Vehicle and pile information matching method and device based on charging behavior, equipment and medium

Abstract

The present application relates to electric vehicle charging technology field, disclose a method, device, equipment and medium based on charging behavior of vehicle pile information matching, the method comprises: obtaining the vehicle charging data of electric vehicle in the target region, the vehicle charging data includes the vehicle position information when the electric vehicle charging;Vehicle charging data is clustered based on vehicle position information, determine the clustering category corresponding to the vehicle charging data;The clustering category is filtered based on the vehicle charging data in each clustering category, determine the public pile category in the clustering category;The distance between the clustering area corresponding to the public pile category and each charging station in the target region is calculated;If the distance is less than the preset distance threshold, then the vehicle charging data in the public pile category is matched with the corresponding charging station.The present application carries out information fusion between electric vehicle and charging station, optimizes the charging strategy of charging station, improves the charging efficiency.

Description

Technical Field

[0001] This invention relates to the field of electric vehicle charging technology, and more specifically to a method, device, equipment, and medium for matching vehicle-charging station information based on charging behavior. Background Technology

[0002] Currently, the data of each entity in the "vehicle-charging-road-network" system are in different forms and isolated from each other. Meanwhile, the usage behavior of electric vehicles, such as driving and charging, is highly flexible and has complex patterns. This results in poor perception and prediction capabilities of adjustable charging and discharging resources, making it difficult to support the efficient guidance and scheduling of large-scale electric vehicles participating in V2G.

[0003] As a fundamental supporting infrastructure for new energy vehicles, public charging stations face challenges due to the independent data transmission between the charging stations and the vehicles themselves. This leads to newly installed public charging stations being unable to effectively meet the charging needs of vehicles within the designated area. Furthermore, the lack of data independence between public charging stations and charging vehicles makes it difficult to optimize charging strategies at charging stations, resulting in insufficient service capacity. Summary of the Invention

[0004] In view of this, the present invention provides a method, device, equipment and medium for matching vehicle and charging station information based on charging behavior, in order to solve the problem that the data between existing charging stations and charging vehicles is independent, resulting in low charging efficiency of charging stations and poor charging experience for vehicle users.

[0005] In a first aspect, the present invention provides a vehicle-charging station information matching method based on charging behavior, the method comprising:

[0006] Obtain vehicle charging data for electric vehicles within the target area. The vehicle charging data includes the vehicle's location information when the electric vehicle is charging.

[0007] Based on vehicle information, vehicle charging data is clustered to determine the corresponding cluster category of vehicle charging data.

[0008] The cluster categories are filtered based on the vehicle charging data in each cluster category to determine the public charging pile category within each cluster category;

[0009] Calculate the distance between the cluster region corresponding to the public pile category and each charging station in the target region;

[0010] If the distance is less than the preset distance threshold, the vehicle charging data in the public charging pile category will be matched with the corresponding charging station.

[0011] The present invention provides a vehicle-charging station information matching method based on charging behavior, which has the following advantages:

[0012] This invention utilizes the locational relationship between charging vehicles and charging stations to match them. The matching data allows for further optimization of new charging station locations, improving charging efficiency. A well-planned layout of charging stations also reduces waiting time for vehicles, enhancing user experience. This invention uses a pre-trained matching model to cluster discrete charging vehicle data according to vehicle location. Then, based on charging data within each cluster (e.g., total number of charges), it determines public charging station categories. Finally, it matches vehicle data within each public charging station category with charging stations based on their distance relationship. This vehicle-to-charging-station matching process ensures accuracy, laying the foundation for subsequent planning of new charging station locations and optimization of charging station strategies.

[0013] In one optional implementation, vehicle charging data is clustered based on vehicle information to determine the cluster category corresponding to the vehicle charging data, including:

[0014] The latitude and longitude coordinates in the vehicle location information are processed using a pre-trained clustering model;

[0015] If the number of vehicle location information items within a cluster area is greater than a preset value, then the vehicle charging data corresponding to the vehicle location information will be classified into a cluster category.

[0016] Specifically, when clustering discrete vehicle charging data, the vehicle location information in the vehicle charging data is clustered, and the discrete vehicle charging data is divided according to a predetermined clustering region. If the number of data contained in a certain region is greater than a preset value, the vehicle charging data in that region is classified into one category.

[0017] In one optional implementation, the cluster categories are filtered based on vehicle charging data within each cluster category to determine the public charging pile category within the cluster category, including:

[0018] Based on the vehicle charging data in each cluster category, determine the total number of charging times and the first number of vehicles corresponding to the cluster category, where the total number of charging times is the total number of times the vehicle charging data corresponds to the vehicle charging data, and the first number of vehicles is the number of vehicles that have participated in charging corresponding to the vehicle charging data.

[0019] If the total number of charging times is greater than the first preset number of charging times and the number of vehicles is greater than the first preset number of vehicles, then the corresponding cluster category will be determined as the public charging pile category.

[0020] Specifically, in the actual charging process, charging stations include public charging stations and private charging stations. Therefore, in order to separate the location categories corresponding to public charging stations from the clustering results, this step uses the total number of vehicle charging times and the number of the first vehicle to be charged in each location category to filter the public charging station categories, and finally determines the public charging station categories within the location categories. By filtering the clustering categories to determine the public charging station categories, the accuracy of matching vehicle charging data with charging stations is ensured.

[0021] In one optional implementation, calculating the distance between the cluster region corresponding to the public charging pile category and each charging station within the target region includes:

[0022] Determine the center point of the cluster region corresponding to the public stake category;

[0023] The distance is obtained based on the location of the center point and the location of the charging station.

[0024] Specifically, when matching vehicles with charging stations, the distance between the cluster area corresponding to each type of public charging pile and the charging station is used for judgment. The smaller the distance value, the higher the degree of matching. The distance value is calculated using the center point of the cluster area corresponding to the public charging pile category.

[0025] In one alternative implementation, the training process of the clustering model includes:

[0026] Acquire charging data of training vehicles and charging behavior data at charging stations within the target area;

[0027] The charging data of the training vehicles is matched with the charging stations by using the same identifier for the same vehicle in the charging data and charging behavior data of the training vehicles.

[0028] The matched training vehicle charging data is clustered according to the preset clustering region and preset clustering value. The training vehicle charging data that are in the preset clustering region and have a data quantity greater than the preset clustering value are classified into a training clustering category.

[0029] The training cluster categories are filtered based on the training vehicle charging data in each training cluster category to determine the training public charging pile category within the training cluster category;

[0030] Calculate the distance between the cluster region corresponding to the public pile category used in training and each charging station in the target region;

[0031] If the distance is less than the preset distance threshold, the charging data of the training vehicles in the category of training public piles will be matched with the corresponding charging stations.

[0032] The preset clustering regions and preset clustering values ​​are adjusted based on the matching results until the error of the matching results is within the preset range, thus obtaining the clustering model.

[0033] In one optional implementation, before matching the training vehicle charging data with charging stations using the same identifier for the same vehicle in the training vehicle charging data and charging behavior data, the method further includes:

[0034] Determine the number of times each charging station will charge a single vehicle within a preset period.

[0035] The number of second vehicles whose count exceeds the preset count;

[0036] If the number of the second vehicle is less than the second preset number of vehicles, the corresponding charging station will be filtered out.

[0037] Specifically, during the training of the matching model, in order to ensure the accuracy of the model training, the acquired charging station data will be preprocessed. Charging stations that do not meet the charging data requirements will be filtered out and will not participate in the subsequent model training process. By filtering out bad data, the effectiveness of model training is guaranteed.

[0038] Secondly, the present invention provides a vehicle-charging station information matching device based on charging behavior, the device comprising:

[0039] The data acquisition module is used to acquire vehicle charging data of electric vehicles in the target area. The vehicle charging data includes the vehicle location information when the electric vehicle is charging.

[0040] The clustering module is used to cluster vehicle charging data based on vehicle information and determine the clustering category corresponding to the vehicle charging data.

[0041] The public charging pile identification module is used to filter clusters based on vehicle charging data in each cluster category and determine the public charging pile category within each cluster category;

[0042] The distance calculation module is used to calculate the distance between the cluster area corresponding to the public pile category and each charging station in the target area;

[0043] The matching module is used to match vehicle charging data within the public charging pile category with the corresponding charging station if the distance is less than a preset distance threshold.

[0044] The present invention provides a vehicle-charging station information matching device based on charging behavior, which has the following advantages:

[0045] This invention utilizes the locational relationship between charging vehicles and charging stations to match them. The matching data allows for further optimization of new charging station locations, improving charging efficiency. A well-planned layout of charging stations also reduces waiting time for vehicles, enhancing user experience. This invention uses a pre-trained matching model to cluster discrete charging vehicle data according to vehicle location. Then, based on charging data within each cluster (e.g., total number of charges), it determines public charging station categories. Finally, it matches vehicle data within each public charging station category with charging stations based on their distance relationship. This vehicle-to-charging-station matching process ensures accuracy, laying the foundation for subsequent planning of new charging station locations and optimization of charging station strategies.

[0046] Thirdly, the present invention provides a computer device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the vehicle-charging station information matching method based on charging behavior described in the first aspect or any corresponding embodiment thereof.

[0047] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the vehicle-charging station information matching method based on charging behavior as described in the first aspect or any corresponding embodiment thereof. Attached Figure Description

[0048] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0049] Figure 1 This is a flowchart illustrating the vehicle-charging station information matching method based on charging behavior provided in an embodiment of the present invention.

[0050] Figure 2 This is a flowchart illustrating the clustering process provided in an embodiment of this application;

[0051] Figure 3 This is a schematic diagram of the clustering results provided in an embodiment of the present invention;

[0052] Figure 4This is a schematic diagram showing the distance between the types of public charging piles and charging stations provided in this embodiment of the invention;

[0053] Figure 5 This is a flowchart illustrating the clustering model training process provided in an embodiment of the present invention;

[0054] Figure 6 This is a schematic diagram of the data filtering process during model training provided in an embodiment of the present invention;

[0055] Figure 7 A schematic diagram of a vehicle-charging station information matching device based on charging behavior according to the present invention;

[0056] Figure 8 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Detailed Implementation

[0057] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0058] Currently, the data from various entities within the "vehicle-charging-road-network" system are diverse and isolated. The highly flexible and complex patterns of electric vehicle (EV) usage, such as driving and charging, result in poor perception and prediction capabilities regarding adjustable charging and discharging resources. This hinders the efficient guidance and scheduling of large-scale EV participation in V2G (Vehicle-to-Grid) systems. Furthermore, the vehicle network data (for charging vehicles) and the charging pile network data (for charging piles) are independent due to differences in construction entities and technical standards. This leads to insufficient service capacity of public charging piles as essential infrastructure for EVs. For example, existing public charging piles may not adequately meet the charging needs of EVs, resulting in long waiting times or unused charging piles. This impacts charging efficiency and the charging experience for EV users.

[0059] To address the aforementioned problems, embodiments of the present invention provide a vehicle-charging station information matching method based on charging behavior. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system (computer device) including a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0060] This invention provides a vehicle-charging station information matching method based on charging behavior. Figure 1 This is a flowchart illustrating the vehicle-charging station information matching method based on charging behavior according to an embodiment of the present invention, as shown below. Figure 1 As shown, the process includes the following steps:

[0061] Step S101: Obtain vehicle charging data of electric vehicles in the target area. The vehicle charging data includes the vehicle location information when the electric vehicles are charging.

[0062] Specifically, the ultimate goal of the vehicle-charging station information matching method based on charging behavior of the present invention is to optimize the layout of charging stations in the region by using the vehicle-charging station information matching relationship based on charging behavior. Therefore, when determining the vehicle-charging station information matching relationship based on charging behavior, the vehicle charging data of the target region is taken as the research object, and the vehicle charging data is acquired, wherein the vehicle charging data includes the vehicle location information when the vehicle is charging.

[0063] Specifically, vehicle charging data is collected through the vehicle's own onboard intelligent system and transmitted to the cloud. The cloud then retrieves vehicle charging data for the target region. This data includes the charging user's VIN code, which is an abbreviation for Vehicle Identification Number. Because the SAE standard stipulates that the VIN code consists of 17 characters, it is commonly referred to as the 17-digit code. It contains information such as the vehicle's manufacturer, year, model, body style and code, engine code, and assembly location; the initial and final SOC parameters of the onboard battery at the start and end of charging; the charging start time, charging end time, charging amount, charging power, and the vehicle's location information during the charging process.

[0064] Step S102: Cluster the vehicle charging data based on the vehicle location information to determine the cluster category corresponding to the vehicle charging data.

[0065] Specifically, vehicle location information consists of the latitude and longitude coordinates of the vehicle at the time of charging. This is represented as discrete points on a map or coordinate system. The vehicle charging data is clustered based on the distribution of these discrete points to obtain the corresponding cluster categories. An 84 coordinate system can be used for this specific processing. In this coordinate system, one vehicle location corresponds to one discrete point, and one discrete point corresponds to one vehicle charging data point. The discrete points are then divided into clustering regions to determine the cluster category corresponding to the vehicle charging data at each discrete point.

[0066] Step S103: Based on the vehicle charging data in each cluster category, filter the cluster categories to determine the public charging pile category within the cluster category.

[0067] Specifically, each cluster after clustering corresponds to a different number of vehicle charging data points. Furthermore, in actual vehicle charging, vehicles can be charged at both public and private charging stations. To differentiate between private charging stations and ensure the accuracy of vehicle charging data matched with charging stations, this step filters out public charging pile category data that matches the characteristics of public charging stations from the clustered categories before proceeding with the subsequent matching process. This ensures the accuracy of subsequent data processing.

[0068] Step S104: Calculate the distance between the cluster area corresponding to the public pile category and each charging station in the target area.

[0069] Specifically, as explained above, each cluster category corresponds to a cluster region; therefore, the identified public charging pile category also corresponds to a cluster region. When matching vehicle charging data for this public charging pile category with charging stations, the matching is based on the distance between them, with closer distances indicating a higher degree of matching. The distance between the public charging pile category and the charging station can be determined by the distance between the cluster region corresponding to the public charging pile category and the charging station.

[0070] Step S105: If the distance is less than the preset distance threshold, the vehicle charging data in the public charging pile category will be matched with the corresponding charging station.

[0071] Specifically, by comparing the calculated distance value with a preset distance threshold, if the distance value is less than the preset distance threshold, the vehicle charging data in the public charging pile category corresponding to that distance value is matched with the corresponding charging station. After the matching is completed, the vehicle charging data corresponding to each charging station in the target area can be determined, thereby optimizing the configuration of new charging stations in the target area and the charging strategies such as charging time within the charging stations based on the matching results.

[0072] This invention utilizes the locational relationship between charging vehicles and charging stations to match them. The matching data allows for further optimization of new charging station locations, improving charging efficiency. A well-planned layout of charging stations also reduces waiting time for vehicles, enhancing user experience. This invention uses a pre-trained matching model to cluster discrete charging vehicle data according to vehicle location. Then, based on charging data within each cluster (e.g., total number of charges), it determines public charging station categories. Finally, it matches vehicle data within each public charging station category with charging stations based on their distance relationship. This vehicle-to-charging-station matching process ensures accuracy, laying the foundation for subsequent planning of new charging station locations and optimization of charging station strategies.

[0073] The vehicle-charging station information matching method based on charging behavior of the present invention first acquires vehicle charging data and determines the corresponding vehicle location information when matching vehicle charging data with charging stations within a target area. Then, the vehicle charging data is represented using the vehicle location information in a unified coordinate system, resulting in multiple discrete points. Subsequently, a clustering process is performed on the discrete points, the clustering process of which is described in the optional embodiments below.

[0074] In one optional implementation, Figure 2 This is a flowchart illustrating the clustering process provided in an embodiment of this application. The process of clustering discrete points to determine the cluster category corresponding to the vehicle charging data is as follows: Figure 2 As shown, the process includes the following steps:

[0075] Step S201: Process the latitude and longitude coordinates in the vehicle location information using a pre-trained clustering model.

[0076] Specifically, when clustering discrete points in a coordinate system, because the discrete vehicle charging data is densely distributed on the map according to vehicle location information, this invention utilizes the DBSCAN model for the clustering process of discrete points. Simply put, the DBSCAN clustering process involves dividing the discrete points into pre-defined regions, and then using pre-defined preset values ​​to determine the clustering results for each region.

[0077] Step S202: If the number of vehicle location information items within the clustering area is greater than a preset value, then the vehicle charging data corresponding to the vehicle location information is classified into a cluster category.

[0078] Specifically, during the clustering process, discrete points are divided using cluster regions of a predetermined size, and the relationship between the number of discrete points within each region and a preset value is determined. If the number of discrete points within a region exceeds the preset value, the discrete points within that region are grouped into one category; that is, the vehicle charging data corresponding to the discrete points within that region belong to one category.

[0079] Preferably, the clustering region can be a circular region with a certain radius. The size of the clustering region and the preset values ​​for judgment are determined during the training process of the clustering model. In practice, the radius of the clustering region is generally selected within the range of 10-100 meters, and the preset value is selected within the range of 2-5. The specific values ​​need to be determined based on the training results of the clustering model within the target region.

[0080] In one optional implementation, after determining the location category corresponding to each vehicle charging data point, since the vehicle charging data includes data from charging at both public and private charging stations, to ensure matching accuracy during the matching process, data from private charging stations needs to be filtered out, retaining only data from charging at public charging stations for subsequent matching with public charging stations. Therefore, from the determined multiple location categories, the category of public charging piles representing charging at public charging stations is identified. The process of filtering clusters based on vehicle charging data within each cluster category to determine the category of public charging piles within each cluster is as follows: Figure 3 As shown, Figure 3 This is a flowchart illustrating the process of determining the type of public post according to an embodiment of this application. The process includes the following steps:

[0081] Step S301: Determine the total number of charging times and the number of first vehicles corresponding to each cluster category based on the vehicle charging data in each cluster category.

[0082] Among them, the total number of charging times is the total number of times the vehicle charging data corresponds to the vehicle charging data, and the first vehicle number is the number of vehicles that have participated in charging corresponding to the vehicle charging data.

[0083] Specifically, this invention utilizes the total number of charging times and the number of vehicles that were the first to be charged in the vehicle charging data corresponding to a cluster category. The following example illustrates the meaning of the total number of charging times and the number of vehicles that were the first to be charged. For instance, the vehicle charging data in a cluster category contains five vehicles, namely vehicle 1, vehicle 2, vehicle 3, vehicle 4, and vehicle 5. Vehicle 1 was charged three times, vehicle 2 was charged twice, vehicle 3 was charged once, vehicle 4 was charged once, and vehicle 5 was charged twice. Therefore, the total number of charging times is 3 + 2 + 1 + 1 + 2 = 9 times. The number of vehicles that were the first to be charged is 5.

[0084] Step S302: If the total number of charging times is greater than the first preset number of charging times, and the number of vehicles is greater than the first preset number of vehicles, then the corresponding cluster category is determined as the public charging pile category.

[0085] Specifically, by comparing the total number of charging times with the first number of social charging times, and comparing the first number of vehicles with the first preset number of vehicles, if the total number of charging times is greater than the first preset number of charging times, and the first number of vehicles is greater than the first preset number of vehicles, then the data volume in this location category is considered to meet the data characteristics of vehicles charging at public charging stations, and therefore this cluster category is determined as the public charging pile category.

[0086] Once the type of public charging station is determined, the vehicle charging data for that type of public charging station is matched with the charging station. The closer the distance between the two, the higher the matching degree. Therefore, this invention uses the relationship between the distance between the two and a preset distance threshold to determine whether the public charging station type matches the charging station.

[0087] In an optional implementation, the process of calculating the distance between the cluster region corresponding to the public charging pile category and each charging station within the target region includes the following steps:

[0088] Step a: Determine the location of the center point of the cluster region corresponding to the public stake category.

[0089] Specifically, as explained above, each type of public charging pile corresponds to a cluster region. This invention uses the center point of this cluster region as the location corresponding to that type of public charging pile to calculate the distance to the charging station. For circular cluster regions, the center point is the location of the center of the circle.

[0090] Step b: Calculate the distance based on the location of the center point and the location of the charging station.

[0091] Specifically, the distance between the center point of the cluster area corresponding to the known public pile category on the map and the location of the charging station is calculated.

[0092] Specifically, Figure 4 This is a schematic diagram illustrating the distance between the types of public charging piles and charging stations provided in this embodiment of the invention. For example... Figure 4 As shown, the clustering region corresponding to the public parking lot category is a circular region C, where the center point of the circular region is denoted as c. A charging site is represented by the letter D. The distance d between the two is the distance between the straight lines shown in the figure.

[0093] After the distance calculation is completed, the calculated distance value is compared with the preset distance threshold. If the distance value is less than the distance threshold, the corresponding public charging pile category is matched with the charging station, thus realizing the matching of vehicle charging data with charging station.

[0094] Specifically, such as Figure 4 As shown, if the calculated distance value d is less than the preset distance threshold, then public charging pile category C matches charging station D, meaning the vehicle charging data in public charging pile category C matches the charging station. Through this matching process, the vehicle charging status of each charging station can be understood, thus enabling better planning of new charging station locations and optimization of charging strategies within charging stations.

[0095] In one optional implementation, Figure 5 This is a flowchart illustrating the clustering model training process provided in an embodiment of the present invention. Figure 5 As shown, the process includes the following steps:

[0096] Step S501: Obtain training vehicle charging data and charging behavior data from charging stations within the target area.

[0097] Specifically, model training begins with acquiring training data. This involves collecting vehicle charging data and charging station data within a predetermined time period in the target region. Vehicle charging data includes: user VIN code, battery SOC parameters at the start and end of charging, start and end times, charging station longitude and latitude, charging capacity, and charging power. Charging station data includes: order ID, user ID, start and end SOC, start and end times, charging station ID, longitude and latitude, charging capacity, and charging power. Vehicle charging data can be collected via an onboard intelligent system and transmitted to a cloud database for storage; charging station data can be collected via smart terminals at each charging station and uploaded locally to a cloud database for storage.

[0098] Step S502: Match the training vehicle charging data with the charging stations using the same identifier for the same vehicle in the training vehicle charging data and charging behavior data.

[0099] Specifically, when acquiring vehicle charging data for the target region, since charging stations include both public and private stations, it's necessary to filter out data related to public charging stations for subsequent training. Charging behavior data at charging stations includes charging user IDs, while the charging data for training vehicles includes charging user VIN codes. By utilizing the correspondence between charging user IDs and VIN codes, data matching charging stations in the training vehicle charging data is extracted for subsequent model training.

[0100] Step S503: Cluster the matched training vehicle charging data according to the preset clustering region and preset clustering value, and classify the training vehicle charging data that are in the preset clustering region and have a data quantity greater than the preset clustering value into a training clustering category.

[0101] Specifically, the charging data of training vehicles matched with charging stations is represented in a unified coordinate system according to their corresponding vehicle location information to obtain a series of discrete points. Then, the data is clustered according to the set clustering region and the preset clustering value. If the number of data in the clustering region, that is, the number of discrete points, is greater than the preset clustering value, the charging data of training vehicles in that region is classified into a training clustering category.

[0102] Step S504: Based on the training vehicle charging data in each training cluster category, filter the training cluster categories to determine the training public charging pile categories within the training cluster categories.

[0103] Step S505: Calculate the distance between the clustering region corresponding to the public pile category used for training and each charging station in the target region.

[0104] Step S506: If the distance is less than the preset distance threshold, the charging data of the training vehicles in the training public pile category will be matched with the corresponding charging stations.

[0105] Specifically, the process of steps S504-S506 is the same as that of steps S103-S105 above, and will not be repeated here.

[0106] Step S507: Adjust the preset clustering region and preset clustering value according to the matching result until the error of the matching result is within the preset range, and obtain the clustering model.

[0107] Specifically, the size of the preset clustering region and the preset clustering value are adjusted according to the accuracy of the matching results. The matching results are continuously optimized until the error of the matching results is within the preset range. This indicates that the accuracy of the clustering model meets the requirements, and the training process of the clustering model is completed.

[0108] In an optional implementation, the process prior to matching the training vehicle charging data with charging stations using the same identifier for the same vehicle from the training vehicle charging data and charging behavior data during training is as follows: Figure 6 As shown, Figure 6 This is a flowchart illustrating the data selection process during model training. The process includes the following steps:

[0109] Step S601: Determine the number of times each charging station will charge a single vehicle within a preset period.

[0110] Specifically, for charging stations, ID mapping technology is used to obtain the vehicle charging data corresponding to the charging station within a preset time period, and then the number of times a single vehicle is charged within that time period is counted. For example, for station E, a total of five vehicles are charged within the preset time period: the first vehicle is charged 3 times, the second vehicle is charged 4 times, the third vehicle is charged once, the fourth vehicle is charged once, and the fifth vehicle is charged 5 times.

[0111] Step S602: Obtain the number of second vehicles that has been counted more than the preset number of times.

[0112] Specifically, as in the example in step 601, if the second preset number of times is 2, then the number of second vehicles that meet the conditions in charging station E is 3.

[0113] Step S603: If the number of the second vehicles is less than the number of the second preset vehicles, the corresponding charging stations will be filtered out.

[0114] Specifically, regarding the distance mentioned in the steps above, if the second preset number of vehicles is 3, charging station E will be retained for subsequent model training. Through the above process, the data of charging stations is filtered, retaining charging station data with certain vehicle charging data, thereby ensuring the correctness of model training.

[0115] This invention utilizes the locational relationship between vehicles and charging stations to match charging vehicles with charging stations. The matching data between charging stations and vehicles allows for further optimization of new charging station locations, improving charging efficiency. A well-planned layout of charging stations also reduces waiting time for vehicles, enhancing user experience. This invention uses a pre-trained matching model to cluster discrete charging vehicle data according to vehicle location. Then, based on charging data within each cluster (e.g., total number of charging cycles), it determines public charging station categories. Finally, it matches vehicle data within each public charging station category with charging stations based on the distance relationship between the public charging station category and the charging station. This vehicle-charging station matching process ensures accuracy, laying the foundation for subsequent planning of new charging station locations and optimization of charging station strategies.

[0116] Figure 7 A schematic diagram of a vehicle-charging station information matching device based on charging behavior according to the present invention. Figure 7 As shown, the device includes:

[0117] The data acquisition module 701 is used to acquire vehicle charging data of electric vehicles in the target area, the vehicle charging data including vehicle location information when the electric vehicle is charging.

[0118] Clustering module 702 is used to cluster the vehicle charging data based on the vehicle information and determine the clustering category corresponding to the vehicle charging data.

[0119] The public charging pile identification module 703 is used to filter the cluster categories based on the vehicle charging data in each cluster category to determine the public charging pile category in the cluster category;

[0120] The distance calculation module 704 is used to calculate the distance between the clustering area corresponding to the public pile category and each charging station in the target area;

[0121] The matching module 705 is used to match the vehicle charging data in the public charging pile category with the corresponding charging station if the distance is less than a preset distance threshold.

[0122] In an optional implementation, the clustering module 702 is specifically used to process the latitude and longitude coordinates in the vehicle location information through a pre-trained clustering model; if the number of vehicle location information items in the clustering area is greater than a preset value, then the vehicle charging data corresponding to the vehicle location information is classified into a cluster category.

[0123] In an optional implementation, the public charging pile identification module 703 is specifically used to determine the total number of charging attempts and the first number of vehicles corresponding to each cluster category based on the vehicle charging data in each cluster category. The total number of charging attempts is the total number of times the vehicles corresponding to the vehicle charging data have been charged, and the first number of vehicles is the number of vehicles that have participated in charging corresponding to the vehicle charging data. If the total number of charging attempts is greater than a first preset number of charging attempts, and the first number of vehicles is greater than a first preset number of vehicles, then the corresponding cluster category is determined as a public charging pile category.

[0124] In an optional implementation, the distance calculation module 704 is specifically used to determine the center point location of the cluster area corresponding to the public pile category; and to obtain the distance based on the center point location and the location of the charging station.

[0125] In an optional implementation, the device further includes a model training module, used to acquire training vehicle charging data and charging behavior data of charging stations within the target area; match the training vehicle charging data with charging stations using the same identifier for the same vehicle in the training vehicle charging data and charging behavior data; cluster the matched training vehicle charging data according to a preset clustering region and a preset clustering value, and classify the training vehicle charging data within the preset clustering region and with a data quantity greater than the preset clustering value into a training clustering category; filter the training clustering categories based on the training vehicle charging data in each training clustering category to determine the training public charging pile category within the training clustering category; calculate the distance between the clustering region corresponding to the training public charging pile category and each charging station within the target area; if the distance is less than a preset distance threshold, match the training vehicle charging data within the training public charging pile category with the corresponding charging station; adjust the preset clustering region and preset clustering value according to the matching result until the error of the matching result is within a preset range, thereby obtaining a clustering model.

[0126] In an optional implementation, the device further includes a filtering module for determining the number of times each charging station charges a single vehicle within a preset period; obtaining a second number of vehicles whose number of charges is greater than a preset number; and filtering out the corresponding charging station if the second number of vehicles is less than a second preset number of vehicles.

[0127] This invention utilizes the locational relationship between vehicles and charging stations to match charging vehicles with charging stations. The matching data between charging stations and vehicles allows for further optimization of new charging station locations, improving charging efficiency. A well-planned layout of charging stations also reduces waiting time for vehicles, enhancing user experience. This invention uses a pre-trained matching model to cluster discrete charging vehicle data according to vehicle location. Then, based on charging data within each cluster (e.g., total number of charging cycles), it determines public charging station categories. Finally, it matches vehicle data within each public charging station category with charging stations based on the distance relationship between the public charging station category and the charging station. This vehicle-charging station matching process ensures accuracy, laying the foundation for subsequent planning of new charging station locations and optimization of charging station strategies.

[0128] This invention also provides a computer device having the above-described features. Figure 7 The matching device for the charging station shown.

[0129] Please see Figure 8 , Figure 8 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of the present invention, such as... Figure 8 As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 8 Take a processor 10 as an example.

[0130] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0131] The memory 20 stores instructions executable by at least one processor 10 to cause at least one processor 10 to perform the method shown in the above embodiments.

[0132] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device as shown by a landing page for an app. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, which can be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0133] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0134] The computer device also includes an input device 30 and an output device 40. The processor 10, memory 20, input device 30, and output device 40 can be connected via a bus or other means. Figure 8 Taking the example of a connection between China and Israel via a bus.

[0135] Input device 30 can receive input numerical or character information, and generate key signal inputs related to user settings and function control of the computer device, such as a touchscreen, keypad, mouse, trackpad, touchpad, joystick, one or more mouse buttons, trackball, joystick, etc. Output device 40 may include display devices, auxiliary lighting devices (e.g., LEDs), and haptic feedback devices (e.g., vibration motors). The aforementioned display devices include, but are not limited to, liquid crystal displays, light-emitting diodes, displays, and plasma displays. In some alternative embodiments, the display device may be a touchscreen.

[0136] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0137] This invention also provides a computer program product storing computer instructions for causing a computer to execute the vehicle-charging station information matching method based on charging behavior described in any of the above embodiments.

[0138] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A vehicle-charging station information matching method based on charging behavior, characterized in that, include: Acquire vehicle charging data of electric vehicles within the target area, wherein the vehicle charging data includes the vehicle location information of the electric vehicles when they are charging; Based on the vehicle location information, the vehicle charging data is clustered to determine the cluster category corresponding to the vehicle charging data. The cluster categories are filtered based on the vehicle charging data in each cluster category to determine the public charging pile category within the cluster category; Calculate the distance between the cluster region corresponding to the public pile category and each charging station in the target region; If the distance is less than a preset distance threshold, the vehicle charging data within the public charging pile category will be matched with the corresponding charging station.

2. The method according to claim 1, characterized in that, Based on the vehicle location information, the vehicle charging data is clustered to determine the corresponding cluster category, including: The latitude and longitude coordinates in the vehicle location information are processed using a pre-trained clustering model; If the number of vehicle location information items within a clustering region is greater than a preset value, then the vehicle charging data corresponding to the vehicle location information will be classified into a cluster category.

3. The method according to claim 1, characterized in that, Based on the vehicle charging data in each cluster category, the cluster categories are filtered to determine the public charging pile categories within each cluster category, including: Based on the vehicle charging data in each cluster category, determine the total number of charging times and the first number of vehicles corresponding to the cluster category, wherein the total number of charging times is the total number of times the vehicle charging data corresponds to the vehicle charging data, and the first number of vehicles is the number of vehicles that have participated in charging corresponding to the vehicle charging data. If the total number of charging times is greater than the first preset number of charging times and the number of vehicles is greater than the first preset number of vehicles, then the corresponding cluster category is determined as the public charging pile category.

4. The method according to claim 1, characterized in that, Calculating the distance between the cluster region corresponding to the public charging pile category and each charging station within the target region includes: Determine the center point location of the cluster region corresponding to the public stake category; The distance is obtained based on the location of the center point and the location of the charging station.

5. The method according to claim 2, characterized in that, The training process of the clustering model includes: Acquire charging data of training vehicles and charging behavior data of charging stations within the target area; The training vehicle charging data and the charging behavior data are matched with the charging stations using the same identifier for the same vehicle. The matched training vehicle charging data is clustered according to a preset clustering region and a preset clustering value. The training vehicle charging data that are within the preset clustering region and have a data quantity greater than the preset clustering value are classified into a training clustering category. The training cluster categories are filtered based on the training vehicle charging data in each training cluster category to determine the training public charging pile category in the training cluster category; Calculate the distance between the clustering region corresponding to the training public pile category and each charging station in the target region; If the distance is less than a preset distance threshold, the charging data of the training vehicles in the category of training public piles will be matched with the corresponding charging stations. The preset clustering regions and preset clustering values ​​are adjusted based on the matching results until the error of the matching results is within a preset range, thus obtaining the clustering model.

6. The method according to claim 5, characterized in that, Before matching the training vehicle charging data with charging stations using the same identifier for the same vehicle in the training vehicle charging data and the charging behavior data, the process further includes: Determine the number of times each of the aforementioned charging stations charges a single vehicle within a preset period; Obtain the number of second vehicles whose count is greater than a preset number; If the second number of vehicles is less than the second preset number of vehicles, the corresponding charging station will be filtered out.

7. A method for optimizing the layout of electric vehicle charging stations, characterized in that, include: The vehicle charging data corresponding to each charging station is determined using the vehicle-charging pile information matching method based on charging behavior as described in any one of claims 1-6. The layout of charging piles in each charging station is optimized based on the vehicle charging data corresponding to each charging station.

8. A vehicle-charging station information matching device based on charging behavior, characterized in that, include: The data acquisition module is used to acquire vehicle charging data of electric vehicles in the target area, including vehicle location information when the electric vehicles are charging. The clustering module is used to cluster the vehicle charging data based on the vehicle location information and determine the clustering category corresponding to the vehicle charging data. The public charging pile identification module is used to filter the cluster categories based on the vehicle charging data in each cluster category to determine the public charging pile category in the cluster category; The distance calculation module is used to calculate the distance between the cluster area corresponding to the public pile category and each charging station in the target area; The matching module is used to match the vehicle charging data in the public charging pile category with the corresponding charging station if the distance is less than a preset distance threshold.

9. A computer device, characterized in that, include: The system includes a memory and a processor, which are interconnected. The memory stores computer instructions, and the processor executes the computer instructions to perform the vehicle-charging pile information matching method based on charging behavior as described in any one of claims 1 to 6, or the electric vehicle charging pile layout optimization method as described in claim 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the vehicle-charging pile information matching method based on charging behavior as described in any one of claims 1 to 6 or the electric vehicle charging pile layout optimization method as described in claim 7.

Images