Automobile energy consumption data visualization method and system

Abstract

The application relates to the technical field of data processing, in particular to a vehicle energy consumption data visualization method and system. The method comprises the following steps: collecting all attribute values in a preset period to form an attribute vector; obtaining an isolated tree of the attribute vector, and obtaining the importance degree of the attribute based on correlation; obtaining the key degree of each attribute based on the number of times of attribute abnormality in historical data, the abnormal data of each attribute and the difference between all attribute values of the attribute; calculating the balanced difference degree of the nodes of each isolated tree, taking the distance of each node from the root node as the weight, weighting the difference between the balanced difference degree of the node and the balanced difference degree of the nodes on the same layer to obtain the structural symmetry of the isolated tree; obtaining the weight of the isolated tree based on the key degree, the importance degree and the structural symmetry, obtaining the abnormal degree in combination with the attribute vector, and deleting the vector; and then constructing a knowledge graph to realize energy consumption data visualization. The application improves the reliability of the vehicle energy consumption knowledge graph after visualization.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a vehicle energy consumption data visualization method and system. BACKGROUND

[0002] Under the big data background of vehicle energy consumption, the application of knowledge graph becomes crucial. It integrates and analyzes massive data from various aspects of the energy consumption industry, including production, distribution, consumption, and multiple dimensions such as policy, market, and environment, providing a powerful analysis and prediction platform for decision-makers. Knowledge graph uses natural language processing and machine learning techniques to automatically identify and extract entities, relationships, and attributes in data, constructing a structured knowledge base that makes it easier to discover patterns, rules, and trends in data. In addition, the visualization function of knowledge graph displays complex data analysis results in an intuitive and easy-to-understand way, greatly improving the transparency and participation of decision-making. Not only can it support automobile enterprises to make accurate decisions in complex market environments, but also can dynamically update and maintain the knowledge base to respond to changes in data sources, maintaining the timeliness and accuracy of data.

[0003] Before visualizing energy consumption data, data needs to be preprocessed, such as performing anomaly detection on the obtained data. However, when existing data is processed using an isolated forest, the weight given to each generated tree is the same, but in reality, the anomaly detection effect brought by the generation result of each tree is inconsistent. Therefore, when performing anomaly detection using the existing isolated forest algorithm, the final detection result may not be ideal. Therefore, it is necessary to analyze each randomly generated tree to avoid the occurrence of the above problems. SUMMARY

[0004] To solve the technical problem of poor anomaly detection effect, the present application provides a vehicle energy consumption data visualization method and system, which adopts the following technical solutions:

[0005] In a first aspect, the present application proposes a vehicle energy consumption data visualization method, which comprises the following steps:

[0006] Statistical properties of different attributes within a predetermined time, all attribute values collected at each time constitute an attribute vector, the attributes include vehicle energy consumption;

[0007] Process all attribute vectors to obtain a number of isolated trees through an isolated forest; and obtain the importance of each attribute according to the correlation between different attributes in all attribute vectors;

[0008] count the number of times of each attribute appearing abnormal in the historical data, and take the ratio of the number of times of each attribute appearing abnormal in the historical data to the total number of each attribute in the historical data as the probability of each attribute appearing abnormal; obtain the abnormal degree of each abnormal data in each attribute according to the difference between the attribute value of each abnormal data in each attribute in the historical data and the average value of the attribute value of each attribute in the historical data; obtain the key degree of each attribute according to the abnormal degree of all abnormal data in each attribute in the historical data and the probability of each attribute appearing abnormal in the historical data;

[0009] For each isolated tree, calculate the difference between the left subtree depth and the right subtree depth of each node in the isolated tree to obtain the balance difference degree of each node; take the distance of each node from the root node as the weight, and weight the balance difference degree of each node and the difference between the balance difference degrees of the node and the nodes in the same layer to obtain the structural symmetry of the isolated tree;

[0010] According to the key degree and the important degree of each attribute, calculate the attribute weight of each attribute, and obtain the weight of the isolated tree based on the attribute weight and the structural symmetry of the isolated tree; weight the attribute value of each attribute vector in the isolated tree through the weight of each isolated tree to obtain the abnormal degree of each attribute vector; and delete the vector through the abnormal degree.

[0011] The attribute vector after excluding the abnormal data is used to form a knowledge graph, and the visualization of the automobile energy consumption data is obtained based on the formed knowledge graph.

[0012] In the above scheme, the present application analyzes the obtained isolated tree, first obtains the attribute weight of the data attribute corresponding to each isolated tree according to the isolated tree attribute analysis, and further obtains the final weight of the isolated tree according to the structure of the isolated tree, greatly considers the difference of different attributes on the importance of data and the problem of unreliable data detection result caused by the structure of the isolated tree, increases the reliability and accuracy of the isolated forest abnormal detection result, improves the quality of the energy consumption data after preprocessing, and improves the reliability of the knowledge graph of the energy consumption data after visualization.

[0013] In one embodiment, the attributes include the driving distance of the vehicle, the energy consumption of the vehicle, the average speed of the vehicle, the average temperature of the external environment, the vehicle altitude change value and the external road congestion time; the knowledge graph of the energy consumption data is updated every preset time, and the attribute values between the two knowledge graph updates are collected.

[0014] In one embodiment, the isolated tree only contains one attribute, and the leaf node of the isolated tree is an attribute value of the corresponding attribute in the attribute vector.

[0015] In one embodiment, the method for obtaining the important degree of each attribute according to the correlation between different attributes in all attribute vectors is:

[0016] Sort the attribute values of the same attribute in all attribute vectors in chronological order to obtain an attribute sequence of each attribute; calculate the correlation of each attribute sequence with the rest of the attribute sequences, calculate the mean of all correlations corresponding to each attribute sequence, and take the mean as the importance of the attribute.

[0017] In one embodiment, the method for obtaining the abnormality degree of each abnormal data in each attribute according to the difference between the attribute value of each abnormal data in each attribute and the mean of the attribute values of each attribute in the historical data is:

[0018] FC (j,r) denotes the attribute value of the jth abnormal data corresponding to attribute r in the historical data, Bc r denotes the mean of all attribute values in attribute r in the historical data, G (j,r) denotes the abnormality degree of the jth abnormal data corresponding to attribute r in the historical data.

[0019] In one embodiment, the method for obtaining the criticality of each attribute according to the abnormality degrees of all abnormal data in each attribute and the probability of each attribute being abnormal in the historical data is:

[0020] The criticality of each attribute is negatively correlated with the abnormality degrees of all abnormal data in each attribute and positively correlated with the probability of each attribute being abnormal.

[0021] In one embodiment, the method for obtaining the structural symmetry of the isolated tree by weighting the balanced difference of each node and the difference between the balanced differences of the node and the nodes at the same level with the distance of each node from the root node as the weight is:

[0022] H i denotes the balanced difference of the ith node, H (i,v) denotes the difference between the balanced differences of the ith node and the vth node at the same level as the ith node, L denotes the depth of the isolated tree, S i denotes the difference between the layer number of the ith node and the depth of the isolated tree, m denotes the number of nodes in the isolated tree, exp() denotes the exponential function with the natural constant as the base, and Hc denotes the structural symmetry of the isolated tree.

[0023] In one embodiment, the method for calculating the attribute weight of each attribute according to the criticality and importance of each attribute and obtaining the weight of the isolated tree based on the attribute weight and the structural symmetry of the isolated tree is:

[0024] The attribute weight is positively correlated with the criticality and importance of each attribute, respectively;

[0025] The weight of the isolated tree is positively correlated with the structural symmetry of the isolated tree and the attribute weight of the attribute corresponding to the isolated tree.

[0026] In one embodiment, the method for obtaining the abnormality degree of each attribute vector by weighting the attribute value of each attribute vector in the isolated tree again by the weight of each isolated tree is as follows:

[0027] Rd c Rd represents the weight of the cth isolated tree, p (c,x) represents the attribute value of the xth attribute vector in the cth isolated tree, B represents the number of isolated trees, exp() represents the exponential function with the natural constant as the base, and E x represents the abnormality degree of the xth attribute vector.

[0028] In a second aspect, the embodiments of the present application also provide an automobile energy consumption data visualization system, which comprises a memory, a processor, and a computer program stored in the memory and running on the processor, and the processor implements the steps of the automobile energy consumption data visualization method according to any one of the above embodiments when executing the computer program.

[0029] The present application has the following beneficial effects:

[0030] The present application analyzes the obtained isolated trees, first obtains the attribute weight of the attribute corresponding to each isolated tree according to the isolated tree partition attribute analysis, and then analyzes the structure of the isolated tree to obtain the final weight of the isolated tree, greatly considers the different importance of different attributes to data and the problem of unreliable data detection results caused by the structure of the isolated tree, increases the reliability and accuracy of the isolated forest abnormality detection result, improves the quality of the energy consumption data after preprocessing, and improves the reliability of the knowledge graph of the energy consumption data after visualization. BRIEF DESCRIPTION OF DRAWINGS

[0031] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the prior art, the drawings needed in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.

[0032] Figure 1 A flowchart of an automobile energy consumption data visualization method provided by one embodiment of the present application. DETAILED DESCRIPTION

[0033] For further elaboration of the technical means and effects taken by the present application to achieve the predetermined object of the application, the specific embodiments, structures, features and effects of the automobile energy consumption data visualization method and system according to the present application are described in detail as follows. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0034] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0035] An embodiment of an automobile energy consumption data visualization method and system:

[0036] The specific scheme of the automobile energy consumption data visualization method provided by the present application is described in detail below with reference to the accompanying drawings.

[0037] Please refer to Figure 1 , which shows a flowchart of an automobile energy consumption data visualization method provided by an embodiment of the present application. The method includes the following steps:

[0038] Step S001, count the attribute values of different attributes within a predetermined time, and form an attribute vector with all the attribute values collected at each time.

[0039] During the running phase of the automobile, data is collected every half hour through the vehicle-mounted sensor and the map API. In this embodiment, the collected data includes the driving distance of the vehicle, the energy consumption of the vehicle, the average speed of the vehicle, the average temperature of the external environment, the altitude change value of the vehicle, and the external road congestion time. Each of these is taken as an attribute, i.e. the data of each attribute is collected every half hour. The knowledge graph formed by the historical data is updated every predetermined time.

[0040] In this embodiment, the knowledge graph is updated every 24 hours of running of the automobile. The data collected every 24 hours of running is preprocessed and added to the new knowledge graph to construct the updated knowledge graph, ensuring the real-time performance of the automobile energy consumption visualization.

[0041] All kinds of attribute data collected each time form an attribute vector, and 48 attribute vectors are obtained when the knowledge graph is updated twice.

[0042] At this point, all attribute vectors between knowledge graph updates have been obtained.

[0043] Step S002, process all attribute vectors through the Isolation Forest to obtain a plurality of isolation trees; and obtain the importance of each attribute according to the correlation between different attributes in all attribute vectors.

[0044] All the attribute vectors are processed using the Isolation Forest, and a plurality of isolation trees are obtained by the Isolation Forest algorithm, wherein each isolation tree corresponds to one attribute, and a leaf node of the isolation tree is an attribute value of the attribute in the attribute vector.

[0045] For example, after all the attribute vectors are processed by the Isolation Forest, the attribute of one of the isolation trees is the energy consumption of the vehicle, and the value of each node in the isolation tree is the energy consumption value of the vehicle in each attribute vector.

[0046] The purpose of using the Isolation Forest algorithm in the present application is to perform anomaly detection on the collected attribute vectors and exclude abnormal data. Since the Isolation Forest is obtained by randomly selecting and constructing isolation trees according to different attributes, there are differences between different attribute features. Therefore, attribute weight values are constructed for different isolation trees.

[0047] The attribute weight value of the isolation tree is positively correlated with the importance of the attribute, that is, the more important the attribute is, the more important the analysis result of the corresponding tree is, that is, the greater the attribute weight value of the tree is.

[0048] All the attribute values of each attribute in all the attribute vectors form an attribute sequence, for example, all the attribute values of the energy consumption of the vehicle in all the attribute vectors form an attribute sequence corresponding thereto, and the sequence is in time sequence.

[0049] The correlation between each attribute sequence and each of the remaining attribute sequences is calculated, the average of all the correlations corresponding to each attribute sequence is calculated, and the average is taken as the importance of the attribute. If the correlation between the attribute sequence and each of the remaining attribute sequences is poor, it means that the attribute has a stronger ability to represent data characteristics, and the importance of the corresponding attribute is greater. In the present embodiment, the correlation between the attribute sequences is calculated by the Pearson correlation coefficient, which is a known technology and will not be described in detail in the present embodiment. Implementers can use other correlation calculation methods.

[0050] At this point, the importance of each attribute is obtained.

[0051] In step S003, the probability of occurrence of an anomaly is obtained based on the number of times each attribute in the historical data occurs abnormally, and the criticality of each attribute is obtained by combining the abnormal data of each attribute and the difference between all the attribute values of the attribute.

[0052] All historical data of the running stage of the automobile is counted, and the obtained historical data is analyzed. Since the obtained data is acquired in real time, the updating of the knowledge graph is also fixed updating. Due to changes in the external environment or aging of instruments and other reasons, some data may have a higher possibility of abnormal detection results. Therefore, the abnormal situation of the historical data can be analyzed according to this, and the probability of each attribute in the historical data being abnormal is taken as a reference to analyze the importance of the obtained attribute, so as to obtain the criticality of each attribute.

[0053] All historical data is counted, and the attribute data collected in each time is analyzed to obtain the number of times each attribute is abnormal. Then, the ratio of the number of times the attribute is abnormal to the number of attribute data collected in the historical data is taken as the probability of the attribute being abnormal.

[0054] The obtained abnormal data is analyzed to analyze the abnormality degree of the abnormal data. If the number of possible abnormal data is large but the abnormality degree is small, that is, the degree of deviation of the obtained abnormal data from the normal value is small, and the deviation degree of some abnormal data from the normal data may be large. Therefore, the abnormality degree of the abnormal data also needs to be analyzed. Based on the difference between the attribute value of each attribute being abnormal and the average attribute value of the attribute in the historical data, the abnormality degree of each abnormal data of each attribute is calculated, and the expression is:

[0055] FC (j,r) represents the attribute value of the jth abnormal data corresponding to attribute r in the historical data, Bc r represents the average value of all attribute values in attribute r in the historical data, G (j,r) represents the abnormality degree of the jth abnormal data corresponding to attribute r in the historical data.

[0056] The greater the difference between the abnormal value and the average value, the greater the difference between the abnormal value and the normal value, that is, the greater the deviation degree of the abnormal value from the normal value, and the greater the abnormality degree of the abnormal data corresponding to the abnormal value.

[0057] The criticality of each attribute is obtained according to the abnormality degree of all abnormal data in each attribute in the historical data and the probability of each attribute being abnormal in the historical data.

[0058] The criticality of each attribute is negatively correlated with the abnormality degree of all abnormal data in each attribute, and is positively correlated with the probability of each attribute being abnormal.

[0059] It should be noted that the positive correlation means that one variable increases, and the other variable also increases, the two variables change in the same direction, and when one variable changes from large to small or from small to large, the other variable also changes from large to small or from small to large; the specific relationship is determined by actual application, and the present application does not make special limitation.

[0060] It should be noted that the negative correlation means that one variable increases, and the other variable decreases, the two variables change in opposite directions, and when one variable changes from large to small or from small to large, the other variable also changes from small to large or from large to small; the specific relationship is determined by actual application, and the present application does not make special limitation.

[0061] Preferably, in the present embodiment, the expression of the key degree of each attribute is:

[0062] G (j,r) represents the abnormal degree of the jth abnormal data corresponding to the attribute r in the historical data, P r represents the number of abnormal data in the attribute r, F r represents the probability of the attribute r appearing abnormal, exp() represents the exponential function with natural constant as the base, Tx r represents the key degree of each attribute.

[0063] When the probability of the attribute r appearing abnormal in the historical data is greater, and the deviation degree of the corresponding abnormal value and normal value is also greater, it means that the attribute r is more likely to appear abnormal, and the attribute is more critical.

[0064] At this point, the key degree of each attribute is obtained.

[0065] In step S004, the balanced difference degree of each node of each isolated tree is calculated, and the structure symmetry of the isolated tree is obtained by weighting the difference between the node balanced difference degree and the balanced difference degree of the nodes on the same layer with the distance of each node from the root node as the weight.

[0066] For an isolated tree used for anomaly detection, the more asymmetric the structure of the tree is, the more it can reflect the characteristics of anomaly detection, that is, if the entire tree has similar number of nodes on both sides, then reliable anomaly detection results cannot be obtained according to the tree, so the structure of the tree can be analyzed.

[0067] For each isolated tree, the depth of the left subtree and the depth of the right subtree of each node in the isolated tree are counted, and the balanced difference degree of each node is calculated based on the difference between the depths of the left and right subtrees; the specific expression is:

[0068] H i = |C (i,1) -C (i,2) |, C (i,1)represents the depth of the left subtree of the i-th node, C (i,2) represents the depth of the right subtree of the i-th node, H i represents the balance difference of the i-th node.

[0069] The greater the balance difference of each node in the isolated tree, the more asymmetric the structure of the isolated tree. In addition, the greater the difference in balance difference between two nodes at the same level, the more different the two nodes, indicating that the structure of the isolated tree is more asymmetric. The difference in balance difference between each node and any node at the same level is calculated, and the greater the difference, the more asymmetric the structure of the isolated tree. The closer to the root node of the isolated tree, the greater the influence of each node. The difference between the number of layers of each node and the depth of the isolated tree is calculated, and the greater the difference, the farther away from the root node of the isolated tree. Therefore, based on the above, the structural symmetry of each isolated tree is calculated, and the expression is:

[0070] H i represents the balance difference of the i-th node, H (i,v) represents the difference in balance difference between the i-th node and the v-th node at the same level of the i-th node, L represents the depth of the isolated tree, S i represents the difference between the number of layers of the i-th node and the depth of the isolated tree, m represents the number of nodes in the isolated tree, exp() represents the exponential function with the natural constant as the base, and Hc represents the structural symmetry of the isolated tree.

[0071] The farther away from the root node, the smaller the influence on the symmetry of the isolated tree, so the distance from the root node is used as the weight to analyze the balance difference of each node. The greater the balance difference of each node, the more asymmetric the isolated tree. The greater the difference in balance difference between each node and the node at the same level, the greater the difference in the corresponding subtree of the node, and the more asymmetric the isolated tree.

[0072] At this point, the structural symmetry of each isolated tree is obtained.

[0073] Step S005, based on the key degree, importance degree and structural symmetry, the weight of the isolated tree is obtained, the abnormal degree is obtained by combining the attribute vector, and the data is deleted.

[0074] Since each isolated tree corresponds to an attribute, the attribute weight of the attribute is calculated based on the key degree and importance degree of each attribute, the weight of each isolated tree is evaluated based on the attribute weight and the structural symmetry of the isolated tree, and the abnormal detection is performed on each attribute vector based on the weight of the isolated tree.

[0075] Specifically, the attribute weight and the key degree and importance degree of each attribute are positively correlated.

[0076] Preferably, in the embodiment, the product of the key degree and the importance degree of each attribute is taken as the attribute weight of each attribute.

[0077] The weight of each isolated tree is obtained according to the structural symmetry of each isolated tree and the attribute weight of the attribute corresponding to the isolated tree.

[0078] The weight of the isolated tree is positively correlated with the structural symmetry of the isolated tree and the attribute weight of the attribute corresponding to the isolated tree.

[0079] Preferably, in the embodiment, the product of the structural symmetry of each isolated tree and the attribute weight of the attribute corresponding to the isolated tree is taken as the weight of the isolated tree.

[0080] Thus, the weight of each isolated tree is obtained, and when the isolated forest algorithm is used for anomaly detection, the closer the leaf node to the root node of the isolated tree, the more abnormal the leaf node. Each leaf node corresponds to an attribute vector, and the abnormality degree of each attribute vector is calculated by combining the abnormality of the attribute vector in all isolated trees and the weight of the isolated tree, and the expression is:

[0081] Rd c Rd represents the weight of the cth isolated tree, p (c,x) represents the attribute value of the xth attribute vector in the cth isolated tree, B represents the number of isolated trees, E x represents the abnormality degree of the xth attribute vector.

[0082] The abnormality degree of each attribute vector between each two knowledge graph updates is obtained by the above method, and if the abnormality degree is greater than a preset abnormality threshold, the attribute vector is an abnormal attribute vector, which is excluded and does not participate in the subsequent construction of the knowledge graph.

[0083] Step S006, constructing the knowledge graph after deleting the data to realize the visualization of the energy consumption data.

[0084] The above steps complete the anomaly detection of the collected data, and the abnormal data is cleaned. The entity is obtained by processing the collected attribute data through the named entity recognition technology, and the relationship is extracted through the relationship extraction algorithm. The entity, attribute and relationship form a triple, and the knowledge graph is formed by the triple. The way of forming the knowledge graph is a known technology, and will not be described here.

[0085] Based on the constructed knowledge graph, the visualization of the automobile energy consumption data can be performed.

[0086] Based on the same inventive concept as the above method, the embodiments of the present application also provide a vehicle energy consumption data visualization system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of any one of the above vehicle energy consumption data visualization methods when executing the computer program.

[0087] It should be noted that the above-mentioned embodiments are only used to illustrate the technical solutions of the present application, but not limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements for some technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

[0088] Each of the embodiments in the specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other. Each embodiment mainly describes the difference from other embodiments.

Claims

1. A method for visualizing automotive energy consumption data, the method comprising: The method includes the following steps: The attribute values ​​of different attributes are statistically analyzed within a preset time period, and all attribute values ​​collected at each moment are used to form an attribute vector, wherein the attributes include the energy consumption of the vehicle. We obtain several isolated trees by processing all attribute vectors through an isolated forest; and determine the importance of each attribute based on the correlation between different attributes in all attribute vectors. The probability of an anomaly for each attribute is calculated by counting the number of times each attribute appears in the historical data and then comparing that number to the total number of times each attribute appears in the historical data. The degree of anomaly for each attribute is determined by comparing the attribute value of each anomaly within each attribute with the mean attribute value in the historical data. The criticality of each attribute is determined by comparing the degree of anomaly of all anomalies within each attribute in the historical data with the probability of an anomaly for each attribute in the historical data. For each isolated tree, calculate the difference between the depth of the left subtree and the depth of the right subtree of each node in the isolated tree to obtain the balance difference degree of each node; use the distance of each node from the root node as the weight to weight the balance difference degree of each node and the difference between the balance difference degree of the node and the nodes at the same level to obtain the structural symmetry of the isolated tree. Calculate the attribute weight of each attribute based on its criticality and importance, and obtain the weight of the isolated tree based on the attribute weight and the structural symmetry of the isolated tree; obtain the degree of anomalousness of each attribute vector by weighting the attribute value of each attribute vector in the isolated tree with the weight of each isolated tree; and reduce the number of vectors based on the degree of anomalousness. The attribute vectors after excluding outlier data are used to construct a knowledge graph, and the visualization of vehicle energy consumption data is obtained based on the constructed knowledge graph.

2. The method of visualizing vehicle energy consumption data of claim 1, wherein, The attributes include the vehicle's travel distance, energy consumption, average speed, average ambient temperature, altitude change, and traffic congestion time. The knowledge graph of energy consumption data is updated every preset time, and the attribute values ​​between two knowledge graph updates are collected.

3. The method of visualizing vehicle energy consumption data of claim 1, wherein, The isolated tree contains only one attribute, and the leaf nodes of the isolated tree are attribute values ​​of the corresponding attribute in the attribute vector.

4. The method of visualizing vehicle energy consumption data of claim 1, wherein, The method for determining the importance of each attribute based on the correlation between different attributes in all attribute vectors is as follows: Sort the attribute values ​​of the same attribute in all attribute vectors in chronological order to obtain the attribute sequence for each attribute; calculate the correlation between each attribute sequence and the other attribute sequences, calculate the mean of all correlations corresponding to each attribute sequence, and use the mean as the importance of the attribute.

5. The method of visualizing vehicle energy consumption data of claim 1, wherein, The method for obtaining the degree of abnormality of each abnormal data in each attribute based on the difference between the attribute value of each abnormal data in each attribute in historical data and the mean attribute value of each attribute in historical data is as follows: FC (j,r) denotes the attribute value of the jth abnormal data corresponding to attribute r in the historical data, Bc r denotes the mean value of all attribute values of attribute r in the historical data, G (j,r) denotes the abnormal degree of the jth abnormal data corresponding to attribute r in the historical data.

6. The method of visualizing vehicle energy consumption data of claim 1, wherein, The method for determining the criticality of each attribute based on the degree of anomalousness of all abnormal data within each attribute in historical data and the probability of anomalies occurring in each attribute in historical data is as follows: The criticality of each attribute is negatively correlated with the degree of anomalousness of all outlier data within that attribute, and positively correlated with the probability of anomalies occurring in each attribute.

7. The method of visualizing vehicle energy consumption data of claim 1, wherein, The method for obtaining the structural symmetry of the isolated tree by weighting the difference between the balanced difference of each node and the balanced difference of the node and the nodes in the same layer according to the distance of each node from the root node is: H i represents the balance difference degree of the i-th node, H (i,v) represents the difference of the balance difference degree of the i-th node and the v-th node in the same layer as the i-th node, L represents the depth of the isolated tree, S i represents the difference between the layer number of the i-th node and the depth of the isolated tree, m represents the number of nodes in the isolated tree, exp() represents the exponential function with the natural constant as the base, and Hc represents the structural symmetry of the isolated tree.

8. The method of visualizing vehicle energy consumption data of claim 1, wherein, The method for calculating the attribute weight of each attribute according to the key degree and the importance degree of each attribute, and obtaining the weight of the isolated tree based on the attribute weight and the structural symmetry of the isolated tree is: The attribute weight is in positive correlation with the key degree and the importance degree of each attribute respectively; The weight of the isolated tree is in positive correlation with the structural symmetry of the isolated tree and the attribute weight of the attribute corresponding to the isolated tree.

9. The method of visualizing vehicle energy consumption data of claim 1, wherein, The method for obtaining the abnormal degree of each attribute vector by weighting the attribute value of each attribute vector of the isolated tree again by the weight of each isolated tree is: Rd c represents the weight of the cth isolated tree, p (c,x) represents the attribute value of the xth attribute vector in the cth isolated tree, B represents the number of isolated trees, exp() represents the exponential function with natural constant as base, E x represents the abnormality degree of the xth attribute vector.

10. A car energy consumption data visualization system comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, The processor implements the steps of the automobile energy consumption data visualization method according to any one of claims 1-9 when executing the computer program.

Images