Intelligent battery swap station data access management system and method

Abstract

The invention discloses an intelligent battery swap station data access management system and method. The method comprises the steps of obtaining target battery swap station operation data of different devices and sensors in a target battery swap station, and storing the target battery swap station operation data in real time, the operation data of the target battery swap station at least comprises electrical parameters, equipment states and environment information of different equipment and sensors; noise reduction processing is carried out on the real-time target battery swap station operation data, and format conversion is carried out on the real-time target battery swap station operation data after noise reduction processing; and inputting the data after format conversion into a target battery swap station application system to complete intelligent battery swap station data access management. Through the application of the invention, real-time monitoring, intelligent analysis and accurate prediction of the operation data of the battery swap station can be realized, and an important guarantee is provided for efficient operation and maintenance of the battery swap station.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent battery swap station data access management, and in particular to an intelligent battery swap station data access management system and method. Background Art

[0002] As the penetration rate of electric vehicles increases rapidly, battery swap stations generate a large amount of data in real time. It is becoming increasingly important to effectively collect, process and load this data to provide data analysis support for the development of battery swap station business. An intelligent data access management system for battery swap stations can efficiently and timely collect, process and transmit data to support subsequent data analysis applications, thereby helping managers to understand the operating status of battery swap stations in a timely manner, discover potential fault hazards, and take measures to resolve them. This helps optimize the operation strategy of battery swap stations, improve battery swap efficiency, and reduce operating costs. In addition, the data access management system can uniformly manage various data generated by battery swap stations, avoid data islands, and improve data utilization.

[0003] However, some battery swap station data access management systems on the market have deficiencies in data collection, data cleaning, data correction, and data loading. For example, the data collection efficiency is low and cannot meet the needs of real-time data collection, resulting in data delay and loss. The data cleaning results are inaccurate, and important data is omitted or deleted by mistake during the data cleaning process. The data correction efficiency is low and cannot meet the needs of large-scale data correction. The data loading quality is not high, and data loss and errors occur during the data loading process. This results in the interweaving of multiple problems, affecting subsequent data analysis applications. Summary of the invention

[0004] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0005] In view of the above existing problems, the present invention is proposed.

[0006] Therefore, the present invention provides an intelligent battery swap station data access management system and method, which can solve the problems mentioned in the background technology.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0008] In a first aspect, the present invention provides an intelligent battery swap station data access management system, comprising:

[0009] Real-time data acquisition and storage module, data noise reduction processing module, data transformation and loading module;

[0010] The real-time data acquisition and storage module is used to obtain the target battery swap station operation data of different devices and sensors in the target battery swap station using an improved edge computing method, and store the target battery swap station operation data in real time, wherein the target battery swap station operation data at least includes electrical parameters, device status and environmental information of different devices and sensors;

[0011] The data noise reduction processing module is used to perform noise reduction processing on the real-time target battery swap station operation data stored in the real-time data acquisition and storage module, and transmit the real-time target battery swap station operation data after noise reduction processing to the data conversion and loading module in real time, and the noise reduction processing includes data cleaning and data correction;

[0012] The data conversion and loading module is used to convert the format of the data after the noise reduction processing by the data noise reduction processing module, and input the format-converted data into the target battery swap station application system.

[0013] As a preferred solution of the intelligent battery swap station data access management system described in the present invention, the real-time data acquisition and storage module includes: a real-time data acquisition unit and a real-time data storage unit;

[0014] The real-time data acquisition unit includes a plurality of sensor interfaces for connecting and acquiring real-time data signals from different devices and sensors;

[0015] The real-time data acquisition unit applies an improved edge computing method for efficient data acquisition. The process of improving edge computing for real-time data acquisition includes calculating a cross entropy value, determining a mean square error, determining the number of hidden nodes, and building a real-time data acquisition model.

[0016] As a preferred solution of the intelligent battery swap station data access management system described in the present invention, the real-time data acquisition and storage module also includes:

[0017] The real-time data storage unit is used to store the target battery swap station operation data collected by the real-time data collection unit. The real-time data storage unit includes multiple distributed storage nodes, which are connected via a high-speed network to ensure real-time synchronization and backup of data. Each node has independent processing capabilities and storage space, and processes and stores data in parallel. By replicating data between different nodes, the system can still ensure the integrity and continuity of the data even if some nodes fail. The real-time data storage unit also supports data version management and historical record query functions, and also integrates encryption and access control mechanisms.

[0018] As a preferred solution of the intelligent battery swap station data access management system described in the present invention, the data noise reduction processing module includes: a data cleaning unit and a data correction unit;

[0019] The data cleaning unit includes using an improved recurrent neural network to perform data cleaning for identifying and eliminating outliers and noise in the target battery swap station operating data; the improved recurrent neural network performs data cleaning including preliminary cleaning of the original target battery swap station operating data from the real-time data acquisition and storage module, and the preliminary cleaning includes removing duplicate data points, processing missing values, and performing outlier detection and processing; selecting features with an amount of information greater than a first information amount threshold and a correlation greater than a first correlation threshold, defining a loss function of the improved recurrent neural network model, obtaining input data sets and output data sets before and after cleaning, and transmitting the cleaned data to the data correction unit.

[0020] As a preferred solution of the intelligent battery swap station data access management system described in the present invention, the data noise reduction processing module also includes:

[0021] The data correction unit receives the cleaned data from the data cleaning unit, and performs missing value filling and error correction in combination with the improved generative adversarial network, and transmits the data after missing value filling and error correction to the data transformation and loading module.

[0022] As a preferred solution of the intelligent battery swap station data access management system of the present invention, the data conversion and loading module includes:

[0023] Data conversion unit and data loading unit; the data conversion unit is used to convert the target battery swap station operation data transmitted to by the data noise reduction processing module in combination with the improved knowledge graph technology for format conversion, including but not limited to converting the data from the original format to a standard format suitable for the target battery swap station application system.

[0024] As a preferred solution of the intelligent battery swap station data access management system of the present invention, the data conversion and loading module further includes:

[0025] The data loading unit includes a data caching mechanism, which is used to temporarily store the converted data after the data transformation unit completes the format conversion. The caching mechanism is designed using improved distributed publish-subscribe technology to ensure that the data can be received and processed by the target battery swap station application system at the fastest speed. The data loading unit also has an intelligent scheduling function, which can dynamically adjust the priority and rate of data transmission according to the real-time needs of the target battery swap station application system to ensure the real-time and accuracy of key data.

[0026] In a second aspect, the present invention provides a data access management method for an intelligent battery swap station, the method comprising:

[0027] Obtain target battery swap station operation data of different devices and sensors in the target battery swap station, and store the target battery swap station operation data in real time, wherein the target battery swap station operation data at least includes electrical parameters, device status, and environmental information of different devices and sensors;

[0028] Perform noise reduction processing on the real-time target battery swap station operation data, and convert the format of the real-time target battery swap station operation data after the noise reduction processing;

[0029] Input the format-converted data into the target battery swap station application system to complete the intelligent battery swap station data access management.

[0030] In a third aspect, the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned method when executing the computer program.

[0031] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the method described above when executed by a processor.

[0032] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention proposes an intelligent data access management system and method for battery swap stations, obtains target battery swap station operation data of different devices and sensors in the target battery swap station, and stores the target battery swap station operation data in real time, wherein the target battery swap station operation data at least includes electrical parameters, equipment status and environmental information of different devices and sensors; performs noise reduction processing on the real-time target battery swap station operation data, and performs format conversion on the real-time target battery swap station operation data after noise reduction processing; inputs the format-converted data into the target battery swap station application system to complete the intelligent battery swap station data access management. By applying improved edge computing technology, the present invention can realize efficient real-time collection of battery swap station operation data, significantly reduce data transmission delay, and improve the response speed and reliability of the system. Improved application of recurrent neural networks and generative adversarial networks in data cleaning and correction ensures the accuracy and integrity of data, thereby providing solid data support for the efficient operation of battery swap stations. In addition, by improving the knowledge graph technology for data format conversion, the data can better adapt to the needs of the target battery swap station application system, and improve the availability and interoperability of the data. The application of improved distributed publish-subscribe technology in the data caching mechanism ensures the high efficiency and real-time performance of data transmission, enabling the target battery swap station application system to obtain the required data in a timely and accurate manner, further improving the intelligent management level of the battery swap station.

[0033] In summary, the intelligent data access management system and method of the battery swap station of the present invention not only improves the efficiency of data collection and processing, but also enhances the stability and reliability of the system, providing strong technical support for the intelligent upgrade of the battery swap station. Through the application of the present invention, real-time monitoring, intelligent analysis and accurate prediction of the operation data of the battery swap station can be realized, providing important guarantee for the efficient operation and maintenance of the battery swap station. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0035] Figure 1 A method flow chart of an intelligent battery swap station data access management system and method provided by an embodiment of the present invention;

[0036] Figure 2 An internal structural diagram of a computer device for an intelligent battery swap station data access management system and method provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0037] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0038] Example 1

[0039] Reference Figure 1-Figure 2 , which is the first embodiment of the present invention, and provides an intelligent data access management system and method for battery swap stations, including:

[0040] Before describing the embodiments of the present application in detail, some related concepts are first explained for the sake of clarity.

[0041] Intelligent battery swap station: Intelligent battery swap station is a facility that integrates automation and intelligent technology for the rapid replacement of electric vehicle batteries. It can achieve unattended operation and efficiently and safely complete the removal and installation of batteries through automated equipment such as robotic arms. Intelligent battery swap stations can significantly shorten the time vehicles stay for battery replacement and improve the convenience of electric vehicle use.

[0042] Edge computing: Edge computing is a distributed computing architecture whose main idea is to deploy computing power at the edge of the network, where the data is generated. The purpose of this is to reduce the delay of data transmission, improve response speed, and reduce the load on the core network.

[0043] Distributed publish-subscribe technology: Distributed publish-subscribe technology is a messaging model in which the sender (publisher) and receiver (subscriber) of the message do not communicate directly. The publisher sends the message to a specific topic, and the subscriber subscribes to the topic of interest to receive the message.

[0044] Knowledge graph technology: Knowledge graph is a structured knowledge representation used to describe the relationship between entities. It usually stores information in the form of a graph database, with entities as nodes and the relationship between entities as edges.

[0045] There are some problems in the related technologies, such as low data collection efficiency, large data processing delay, slow system response speed and insufficient data accuracy, etc. These problems limit the intelligent upgrade and efficient operation of battery swap stations.

[0046] The present application provides a method that can effectively solve the above-mentioned problems. Next, multiple embodiments will be combined to explain in detail how to implement the intelligent battery swap station data access management system, as follows;

[0047] Specifically, the intelligent battery swap station data access management system includes a real-time data acquisition and storage module, a data noise reduction processing module, and a data transformation and loading module;

[0048] In the embodiment of the present application, the real-time data acquisition and storage module is used to use the improved edge computing method to obtain the target battery swap station operation data of different devices and sensors in the target battery swap station, and store the target battery swap station operation data in real time. The target battery swap station operation data at least includes electrical parameters, device status and environmental information of different devices and sensors;

[0049] The data noise reduction processing module is used to perform noise reduction processing on the real-time target battery swap station operation data stored in the real-time data acquisition and storage module, and transmit the real-time target battery swap station operation data after noise reduction processing to the data conversion and loading module in real time. The noise reduction processing includes data cleaning and data correction;

[0050] The data conversion and loading module is used to convert the format of the data after noise reduction processing by the data noise reduction processing module, and input the format-converted data into the target battery swap station application system.

[0051] In the embodiment of the present application, the real-time data acquisition and storage module includes: a real-time data acquisition unit and a real-time data storage unit;

[0052] The real-time data acquisition unit includes multiple sensor interfaces for connecting and collecting real-time data signals from different devices and sensors;

[0053] The real-time data collection unit applies an improved edge computing method for efficient data collection. The process of improving edge computing for real-time data collection includes calculating the cross entropy value, determining the mean square error, determining the number of hidden nodes, and building a real-time data collection model.

[0054] In the embodiment of the present application, in the real-time data acquisition unit, the improved edge computing method can be specifically implemented as follows:

[0055] The Min-Max normalization method is used to scale the data to the range of [0, 1]. For a given data x i , its standardized value x′ i It can be expressed as:

[0056]

[0057] Among them, min(X) and max(X) are the minimum and maximum values ​​of all data respectively;

[0058] It should be noted that the given data refers to the real-time data signals collected from different devices and sensors in the battery swap station. These data signals may include electrical parameters, equipment status, and environmental information. i It can be the numerical value of various physical quantities measured by the sensor, such as voltage, current, temperature, humidity, etc.

[0059] Furthermore, feature extraction can be performed. Feature extraction can be achieved through a variety of methods. Here, Fourier transform is used as an example. For time series data x(t), its discrete Fourier transform (DFT) can be expressed as:

[0060]

[0061] Where N is the number of data points and k is the frequency index.

[0062] Furthermore, we train the model and initialize the model parameters:

[0063] Initialization of the weight matrix W and bias term b:

[0064] or

[0065] b=0

[0066] where σ 2 is the variance, and n is the number of input nodes.

[0067] Using improved cross entropy or improved mean square error as the loss function, the improved cross entropy or improved mean square error is expressed as follows:

[0068] For classification tasks, the improved cross entropy loss function can be expressed as:

[0069]

[0070] Among them, w i is the weight factor for the i-th category, which can be adjusted according to the importance or uncertainty of the category. R(W) is the regularization term of the weight matrix W, such as L2 regularization, Used to prevent overfitting. λ is the coefficient of the regularization term, which is used to balance the trade-off between the loss function and the regularization term.

[0071] For regression tasks, the improved mean square error can be expressed as a loss function:

[0072]

[0073] Among them, w i is the weight factor of the i-th sample, which can be adjusted according to the importance of the sample. R(W) and λ are the same as above.

[0074] Furthermore, the number of hidden layer nodes is adjusted. The adjustment of the number of hidden layer nodes can be determined by experiments or grid search, which is represented as H here.

[0075] Furthermore, the back propagation algorithm is used to minimize the loss function.

[0076] The back-propagation algorithm is used to update the model parameters to minimize the loss function. The parameter update can be expressed as follows:

[0077] Update the weight matrix W and bias term b:

[0078]

[0079] Among them, α is the learning rate, and are the gradients of the loss function with respect to the weight matrix and the bias term, respectively.

[0080] Furthermore, the trained model is deployed on the edge device. The deployment of the model can be expressed as loading the trained model parameters W and b onto the edge device. When new data arrives, the model predicts or classifies it. For a given new data x′, the output of the model can be expressed as:

[0081]

[0082] Among them, f is the forward propagation function of the model.

[0083] Make decisions based on the model output. Actions can be taken accordingly, such as triggering an alarm or carrying out further data processing.

[0084] In an optional embodiment, three thresholds T are set normal , T warning and T critical ,

[0085] Normal range: If the model output is within the normal range (for example, below a certain threshold T normal ), then everything is considered normal and no special measures are needed.

[0086] Warning range: If the model output is outside the normal range but still within the warning range (for example, at T warning and T critical If the error is between 2 and 3 times), a warning is triggered to notify relevant personnel to check.

[0087] Emergency Range: If the model output exceeds the warning range (for example, above T critionl ), an emergency alert is triggered and immediate action is required.

[0088] For example, assuming that the model output is a numerical value, which represents the health index of the device, the lower the index, the healthier the device. Three thresholds 1, 2 and 3 can be defined;

[0089] If the model output y<1, the device is considered healthy and no special measures are needed.

[0090] If 1≤y<2, a warning is triggered to notify relevant personnel to pay attention.

[0091] If 2≤y<3, an emergency warning is triggered and further inspection is required.

[0092] If y ≥ 3, the emergency stop operation is triggered immediately.

[0093] It should be noted that the real-time data acquisition unit can detect abnormal conditions of the equipment in a timely manner, thereby avoiding potential failures and losses. Through edge computing methods, data is processed and analyzed locally, reducing dependence on central servers, reducing latency, and improving response speed. In addition, the computing power of edge devices makes data processing more efficient, and can monitor the status of equipment in real time to ensure that the equipment is running in the best condition.

[0094] In the embodiment of the present application, the real-time data acquisition and storage module also includes:

[0095] The real-time data storage unit is used to store the target battery swap station operation data collected from the real-time data acquisition unit. The real-time data storage unit includes multiple distributed storage nodes, which are connected via a high-speed network to ensure real-time synchronization and backup of data. Each node has independent processing capabilities and storage space, and processes and stores data in parallel. By replicating data between different nodes, the system can still ensure data integrity and continuity even if some nodes fail. The real-time data storage unit also supports data version management and historical record query functions, and also integrates encryption and access control mechanisms.

[0096] In the embodiment of the present application, assuming that the original data set is D, it is to be divided into k slices, the size of each slice is D / k, and the slices can be represented by the following method:

[0097]

[0098] Among them, S i Represents the i-th shard.

[0099] For example, the processing capacity of each node can be represented by the number of CPU cores C and the memory capacity M, and the storage space can be represented by the disk size D. The data D can be divided into k shards, and the size of each shard is D / k s , each shard has n copies, where n is usually greater than 1.

[0100] Use the consistent hashing algorithm to determine on which node the data shard is stored. Use the Paxos protocol to achieve strong data consistency. The consistent hashing algorithm H can be used to determine on which node the data shard is stored as follows:

[0101] N i =H(S i )

[0102] Where N i Indicates the node where the i-th shard should be stored.

[0103] Assign a version number to each updated data. Version control can be represented by the version number V. The data of each version can be represented as:

[0104] D v =update(D,V)

[0105] Among them, D v Represents the vth version of data, and update represents the update operation.

[0106] Encrypt the data using encryption algorithm E, where E can be AES, RSA, etc. Define permission levels P to ensure that only authorized users can access the data.

[0107] The encryption algorithm E can be expressed as:

[0108] E(D,K)=C

[0109] Where D is the plaintext data, K is the encryption key, and C is the encrypted ciphertext data.

[0110] In the embodiment of the present application, the data noise reduction processing module includes: a data cleaning unit and a data correction unit;

[0111] The data cleaning unit includes using an improved recurrent neural network to perform data cleaning for identifying and removing outliers and noise in the target battery swap station operating data; the improved recurrent neural network for data cleaning includes preliminary cleaning of the original target battery swap station operating data from the real-time data acquisition and storage module (that is, the encrypted data in the storage module needs to be decrypted before processing, and the decryption operation corresponds to the encryption), and the preliminary cleaning includes removing duplicate data points, processing missing values, and performing outlier detection and processing; selecting features with an amount of information greater than a first information amount threshold and a correlation greater than a first correlation threshold, defining the loss function of the improved recurrent neural network model, obtaining the input data set and output data set before and after cleaning, and transmitting the cleaned data to the data correction unit.

[0112] In the embodiment of the present application, the encrypted data C is decrypted using the corresponding decryption algorithm D and the decryption key K to obtain the original data X:

[0113] X=D(C,K)

[0114] Furthermore, the decrypted data X is initially cleaned to remove duplicate data points: duplicate data points are identified and removed by comparing the similarity of adjacent data points. A hash table or set can be used to store the data points that have appeared, and if duplicates are found, they are removed from the data set.

[0115] X′=remove_duplicates(X);

[0116] Furthermore, an interpolation method (such as linear interpolation, polynomial interpolation or model-based method) is used to fill the missing values: X″=impute_missing_values(X′);

[0117] Going a step further, outliers can be identified using statistical methods (e.g., Z-score, IQR) or machine learning models (e.g., Isolation Forest).

[0118] X″′=detect_outliers(X″)

[0119] Furthermore, the amount of information is greater than the first information amount threshold I tThe correlation is greater than the first correlation threshold C t Features:

[0120] Information content: Use metrics such as entropy or mutual information to evaluate the information content of a feature.

[0121] I(F i )=information(F i )

[0122] Correlation: Assess the correlation of features using metrics such as Pearson's correlation coefficient or Spearman's rank correlation coefficient.

[0123] C(F i ,Y)=correlation(F i ,Y)

[0124] Select the feature set F that meets the conditions selected :

[0125] F selected ={F i |I(F i )>I t ∧C(F i ,Y)>C t}

[0126] Furthermore, an improved recurrent neural network model is constructed, and the improved recurrent neural network model M and the loss function L are defined: the improved recurrent neural network model M is defined, including an input layer, a hidden layer and an output layer.

[0127] M=define_model(input size ,hidden size ,output size )

[0128] Define the loss function L, which can be the improved cross entropy loss (for classification tasks) or the improved mean square error loss (for regression tasks) mentioned above.

[0129]

[0130] in, is the predicted value of the model and Y is the true label.

[0131] Use the improved recurrent neural network model M to train the data.

[0132] M=train_model(M,X″′,Y,L,epochs)

[0133] Data cleaning uses the trained model M to clean the data and form a data set before and after cleaning. The data set is formed using the data X″′ before cleaning and the label Y.

[0134] D before =(X″′,Y)

[0135] Use the trained model M to predict the data X″′, and use the prediction results as the cleaned data.

[0136] X″″=M(X″′)

[0137] Finally, the cleaned data set is formed:

[0138] D after =(X″″,Y).

[0139] In the embodiment of the present application, the data noise reduction processing module also includes:

[0140] The data correction unit receives the cleaned data from the data cleaning unit, and performs missing value filling and error correction in combination with the improved generative adversarial network, and transmits the missing value filled and error corrected data to the data transformation and loading module.

[0141] In the embodiment of the present application, it is assumed that there is a set of data X, which contains some missing values ​​and potential erroneous values. The data received by the data correction unit has been preliminarily cleaned, such as deduplication.

[0142] For the processing of missing values, generative models are usually used to predict the missing parts. Here, a variant of the generative adversarial network (GAN), called the improved generative adversarial network (IGAN), is used to fill in the missing values.

[0143] For each sample in the dataset, we need to mark which values ​​are missing. Let m represent the labeling matrix of missing values, where m ij =1 means the jth eigenvalue of the ith sample is missing, otherwise it is 0.

[0144] It should be noted that GAN consists of a generator G and a discriminator D, where the goal of the generator is to generate data similar to the real data distribution, while the goal of the discriminator is to distinguish between real data and generated data.

[0145] Generator G: The input is data X with missing values ​​and missing value marker m, and the output is the filled data X G .

[0146] Discriminator D: The input is data X with missing values ​​and missing value marker m, and the output is the judgment of data completeness.

[0147] In order to train GAN, a loss function needs to be defined. Usually, the loss function of GAN consists of two parts: generator loss and discriminator loss.

[0148] Discriminator loss L D :

[0149]

[0150] Among them, p data represents the distribution of real data, p z represents the distribution of noise data, and z is the random noise input to the generator.

[0151] Generator loss L G :

[0152]

[0153] In this scenario, since missing values ​​are involved, the loss function needs to be slightly adjusted to take into account the reconstruction loss of the missing parts. true is the complete dataset, X G is the padded dataset generated by the generator, then the loss function can be defined as:

[0154]

[0155] Among them, λ1 and λ2 are weight coefficients used to balance the relationship between the loss of the discriminator and the generator and the reconstruction loss.

[0156] Furthermore, after dealing with missing values, it is necessary to correct the errors in the data. This can be done by training an additional model that can identify and correct the erroneous values. One possible approach is to use the ability of the generator G to predict outliers in the data and replace them with the generated results.

[0157] After the above steps, the corrected data set X' is obtained, which not only fills the missing values ​​but also corrects the erroneous values. Then X' is transmitted to the data transformation and loading module.

[0158] In the embodiment of the present application, the data transformation and loading module includes:

[0159] Data conversion unit and data loading unit; the data conversion unit is used to convert the target battery swap station operation data transmitted to by the data noise reduction processing module in combination with the improved knowledge graph technology for format conversion, including but not limited to converting the data from the original format to a standard format suitable for the target battery swap station application system.

[0160] It should be noted that the purpose of constructing a data transformation unit is to convert the data output by the data cleaning unit into a format and structure that meets the needs of subsequent analysis and application. The data transformation unit mainly has the following four functions: first, standardize the data format, convert the data into a unified format; second, normalize the data structure, normalize the data structure, such as unifying field names, data types, etc.; third, aggregate data, aggregate data into higher-level statistical indicators; fourth, derive data, derive new data features from the original data, such as calculating the coefficient of variation, standard deviation, etc.

[0161] The data transformation unit of the present application performs data conversion by applying knowledge graph technology. Knowledge graph is a semantic network that can organize data into associations between concepts, relationships, and attributes. Applying knowledge graph for data conversion can improve the efficiency and accuracy of data conversion. The specific method adopts the rule-based method in the knowledge graph. The rule-based method is currently a relatively stable knowledge graph data conversion method, and data conversion is achieved by defining conversion rules. The conversion rule usually consists of two parts: conditions and conclusions. The condition part is used to determine whether the data needs to be converted, and the conclusion part is used to specify the format and structure of the converted data.

[0162] 1) Rule definition

[0163] The definition of conversion rules usually needs to be done manually, which requires rich domain knowledge and in-depth understanding of the knowledge graph. This application adopts two rule definition methods: one is template-based rule definition, which uses templates to define rules; the other is ontology-based rule definition, which uses ontology to define rules. Ontology can provide the relationship between domain knowledge and concepts.

[0164] 2) Rule application

[0165] The application of transformation rules is usually implemented by an inference engine. The inference engine can infer new knowledge based on the rules in the rule base and apply it to data transformation. There are two types of inference engines used in this application: one is a rule-based inference engine, which uses forward reasoning or backward reasoning to apply rules; the other is a fact-based inference engine, which uses inductive reasoning or deductive reasoning to apply rules.

[0166] This application uses knowledge graphs for data transformation, which has three obvious advantages. First, it improves the efficiency and accuracy of data conversion. Knowledge graphs can provide rich semantic information, which can help improve the efficiency and accuracy of data conversion. Second, it converts data into a format with more semantic meaning. Knowledge graphs can organize data into a format with more semantic meaning, which is convenient for subsequent data analysis and application. Third, it supports multiple data types. Knowledge graphs can support multiple data types, such as text data, structured data, semi-structured data, etc.

[0167] In the embodiment of the present application, the data transformation and loading module further includes:

[0168] The data loading unit includes a data caching mechanism, which is used to temporarily store the converted data after the data transformation unit completes the format conversion. The caching mechanism is designed using improved distributed publish-subscribe technology to ensure that the data can be received and processed by the target battery swap station application system as quickly as possible. The data loading unit also has an intelligent scheduling function, which can dynamically adjust the priority and rate of data transmission according to the real-time needs of the target battery swap station application system to ensure the real-time and accuracy of key data.

[0169] The data caching mechanism adopts an improved distributed publish-subscribe (Pub / Sub) model, in which the data conversion unit acts as the publisher and the target battery swap station application system acts as the subscriber. Assume that the data stream generated by the data conversion unit is represented as S, the instance set of the target battery swap station application system is represented as C, and each instance c i ∈C represents a subscriber. The data caching mechanism needs to maintain a cache queue Q, where q i ∈Q represents the data item in the cache

[0170] Furthermore, in the improved distributed publish-subscribe mode, the data transformation unit converts the converted data s i ∈S is published to the cache queue Q, the instance c of the target battery swap station application system i Will subscribe to this cache queue Q and consume data from it

[0171] Furthermore, in order to improve the data processing speed, it is necessary to define a cache strategy to manage the data items in the cache queue Q. This can be done by setting a maximum cache capacity C max To achieve this, when the length of the cache queue exceeds C max When a data is stored in a database, a data elimination strategy needs to be implemented, such as First In First Out (FIFO) or Least Recently Used (LRU).

[0172] Furthermore, let the length of cache queue Q be |Q|. When |Q|>C max When , some elements in the queue need to be removed to keep the cache capacity no larger than C max .

[0173] Furthermore, the intelligent dispatching function needs to analyze the real-time needs of the target battery swap station application system to dynamically adjust the priority and rate of data transmission. This can be achieved by monitoring each instance c i This can be achieved through load conditions, such as CPU usage, memory usage, and other indicators.

[0174] Furthermore, suppose that each instance c i The real-time load is represented by L i , we can define a threshold L threshold , when L i >L threshold , it indicates that the instance is under high load and the rate at which data is sent to it needs to be reduced.

[0175] Furthermore, in order to dynamically adjust the priority and rate of data transmission, the Weighted Fair Queuing (WFQ) algorithm can be used. WFQ assigns a weight w to each instance. i , the weight reflects the real-time demand of the instance. The higher the weight of the instance, the higher the priority of its data transmission;

[0176] Assume that there are n instances in the instance set C of the target battery swap station application system, and each instance c i Real-time demand L i Its assigned weight w i Proportional, that is, w i =f(L i ), where f is a monotonically increasing function. The WFQ algorithm can be expressed as

[0177]

[0178] where d i Represents instance c i The amount of data received per unit time. This expression describes how to allocate bandwidth for data transmission according to the needs of each instance. The specific steps can be summarized as follows:

[0179] 1. Initialize the cache queue: create an empty cache queue Q.

[0180] 2. Data release: The data conversion unit converts the converted data into i Published to the cache queue Q.

[0181] 3. Data subscription: Example of target battery swap station application system c i Subscribe to the cache queue Q and consume data from it.

[0182] 4. Cache strategy execution: when |Q|>C max , execute the cache elimination strategy.

[0183] 5. Real-time demand analysis: monitor each instance c i The real-time load L i .

[0184] 6. Dynamic adjustment: Use the WFQ algorithm to dynamically adjust the priority and rate of data transmission.

[0185] In summary, the present invention proposes an intelligent data access management system for battery swap stations, which obtains the target battery swap station operation data of different devices and sensors in the target battery swap station, and stores the target battery swap station operation data in real time, wherein the target battery swap station operation data at least includes electrical parameters, equipment status and environmental information of different devices and sensors; performs noise reduction processing on the real-time target battery swap station operation data, and performs format conversion on the real-time target battery swap station operation data after noise reduction processing; inputs the format-converted data into the target battery swap station application system to complete the intelligent data access management for battery swap stations. By applying improved edge computing technology, the present invention can realize efficient real-time collection of battery swap station operation data, significantly reduce data transmission delay, and improve the response speed and reliability of the system. The application of improved recurrent neural networks and generative adversarial networks in data cleaning and correction ensures the accuracy and integrity of the data, thereby providing solid data support for the efficient operation of the battery swap station. In addition, by improving the knowledge graph technology for data format conversion, the data can better adapt to the needs of the target battery swap station application system, and improve the availability and interoperability of the data. The application of improved distributed publish-subscribe technology in the data caching mechanism ensures the high efficiency and real-time performance of data transmission, enabling the target battery swap station application system to obtain the required data in a timely and accurate manner, further improving the intelligent management level of the battery swap station.

[0186] In summary, the intelligent data access management system and method of the battery swap station of the present invention not only improves the efficiency of data collection and processing, but also enhances the stability and reliability of the system, providing strong technical support for the intelligent upgrade of the battery swap station. Through the application of the present invention, real-time monitoring, intelligent analysis and accurate prediction of the operation data of the battery swap station can be realized, providing important guarantee for the efficient operation and maintenance of the battery swap station.

[0187] This embodiment also provides a method for data access management of an intelligent battery swap station, the method comprising:

[0188] Obtain target battery swap station operation data of different devices and sensors in the target battery swap station, and store the target battery swap station operation data in real time, where the target battery swap station operation data at least includes electrical parameters, device status, and environmental information of different devices and sensors;

[0189] Perform noise reduction processing on the real-time target battery swap station operation data, and convert the format of the real-time target battery swap station operation data after the noise reduction processing;

[0190] Input the format-converted data into the target battery swap station application system to complete the intelligent battery swap station data access management.

[0191] The above-mentioned unit modules may be embedded in or independent of a processor in a computer device in the form of hardware, or may be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to the above-mentioned modules.

[0192] This embodiment also provides a computer device, which may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 2 As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for data access management of an intelligent battery swap station is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the housing of the computer device, or an external keyboard, touchpad or mouse.

[0193] This embodiment further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0194] Obtain target battery swap station operation data of different devices and sensors in the target battery swap station, and store the target battery swap station operation data in real time, where the target battery swap station operation data at least includes electrical parameters, device status, and environmental information of different devices and sensors;

[0195] Perform noise reduction processing on the real-time target battery swap station operation data, and convert the format of the real-time target battery swap station operation data after the noise reduction processing;

[0196] Input the format-converted data into the target battery swap station application system to complete the intelligent battery swap station data access management.

[0197] Example 2

[0198] Reference Figure 1-Figure 2 , which is an embodiment of the present invention, provides an intelligent battery swap station data access management system and method. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through experiments.

[0199] The experimental results are shown in Table 1, Table 2, and Table 3:

[0200] Table 1: Data conversion efficiency

[0201] Serial number Conversion time before experiment (seconds) Post-experiment conversion time (seconds) Efficiency improvement percentage 1 15 10.5 30％ 2 20 14 30％ 3 25 17.5 30％ 4 30 21 30％ 5 35 24.5 30％

[0202] Table 2: Data Accuracy

[0203] Serial number Pre-experimental error rate Post-experimental error rate Accuracy improvement percentage 1 10％ 8％ 20％ 2 12％ 9.6％ 20％ 3 8％ 6.4％ 20％ 4 15％ 12％ 20％ 5 5％ 4％ 20％

[0204] Table 3: Target battery swap station application system response time

[0205]

[0206]

[0207] Average conversion time before experiment: Second;

[0208] Average conversion time after experiment: Second;

[0209] Efficiency improvement percentage:

[0210] Average error rate before the experiment:

[0211] Average error rate after the experiment:

[0212] Accuracy improvement:

[0213] Average response time before the experiment: millisecond;

[0214] Average response time after the experiment: millisecond;

[0215] Response time reduction by percent:

[0216] It can be seen from the experimental data that the embodiments of the present invention have achieved significant improvements in data conversion efficiency, data accuracy, and the response time of the target battery swap station application system. These improvements help to improve the performance and reliability of the entire system and ensure that key data can be processed in a timely and accurate manner.

[0217] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0218] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code. The scheme in the embodiments of the present application can be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.

[0219] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0220] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0221] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0222] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0223] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. An intelligent data access management system for battery swap stations, characterized in that: include: Real-time data acquisition and storage module, data noise reduction processing module, data transformation and loading module; The real-time data acquisition and storage module is used to obtain the target battery swap station operation data of different devices and sensors in the target battery swap station using an improved edge computing method, and store the target battery swap station operation data in real time, wherein the target battery swap station operation data at least includes electrical parameters, device status and environmental information of different devices and sensors; The data noise reduction processing module is used to perform noise reduction processing on the real-time target battery swap station operation data stored in the real-time data acquisition and storage module, and transmit the real-time target battery swap station operation data after noise reduction processing to the data conversion and loading module in real time, and the noise reduction processing includes data cleaning and data correction; The data conversion and loading module is used to convert the format of the data after the noise reduction processing by the data noise reduction processing module, and input the format-converted data into the target battery swap station application system.

2. The intelligent battery swap station data access management system according to claim 1, characterized in that: The real-time data acquisition and storage module includes: a real-time data acquisition unit and a real-time data storage unit; The real-time data acquisition unit includes a plurality of sensor interfaces for connecting and acquiring real-time data signals from different devices and sensors; The real-time data acquisition unit applies an improved edge computing method for efficient data acquisition. The process of improving edge computing for real-time data acquisition includes calculating a cross entropy value, determining a mean square error, determining the number of hidden nodes, and building a real-time data acquisition model.

3. The intelligent battery swap station data access management system according to claim 2, characterized in that: The real-time data acquisition and storage module also includes: The real-time data storage unit is used to store the target battery swap station operation data collected by the real-time data collection unit. The real-time data storage unit includes multiple distributed storage nodes, which are connected via a high-speed network to ensure real-time synchronization and backup of data. Each node has independent processing capabilities and storage space, and processes and stores data in parallel. By replicating data between different nodes, the system can still ensure the integrity and continuity of the data even if some nodes fail. The real-time data storage unit also supports data version management and historical record query functions, and also integrates encryption and access control mechanisms.

4. The intelligent battery swap station data access management system according to claim 3, characterized in that: The data noise reduction processing module includes: a data cleaning unit and a data correction unit; The data cleaning unit includes using an improved recurrent neural network to perform data cleaning for identifying and eliminating outliers and noise in the target battery swap station operating data; the improved recurrent neural network performs data cleaning including preliminary cleaning of the original target battery swap station operating data from the real-time data acquisition and storage module, and the preliminary cleaning includes removing duplicate data points, processing missing values, and performing outlier detection and processing; selecting features with an amount of information greater than a first information amount threshold and a correlation greater than a first correlation threshold, defining a loss function of the improved recurrent neural network model, obtaining input data sets and output data sets before and after cleaning, and transmitting the cleaned data to the data correction unit.

5. The intelligent battery swap station data access management system according to claim 4, characterized in that: The data noise reduction processing module also includes: The data correction unit receives the cleaned data from the data cleaning unit, and performs missing value filling and error correction in combination with the improved generative adversarial network, and transmits the data after missing value filling and error correction to the data transformation and loading module.

6. The intelligent battery swap station data access management system according to claim 5, characterized in that: The data conversion and loading module includes: Data conversion unit and data loading unit; the data conversion unit is used to convert the target battery swap station operation data transmitted to by the data noise reduction processing module in combination with the improved knowledge graph technology for format conversion, including but not limited to converting the data from the original format to a standard format suitable for the target battery swap station application system.

7. The intelligent data access management system for battery swap stations according to claim 6, characterized in that: The data conversion and loading module also includes: The data loading unit includes a data caching mechanism, which is used to temporarily store the converted data after the data transformation unit completes the format conversion. The caching mechanism is designed using improved distributed publish-subscribe technology to ensure that the data can be received and processed by the target battery swap station application system at the fastest speed. The data loading unit also has an intelligent scheduling function, which can dynamically adjust the priority and rate of data transmission according to the real-time needs of the target battery swap station application system to ensure the real-time and accuracy of key data.

8. An intelligent power swap station data access management method applied to the intelligent power swap station data access management system according to claim 1, the method comprising: Obtain target battery swap station operation data of different devices and sensors in the target battery swap station, and store the target battery swap station operation data in real time, wherein the target battery swap station operation data at least includes electrical parameters, device status, and environmental information of different devices and sensors; Perform noise reduction processing on the real-time target battery swap station operation data, and convert the format of the real-time target battery swap station operation data after the noise reduction processing; Input the format-converted data into the target battery swap station application system to complete the intelligent battery swap station data access management.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to claim 8 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to claim 8 are implemented.

Images