Charging pile digital payment system and method based on cloud computing

Abstract

The invention relates to the technical field of cloud computing, in particular to a charging pile digital payment system and method based on cloud computing. The method comprises the following steps: acquiring charging station sensing data, and constructing a charging station sensing network; historical transaction data of the charging pile is acquired, and an abnormal transaction classification model is constructed; obtaining charging pile transaction request data, and performing abnormal transaction classification on the charging pile transaction request data through the abnormal transaction classification model to obtain to-be-transacted order data; performing electric energy charging amount data extraction on the to-be-transacted order data to obtain electric energy charging amount data, and performing charging pile electric energy transmission loss analysis on the electric energy charging amount data based on a charging station sensing network to obtain actual electric energy charging amount data and charging pile electric energy transmission loss data; and performing amount correction on the to-be-transacted order data based on the actual electric energy charging amount data and the charging pile electric energy transmission loss data to obtain to-be-transacted order correction data. According to the invention, the security of digital payment can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of cloud computing, and particularly to a digital payment system and method for charging piles based on cloud computing. Background Art

[0002] At the end of the 20th century and the beginning of the 21st century, with the enhancement of environmental protection awareness and the need for energy structure adjustment, electric vehicles began to become an important option for solving traffic pollution and energy consumption problems. However, the electric vehicle charging systems at that time mainly relied on traditional charging piles, and users needed to pay by coin insertion or through pre-purchased recharge cards. This method had problems such as inconvenient charging and insecure payment, which restricted the popularization and promotion of electric vehicles. With the development of the Internet and the popularization of mobile payment, the electric vehicle charging system has been upgraded to a brand-new digital level. Users can achieve remote charging control and payment only through a mobile phone App or other mobile payment platforms, and no longer need to carry cash or recharge cards. The emergence of this technology not only improves the charging experience of users, but also greatly reduces the operation cost and maintenance cost, providing strong support for the popularization of electric vehicles. However, the traditional mobile payment method for charging piles has problems of low payment security and low transparency of payment fees. Summary of the Invention

[0003] Based on this, it is necessary for the present invention to provide a digital payment system and method for charging piles based on cloud computing to solve at least one of the above technical problems.

[0004] To achieve the above object, a digital payment method for charging piles based on cloud computing includes the following steps:

[0005] Step S1: Obtain the sensing data of the charging station, and construct a sensing network of the charging station based on the sensing data of the charging station, so as to obtain the sensing network of the charging station;

[0006] Step S2: Obtain the historical transaction data of the charging pile, detect abnormal transactions according to the historical transaction data of the charging pile, so as to obtain the abnormal transaction data of the charging pile, and construct an abnormal transaction classification model according to the abnormal transaction data of the charging pile;

[0007] Step S3: Obtain the transaction request data of the charging pile, and classify the abnormal transactions of the transaction request data of the charging pile through the abnormal transaction classification model, so as to obtain the data of the order to be traded;

[0008] Step S4: Extract the electric energy charging amount data from the data of the order to be traded, so as to obtain the electric energy charging amount data, and analyze the power transmission loss of the charging pile for the electric energy charging amount data based on the sensing network of the charging station, so as to obtain the actual electric energy charging amount data and the power transmission loss data of the charging pile;

[0009] Step S5: Based on the actual electricity charging amount data and the charging pile electricity transmission loss data, correct the order transaction amount for the order data to be traded, so as to obtain the corrected order data to be traded, and upload it to the charging pile transaction cloud platform to execute the collection task.

[0010] Through acquiring the charging station sensing data and constructing a sensing network, the present invention can monitor the operating state of the charging equipment in real time, including information such as the charging efficiency, charging speed, and equipment failures of the charging piles. In this way, problems can be discovered in a timely manner and measures can be taken for repair, improving the reliability of the charging equipment and the user experience. The abnormal transactions of the charging piles include situations such as malicious users, transaction failures, and payment anomalies. By analyzing the historical transaction data and constructing an abnormal transaction classification model, the system can automatically identify and classify abnormal transactions, give early warnings in a timely manner and take measures, thereby ensuring the security and transparency of payments. For the transaction request data of each charging pile, the system can perform real-time classification according to the abnormal transaction classification model to identify potential abnormal transaction requests. In this way, intervention can be carried out before the transaction occurs to prevent abnormal transactions from causing losses to the system. The actual charging amount of the charging pile will be affected by the charging pile itself and the losses in electricity transmission. By extracting the charging amount and analyzing the losses from the order data, the system can accurately calculate the actual charging amount enjoyed by the user, help the user understand the charging cost, and at the same time provide data support for subsequent correction of the transaction amount. Based on the actual charging amount and loss data, the system can correct the order amount to ensure that the user pays according to the actual charging amount. This improves the fairness and transparency of the transaction, enhances the user's trust in the charging service, and at the same time improves the income stability and management efficiency of the charging station.

[0011] Optionally, step S1 is specifically as follows:

[0012] Step S11: Acquire the charging station sensing data, and perform environmental sensing feature extraction and electrical energy sensing feature extraction on the charging station sensing data, so as to obtain the charging station environmental sensing data and the charging station electrical energy sensing data;

[0013] Step S12: Based on the charging station environmental sensing data, extract the charging station camera images, so as to obtain the charging station camera images;

[0014] Step S13: Based on the charging station camera images, construct a three-dimensional coordinate system, so as to obtain the charging station three-dimensional coordinate system;

[0015] Step S14: Based on the charging station environmental sensing data, perform environmental sensing data fusion on the charging station three-dimensional coordinate system, so as to obtain the charging station environmental sensing network;

[0016] Step S15: According to the charging station electrical energy sensing data, perform electrical energy sensing space mapping on the charging station environmental sensing network, so as to obtain the charging station sensing network.

[0017] By collecting the sensing data of the charging station, including environmental sensing data and electrical energy sensing data, the system can monitor the operating conditions and environmental situation of the charging station in real time. The extracted features can help the system better understand the operating state of the charging station and provide data support for subsequent analysis and decision-making. Using camera image technology to obtain real-time images of the charging station can help remotely monitor the safety and operating state of the charging station. For example, abnormal situations of the charging pile or user violation behaviors can be detected in a timely manner, and corresponding measures can be taken. By constructing a three-dimensional coordinate system from the camera images of the charging station, the system can more accurately locate the position information of the charging piles and other devices. This is crucial for subsequent fusion of environmental sensing data and spatial mapping, providing an accurate spatial reference for the system. Fusing the environmental sensing data with the three-dimensional coordinate system of the charging station can accurately locate the source of the sensing data in space, thereby better understanding the environmental situation in each area of the charging station. This can provide the system with more precise environmental perception capabilities and help operators better manage the charging station. Using the electrical energy sensing data to perform spatial mapping on the environmental sensing network of the charging station can help the system better understand the electrical energy distribution in each area of the charging station. This helps optimize the layout and configuration of the charging equipment, improve the charging efficiency, and ensure the stable operation of the charging equipment.

[0018] Optionally, step S2 is specifically as follows:

[0019] Step S21: Obtain the historical transaction data of the charging pile;

[0020] Step S22: Extract the transaction account features from the historical transaction data of the charging pile to obtain the transaction account data, and classify the transaction account data by account type to obtain the member transaction account data and the temporary transaction account data;

[0021] Step S23: Extract the transaction data from the historical transaction data of the charging pile according to the member transaction account data and the temporary transaction account data respectively to obtain the member account historical transaction data and the temporary account historical transaction data;

[0022] Step S24: Detect abnormal transactions of the member account from the member account historical transaction data to obtain the member account abnormal transaction data;

[0023] Step S25: Detect abnormal transactions of the temporary account from the temporary account historical transaction data to obtain the temporary account abnormal transaction data;

[0024] Step S26: Merge the member account abnormal transaction data and the temporary account abnormal transaction data to obtain the charging pile abnormal transaction data, and construct an abnormal transaction classification model according to the charging pile abnormal transaction data.

[0025] By obtaining the historical transaction data of the charging pile, the system can establish a complete transaction database, which contains all records of users using the charging pile. This provides a data basis for subsequent analysis. By extracting the characteristics of the transaction account, the system can conduct a more in-depth analysis of the transaction data. Classifying the transaction account data by account type can distinguish between member transaction accounts and temporary transaction accounts, which helps to adopt different analysis strategies for different types of accounts. According to different types of transaction accounts, the system can extract the historical transaction data of member accounts and the historical transaction data of temporary accounts respectively. This helps to analyze the usage patterns and behavioral differences between the two types of accounts. By performing anomaly detection on the historical transaction data of member accounts, the system can discover existing fraud, unauthorized swiping, or other abnormal situations. This helps to protect the security of member accounts and take timely measures to prevent the loss from expanding. Performing anomaly detection on the historical transaction data of temporary accounts also helps to discover potential abnormal situations, such as malicious use and illegal charging. Discovering and handling these anomalies in a timely manner can ensure the safe and stable operation of the charging pile system. Merging the abnormal transaction data of member accounts and temporary accounts can build a comprehensive abnormal transaction database. Based on these data, the system can further establish an abnormal transaction classification model, identify different types of abnormal behaviors, and provide a more accurate basis for future transaction monitoring.

[0026] Optionally, step S24 is specifically as follows:

[0027] Step S241: Extract the transaction location characteristics and transaction time series characteristics from the historical transaction data of the member account, so as to obtain the member account transaction location data and the member account transaction time series data;

[0028] Step S242: Conduct location statistical analysis on the member account transaction location data, so as to obtain the high-frequency transaction location data and the low-frequency transaction location data;

[0029] Step S243: Divide the high-frequency transaction range based on the high-frequency transaction location data, so as to obtain the member high-frequency transaction range data;

[0030] Step S244: Calculate the spatial distance between the low-frequency transaction location data and the member high-frequency transaction range, so as to obtain the low-frequency transaction spatial distance data;

[0031] Step S245: Evaluate the rationality of the low-frequency transactions of the member account based on the member account transaction time series data and the low-frequency transaction spatial distance data, so as to obtain the rationality data of the low-frequency transactions of the member account;

[0032] Step S246: Extract low - rationality transaction data from the historical transaction data of the member account based on the low - frequency transaction rationality data of the member account, so as to obtain the abnormal transaction data of the member account.

[0033] Through the present invention, by extracting the characteristics of transaction location and transaction time sequence, the system can deeply understand the transaction behavior patterns and habits of the member account. This helps with subsequent analysis of transaction data and anomaly detection. By statistically analyzing the transaction location data, the system can identify high - frequency and low - frequency transaction locations. High - frequency transaction locations are the charging stations that users often visit, while low - frequency transaction locations are the charging stations that users rarely visit, which provides a basis for subsequent anomaly detection. Dividing high - frequency transaction locations into high - frequency transaction ranges helps define the commonly used transaction areas of users. This can help the system more accurately judge the normal transaction behavior of users, thereby reducing false alarms. By calculating the spatial distance between low - frequency transaction locations and high - frequency transaction ranges, the system can evaluate the relationship between low - frequency transaction locations and the commonly used locations of users. This can be used as one of the important bases for evaluating abnormal transactions. Combining the transaction time - sequence data and the low - frequency transaction spatial - distance data, the system can evaluate the rationality of low - frequency transactions of the member account. This helps identify abnormal transactions that do not conform to the user's behavior pattern. According to the evaluation results of the rationality of low - frequency transactions, the system can extract low - rationality transaction data, that is, potential abnormal transaction data. This provides important information for subsequent abnormal transaction detection and processing.

[0034] Optionally, step S25 is specifically as follows:

[0035] Step S251: Extract the transaction frequency characteristics and transaction amount characteristics from the historical transaction data of the temporary account, so as to obtain the transaction frequency data of the temporary account and the transaction amount data of the temporary account;

[0036] Step S252: Perform high - frequency transaction clustering calculation on the transaction frequency data of the temporary account, so as to obtain high - frequency temporary account transaction data;

[0037] Step S253: Calculate the transaction interval for the high - frequency temporary account transaction data, so as to obtain the transaction interval data, and extract the low - transaction - interval transaction data from the high - frequency temporary account transaction data according to the transaction interval data, so as to obtain short - time high - frequency transaction data;

[0038] Step S254: Statistically analyze the transaction amount of the transaction amount data of the temporary account, so as to obtain high - amount transaction amount data and low - amount transaction amount data;

[0039] Step S255: Calculate the intersection of transaction orders for the high - amount transaction amount data and the short - time high - frequency transaction data, so as to obtain the first temporary account abnormal transaction data;

[0040] Step S256: Calculate the intersection of the low-amount transaction data and the short-term high-frequency transaction data to obtain the second temporary account abnormal transaction data;

[0041] Step S257: Merge the first temporary account abnormal transaction data and the second temporary account abnormal transaction data to obtain the temporary account abnormal transaction data.

[0042] By extracting the characteristics of the transaction frequency and transaction amount, the system of the present invention can understand the transaction behavior patterns and transaction amount distributions of the temporary accounts. This helps with subsequent analysis and anomaly detection. By performing clustering calculations on the transaction frequency data, the system can identify high-frequency temporary account transaction behaviors. These high-frequency transactions are one of the indicators of abnormal behaviors. By calculating the transaction intervals of the high-frequency transaction data, the system can evaluate whether the transaction frequency of the temporary account is abnormal. This helps identify short-term high-frequency abnormal transaction behaviors. By performing statistics on the transaction amount data, the system can understand the transaction amount distributions of the temporary accounts. This can help identify high-amount and low-amount transactions. By calculating the intersection between the high-amount transaction data and the short-term high-frequency transaction data, the system can discover abnormal transactions with both high amounts and high frequencies. By calculating the intersection between the low-amount transaction data and the short-term high-frequency transaction data, the system can discover low-amount but high-frequency abnormal transactions. By merging the abnormal transaction data obtained in the first step and the second step, the system can obtain comprehensive temporary account abnormal transaction data, providing a basis for subsequent processing and management.

[0043] Optionally, step S3 is specifically as follows:

[0044] Step S31: Obtain the charging pile transaction request data, and extract the transaction account characteristics from the charging pile transaction request data to obtain the real-time transaction account data;

[0045] Step S32: Extract the account historical transaction data from the charging pile historical transaction data according to the real-time transaction account data to obtain the real-time account historical transaction data;

[0046] Step S33: Merge the real-time account historical transaction data and the charging pile transaction request data to obtain the real-time account transaction data;

[0047] Step S34: Classify the real-time account transaction data through the abnormal transaction classification model. If the real-time account transaction data is classified as abnormal transaction data, upload the real-time account transaction data to the charging pile transaction cloud platform to execute the stop transaction task; if the real-time account transaction data is classified as normal transaction data, obtain the pending transaction order data.

[0048] By extracting the characteristics of the trading account, such as trading frequency, trading amount, trading time, etc., the system can obtain the account data of the charging pile transaction in real time, providing a basis for subsequent analysis and processing. By matching and extracting the real-time trading account data with the historical transaction data of the charging pile, the system can obtain the historical transaction records of the real-time account, which helps to analyze the trading behavior patterns and historical trends of the account. Merging the historical transaction data of the real-time account with the transaction request data of the charging pile can form a complete real-time account transaction data set, providing more comprehensive data support for subsequent anomaly detection and classification. Using the abnormal transaction classification model, the system can perform real-time monitoring and anomaly detection on the real-time account transaction data. If the transaction data is classified as an abnormal transaction, there are fraud or other security risks, and the stop transaction task needs to be executed to ensure the security of the charging pile transaction; if the transaction data is classified as a normal transaction, the pending transaction order data can be continued to be processed.

[0049] Optionally, step S4 is specifically as follows:

[0050] Step S41: Extract the electric energy charging amount data from the pending transaction order data to obtain the electric energy charging amount data;

[0051] Step S42: Extract the characteristics of the electric energy transmission charging pile from the electric energy charging amount data to obtain the electric energy transmission charging pile data;

[0052] Step S43: Extract the charging pile sensing data from the charging station sensing network according to the electric energy transmission charging pile data to obtain the charging pile sensing data;

[0053] Step S44: Analyze the electric energy transmission loss based on the charging pile sensing data to obtain the charging pile electric energy transmission loss data;

[0054] Step S45: Calculate the actual electric energy charging amount based on the charging pile electric energy transmission loss data and the electric energy charging amount data to obtain the actual electric energy charging amount data.

[0055] By extracting the electric energy charging amount information from the order data to be traded, the system can obtain the electric energy consumed during each charging process, providing basic data for subsequent electric energy transmission and loss analysis. By extracting features from the electric energy charging amount data, the system can analyze the charging characteristics of the charging pile, including charging rate, charging efficiency, etc., so as to understand the performance and working status of the charging pile. By obtaining the sensing data of the charging pile, such as temperature, voltage, current, etc., the system can monitor the real-time working status of the charging pile, detect abnormal situations in time and handle them. By analyzing the sensing data of the charging pile, the system can calculate the loss situation of the charging pile during the electric energy transmission process, understand the energy conversion efficiency of the charging pile, and optimize and improve it. By combining the electric energy transmission loss data and the electric energy charging amount data, the system can accurately calculate the actual electric energy charging amount, provide accurate charging services for users, and optimize the use efficiency of the charging pile.

[0056] Optionally, step S44 is specifically as follows:

[0057] Step S441: Extract electric energy sensing data from the sensing data of the charging pile to obtain the electric energy sensing data of the charging pile;

[0058] Step S442: Analyze the topological structure of the electric energy transmission line based on the electric energy sensing data of the charging pile to obtain the electric energy transmission path data of the charging pile;

[0059] Step S443: Calculate the electric energy difference of the transmission path for the electric energy sensing data of the charging pile and the electric energy transmission path data of the charging pile to obtain the line electric energy difference data;

[0060] Step S444: Perform electric energy transmission simulation based on the electric energy transmission path data of the charging pile and the line electric energy difference data to obtain the electric energy transmission simulation data;

[0061] Step S445: Conduct statistics on the transmission loss of the electric energy transmission simulation data to obtain the electric energy transmission loss data of the charging pile.

[0062] By extracting electrical energy-related information in the sensing data of charging piles, such as voltage, current, temperature, etc., the system can obtain the real-time electrical energy transmission status of the charging piles, providing basic data for subsequent analysis and optimization. By analyzing the electrical energy sensing data of the charging piles, the system can establish the topological structure of the transmission lines between the charging piles, understand the transmission path and connection relationship of electrical energy in the charging station, and provide a basis for subsequent electrical energy transmission analysis. By calculating the electrical energy difference on the transmission path between the charging piles, the system can evaluate the loss situation of electrical energy during transmission, identify potential energy loss points, and provide a reference basis for optimizing electrical energy transmission. By simulating the electrical energy transmission process between the charging piles, the system can predict the electrical energy loss situation under different transmission paths, evaluate the transmission efficiency of different schemes, and provide optimization suggestions. By statistically analyzing the loss situation in the electrical energy transmission simulation data, the system can quantify the energy losses in each link, identify the factors causing energy losses, and provide guidance for improving the electrical energy transmission system.

[0063] Optionally, step S5 is specifically as follows:

[0064] Step S51: Obtain the electrical energy cost data of the charging pile;

[0065] Step S52: Based on the electrical energy cost data of the charging pile, calculate the electrical energy costs for the actual electrical energy charging amount data and the electrical energy transmission loss data of the charging pile respectively, so as to obtain the actual electrical energy cost data and the transmission loss cost data;

[0066] Step S53: Based on the actual electrical energy cost data, correct the electrical energy cost of the to-be-traded order data, so as to obtain the corrected electrical energy trading order data;

[0067] Step S54: Based on the transmission loss cost data, correct the transmission loss cost of the corrected electrical energy trading order data, so as to obtain the corrected to-be-traded order data, and upload it to the charging pile trading cloud platform to execute the collection task.

[0068] By obtaining the electricity cost data of the charging pile, the system can understand the actual cost of the charging service, providing basic data for subsequent electricity cost calculation and correction of transaction orders. By combining the actual electricity charging volume data with the electricity transmission loss data of the charging pile, the system can accurately calculate the actual electricity cost consumed and the cost generated by the transmission loss, providing an accurate cost basis for electricity trading. By correcting the to-be-traded order data according to the actual electricity cost data, the system can ensure that the electricity cost involved in the transaction order is consistent with the actual situation, guaranteeing the fairness and accuracy of electricity trading. By considering the cost generated by the transmission loss, the system can further correct the corrected data of the electricity trading order to ensure that the transmission loss cost in electricity trading is reasonably calculated and charged, guaranteeing the fairness and transparency of the transaction. When uploading the corrected data of the to-be-traded order to the charging pile trading cloud platform to execute the collection task, it is conducive to the openness and transparency of transaction information. Users can query their transaction orders and cost details at any time, ensuring the openness and accessibility of information. This process ensures the fairness, accuracy, and transparency of electricity trading by accurately calculating the electricity cost and transmission loss cost and correcting the transaction order, improving the quality of the charging service and user satisfaction.

[0069] Optionally, this specification also provides a cloud computing-based charging pile digital trading system for executing the cloud computing-based charging pile digital trading method described above. The cloud computing-based charging pile digital trading system includes:

[0070] A sensing network construction module for obtaining charging station sensing data and constructing a charging station sensing network based on the charging station sensing data to obtain a charging station sensing network;

[0071] An abnormal transaction detection module for obtaining the historical transaction data of the charging pile, detecting abnormal transactions according to the historical transaction data of the charging pile to obtain the abnormal transaction data of the charging pile, and constructing an abnormal transaction classification model according to the abnormal transaction data of the charging pile;

[0072] An abnormal transaction classification module for obtaining the charging pile transaction request data and classifying the abnormal transactions of the charging pile transaction request data through the abnormal transaction classification model to obtain the to-be-traded order data;

[0073] A transmission loss analysis module for extracting the electricity charging volume data from the to-be-traded order data to obtain the electricity charging volume data, and analyzing the electricity transmission loss of the charging pile for the electricity charging volume data based on the charging station sensing network to obtain the actual electricity charging volume data and the electricity transmission loss data of the charging pile;

[0074] A transaction amount correction module is used to correct the order transaction amount of the order to be traded based on the actual electricity charging amount data and the electricity transmission loss data of the charging pile, so as to obtain the corrected data of the order to be traded and upload it to the charging pile transaction cloud platform to execute the collection task.

[0075] The cloud computing-based charging pile digital trading system of the present invention can implement any cloud computing-based charging pile digital trading method of the present invention. It is a medium for coordinating the operations and signal transmissions between various modules to complete the cloud computing-based charging pile digital trading method. The internal modules of the system cooperate with each other, thereby improving the security of digital payment and the accuracy of electricity trading. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] By reading the detailed description of the non-restrictive embodiments with reference to the following drawings, other features, objectives, and advantages of the present invention will become more apparent:

[0077] Figure 1 It is a schematic flowchart of the steps of the cloud computing-based charging pile digital payment method of the present invention;

[0078] Figure 2 It is a detailed schematic flowchart of step S1 in the present invention;

[0079] Figure 3 It is a detailed schematic flowchart of step S2 in the present invention.

[0080] The realization, functional features, and advantages of the objectives of the present invention will be further described with reference to the embodiments and the drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0081] The technical method of the present invention will be clearly and completely described below with reference to the drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0082] In addition, the drawings are only schematic diagrams of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings represent the same or similar parts, so repeated descriptions thereof will be omitted. Some of the block diagrams shown in the 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 in one or more hardware modules or integrated circuits, or in different networks and / or processor methods and / or microcontroller methods.

[0083] It should be understood that although terms such as "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. 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.

[0084] To achieve the above object, please refer to Figures 1 to 3 , the present invention provides a cloud computing-based digital payment method for charging piles, and the method includes the following steps:

[0085] Step S1: Obtain the charging station sensing data, and construct a charging station sensing network based on the charging station sensing data, so as to obtain a charging station sensing network;

[0086] In this embodiment, sensor devices are installed on each charging pile to monitor data such as current, voltage, and power in real time. These sensors transmit the data to the data center of the charging station through a wireless network. In the data center, real-time data stream processing technology is used to process and analyze the sensor data. A distributed system architecture is adopted, and tools such as Apache Kafka are used for data stream processing to ensure the real-time and accuracy of the data. According to the sensor data, a charging station sensing network is constructed by using graph theory algorithms and machine learning techniques to reflect the association relationship and topological structure between the internal devices of the charging station.

[0087] Step S2: Obtain the historical transaction data of the charging pile, perform abnormal transaction detection according to the historical transaction data of the charging pile, so as to obtain the abnormal transaction data of the charging pile, and construct an abnormal transaction classification model according to the abnormal transaction data of the charging pile;

[0088] In this embodiment, historical transaction record data, including information such as transaction time, charging amount, and transaction amount, is extracted from the transaction record database in the charging pile management system. Data preprocessing and cleaning are performed by using libraries such as Pandas and NumPy in Python to identify and process missing values and outliers. Then, statistical methods and anomaly detection algorithms (such as the Isolation Forest algorithm) are used to analyze the cleaned data to identify abnormal transactions. An abnormal transaction classification model is constructed by using machine learning frameworks such as Scikit-learn or TensorFlow to classify and label abnormal transactions.

[0089] Step S3: Obtain the charging pile transaction request data, and perform abnormal transaction classification on the charging pile transaction request data through the abnormal transaction classification model, so as to obtain the to-be-transacted order data;

[0090] In this embodiment, when new charging pile transaction request data enters the system, data is extracted from the charging pile management system using an API or a message queue. A data processing script is written in Python to preprocess and extract features from the transaction request data. The transaction request data is input into the previously constructed abnormal transaction classification model, and the model is used for abnormal transaction detection and classification. Finally, the valid transaction request data is stored in the database as pending transaction order data for subsequent processing.

[0091] Step S4: Extract the electric energy charging amount data from the pending transaction order data to obtain the electric energy charging amount data, and perform an analysis of the charging pile electric energy transmission loss on the electric energy charging amount data based on the charging station sensing network, so as to obtain the actual electric energy charging amount data and the charging pile electric energy transmission loss data;

[0092] In this embodiment, when extracting the electric energy charging amount data from the pending transaction order data, the order data is retrieved from the database, and the charging amount information therein is extracted. Using the real-time data in the charging station sensing network, the electric energy transmission loss of each charging pile is calculated. Data visualization tools such as Matplotlib or Seaborn are used to perform a visual analysis of the electric energy transmission loss data to better understand and identify the loss patterns. Combining the actual charging amount data and the transmission loss data, the actual electric energy charging amount of each order is calculated, and the order data is updated.

[0093] Step S5: Based on the actual electric energy charging amount data and the charging pile electric energy transmission loss data, correct the order transaction amount for the pending transaction order data to obtain the pending transaction order correction data, and upload it to the charging pile transaction cloud platform to perform the collection task.

[0094] In this embodiment, the order transaction amount is corrected based on the actual electric energy charging amount data and the transmission loss data. According to the charging service rate and the electric energy price, the payable amount of each order is calculated and adjusted according to the actual charging amount and the transmission loss. A fee correction algorithm is written in Python, and the corrected order data is uploaded to the charging pile transaction cloud platform. Through a RESTful API or other network interfaces, the order data is sent to the cloud platform to perform the collection task and generate a transaction record.

[0095] By obtaining the sensing data of the charging station and constructing a sensing network, the present invention can monitor the operating status of charging devices in real time, including information such as the charging efficiency, charging speed, and equipment failures of charging piles. This can promptly detect problems and take measures for repair, improving the reliability of charging devices and the user experience. Abnormal transactions of charging piles include situations such as malicious users, transaction failures, and payment anomalies. By analyzing historical transaction data and constructing an abnormal transaction classification model, the system can automatically identify and classify abnormal transactions, issue early warnings, and take measures, thereby ensuring the security and transparency of payments. For the transaction request data of each charging pile, the system can perform real-time classification according to the abnormal transaction classification model to identify potential abnormal transaction requests. This can intervene before the transaction occurs to prevent losses caused by abnormal transactions to the system. The actual charging amount of the charging pile is affected by the charging pile itself and the losses in power transmission. By extracting the charging amount and analyzing the losses from the order data, the system can accurately calculate the actual charging amount enjoyed by the user, helping the user understand the charging cost and providing data support for subsequent correction of the transaction amount. Based on the actual charging amount and loss data, the system can correct the order amount to ensure that the user pays according to the actual charging amount. This improves the fairness and transparency of transactions, enhances the user's trust in the charging service, and also improves the revenue stability and management efficiency of the charging station.

[0096] Optionally, step S1 is specifically as follows:

[0097] Step S11: Obtain the sensing data of the charging station, and perform environmental sensing feature extraction and electrical energy sensing feature extraction on the sensing data of the charging station, so as to obtain the environmental sensing data of the charging station and the electrical energy sensing data of the charging station;

[0098] In this embodiment, real-time environmental and electrical energy sensing data are obtained through sensor devices installed in the charging station. For environmental sensing data, devices such as temperature sensors, humidity sensors, and gas sensors can be used to obtain relevant characteristics of the environment around the charging station. At the same time, electrical energy sensing data, including the charging power of the charging pile and the power consumption situation, are obtained by using devices such as current sensors and voltage sensors. Through the data acquisition and processing system, the sensor data are processed and feature-extracted in real time. For example, features such as the temperature change trend and humidity fluctuation of the environmental data are extracted, and the change situation of the charging power of the electrical energy data is extracted.

[0099] Step S12: Extract the camera images of the charging station based on the environmental sensing data of the charging station, so as to obtain the camera images of the charging station;

[0100] In this embodiment, a camera device installed around the charging station is used to obtain the camera images of the charging station. Through image processing technology, the camera images included in the environmental sensing data of the charging station are extracted and processed to identify information such as the location of the charging pile, the parking situation of the vehicle, and the situation of the surrounding environment. The object detection and image segmentation algorithms in computer vision technology can be used to extract the location of the charging pile and the information of the surrounding environment from the image.

[0101] Step S13: Construct a three-dimensional coordinate system based on the camera image of the charging station, so as to obtain the three-dimensional coordinate system of the charging station;

[0102] In this embodiment, based on the obtained camera image data of the charging station, a three-dimensional coordinate system of the charging station is constructed by using computer vision and three-dimensional reconstruction technology. Through image processing and feature extraction algorithms, the objects in the camera image are located and tracked to determine the three-dimensional positions of the charging pile and the surrounding environment. Using the geometric relationship of multi-view images and combining the position and angle information of the camera, a three-dimensional coordinate system of the charging station is established to ensure the accurate positioning and description of the charging pile and the surrounding environment.

[0103] Step S14: Perform environmental sensing data fusion on the three-dimensional coordinate system of the charging station based on the environmental sensing data of the charging station, so as to obtain the environmental sensing network of the charging station;

[0104] In this embodiment, environmental sensing data fusion is performed based on the environmental sensing data of the charging station and the constructed three-dimensional coordinate system. By associating the environmental sensing data with the position information of the charging pile and the surrounding environment, an environmental sensing network of the charging station is established. Using data fusion technology, the environmental sensing data and the spatial position information are integrated to more comprehensively and accurately describe the environmental conditions of the charging station and provide more powerful support for subsequent data analysis and applications.

[0105] Step S15: Perform electrical energy sensing spatial mapping on the environmental sensing network of the charging station according to the electrical energy sensing data of the charging station, so as to obtain the sensing network of the charging station.

[0106] In this embodiment, according to the electrical energy sensing data of the charging station, electrical energy sensing spatial mapping is performed on the environmental sensing network of the charging station. Using the position information of the charging pile and the electrical energy sensing data, the electrical energy consumption situation is mapped and analyzed within the spatial range of the charging station. Through spatial data analysis technology, the electrical energy consumption situation in different areas inside the charging station is visually displayed and analyzed to better understand and optimize the operation and management of the charging station.

[0107] By collecting the sensing data of the charging station, including environmental sensing data and power sensing data, the system can monitor the operating status and environmental conditions of the charging station in real time. The extracted features can help the system better understand the operating state of the charging station and provide data support for subsequent analysis and decision-making. Using camera image technology to obtain real-time images of the charging station can help remotely monitor the safety and operating status of the charging station. For example, abnormal situations of charging piles or user violations can be detected in a timely manner, and corresponding measures can be taken. By constructing a three-dimensional coordinate system from the camera images of the charging station, the system can more accurately locate the position information of charging piles and other devices. This is crucial for subsequent fusion of environmental sensing data and spatial mapping, providing an accurate spatial reference for the system. Fusing the environmental sensing data with the three-dimensional coordinate system of the charging station can accurately locate the source of the sensing data in space, thus better understanding the environmental conditions in each area of the charging station. This can provide the system with more precise environmental perception capabilities and help operators better manage the charging station. Using power sensing data to perform spatial mapping of the environmental sensing network of the charging station can help the system better understand the power distribution in each area of the charging station. This helps optimize the layout and configuration of charging devices, improve charging efficiency, and ensure the stable operation of charging devices.

[0108] Optionally, step S2 is specifically as follows:

[0109] Step S21: Obtain the historical transaction data of the charging pile;

[0110] In this embodiment, the historical transaction data of the charging pile is obtained through the transaction record database of the charging pile. These data include information such as the charging start time, end time, charging duration, charging pile number, and charging power. Use database query language or API to extract the required transaction data from the database to ensure data integrity and accuracy.

[0111] Step S22: Extract transaction account features from the historical transaction data of the charging pile to obtain transaction account data, and classify the transaction account data by account type to obtain member transaction account data and temporary transaction account data;

[0112] In this embodiment, transaction account features are extracted from the historical transaction data of the charging pile to obtain transaction account data. In this step, account-related features such as transaction frequency, charging amount, and charging period can be extracted from the transaction data. Then, the transaction account data is classified, and according to the charging behavior and features, the accounts are divided into member transaction accounts and temporary transaction accounts. For example, the account type is judged according to registration information, recharge records, etc.

[0113] Step S23: Extract transaction data from the historical transaction data of the charging piles based on the member transaction account data and the temporary transaction account data respectively, so as to obtain the historical transaction data of the member accounts and the historical transaction data of the temporary accounts;

[0114] In this embodiment, according to the member transaction account data and the temporary transaction account data, the historical transaction data of the charging piles is extracted respectively. For the member transaction account, the corresponding transaction records are screened out, including information such as member ID, charging time, and charging power. For the temporary transaction account, the corresponding transaction records are also extracted, including information such as temporary account ID, charging time, and charging power.

[0115] Step S24: Perform abnormal transaction detection on the historical transaction data of the member accounts to obtain the abnormal transaction data of the member accounts;

[0116] In this embodiment, for the historical transaction data of the member accounts, abnormal transaction detection of the member accounts is performed. Using abnormal detection algorithms, such as statistical models or machine learning models, the charging behaviors of the member accounts are analyzed and compared to identify abnormal charging behaviors, such as abnormal charging frequencies and abnormal charging amounts. This can help detect potential fraud behaviors or abnormal situations.

[0117] Step S25: Perform abnormal transaction detection on the historical transaction data of the temporary accounts to obtain the abnormal transaction data of the temporary accounts;

[0118] In this embodiment, for the historical transaction data of the temporary accounts, abnormal transaction detection of the temporary accounts is performed. Similarly, abnormal detection algorithms are used to analyze and compare the charging behaviors of the temporary accounts to identify abnormal charging behaviors, such as abnormal charging periods and abnormal charging locations. This helps detect situations such as illegal use or abnormal operations.

[0119] Step S26: Merge the abnormal transaction data of the member accounts and the abnormal transaction data of the temporary accounts to obtain the abnormal transaction data of the charging piles, and construct an abnormal transaction classification model based on the abnormal transaction data of the charging piles.

[0120] In this embodiment, the abnormal transaction data of the member accounts and the abnormal transaction data of the temporary accounts are merged to form an abnormal transaction data set of the charging piles. Then, based on these abnormal transaction data, an abnormal transaction classification model is constructed. Machine learning algorithms, such as support vector machine (SVM), decision tree, or neural network, can be used to classify and predict abnormal transactions to identify possible abnormal situations in the future and take corresponding preventive measures.

[0121] By obtaining the historical transaction data of the charging pile, the system can establish a complete transaction database, which contains all the records of users using the charging pile. This provides a data basis for subsequent analysis. By extracting the characteristics of the transaction accounts, the system can conduct a more in-depth analysis of the transaction data. Classifying the transaction account data by account type can distinguish between member transaction accounts and temporary transaction accounts, which helps to adopt different analysis strategies for different types of accounts. According to different types of transaction accounts, the system can extract the historical transaction data of member accounts and temporary account historical transaction data respectively. This helps to analyze the usage patterns and behavioral differences between the two types of accounts. By performing anomaly detection on the historical transaction data of member accounts, the system can detect existing fraud, unauthorized swiping, or other abnormal situations. This helps to protect the security of member accounts and take timely measures to prevent the loss from expanding. Conducting anomaly detection on the historical transaction data of temporary accounts also helps to discover potential abnormal situations, such as malicious use, illegal charging, etc. Discovering and handling these anomalies in a timely manner can ensure the safe and stable operation of the charging pile system. Merging the abnormal transaction data of member accounts and temporary accounts can build a comprehensive abnormal transaction database. Based on these data, the system can further establish an abnormal transaction classification model, identify different types of abnormal behaviors, and provide a more accurate basis for future transaction monitoring.

[0122] Optionally, step S24 is specifically as follows:

[0123] Step S241: Extract the transaction location characteristics and transaction time series characteristics from the historical transaction data of the member account, so as to obtain the member account transaction location data and the member account transaction time series data;

[0124] In this embodiment, by extracting the transaction location characteristics from the historical transaction data of the member account, the geographical location information of the charging pile, such as longitude and latitude coordinates or geographical location descriptions, can be extracted from each transaction. At the same time, extracting the transaction time series characteristics, including transaction time, transaction frequency, etc. In this way, the transaction location data and transaction time series data of the member account can be obtained. For example, extracting the location of the charging pile and the transaction time of each transaction to construct a transaction location and time series.

[0125] Step S242: Conduct location statistical analysis on the member account transaction location data, so as to obtain high-frequency transaction location data and low-frequency transaction location data;

[0126] In this embodiment, the location statistical analysis is performed on the location data of the membership account transactions to obtain the high-frequency and low-frequency transaction location data. By statistically analyzing the occurrence frequency of each transaction location, the high-frequency and low-frequency transaction locations can be determined. For example, for the frequency statistics of the transaction locations, if the frequency of a certain location exceeds a certain threshold within a certain period of time, it is classified as a high-frequency transaction location, otherwise it is classified as a low-frequency transaction location.

[0127] Step S243: Based on the high-frequency transaction location data, divide the high-frequency transaction range to obtain the high-frequency transaction range data of the membership.

[0128] In this embodiment, based on the high-frequency transaction location data, the high-frequency transaction range is divided to obtain the high-frequency transaction range data of the membership. By methods such as clustering analysis or regional division, the high-frequency transaction locations are divided into different transaction ranges. For example, using the clustering algorithm to cluster the high-frequency transaction locations into several clusters, and each cluster represents a high-frequency transaction range.

[0129] Step S244: Calculate the spatial distance between the low-frequency transaction location data and the high-frequency transaction range of the membership to obtain the low-frequency transaction spatial distance data.

[0130] In this embodiment, the spatial distance between the low-frequency transaction location data and the high-frequency transaction range of the membership is calculated to obtain the low-frequency transaction spatial distance data. By calculating the spatial distance between the low-frequency transaction location and the high-frequency transaction range, the location distribution of the low-frequency transactions can be evaluated. For example, calculate the distance from the low-frequency transaction location to the nearest high-frequency transaction range to determine its spatial distribution.

[0131] Step S245: Evaluate the rationality of the low-frequency transactions of the membership account based on the transaction time series data of the membership account and the low-frequency transaction spatial distance data to obtain the rationality data of the low-frequency transactions of the membership account.

[0132] In this embodiment, the rationality of the low-frequency transactions of the membership account is evaluated based on the transaction time series data of the membership account and the low-frequency transaction spatial distance data to obtain the rationality data of the low-frequency transactions of the membership account. Combining the transaction time series information and the low-frequency transaction spatial distance data, the rationality of the low-frequency transactions of the membership account is evaluated. For example, analyze the time interval and location distribution of the low-frequency transactions to determine whether they conform to the normal charging behavior pattern.

[0133] Step S246: Extract the low-rationality transaction data from the historical transaction data of the membership account according to the rationality data of the low-frequency transactions of the membership account to obtain the abnormal transaction data of the membership account.

[0134] In this embodiment, low - rationality transaction data is extracted from the historical transaction data of the member account according to the low - frequency transaction rationality data of the member account, and the abnormal transaction data of the member account is obtained. According to the rationality evaluation result of the low - frequency transaction, the transaction records with unreasonable low - frequency transactions are screened out as the abnormal transaction data of the member account. For example, the transaction records with the low - frequency transaction location deviating from the normal range or the low - frequency transaction time conflicting with the high - frequency transaction range are identified.

[0135] By extracting the characteristics of the transaction location and transaction timing, the system of the present invention can deeply understand the transaction behavior patterns and habits of the member account. This helps with subsequent analysis of transaction data and anomaly detection. Through statistical analysis of the transaction location data, the system can identify high - frequency and low - frequency transaction locations. The high - frequency transaction location is the charging station that the user often goes to, while the low - frequency transaction location is the charging station that the user seldom goes to, which provides a basis for subsequent anomaly detection. Dividing the high - frequency transaction locations into high - frequency transaction ranges helps to define the transaction areas commonly used by the user. This can help the system more accurately judge the normal transaction behavior of the user, thereby reducing false alarms. By calculating the spatial distance between the low - frequency transaction location and the high - frequency transaction range, the system can evaluate the relationship between the low - frequency transaction location and the user's common locations. This can be one of the important bases for evaluating abnormal transactions. Combining the transaction timing data and the low - frequency transaction spatial distance data, the system can evaluate the rationality of the low - frequency transactions of the member account. This helps to identify abnormal transactions that do not conform to the user's behavior pattern. According to the rationality evaluation result of the low - frequency transaction, the system can extract the transaction data with low rationality, that is, potential abnormal transaction data. This provides important information for subsequent anomaly transaction detection and processing.

[0136] Optionally, step S25 is specifically as follows:

[0137] Step S251: Extract the transaction frequency characteristics and transaction amount characteristics from the historical transaction data of the temporary account, so as to obtain the transaction frequency data and transaction amount data of the temporary account;

[0138] In this embodiment, by extracting the transaction frequency characteristics from the historical transaction data of the temporary account, the average number of transactions or the transaction frequency distribution of each temporary account within a certain period can be calculated. At the same time, the transaction amount characteristics are extracted, such as calculating the amount of each transaction or counting the transaction amount distribution of each temporary account. In this way, the transaction frequency data and transaction amount data of the temporary account can be obtained. For example, the number of transactions and the total transaction amount of each temporary account in the past month are counted.

[0139] Step S252: Perform high - frequency transaction clustering calculation on the transaction frequency data of the temporary account, so as to obtain the high - frequency temporary account transaction data;

[0140] In this embodiment, when performing high-frequency trading clustering calculation on the temporary account trading frequency data, clustering algorithms such as K-means clustering or density clustering can be used to cluster temporary accounts with similar trading frequencies, so as to obtain high-frequency temporary account trading data. For example, temporary accounts with higher trading frequencies are aggregated into several clusters, and each cluster represents a high-frequency trading group.

[0141] Step S253: Calculate the trading intervals for the high-frequency temporary account trading data to obtain trading interval data, and extract low-trading-interval trading data from the high-frequency temporary account trading data based on the trading interval data, so as to obtain short-term high-frequency trading data;

[0142] In this embodiment, when calculating the trading intervals for the high-frequency temporary account trading data, the trading time intervals of each high-frequency temporary account can be calculated, and then low-trading-interval trading data is extracted from the high-frequency temporary account trading data based on the trading interval data, so as to obtain short-term high-frequency trading data. For example, high-frequency temporary account trading records with shorter trading intervals are screened out to identify cases of multiple transactions within a short period of time.

[0143] Step S254: Statistically analyze the trading amounts of the temporary account trading amount data to obtain high-amount trading amount data and low-amount trading amount data;

[0144] In this embodiment, when statistically analyzing the trading amounts of the temporary account trading amount data, the distribution of the trading amounts can be analyzed to identify high-amount and low-amount trading amounts. For example, the average trading amount of each temporary account or the quantiles of the trading amounts can be calculated to determine the thresholds for high-amount and low-amount trading amounts.

[0145] Step S255: Calculate the intersection of the trading orders for the high-amount trading amount data and the short-term high-frequency trading data to obtain the first temporary account abnormal trading data;

[0146] In this embodiment, when calculating the intersection of the trading orders for the high-amount trading amount data and the short-term high-frequency trading data, trading records with both high-amount trading amounts and short-term high-frequency trading characteristics can be found, so as to obtain the first temporary account abnormal trading data. For example, find the trading records of temporary accounts with high-amount trading amounts and multiple transactions within a short period of time.

[0147] Step S256: Calculate the intersection of the trading orders for the low-amount trading amount data and the short-term high-frequency trading data to obtain the second temporary account abnormal trading data;

[0148] In this embodiment, by calculating the intersection of trading orders for low-amount transaction data and short-term high-frequency transaction data, abnormal situations where transactions occur frequently within a short period with low transaction amounts can be identified, thereby obtaining abnormal transaction data for the second temporary account. For example, transaction records of temporary accounts with relatively low transaction amounts but frequent transactions within a short period are identified.

[0149] Step S257: Merge the abnormal transaction data of the first temporary account and the abnormal transaction data of the second temporary account to obtain abnormal transaction data for the temporary account.

[0150] In this embodiment, the abnormal transaction data of the first temporary account and the abnormal transaction data of the second temporary account are merged, that is, the two types of abnormal transaction data are integrated to obtain abnormal transaction data for the temporary account. For example, the first type and the second type of abnormal transaction data are merged into a single data set for subsequent abnormal transaction analysis and processing.

[0151] By extracting the characteristics of transaction frequency and transaction amount, the system of the present invention can understand the transaction behavior patterns and transaction amount distributions of temporary accounts. This is helpful for subsequent analysis and anomaly detection. Through clustering calculations on transaction frequency data, the system can identify high-frequency transaction behaviors of temporary accounts. These high-frequency transactions are one of the indicators of abnormal behaviors. By calculating the transaction intervals of high-frequency transaction data, the system can evaluate whether the transaction frequency of the temporary account is abnormal. This helps to identify short-term high-frequency abnormal transaction behaviors. By statistically analyzing transaction amount data, the system can understand the transaction amount distributions of temporary accounts. This can help identify high-amount and low-amount transactions. By calculating the intersection between high-amount transaction data and short-term high-frequency transaction data, the system can discover abnormal transaction situations with both high amounts and high frequencies. By calculating the intersection between low-amount transaction data and short-term high-frequency transaction data, the system can discover abnormal transactions that are low in amount but high in frequency. By merging the abnormal transaction data obtained in the first step and the second step, the system can obtain comprehensive abnormal transaction data for the temporary account, providing a basis for subsequent processing and management.

[0152] Optionally, step S3 is specifically as follows:

[0153] Step S31: Obtain charging pile transaction request data and extract transaction account characteristics from the charging pile transaction request data to obtain real-time transaction account data;

[0154] In this embodiment, real-time transaction request data is obtained through the charging pile system, including information such as the transaction initiation time, transaction amount, and transaction location. Then, transaction account characteristics are extracted from these transaction request data. For example, characteristics such as the transaction frequency, transaction amount distribution, and common transaction time of the transaction account are extracted. For example, characteristics such as the average transaction amount, transaction times, and transaction time distribution of each account are extracted from the transaction requests for subsequent transaction data analysis and anomaly detection.

[0155] Step S32: Extract account historical transaction data from the charging pile historical transaction data according to the real-time transaction account data, so as to obtain real-time account historical transaction data;

[0156] In this embodiment, according to the real-time transaction account data, historical transaction records related to the real-time account are extracted from the charging pile historical transaction data to obtain real-time account historical transaction data. This includes querying historical transaction records, screening out transaction information related to the real-time account, and integrating it into a real-time account historical transaction data set. For example, according to the real-time transaction account, the transaction records of this account are extracted from the historical transaction data.

[0157] Step S33: Merge the real-time account historical transaction data and the charging pile transaction request data to obtain real-time account transaction data;

[0158] In this embodiment, the real-time account historical transaction data is merged with the charging pile transaction request data to form real-time account transaction data. This can combine the historical behavior of the real-time transaction account with the current transaction request data to provide more comprehensive transaction information. For example, the historical transaction data of the real-time account and the current transaction request data are matched and integrated according to the account.

[0159] Step S34: Classify the real-time account transaction data through the abnormal transaction classification model. If the real-time account transaction data is classified as abnormal transaction data, the real-time account transaction data is uploaded to the charging pile transaction cloud platform to execute the stop transaction task; if the real-time account transaction data is classified as normal transaction data, the pending transaction order data is obtained.

[0160] In this embodiment, the abnormal transaction classification model is used to classify the real-time account transaction data to identify abnormal transaction behaviors. If a certain transaction is classified as an abnormal transaction, the system will upload the transaction data to the charging pile transaction cloud platform and execute the stop transaction task. If it is classified as a normal transaction, the system extracts the pending transaction order data from the real-time account transaction data. For example, machine learning models such as support vector machines (SVM) or neural networks are used to classify the real-time account transaction data to determine whether there are abnormal behaviors and perform corresponding operations according to the classification results.

[0161] By extracting the characteristics of the trading account, such as trading frequency, trading amount, trading time, etc., the system can obtain the account data of the charging pile transaction in real time, providing a basis for subsequent analysis and processing. By matching and extracting the real-time trading account data with the historical transaction data of the charging pile, the system can obtain the historical transaction records of the real-time account, which helps to analyze the trading behavior patterns and historical trends of the account. Merging the historical transaction data of the real-time account with the transaction request data of the charging pile can form a complete real-time account transaction data set, providing more comprehensive data support for subsequent anomaly detection and classification. Using the abnormal transaction classification model, the system can perform real-time monitoring and anomaly detection on the real-time account transaction data. If the transaction data is classified as an abnormal transaction, there is a risk of fraud or other security issues, and the stop trading task needs to be executed to ensure the security of the charging pile transaction; if the transaction data is classified as a normal transaction, the pending transaction order data can be processed continuously.

[0162] Optionally, step S4 is specifically as follows:

[0163] Step S41: Extract the electric energy charging amount data from the pending transaction order data to obtain the electric energy charging amount data;

[0164] In this embodiment, extracting the electric energy charging amount data from the pending transaction order data involves parsing the charging amount information in the order, usually in kilowatt-hours (kWh). For example, use corresponding data parsing tools or programming languages, such as the JSON parser in Python, to extract the charging amount information from the order data. Analyze the order data structure to determine the field name or key name containing the charging amount information. According to the field name or key name, extract the charging amount data from the order data. Format the extracted charging amount data into a unified data format, such as a numeric type (kWh).

[0165] Step S42: Extract the characteristics of the electric energy transmission charging pile from the electric energy charging amount data to obtain the electric energy transmission charging pile data;

[0166] In this embodiment, based on the electric energy charging amount data, extract the characteristics of the electric energy transmission charging pile, including information such as the power characteristics of the charging pile, charging rate, charging method (DC or AC), model and manufacturer of the charging pile. For example, according to the specified charging pile type and charging specifications in the order, extract the corresponding characteristic information.

[0167] Step S43: Extract the charging pile sensing data from the charging station sensing network according to the electric energy transmission charging pile data to obtain the charging pile sensing data;

[0168] In this embodiment, according to the data of the electric energy transmission charging pile, the charging pile sensing data including the temperature, voltage, current, etc. of the charging pile is extracted from the charging station sensing network. For example, real-time data is obtained through the sensors of the charging pile, and then parsed and processed to obtain various sensing data.

[0169] Step S44: Perform an analysis of the electric energy transmission loss based on the charging pile sensing data, so as to obtain the charging pile electric energy transmission loss data;

[0170] In this embodiment, an analysis of the electric energy transmission loss is performed based on the charging pile sensing data, which involves evaluating and analyzing the efficiency and energy transmission situation of the charging pile system to determine the loss situation of the electric energy during the transmission process. For example, by statistically analyzing the charging pile sensing data, the energy loss of the charging pile system is calculated.

[0171] Step S45: Calculate the actual electric energy charging amount based on the charging pile electric energy transmission loss data and the electric energy charging amount data, so as to obtain the actual electric energy charging amount data.

[0172] In this embodiment, the actual electric energy charging amount is calculated according to the charging pile electric energy transmission loss data and the electric energy charging amount data. This involves comparing and adjusting the actual charging amount of the charging pile with the energy loss during the transmission process to obtain the final actual charging amount data. For example, the charging amount is corrected according to the charging pile transmission loss data to obtain accurate actual electric energy charging amount data.

[0173] In the present invention, by extracting the electric energy charging amount information in the order data to be traded, the system can obtain the electric energy consumed during each charging process, providing basic data for subsequent electric energy transmission and loss analysis. By extracting features from the electric energy charging amount data, the system can analyze the charging characteristics of the charging pile, including the charging rate, charging efficiency, etc., so as to understand the performance and working state of the charging pile. By obtaining the sensing data of the charging pile, such as temperature, voltage, current, etc., the system can monitor the real-time working state of the charging pile, timely detect abnormal situations and handle them. By analyzing the charging pile sensing data, the system can calculate the loss situation of the charging pile during the electric energy transmission process, understand the energy conversion efficiency of the charging pile, and optimize and improve it. By combining the electric energy transmission loss data and the electric energy charging amount data, the system can accurately calculate the actual electric energy charging amount, provide accurate charging services for users, and optimize the use efficiency of the charging pile.

[0174] Optionally, step S44 is specifically:

[0175] Step S441: Extract the electric energy sensing data from the charging pile sensing data, so as to obtain the charging pile electric energy sensing data;

[0176] In this embodiment, data is collected from the sensors of each charging pile. These sensors usually include current sensors, voltage sensors, etc. Then, the collected data is preprocessed, including operations such as noise removal and filtering, to ensure the accuracy and reliability of the data. Next, the data is sampled using the sampling theorem and digitally processed to convert the analog signal into a digital signal. Finally, according to data processing algorithms such as power calculation formulas, the electrical energy sensing data of the charging pile is calculated, including information such as real-time current, voltage, and power.

[0177] Step S442: Analyze the topological structure of the electrical energy transmission line based on the electrical energy sensing data of the charging pile, so as to obtain the electrical energy transmission path data of the charging pile;

[0178] In this embodiment, using Geographic Information System (GIS) software such as ArcGIS or QGIS, the charging pile location data is loaded into the map, and the connection lines between the charging piles and the power transmission end are established to form an electrical energy transmission path network. Then, according to the electrical energy sensing data, the electrical energy transmission amount or power on the electrical energy transmission path between the charging piles is calculated. By analyzing the transmission amount distribution and topological structure on the transmission path, the characteristics and potential problems of the transmission path can be identified. For example, using the electrical energy sensing data of the charging pile, analyze the electrical energy transmission path and its topological structure between the charging piles. First, according to the location and connection relationship of the charging piles, construct the topological structure of the electrical energy transmission network. Then, based on the electrical energy sensing data, calculate the electrical energy transmission path between the charging piles, including relevant information such as transmission distance and transmission loss. Finally, the obtained electrical energy transmission path data of the charging pile is used for subsequent electrical energy transmission simulation and analysis.

[0179] Step S443: Calculate the electrical energy difference on the transmission path for the electrical energy sensing data of the charging pile and the electrical energy transmission path data of the charging pile, so as to obtain the line electrical energy difference data;

[0180] In this embodiment, using the electrical energy sensing data of the charging pile and the electrical energy transmission path data, calculate the electrical energy difference during the electrical energy transmission between the charging piles. First, based on the electrical energy sensing data, determine the electrical energy transmission path between the starting charging pile and the target charging pile. Then, by comparing the electrical energy transmission efficiency between the starting charging pile and the target charging pile, calculate the electrical energy difference on the electrical energy transmission path. This includes considering factors such as electrical energy loss and transmission distance. Finally, the obtained line electrical energy difference data reflects the electrical energy loss situation during the transmission process.

[0181] Step S444: Perform electrical energy transmission simulation based on the electrical energy transmission path data of the charging pile and the line electrical energy difference data, so as to obtain the electrical energy transmission simulation data;

[0182] In this embodiment, a power system simulation software, such as PSS / E or DIgSILENT, is used to establish a charging pile power transmission network model based on the charging pile power transmission path data and the line power difference data, and the transmission path data and the power difference data are imported into the model. Then, power transmission simulation is carried out to simulate the power transmission process under different conditions, including the power transmission efficiency under different transmission distances and loads. Through simulation analysis, power transmission simulation data is obtained, which is used to evaluate the performance of the power transmission system and guide system optimization.

[0183] Step S445: Conduct a statistical analysis of the power transmission simulation data to obtain the charging pile power transmission loss data.

[0184] In this embodiment, data analysis software, such as the Pandas library of Python or the R language, is used to conduct a statistical analysis of the power transmission simulation data. Calculate the total energy consumption or the energy consumption ratio on the transmission path to evaluate the loss situation during the power transmission process. Through statistical analysis, the main energy consumption sources and influencing factors can be identified, and improvement measures can be proposed to reduce the transmission loss.

[0185] By extracting the power-related information in the charging pile sensing data, such as voltage, current, temperature, etc., the system can obtain the real-time power transmission status of the charging pile, providing basic data for subsequent analysis and optimization. By analyzing the charging pile power sensing data, the system can establish the transmission line topology structure between the charging piles, understand the power transmission path and connection relationship in the charging station, providing a basis for subsequent power transmission analysis. By calculating the power difference on the transmission path between the charging piles, the system can evaluate the loss situation of the power during the transmission process, identify potential energy loss points, and provide a reference basis for optimizing the power transmission. By simulating the power transmission process between the charging piles, the system can predict the power loss situation under different transmission paths, evaluate the transmission efficiency of different schemes, and provide optimization suggestions. By statistically analyzing the loss situation in the power transmission simulation data, the system can quantify the energy loss in each link, identify the factors causing the energy loss, and provide guidance for improving the power transmission system.

[0186] Optionally, step S5 is specifically as follows:

[0187] Step S51: Obtain the charging pile power cost data;

[0188] In this embodiment, the electricity cost data of the charging pile is obtained by cooperating with an electricity supplier or using a third-party electricity metering device. A common method is to install an intelligent electricity meter, which can monitor the electricity consumption of the charging pile in real time and generate electricity cost data. For example, an electricity meter that meets international standards, such as Siemens SENTRON PAC3200, can be selected, which has high precision and reliability. By installing such a device, the electricity cost data of the charging pile can be accurately obtained, providing an accurate basis for subsequent electricity cost calculation.

[0189] Step S52: Based on the electricity cost data of the charging pile, calculate the electricity costs for the actual electricity charging amount data and the electricity transmission loss data of the charging pile respectively, so as to obtain the actual electricity cost data and the transmission loss cost data;

[0190] In this embodiment, using the obtained electricity cost data of the charging pile, combined with the actual electricity charging amount data and the transmission loss data, the electricity cost is calculated. For example, a simple rate model can be used to convert the actual electricity consumption of the charging pile into actual electricity cost data according to the electricity rate. At the same time, according to the transmission loss data and relevant rate regulations, the transmission loss cost data during the electricity transmission process of the charging pile can also be calculated. In this way, the actual electricity cost data and the transmission loss cost data can be obtained respectively for subsequent correction of the electricity trading order.

[0191] Step S53: Based on the actual electricity cost data, correct the electricity cost of the order to be traded, so as to obtain the corrected data of the electricity trading order;

[0192] In this embodiment, using the actual electricity cost data, the electricity cost of the order to be traded can be corrected. For example, for a charging order, according to information such as the charging period and charging power, the calculated electricity cost in the order can be compared and corrected using the actual electricity cost data, and the corrected data of the electricity trading order is generated. In this way, it can be ensured that the electricity cost in the trading order is consistent with the actual consumption, improving the accuracy and reliability of the transaction.

[0193] Step S54: Based on the transmission loss cost data, correct the transmission loss cost of the corrected data of the electricity trading order, so as to obtain the corrected data of the order to be traded, and upload it to the charging pile trading cloud platform to execute the collection task.

[0194] In this embodiment, the transmission loss cost data is used to correct the transmission loss cost of the electric energy trading order correction data. For example, according to the transmission loss data and relevant rate regulations, the transmission loss cost during the electric energy transmission in the order can be calculated and added to the trading order to generate the to-be-traded order correction data. Then, these corrected order data are uploaded to the charging pile trading cloud platform to perform the collection task. In this way, it can be ensured that the impact of transmission loss is considered during the electric energy trading process, guaranteeing the fairness and accuracy of the transaction.

[0195] By obtaining the electric energy cost data of the charging pile, the system can understand the actual cost of the charging service, providing basic data for subsequent electric energy cost calculation and correction of trading orders. By combining the actual electric energy charging volume data with the electric energy transmission loss data of the charging pile, the system can accurately calculate the actual consumed electric energy cost and the cost generated by transmission loss, providing an accurate cost basis for electric energy trading. By correcting the to-be-traded order data according to the actual electric energy cost data, the system can ensure that the electric energy cost involved in the trading order is consistent with the actual situation, guaranteeing the fairness and accuracy of electric energy trading. By considering the cost generated by transmission loss, the system can further correct the electric energy trading order correction data to ensure that the transmission loss cost in electric energy trading is reasonably calculated and charged, guaranteeing the fairness and transparency of the transaction. When uploading the to-be-traded order correction data to the charging pile trading cloud platform to perform the collection task, it is conducive to the openness and transparency of trading information. Users can query their trading orders and cost details at any time, ensuring the openness and accessibility of information. This process ensures the fairness, accuracy, and transparency of electric energy trading by precisely calculating the electric energy cost and transmission loss cost and correcting the trading order, improving the quality of charging services and user satisfaction.

[0196] Optionally, this specification also provides a cloud computing-based charging pile digital trading system for executing the cloud computing-based charging pile digital trading method as described above. The cloud computing-based charging pile digital trading system includes:

[0197] A sensing network construction module, configured to obtain the sensing data of the charging station and construct a sensing network for the charging station based on the sensing data of the charging station, thereby obtaining a sensing network for the charging station;

[0198] An abnormal transaction detection module, configured to obtain the historical transaction data of the charging pile, perform abnormal transaction detection based on the historical transaction data of the charging pile, thereby obtaining the abnormal transaction data of the charging pile, and constructing an abnormal transaction classification model according to the abnormal transaction data of the charging pile;

[0199] An abnormal transaction classification module, configured to obtain the charging pile transaction request data and perform abnormal transaction classification on the charging pile transaction request data through the abnormal transaction classification model, thereby obtaining the to-be-traded order data;

[0200] A transmission loss analysis module is configured to extract power charging amount data from the to-be-transacted order data, so as to obtain the power charging amount data, and perform power transmission loss analysis of the charging piles on the power charging amount data based on the charging station sensing network, so as to obtain the actual power charging amount data and the power transmission loss data of the charging piles;

[0201] A transaction amount correction module is configured to correct the order transaction amount of the to-be-transacted order data based on the actual power charging amount data and the power transmission loss data of the charging piles, so as to obtain the to-be-transacted order correction data, and upload the to-be-transacted order correction data to the charging pile transaction cloud platform to perform the collection task.

[0202] The cloud computing-based charging pile digital trading system of the present invention can implement any cloud computing-based charging pile digital trading method of the present invention, and is used as a medium for coordinating the operations and signal transmissions between various modules to complete the cloud computing-based charging pile digital trading method. The internal modules of the system cooperate with each other, thereby improving the security of digital payment and the accuracy of power trading.

[0203] Therefore, from any perspective, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the application document are intended to be encompassed within the present invention.

[0204] The above are only specific embodiments of the present invention, which enable those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art. The general principles defined herein can 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 these embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A charging pile digital transaction method based on cloud computing, characterized in that: The following steps are involved: Step S1: acquiring charging station sensor data, and constructing a charging station sensor network based on the charging station sensor data, thereby obtaining a charging station sensor network; Step S2: Acquire historical transaction data of charging piles, perform abnormal transaction detection based on the historical transaction data of charging piles, thereby obtaining abnormal transaction data of charging piles, and construct an abnormal transaction classification model based on the abnormal transaction data of charging piles; Step S3: Acquire charging pile transaction request data, and classify the charging pile transaction request data into abnormal transactions through an abnormal transaction classification model, thereby obtaining pending transaction order data; Step S4: extracting electric energy charging data from the transaction order data to obtain electric energy charging data, and performing charging pile electric energy transmission loss analysis on the electric energy charging data based on the charging station sensor network to obtain actual electric energy charging data and charging pile electric energy transmission loss data; Step S5: Based on the actual electric energy charging amount data and the charging pile electric energy transmission loss data, the order transaction amount is corrected for the order data to be traded, so as to obtain the corrected data of the order to be traded, and upload it to the charging pile transaction cloud platform to execute the collection task.

2. The charging pile digital transaction method based on cloud computing according to claim 1 is characterized in that: Step S1 is specifically as follows: Step S11: acquiring charging station sensor data, and performing environmental sensor feature extraction and electric energy sensor feature extraction on the charging station sensor data, thereby obtaining charging station environmental sensor data and charging station electric energy sensor data; Step S12: extracting a camera image of the charging station based on the environmental sensor data of the charging station, thereby obtaining a camera image of the charging station; Step S13: constructing a three-dimensional coordinate system based on the camera image of the charging station, thereby obtaining a three-dimensional coordinate system of the charging station; Step S14: performing environmental sensing data fusion on the three-dimensional coordinate system of the charging station based on the environmental sensing data of the charging station, thereby obtaining an environmental sensing network of the charging station; Step S15: Performing power sensing space mapping on the charging station environment sensor network according to the charging station power sensing data, thereby obtaining the charging station sensor network.

3. The charging pile digital transaction method based on cloud computing according to claim 1 is characterized in that: Step S2 is specifically as follows: Step S21: Obtain charging pile historical transaction data; Step S22: extracting transaction account features from the historical transaction data of the charging piles to obtain transaction account data, and classifying the transaction account data by account type to obtain member transaction account data and temporary transaction account data; Step S23: extracting transaction data from the charging pile historical transaction data according to the member transaction account data and the temporary transaction account data, thereby obtaining the member account historical transaction data and the temporary account historical transaction data; Step S24: performing abnormal transaction detection on the member account historical transaction data, thereby obtaining abnormal transaction data of the member account; Step S25: Perform temporary account abnormal transaction detection on the temporary account historical transaction data, thereby obtaining temporary account abnormal transaction data; Step S26: Merge the member account abnormal transaction data and the temporary account abnormal transaction data to obtain the charging pile abnormal transaction data, and build an abnormal transaction classification model based on the charging pile abnormal transaction data.

4. The charging pile digital transaction method based on cloud computing according to claim 3 is characterized in that: Step S24 is specifically as follows: Step S241: extracting transaction location features and transaction time series features from historical transaction data of member accounts, thereby obtaining member account transaction location data and member account transaction time series data; Step S242: performing location statistics analysis on the member account transaction location data, thereby obtaining high-frequency transaction location data and low-frequency transaction location data; Step S243: dividing the high-frequency trading range based on the high-frequency trading location data, thereby obtaining the member's high-frequency trading range data; Step S244: performing spatial distance calculation on the low-frequency transaction location data and the member's high-frequency transaction range, thereby obtaining low-frequency transaction spatial distance data; Step S245: evaluating the rationality of low-frequency transactions of member accounts on the member account transaction time series data and the low-frequency transaction space distance data, thereby obtaining rationality data of low-frequency transactions of member accounts; Step S246: extract low-rationality transaction data from the historical transaction data of the member account according to the low-frequency transaction rationality data of the member account, thereby obtaining abnormal transaction data of the member account.

5. The charging pile digital transaction method based on cloud computing according to claim 3 is characterized in that: Step S25 is specifically as follows: Step S251: extracting transaction frequency features and transaction amount features from the temporary account historical transaction data, thereby obtaining temporary account transaction frequency data and temporary account transaction amount data; Step S252: performing high-frequency transaction clustering calculation on the temporary account transaction frequency data, thereby obtaining high-frequency temporary account transaction data; Step S253: Calculate the transaction interval of the high-frequency temporary account transaction data to obtain transaction interval data, and extract low transaction interval transaction data from the high-frequency temporary account transaction data according to the transaction interval data to obtain short-term high-frequency transaction data; Step S254: performing transaction amount statistics on the temporary account transaction amount data, thereby obtaining high transaction amount data and low transaction amount data; Step S255: performing transaction order intersection calculation on the high-value transaction amount data and the short-term high-frequency transaction data, thereby obtaining abnormal transaction data of the first temporary account; Step S256: performing transaction order intersection calculation on the low transaction amount data and the short-term high-frequency transaction data, thereby obtaining abnormal transaction data of the second temporary account; Step S257: Merging the abnormal transaction data of the first temporary account and the abnormal transaction data of the second temporary account to obtain the abnormal transaction data of the temporary account.

6. The charging pile digital transaction method based on cloud computing according to claim 1 is characterized in that: Step S3 is specifically as follows: Step S31: acquiring charging pile transaction request data, and extracting transaction account features from the charging pile transaction request data, thereby obtaining real-time transaction account data; Step S32: extracting the historical transaction data of the charging pile according to the real-time transaction account data, thereby obtaining the real-time historical transaction data of the account; Step S33: merging the real-time account historical transaction data and the charging pile transaction request data to obtain the real-time account transaction data; Step S34: classifying the real-time account transaction data as abnormal transactions through the abnormal transaction classification model. If the real-time account transaction data is classified as abnormal transaction data, the real-time account transaction data is uploaded to the charging pile transaction cloud platform to execute the transaction stop task; If the real-time account transaction data is classified as normal transaction data, the pending transaction order data is obtained.

7. The charging pile digital transaction method based on cloud computing according to claim 1 is characterized in that: Step S4 is specifically as follows: Step S41: extracting electric energy charging amount data from the transaction order data to obtain electric energy charging amount data; Step S42: extracting the characteristics of the power transmission charging pile from the power charging amount data, thereby obtaining the power transmission charging pile data; Step S43: extracting charging pile sensor data from the charging station sensor network according to the power transmission charging pile data, thereby obtaining the charging pile sensor data; Step S44: performing power transmission loss analysis based on the charging pile sensor data, thereby obtaining charging pile power transmission loss data; Step S45: Calculate the actual electric energy charging amount based on the electric energy transmission loss data of the charging pile and the electric energy charging amount data, so as to obtain the actual electric energy charging amount data.

8. The charging pile digital transaction method based on cloud computing according to claim 7 is characterized in that: Step S44 is specifically as follows: Step S441: extracting electric energy sensor data from the charging pile sensor data, thereby obtaining the charging pile electric energy sensor data; Step S442: performing a power transmission line topology analysis based on the charging pile power sensor data, thereby obtaining the charging pile power transmission path data; Step S443: Calculating the transmission path power difference of the charging pile power sensor data and the charging pile power transmission path data, thereby obtaining line power difference data; Step S444: performing power transmission simulation based on the charging pile power transmission path data and the line power difference data, thereby obtaining power transmission simulation data; Step S445: Perform transmission loss statistics on the power transmission simulation data to obtain charging pile power transmission loss data.

9. The charging pile digital transaction method based on cloud computing according to claim 1 is characterized in that: Step S5 is specifically as follows: Step S51: Obtain charging pile electricity cost data; Step S52: Calculating the electric energy cost of the actual electric energy charging amount data and the electric energy transmission loss data of the charging pile based on the electric energy cost data of the charging pile, thereby obtaining the actual electric energy cost data and the transmission loss cost data; Step S53: Correcting the transaction order data for electricity costs based on the actual electricity cost data, thereby obtaining electricity transaction order correction data; Step S54: Perform transmission loss cost correction on the electric energy transaction order correction data based on the transmission loss cost data, thereby obtaining the correction data of the order to be traded, and upload it to the charging pile transaction cloud platform to execute the collection task.

10. A charging pile digital transaction system based on cloud computing, characterized in that: For executing the charging pile digital transaction method based on cloud computing as claimed in claim 1, the charging pile digital transaction system based on cloud computing comprises: A sensor network construction module is used to obtain sensor data of the charging station and construct a sensor network of the charging station based on the sensor data of the charging station, thereby obtaining a sensor network of the charging station; The abnormal transaction detection module is used to obtain the historical transaction data of the charging pile, perform abnormal transaction detection based on the historical transaction data of the charging pile, thereby obtaining the abnormal transaction data of the charging pile, and construct an abnormal transaction classification model based on the abnormal transaction data of the charging pile; The abnormal transaction classification module is used to obtain charging pile transaction request data and classify the charging pile transaction request data into abnormal transactions through an abnormal transaction classification model, thereby obtaining pending transaction order data; The transmission loss analysis module is used to extract the electric energy charging data from the transaction order data to obtain the electric energy charging data, and to analyze the electric energy transmission loss of the charging pile based on the charging station sensor network to obtain the actual electric energy charging data and the electric energy transmission loss data of the charging pile; The transaction amount correction module is used to correct the order transaction amount of the pending transaction order data based on the actual electric energy charging amount data and the charging pile electric energy transmission loss data, so as to obtain the pending transaction order correction data and upload it to the charging pile transaction cloud platform to execute the collection task.

Images