A charging pile data push method and system

Abstract

The present invention relates to the field of big data push processing technology, and in particular to a charging pile data push method and system. The method comprises the following steps: obtaining urban geographic traffic data; using urban geographic traffic data to analyze the regional distribution of charging piles, and obtaining regional distribution data of charging piles; extracting charging pile usage history data according to the regional distribution data of charging piles, and obtaining charging pile usage history data; extracting charging pile usage preference features from the charging pile usage history data according to the regional distribution data of charging piles, and obtaining charging pile usage preference feature data; mining user charging habits from the charging pile usage preference feature data, and thus obtaining regional user charging habit data. The present invention not only meets the goal of charging pile data push by pushing charging pile data for target users who may have charging needs without involving user privacy, but also realizes highly personalized services under the premise of protecting user privacy.

Description

Technical Field

[0001] The present invention relates to the technical field of large data push processing, and in particular to a charging pile data push method and system. Background Art

[0002] The development of charging pile data push methods has evolved from fixed time periods to real-time status, to user location-based and personalized push, and finally to the intelligent stage of predictive push. In this process, the continuous innovation of technology and the continuous changes in user needs have promoted the continuous progress of push methods. With the continuous development of technology, charging pile data push methods are expected to be more intelligent and personalized, and better meet the actual needs of users. However, the existing intelligent and personalized charging pile data push will involve user privacy issues, and large-scale push will result in a waste of network resources. Summary of the invention

[0003] Based on this, it is necessary to provide a charging pile data push method and system to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a charging pile data push method includes the following steps:

[0005] Step S1: obtaining urban geographic traffic data; using the urban geographic traffic data to analyze the regional distribution of charging piles, thereby obtaining regional distribution data of charging piles; extracting charging pile usage history data based on the regional distribution data of charging piles, thereby obtaining historical usage data of charging piles;

[0006] Step S2: extracting the usage preference features of charging piles from the usage history data of charging piles according to the regional distribution data of charging piles, thereby obtaining the usage preference feature data of charging piles; mining the user charging habits of the usage preference feature data of charging piles, thereby obtaining the charging habit data of regional users;

[0007] Step S3: Extract the characteristics of electric vehicle stop points using urban geographic traffic data, thereby obtaining electric vehicle stop time characteristic data; extract regional charging pile associated weight factors based on charging pile distribution map data, thereby obtaining regional charging pile associated weight factors; construct a regional stop electric vehicle charging prediction model based on the regional charging pile associated weight factors, thereby obtaining a regional stop electric vehicle charging prediction model;

[0008] Step S4: using the regional electric vehicle charging prediction model to predict the regional electric vehicle charging, thereby obtaining the regional electric vehicle charging parameters; calculating the user charging demand expectation value according to the regional electric vehicle charging parameters, thereby obtaining the user charging demand expectation value;

[0009] Step S5: Make an expected value judgment based on the expected value of the user's charging demand, so as to obtain the regional data of the charging piles to be matched; match the regional user charging demand of the charging pile regional data to be matched and the regional user charging habit data, so as to obtain the regional data of the charging piles to be pushed; push the charging data of users in a specific area to the regional data of the charging piles to be pushed according to the regional distribution data of the charging piles, so as to realize the charging pile data push work.

[0010] By acquiring urban geographic traffic data, the present invention can fully understand the urban traffic conditions and provide a basis for the reasonable distribution of subsequent charging piles. The regional distribution analysis of charging piles can reveal the differences in charging demand in different regions, which is helpful to optimize the distribution of charging piles. The extraction of historical data on the use of charging piles provides an important basis for understanding user behavior, thereby laying a foundation for the subsequent construction of user behavior models; by extracting the characteristics of charging pile usage preferences, the user's use tendency of charging piles can be deeply understood, and the user portrait can be further refined. User charging habit mining helps to identify the charging characteristics of different user groups, provide a basis for personalized push, and improve service accuracy. The extraction of electric vehicle dwell time feature data helps to understand the driving mode of electric vehicles and provide time dimension support for predicting charging demand. The extraction of regional charging pile association weight factors can consider the correlation between charging piles and improve the accuracy of charging prediction. Constructing a regional stop electric vehicle charging prediction model helps to predict the charging demand in a certain area in advance, so as to better meet user expectations. Using the prediction model to predict the regional electric vehicle dwell charging can more accurately estimate the charging demand and provide a basis for charging pile data push. By calculating the expected value of user charging demand, the user's expectation for charging can be quantified, providing data support for subsequent personalized push. By making an expected value judgment based on the expected value of the user's charging demand, it is possible to more intelligently select the regional data of the charging pile to be matched, thereby improving the accuracy of the charging push. The regional user charging demand matching is combined with the user's charging habit data to match the most suitable charging pile for the user, thereby improving user satisfaction. Pushing charging data of users in a specific area helps to refine services and improve user experience. Therefore, the present invention provides a charging pile data push method and system, which pushes charging pile data to target users who may have charging needs without involving user privacy. This system not only meets the goal of charging pile data push, but also realizes highly personalized services under the premise of protecting user privacy.

[0011] Preferably, step S1 comprises the following steps:

[0012] Step S11: obtaining urban geographic traffic data; performing data standardization on the urban geographic traffic data, thereby obtaining urban geographic traffic standard data, wherein the urban geographic traffic standard data includes urban geographic standard data and electric vehicle traffic standard data;

[0013] Step S12: Analyze the distribution of charging piles using the urban geographic standard data, so as to obtain the distribution map data of charging piles;

[0014] Step S13: Divide the charging pile distribution map data into regions and perform labeling processing to obtain charging pile regional distribution data;

[0015] Step S14: extracting charging pile usage history data according to the charging pile regional distribution data, thereby obtaining the charging pile usage history data.

[0016] By standardizing urban geographic traffic data, the present invention can process data from different sources and formats in a consistent manner, thereby improving the comparability and consistency of the data; by analyzing urban geographic standard data, it is possible to fully understand the spatial distribution of charging piles, discover potential areas of concentrated charging demand, and provide strong support for subsequent push strategies; by performing regional division and annotation processing on the charging pile distribution map data, a detailed portrayal of urban areas is achieved, which helps to accurately capture the charging demand characteristics in different areas; by extracting historical data on the charging pile regional distribution data, the usage of charging piles in each area is obtained, providing a key data basis for subsequent modeling.

[0017] Preferably, step S2 comprises the following steps:

[0018] Step S21: performing spatial cluster analysis on the charging pile usage history data according to the charging pile regional distribution data, thereby obtaining the charging pile usage history spatial cluster data;

[0019] Step S22: extracting the charging pile usage preference features from the charging pile usage history data according to the charging pile usage history spatial cluster data, thereby obtaining the charging pile usage preference feature data, wherein the charging pile usage preference feature data includes user behavior time series feature data, usage frequency trend feature data, and power preference feature data;

[0020] Step S23: clustering the user behavior time series feature data by charging preference time period, thereby obtaining charging preference time period clustering data;

[0021] Step S24: performing temporal-spatial fusion on the historical spatial cluster data of charging pile usage and the cluster data of charging preference time periods, thereby obtaining spatiotemporal user charging preference data;

[0022] Step S25: using probability distribution analysis technology to perform user charging characteristic distribution analysis on the spatiotemporal user charging preference data, thereby obtaining user charging characteristic distribution data;

[0023] Step S26: Perform regional association rule mining on the user charging feature distribution data to obtain regional user charging habit data.

[0024] Through spatial cluster analysis, the present invention can cluster the charging pile usage history data according to geographical location and identify charging pile groups with similar usage characteristics in similar areas; it helps to better understand the spatial distribution pattern of charging piles and improve the spatial perception of regional charging needs. Extracting charging pile usage preference features from the charging pile usage history spatial cluster data, including user behavior time series features, usage frequency trend features and power preference features, helps to deeply understand the user's charging preferences in different areas and provide more accurate feature information for subsequent personalized push. Clustering the user behavior time series feature data into charging preference time periods helps to mine the user's charging preference time periods in different time periods; it enables us to understand the user's behavior patterns in more detail and further improve the time perception of user needs. Through time-series space fusion, the charging pile usage history spatial cluster data is combined with the charging preference time period cluster data to form spatiotemporal user charging preference data; it helps to capture the user's complex charging behavior patterns in the spatiotemporal dimension and provide more comprehensive user charging preference information. Using probability distribution analysis technology to analyze the spatiotemporal user charging preference data helps to deeply understand the probability distribution of user charging behavior; it provides statistical support for the formulation of subsequent push strategies and ensures the accuracy and rationality of push. By mining regional association rules of user charging feature distribution data, we can discover the association patterns of user charging habits between different regions; this helps to build a regional user charging habit model and provide a deeper understanding for the personalized design of push strategies.

[0025] Preferably, step S22 includes the following steps:

[0026] Step S221: extracting user behavior time series features from the charging pile usage history data according to the charging pile usage history spatial cluster data, thereby obtaining user behavior time series feature data;

[0027] Step S222: performing a charging pile usage frequency analysis on the charging pile usage history data according to the charging pile usage history spatial cluster data, thereby obtaining usage frequency trend feature data;

[0028] Step S223: collecting charging pile power from the charging pile usage history data according to the charging pile usage history spatial cluster data, thereby obtaining charging pile power data;

[0029] Step S224: Utilize the user behavior time series feature data to perform time period power preference analysis on the charging pile power data and perform power charging duration analysis, thereby obtaining power preference feature data.

[0030] Through spatial cluster analysis, the present invention can cluster the charging pile usage history data according to geographical location and identify charging pile groups with similar usage characteristics in similar areas; it helps to better understand the spatial distribution pattern of charging piles and improve the spatial perception of regional charging needs. Extracting charging pile usage preference features from the charging pile usage history spatial cluster data, including user behavior time series features, usage frequency trend features and power preference features, helps to deeply understand the user's charging preferences in different areas and provide more accurate feature information for subsequent personalized push. Clustering the user behavior time series feature data into charging preference time periods helps to mine the user's charging preference time periods in different time periods; it enables us to understand the user's behavior patterns in more detail and further improve the time perception of user needs. Through time-series space fusion, the charging pile usage history spatial cluster data is combined with the charging preference time period cluster data to form spatiotemporal user charging preference data; it helps to capture the user's complex charging behavior patterns in the spatiotemporal dimension and provide more comprehensive user charging preference information. Using probability distribution analysis technology to analyze the spatiotemporal user charging preference data helps to deeply understand the probability distribution of user charging behavior; it provides statistical support for the formulation of subsequent push strategies and ensures the accuracy and rationality of push. By mining regional association rules of user charging feature distribution data, we can discover the association patterns of user charging habits between different regions; this helps to build a regional user charging habit model and provide a deeper understanding for the personalized design of push strategies.

[0031] Preferably, step S3 comprises the following steps:

[0032] Step S31: using the urban geographic standard data to spatially align and map the electric vehicle traffic standard data, thereby obtaining the electric vehicle traffic spatial alignment data;

[0033] Step S32: performing spatial regional division on the electric vehicle traffic spatial alignment data, thereby obtaining regional electric vehicle trajectory data; performing spatial trajectory density analysis on the regional electric vehicle trajectory data, thereby obtaining a spatial trajectory density heat map;

[0034] Step S33: extracting electric vehicle stop points from the regional electric vehicle trajectory data, thereby obtaining electric vehicle stop point data; extracting electric vehicle stop time features from the electric vehicle stop point data, thereby obtaining electric vehicle stop time feature data;

[0035] Step S34: extracting regional charging pile associated weight factors according to the charging pile distribution map data, thereby obtaining regional charging pile associated weight factors, wherein the regional charging pile associated weight factors include regional charging pile high weight associated factors, regional charging pile medium weight associated factors, and regional charging pile low weight associated factors;

[0036] Step S35: constructing a regional stopover electric vehicle charging prediction model based on the electric vehicle dwell time characteristic data, the spatial trajectory density heat map, and the regional charging pile associated weight factors, thereby obtaining a regional stopover electric vehicle charging prediction model.

[0037] The present invention obtains the accurate position of electric vehicle traffic data on the urban geographic standard through spatial alignment and mapping of urban geographic standard data, ensuring the accuracy and credibility of subsequent analysis; uses electric vehicle traffic spatial alignment data to perform spatial regional division and generate regional electric vehicle trajectory data; makes the analysis of electric vehicle driving trajectory more targeted, and can more accurately understand the movement characteristics of electric vehicles in different regions. Spatial trajectory density analysis generates a spatial trajectory density heat map, which provides an intuitive understanding of the hot spot distribution of electric vehicle traffic in different areas of the city, and provides visualization support for the subsequent extraction of electric vehicle stop points. By extracting electric vehicle stop points from regional electric vehicle trajectory data, the stop point information of electric vehicles in different areas of the city is obtained. Extracting the characteristics of electric vehicle stay time helps to deeply understand the stop behavior of electric vehicles in different locations, and provides key features for the subsequent prediction model construction. According to the charging pile distribution map data, the regional charging pile association weight factor is extracted, including high, medium and low weight association factors. This step provides a detailed regulation of the correlation of regional charging piles for the electric vehicle stop charging prediction model, and more comprehensively considers the importance of charging piles in different regions. Based on the electric vehicle stop time feature data, the spatial trajectory density heat map and the regional charging pile association weight factor, a regional stop electric vehicle charging prediction model is constructed. This model comprehensively considers the parking behavior of electric vehicles, regional traffic hotspots and the associated weights of charging piles, improving the accurate prediction of the charging demand of electric vehicles parked in the region.

[0038] Preferably, step S34 includes the following steps:

[0039] Step S341: collecting surrounding environment characteristics according to the charging pile distribution map data, thereby obtaining surrounding environment characteristic data; performing regional and charging pile data analysis according to the surrounding environment characteristic data, thereby obtaining regional and charging pile data;

[0040] Step S342: Calculate the distance between the area and the charging pile data, thereby obtaining the distance data between the charging piles; calculate the density of commercial facilities and perform workplace analysis on the area and the charging pile data, thereby obtaining the industrial and commercial distribution density value;

[0041] Step S343: when the distance value corresponding to the charging pile distance data is less than the preset charging pile standard distance value and the industrial and commercial distribution density value is greater than the preset industrial and commercial distribution standard density value, a high weight is assigned to the area and the charging pile data, thereby obtaining a high weight association factor of the regional charging pile;

[0042] Step S344: when the distance value corresponding to the charging pile distance data is less than the preset charging pile standard distance value and the industrial and commercial distribution density value is less than or equal to the preset industrial and commercial distribution standard density value, the charging pile distance data is weighted, thereby obtaining the weight association factor of the regional charging pile;

[0043] Step S345: When the distance value corresponding to the charging pile distance data is greater than or equal to the preset charging pile standard distance value and the industrial and commercial distribution density value is greater than the preset industrial and commercial distribution standard density value, a low weight is assigned to the area and the charging pile data, thereby obtaining a low weight association factor of the regional charging pile;

[0044] Step S346: When the distance value corresponding to the charging pile distance data is greater than or equal to the preset charging pile standard distance value and the industrial and commercial distribution density value is less than or equal to the preset industrial and commercial distribution standard density value, the area and the charging pile data are removed.

[0045] The present invention can more comprehensively understand the environmental conditions of the area where the charging piles are located by collecting surrounding environmental characteristic data, such as traffic flow, crowd density, commercial facility distribution, etc., combined with the charging pile distribution map data; it is helpful to identify potential factors affecting charging demand and improve the prediction accuracy of the model. The charging pile distance data is obtained through the distance calculation algorithm, and combined with the commercial facility density calculation and workplace analysis, the spatial distribution of the charging piles in the area can be evaluated. This helps to identify the coverage of the charging piles and the surrounding commercial prosperity, and provides data support for the subsequent calculation of the correlation factor. When the charging pile distance is less than the preset standard value and the commercial facility density is greater than the preset standard value, the area is given a high-weight correlation factor with the charging pile data; it helps to emphasize the commercial prosperous area within the coverage of the charging pile, the density of the electric vehicles staying is high, and the parking time is relatively long, so the probability of having a charging demand is high. When the charging pile distance is less than the preset standard value but the commercial facility density is less than or equal to the preset standard value, the charging pile distance data is given a weight; it helps to balance the areas with low commercial prosperity within the distribution range of the charging piles, the density of electric vehicles is low, and there are fewer users with charging needs in the area, so as to maintain a certain degree of attention to the area. When the distance to the charging pile is greater than or equal to the preset standard value and the density of commercial facilities is greater than the preset standard value, a low-weight association factor is assigned to the area and the charging pile data; this helps identify areas where charging piles are distributed around commercial bustling areas but are far away, reducing the emphasis on charging demand in this area. When the distance to the charging pile is greater than or equal to the preset standard value and the density of commercial facilities is less than or equal to the preset standard value, the area and the charging pile data are removed. This helps reduce the focus on areas with low commercial bustling and long distances, improves the simplicity of the model, and reduces redundant calculations.

[0046] Preferably, step S4 comprises the following steps:

[0047] Step S41: using a regional electric vehicle charging prediction model to predict the regional electric vehicle charging, thereby obtaining regional electric vehicle charging parameters;

[0048] Step S42: dividing the charging pile distribution map data and the charging pile usage history data by time dimension, thereby obtaining time dimension division data;

[0049] Step S43: performing spatial hot spot analysis on the charging pile distribution map data and the charging pile usage history data according to the time dimension division data, so as to obtain a time dimension charging hot spot map;

[0050] Step S44: Calculate the user's expected charging demand using the charging demand expected value calculation formula according to the regional electric vehicle stop charging parameters and the time dimension charging heat map, thereby obtaining the user's expected charging demand value.

[0051] Through accurate prediction, the present invention can reasonably allocate charging pile resources in the region, avoid overcrowding or waste of resources, and improve the utilization efficiency of charging piles; the prediction model can understand the possibility of electric vehicles stopping for charging in advance, thereby providing users with more intelligent and personalized charging services, reducing user waiting time, and improving charging experience; the prediction model helps to plan charging pile maintenance plans, reduce unnecessary maintenance and operating costs, and improve the overall operating efficiency of charging piles. Time dimension division helps to deeply understand the characteristics of charging demand in different time periods, such as peak hours and trough hours, and provide more accurate time information for subsequent analysis; time dimension division provides a time basis for subsequent spatial hot spot analysis, making the distribution of charging demand more comprehensive; time dimension division enables the model to better capture the temporal change law and improve the prediction accuracy of charging demand. Spatial hot spot analysis helps to identify areas where charging demand is more concentrated in different time periods, providing an important reference for resource allocation; by understanding the hot spot distribution of charging demand, the layout of charging piles can be optimized, the coverage of charging services can be improved, and the diverse charging needs of users can be met; the time dimension charging hot spot map is a key factor in calculating user expectations, providing users with more expected charging services. The expected value calculation quantifies the user's charging needs and provides a clear goal for subsequent matching and push. The calculation of the expected value of charging demand helps to formulate a personalized charging pile push strategy and improve user satisfaction with charging services. The expected value of charging demand is the basis of the push strategy. Through accurate understanding of user needs, charging pile information that meets user expectations can be pushed more accurately.

[0052] Preferably, in step S44, the user's expected charging demand value is calculated, wherein the user's expected charging demand value calculation formula is specifically:

[0053]

[0054] Where D is the expected value of the electric vehicle's charging demand, n is the total number of charging piles in the area, F is the capacity factor of the charging pile, L is the frequency of the charging pile being used, C is the power capacity of the charging pile, P is the distance from the electric vehicle to the nearest charging pile, S is the characteristic value of the parking area, and H is the distribution value of charging hotspots in different time periods in the area.

[0055] The present invention constructs a user charging demand expected value calculation formula for calculating the user charging demand expected value according to the regional electric vehicle charging parameters and the time dimension charging heat map; for the formula In the part, a larger F value means that the charging pile has a higher capacity and a faster charging speed, and the charging demand of electric vehicles is met more quickly and efficiently; L reflects the utilization rate of the charging pile. When calculating the expected value of charging demand, high frequency of use will increase the demand value, taking into account the actual use of the charging pile; a larger C value means that the charging pile can accommodate more electricity to meet the charging needs of larger electric vehicles; a smaller P value will reduce the score, indicating that a closer charging pile is more likely to be selected, which improves the convenience of charging; the sin(n)·log2(1+S) part contains the characteristic value S of the parking lot, where sin(n) reflects the impact of the number of charging piles, and log2(1+S) reflects the impact of the characteristic value of the parking lot on demand. The product of these two items represents the impact of the parking lot, which increases the attention paid to the characteristics of the parking lot; The cube root of the distribution value of some charging hotspots corrects the impact of charging hotspots on the expected value of demand, making it more reasonable to affect the overall demand. In the first part, 2·F·C represents twice the product of the charging pile capacity factor and the power capacity, taking into account the total charging capacity of the charging pile; P is the same as the first part, reflecting the distance between the electric vehicle and the nearest charging pile; cos(n) reflects the impact of the number of charging piles on demand, and the multiplication term of cos(n) takes into account the impact of the number of charging piles, making the demand more comprehensively affected by the number of charging piles; Same as the first part, indicating the utilization rate of charging piles.

[0056] Preferably, step S5 comprises the following steps:

[0057] Step S51: when the user's expected charging demand value is greater than or equal to the preset standard user's expected charging demand value, the area where the user is located is marked, thereby obtaining the area data of the charging pile to be matched;

[0058] Step S52: Matching the charging pile area data to be matched and the charging habit data of the regional users with the charging needs of the regional users, thereby obtaining the charging pile area data to be pushed;

[0059] Step S53: Push charging data of users in a specific area based on the charging pile area distribution data to be pushed, so as to realize the charging pile data push work.

[0060] The present invention can determine which areas of users have higher charging needs by comparing the expected value of user charging needs with preset standards. The labeling process enables the system to more accurately identify important areas and improves the pertinence of subsequent charging pile pushes; when the expected value of user charging needs is greater than or equal to the preset standard user charging demand expected value, the area where the user is located is labeled and the area is marked as a high charging demand area. By matching the charging pile area data to be matched with the regional user charging habit data, the system can better understand the user's charging needs in a specific area and improve the accuracy of the push; the regional user charging needs are matched using the charging pile area data to be matched and the regional user charging habit data; this matching process takes into account the user's preferences and historical charging behavior factors. According to the charging pile area distribution data, the successfully matched areas are accurately pushed to meet the personalized charging needs of users in specific areas; the successfully matched charging pile area data to be pushed is filtered according to the charging pile area distribution data, and is only pushed to the high charging demand area to ensure that the pushed charging pile data is more in line with user expectations.

[0061] Preferably, the present invention also provides a charging pile data push system, comprising:

[0062] The charging pile usage history data extraction module is used to obtain urban geographic traffic data; use urban geographic traffic data to perform charging pile regional distribution analysis, thereby obtaining charging pile regional distribution data; extract charging pile usage history data based on charging pile regional distribution data, thereby obtaining charging pile usage history data.

[0063] The user charging habit mining module is used to extract the charging pile usage preference features from the charging pile usage history data according to the charging pile regional distribution data, thereby obtaining the charging pile usage preference feature data; the user charging habit mining is performed on the charging pile usage preference feature data, thereby obtaining the regional user charging habit data;

[0064] The regional charging pile associated weight factor extraction module is used to extract the characteristics of electric vehicle stop points by using urban geographic traffic data, so as to obtain the characteristic data of electric vehicle stop time; extract the regional charging pile associated weight factors according to the charging pile distribution map data, so as to obtain the regional charging pile associated weight factors; construct a regional stop electric vehicle charging prediction model based on the regional charging pile associated weight factors, so as to obtain the regional stop electric vehicle charging prediction model;

[0065] A user charging demand expected value calculation module is used to predict the regional electric vehicle stop charging by using the regional electric vehicle stop charging prediction model, thereby obtaining the regional electric vehicle stop charging parameters; and calculate the user charging demand expected value according to the regional electric vehicle stop charging parameters, thereby obtaining the user charging demand expected value;

[0066] The module for pushing charging data for users in a specific area is used to make an expected value judgment based on the expected value of the user's charging demand, so as to obtain the regional data of the charging piles to be matched; to match the regional data of the charging piles to be matched and the regional user's charging habit data, so as to obtain the regional data of the charging piles to be pushed; to push the charging data of users in a specific area to the regional data of the charging piles to be pushed based on the regional distribution data of the charging piles, so as to realize the charging pile data push work

[0067] By acquiring urban geographic traffic data, the present invention can fully understand the urban traffic conditions and provide a basis for the reasonable distribution of subsequent charging piles. The regional distribution analysis of charging piles can reveal the differences in charging demand in different regions, which is helpful to optimize the distribution of charging piles. The extraction of historical data on the use of charging piles provides an important basis for understanding user behavior, thereby laying a foundation for the subsequent construction of user behavior models; by extracting the characteristics of charging pile usage preferences, the user's use tendency of charging piles can be deeply understood, and the user portrait can be further refined. User charging habit mining helps to identify the charging characteristics of different user groups, provide a basis for personalized push, and improve service accuracy. The extraction of electric vehicle dwell time feature data helps to understand the driving mode of electric vehicles and provide time dimension support for predicting charging demand. The extraction of regional charging pile association weight factors can consider the correlation between charging piles and improve the accuracy of charging prediction. Constructing a regional stop electric vehicle charging prediction model helps to predict the charging demand in a certain area in advance, so as to better meet user expectations. Using the prediction model to predict the regional electric vehicle dwell charging can more accurately estimate the charging demand and provide a basis for charging pile data push. By calculating the expected value of user charging demand, the user's expectation for charging can be quantified, providing data support for subsequent personalized push. By making an expected value judgment based on the expected value of the user's charging demand, it is possible to more intelligently select the regional data of the charging pile to be matched, thereby improving the accuracy of the charging push. The regional user charging demand matching is combined with the user's charging habit data to match the most suitable charging pile for the user, thereby improving user satisfaction. Pushing charging data of users in a specific area helps to refine services and improve user experience. Therefore, the present invention provides a charging pile data push method and system, which pushes charging pile data to target users who may have charging needs without involving user privacy. This system not only meets the goal of charging pile data push, but also realizes highly personalized services under the premise of protecting user privacy. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1 A schematic diagram of the steps of a charging pile data push method;

[0069] Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart;

[0070] Figure 3 for Figure 2 Detailed implementation steps of step S22;

[0071] Figure 4 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0072] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0073] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. 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 technicians in this field without creative work are within the scope of protection of the present invention.

[0074] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0075] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0076] To achieve this, please refer to Figures 1 to 4 , a charging pile data push method, comprising the following steps:

[0077] Step S1: obtaining urban geographic traffic data; using the urban geographic traffic data to analyze the regional distribution of charging piles, thereby obtaining regional distribution data of charging piles; extracting charging pile usage history data based on the regional distribution data of charging piles, thereby obtaining historical usage data of charging piles;

[0078] Step S2: extracting the usage preference features of charging piles from the usage history data of charging piles according to the regional distribution data of charging piles, thereby obtaining the usage preference feature data of charging piles; mining the user charging habits of the usage preference feature data of charging piles, thereby obtaining the charging habit data of regional users;

[0079] Step S3: Extract the characteristics of electric vehicle stop points using urban geographic traffic data, thereby obtaining electric vehicle stop time characteristic data; extract regional charging pile associated weight factors based on charging pile distribution map data, thereby obtaining regional charging pile associated weight factors; construct a regional stop electric vehicle charging prediction model based on the regional charging pile associated weight factors, thereby obtaining a regional stop electric vehicle charging prediction model;

[0080] Step S4: using the regional electric vehicle charging prediction model to predict the regional electric vehicle charging, thereby obtaining the regional electric vehicle charging parameters; calculating the user charging demand expectation value according to the regional electric vehicle charging parameters, thereby obtaining the user charging demand expectation value;

[0081] Step S5: Make an expected value judgment based on the expected value of the user's charging demand, so as to obtain the regional data of the charging piles to be matched; match the regional user charging demand of the charging pile regional data to be matched and the regional user charging habit data, so as to obtain the regional data of the charging piles to be pushed; push the charging data of users in a specific area to the regional data of the charging piles to be pushed according to the regional distribution data of the charging piles, so as to realize the charging pile data push work.

[0082] By acquiring urban geographic traffic data, the present invention can fully understand the urban traffic conditions and provide a basis for the reasonable distribution of subsequent charging piles. The regional distribution analysis of charging piles can reveal the differences in charging demand in different regions, which is helpful to optimize the distribution of charging piles. The extraction of historical data on the use of charging piles provides an important basis for understanding user behavior, thereby laying a foundation for the subsequent construction of user behavior models; by extracting the characteristics of charging pile usage preferences, the user's use tendency of charging piles can be deeply understood, and the user portrait can be further refined. User charging habit mining helps to identify the charging characteristics of different user groups, provide a basis for personalized push, and improve service accuracy. The extraction of electric vehicle dwell time feature data helps to understand the driving mode of electric vehicles and provide time dimension support for predicting charging demand. The extraction of regional charging pile association weight factors can consider the correlation between charging piles and improve the accuracy of charging prediction. Constructing a regional stop electric vehicle charging prediction model helps to predict the charging demand in a certain area in advance, so as to better meet user expectations. Using the prediction model to predict the regional electric vehicle dwell charging can more accurately estimate the charging demand and provide a basis for charging pile data push. By calculating the expected value of user charging demand, the user's expectation for charging can be quantified, providing data support for subsequent personalized push. By making an expected value judgment based on the expected value of the user's charging demand, it is possible to more intelligently select the regional data of the charging pile to be matched, thereby improving the accuracy of the charging push. The regional user charging demand matching is combined with the user's charging habit data to match the most suitable charging pile for the user, thereby improving user satisfaction. Pushing charging data of users in a specific area helps to refine services and improve user experience. Therefore, the present invention provides a charging pile data push method and system, which pushes charging pile data to target users who may have charging needs without involving user privacy. This system not only meets the goal of charging pile data push, but also realizes highly personalized services under the premise of protecting user privacy.

[0083] In the embodiment of the present invention, reference Figure 1 The above is a schematic diagram of the steps of a charging pile data push method of the present invention. In this example, the charging pile data push method includes the following steps:

[0084] Step S1: obtaining urban geographic traffic data; using the urban geographic traffic data to analyze the regional distribution of charging piles, thereby obtaining regional distribution data of charging piles; extracting charging pile usage history data based on the regional distribution data of charging piles, thereby obtaining historical usage data of charging piles;

[0085] In an embodiment of the present invention, urban geographic traffic data is obtained through GIS, including information on road networks, intersections, traffic flow, and electric vehicles; based on the urban geographic traffic data, the traffic conditions in different areas are analyzed, and areas where charging piles exist are identified to form charging pile area distribution data; using the determined charging pile areas, information related to these areas is extracted from the charging pile usage history data, including the location of the charging piles, frequency of use, and charging power.

[0086] Step S2: extracting the usage preference features of charging piles from the usage history data of charging piles according to the regional distribution data of charging piles, thereby obtaining the usage preference feature data of charging piles; mining the user charging habits of the usage preference feature data of charging piles, thereby obtaining the charging habit data of regional users;

[0087] In an embodiment of the present invention, the regional distribution data of charging piles is used to extract features of the historical data on the use of charging piles, including the location features, usage frequency, and charging power of the charging piles. Based on the extracted characteristic data on the use preference of charging piles, data mining techniques, such as cluster analysis or association rule mining, are used to mine the charging habits of different users and form regional user charging habit data.

[0088] Step S3: Extract the characteristics of electric vehicle stop points using urban geographic traffic data, thereby obtaining electric vehicle stop time characteristic data; extract regional charging pile associated weight factors based on charging pile distribution map data, thereby obtaining regional charging pile associated weight factors; construct a regional stop electric vehicle charging prediction model based on the regional charging pile associated weight factors, thereby obtaining a regional stop electric vehicle charging prediction model;

[0089] In an embodiment of the present invention, the electric vehicle traffic standard data is processed using urban geographic standard data to extract the characteristics of the electric vehicle's dwell time and dwell location; based on the charging pile distribution map data, the correlation weight factors between charging piles in different regions are calculated to reflect the degree of correlation between the charging piles; based on the extracted electric vehicle dwell time characteristic data and the regional charging pile correlation weight factors, a regional dwelling electric vehicle charging prediction model is constructed.

[0090] Step S4: using the regional electric vehicle charging prediction model to predict the regional electric vehicle charging, thereby obtaining the regional electric vehicle charging parameters; calculating the user charging demand expectation value according to the regional electric vehicle charging parameters, thereby obtaining the user charging demand expectation value;

[0091] In an embodiment of the present invention, a constructed regional electric vehicle charging prediction model is used to predict the electric vehicle charging in each area, and the regional electric vehicle charging parameters are obtained; based on the regional electric vehicle charging parameters, the user's charging demand expectation value is calculated, taking into account the charging situation in the user's area.

[0092] Step S5: performing expected value judgment according to the expected value of the user's charging demand, thereby obtaining the regional data of the charging pile to be matched; performing regional user charging demand matching on the regional data of the charging pile to be matched and the regional user charging habit data, thereby obtaining the regional data of the charging pile to be pushed; and pushing the charging data of users in a specific area to the regional data of the charging pile to be pushed according to the regional distribution data of the charging piles, thereby realizing the charging pile data push work;

[0093] In an embodiment of the present invention, the expected value of the user's charging demand is judged to determine the user's expected level of charging, such as high, medium, or low; based on the expected value, the charging pile area data to be matched and the regional user charging habit data are matched to determine the charging pile area to be pushed; based on the charging pile area distribution data, the charging pile data in a specific area is pushed to the user to implement the charging pile data push work.

[0094] Preferably, step S1 comprises the following steps:

[0095] Step S11: obtaining urban geographic traffic data; performing data standardization on the urban geographic traffic data, thereby obtaining urban geographic traffic standard data, wherein the urban geographic traffic standard data includes urban geographic standard data and electric vehicle traffic standard data;

[0096] Step S12: Analyze the distribution of charging piles using the urban geographic standard data, so as to obtain the distribution map data of charging piles;

[0097] Step S13: Divide the charging pile distribution map data into regions and perform labeling processing to obtain charging pile regional distribution data;

[0098] Step S14: extracting charging pile usage history data according to the charging pile regional distribution data, thereby obtaining the charging pile usage history data.

[0099] By standardizing urban geographic traffic data, the present invention can process data from different sources and formats in a consistent manner, thereby improving the comparability and consistency of the data; by analyzing urban geographic standard data, it is possible to fully understand the spatial distribution of charging piles, discover potential areas of concentrated charging demand, and provide strong support for subsequent push strategies; by performing regional division and annotation processing on the charging pile distribution map data, a detailed portrayal of urban areas is achieved, which helps to accurately capture the charging demand characteristics in different areas; by extracting historical data on the charging pile regional distribution data, the usage of charging piles in each area is obtained, providing a key data basis for subsequent modeling.

[0100] In the embodiment of the present invention, the urban geographic traffic data including road network, intersection, traffic flow and electric vehicle information are obtained through GIS; the collected data are cleaned, missing values ​​and outliers are processed, and information from different data sources is integrated to ensure data consistency and integrity; data in different formats and units are standardized into a unified data format; information related to electric vehicles, such as road usage of electric vehicles and parking lot information, is extracted from the integrated urban geographic traffic data as needed. The standardized urban geographic traffic data is imported into an analysis tool, such as a geographic information system (GIS) or data analysis software; the location information of the charging pile is identified in combination with the electric vehicle traffic standard data for subsequent analysis; spatial analysis is performed using GIS technology to evaluate the distribution of charging piles in the urban space and identify possible hot spots; a charging pile distribution map is generated based on the analysis results to display the spatial distribution of charging piles in the city. The charging pile distribution map is divided into regions, and grid division can be used to form different regions; each region is labeled to record the characteristics, flow of people and commercial areas of the region to enrich the background information of the region; the data after regional division and labeling are integrated to form charging pile regional distribution data, including feature labels and corresponding information of each region. The regional distribution data of charging piles is associated with the historical data of charging pile usage to establish the relationship between the region and the use of charging piles; the historical data of charging pile usage, including the number of charging times, charging time, and user information, is extracted from the associated data to finally generate a data set containing the historical information of charging pile usage.

[0101] Preferably, step S2 comprises the following steps:

[0102] Step S21: performing spatial cluster analysis on the charging pile usage history data according to the charging pile regional distribution data, thereby obtaining the charging pile usage history spatial cluster data;

[0103] Step S22: extracting the charging pile usage preference features from the charging pile usage history data according to the charging pile usage history spatial cluster data, thereby obtaining the charging pile usage preference feature data, wherein the charging pile usage preference feature data includes user behavior time series feature data, usage frequency trend feature data, and power preference feature data;

[0104] Step S23: clustering the user behavior time series feature data by charging preference time period, thereby obtaining charging preference time period clustering data;

[0105] Step S24: performing temporal-spatial fusion on the historical spatial cluster data of charging pile usage and the cluster data of charging preference time periods, thereby obtaining spatiotemporal user charging preference data;

[0106] Step S25: using probability distribution analysis technology to perform user charging characteristic distribution analysis on the spatiotemporal user charging preference data, thereby obtaining user charging characteristic distribution data;

[0107] Step S26: Perform regional association rule mining on the user charging feature distribution data to obtain regional user charging habit data.

[0108] Through spatial cluster analysis, the present invention can cluster the charging pile usage history data according to geographical location and identify charging pile groups with similar usage characteristics in similar areas; it helps to better understand the spatial distribution pattern of charging piles and improve the spatial perception of regional charging needs. Extracting charging pile usage preference features from the charging pile usage history spatial cluster data, including user behavior time series features, usage frequency trend features and power preference features, helps to deeply understand the user's charging preferences in different areas and provide more accurate feature information for subsequent personalized push. Clustering the user behavior time series feature data into charging preference time periods helps to mine the user's charging preference time periods in different time periods; it enables us to understand the user's behavior patterns in more detail and further improve the time perception of user needs. Through time-series space fusion, the charging pile usage history spatial cluster data is combined with the charging preference time period cluster data to form spatiotemporal user charging preference data; it helps to capture the user's complex charging behavior patterns in the spatiotemporal dimension and provide more comprehensive user charging preference information. Using probability distribution analysis technology to analyze the spatiotemporal user charging preference data helps to deeply understand the probability distribution of user charging behavior; it provides statistical support for the formulation of subsequent push strategies and ensures the accuracy and rationality of push. By mining regional association rules of user charging feature distribution data, we can discover the association patterns of user charging habits between different regions; this helps to build a regional user charging habit model and provide a deeper understanding for the personalized design of push strategies.

[0109] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0110] Step S21: performing spatial cluster analysis on the charging pile usage history data according to the charging pile regional distribution data, thereby obtaining the charging pile usage history spatial cluster data;

[0111] In the embodiment of the present invention, the charging piles are grouped using the regional distribution data of the charging piles using a spatial clustering algorithm (such as K-means) to form the charging pile usage history spatial cluster data.

[0112] Step S22: extracting the charging pile usage preference features from the charging pile usage history data according to the charging pile usage history spatial cluster data, thereby obtaining the charging pile usage preference feature data, wherein the charging pile usage preference feature data includes user behavior time series feature data, usage frequency trend feature data, and power preference feature data;

[0113] In the embodiment of the present invention, based on the historical spatial cluster data of charging pile usage, user behavior time series feature data, usage frequency trend feature data and power preference feature data are extracted.

[0114] Step S23: clustering the user behavior time series feature data by charging preference time period, thereby obtaining charging preference time period clustering data;

[0115] In the embodiment of the present invention, a time series clustering algorithm (such as DBSCAN) is used to cluster the charging preference time periods for the user behavior time series feature data to obtain charging preference time period clustering data.

[0116] Step S24: performing temporal-spatial fusion on the historical spatial cluster data of charging pile usage and the cluster data of charging preference time periods, thereby obtaining spatiotemporal user charging preference data;

[0117] In the embodiment of the present invention, the historical spatial cluster data of charging pile usage and the charging preference time period cluster data are fused in time series and space to establish the spatiotemporal user charging preference data.

[0118] Step S25: using probability distribution analysis technology to perform user charging characteristic distribution analysis on the spatiotemporal user charging preference data, thereby obtaining user charging characteristic distribution data;

[0119] In the embodiment of the present invention, probability distribution analysis technology is used to perform statistical analysis on spatiotemporal user charging preference data to obtain user charging feature distribution data.

[0120] Step S26: performing regional association rule mining on the user charging feature distribution data to obtain regional user charging habit data;

[0121] In the embodiment of the present invention, regional association rule mining is performed on user charging feature distribution data to find out association rules between different regions, so as to obtain regional user charging habit data.

[0122] Preferably, step S22 includes the following steps:

[0123] Step S221: extracting user behavior time series features from the charging pile usage history data according to the charging pile usage history spatial cluster data, thereby obtaining user behavior time series feature data;

[0124] Step S222: performing a charging pile usage frequency analysis on the charging pile usage history data according to the charging pile usage history spatial cluster data, thereby obtaining usage frequency trend feature data;

[0125] Step S223: collecting charging pile power from the charging pile usage history data according to the charging pile usage history spatial cluster data, thereby obtaining charging pile power data;

[0126] Step S224: Utilize the user behavior time series feature data to perform time period power preference analysis on the charging pile power data and perform power charging duration analysis, thereby obtaining power preference feature data.

[0127] Through spatial cluster analysis, the present invention can cluster the charging pile usage history data according to geographical location and identify charging pile groups with similar usage characteristics in similar areas; it helps to better understand the spatial distribution pattern of charging piles and improve the spatial perception of regional charging needs. Extracting charging pile usage preference features from the charging pile usage history spatial cluster data, including user behavior time series features, usage frequency trend features and power preference features, helps to deeply understand the user's charging preferences in different areas and provide more accurate feature information for subsequent personalized push. Clustering the user behavior time series feature data into charging preference time periods helps to mine the user's charging preference time periods in different time periods; it enables us to understand the user's behavior patterns in more detail and further improve the time perception of user needs. Through time-series space fusion, the charging pile usage history spatial cluster data is combined with the charging preference time period cluster data to form spatiotemporal user charging preference data; it helps to capture the user's complex charging behavior patterns in the spatiotemporal dimension and provide more comprehensive user charging preference information. Using probability distribution analysis technology to analyze the spatiotemporal user charging preference data helps to deeply understand the probability distribution of user charging behavior; it provides statistical support for the formulation of subsequent push strategies and ensures the accuracy and rationality of push. By mining regional association rules of user charging feature distribution data, we can discover the association patterns of user charging habits between different regions; this helps to build a regional user charging habit model and provide a deeper understanding for the personalized design of push strategies.

[0128] As an example of the present invention, refer to Figure 3 As shown, in this example, step S22 includes:

[0129] Step S221: extracting user behavior time series features from the charging pile usage history data according to the charging pile usage history spatial cluster data, thereby obtaining user behavior time series feature data;

[0130] In an embodiment of the present invention, historical data on the use of a charging pile is obtained, including information on a user ID, a charging start time, and a charging end time; time series features are extracted for the charging behavior of each user using the charging pile, such as the usage time period, charging duration, and number of charging times; a time series analysis method is used, such as extracting the user's daily and weekly charging behavior features; a clustering algorithm is used to divide the user's behavior time series features into spatial clusters, and users with similar charging behaviors are aggregated together to form spatial clusters; and the time series features of the users in each spatial cluster are summarized to form user behavior time series feature data.

[0131] Step S222: performing a charging pile usage frequency analysis on the charging pile usage history data according to the charging pile usage history spatial cluster data, thereby obtaining usage frequency trend feature data;

[0132] In an embodiment of the present invention, the charging pile usage history data is used to extract the charging pile ID and charging start time information; the usage frequency of the charging piles is analyzed by using statistical methods, such as calculating the average usage times and peak usage times of each charging pile; the charging piles are clustered according to the usage frequency to form spatial clusters, and the charging piles with similar usage frequencies are divided into the same cluster; the usage frequency trend characteristics of the charging piles in each spatial cluster are summarized to form usage frequency trend characteristic data.

[0133] Step S223: collecting charging pile power from the charging pile usage history data according to the charging pile usage history spatial cluster data, thereby obtaining charging pile power data;

[0134] In an embodiment of the present invention, the charging pile usage history data is used to extract the charging pile ID, charging start time, charging end time, and power information; the power of each charging pile is collected to calculate the average power and peak power; the charging piles are clustered according to the power to form a spatial cluster, and the charging piles with similar power characteristics are divided into the same cluster; the power characteristics of the charging piles in each spatial cluster are summarized to form charging pile power data.

[0135] Step S224: using the user behavior time series feature data to perform time period power preference analysis on the charging pile power data and power charging duration analysis, thereby obtaining power preference feature data;

[0136] In an embodiment of the present invention, user behavior time series feature data and charging pile power data are utilized; the power preferences of users in different time periods, such as daytime, nighttime, and peak hours, are analyzed; the power of the charging piles is analyzed for duration, and the charging duration distribution of users at different powers is calculated; the power preference characteristics of users in each spatial cluster are summarized to form power preference feature data.

[0137] Preferably, step S3 comprises the following steps:

[0138] Step S31: using the urban geographic standard data to spatially align and map the electric vehicle traffic standard data, thereby obtaining the electric vehicle traffic spatial alignment data;

[0139] Step S32: performing spatial regional division on the electric vehicle traffic spatial alignment data, thereby obtaining regional electric vehicle trajectory data; performing spatial trajectory density analysis on the regional electric vehicle trajectory data, thereby obtaining a spatial trajectory density heat map;

[0140] Step S33: extracting electric vehicle stop points from the regional electric vehicle trajectory data, thereby obtaining electric vehicle stop point data; extracting electric vehicle stop time features from the electric vehicle stop point data, thereby obtaining electric vehicle stop time feature data;

[0141] Step S34: extracting regional charging pile associated weight factors according to the charging pile distribution map data, thereby obtaining regional charging pile associated weight factors, wherein the regional charging pile associated weight factors include regional charging pile high weight associated factors, regional charging pile medium weight associated factors, and regional charging pile low weight associated factors;

[0142] Step S35: constructing a regional stopover electric vehicle charging prediction model based on the electric vehicle dwell time characteristic data, the spatial trajectory density heat map, and the regional charging pile associated weight factors, thereby obtaining a regional stopover electric vehicle charging prediction model.

[0143] The present invention obtains the accurate position of electric vehicle traffic data on the urban geographic standard through spatial alignment and mapping of urban geographic standard data, ensuring the accuracy and credibility of subsequent analysis; uses electric vehicle traffic spatial alignment data to perform spatial regional division and generate regional electric vehicle trajectory data; makes the analysis of electric vehicle driving trajectory more targeted, and can more accurately understand the movement characteristics of electric vehicles in different regions. Spatial trajectory density analysis generates a spatial trajectory density heat map, which provides an intuitive understanding of the hot spot distribution of electric vehicle traffic in different areas of the city, and provides visualization support for the subsequent extraction of electric vehicle stop points. By extracting electric vehicle stop points from regional electric vehicle trajectory data, the stop point information of electric vehicles in different areas of the city is obtained. Extracting the characteristics of electric vehicle stay time helps to deeply understand the stop behavior of electric vehicles in different locations, and provides key features for the subsequent prediction model construction. According to the charging pile distribution map data, the regional charging pile association weight factor is extracted, including high, medium and low weight association factors. This step provides a detailed regulation of the correlation of regional charging piles for the electric vehicle stop charging prediction model, and more comprehensively considers the importance of charging piles in different regions. Based on the electric vehicle stop time feature data, the spatial trajectory density heat map and the regional charging pile association weight factor, a regional stop electric vehicle charging prediction model is constructed. This model comprehensively considers the parking behavior of electric vehicles, regional traffic hotspots and the associated weights of charging piles, improving the accurate prediction of the charging demand of electric vehicles parked in the region.

[0144] As an example of the present invention, refer to Figure 4 As shown, in this example, step S3 includes:

[0145] Step S31: using the urban geographic standard data to spatially align and map the electric vehicle traffic standard data, thereby obtaining the electric vehicle traffic spatial alignment data;

[0146] In an embodiment of the present invention, the coordinate system of geographic standard data is used to spatially align the electric vehicle traffic data to ensure that the two have the same coordinate system and reference; GIS tools are used to map the electric vehicle traffic data to the city's geographic standard data to ensure the accuracy of the spatial position.

[0147] Step S32: performing spatial regional division on the electric vehicle traffic spatial alignment data, thereby obtaining regional electric vehicle trajectory data; performing spatial trajectory density analysis on the regional electric vehicle trajectory data, thereby obtaining a spatial trajectory density heat map;

[0148] In an embodiment of the present invention, the mapped electric vehicle traffic data is divided into spatial regions, such as industrial and commercial facilities regions; a geographic information system (GIS) tool is used to perform density analysis on the electric vehicle trajectory data in the region to generate a spatial trajectory density heat map.

[0149] Step S33: extracting electric vehicle stop points from the regional electric vehicle trajectory data, thereby obtaining electric vehicle stop point data; extracting electric vehicle stop time features from the electric vehicle stop point data, thereby obtaining electric vehicle stop time feature data;

[0150] In the embodiment of the present invention, trajectory data is used to detect the stop points of the electric vehicle through an algorithm, and the positions of the stop points are marked; the stop time of each stop point is calculated, and the time characteristics of the stop points, such as the average stop time and the longest stop time, are extracted.

[0151] Step S34: extracting regional charging pile associated weight factors according to the charging pile distribution map data, thereby obtaining regional charging pile associated weight factors, wherein the regional charging pile associated weight factors include regional charging pile high weight associated factors, regional charging pile medium weight associated factors, and regional charging pile low weight associated factors;

[0152] In the embodiment of the present invention, according to the location of the electric vehicle stop point and the distribution of the charging piles, the regional charging pile association weight factors are calculated, including high-weight, medium-weight and low-weight association factors.

[0153] Step S35: construct a regional stopover electric vehicle charging prediction model based on the electric vehicle dwell time characteristic data, the spatial trajectory density heat map, and the regional charging pile associated weight factor, thereby obtaining a regional stopover electric vehicle charging prediction model

[0154] In an embodiment of the present invention, the electric vehicle dwell time characteristic data, the spatial trajectory density heat map, and the regional charging pile associated weight factors are integrated into a training data set; based on the training data set, a regional dwelling electric vehicle charging prediction model is constructed using a machine learning or statistical modeling method, taking into account the dwell time, trajectory density, and charging pile associated weight factors; the constructed model is verified and adjusted to ensure its accuracy and generalization on actual data.

[0155] Preferably, step S34 includes the following steps:

[0156] Step S341: collecting surrounding environment characteristics according to the charging pile distribution map data, thereby obtaining surrounding environment characteristic data; performing regional and charging pile data analysis according to the surrounding environment characteristic data, thereby obtaining regional and charging pile data;

[0157] Step S342: Calculate the distance between the area and the charging pile data, thereby obtaining the distance data between the charging piles; calculate the density of commercial facilities and perform workplace analysis on the area and the charging pile data, thereby obtaining the industrial and commercial distribution density value;

[0158] Step S343: when the distance value corresponding to the charging pile distance data is less than the preset charging pile standard distance value and the industrial and commercial distribution density value is greater than the preset industrial and commercial distribution standard density value, a high weight is assigned to the area and the charging pile data, thereby obtaining a high weight association factor of the regional charging pile;

[0159] Step S344: when the distance value corresponding to the charging pile distance data is less than the preset charging pile standard distance value and the industrial and commercial distribution density value is less than or equal to the preset industrial and commercial distribution standard density value, the charging pile distance data is weighted, thereby obtaining the weight association factor of the regional charging pile;

[0160] Step S345: When the distance value corresponding to the charging pile distance data is greater than or equal to the preset charging pile standard distance value and the industrial and commercial distribution density value is greater than the preset industrial and commercial distribution standard density value, a low weight is assigned to the area and the charging pile data, thereby obtaining a low weight association factor of the regional charging pile;

[0161] Step S346: When the distance value corresponding to the charging pile distance data is greater than or equal to the preset charging pile standard distance value and the industrial and commercial distribution density value is less than or equal to the preset industrial and commercial distribution standard density value, the area and the charging pile data are removed.

[0162] The present invention can more comprehensively understand the environmental conditions of the area where the charging piles are located by collecting surrounding environmental characteristic data, such as traffic flow, crowd density, commercial facility distribution, etc., combined with the charging pile distribution map data; it is helpful to identify potential factors affecting charging demand and improve the prediction accuracy of the model. The charging pile distance data is obtained through the distance calculation algorithm, and combined with the commercial facility density calculation and workplace analysis, the spatial distribution of the charging piles in the area can be evaluated. This helps to identify the coverage of the charging piles and the surrounding commercial prosperity, and provides data support for the subsequent calculation of the correlation factor. When the charging pile distance is less than the preset standard value and the commercial facility density is greater than the preset standard value, the area is given a high-weight correlation factor with the charging pile data; it helps to emphasize the commercial prosperous area within the coverage of the charging pile, the density of the electric vehicles staying is high, and the parking time is relatively long, so the probability of having a charging demand is high. When the charging pile distance is less than the preset standard value but the commercial facility density is less than or equal to the preset standard value, the charging pile distance data is given a weight; it helps to balance the areas with low commercial prosperity within the distribution range of the charging piles, the density of electric vehicles is low, and there are fewer users with charging needs in the area, so as to maintain a certain degree of attention to the area. When the distance to the charging pile is greater than or equal to the preset standard value and the density of commercial facilities is greater than the preset standard value, a low-weight association factor is assigned to the area and the charging pile data; this helps identify areas where charging piles are distributed around commercial bustling areas but are far away, reducing the emphasis on charging demand in this area. When the distance to the charging pile is greater than or equal to the preset standard value and the density of commercial facilities is less than or equal to the preset standard value, the area and the charging pile data are removed. This helps reduce the focus on areas with low commercial bustling and long distances, improves the simplicity of the model, and reduces redundant calculations.

[0163] In the embodiment of the present invention, the charging pile distribution map data is used to collect the surrounding environment characteristics, including but not limited to the information of commercial facilities, workplaces, and public facilities; the collected surrounding environment characteristic data is combined with the charging pile distribution data for analysis; the distribution of charging piles in the area and the density of surrounding electric vehicles and the data and distribution of parked electric vehicles can be obtained through data visualization, statistical analysis and other methods. The distance between each charging pile and the surrounding area is calculated using the area and charging pile data; a geographic information system (GIS) or mathematical calculation method can be used to ensure accurate calculation of the distance; the commercial facility density is calculated for the area and charging pile data, taking into account the number and distribution of commercial facilities; workplace analysis is performed to examine the situation of workplaces in the area to understand the impact of workplace distribution on charging demand.

[0164] The standard distance value of charging piles and the standard density value of industrial and commercial distribution are preset, which may be based on previous data analysis or professional knowledge. For each area and charging pile data, the distance value and industrial and commercial distribution density value corresponding to the charging pile distance data are calculated; and the relationship between the distance value and the density value and the preset value is compared. If the distance value corresponding to the charging pile distance data is less than the preset charging pile standard distance value and the industrial and commercial distribution density value is greater than the preset industrial and commercial distribution standard density value, the correlation factor between the area and the charging pile data is assigned a high weight value; for example, the value is assigned to 0.8, indicating that the area has a high correlation with the charging pile. If the distance value corresponding to the charging pile distance data is less than the preset charging pile standard distance value and the industrial and commercial distribution density value is less than or equal to the preset industrial and commercial distribution standard density value, the correlation factor between the area and the charging pile data is assigned a medium weight value; for example, the value is assigned to 0.5, indicating that the area has a medium correlation with the charging pile. If the distance value corresponding to the charging pile distance data is greater than or equal to the preset charging pile standard distance value and the industrial and commercial distribution density value is greater than the preset industrial and commercial distribution standard density value, the correlation factor between the area and the charging pile data is assigned a low weight value; for example, the value is assigned to 0.2, indicating that the area has a low correlation with the charging pile. For areas and charging pile data that do not meet the above conditions, they can be eliminated to avoid adverse effects on subsequent analysis and recommendations.

[0165] Preferably, step S4 comprises the following steps:

[0166] Step S41: using a regional electric vehicle charging prediction model to predict the regional electric vehicle charging, thereby obtaining regional electric vehicle charging parameters;

[0167] Step S42: dividing the charging pile distribution map data and the charging pile usage history data by time dimension, thereby obtaining time dimension division data;

[0168] Step S43: performing spatial hot spot analysis on the charging pile distribution map data and the charging pile usage history data according to the time dimension division data, so as to obtain a time dimension charging hot spot map;

[0169] Step S44: Calculate the expected value of user charging demand using the charging demand expected value calculation formula according to the regional electric vehicle stop charging parameters and the time dimension charging heat map, so as to obtain the user's expected value of charging demand.

[0170] Through accurate prediction, the present invention can reasonably allocate charging pile resources in the region, avoid overcrowding or waste of resources, and improve the utilization efficiency of charging piles; the prediction model can understand the possibility of electric vehicles stopping for charging in advance, thereby providing users with more intelligent and personalized charging services, reducing user waiting time and improving charging experience; the prediction model is helpful for charging pile maintenance planning, reducing unnecessary maintenance and operating costs, and improving the overall operating efficiency of charging piles. Time dimension division helps to deeply understand the characteristics of charging demand in different time periods, such as peak hours and valley hours, and provide more accurate time information for subsequent analysis; time dimension division provides a time basis for subsequent spatial hot spot analysis, making the distribution of charging demand more comprehensive; time dimension division enables the model to better capture the temporal change law and improve the prediction accuracy of charging demand. Spatial hot spot analysis helps to identify areas where charging demand is more concentrated in different time periods, providing an important reference for resource allocation; by understanding the hot spot distribution of charging demand, the layout of charging piles can be optimized, the coverage of charging services can be improved, and the diverse charging needs of users can be met; the time dimension charging hot spot map is a key factor in calculating user expectations, providing users with more expected charging services. The expected value calculation quantifies the user's charging needs and provides a clear goal for subsequent matching and push. The calculation of the expected value of charging demand helps to formulate a personalized charging pile push strategy and improve user satisfaction with charging services. The expected value of charging demand is the basis of the push strategy. Through accurate understanding of user needs, charging pile information that meets user expectations can be pushed more accurately.

[0171] In an embodiment of the present invention, the electric vehicle parking charging data in the region is collected, including information on the parking time and charging power; a regional electric vehicle parking charging prediction model is established using machine learning or statistical methods, and the model should consider factors such as time, space, and charging pile distribution to accurately predict the parking and charging conditions of electric vehicles in a specific area; the model is trained using historical data, and the parameters are adjusted to improve the prediction accuracy; the model is evaluated using a validation set to ensure the generalization performance of the model on future data. The charging pile distribution map data and the charging pile usage history data are divided according to the time dimension, such as by hour or day; the data of each time dimension is preprocessed, including removing outliers and filling missing values ​​to ensure the accuracy of subsequent analysis. Using GIS technology and statistical methods, a spatial hot spot analysis is performed on the divided charging pile data to identify charging hot spot areas in different time dimensions; a time dimension charging hot spot map is generated based on the analysis results to reflect the spatiotemporal distribution of electric vehicle charging activities in the region. The established regional electric vehicle parking and charging prediction model is used to predict the parking and charging parameters of electric vehicles in the region, including the parking time and charging power. The charging hotspot map in the time dimension is combined to obtain the distribution of charging hotspots in the corresponding time period. The charging demand expected value calculation formula is used to combine the prediction parameters and the charging hotspot map to calculate the user's expected charging demand in a specific time period.

[0172] Preferably, in step S44, the user's expected charging demand value is calculated, wherein the user's expected charging demand value calculation formula is specifically:

[0173]

[0174] Where D is the expected value of the electric vehicle's charging demand, n is the total number of charging piles in the area, F is the capacity factor of the charging pile, L is the frequency of the charging pile being used, C is the power capacity of the charging pile, P is the distance from the electric vehicle to the nearest charging pile, S is the characteristic value of the parking area, and H is the distribution value of charging hotspots in different time periods in the area.

[0175] The present invention constructs a user charging demand expected value calculation formula for calculating the user charging demand expected value according to the regional electric vehicle charging parameters and the time dimension charging heat map; for the formula In the part, a larger F value means that the charging pile has a higher capacity and a faster charging speed, and the charging demand of electric vehicles is met more quickly and efficiently; L reflects the utilization rate of the charging pile. When calculating the expected value of charging demand, high frequency of use will increase the demand value, taking into account the actual use of the charging pile; a larger C value means that the charging pile can accommodate more electricity to meet the charging needs of larger electric vehicles; a smaller P value will reduce the score, indicating that a closer charging pile is more likely to be selected, which improves the convenience of charging; the sin(n)·log2(1+S) part contains the characteristic value S of the parking lot, where sin(n) reflects the impact of the number of charging piles, and log2(1+S) reflects the impact of the characteristic value of the parking lot on demand. The product of these two items represents the impact of the parking lot, which increases the attention paid to the characteristics of the parking lot; The cube root of the distribution value of some charging hotspots corrects the impact of charging hotspots on the expected value of demand, making it more reasonable to affect the overall demand. In the first part, 2·F·C represents twice the product of the charging pile capacity factor and the power capacity, taking into account the total charging capacity of the charging pile; P is the same as the first part, reflecting the distance between the electric vehicle and the nearest charging pile; cos(n) reflects the impact of the number of charging piles on demand, and the multiplication term of cos(n) takes into account the impact of the number of charging piles, making the demand more comprehensively affected by the number of charging piles; Same as the first part, indicating the utilization rate of charging piles.

[0176] Preferably, step S5 comprises the following steps:

[0177] Step S51: when the user's expected charging demand value is greater than or equal to the preset standard user's expected charging demand value, the area where the user is located is marked, thereby obtaining the area data of the charging pile to be matched;

[0178] Step S52: Matching the charging pile area data to be matched and the charging habit data of the regional users with the charging needs of the regional users, thereby obtaining the charging pile area data to be pushed;

[0179] Step S53: Push charging data of users in a specific area based on the charging pile area distribution data to be pushed, so as to realize the charging pile data push work.

[0180] The present invention can determine which areas of users have higher charging needs by comparing the expected value of user charging needs with preset standards. The labeling process enables the system to more accurately identify important areas and improves the pertinence of subsequent charging pile pushes; when the expected value of user charging needs is greater than or equal to the preset standard user charging demand expected value, the area where the user is located is labeled and the area is marked as a high charging demand area. By matching the charging pile area data to be matched with the regional user charging habit data, the system can better understand the user's charging needs in a specific area and improve the accuracy of the push; the regional user charging needs are matched using the charging pile area data to be matched and the regional user charging habit data; this matching process takes into account the user's preferences and historical charging behavior factors. According to the charging pile area distribution data, the successfully matched areas are accurately pushed to meet the personalized charging needs of users in specific areas; the successfully matched charging pile area data to be pushed is filtered according to the charging pile area distribution data, and is only pushed to the high charging demand area to ensure that the pushed charging pile data is more in line with user expectations.

[0181] In the embodiment of the present invention, according to the formula in step S44, the user's expected charging demand value (represented by the symbol D) is calculated; the calculated user's expected charging demand value is compared with the preset standard user's expected charging demand value; if D is greater than or equal to the preset standard value, it means that the user has a higher charging demand, and the next step is executed; otherwise, the processing is terminated. The area where the user is located is marked and the area is marked as the charging pile area to be matched; the area marking can use map coordinates or other identification methods to facilitate subsequent matching work. Using the information of the area marking, the data of the charging pile area to be matched is obtained; using the regional user charging habit data obtained in step S2; combining the user's expected charging demand value, the regional charging pile data and the user's charging habits, a complex matching algorithm is executed to determine the charging pile area that best suits the user's needs. According to the matching result in step S52, the charging pile area data to be pushed is obtained; using the charging pile area distribution data, the charging pile information in the matching result is pushed to the specific area where the user is located; the push method can use APP notification, SMS reminder, etc. to ensure that the user is aware of the charging pile information that meets his needs in a timely manner.

[0182] Preferably, the present invention also provides a charging pile data push system, comprising:

[0183] The charging pile usage history data extraction module is used to obtain urban geographic traffic data; use urban geographic traffic data to perform charging pile regional distribution analysis, thereby obtaining charging pile regional distribution data; extract charging pile usage history data based on charging pile regional distribution data, thereby obtaining charging pile usage history data.

[0184] The user charging habit mining module is used to extract the charging pile usage preference features from the charging pile usage history data according to the charging pile regional distribution data, thereby obtaining the charging pile usage preference feature data; the user charging habit mining is performed on the charging pile usage preference feature data, thereby obtaining the regional user charging habit data;

[0185] The regional charging pile associated weight factor extraction module is used to extract the characteristics of electric vehicle stop points by using urban geographic traffic data, so as to obtain the characteristic data of electric vehicle stop time; extract the regional charging pile associated weight factors according to the charging pile distribution map data, so as to obtain the regional charging pile associated weight factors; construct a regional stop electric vehicle charging prediction model based on the regional charging pile associated weight factors, so as to obtain the regional stop electric vehicle charging prediction model;

[0186] A user charging demand expected value calculation module is used to predict the regional electric vehicle stop charging by using the regional electric vehicle stop charging prediction model, thereby obtaining the regional electric vehicle stop charging parameters; and calculate the user charging demand expected value according to the regional electric vehicle stop charging parameters, thereby obtaining the user charging demand expected value;

[0187] The module for pushing charging data for users in a specific area is used to make an expected value judgment based on the expected value of the user's charging demand, so as to obtain the regional data of the charging piles to be matched; to match the regional data of the charging piles to be matched and the regional user's charging habit data, so as to obtain the regional data of the charging piles to be pushed; to push the charging data of users in a specific area to the regional data of the charging piles to be pushed based on the regional distribution data of the charging piles, so as to realize the charging pile data push work

[0188] By acquiring urban geographic traffic data, the present invention can fully understand the urban traffic conditions and provide a basis for the reasonable distribution of subsequent charging piles. The regional distribution analysis of charging piles can reveal the differences in charging demand in different regions, which is helpful to optimize the distribution of charging piles. The extraction of historical data on the use of charging piles provides an important basis for understanding user behavior, thereby laying a foundation for the subsequent construction of user behavior models; by extracting the characteristics of charging pile usage preferences, the user's use tendency of charging piles can be deeply understood, and the user portrait can be further refined. User charging habit mining helps to identify the charging characteristics of different user groups, provide a basis for personalized push, and improve service accuracy. The extraction of electric vehicle dwell time feature data helps to understand the driving mode of electric vehicles and provide time dimension support for predicting charging demand. The extraction of regional charging pile association weight factors can consider the correlation between charging piles and improve the accuracy of charging prediction. Constructing a regional stop electric vehicle charging prediction model helps to predict the charging demand in a certain area in advance, so as to better meet user expectations. Using the prediction model to predict the regional electric vehicle dwell charging can more accurately estimate the charging demand and provide a basis for charging pile data push. By calculating the expected value of user charging demand, the user's expectation for charging can be quantified, providing data support for subsequent personalized push. By making an expected value judgment based on the expected value of the user's charging demand, it is possible to more intelligently select the regional data of the charging pile to be matched, thereby improving the accuracy of the charging push. The regional user charging demand matching is combined with the user's charging habit data to match the most suitable charging pile for the user, thereby improving user satisfaction. Pushing charging data of users in a specific area helps to refine services and improve user experience. Therefore, the present invention provides a charging pile data push method and system, which pushes charging pile data to target users who may have charging needs without involving user privacy. This system not only meets the goal of charging pile data push, but also realizes highly personalized services under the premise of protecting user privacy.

[0189] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0190] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A charging pile data push method, characterized in that: The following steps are involved: Step S1: obtaining urban geographic traffic data; using the urban geographic traffic data to analyze the regional distribution of charging piles, thereby obtaining regional distribution data of charging piles; Extract the historical data of charging pile usage according to the regional distribution data of charging piles, so as to obtain the historical data of charging pile usage; Step S2: extracting the usage preference features of charging piles from the usage history data of charging piles according to the regional distribution data of charging piles, thereby obtaining the usage preference feature data of charging piles; mining the user charging habits of the usage preference feature data of charging piles, thereby obtaining the charging habit data of regional users; Step S3: extracting the features of electric vehicle stop points using urban geographic traffic data, thereby obtaining electric vehicle stop time feature data; According to the charging pile distribution map data, the regional charging pile associated weight factor is extracted to obtain the regional charging pile associated weight factor; based on the regional charging pile associated weight factor, a regional stop electric vehicle charging prediction model is constructed to obtain the regional stop electric vehicle charging prediction model, wherein step S3 is specifically as follows: Step S31: using the urban geographic standard data to spatially align and map the electric vehicle traffic standard data, thereby obtaining the electric vehicle traffic spatial alignment data; Step S32: performing spatial regional division on the electric vehicle traffic spatial alignment data, thereby obtaining regional electric vehicle trajectory data; performing spatial trajectory density analysis on the regional electric vehicle trajectory data, thereby obtaining a spatial trajectory density heat map; Step S33: extracting electric vehicle stop points from the regional electric vehicle trajectory data, thereby obtaining electric vehicle stop point data; extracting electric vehicle stop time features from the electric vehicle stop point data, thereby obtaining electric vehicle stop time feature data; Step S34: extracting the regional charging pile associated weight factor according to the charging pile distribution map data, thereby obtaining the regional charging pile associated weight factor, wherein the regional charging pile associated weight factor includes a regional charging pile high weight associated factor, a regional charging pile medium weight associated factor, and a regional charging pile low weight associated factor, wherein step S34 is specifically as follows: Step S341: collecting surrounding environment characteristics according to the charging pile distribution map data, thereby obtaining surrounding environment characteristic data; performing regional and charging pile data analysis according to the surrounding environment characteristic data, thereby obtaining regional and charging pile data; Step S342: Calculate the distance between the area and the charging pile data, thereby obtaining the distance data between the charging piles; calculate the density of commercial facilities and perform workplace analysis on the area and the charging pile data, thereby obtaining the industrial and commercial distribution density value; Step S343: When the distance value corresponding to the charging pile distance data is less than the preset charging pile standard distance value and the industrial and commercial distribution density value is greater than the preset industrial and commercial distribution standard density value, a high weight is assigned to the region and the charging pile data, thereby obtaining a high weight association factor of the regional charging pile, wherein the association factor of the region and the charging pile data is assigned a high weight value, which is 0.8; Step S344: when the distance value corresponding to the charging pile distance data is less than the preset charging pile standard distance value and the industrial and commercial distribution density value is less than or equal to the preset industrial and commercial distribution standard density value, the charging pile distance data is assigned a medium weight, thereby obtaining a medium weight association factor of the regional charging pile, wherein the association factor between the region and the charging pile data is assigned a medium weight value of 0.5; Step S345: When the distance value corresponding to the charging pile distance data is greater than or equal to the preset charging pile standard distance value and the industrial and commercial distribution density value is greater than the preset industrial and commercial distribution standard density value, a low weight is assigned to the region and the charging pile data, thereby obtaining a low weight association factor of the regional charging pile, wherein the association factor of the region and the charging pile data is assigned a low weight value, which is 0.2; Step S346: When the distance value corresponding to the charging pile distance data is greater than or equal to the preset charging pile standard distance value and the industrial and commercial distribution density value is less than or equal to the preset industrial and commercial distribution standard density value, the area and the charging pile data are removed; Step S35: constructing a regional stopover electric vehicle charging prediction model based on the electric vehicle dwell time characteristic data, the spatial trajectory density heat map, and the regional charging pile associated weight factors, thereby obtaining a regional stopover electric vehicle charging prediction model; Step S4: using the regional electric vehicle charging prediction model to predict the regional electric vehicle charging, thereby obtaining the regional electric vehicle charging parameters; calculating the user charging demand expectation value according to the regional electric vehicle charging parameters, thereby obtaining the user charging demand expectation value; Step S5: performing expected value judgment according to the expected value of the user's charging demand, thereby obtaining the regional data of the charging pile to be matched; performing regional user charging demand matching on the regional data of the charging pile to be matched and the regional user's charging habit data, thereby obtaining the regional data of the charging pile to be pushed; According to the charging pile area distribution data, the charging pile area data to be pushed is used to push the charging data of users in a specific area, so as to realize the charging pile data push work.

2. The charging pile data push method according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: obtaining urban geographic traffic data; performing data standardization on the urban geographic traffic data, thereby obtaining urban geographic traffic standard data, wherein the urban geographic traffic standard data includes urban geographic standard data and electric vehicle traffic standard data; Step S12: Analyze the distribution of charging piles using the urban geographic standard data, so as to obtain the distribution map data of charging piles; Step S13: Divide the charging pile distribution map data into regions and perform labeling processing to obtain charging pile regional distribution data; Step S14: extracting charging pile usage history data according to the charging pile regional distribution data, thereby obtaining the charging pile usage history data.

3. The charging pile data push method according to claim 2, characterized in that: Step S2 includes the following steps: Step S21: performing spatial cluster analysis on the charging pile usage history data according to the charging pile regional distribution data, thereby obtaining the charging pile usage history spatial cluster data; Step S22: extracting the charging pile usage preference features from the charging pile usage history data according to the charging pile usage history spatial cluster data, thereby obtaining the charging pile usage preference feature data, wherein the charging pile usage preference feature data includes user behavior time series feature data, usage frequency trend feature data, and power preference feature data; Step S23: clustering the user behavior time series feature data by charging preference time period, thereby obtaining charging preference time period clustering data; Step S24: performing temporal-spatial fusion on the historical spatial cluster data of charging pile usage and the cluster data of charging preference time periods, thereby obtaining spatiotemporal user charging preference data; Step S25: using probability distribution analysis technology to perform user charging characteristic distribution analysis on the spatiotemporal user charging preference data, thereby obtaining user charging characteristic distribution data; Step S26: Perform regional association rule mining on the user charging feature distribution data to obtain regional user charging habit data.

4. The charging pile data push method according to claim 3, characterized in that: Step S22 includes the following steps: Step S221: extracting user behavior time series features from the charging pile usage history data according to the charging pile usage history spatial cluster data, thereby obtaining user behavior time series feature data; Step S222: performing a charging pile usage frequency analysis on the charging pile usage history data according to the charging pile usage history spatial cluster data, thereby obtaining usage frequency trend feature data; Step S223: collecting charging pile power from the charging pile usage history data according to the charging pile usage history spatial cluster data, thereby obtaining charging pile power data; Step S224: Utilize the user behavior time series feature data to perform time period power preference analysis on the charging pile power data and perform power charging duration analysis, thereby obtaining power preference feature data.

5. The charging pile data push method according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: using a regional electric vehicle charging prediction model to predict the regional electric vehicle charging, thereby obtaining regional electric vehicle charging parameters; Step S42: dividing the charging pile distribution map data and the charging pile usage history data by time dimension, thereby obtaining time dimension division data; Step S43: performing spatial hot spot analysis on the charging pile distribution map data and the charging pile usage history data according to the time dimension division data, so as to obtain a time dimension charging hot spot map; Step S44: Calculate the user's expected charging demand using the charging demand expected value calculation formula according to the regional electric vehicle stop charging parameters and the time dimension charging heat map, thereby obtaining the user's expected charging demand value.

6. The charging pile data push method according to claim 5, characterized in that: In step S44, the expected value of the user's charging demand is calculated, wherein the formula for calculating the expected value of the user's charging demand is specifically: ; In the formula, represents the expected value of electric vehicle charging demand, Indicates the total number of charging piles in the area. represents the capacity factor of the charging pile, Indicates the frequency of charging pile being used. Indicates the power capacity of the charging pile. Indicates the distance from the electric vehicle to the nearest charging station. The characteristic value of the parking lot, Indicates the distribution value of charging hotspots in different time periods in the area.

7. The charging pile data push method according to claim 1, characterized in that: Step S5 includes the following steps: Step S51: when the user's expected charging demand value is greater than or equal to the preset standard user's expected charging demand value, the area where the user is located is marked, thereby obtaining the area data of the charging pile to be matched; Step S52: Matching the charging pile area data to be matched and the charging habit data of the regional users with the charging needs of the regional users, thereby obtaining the charging pile area data to be pushed; Step S53: Push charging data of users in a specific area based on the charging pile area distribution data to be pushed, so as to realize the charging pile data push work.

8. A charging pile data push system, characterized in that: Used to execute the charging pile data push method according to claim 1, the charging pile data push system comprises: The charging pile usage history data extraction module is used to obtain urban geographic traffic data; use urban geographic traffic data to analyze the regional distribution of charging piles, thereby obtaining the regional distribution data of charging piles; extract the charging pile usage history data based on the regional distribution data of charging piles, thereby obtaining the charging pile usage history data; The user charging habit mining module is used to extract the charging pile usage preference features from the charging pile usage history data according to the charging pile regional distribution data, thereby obtaining the charging pile usage preference feature data; the user charging habit mining is performed on the charging pile usage preference feature data, thereby obtaining the regional user charging habit data; The regional charging pile associated weight factor extraction module is used to extract the characteristics of electric vehicle stop points by using urban geographic traffic data, so as to obtain the characteristic data of electric vehicle stop time; extract the regional charging pile associated weight factors according to the charging pile distribution map data, so as to obtain the regional charging pile associated weight factors; construct a regional stop electric vehicle charging prediction model based on the regional charging pile associated weight factors, so as to obtain the regional stop electric vehicle charging prediction model; A user charging demand expected value calculation module is used to predict the regional electric vehicle stop charging by using the regional electric vehicle stop charging prediction model, thereby obtaining the regional electric vehicle stop charging parameters; and calculate the user charging demand expected value according to the regional electric vehicle stop charging parameters, thereby obtaining the user charging demand expected value; The module for pushing charging data for users in specific areas is used to make expected value judgments based on the expected values ​​of the users' charging needs, thereby obtaining the regional data of charging piles to be matched; to match the regional data of charging piles to be matched with the regional data of users' charging habits, thereby obtaining the regional data of charging piles to be pushed; and to push the charging data of users in specific areas to the regional data of charging piles to be pushed based on the regional distribution data of charging piles, thereby realizing the work of pushing charging pile data.

Images