Public and private charging pile classification method and device based on vehicle charging behavior data

Abstract

The present invention relates to the field of vehicle charging technology, and discloses a method and device for classifying public and private charging piles based on vehicle charging behavior data. The method comprises: determining clustering behavior data corresponding to the charging behavior data based on the charging behavior data of the vehicle; determining the public charging pile category corresponding to the clustering behavior data; and determining the private charging pile category corresponding to the clustering behavior data based on preset matching rules, clustering behavior data, and public charging pile categories. The present invention can identify the charging locations and times frequently visited by vehicles by collecting and analyzing the charging behavior data of vehicles. By identifying the clustering features of the charging behavior data, the potential location of the charging pile can be inferred, especially for those areas with poor GPS signals. Based on the preset matching rules, clustering behavior data, and public charging pile categories, the private charging pile category corresponding to the clustering behavior data can be determined, thereby improving the identification of whether the user owns a private charging pile and the usage of the private charging pile, and providing data support for the promotion and optimization of private charging piles.

Description

Technical Field

[0001] The present invention relates to the field of vehicle charging technology, and in particular to a method, device, computer equipment, storage medium and program product for classifying public and private charging piles based on vehicle charging behavior data. Background Art

[0002] With the increasing global awareness of environmental protection and the transformation of energy structure, electric vehicles (EVs) have gradually become the main choice to replace traditional fuel vehicles with their advantages of zero emissions, low noise, and high efficiency. The rapid development of the electric vehicle industry has not only promoted the progress of related fields such as battery technology and drive systems, but also put forward higher requirements for the construction of charging infrastructure. As a key facility for energy replenishment of electric vehicles, the number, distribution and operation efficiency of charging piles directly affect the popularity of electric vehicles and user experience.

[0003] In order to distinguish between public and private charging piles and optimize their use, a charging pile classification system based on geographic location information is currently used to mark charging piles as public or private through GPS positioning and database matching.

[0004] However, although GPS positioning technology can provide geographical location information of charging piles to a certain extent, the positioning accuracy may be affected by environmental factors (such as high-rise buildings, tunnels and other obstructions). In some cases, users may find it difficult to find the exact location of the charging pile due to inaccurate positioning, which increases the difficulty of use. Summary of the invention

[0005] In view of this, the present invention provides a method, device, computer equipment, storage medium and program product for classifying public and private charging piles based on vehicle charging behavior data, so as to solve the problem that although GPS positioning technology can provide geographical location information of charging piles to a certain extent, the positioning accuracy may be affected by environmental factors (such as high-rise buildings, tunnels and other obstructions). In some cases, users may find it difficult to find the exact location of the charging pile due to inaccurate positioning, which increases the difficulty of use.

[0006] In a first aspect, the present invention provides a method for classifying public and private charging piles based on vehicle charging behavior data, the method comprising: determining clustering behavior data corresponding to the charging behavior data based on the vehicle charging behavior data; determining the public charging pile category corresponding to the clustering behavior data; and determining the private charging pile category corresponding to the clustering behavior data based on preset matching rules, clustering behavior data and public charging pile category.

[0007] The public and private charging pile classification method based on vehicle charging behavior data provided in this embodiment can identify the charging locations and times frequently visited by vehicles by collecting and analyzing the charging behavior data of vehicles. These behavior patterns can provide users with additional positioning references. Even if the GPS signal is interfered with, the possible charging pile locations can be inferred based on historical charging behaviors. Using clustered behavior data, the distribution of charging piles can be further refined. By identifying the clustering characteristics of charging behavior data, the potential location of charging piles can be inferred, especially for areas with poor GPS signals. Based on preset matching rules, clustered behavior data, and public pile categories, the private pile category corresponding to the clustered behavior data can be determined, which improves the identification of whether users own private piles and the use of private piles, and provides data support for the promotion and optimization of private piles.

[0008] In an optional embodiment, based on preset matching rules, clustering behavior data and public pile categories, the private pile category corresponding to the clustering behavior data is determined, including: based on the public pile category, determining the target category; wherein the target category refers to the category in the clustering category other than the public pile category; detecting whether the target category has station location information; if the target category does not have station location information, detecting whether the clustering behavior data corresponding to the target category meets preset conditions; if the clustering behavior data meets the preset conditions, judging the target category to be a private pile category.

[0009] The public and private charging pile classification method based on vehicle charging behavior data provided in this embodiment can effectively screen out clustered behavior data that may belong to private charging piles by first determining the target category and then detecting the station location information. This step greatly reduces the amount of data for subsequent judgment, improves processing efficiency, and reduces misjudgment.

[0010] In an optional embodiment, the station location information includes: the location of the private charging station; wherein the method further includes: if the target category has station location information, calculating the first distance between the clustering area corresponding to the target category and the location of the private charging station; if the first distance is less than the first preset distance threshold, matching the clustering behavior data within the target category with the corresponding private charging station to determine that the target category is a private charging station category.

[0011] The public and private charging pile classification method based on vehicle charging behavior data provided in this embodiment can accurately identify which charging stations belong to private charging piles by including the location information of private charging stations. This avoids the mistaken classification of public charging piles as private piles and improves the accuracy of classification. When the target category has station location information, the first distance between the category and the private charging station can be calculated. By setting the first preset distance threshold, the target category that is close to the private charging station can be quickly screened out and then classified as a private charging pile category. This matching method based on geographic location is more intuitive and reliable.

[0012] In an optional embodiment, the clustering behavior data includes: at least one of the latitude and longitude information of the center point, the number of vehicles, the number of vehicle charges, the average charging time, the average time interval between two consecutive charges, the proportion of fast charging and the proportion of night charging times; wherein, detecting whether the clustering behavior data corresponding to the target category meets the preset conditions includes: obtaining the location information of the preset point of interest; determining the second distance between the location information of the preset point of interest and the longitude and latitude information of the center point; detecting whether the second distance is less than a preset distance threshold; and / or, detecting whether the number of vehicles is less than a preset number within a preset period; and / or, detecting whether the number of charges is less than a preset number of charges within a preset period; and / or, detecting whether the average charging time is less than a preset charging time; and / or, detecting whether the average time interval between two consecutive charges is less than a preset time interval; and / or, detecting whether the proportion of fast charging is less than a preset proportion; and / or, detecting whether the proportion of night charging times is less than a preset number of night charging times.

[0013] The public and private charging pile classification method based on vehicle charging behavior data provided in this embodiment includes multiple dimensions such as the center point longitude and latitude information, the number of vehicles, the number of charging times, the average charging time, the average time interval between two consecutive charging times, the proportion of fast charging, and the proportion of nighttime charging times. By matching the clustering behavior data with the preset conditions, the charging stations that meet the specific conditions can be accurately identified.

[0014] In an optional embodiment, the charging behavior data of the vehicle includes: the longitude and latitude information of the vehicle when the vehicle is charging; wherein, based on the charging behavior data of the vehicle, determining the clustering behavior data corresponding to the charging behavior data includes: clustering the longitude and latitude information of the vehicle when the vehicle is charging corresponding to each vehicle, respectively, to obtain multiple clustering processing results; wherein the clustering processing results include: the longitude and latitude information of the clustered vehicles; based on the longitude and latitude information of the clustered vehicles, clustering the multiple clustering processing results to determine the clustering behavior data corresponding to the charging behavior data.

[0015] The public and private charging pile classification method based on vehicle charging behavior data provided in this embodiment performs preliminary clustering processing on the charging latitude and longitude information of each vehicle, and can obtain multiple clustering processing results, which reflect the spatial distribution and agglomeration of charging behaviors of different vehicle groups. Based on these preliminary clustering results, a higher level of clustering processing is performed to more accurately determine the clustering behavior data corresponding to the charging behavior data, and to capture subtle differences in charging behavior.

[0016] In an optional embodiment, the clustering behavior data includes multiple clustering categories, a total number of charging times and a number of vehicles; wherein, determining the public charging pile category corresponding to the clustering behavior data includes: determining the total number of charging times and the number of vehicles corresponding to the clustering category; wherein, the total number of charging times is the total number of times the vehicles corresponding to the clustering behavior data are charged, and the number of vehicles is the number of vehicles involved in charging corresponding to the clustering behavior data; if the total number of charging times is greater than the preset number of charging times and the number of vehicles is greater than the preset number of vehicles, the clustering category corresponding to the clustering behavior data is determined as the public charging pile category.

[0017] The public and private charging pile classification method based on vehicle charging behavior data provided in this embodiment can more accurately evaluate the characteristics of clustering behavior data by comprehensively considering the two dimensions of total charging times and number of vehicles, thereby more accurately determining which clustering categories belong to the public charging pile category. In addition, setting the preset charging times and the preset number of vehicles as judgment criteria helps to avoid interference from subjective judgment and improve the objectivity and accuracy of data processing.

[0018] In a second aspect, the present invention provides a public-private charging pile classification device based on vehicle charging behavior data, the device comprising: a first determination module, used to determine the clustering behavior data corresponding to the charging behavior data based on the vehicle charging behavior data; a second determination module, used to determine the public charging pile category corresponding to the clustering behavior data; a third determination module, used to determine the private charging pile category corresponding to the clustering behavior data based on preset matching rules, clustering behavior data and public charging pile category.

[0019] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the public and private charging pile classification method based on vehicle charging behavior data of the above-mentioned first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0020] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the method for classifying public and private charging piles based on vehicle charging behavior data of the first aspect or any corresponding embodiment thereof.

[0021] In a fifth aspect, the present invention provides a computer program product, including computer instructions, which are used to enable a computer to execute the public and private charging pile classification method based on vehicle charging behavior data of the above-mentioned first aspect or any corresponding embodiment. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0023] Figure 1 is a flow chart of a method for classifying public and private charging piles based on vehicle charging behavior data according to an embodiment of the present invention;

[0024] Figure 2 is a structural block diagram of a public and private charging pile classification device based on vehicle charging behavior data according to an embodiment of the present invention;

[0025] Figure 3 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0027] Based on relevant technologies, as the world's awareness of environmental protection increases and the energy structure transforms, electric vehicles (EVs) have gradually become the main choice to replace traditional fuel vehicles with their advantages of zero emissions, low noise, and high efficiency. The rapid development of the electric vehicle industry has not only promoted the progress of related fields such as battery technology and drive systems, but also put forward higher requirements for the construction of charging infrastructure. As a key facility for electric vehicle energy replenishment, the number, distribution and operation efficiency of charging piles directly affect the popularity of electric vehicles and user experience.

[0028] In order to distinguish between public and private charging piles and optimize their use, a charging pile classification system based on geographic location information is currently used to mark charging piles as public or private through GPS positioning and database matching.

[0029] However, although GPS positioning technology can provide geographical location information of charging piles to a certain extent, the positioning accuracy may be affected by environmental factors (such as high-rise buildings, tunnels and other obstructions). In some cases, users may find it difficult to find the exact location of the charging pile due to inaccurate positioning, which increases the difficulty of use.

[0030] Based on this, the present invention provides a method for classifying public and private charging piles based on vehicle charging behavior data. By collecting and analyzing the charging behavior data of the vehicle, the charging locations and times frequently visited by the vehicle can be identified. These behavior patterns can provide users with additional positioning references. Even if the GPS signal is interfered with, the possible charging pile locations can be inferred based on historical charging behaviors. Using clustered behavior data, the distribution of charging piles can be further refined. By identifying the clustering characteristics of charging behavior data, the potential location of the charging pile can be inferred, especially for areas with poor GPS signals. Based on preset matching rules, clustered behavior data, and public pile categories, the private pile category corresponding to the clustered behavior data can be determined, which improves the identification of whether the user owns a private pile and the use of the private pile, and provides data support for the promotion and optimization of private piles.

[0031] According to an embodiment of the present invention, an embodiment of a method for classifying public and private charging piles based on vehicle charging behavior data is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0032] In this embodiment, a method for classifying public and private charging piles based on vehicle charging behavior data is provided, which can be used for computer devices such as computers, servers, etc. Figure 1 FIG. 1 is a flow chart of a method for classifying public and private charging piles based on vehicle charging behavior data according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0033] Step S101 : determining clustering behavior data corresponding to the charging behavior data based on the charging behavior data of the vehicle.

[0034] The charging behavior data of the vehicle can be used to characterize the relevant data generated when the vehicle is charged. Among them, the charging behavior data may include but is not limited to the vehicle vin, charging start time, charging end time, charging start SOC, charging end SOC, charging longitude, charging latitude and charging power, etc., wherein the charging behavior data may be the charging behavior data within an area (such as area A, area B, etc.). Clustering behavior data can be used to characterize the data set obtained by clustering analysis of the charging behavior data. Among them, the clustering behavior data may be: cluster ID (such as the ID of each cluster forming a cluster), province, city, cluster center point longitude, cluster center point latitude and each charging detail information data set in the category (such as charging start time, charging end time, charging start SOC, charging end SOC, etc.). For example: area A and area B are two clustered clusters, A and B are corresponding cluster IDs, and each charging detail information data set in area A is divided into cluster A, and each charging detail information data set in area B is divided into cluster B. Specifically, the charging behavior data of the vehicle is collected. The collected charging behavior data is preprocessed, such as data cleaning and data conversion, to ensure the accuracy and consistency of the data. Clustering algorithms (such as K-means, hierarchical clustering, density-based clustering algorithm DBSCAN, etc.) are used to perform cluster analysis on the preprocessed charging behavior data to obtain clustered behavior data.

[0035] Optionally, the charging order data provided by the charging operator can also be obtained, including but not limited to order ID, charging user ID, charging start time, charging end time, charging start SOC, charging end SOC, charging station ID, charging station longitude, charging station latitude, and charging power. You can also obtain the charging station static information table: the charging station information table contains the description information of the station, including but not limited to the station ID, station name, province, city, longitude, latitude, operator, number of fast charging piles, and number of slow charging piles. You can also obtain the private pile static information table; the private pile information table contains the description information of the station, including but not limited to: private pile ID, private pile name, province, city, longitude and latitude.

[0036] Step S102, determining the public pile category corresponding to the clustering behavior data.

[0037] The public pile category can characterize the category to which the clustering behavior data corresponding to the public charging pile belongs. Public charging piles usually refer to charging piles built in public places. Specifically, the clustering behavior data is analyzed to calculate the total number of charging times and the number of vehicles in each clustering category. According to the preset thresholds (such as the thresholds of the total number of charging times and the number of vehicles), it is judged whether each clustering category belongs to the public pile category. If the total number of charging times and the number of vehicles of a clustering category exceed the preset thresholds, it is judged as a public pile category, etc. For example: Assume that the preset total number of charging times threshold is 1000 times, and the number of vehicles threshold is 50 vehicles. Among the 5 clustering behavior data sets obtained in step S101, the total number of charging times and the number of vehicles of 2 sets exceed the preset thresholds, so these 2 sets are judged as public pile categories.

[0038] Step S103, based on the preset matching rule, the clustering behavior data and the public pile category, determine the private pile category corresponding to the clustering behavior data.

[0039] The private pile category can be characterized as the category to which the clustering behavior data corresponding to the private charging pile belongs. Private charging piles usually refer to charging piles installed by individuals or families near their own parking spaces or residences for private use. Specifically, the remaining clustering behavior data are analyzed to exclude data that have been determined to be public pile categories. According to the preset matching rules (such as charging location, charging time and other features), the remaining clustering behavior data are matched to the private pile category. If the characteristics of a certain clustering behavior data are highly matched with the characteristics of the private pile category, it is determined to be a private pile category. For example: In addition to the two sets determined as public pile categories in step S102, there are three clustering behavior data sets. Assume that the preset matching rule is: the clustering behavior data with charging locations near residential areas and charging time mainly at night is determined to be a private pile category. According to this rule, two of the sets that meet the characteristics are determined to be private pile categories.

[0040] In a possible implementation, the preset matching rules can be adjusted according to actual needs to obtain a more accurate private pile category determination result. A machine learning algorithm (such as a decision tree, a support vector machine, etc.) can be used to automatically match the private pile category, etc., which is not specifically limited here.

[0041] The public and private charging pile classification method based on vehicle charging behavior data provided in this embodiment can identify the charging locations and times frequently visited by vehicles by collecting and analyzing the charging behavior data of vehicles. These behavior patterns can provide users with additional positioning references. Even if the GPS signal is interfered with, the possible charging pile locations can be inferred based on historical charging behaviors. Using clustered behavior data, the distribution of charging piles can be further refined. By identifying the clustering characteristics of charging behavior data, the potential location of charging piles can be inferred, especially for areas with poor GPS signals. Based on preset matching rules, clustered behavior data, and public pile categories, the private pile category corresponding to the clustered behavior data can be determined, which improves the identification of whether users own private piles and the use of private piles, and provides data support for the promotion and optimization of private piles.

[0042] In an optional implementation, the above step S103 includes:

[0043] Step a1, based on the public pile category, determine the target category; wherein the target category refers to the category in the cluster category except the public pile category.

[0044] The target category refers to other clustering categories besides the public charging pile category, which may be the private charging pile category or other charging pile categories that have not yet been clearly classified. Specifically, the charging piles that have been marked as public charging piles in the data set are identified, and then the remaining charging piles are processed as target categories. Specifically, the public charging pile category can be directly filtered based on the existing classification labels. Machine learning algorithms can also be used to preliminarily classify the data, and then the data in the non-public charging pile category is selected as the target category.

[0045] Step a2, detecting whether there is station location information for the target category.

[0046] The station location information may refer to the specific location information of the station (private charging pile) where the charging pile is located, such as address, longitude and latitude, etc. Check whether each charging pile in the target category contains the station location information.

[0047] Step a3: If there is no station location information for the target category, detect whether the clustering behavior data corresponding to the target category meets the preset conditions.

[0048] The preset conditions can characterize the characteristics used to determine whether the clustering behavior data meets a specific category (such as a private pile category). Specifically, for charging piles that do not contain station location information, their clustering behavior data is further analyzed to determine whether they meet the preset private pile category conditions. For example: for 200 charging piles that do not contain station location information, if their clustering behavior data (such as frequency of use, usage time, etc.) meet the preset private pile category conditions (such as low frequency of use, mainly used during non-working hours, etc.), the next step of judgment is performed.

[0049] Step a4: If the clustering behavior data meets the preset conditions, the target category is determined to be a private pile category.

[0050] If the clustering behavior data of the charging piles of the target category meets the preset private pile category conditions without the site location information, they will be judged as private pile categories. For example: among the 200 charging piles mentioned above, if the clustering behavior data of 150 of them meet the preset private pile category conditions, they will be judged as private pile categories. Through the above steps, the charging pile data can be effectively classified, and the public and private pile categories can be distinguished, providing a basis for subsequent analysis and management.

[0051] The public and private charging pile classification method based on vehicle charging behavior data provided in this embodiment can effectively screen out clustered behavior data that may belong to private charging piles by first determining the target category and then detecting the station location information. This step greatly reduces the amount of data for subsequent judgment, improves processing efficiency, and reduces misjudgment.

[0052] In an optional implementation, the station location information includes: the location of the private charging station; wherein the above method further includes:

[0053] Step b1: If the target category has station location information, calculate the first distance between the cluster area corresponding to the target category and the location of the private charging station.

[0054] The clustering area can characterize the area obtained by clustering analysis, which contains a group of charging piles with similar characteristics. The first distance refers to the spatial distance between the clustering area and the private charging station. Specifically, for the target category containing the station location information, its clustering area is first determined, and then the spatial distance between the clustering area and the known private charging station is calculated. For example: the target category M contains 50 charging piles, and the longitude and latitude of the center point of its clustering area are (X1, Y1). The longitude and latitude of the known private charging station N are (X2, Y2). The Haversine formula can be used to calculate the first distance between M and N.

[0055] Preferably, the clustering area can be a circular area with a certain radius, wherein the size of the clustering area and the preset value for judgment are determined during the training process of the clustering model. In actual situations, the radius of the clustering area is generally selected within the range of 10-100 meters, and the preset value is selected within the range of 2-5.

[0056] Step b2: if the first distance is less than the first preset distance threshold, the clustering behavior data within the target category is matched with the corresponding private pile charging station to determine that the target category is a private pile category.

[0057] If the calculated first distance is less than the preset distance threshold, it is considered that there may be an association between the target category and the private pile charging station, and the clustering behavior data within the target category is further matched with the private pile charging station to determine whether it is a private pile category. Specifically, the characteristics of the clustering behavior data (such as charging time, charging amount, etc.) are matched with the usage pattern of the private pile charging station. If the number of charging piles in the target category is small, and its clustering behavior data is highly consistent with the usage pattern of the private pile charging station, it can be directly judged that the target category is a private pile category. If the number of charging piles in the target category is large, it may be necessary to further analyze the distribution and characteristics of its behavior data to more accurately judge its category. For example: the first preset distance threshold is 1 kilometer. If the first distance between the target category M and the private pile charging station N is less than 1 kilometer, and the clustering behavior data in M ​​(such as charging time is mainly concentrated at night, charging amount is small, etc.) is highly consistent with the usage pattern of N, then the target category N can be judged to be a private pile category.

[0058] The public and private charging pile classification method based on vehicle charging behavior data provided in this embodiment can accurately identify which charging stations belong to private charging piles by including the location information of private charging stations. This avoids the mistaken classification of public charging piles as private piles and improves the accuracy of classification. When the target category has station location information, the first distance between the category and the private charging station can be calculated. By setting the first preset distance threshold, the target category that is close to the private charging station can be quickly screened out and then classified as a private charging pile category. This matching method based on geographic location is more intuitive and reliable.

[0059] In an optional embodiment, the clustering behavior data includes: at least one of the latitude and longitude information of the center point, the number of vehicles, the number of vehicle charging times, the average charging time, the average time interval between two consecutive charging times, the proportion of fast charging, and the proportion of nighttime charging times; wherein the above step a2 includes:

[0060] Step a21, obtaining the location information of the preset point of interest.

[0061] The preset points of interest can be used to represent predefined geographical locations, such as residential areas, commercial areas, office areas, etc. The geographical location coordinates of the preset points of interest can be obtained from a database or a map service. Specifically, the location information of the preset points of interest can be queried using a geographic information system (GIS) tool. The latitude and longitude information of the preset points of interest can also be obtained from an online map service API. This is not specifically limited here and can be implemented by those skilled in the art.

[0062] Step a22, determining a second distance between the location information of the preset point of interest and the longitude and latitude information of the center point.

[0063] The center point longitude and latitude information may be the geographic location coordinates of a cluster center, expressed in longitude and latitude. The spatial distance between the location information of the preset point of interest and the center point longitude and latitude information is calculated. For example, the second distance between the residential area F and the center point G is calculated to be 0.5 kilometers.

[0064] Step a23, detecting whether the second distance is less than a preset distance threshold.

[0065] The preset distance threshold can be used to determine whether the distance between the preset interest point and the center point is close enough. Specifically, it is determined whether the second distance is less than the preset threshold to determine whether the preset interest point and the center point are close enough.

[0066] In one possible implementation, the following features are calculated for each cluster category:

[0067] POI feature: If the center point is in the community, the isCommunity feature is 1, otherwise it is 0. The solution to determine whether the center point is in the community is based on the Euclidean distance between the center point and the POI point.

[0068] Among them: lng q is the longitude of the center point, lat q is the latitude of the center point, lng p is the longitude of the POI, lat p is the latitude of the POI. If D is less than each threshold, for example, 500 meters, and the category of the POI is a community, isCommunity is 1, otherwise it is 0.

[0069] Step a24, detecting whether the number of vehicles is less than a preset number within a preset period.

[0070] The preset period refers to the time range for data analysis, such as one day, one week, one month, etc. The number of vehicles charging near the center point within the preset period is counted, and it is determined whether it is less than the preset number. For example: In one day, the number of vehicles charging near the center point C is 10. If the preset number is 20, the condition is met.

[0071] Step a25, detecting whether the number of charging times within a preset period is less than a preset number of charging times.

[0072] Count the number of times the battery is charged near the center point within a preset period, and determine whether it is less than the preset number of times. For example, if the number of times the battery is charged near the center point C is 20 times in one day, if the preset number of times is 50, the condition is met.

[0073] Step a26, detecting whether the average charging time is less than the preset charging time.

[0074] The preset charging time is used to determine whether the average charging time is short enough. Calculate the average charging time near the center point within the preset period and determine whether it is less than the preset charging time. For example, if the average charging time near the center point C is 2 hours in one day, if the preset charging time is 4 hours, the condition is met.

[0075] In a possible implementation, the average duration of each charging may be calculated using the following formula:

[0076] Where N is the total number of charging times within the category, Dur i is the duration of the i-th charging.

[0077] Step a27, detecting whether the average time interval between two consecutive charges is less than a preset time interval.

[0078] The preset time interval is used to determine whether the average time interval between two consecutive charges is short enough. The preset time interval can be 1 hour, 5 hours, 1 day, etc., which is not specifically limited here.

[0079] In a possible implementation, the charging behaviors within a category are sorted according to the charging start time, and then the difference between two charging start times is calculated. The following formula may be used:

[0080] Where: N is the total number of charging times within the category, t i is the timestamp of the start of the i-th charging, t i-1 The timestamp of the start of the last charging of the i-th time.

[0081] Step a28, detecting whether the fast charging ratio is less than the preset ratio.

[0082] The preset ratio can be used to determine whether the fast charge ratio is low enough. Specifically, first calculate the number of fast charges (charging power greater than a certain threshold) and the total number of charges within the category, and the calculation formula is as follows:

[0083] Among them, quick_ratio is the proportion of fast charging, count quick is the number of fast charging times, and N is the total number of charging times.

[0084] Step a29, detecting whether the proportion of nighttime charging times is less than a preset nighttime charging times.

[0085] The preset number of nighttime charging times can be used as a threshold for determining whether the proportion of nighttime charging times is sufficiently low. Specifically, the time period defined for nighttime charging can be between 18:00 and 6:00 the next day when charging starts.

[0086] Among them, night_ratio is the proportion of charging at night, count night is the number of nighttime charging times, and N is the total number of charging times.

[0087] The public and private charging pile classification method based on vehicle charging behavior data provided in this embodiment includes multiple dimensions such as the center point longitude and latitude information, the number of vehicles, the number of charging times, the average charging time, the average time interval between two consecutive charging times, the proportion of fast charging, and the proportion of nighttime charging times. By matching the clustering behavior data with the preset conditions, the charging stations that meet the specific conditions can be accurately identified.

[0088] In an optional embodiment, the charging behavior data of the vehicle includes: the latitude and longitude information of the vehicle when the vehicle is charging; wherein the above step S101 includes:

[0089] Step c1, clustering the vehicle longitude and latitude information corresponding to each vehicle during vehicle charging to obtain a plurality of clustering results; wherein the clustering results include: clustered vehicle longitude and latitude information.

[0090] The clustering processing results may include: cluster ID, province, city, longitude of cluster center, latitude of cluster center, and a data set of charging details for each category. Specifically, collect the longitude and latitude information of each vehicle when charging. Use clustering algorithms (such as K-means, DBSCAN, etc.) to cluster these longitude and latitude information. Get multiple clustering processing results, each result represents a cluster center of a charging location or area and the charging points it contains. For example: For each vehicle, select charging data for a period of time (for example: 1 month). Based on the longitude and latitude of the vehicle when charging as clustering features. According to the characteristics of the data, and because the number of cluster categories is unknown, the density-based clustering algorithm DBSCAN is selected for clustering. After multiple optimizations, the single vehicle charging data is clustered.

[0091] Step c2: performing clustering processing on a plurality of clustering processing results based on the clustered vehicle longitude and latitude information to determine clustering behavior data corresponding to the charging behavior data.

[0092] The multiple clustering results obtained in step c1 are regarded as new data points, which contain the clustered vehicle latitude and longitude information and their corresponding clustering features (such as cluster center, cluster size, etc.). These new data points are clustered again to find the characteristics of different charging behaviors or modes. Clustering behavior data are obtained, which reflect the clustering characteristics or modes of different charging behaviors.

[0093] The public and private charging pile classification method based on vehicle charging behavior data provided in this embodiment performs preliminary clustering processing on the charging latitude and longitude information of each vehicle, and can obtain multiple clustering processing results, which reflect the spatial distribution and agglomeration of charging behaviors of different vehicle groups. Based on these preliminary clustering results, a higher level of clustering processing is performed to more accurately determine the clustering behavior data corresponding to the charging behavior data, and to capture subtle differences in charging behavior.

[0094] In an optional implementation, the clustering behavior data includes multiple clustering categories, a total number of charging times, and a number of vehicles; wherein the above step S102 includes:

[0095] Step d1, determining the total number of charging times and the number of vehicles corresponding to the clustering category; wherein the total number of charging times is the total number of times the vehicles corresponding to the clustering behavior data are charged, and the number of vehicles is the number of vehicles participating in overcharging corresponding to the clustering behavior data.

[0096] Specifically, the present invention utilizes clustering categories to correspond to the total number of charging times of vehicles and the number of vehicles that have been charged in vehicle charging data. The following is an example to illustrate the meaning of the total number of charging times and the number of vehicles. For example, the vehicle charging data in a clustering category includes five vehicles, namely the first vehicle, the second vehicle, the third vehicle, the fourth vehicle, and the fifth vehicle. The first vehicle is charged three times, the second vehicle is charged twice, the third vehicle is charged once, the fourth vehicle is charged once, and the fifth vehicle is charged twice. Therefore, the total number of charging times is 3+2+1+1+2=9 times. The number of vehicles that have been charged is 5.

[0097] Step d2: if the total number of charging times is greater than the preset number of charging times and the number of vehicles is greater than the preset number of vehicles, the clustering category corresponding to the clustering behavior data is determined as a public charging pile category.

[0098] Specifically, by comparing the total number of charging times with the preset number of charging times, and comparing the number of vehicles with the preset number of vehicles, if the total number of charging times is greater than the preset number of charging times, and the number of vehicles is greater than the preset number of vehicles, it is considered that the amount of data in the location category meets the data characteristics of vehicles charging at public charging stations, and therefore the cluster category is determined as a public pile category. After the public pile category is determined, the vehicle charging data of the public pile category is matched with the charging station. The closer the distance between the two, the higher the degree of match between the two. Therefore, the present invention uses the relationship between the distance value between the two and the preset distance threshold to determine whether the public pile category matches the charging station.

[0099] The public and private charging pile classification method based on vehicle charging behavior data provided in this embodiment can more accurately evaluate the characteristics of clustering behavior data by comprehensively considering the two dimensions of total charging times and number of vehicles, thereby more accurately determining which clustering categories belong to the public charging pile category. In addition, setting the preset charging times and the preset number of vehicles as judgment criteria helps to avoid interference from subjective judgment and improve the objectivity and accuracy of data processing.

[0100] In one possible implementation, the clustering behavior data is balanced by downsampling, and then the samples are divided into a training set and a test set in a ratio of 8:2. The tree model LightGBM is used for training on the training set, and the best key hyperparameters are selected through parameter tuning as follows to train the model clf1.

[0101] params={

[0102] 'n_estimators':200,

[0103] 'max_depth':5,

[0104] 'num_leaves':10,

[0105] 'learning_rate':0.01,

[0106] 'subsample':0.7,

[0107] }

[0108] Step 2: Use model clf1 to predict all unlabeled cluster categories. For each category, the probability of belonging to private piles can be calculated, and then sorted from large to small according to probability, and the top N% are taken as private pile samples to supplement the original sample set. N can be selected according to the accuracy rate of public piles in the selected category set. After obtaining a new sample set, repeat the steps of step 1 to train the final classification model clf.

[0109] In this embodiment, a public and private pile classification device based on vehicle charging behavior data is also provided, which is used to implement the above-mentioned embodiments and preferred embodiments, and will not be repeated here. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0110] This embodiment provides a public and private charging pile classification device based on vehicle charging behavior data, such as Figure 2As shown, it includes: a first determination module 201, which is used to determine the clustering behavior data corresponding to the charging behavior data based on the charging behavior data of the vehicle; a second determination module 202, which is used to determine the public charging pile category corresponding to the clustering behavior data; a third determination module 203, which is used to determine the private charging pile category corresponding to the clustering behavior data based on a preset matching rule, the clustering behavior data and the public charging pile category.

[0111] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0112] The public and private charging pile classification device based on vehicle charging behavior data in this embodiment is presented in the form of a functional unit, where the functional unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0113] The embodiment of the present invention also provides a computer device having the above Figure 2 The public and private charging pile classification device based on vehicle charging behavior data is shown.

[0114] See also Figure 3 , Figure 3 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 3 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 3 A processor 10 is taken as an example.

[0115] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0116] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0117] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0118] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0119] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0120] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0121] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0122] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for classifying public and private charging piles based on vehicle charging behavior data, characterized in that: The method comprises: Based on the charging behavior data of the vehicle, determining clustering behavior data corresponding to the charging behavior data; Determining the public pile category corresponding to the clustering behavior data; Based on the preset matching rules, the clustering behavior data and the public pile category, the private pile category corresponding to the clustering behavior data is determined.

2. The method for classifying public and private charging piles based on vehicle charging behavior data according to claim 1 is characterized in that: The determining, based on a preset matching rule, the clustering behavior data and the public pile category, the private pile category corresponding to the clustering behavior data includes: Based on the public pile category, determine the target category; wherein the target category refers to the category in the cluster category except the public pile category; Detecting whether there is station location information for the target category; If the target category does not have station location information, detecting whether the clustering behavior data corresponding to the target category meets a preset condition; If the clustering behavior data meets the preset conditions, the target category is determined to be the private pile category.

3. The method for classifying public and private charging piles based on vehicle charging behavior data according to claim 2 is characterized in that: The station location information includes: the location of the private charging station; wherein the method further includes: If the target category has station location information, calculate a first distance between the cluster area corresponding to the target category and the location of the private charging station; If the first distance is less than a first preset distance threshold, the clustering behavior data within the target category is matched with the corresponding private pile charging station to determine that the target category is the private pile category.

4. The method for classifying public and private charging piles based on vehicle charging behavior data according to claim 2 is characterized in that: The clustering behavior data includes at least one of the latitude and longitude information of the center point, the number of vehicles, the number of vehicle charging times, the average charging time, the average time interval between two consecutive charging times, the proportion of fast charging, and the proportion of nighttime charging times; wherein, whether the clustering behavior data corresponding to the detection target category meets the preset conditions includes: Get the location information of preset points of interest; Determine a second distance between the location information of the preset point of interest and the latitude and longitude information of the center point; detecting whether the second distance is less than a preset distance threshold; and / or, Detecting whether the number of vehicles is less than a preset number within a preset period; and / or, Detecting whether the number of charging times within a preset period is less than a preset number of charging times; and / or, Detecting whether the average charging time is less than a preset charging time; and / or, Detecting whether the average time interval between two consecutive charges is less than a preset time interval; and / or, Detect whether the fast charging ratio is less than the preset ratio; and / or, Check whether the proportion of nighttime charging times is less than the preset nighttime charging times.

5. The method for classifying public and private charging piles based on vehicle charging behavior data according to claim 1 is characterized in that: The charging behavior data of the vehicle includes: the latitude and longitude information of the vehicle when the vehicle is charging; wherein, based on the charging behavior data of the vehicle, the clustering behavior data corresponding to the charging behavior data is determined, including: Clustering the vehicle longitude and latitude information corresponding to each vehicle during vehicle charging to obtain multiple clustering results; wherein the clustering results include: clustered vehicle longitude and latitude information; Based on the clustered vehicle longitude and latitude information, cluster processing is performed on the plurality of cluster processing results to determine cluster behavior data corresponding to the charging behavior data.

6. The method for classifying public and private charging piles based on vehicle charging behavior data according to claim 5 is characterized in that: The clustering behavior data includes multiple clustering categories, a total number of charging times, and a number of vehicles; wherein determining the public charging pile category corresponding to the clustering behavior data includes: Determine the total number of charging times and the number of vehicles corresponding to the clustering category; wherein the total number of charging times is the total number of times the vehicles corresponding to the clustering behavior data are charged, and the number of vehicles is the number of vehicles involved in overcharging corresponding to the clustering behavior data; If the total number of charging times is greater than a preset number of charging times and the number of vehicles is greater than a preset number of vehicles, the clustering category corresponding to the clustering behavior data is determined as the public charging pile category.

7. A public and private charging pile classification device based on vehicle charging behavior data, characterized in that: The device comprises: A first determination module, configured to determine clustering behavior data corresponding to the charging behavior data based on the charging behavior data of the vehicle; A second determination module is used to determine the public pile category corresponding to the clustering behavior data; The third determination module is used to determine the private pile category corresponding to the clustering behavior data based on a preset matching rule, the clustering behavior data and the public pile category.

8. A computer device, characterized in that: include: 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 public-private charging pile classification method based on vehicle charging behavior data according to any one of claims 1 to 6 by executing the computer instructions.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the public-private charging pile classification method based on vehicle charging behavior data according to any one of claims 1 to 6.

10. A computer program product, characterized in that The method comprises computer instructions for causing a computer to execute the method for classifying public and private charging piles based on vehicle charging behavior data according to any one of claims 1 to 6.

Images