Electric vehicle mileage anxiety quantification method, device, equipment and medium

Abstract

The invention relates to an electric vehicle mileage anxiety quantification method, device and equipment and a medium. The electric vehicle mileage anxiety quantification method comprises the following steps: acquiring operation data of an electric vehicle, and carrying out data preprocessing and target feature extraction on the operation data; on the basis of the extracted target features, performing anxiety value calculation according to a principal component analysis method and a Weber-Fechner law to obtain a corresponding static anxiety score; performing simulation prediction through a random forest algorithm to obtain a corresponding dynamic anxiety score; and performing fitting processing based on the static anxiety score and the dynamic anxiety score to obtain a corresponding comprehensive anxiety index. According to the embodiment of the invention, the anxiety level of the user under different driving situations can be reflected more accurately, other technical optimization is carried out based on the accurate anxiety index, the user is helped to better understand and manage mileage anxiety, confidence in the electric vehicle is enhanced, and wide popularization and application of the electric vehicle are promoted.

Description

Technical Field

[0001] The present disclosure relates to the application field of electric vehicle range anxiety quantification technology, and in particular to an electric vehicle range anxiety quantification method, device, equipment and medium. Background Art

[0002] With the improvement of global environmental awareness, electric vehicles have gradually attracted widespread attention due to their environmental protection and low emission advantages. However, the promotion of electric vehicles still faces the challenge of "range anxiety", that is, users are worried that they will not be able to reach their destination smoothly or find charging facilities due to insufficient power. This anxiety directly affects users' acceptance of electric vehicles. At present, most methods for measuring range anxiety are mainly based on user questionnaires, which measure users' perception of insufficient power through subjective feedback. However, the questionnaire method relies on the subjective feelings of users and is greatly restricted by individual psychological differences, environmental influences and other factors. It is difficult to accurately quantify the actual degree of anxiety and lacks objective behavioral data support.

[0003] In addition, traditional methods usually ignore the impact of dynamic driving behavior when quantifying range anxiety. Drivers' anxiety fluctuates significantly in different driving scenarios, and existing questionnaire methods cannot capture these dynamic changes. At the same time, the health of the battery decays over time, which has a direct impact on the actual range of electric vehicles, but traditional questionnaire methods cannot consider changes in battery status in real time, making anxiety assessments lack the integration of battery decay factors. These deficiencies make it impossible for questionnaire-based measurement results to fully reflect the actual anxiety experience of users during travel. Summary of the invention

[0004] In order to solve the above technical problems, the present disclosure provides a method, device, equipment and medium for quantifying range anxiety of electric vehicles.

[0005] In a first aspect, the present disclosure provides a method for quantifying electric vehicle range anxiety, comprising:

[0006] Acquiring operation data of the electric vehicle, and performing data preprocessing and target feature extraction on the operation data;

[0007] Based on the extracted target features, the anxiety value is calculated according to the principal component analysis method and the Weber-Fechner law to obtain the corresponding static anxiety score;

[0008] The corresponding dynamic anxiety score is obtained by simulation prediction through random forest algorithm;

[0009] A fitting process is performed based on the static anxiety score and the dynamic anxiety score to obtain a corresponding comprehensive anxiety index.

[0010] In a second aspect, the present disclosure provides a device for quantifying range anxiety of an electric vehicle, comprising:

[0011] A data acquisition module, used to acquire the operation data of the electric vehicle, and perform data preprocessing and target feature extraction on the operation data;

[0012] The first processing module is used to calculate the anxiety value based on the extracted target features according to the principal component analysis method and the Weber-Fechner law to obtain the corresponding static anxiety score;

[0013] The simulation prediction module is used to perform simulation prediction through the random forest algorithm to obtain the corresponding dynamic anxiety score;

[0014] The second processing module is used to perform fitting processing based on the static anxiety score and the dynamic anxiety score to obtain a corresponding comprehensive anxiety index.

[0015] In a third aspect, the present disclosure provides a device for quantifying range anxiety of an electric vehicle, comprising:

[0016] processor;

[0017] A memory for storing executable instructions;

[0018] The processor is used to read executable instructions from the memory and execute the executable instructions to implement the electric vehicle range anxiety quantification method of the first aspect.

[0019] In a fourth aspect, the present disclosure provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the processor implements the electric vehicle range anxiety quantification method of the first aspect.

[0020] Compared with the prior art, the technical solution provided by the embodiments of the present disclosure has the following advantages:

[0021] The electric vehicle range anxiety quantification method, device, equipment and medium of the disclosed embodiment can obtain the operation data of the electric vehicle, perform data preprocessing and target feature extraction on the operation data, and then calculate the anxiety value based on the extracted target features according to the principal component analysis method and the Weber-Fechner law to obtain the corresponding static anxiety score, and then simulate and predict through the random forest algorithm to obtain the corresponding dynamic anxiety score, and finally perform fitting processing based on the static anxiety score and the dynamic anxiety score to obtain the corresponding comprehensive anxiety index. Thus, the user's driving behavior, charging habits, battery status and other multidimensional factors are comprehensively considered to achieve accurate quantification of range anxiety. In this way, the user's anxiety level in different driving situations is more accurately reflected, and other technical optimizations are performed based on accurate anxiety indicators to help users better understand and manage range anxiety, enhance confidence in electric vehicles, and promote the widespread popularization and application of electric vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0023] Figure 1 A flow chart of a method for quantifying range anxiety of electric vehicles provided in an embodiment of the present disclosure;

[0024] Figure 2 A schematic diagram of the relationship between the three provided in an embodiment of the present disclosure;

[0025] Figure 3 A three-dimensional schematic diagram of a dynamic anxiety score provided by an embodiment of the present disclosure;

[0026] Figure 4 A three-dimensional schematic diagram of another dynamic anxiety score provided by an embodiment of the present disclosure;

[0027] Figure 5 A schematic diagram of the structure of a device for quantifying range anxiety of an electric vehicle provided in an embodiment of the present disclosure;

[0028] Figure 6 A schematic diagram of the structure of a device for quantifying range anxiety of an electric vehicle provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0029] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0030] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0031] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0032] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0033] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0034] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0035] In order to solve the above problems, the present disclosure provides a method, device, equipment and medium for quantifying electric vehicle range anxiety. Figures 1 to 4 The method for quantifying electric vehicle range anxiety provided by the embodiment of the present disclosure is described in detail.

[0036] Figure 1 A flow chart of a method for quantifying range anxiety of an electric vehicle provided in an embodiment of the present disclosure is shown.

[0037] In the disclosed embodiment, the electric vehicle range anxiety quantification method may be executed by an electronic device, wherein the electronic device may include but is not limited to devices such as computer devices, cloud servers or cloud server clusters.

[0038] like Figure 1 As shown, the electric vehicle range anxiety quantification method may include the following steps.

[0039] S110, acquiring operation data of the electric vehicle, and performing data preprocessing and target feature extraction on the operation data.

[0040] In the disclosed embodiment, the electronic device may acquire the operation data of the electric vehicle, and perform data preprocessing and target feature extraction on the operation data.

[0041] Optionally, the operating data may be data collected by various sensors when the vehicle is running.

[0042] Specifically, the electronic device can collect the operation data of the electric vehicle at a preset collection interval (such as 30s, 40s, etc.), such as timestamp, battery charge and discharge status, vehicle operation information, driver's driving behavior and total mileage, and then perform data preprocessing and target feature extraction on the operation data.

[0043] S120. Based on the extracted target features, the anxiety value is calculated according to the principal component analysis method and the Weber-Fechner law to obtain a corresponding static anxiety score.

[0044] In the disclosed embodiment, the electronic device may calculate the anxiety value based on the extracted target features according to the principal component analysis method and the Weber-Fechner law to obtain a corresponding static anxiety score.

[0045] Optionally, the principal component analysis method may be a statistical method, which aims to convert multidimensional features into a few comprehensive indicators (principal components) through linear transformation, thereby achieving dimensionality reduction of data.

[0046] Alternatively, the Weber-Fechner law is a law that shows the relationship between psychological quantities and physical quantities.

[0047] Specifically, the electronic device can calculate the anxiety value based on the extracted target features according to the principal component analysis method and the Weber-Fechner law to obtain a corresponding static anxiety score.

[0048] S130. Perform simulation prediction using a random forest algorithm to obtain a corresponding dynamic anxiety score.

[0049] In the disclosed embodiment, the electronic device can perform simulation prediction through a random forest algorithm to obtain a corresponding dynamic anxiety score.

[0050] Alternatively, the random forest algorithm is an ensemble learning method that builds multiple decision trees and combines their predictions to improve the accuracy and robustness of the overall model.

[0051] S140, performing fitting processing based on the static anxiety score and the dynamic anxiety score to obtain a corresponding comprehensive anxiety index.

[0052] In an embodiment of the present disclosure, the electronic device may perform fitting processing based on the static anxiety score and the dynamic anxiety score to obtain a corresponding comprehensive anxiety index.

[0053] Therefore, in the disclosed embodiment, the operation data of the electric vehicle can be obtained, and the operation data can be preprocessed and the target features can be extracted. Then, based on the extracted target features, the anxiety value is calculated according to the principal component analysis method and the Weber-Fechner law to obtain the corresponding static anxiety score. Then, the random forest algorithm is used for simulation prediction to obtain the corresponding dynamic anxiety score. Finally, the static anxiety score and the dynamic anxiety score are fitted to obtain the corresponding comprehensive anxiety index. Thus, the multi-dimensional factors such as the user's driving behavior, charging habits and battery status are comprehensively considered to achieve accurate quantification of mileage anxiety. This can more accurately reflect the user's anxiety level in different driving scenarios, thereby helping users to better understand and manage mileage anxiety, enhance confidence in electric vehicles, and promote the widespread popularization and application of electric vehicles.

[0054] Optionally, S110 may specifically include: performing data cleaning on the operating data, and dividing the operating data into travel data and charging data according to vehicle operating information, the vehicle operating information including vehicle status, charging status and vehicle operating mode; performing event division on the travel data and the charging data based on the vehicle status, the charging status and the vehicle operating mode to obtain corresponding target events, the target events including travel events and charging events.

[0055] In an embodiment of the present disclosure, the electronic device may perform data cleaning on the operating data and divide the operating data into travel data and charging data according to vehicle operating information, wherein the vehicle operating information includes vehicle status, charging status and vehicle operating mode.

[0056] Specifically, the electronic device can clean the operation data, process missing values ​​and abnormal values, and divide the data into travel data and charging data according to the vehicle operation information, and the vehicle operation information includes vehicle status, charging status and vehicle operation mode. For example, the electronic device can obtain the original data of the electric vehicle operation information and extract valid information. Each record of the original data consists of 17 fields, including: vehicle (VIN), data collection time (Time), longitude (Longitude), latitude (Latitude), vehicle status (Vehicle_Status), charging status (Charging_Status), operation mode (Operation_Mode), vehicle speed (Speed), cumulative mileage (Total_Mileage), total voltage (Total_Voltage), total current (Total_Current), battery power (SOC), gear (Gear), drive force (Drive_Force), brake force (Brake_Force), accelerator pedal travel value (Accelerator_Pedal_Travel), brake pedal status (Brake_Pedal_Status). According to the needs of the present invention, after extracting valid information, the data is divided into travel data and charging data and the events are numbered. The specific structure is shown in Table 1 and Table 2:

[0057] Table 1: Electric vehicle travel data

[0058]

[0059] Table 2: Electric vehicle charging data

[0060]

[0061]

[0062] Furthermore, the electronic device may divide the travel data and the charging data into events based on the vehicle state, the charging state and the vehicle operation mode to obtain corresponding target events, where the target events include travel events and charging events.

[0063] For example, the state values ​​corresponding to the vehicle operation mode field are all "1", which means that the collected cars are all pure electric vehicles; the state values ​​corresponding to the vehicle status field are "1" and "3", when the corresponding value of the vehicle status field is "1", it means that the electric vehicle is running, and when the corresponding value of the vehicle status field is "3", it means that the vehicle is stationary; the state values ​​corresponding to the charging status field are "1" and "3", when the corresponding value of the charging status field is "1", it means that the electric vehicle is charging, and when the corresponding value of the charging status field is "3", it means that the electric vehicle is not charging, which may include the situation where the vehicle is stationary and the vehicle is driving;

[0064] In order to distinguish different travel and charging situations of vehicles, the combination of vehicle status and charging status will be used for screening. When the vehicle status is "2" and the charging status is "1", the vehicle is in a stopped charging state, when the vehicle status is "1" and the charging status is "1", the vehicle is in a stationary charging state (the owner may stay in the car), and the charging status is "4" when charging is completed. These fragments are extracted to identify charging events (after the charging fragment is extracted, the points will be removed from the original data to facilitate extraction with subsequent fragments); the data with a vehicle status of "1" is regarded as a travel fragment.

[0065] Furthermore, the travel events and charging events of each vehicle are marked: Marking of charging events: Charging events are identified by monitoring the increase and decrease trend of the power (SOC). When the SOC value continues to increase, it means that the vehicle is charging. Until the SOC value stops rising, it is marked as a charging event. When the SOC decreases, it means that the charging is over and a new event is identified; Marking of travel events: Travel events are identified based on the decreasing trend of time and SOC. The data continuity is required in time, and the maximum time interval shall not exceed 30 minutes. At the same time, the SOC needs to show a decreasing trend. In order to avoid the introduction of noise, a small increase in SOC (less than 2) is allowed and regarded as an acceptable fluctuation in the data. Finally, each travel and charging event of each vehicle during the study period is marked.

[0066] Optionally, the electric vehicle range anxiety quantification method may further include: extracting original features of the operating data, and constructing features based on the original features to obtain corresponding new features, wherein the target features include the new features.

[0067] In the disclosed embodiment, the electronic device may extract original features of the operating data, and perform feature construction based on the original features to obtain corresponding new features.

[0068] Specifically, the electronic device can extract the original features of the operating data, such as battery power, vehicle speed, accelerator pedal travel value, cumulative mileage, etc., and construct features based on the original features to obtain corresponding new features, such as the average state of charge (SOC) at the beginning and end of charging, the proportion of time driving at low SOC, the average speed under different power states, the average accelerator pedal under different power states, the vehicle's SOC decrease rate, etc.

[0069] For example, in order to capture the behavioral characteristics of mileage anxiety, new features were introduced through the battery power, vehicle speed, accelerator pedal travel value, and cumulative mileage in the original data: the average SOC at the beginning and end of charging, the proportion of time driving with low SOC, the average speed at different power states, the average accelerator pedal at different power states, and the vehicle's SOC decrease rate; the higher the average SOC at the beginning of charging, the more worried the user is about the low power of the vehicle, while the lower the average SOC at the end of charging, the less worried the user is about the low power; the proportion of time driving with low SOC, defining the time when SOC is below 30 as a low power state, and calculating the proportion of driving time under low power to the total travel time, reflecting the user's tolerance for low power, and the proportion of low SOC driving time. A high value of the driving time ratio may mean that the user has a high tolerance for low battery, which reflects a lower tendency to anxiety, while a low value of the low SOC driving time ratio is the opposite; the SOC is divided into three intervals (high battery: ≥80, medium battery: 30-80, low battery: <30), and the extraction of the average speed under different battery states and the average accelerator pedal under different battery states reflects the anxiety tendency well; the SOC decrease rate of the vehicle is the SOC consumption per kilometer, and the total travel distance and SOC difference are calculated by the cumulative mileage difference of each travel event, which is the travel power consumption. The ratio of the two is the SOC decrease rate of this trip, and the average SOC decrease rate of multiple travel events of the vehicle is calculated as the energy efficiency feature of a single vehicle.

[0070] Next, for each vehicle, all travel events and charging events are extracted features: the average SOC at the start and end of charging, the proportion of time for low SOC driving, the average speed at different power states, the average accelerator pedal at different power states, and the vehicle's SOC drop rate; after integrating all valid features, a feature data set is formed. The specific structure is shown in Table 3:

[0071] Table 3: Feature set

[0072]

[0073]

[0074] Optionally, the electric vehicle range anxiety quantification method may further include: based on the target features, performing component extraction according to the principal component analysis method to obtain a perception coefficient.

[0075] In the disclosed embodiment, the electronic device may extract components based on the target features according to the principal component analysis method to obtain a perception coefficient.

[0076] Specifically, the electronic device can extract components based on the target features according to the principal component analysis (PCA) method to obtain a perception coefficient (k). A higher k value means that the user has a higher anxiety tendency.

[0077] For example, PCA is used to extract the first principal component to capture the main trend in the features, and the generated k value is expected to reflect the user's anxiety tendency to the greatest extent; in the feature processing process, the direction is adjusted to ensure that the larger the feature values, the stronger the anxiety tendency; specifically, the low-battery driving ratio is inverted, and the ratio is defined as "1-low-battery driving ratio", that is, the less time the user drives at low battery, the stronger the anxiety tendency; the starting SOC (Start_SOC) directly uses the original value, which represents the user's higher anxiety tendency when starting charging at a higher battery; the ending SOC (En_SOC) is directly used. d_SOC) directly uses the original value, which represents the user's lower anxiety tendency when the charging is completed at a lower power level; for the speed and acceleration at different power levels, the speed and acceleration at a high power level keep the original value, indicating that the user is in a relaxed state, while the speed and acceleration at a low power level are reversed, specifically "maximum speed-low SOC average speed" and "maximum acceleration-low SOC average acceleration", ensuring that the lower speed and acceleration at a low power level can reflect a higher anxiety tendency; the vehicle characteristics are added to the feature matrix by appropriately reducing the weight (such as multiplying by a coefficient of 0.2) to avoid excessive influence in the final model.

[0078] After the direction adjustment, the feature matrix was constructed and the adjusted features were merged with the missing mark matrix. Before entering the PCA, the feature matrix was standardized to adjust each feature to a standard normal distribution with a mean of 0 and a variance of 1 to ensure the balance of features of different scales and prevent features with values ​​that are too large or too small from dominating the PCA calculation results. Next, PCA dimensionality reduction was performed on the standardized feature matrix, and the one-dimensional principal component was extracted as the perception coefficient k value, so that the influence of multiple features can be measured by a single value. To ensure the non-negativity of the k value, it was translated, that is, the minimum k value was translated to zero and a small positive value was added.

[0079] Optionally, the electric vehicle range anxiety quantification method may further include: based on the perception coefficient, calculating the anxiety value of different travel events according to the Weber-Fechner law to obtain an original range anxiety value; normalizing the original range anxiety value to obtain the static anxiety score.

[0080] In an embodiment of the present disclosure, the electronic device can calculate the anxiety value of different travel events based on the perception coefficient and according to the Weber-Fechner law to obtain the original mileage anxiety value, and then normalize the original mileage anxiety value to obtain the static anxiety score.

[0081] The Weber-Fechner Law is a psychophysical law that describes the relationship between the intensity of physical stimuli and human subjective perception, usually expressed as:

[0082] S = k × ln (I) (1).

[0083] In the formula, s is the intensity of perception; I is the intensity of external stimulation; k is the perception coefficient, which is related to the individual's sensitivity to stimulation.

[0084] Among them, the ratio of the total travel distance to the initial power of the trip is regarded as the intensity of external stimulation. This ratio can effectively reflect the relationship between the driving distance and the power pressure: the longer the travel distance and the lower the initial power, the greater the stimulation intensity, and the higher the mileage anxiety caused to the user; based on the logarithmic perception formula of the Weber-Fechner law, the original mileage anxiety value Sraw of each travel event is calculated, that is:

[0085] S raw =k×ln(1+I) (2).

[0086] Where: S raw is the original mileage anxiety value, k is the anxiety tendency of the vehicle, and I is the stimulus intensity of the current travel event. Using ln(1+I) instead of directly taking the logarithm can ensure that a non-zero perceptual effect can be produced even in low-intensity situations.

[0087] To facilitate the comparison of anxiety levels, the original anxiety value s raw Normalized to a scale of 0 to 10:

[0088]

[0089] where s min and max are the minimum and maximum original anxiety values ​​of all travel events, respectively. This normalization method makes the normalized score values ​​distributed between 0 and 10, and a larger score indicates a higher anxiety tendency.

[0090] Next, the first principal component of the extracted features was extracted through PCA as the anxiety tendency k value, which was used as the inherent feature of each vehicle. For all travel events of different vehicles, the ratio of the total travel distance of each event to the initial travel power was regarded as the external stimulus intensity at that time, and the static anxiety scores generated by different vehicles and different travels were calculated. The results are shown in Table 4:

[0091] Table 4: Anxiety scores for different travel events

[0092]

[0093] Optionally, S130 may specifically include: performing model training based on the random forest algorithm to obtain a target prediction model; and performing simulation predictions on different travel events based on the target prediction model to obtain corresponding dynamic anxiety scores.

[0094] In an embodiment of the present disclosure, the electronic device may perform model training based on the random forest algorithm to obtain a target prediction model, and then perform simulation predictions on different travel events based on the target prediction model to obtain corresponding dynamic anxiety scores.

[0095] For example, the anxiety score of a travel event is predicted based on the total travel distance, initial battery power, and anxiety tendency k. Five models, including linear regression, decision tree, random forest, gradient boosting, and support vector regressor, are used for prediction. The three indicators of RMSE, R2 Score, and Cross-validated RMSE are used for comparison to select the most appropriate model for prediction.

[0096] Figure 2 A schematic diagram showing a relationship between three provided by an embodiment of the present disclosure is shown.

[0097] like Figure 2 As shown in the figure, in order to verify the rationality of the quantification results, the data are grouped according to the stimulation intensity I, and the anxiety scores of users with different k values ​​are observed under the same stimulation intensity. As the k value (i.e., sensitivity to mileage anxiety) increases, the anxiety score also increases accordingly, indicating that a higher k value usually corresponds to a higher sense of anxiety. At the same time, as the stimulation intensity increases, the range of anxiety scores in each group gradually increases, especially under the conditions of high k value and high stimulation intensity, the anxiety score of the user increases significantly, verifying the rationality of the quantification model.

[0098] Next, for Initial_SOC, Stimulus_Intensity, and k_value to predict the Anxiety_Score of travel events, five models, including linear regression, decision tree, random forest, gradient boosting, and support vector regressor, were used for prediction. The three indicators of RMSE, R2 Score, and Cross-validated RMSE were used for comparison. Finally, the random forest with the lowest three indicators was selected for prediction. The prediction results of the model are summarized in Table 5:

[0099] Table 5: Model prediction results

[0100] Model RMSE <![CDATA[R 2 Score]]> Cross-validated RMSE Linear Regression 0.771352977 0.620583856 0.756687329 Decision Tree 0.228444277 0.966721017 0.271515781 Random Forest 0.168508678 0.981892686 0.196714857 Gradient Boosting 0.185398493 0.978080942 0.230054412 Support Vector Regressor 0.382365282 0.906767702 0.419348483

[0101] Figure 3 A three-dimensional schematic diagram of a dynamic anxiety score provided by an embodiment of the present disclosure is shown.

[0102] like Figure 3 As shown, in order to more intuitively see the dynamic changes of anxiety value with the increase of travel distance, a three-dimensional graph is displayed based on the predicted data. First, the mean value of k_value is used as a fixed value to observe the dynamic relationship between Distance_Traveled, Initial_SOC and Anxiety_Score. Figure 3 The effect of distance traveled and initial power (Initial_SOC) on the predicted anxiety score (Predicted Anxiety_Score) under the condition of a fixed perception coefficient k value (4.23) is shown. Overall, the predicted anxiety score gradually increases with the increase in driving distance, reflecting the driving effect of increased mileage on user anxiety. At the same time, the initial power also has a significant impact on the anxiety score: in the case of high initial power (for example, above 80), the anxiety score remains low, indicating that the user has less anxiety when the power is sufficient; and in the case of low initial power, the longer the driving distance, the faster the anxiety score rises. This shows that under low power and long distance conditions, the user's mileage anxiety will increase significantly, which is in line with expectations.

[0103] Figure 4 A three-dimensional schematic diagram of another dynamic anxiety score provided by an embodiment of the present disclosure is shown.

[0104] like Figure 4 As shown, taking the mean value of Initial_SOC as a fixed value, the dynamic relationship among Distance_Traveled, k_value and Anxiety_Score is observed. Figure 4The effect of driving distance and perception coefficient k value on anxiety score under the condition of fixed initial power (67.52) is shown. As the driving distance increases, the anxiety score continues to rise, indicating the promoting effect of increased mileage on anxiety. More significantly, the increase in the perception coefficient k value significantly increases the anxiety score, especially when the k value is high (above 8), the effect of long-distance driving on the anxiety score is particularly significant. This shows that users with higher k values ​​(i.e., higher anxiety sensitivity) are more likely to have higher mileage anxiety during long-distance driving. The two figures jointly verify the rationality of the changes in anxiety scores with driving distance, initial power and k value, showing that the quantitative model effectively characterizes the user's mileage anxiety level.

[0105] Optionally, S140 may specifically include: fitting a dynamic change curve of different travel events based on the dynamic anxiety score; extracting a normalized average mileage anxiety value and a maximum anxiety score based on the static anxiety score, and extracting an anxiety growth rate based on the dynamic change curve to obtain a plurality of anxiety indicators; fitting the plurality of anxiety indicators by principal component analysis to obtain the comprehensive anxiety index.

[0106] In an embodiment of the present disclosure, the electronic device can fit a dynamic change curve of different travel events based on the dynamic anxiety score, then extract the normalized average mileage anxiety value and the maximum anxiety score based on the static anxiety score, and extract the anxiety growth rate based on the dynamic change curve to obtain multiple anxiety indicators, and finally fit the multiple anxiety indicators through principal component analysis to obtain the comprehensive anxiety index.

[0107] For example, the comprehensive index of each vehicle is calculated by grouping by vehicle (VIN). First, three features are extracted: the normalized average mileage anxiety value, the maximum anxiety score, and the anxiety growth rate. For the normalized average mileage anxiety value, the predicted anxiety score at each driving distance is normalized according to the initial SOC, and the average of the normalized scores is calculated. This feature represents the average anxiety level of the user per unit of initial power, which is used to quantify the anxiety sensitivity of the user at similar driving distances. The maximum anxiety score extracts the highest anxiety score of each vehicle in actual travel events to reflect the user's maximum experience of mileage anxiety in historical records, which provides a peak reference point for the comprehensive index and facilitates understanding of the user's anxiety level under extreme conditions. For the anxiety growth rate, a distance sequence from 0 to 100 kilometers is used to simulate the change of anxiety scores at different driving distances. By calculating the change rate of the predicted anxiety score at different distance values, the anxiety growth rate is obtained, that is, the change of the anxiety score with the increase of driving distance. Specifically, the difference of each adjacent distance is calculated, and the difference of the anxiety score is divided by the corresponding distance difference to obtain the anxiety growth rate per unit distance. This indicator reflects the sensitivity of user anxiety to the increase of driving distance.

[0108] The principal component analysis (PCA) was used to integrate multiple anxiety indicators for each vehicle to generate a composite anxiety score. The three features of normalized average mileage anxiety value, anxiety growth rate, and maximum anxiety score were standardized to ensure balanced contributions in the PCA. The three features were compressed into a principal component through PCA to represent the overall anxiety level of each vehicle. In order to make the larger score represent higher anxiety, the principal component was reversed and the result was normalized to a scale of 0 to 10.

[0109] The comprehensive anxiety index provides a unified quantitative indicator for each vehicle, reflecting its range anxiety level during driving. By integrating multiple anxiety characteristics, the score can intuitively quantify the anxiety tendency of individual users, facilitate cross-vehicle comparison, and identify which models or user groups are more prone to anxiety. At the same time, the score also reflects the user's anxiety sensitivity, providing a valuable reference for vehicle management and service providers to develop personalized anxiety intervention strategies and optimize the user's range experience.

[0110] In order to obtain a single composite anxiety index (Composite Anxiety Score), principal component analysis (PCA) was used to reduce the dimensionality of the above three features. First, the features were standardized to eliminate the impact of dimensional differences, and then a principal component was extracted through PCA as a comprehensive score to retain the information of the original features to the maximum extent. To ensure that the scoring direction is reasonable (that is, the higher the score, the stronger the anxiety), the principal component was reversed and normalized to a scale of 0 to 10 to facilitate direct comparison between different vehicles. The specific results are shown in Table 6:

[0111] Table 6: Comprehensive anxiety index

[0112]

[0113] The comprehensive anxiety index obtained through this method can stably and objectively reflect the anxiety level of each vehicle in different driving scenarios, providing data support for further optimizing the design and improving the user experience.

[0114] Figure 5 A schematic structural diagram of a device for quantifying range anxiety of an electric vehicle provided in an embodiment of the present disclosure is shown.

[0115] like Figure 5 As shown, the electric vehicle range anxiety quantification device 500 may include a data acquisition module 510 , a first processing module 520 , a simulation prediction module 530 and a third processing module 540 .

[0116] The data acquisition module 510 can be used to acquire the operation data of the electric vehicle, and perform data preprocessing and target feature extraction on the operation data.

[0117] The first processing module 520 can be used to calculate the anxiety value based on the extracted target features according to the principal component analysis method and the Weber-Fechner law to obtain a corresponding static anxiety score.

[0118] The simulation prediction module 530 can be used to perform simulation prediction using a random forest algorithm to obtain a corresponding dynamic anxiety score.

[0119] The third processing module 540 may be used to perform fitting processing based on the static anxiety score and the dynamic anxiety score to obtain a corresponding comprehensive anxiety index.

[0120] Therefore, in the disclosed embodiment, the operation data of the electric vehicle can be obtained, and the operation data can be preprocessed and the target features can be extracted. Then, based on the extracted target features, the anxiety value is calculated according to the principal component analysis method and the Weber-Fechner law to obtain the corresponding static anxiety score. Then, the random forest algorithm is used for simulation prediction to obtain the corresponding dynamic anxiety score. Finally, the static anxiety score and the dynamic anxiety score are fitted to obtain the corresponding comprehensive anxiety index. Thus, the multi-dimensional factors such as the user's driving behavior, charging habits and battery status are comprehensively considered to achieve accurate quantification of mileage anxiety. This can more accurately reflect the user's anxiety level in different driving scenarios, thereby helping users to better understand and manage mileage anxiety, enhance confidence in electric vehicles, and promote the widespread popularization and application of electric vehicles.

[0121] In some embodiments of the present disclosure, the data acquisition module 510 may specifically include a first processing unit and a second processing unit.

[0122] The first processing unit may be used to clean the operating data and divide the operating data into travel data and charging data according to vehicle operating information, wherein the vehicle operating information includes a vehicle state, a charging state, and a vehicle operating mode.

[0123] The second processing unit can be used to perform event division on the travel data and the charging data based on the vehicle state, the charging state and the vehicle operation mode to obtain corresponding target events, where the target events include travel events and charging events.

[0124] In some embodiments of the present disclosure, the electric vehicle range anxiety quantification device 500 may further include a first extraction module.

[0125] The first extraction module can be used to extract original features of the operating data, and perform feature construction based on the original features to obtain corresponding new features, and the target features include the new features.

[0126] In some embodiments of the present disclosure, the electric vehicle range anxiety quantification device 500 may further include a second extraction module and a third processing module.

[0127] The second extraction module can be used to calculate the anxiety value of different travel events based on the perception coefficient and according to the Weber-Fechner law to obtain the original mileage anxiety value.

[0128] The third processing module can be used to normalize the original mileage anxiety value to obtain the static anxiety score.

[0129] In some embodiments of the present disclosure, the simulation prediction module 530 may specifically include a model training unit and a simulation prediction unit.

[0130] The model training unit can be used to perform model training based on the random forest algorithm to obtain a target prediction model.

[0131] The simulation prediction unit can be used to simulate and predict different travel events based on the target prediction model to obtain corresponding dynamic anxiety scores.

[0132] In some embodiments of the present disclosure, the third processing module 540 may specifically include a third processing unit, a fourth processing unit, and a fifth processing unit.

[0133] The third processing unit can be used to fit dynamic change curves of different travel events based on the dynamic anxiety score.

[0134] The fourth processing unit can be used to extract a normalized average mileage anxiety value and a maximum anxiety score based on the static anxiety score, and extract an anxiety growth rate based on the dynamic change curve to obtain a plurality of anxiety indicators.

[0135] The fifth processing unit can be used to perform fitting processing on the multiple anxiety indicators through principal component analysis to obtain the comprehensive anxiety indicator.

[0136] It should be noted that Figure 5 The electric vehicle range anxiety quantification device 500 shown can perform Figures 1 to 4 The various steps in the method embodiment shown in the figure are implemented Figures 1 to 4 The various processes and effects in the method embodiment shown are not described in detail here.

[0137] Figure 6A schematic structural diagram of a device for quantifying range anxiety of an electric vehicle provided in an embodiment of the present disclosure is shown.

[0138] In some embodiments of the present disclosure, Figure 6 The electric vehicle range anxiety quantification device shown may be an electronic device. Specifically, the electronic device may include but is not limited to devices such as computer devices, cloud servers or cloud server clusters.

[0139] like Figure 6 As shown, the electric vehicle range anxiety quantification device may include a processor 601 and a memory 602 storing computer program instructions.

[0140] Specifically, the processor 601 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0141] The memory 602 may include a large capacity memory for information or instructions. By way of example and not limitation, the memory 602 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a tape, or a universal serial bus (USB) drive or a combination of two or more of these. Where appropriate, the memory 602 may include a removable or non-removable (or fixed) medium. Where appropriate, the memory 602 may be inside or outside the integrated gateway device. In a particular embodiment, the memory 602 is a non-volatile solid-state memory. In a particular embodiment, the memory 602 includes a read-only memory (ROM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (Electrically Erasable Programmable ROM, EEPROM), an electrically rewritable ROM (EAROM) or a flash memory, or a combination of two or more of these.

[0142] The processor 601 reads and executes the computer program instructions stored in the memory 602 to perform the steps of the electric vehicle range anxiety quantification method provided in the embodiment of the present disclosure.

[0143] In one example, the electric vehicle range anxiety quantification device may further include a transceiver 603 and a bus 604. Figure 6 As shown, the processor 601, the memory 602 and the transceiver 603 are connected via a bus 604 and communicate with each other.

[0144] The bus 604 includes hardware, software, or both. For example, but not limitation, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industrial Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a MicroChannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses or a combination of two or more of these. Where appropriate, the bus 604 may include one or more buses. Although embodiments of the present application describe and illustrate a particular bus, the present application contemplates any suitable bus or interconnect.

[0145] The embodiment of the present disclosure also provides a computer-readable storage medium, which can store a computer program. When the computer program is executed by a processor, the processor implements the electric vehicle range anxiety quantification method provided by the embodiment of the present disclosure.

[0146] The above-mentioned storage medium may, for example, include a memory 602 of computer program instructions, and the above-mentioned instructions may be executed by a processor 601 of an electric vehicle range anxiety quantification device to complete the electric vehicle range anxiety quantification method provided by the embodiment of the present disclosure. Optionally, the storage medium may be a non-temporary computer-readable storage medium, for example, the non-temporary computer-readable storage medium may be a ROM, a random access memory (Random Access Memory, RAM), a compact disc read-only memory (Compact Disc ROM, CD-ROM), a magnetic tape, a floppy disk, and an optical data storage device, etc.

[0147] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the term "comprising" is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0148] The above description is only a specific embodiment of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for quantifying electric vehicle range anxiety, characterized in that: include: Acquiring operation data of the electric vehicle, and performing data preprocessing and target feature extraction on the operation data; Based on the extracted target features, the anxiety value is calculated according to the principal component analysis method and the Weber-Fechner law to obtain the corresponding static anxiety score; The corresponding dynamic anxiety score is obtained by simulation prediction through random forest algorithm; A fitting process is performed based on the static anxiety score and the dynamic anxiety score to obtain a corresponding comprehensive anxiety index.

2. The method according to claim 1, characterized in that: The performing data preprocessing on the operation data comprises: Cleaning the operation data, and dividing the operation data into travel data and charging data according to vehicle operation information, wherein the vehicle operation information includes vehicle status, charging status, and vehicle operation mode; The travel data and the charging data are divided into events based on the vehicle state, the charging state and the vehicle operation mode to obtain corresponding target events, where the target events include travel events and charging events.

3. The method according to claim 2, characterized in that The method further comprises: Original features of the operation data are extracted, and features are constructed based on the original features to obtain corresponding new features, wherein the target features include the new features.

4. The method according to claim 1, characterized in that The method further comprises: Based on the target features, components are extracted according to the principal component analysis method to obtain perception coefficients.

5. The method according to claim 4, characterized in that The method further comprises: Based on the perception coefficient, anxiety values ​​of different travel events are calculated according to the Weber-Fechner law to obtain an original mileage anxiety value; The original mileage anxiety value is normalized to obtain the static anxiety score.

6. The method according to claim 1, characterized in that The simulation prediction by the random forest algorithm is used to obtain the corresponding dynamic anxiety score, including: Performing model training based on the random forest algorithm to obtain a target prediction model; Based on the target prediction model, different travel events are simulated and predicted to obtain corresponding dynamic anxiety scores.

7. The method according to claim 1, characterized in that A fitting process is performed based on the static anxiety score and the dynamic anxiety score to obtain a corresponding comprehensive anxiety index, including: Fitting dynamic change curves of different travel events based on the dynamic anxiety scores; Extracting a normalized average mileage anxiety value and a maximum anxiety score based on the static anxiety score, and extracting an anxiety growth rate based on the dynamic change curve to obtain a plurality of anxiety indicators; The plurality of anxiety indices are fitted by principal component analysis to obtain the comprehensive anxiety index.

8. A device for quantifying electric vehicle range anxiety, characterized in that: include: A data acquisition module, used to acquire the operation data of the electric vehicle, and perform data preprocessing and target feature extraction on the operation data; The first processing module is used to calculate the anxiety value based on the extracted target features according to the principal component analysis method and the Weber-Fechner law to obtain the corresponding static anxiety score; The simulation prediction module is used to perform simulation prediction through the random forest algorithm to obtain the corresponding dynamic anxiety score; The second processing module is used to perform fitting processing based on the static anxiety score and the dynamic anxiety score to obtain a corresponding comprehensive anxiety index.

9. An electric vehicle range anxiety quantification device, characterized in that: include: processor; A memory for storing executable instructions; Wherein, the processor is used to read the executable instructions from the memory and execute the executable instructions to implement the electric vehicle range anxiety quantification method described in any one of claims 1-7.

10. A non-volatile computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements the electric vehicle range anxiety quantification method described in any one of claims 1 to 7.

Images