterized in that, Before using the pre-trained charging area size prediction model to predict the size of the charging difficulty area and the set of human geographical environment types, the method further includes: Based on the construction scale and average utilization rate of each pre-built charging station, the effective scale label of each charging station is obtained, and the human geographical environment type of each charging station is obtained. The training sample set is constructed using the human geographical environment type, the distribution range of loyal users, and the effective scale label of each charging station. The pre-built charging station scale prediction model is used to extract a training sample one by one for network forward propagation calculation to obtain the predicted charging scale, and the loss value between the predicted charging scale and the effective scale label corresponding to the training sample is calculated using a preset cross-entropy algorithm. Calculate the model parameters when the loss value is minimized, and perform network inverse update on the model parameters to obtain an optimized charging area size prediction model; Determine the convergence of the loss value; When the loss value does not converge, return to the above steps of extracting a training sample from the pre-built charging area size prediction model and performing forward propagation calculation to obtain the predicted charging area, and iteratively update the optimized charging area size prediction model. When the loss value converges, the finally updated optimized charging area size prediction model is used as the trained charging area size prediction model.

4. The charging pile site selection method as described in claim 1, characterized in that, The step of obtaining the set of vehicles with the greatest charging demand in the target area based on a preset intersection and union strategy and the number of vehicles of each type includes: Based on the number of vehicles charging during the day and the number of vehicles charging at night, the charging type with the larger number of vehicles is selected as the primary demand type. Calculate the union of vehicles with primary demand type and vehicles with intermittent charging type, and use it as the set of vehicles with the maximum charging demand in the target area.

5. The charging pile site selection method as described in claim 1, characterized in that, The method involves configuring layers on the distribution map of the largest electric vehicle users using the distribution range of loyal users at each charging station and a preset distance-ratio-level configuration rule, to obtain a user charging convenience map, including: Based on the preset distance ratio-level configuration rules, the distribution range of loyal users at each charging station is classified into levels. The average level of each user under the influence of each charging station is obtained, and a heat map is applied to the distribution map of the largest electric vehicle based on the average level to obtain a user charging convenience map.

6. The charging pile site selection method as described in claim 1, characterized in that, Before selecting the location corresponding to the human geographical environment type with the smallest predicted charging area as the site selection area for charging piles, the method further includes: Determine whether the predicted size of the smallest charging area is less than the preset construction limit; When the predicted size of the smallest charging area is less than or equal to the construction quota, it is determined that no charging piles need to be built in the charging difficulty area. When the predicted size of the smallest charging area is greater than the construction limit, the location corresponding to the human geographical environment type with the smallest predicted size of the charging area is selected as the site selection area for the charging pile.

7. The charging pile site selection method as described in claim 1, characterized in that, The pre-trained charging area size prediction model is used to predict the size of the charging difficulty area and the set of human geographical environment types, obtaining the predicted charging area size for each human geographical environment type in the set of human geographical environment types, including: From the set of human geographical environment types, one human geographical environment type is selected in sequence. The pre-trained charging area size prediction model is used to perform feature extraction operations on the range size of the charging difficulty area and the environment type to obtain range quantification parameters and a set of environmental feature sequences. A fully connected operation is performed on the range quantization parameters and the set of environmental feature sequences to obtain the predicted scale of the charging area corresponding to the environmental type.

8. A charging pile site selection device, characterized in that, The device includes: The vehicle statistics module is used to acquire charging data of electric vehicles in the target area by using the data points of the preset charging application, and to classify the electric vehicles into daytime charging type, nighttime charging type and irregular charging type according to the charging data, and to count the number of vehicles of each type. According to the preset intersection and union strategy and the number of vehicles of each type, the module obtains the set of vehicles with the maximum charging demand in the target area, and constructs a distribution map of the maximum electricity-consuming vehicles based on the permanent address information of each vehicle in the charging application and the administrative region layer of the target area. The user charging convenience acquisition module is used to acquire the charging records of each existing charging station according to the maximum electric vehicle distribution map, and obtain the distribution range of loyal users of each charging station according to the preset clustering strategy and the permanent address information of each vehicle in the charging records. It also uses the distribution range of loyal users of each charging station and the preset distance ratio-level configuration rules to configure the maximum electric vehicle distribution map into layers to obtain the user charging convenience map. The candidate environment type acquisition module is used to erode the user charging convenience map according to a preset threshold to obtain charging difficulty areas, and obtain the cluster center of the charging difficulty areas according to the vehicle distribution density in the charging difficulty areas, and obtain the human geographical environment type set of the cluster center within a preset range. The scale prediction module is used to use a pre-trained charging area scale prediction model to predict the size of the charging difficulty area and the set of human geographical environment types, obtain the predicted scale of the charging area under each human geographical environment type in the set of human geographical environment types, and select the location corresponding to the human geographical environment type with the smallest predicted charging area scale as the charging pile site selection area.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the charging pile site selection method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the charging pile site selection method as described in any one of claims 1 to 7.

Images