Driving condition construction method and device, computer equipment, readable storage medium and program product

Abstract

The invention relates to a driving condition construction method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the steps of obtaining vehicle driving data; dividing the vehicle driving data into a plurality of kinematics segments; according to pre-extracted speed dimension features, clustering processing is carried out on the plurality of kinematics fragments in a vehicle speed dimension, and a vehicle speed cluster corresponding to each vehicle speed category is obtained; for the vehicle speed clustering cluster corresponding to each vehicle speed category, according to pre-extracted seasonal dimension features, performing clustering processing on kinematics fragments in the vehicle speed clustering cluster corresponding to the current vehicle speed category in seasonal dimensions to obtain a seasonal clustering cluster corresponding to each seasonal category under the current vehicle speed category; and constructing a multi-dimensional driving condition based on the season cluster corresponding to each season category under each vehicle speed category. The multi-dimensional driving condition comprises information of two dimensions of speed and season, and real driving characteristics in different seasons can be better reflected.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a driving condition construction method, device, computer equipment, computer-readable storage medium and computer program product. Background Art

[0002] The construction of driving conditions is one of the most important aspects of vehicle testing. In the existing scheme, the driving conditions are mainly constructed based on the dimension of vehicle speed. However, this method has a relatively single dimension and the driving characteristics reflected by the constructed driving conditions are limited. Summary of the invention

[0003] Based on this, it is necessary to provide a driving condition construction method, device, computer equipment, computer-readable storage medium and computer program product that can improve the richness of driving conditions in response to the above technical problems.

[0004] In a first aspect, the present application provides a driving condition construction method, comprising:

[0005] Acquire vehicle driving data, wherein the vehicle driving data includes vehicle speed dimension data, electric drive dimension data, and season dimension data collected at each collection time;

[0006] Dividing the vehicle driving data into a plurality of kinematic segments;

[0007] According to the pre-extracted speed dimension features, clustering processing is performed on the multiple kinematic segments in the vehicle speed dimension to obtain a vehicle speed cluster corresponding to each vehicle speed category;

[0008] For the vehicle speed clusters corresponding to each vehicle speed category, according to the pre-extracted seasonal dimension features, the kinematic segments in the vehicle speed clusters corresponding to the current vehicle speed category are clustered in the seasonal dimension to obtain seasonal clusters corresponding to each seasonal category under the current vehicle speed category;

[0009] Based on the seasonal clusters corresponding to each seasonal category under each vehicle speed category, a multi-dimensional driving condition is constructed.

[0010] In one embodiment, before dividing the vehicle driving data into a plurality of kinematic segments, the method further includes:

[0011] The vehicle driving data is sequentially subjected to at least one of data cleaning processing, abnormal information elimination processing, and missing information completion processing.

[0012] In one embodiment, before clustering the plurality of kinematic segments in the vehicle speed dimension, the method further includes:

[0013] Performing principal component analysis on the extracted speed dimension features to obtain the contribution of each speed dimension feature; and performing data screening processing on the extracted speed dimension features based on the contribution;

[0014] Before clustering the kinematic segments in the vehicle speed cluster corresponding to the current vehicle speed category in the seasonal dimension, the method further includes:

[0015] The extracted seasonal dimension features are subjected to principal component analysis to obtain the contribution of each seasonal dimension feature; based on the contribution, the extracted seasonal dimension features are subjected to data screening processing.

[0016] In one embodiment, dividing the vehicle driving data into a plurality of kinematic segments comprises:

[0017] extracting an idle segment from the vehicle driving data;

[0018] The segment between two adjacent idle segments is regarded as a stable operation segment;

[0019] For each idle segment, the current idle segment and the stable operation segment after the current idle segment are divided into one kinematic segment, thereby obtaining a plurality of kinematic segments.

[0020] In one embodiment, clustering the plurality of kinematic segments in the vehicle speed dimension according to the pre-extracted speed dimension features to obtain a vehicle speed cluster corresponding to each vehicle speed category includes:

[0021] Determine a corresponding number of vehicle speed cluster centers according to the pre-extracted speed dimension features;

[0022] Divide each kinematic segment into a vehicle speed cluster corresponding to the nearest vehicle speed cluster center, and obtain vehicle speed clusters matching the number of pre-divided vehicle speed categories;

[0023] For each vehicle speed cluster, a fitness value is calculated according to each kinematic segment in the current vehicle speed cluster, and a latest cluster center is calculated according to the fitness value;

[0024] The vehicle speed cluster center is updated to the latest cluster center, and the step of dividing each kinematic segment into the vehicle speed cluster corresponding to the nearest vehicle speed cluster center is continued until the kinematic segments included in each vehicle speed cluster no longer change or the number of executions reaches a preset value.

[0025] In one embodiment, the multi-dimensional driving condition is constructed based on the seasonal clusters corresponding to each seasonal category under each vehicle speed category, including:

[0026] Obtain seasonal requirements for working condition construction;

[0027] Extracting a seasonal cluster that meets the seasonal requirements from the seasonal clusters corresponding to each seasonal category under each vehicle speed category;

[0028] Sampling the kinematic segments in the extracted seasonal clusters to obtain a plurality of kinematic samples that meet the seasonal requirements;

[0029] The multiple kinematic samples are spliced ​​together to obtain a multi-dimensional driving condition.

[0030] In a second aspect, the present application also provides a driving condition construction device, comprising:

[0031] An acquisition module, used to acquire vehicle driving data, wherein the vehicle driving data includes vehicle speed dimension data, electric drive dimension data and season dimension data collected at each collection time;

[0032] A division module, used for dividing the vehicle driving data into a plurality of kinematic segments;

[0033] A clustering processing module is used to perform clustering processing on the multiple kinematic segments in the vehicle speed dimension according to the pre-extracted speed dimension features, so as to obtain a vehicle speed cluster corresponding to each vehicle speed category; for the vehicle speed cluster corresponding to each vehicle speed category, the kinematic segments in the vehicle speed cluster corresponding to the current vehicle speed category are clustered in the season dimension according to the pre-extracted season dimension features, so as to obtain a season cluster corresponding to each season category under the current vehicle speed category;

[0034] The construction module is used to construct multi-dimensional driving conditions based on the seasonal clusters corresponding to each seasonal category under each vehicle speed category.

[0035] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0036] Acquire vehicle driving data, wherein the vehicle driving data includes vehicle speed dimension data, electric drive dimension data, and season dimension data collected at each collection time;

[0037] Dividing the vehicle driving data into a plurality of kinematic segments;

[0038] According to the pre-extracted speed dimension features, clustering processing is performed on the multiple kinematic segments in the vehicle speed dimension to obtain a vehicle speed cluster corresponding to each vehicle speed category;

[0039] For the vehicle speed clusters corresponding to each vehicle speed category, according to the pre-extracted seasonal dimension features, the kinematic segments in the vehicle speed clusters corresponding to the current vehicle speed category are clustered in the seasonal dimension to obtain seasonal clusters corresponding to each seasonal category under the current vehicle speed category;

[0040] Based on the seasonal clusters corresponding to each seasonal category under each vehicle speed category, a multi-dimensional driving condition is constructed.

[0041] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0042] Acquire vehicle driving data, wherein the vehicle driving data includes vehicle speed dimension data, electric drive dimension data, and season dimension data collected at each collection time;

[0043] Dividing the vehicle driving data into a plurality of kinematic segments;

[0044] According to the pre-extracted speed dimension features, clustering processing is performed on the multiple kinematic segments in the vehicle speed dimension to obtain a vehicle speed cluster corresponding to each vehicle speed category;

[0045] For the vehicle speed clusters corresponding to each vehicle speed category, according to the pre-extracted seasonal dimension features, the kinematic segments in the vehicle speed clusters corresponding to the current vehicle speed category are clustered in the seasonal dimension to obtain seasonal clusters corresponding to each seasonal category under the current vehicle speed category;

[0046] Based on the seasonal clusters corresponding to each seasonal category under each vehicle speed category, a multi-dimensional driving condition is constructed.

[0047] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0048] Acquire vehicle driving data, wherein the vehicle driving data includes vehicle speed dimension data, electric drive dimension data, and season dimension data collected at each collection time;

[0049] Dividing the vehicle driving data into a plurality of kinematic segments;

[0050] According to the pre-extracted speed dimension features, clustering processing is performed on the multiple kinematic segments in the vehicle speed dimension to obtain a vehicle speed cluster corresponding to each vehicle speed category;

[0051] For the vehicle speed clusters corresponding to each vehicle speed category, according to the pre-extracted seasonal dimension features, the kinematic segments in the vehicle speed clusters corresponding to the current vehicle speed category are clustered in the seasonal dimension to obtain seasonal clusters corresponding to each seasonal category under the current vehicle speed category;

[0052] Based on the seasonal clusters corresponding to each seasonal category under each vehicle speed category, a multi-dimensional driving condition is constructed.

[0053] The above-mentioned driving condition construction method, device, computer equipment, computer-readable storage medium and computer program product obtain vehicle driving data, which includes vehicle speed dimension data, electric drive dimension data and season dimension data collected at each collection time; divide the vehicle driving data into multiple kinematic segments; cluster the multiple kinematic segments in the vehicle speed dimension according to the pre-extracted speed dimension features to obtain the vehicle speed clusters corresponding to each vehicle speed category; for the vehicle speed clusters corresponding to each vehicle speed category, cluster the kinematic segments in the vehicle speed clusters corresponding to the current vehicle speed category in the season dimension according to the pre-extracted season dimension features to obtain the season clusters corresponding to each season category under the current vehicle speed category; construct a multi-dimensional driving condition based on the season clusters corresponding to each season category under each vehicle speed category. The multi-dimensional driving condition includes information in two dimensions, speed and season, and can better reflect the real driving characteristics of different seasons. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0055] FIG1 is an application environment diagram of a driving condition construction method in one embodiment;

[0056] Figure 2 A schematic diagram of a process flow of a driving condition construction method in one embodiment;

[0057] Figure 3 A schematic diagram of clustering principle in one embodiment;

[0058] Figure 4 A schematic flow chart of a driving condition construction method in another embodiment;

[0059] Figure 5 A structural block diagram of a driving condition building device in one embodiment;

[0060] Figure 6 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0061] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0062] The driving condition construction method provided by the embodiment of the present application can be applied to the application environment shown in Figure 1. Among them, the vehicle 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The vehicle 102 reports the vehicle driving data to the server 104, and the server 104 divides the vehicle driving data into multiple kinematic segments; according to the pre-extracted speed dimension features, the multiple kinematic segments are clustered in the vehicle speed dimension to obtain the vehicle speed clustering clusters corresponding to each vehicle speed category; for the vehicle speed clustering clusters corresponding to each vehicle speed category, according to the pre-extracted season dimension features, the kinematic segments in the vehicle speed clustering clusters corresponding to the current vehicle speed category are clustered in the season dimension to obtain the seasonal clustering clusters corresponding to each season category under the current vehicle speed category; based on the seasonal clustering clusters corresponding to each season category under each vehicle speed category, a multi-dimensional driving condition is constructed. The constructed multi-dimensional driving condition includes two dimensions, the speed dimension and the season dimension, which can better reflect the real driving characteristics of different seasons. Among them, the vehicle 102 can be but is not limited to a fuel vehicle, a hybrid vehicle, a pure electric vehicle, etc. FIG. 1 shows only one vehicle 102 , and there can be multiple vehicles 102 , which is not limited in the embodiment of the present application.

[0063] In an exemplary embodiment, Figure 2 As shown, a driving condition construction method is provided, and the method is applied to the server in FIG. 1 as an example for explanation, including the following steps 202 to 210. Among them:

[0064] Step 202 , obtaining vehicle driving data, wherein the vehicle driving data includes vehicle speed dimension data, electric drive dimension data, and season dimension data collected at each collection time.

[0065] Among them, the vehicle can collect driving data according to a preset collection frequency. For example, the vehicle can collect driving data every 1 second. The vehicle can be installed with a global positioning system (GPS), a speed sensor, an acceleration sensor, a temperature sensor, etc. The vehicle can use these installed devices to collect longitude and latitude, speed, acceleration, battery voltage, battery current, battery state of charge (SOC), motor speed, motor temperature, ambient temperature, air-conditioning gear, etc., and these data can be used as the above-mentioned driving data.

[0066] Among them, each time the vehicle collects driving data, the driving data can be reported to the server. The server can summarize all the driving data received as vehicle driving data; or summarize the driving data received within a certain time period as vehicle driving data. In other words, the vehicle driving data is composed of driving data collected by the vehicle at several collection times. As mentioned above, the driving data may include longitude and latitude, vehicle speed, acceleration, battery voltage, battery current, battery state of charge (State of charge, referred to as SOC), motor speed, motor temperature, ambient temperature, air conditioning gear, etc. The vehicle speed, acceleration, etc. can be used as vehicle speed dimension data; battery voltage, battery current, SOC, motor speed, motor temperature, etc. can be used as electric drive dimension data; ambient temperature, air conditioning gear, etc. can be used as season dimension data.

[0067] Step 204: Divide the vehicle driving data into a plurality of kinematic segments.

[0068] The vehicle driving data may be divided into a plurality of kinematic segments according to a preset rule. For example, as described above, the vehicle driving data includes the driving data collected by the vehicle at each collection time. The driving data with a vehicle speed of a set value (such as 0) may be searched in each driving data as a segmentation node. For each segmentation node, the segmentation node and the driving data before the segmentation node may be divided into a kinematic segment; or the segmentation node and the driving data after the segmentation node may be divided into a kinematic segment. Alternatively, other segmentation methods may be used to divide the vehicle driving data, thereby obtaining a plurality of kinematic segments.

[0069] Step 206 : clustering the plurality of kinematic segments in the vehicle speed dimension according to the pre-extracted speed dimension features to obtain a vehicle speed cluster corresponding to each vehicle speed category.

[0070] Among them, speed dimension data in the driving data contained in each kinematic segment, such as vehicle speed, acceleration, motor speed, motor torque, etc., can be extracted as speed dimension features.

[0071] Among them, the vehicle speed can be divided into four speed categories: low speed, medium speed, high speed, and super high speed. The initial cluster center corresponding to the low speed category, the initial cluster center corresponding to the medium speed category, the initial cluster center corresponding to the high speed category, and the initial cluster center corresponding to the super high speed category can be defined. Based on the initial cluster centers corresponding to each of the four speed categories, the multiple kinematic segments are clustered in the speed dimension according to the pre-extracted speed dimension features to obtain a speed cluster cluster corresponding to each speed category.

[0072] Among them, based on the initial clustering centers corresponding to each of the above four vehicle speed categories, the K-Means clustering algorithm can be used to cluster the multiple kinematic segments in the vehicle speed dimension to obtain a vehicle speed clustering cluster corresponding to each vehicle speed category; or, the Dingo Optimization Algorithm (DOA) can be used to improve the K-Means clustering algorithm, and based on the initial clustering centers corresponding to each of the above four vehicle speed categories, the improved K-Means clustering algorithm can be used to cluster the multiple kinematic segments in the vehicle speed dimension to obtain a vehicle speed clustering cluster corresponding to each vehicle speed category.

[0073] Step 208, for the vehicle speed clusters corresponding to each vehicle speed category, according to the pre-extracted seasonal dimension features, the kinematic segments in the vehicle speed clusters corresponding to the current vehicle speed category are clustered in the seasonal dimension to obtain seasonal clusters corresponding to each seasonal category under the current vehicle speed category.

[0074] Among them, for the vehicle speed cluster corresponding to each vehicle speed category, seasonal dimension data in the driving data contained in the vehicle speed cluster, such as ambient temperature, air conditioning setting gear, etc., can be extracted as seasonal dimension features.

[0075] Among them, the seasons can be divided into four seasonal categories: spring, summer, autumn and winter. The initial cluster center corresponding to the spring season category, the initial cluster center corresponding to the summer season category, the initial cluster center corresponding to the autumn season category, and the initial cluster center corresponding to the winter season category can be defined. After obtaining the vehicle speed clustering cluster corresponding to each vehicle speed category, for the vehicle speed clustering cluster corresponding to each vehicle speed category, based on the initial clustering centers corresponding to the above four seasonal categories, according to the pre-extracted seasonal dimension features, the kinematic fragments in the vehicle speed clustering cluster corresponding to the current vehicle speed category can be clustered in the seasonal dimension to obtain the seasonal clustering cluster corresponding to each seasonal category under the current vehicle speed category.

[0076] See also Figure 3As shown, after multiple kinematic segments are obtained through step 204, the multiple kinematic segments can be clustered in the vehicle speed dimension according to the four vehicle speed categories of low speed, medium speed, high speed, and super high speed, to obtain vehicle speed clustering clusters corresponding to the low speed category, vehicle speed clustering clusters corresponding to the medium speed category, vehicle speed clustering clusters corresponding to the high speed category, and vehicle speed clustering clusters corresponding to the super high speed category. For the vehicle speed clustering clusters corresponding to the low speed category, the kinematic segments of the vehicle speed clustering clusters corresponding to the low speed category are clustered in the season dimension according to the four season categories of spring, summer, autumn, and winter, to obtain seasonal clustering clusters corresponding to the spring category under the low speed category, seasonal clustering clusters corresponding to the summer category under the low speed category, seasonal clustering clusters corresponding to the autumn category under the low speed category, and seasonal clustering clusters corresponding to the winter category under the low speed category. By performing the same processing on the vehicle speed clustering clusters corresponding to the medium-speed category, high-speed category, and super-high-speed category, we can obtain the seasonal clustering cluster corresponding to the spring category under the medium-speed category, the seasonal clustering cluster corresponding to the summer category under the medium-speed category, the seasonal clustering cluster corresponding to the autumn category under the medium-speed category, the seasonal clustering cluster corresponding to the winter category under the medium-speed category, the seasonal clustering cluster corresponding to the spring category under the high-speed category, the seasonal clustering cluster corresponding to the summer category under the high-speed category, the seasonal clustering cluster corresponding to the autumn category under the high-speed category, the seasonal clustering cluster corresponding to the winter category under the high-speed category, the seasonal clustering cluster corresponding to the spring category under the super-high-speed category, the seasonal clustering cluster corresponding to the summer category under the super-high-speed category, the seasonal clustering cluster corresponding to the autumn category under the super-high-speed category, and the seasonal clustering cluster corresponding to the winter category under the super-high-speed category, for a total of 16 clusters.

[0077] Among them, in the same vehicle speed dimension, for the vehicle speed clusters corresponding to each vehicle speed category, based on the initial cluster centers corresponding to the above four seasonal categories, the K-Means clustering algorithm can be used to cluster the kinematic segments in the vehicle speed clusters corresponding to the current vehicle speed category in the seasonal dimension to obtain the seasonal clusters corresponding to each seasonal category under the current vehicle speed category; or the improved K-Means clustering algorithm can be used to cluster the kinematic segments in the vehicle speed clusters corresponding to the current vehicle speed category in the seasonal dimension to obtain the seasonal clusters corresponding to each seasonal category under the current vehicle speed category.

[0078] Step 210 , constructing a multi-dimensional driving condition based on the seasonal clusters corresponding to each seasonal category under each vehicle speed category.

[0079] Among them, the seasonal demand for working condition construction can be obtained, and based on the seasonal demand, the seasonal cluster clusters that meet the seasonal demand are extracted from the seasonal cluster clusters corresponding to each seasonal category under each vehicle speed category, and then the kinematic fragments in the extracted seasonal cluster clusters are spliced ​​to obtain a multi-dimensional driving condition.

[0080] In the above embodiment, vehicle driving data is obtained, and the vehicle driving data includes vehicle speed dimension data, electric drive dimension data, and season dimension data collected at each collection time; the vehicle driving data is divided into multiple kinematic segments; according to the pre-extracted speed dimension features, the multiple kinematic segments are clustered in the vehicle speed dimension to obtain vehicle speed clusters corresponding to each vehicle speed category; for the vehicle speed clusters corresponding to each vehicle speed category, according to the pre-extracted season dimension features, the kinematic segments in the vehicle speed clusters corresponding to the current vehicle speed category are clustered in the season dimension to obtain the season clusters corresponding to each season category under the current vehicle speed category; based on the season clusters corresponding to each season category under each vehicle speed category, a multi-dimensional driving condition is constructed. The multi-dimensional driving condition includes information in two dimensions, speed and season, and can better reflect the real driving characteristics of different seasons.

[0081] In some embodiments, before dividing the vehicle driving data into a plurality of kinematic segments, the method further includes: performing at least one of data cleaning processing, abnormal information elimination processing, and missing information completion processing on the vehicle driving data in sequence.

[0082] Among them, after the server obtains the vehicle driving data, the vehicle driving data can be re-examined and verified to achieve data cleaning of the vehicle driving data. The specific process of re-examination and verification can be referred to the prior art; after the vehicle driving data is cleaned, the vehicle driving data can be further processed to eliminate abnormal information. For example, as described above, the vehicle driving data is composed of driving data collected by the vehicle at several collection times. The speed of the vehicle in the driving data collected at a certain collection time drops or rises sharply compared with the adjacent collection times, then the driving data can be eliminated as abnormal information. Due to network instability, sensor abnormality and other reasons, the driving data collected at a certain collection time may not be complete, or the driving data at a certain collection time may be missing as a whole. Therefore, after the vehicle driving data is processed to eliminate abnormal information, the vehicle driving data can be further processed to complete the missing information. For example, a machine learning algorithm can be used to complete the missing information of the vehicle driving data, or the vehicle driving data can be completed by interpolation.

[0083] In the above embodiment, after the vehicle driving data is acquired, the vehicle driving data may be sequentially subjected to data cleaning processing, abnormal information elimination processing, and missing information completion processing, thereby reducing data noise and improving the accuracy of the driving conditions finally constructed.

[0084] In some embodiments, before clustering the multiple kinematic segments in the vehicle speed dimension, the method further includes: performing principal component analysis on the extracted speed dimension features to obtain the contribution of each speed dimension feature; based on the contribution, performing data screening on the extracted speed dimension features; before clustering the kinematic segments in the vehicle speed clustering cluster corresponding to the current vehicle speed category in the season dimension, the method further includes: performing principal component analysis on the extracted season dimension features to obtain the contribution of each season dimension feature; based on the contribution, performing data screening on the extracted season dimension features.

[0085] As described above, vehicle driving data is composed of driving data collected by the vehicle at several collection times. The driving data may include longitude and latitude, vehicle speed, acceleration, battery voltage, battery current, battery state of charge (SOC), motor speed, motor temperature, ambient temperature, air-conditioning gear, etc. Different data dimensions have different contributions. The data corresponding to the data dimensions with lower contributions can be deleted to achieve the purpose of dimensionality reduction, reduce the subsequent data processing volume, and improve processing efficiency.

[0086] Among them, the extracted speed dimension features can be subjected to principal component analysis to obtain the contribution of each speed dimension feature; the speed dimension features are sorted in descending order of contribution, starting from the first speed dimension feature, and the sum of the contributions is calculated one by one. When the sum of the contributions reaches 80%, the speed dimension features involved in the summation are retained, and the remaining speed dimension features are deleted.

[0087] Similarly, the extracted seasonal dimension features can be subjected to principal component analysis to obtain the contribution of each seasonal dimension feature; the seasonal dimension features are sorted in descending order of contribution, starting from the first seasonal dimension feature, and the sum of the contributions is calculated one by one. When the sum of the contributions reaches 80%, the seasonal dimension features involved in the summation are retained, and the remaining seasonal dimension features are deleted.

[0088] In the above embodiment, principal component analysis is performed on the extracted speed dimension features and season dimension features to achieve the purpose of dimensionality reduction, reduce the amount of subsequent data processing, and improve processing efficiency.

[0089] In some embodiments, dividing the vehicle driving data into multiple kinematic segments includes: extracting an idle segment from the vehicle driving data; taking a segment between two adjacent idle segments as a stable operation segment; for each idle segment, dividing the current idle segment and the stable operation segment after the current idle segment into one kinematic segment, thereby obtaining multiple kinematic segments.

[0090] The vehicle driving data is composed of driving data collected by the vehicle at several collection moments. All driving data can be sorted according to the order of the collection moments, and the sorted driving data can be analyzed to determine at least one idle segment, and the driving data between two adjacent idle segments constitute a stable operation segment. For each idle segment, the idle segment and the stable operation segment after the idle segment can be divided into a kinematic segment, thereby obtaining multiple kinematic segments.

[0091] In the above embodiment, a specific method for dividing the vehicle driving data into multiple kinematic segments is provided. First, an idle segment is extracted from the vehicle driving data; the segment between two adjacent idle segments is used as a stable operation segment; for each idle segment, the current idle segment and the stable operation segment after the current idle segment are divided into a kinematic segment, thereby obtaining multiple kinematic segments. In this division method, each kinematic segment represents a complete driving process, making the driving condition constructed subsequently more accurate.

[0092] In some embodiments, the multiple kinematic segments are clustered in the vehicle speed dimension according to the pre-extracted speed dimension features to obtain a vehicle speed cluster corresponding to each vehicle speed category, including: determining a corresponding number of vehicle speed cluster centers according to the pre-extracted speed dimension features; dividing each kinematic segment into a vehicle speed cluster corresponding to the nearest vehicle speed cluster center to obtain a vehicle speed cluster matching the number of pre-divided vehicle speed categories; for each vehicle speed cluster cluster, calculating a fitness value according to each kinematic segment in the current vehicle speed cluster cluster, and calculating a latest cluster center according to the fitness value; updating the vehicle speed cluster center to the latest cluster center, and continuing to execute the step of dividing each kinematic segment into a vehicle speed cluster corresponding to the nearest vehicle speed cluster center, until the kinematic segments contained in each vehicle speed cluster cluster no longer change or the number of executions reaches a preset value.

[0093] Among them, the vehicle speed can be divided into four speed categories: low speed, medium speed, high speed, and super high speed. According to the pre-extracted speed dimension features, the speed cluster center corresponding to the low speed category, the speed cluster center corresponding to the medium speed category, the speed cluster center corresponding to the high speed category, and the speed cluster center corresponding to the super high speed category can be determined, and each kinematic segment is divided into the speed cluster corresponding to the nearest speed cluster center to obtain four speed cluster clusters. For each speed cluster cluster, the fitness value is calculated according to each kinematic segment in the current speed cluster cluster. The calculation method of the fitness value refers to the wild dog optimization algorithm. The fitness value is divided by the number of kinematic segments in the current speed cluster cluster to obtain the latest cluster center, and the speed cluster center of the current speed cluster cluster is updated to the latest cluster center. Continue to perform the step of dividing each kinematic segment into the speed cluster corresponding to the nearest speed cluster center until the kinematic segments contained in each speed cluster cluster no longer change or the number of executions reaches a preset value.

[0094] In the above embodiment, the wild dog optimization algorithm and the K-Means clustering algorithm are combined to perform clustering processing on multiple kinematic segments in the vehicle speed dimension, so that the clustering result is more accurate.

[0095] In some embodiments, for the vehicle speed clusters corresponding to each vehicle speed category, the kinematic segments in the vehicle speed clusters corresponding to the current vehicle speed category can also be clustered in the seasonal dimension according to the pre-divided seasonal categories, combining the wild dog optimization algorithm and the K-Means clustering algorithm. The principle is similar to the vehicle speed dimension, and the embodiments of this application will not be repeated here. It should be noted that when clustering is performed in the seasonal dimension, the data dimension involved in the calculation is the ambient temperature or the air conditioning gear.

[0096] In some embodiments, the vehicle driving condition is constructed based on the seasonal clustering clusters corresponding to each seasonal category under each vehicle speed category, including: obtaining the seasonal demand for condition construction; extracting the seasonal clustering clusters that meet the seasonal demand from the seasonal clustering clusters corresponding to each seasonal category under each vehicle speed category; sampling the kinematic fragments in the extracted seasonal clustering clusters to obtain multiple kinematic samples that meet the seasonal demand; and splicing the multiple kinematic samples to obtain a multi-dimensional driving condition.

[0097] The seasonal demand of the operating condition construction can be at least one of spring, summer, autumn and winter. For example, if the seasonal demand of the operating condition construction is winter, the seasonal clusters corresponding to each season category under each vehicle speed category can be selected, that is, Figure 3Among the clusters shown, four clusters are extracted, namely low speed-winter, medium speed-winter, high speed-winter, and ultra-high speed-winter. For each of these four clusters, the Markov process and Monte Carlo sampling method are used to sample the kinematic fragments in the cluster to obtain multiple kinematic samples in winter. By splicing these kinematic samples, multi-dimensional driving conditions can be obtained.

[0098] In the above embodiment, the seasonal requirements of the working conditions can be combined to obtain corresponding kinematic samples from the seasonal clusters corresponding to each seasonal category under each vehicle speed category and splice them, so as to obtain driving conditions that meet the seasonal requirements and better reflect the actual driving characteristics of different seasons.

[0099] In some embodiments, see Figure 4 As shown, a driving condition construction method is provided, taking application to a server as an example, the method includes:

[0100] Step 401, obtaining vehicle driving data.

[0101] Step 402: performing at least one of data cleaning processing, abnormal information elimination processing, and missing information completion processing on the vehicle driving data.

[0102] Step 403: Divide the vehicle driving data into a plurality of kinematic segments.

[0103] Step 404: extract velocity dimension features from multiple kinematic segments, perform principal component analysis on them, and delete velocity dimension features with low contribution.

[0104] Step 405 , clustering the plurality of kinematic segments in the vehicle speed dimension according to the pre-extracted speed dimension features, to obtain a vehicle speed cluster corresponding to each vehicle speed category.

[0105] Step 406 , for the vehicle speed clusters corresponding to each vehicle speed category, extract the seasonal dimension features from the vehicle speed clusters, perform principal component analysis on them, and delete the seasonal dimension features with low contribution.

[0106] Step 407 , according to the pre-extracted seasonal dimension features, the kinematic segments in the vehicle speed cluster corresponding to the current vehicle speed category are clustered in the seasonal dimension to obtain seasonal clusters corresponding to each seasonal category under the current vehicle speed category.

[0107] Step 408 : extracting a seasonal cluster that meets the seasonal requirement from the seasonal clusters corresponding to each season category under each vehicle speed category.

[0108] Step 409 , sampling the kinematic segments in the extracted seasonal clusters to obtain a plurality of kinematic samples that meet the seasonal requirements.

[0109] Step 410: splicing the multiple kinematic samples to obtain a multi-dimensional driving condition.

[0110] In the above embodiment, vehicle driving data is obtained, and the vehicle driving data includes vehicle speed dimension data, electric drive dimension data, and season dimension data collected at each collection time; the vehicle driving data is divided into multiple kinematic segments; according to the pre-extracted speed dimension features, the multiple kinematic segments are clustered in the vehicle speed dimension to obtain vehicle speed clusters corresponding to each vehicle speed category; for the vehicle speed clusters corresponding to each vehicle speed category, according to the pre-extracted season dimension features, the kinematic segments in the vehicle speed clusters corresponding to the current vehicle speed category are clustered in the season dimension to obtain the season clusters corresponding to each season category under the current vehicle speed category; based on the season clusters corresponding to each season category under each vehicle speed category, a multi-dimensional driving condition is constructed. The multi-dimensional driving condition includes information in two dimensions, speed and season, and can better reflect the real driving characteristics of different seasons.

[0111] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0112] Based on the same inventive concept, the embodiment of the present application also provides a driving condition construction device for implementing the driving condition construction method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more driving condition construction device embodiments provided below can refer to the limitations of the driving condition construction method above, and will not be repeated here.

[0113] In an exemplary embodiment, Figure 5 As shown, a driving condition construction device is provided, comprising:

[0114] An acquisition module, used to acquire vehicle driving data, wherein the vehicle driving data includes vehicle speed dimension data, electric drive dimension data and season dimension data collected at each collection time;

[0115] A division module, used for dividing the vehicle driving data into a plurality of kinematic segments;

[0116] A clustering processing module is used to perform clustering processing on the multiple kinematic segments in the vehicle speed dimension according to the pre-extracted speed dimension features, so as to obtain a vehicle speed cluster corresponding to each vehicle speed category; for the vehicle speed cluster corresponding to each vehicle speed category, the kinematic segments in the vehicle speed cluster corresponding to the current vehicle speed category are clustered in the season dimension according to the pre-extracted season dimension features, so as to obtain a season cluster corresponding to each season category under the current vehicle speed category;

[0117] The construction module is used to construct multi-dimensional driving conditions based on the seasonal clusters corresponding to each seasonal category under each vehicle speed category.

[0118] In some embodiments, the acquisition module is also used to perform at least one of data cleaning processing, abnormal information elimination processing, and missing information completion processing on the vehicle driving data.

[0119] In some embodiments, the acquisition module is also used to perform principal component analysis on the extracted speed dimension features to obtain the contribution of each speed dimension feature; based on the contribution, perform data screening on the extracted speed dimension features; perform principal component analysis on the extracted season dimension features to obtain the contribution of each season dimension feature; based on the contribution, perform data screening on the extracted season dimension features.

[0120] In some embodiments, a division module is used to extract idle segments from the vehicle driving data; the segment between two adjacent idle segments is used as a stable operation segment; for each idle segment, the current idle segment and the stable operation segment after the current idle segment are divided into a kinematic segment to obtain multiple kinematic segments.

[0121] In some embodiments, a clustering processing module is used to determine a corresponding number of vehicle speed clustering centers based on a pre-extracted speed dimension feature; divide each kinematic segment into a vehicle speed clustering cluster corresponding to the nearest vehicle speed clustering center to obtain a vehicle speed clustering cluster that matches the number of pre-divided vehicle speed categories; for each vehicle speed clustering cluster, calculate a fitness value based on each kinematic segment in the current vehicle speed clustering cluster, and calculate the latest clustering center based on the fitness value; update the vehicle speed clustering center to the latest clustering center, and continue to execute the step of dividing each kinematic segment into a vehicle speed clustering cluster corresponding to the nearest vehicle speed clustering center until the kinematic segments contained in each vehicle speed clustering cluster no longer change or the number of executions reaches a preset value.

[0122] In some embodiments, a construction module is used to obtain seasonal requirements for operating condition construction; extract seasonal clusters that meet the seasonal requirements from the seasonal clusters corresponding to each seasonal category under each vehicle speed category; sample the kinematic fragments in the extracted seasonal clusters to obtain multiple kinematic samples that meet the seasonal requirements; and splice the multiple kinematic samples to obtain a multi-dimensional driving condition.

[0123] Each module in the driving condition construction device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0124] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 6 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store vehicle driving data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a driving condition construction method is implemented.

[0125] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0126] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0127] Acquire vehicle driving data, wherein the vehicle driving data includes vehicle speed dimension data, electric drive dimension data, and season dimension data collected at each collection time;

[0128] Dividing the vehicle driving data into a plurality of kinematic segments;

[0129] According to the pre-extracted speed dimension features, clustering processing is performed on the multiple kinematic segments in the vehicle speed dimension to obtain a vehicle speed cluster corresponding to each vehicle speed category;

[0130] For the vehicle speed clusters corresponding to each vehicle speed category, according to the pre-extracted seasonal dimension features, the kinematic segments in the vehicle speed clusters corresponding to the current vehicle speed category are clustered in the seasonal dimension to obtain seasonal clusters corresponding to each seasonal category under the current vehicle speed category;

[0131] Based on the seasonal clusters corresponding to each seasonal category under each vehicle speed category, a multi-dimensional driving condition is constructed.

[0132] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0133] The vehicle driving data is sequentially subjected to at least one of data cleaning processing, abnormal information elimination processing, and missing information completion processing.

[0134] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0135] The extracted speed dimension features are subjected to principal component analysis to obtain the contribution of each speed dimension feature; based on the contribution, the extracted speed dimension features are subjected to data screening; the extracted season dimension features are subjected to principal component analysis to obtain the contribution of each season dimension feature; based on the contribution, the extracted season dimension features are subjected to data screening.

[0136] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0137] extracting an idle segment from the vehicle driving data;

[0138] The segment between two adjacent idle segments is regarded as a stable operation segment;

[0139] For each idle segment, the current idle segment and the stable operation segment after the current idle segment are divided into one kinematic segment, thereby obtaining a plurality of kinematic segments.

[0140] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0141] Determine a corresponding number of vehicle speed cluster centers according to the pre-extracted speed dimension features;

[0142] Divide each kinematic segment into a vehicle speed cluster corresponding to the nearest vehicle speed cluster center, and obtain vehicle speed clusters matching the number of pre-divided vehicle speed categories;

[0143] For each vehicle speed cluster, a fitness value is calculated according to each kinematic segment in the current vehicle speed cluster, and a latest cluster center is calculated according to the fitness value;

[0144] The vehicle speed cluster center is updated to the latest cluster center, and the step of dividing each kinematic segment into the vehicle speed cluster corresponding to the nearest vehicle speed cluster center is continued until the kinematic segments included in each vehicle speed cluster no longer change or the number of executions reaches a preset value.

[0145] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0146] Obtain seasonal requirements for working condition construction;

[0147] Extracting a seasonal cluster that meets the seasonal requirements from the seasonal clusters corresponding to each seasonal category under each vehicle speed category;

[0148] Sampling the kinematic segments in the extracted seasonal clusters to obtain a plurality of kinematic samples that meet the seasonal requirements;

[0149] The multiple kinematic samples are spliced ​​together to obtain a multi-dimensional driving condition.

[0150] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0151] Acquire vehicle driving data, wherein the vehicle driving data includes vehicle speed dimension data, electric drive dimension data, and season dimension data collected at each collection time;

[0152] Dividing the vehicle driving data into a plurality of kinematic segments;

[0153] According to the pre-extracted speed dimension features, clustering processing is performed on the multiple kinematic segments in the vehicle speed dimension to obtain a vehicle speed cluster corresponding to each vehicle speed category;

[0154] For the vehicle speed clusters corresponding to each vehicle speed category, according to the pre-extracted seasonal dimension features, the kinematic segments in the vehicle speed clusters corresponding to the current vehicle speed category are clustered in the seasonal dimension to obtain seasonal clusters corresponding to each seasonal category under the current vehicle speed category;

[0155] Based on the seasonal clusters corresponding to each seasonal category under each vehicle speed category, a multi-dimensional driving condition is constructed.

[0156] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0157] The vehicle driving data is sequentially subjected to at least one of data cleaning processing, abnormal information elimination processing, and missing information completion processing.

[0158] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0159] The extracted speed dimension features are subjected to principal component analysis to obtain the contribution of each speed dimension feature; based on the contribution, the extracted speed dimension features are subjected to data screening; the extracted season dimension features are subjected to principal component analysis to obtain the contribution of each season dimension feature; based on the contribution, the extracted season dimension features are subjected to data screening.

[0160] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0161] extracting an idle segment from the vehicle driving data;

[0162] The segment between two adjacent idle segments is regarded as a stable operation segment;

[0163] For each idle segment, the current idle segment and the stable operation segment after the current idle segment are divided into one kinematic segment, thereby obtaining a plurality of kinematic segments.

[0164] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0165] Determine a corresponding number of vehicle speed cluster centers according to the pre-extracted speed dimension features;

[0166] Divide each kinematic segment into a vehicle speed cluster corresponding to the nearest vehicle speed cluster center, and obtain vehicle speed clusters matching the number of pre-divided vehicle speed categories;

[0167] For each vehicle speed cluster, a fitness value is calculated according to each kinematic segment in the current vehicle speed cluster, and a latest cluster center is calculated according to the fitness value;

[0168] The vehicle speed cluster center is updated to the latest cluster center, and the step of dividing each kinematic segment into the vehicle speed cluster corresponding to the nearest vehicle speed cluster center is continued until the kinematic segments included in each vehicle speed cluster no longer change or the number of executions reaches a preset value.

[0169] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0170] Obtain seasonal requirements for working condition construction;

[0171] Extracting a seasonal cluster that meets the seasonal requirements from the seasonal clusters corresponding to each seasonal category under each vehicle speed category;

[0172] Sampling the kinematic segments in the extracted seasonal clusters to obtain a plurality of kinematic samples that meet the seasonal requirements;

[0173] The multiple kinematic samples are spliced ​​together to obtain a multi-dimensional driving condition.

[0174] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0175] Acquire vehicle driving data, wherein the vehicle driving data includes vehicle speed dimension data, electric drive dimension data, and season dimension data collected at each collection time;

[0176] Dividing the vehicle driving data into a plurality of kinematic segments;

[0177] According to the pre-extracted speed dimension features, clustering processing is performed on the multiple kinematic segments in the vehicle speed dimension to obtain a vehicle speed cluster corresponding to each vehicle speed category;

[0178] For the vehicle speed clusters corresponding to each vehicle speed category, according to the pre-extracted seasonal dimension features, the kinematic segments in the vehicle speed clusters corresponding to the current vehicle speed category are clustered in the seasonal dimension to obtain seasonal clusters corresponding to each seasonal category under the current vehicle speed category;

[0179] Based on the seasonal clusters corresponding to each seasonal category under each vehicle speed category, a multi-dimensional driving condition is constructed.

[0180] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0181] The vehicle driving data is sequentially subjected to at least one of data cleaning processing, abnormal information elimination processing, and missing information completion processing.

[0182] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0183] The extracted speed dimension features are subjected to principal component analysis to obtain the contribution of each speed dimension feature; based on the contribution, the extracted speed dimension features are subjected to data screening; the extracted season dimension features are subjected to principal component analysis to obtain the contribution of each season dimension feature; based on the contribution, the extracted season dimension features are subjected to data screening.

[0184] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0185] extracting an idle segment from the vehicle driving data;

[0186] The segment between two adjacent idle segments is regarded as a stable operation segment;

[0187] For each idle segment, the current idle segment and the stable operation segment after the current idle segment are divided into one kinematic segment, thereby obtaining a plurality of kinematic segments.

[0188] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0189] Determine a corresponding number of vehicle speed cluster centers according to the pre-extracted speed dimension features;

[0190] Divide each kinematic segment into a vehicle speed cluster corresponding to the nearest vehicle speed cluster center, and obtain vehicle speed clusters matching the number of pre-divided vehicle speed categories;

[0191] For each vehicle speed cluster, a fitness value is calculated according to each kinematic segment in the current vehicle speed cluster, and a latest cluster center is calculated according to the fitness value;

[0192] The vehicle speed cluster center is updated to the latest cluster center, and the step of dividing each kinematic segment into the vehicle speed cluster corresponding to the nearest vehicle speed cluster center is continued until the kinematic segments included in each vehicle speed cluster no longer change or the number of executions reaches a preset value.

[0193] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0194] Obtain seasonal requirements for working condition construction;

[0195] Extracting a seasonal cluster that meets the seasonal requirements from the seasonal clusters corresponding to each seasonal category under each vehicle speed category;

[0196] Sampling the kinematic segments in the extracted seasonal clusters to obtain a plurality of kinematic samples that meet the seasonal requirements;

[0197] The multiple kinematic samples are spliced ​​together to obtain a multi-dimensional driving condition.

[0198] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0199] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0200] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A driving condition construction method, characterized in that: The method comprises: Acquire vehicle driving data, wherein the vehicle driving data includes vehicle speed dimension data, electric drive dimension data, and season dimension data collected at each collection time; Dividing the vehicle driving data into a plurality of kinematic segments; According to the pre-extracted speed dimension features, the plurality of kinematic segments are clustered in the vehicle speed dimension to obtain a vehicle speed cluster corresponding to each vehicle speed category; For the vehicle speed clusters corresponding to each vehicle speed category, according to the pre-extracted seasonal dimension features, the kinematic segments in the vehicle speed clusters corresponding to the current vehicle speed category are clustered in the seasonal dimension to obtain the seasonal clusters corresponding to each seasonal category under the current vehicle speed category; Based on the seasonal clusters corresponding to each seasonal category under each vehicle speed category, a multi-dimensional driving condition is constructed.

2. The method according to claim 1, characterized in that Before dividing the vehicle driving data into a plurality of kinematic segments, the method further includes: The vehicle driving data is sequentially subjected to at least one of data cleaning processing, abnormal information elimination processing, and missing information completion processing.

3. The method according to claim 1, characterized in that Before clustering the plurality of kinematic segments in the vehicle speed dimension, the method further includes: Performing principal component analysis on the extracted speed dimension features to obtain the contribution of each speed dimension feature; and performing data screening processing on the extracted speed dimension features based on the contribution; Before clustering the kinematic segments in the vehicle speed cluster corresponding to the current vehicle speed category in the seasonal dimension, the method further includes: The extracted seasonal dimension features are subjected to principal component analysis to obtain the contribution of each seasonal dimension feature; based on the contribution, the extracted seasonal dimension features are subjected to data screening processing.

4. The method according to claim 1, characterized in that The step of dividing the vehicle driving data into a plurality of kinematic segments comprises: extracting an idle segment from the vehicle driving data; The segment between two adjacent idle segments is regarded as a stable operation segment; For each idle segment, the current idle segment and the stable operation segment after the current idle segment are divided into one kinematic segment, thereby obtaining a plurality of kinematic segments.

5. The method according to claim 1, characterized in that The clustering process is performed on the plurality of kinematic segments in the vehicle speed dimension according to the pre-extracted speed dimension features to obtain a vehicle speed cluster corresponding to each vehicle speed category, including: Determine a corresponding number of vehicle speed cluster centers according to the pre-extracted speed dimension features; Divide each kinematic segment into a vehicle speed cluster corresponding to the nearest vehicle speed cluster center, and obtain vehicle speed clusters matching the number of pre-divided vehicle speed categories; For each vehicle speed cluster, a fitness value is calculated according to each kinematic segment in the current vehicle speed cluster, and a latest cluster center is calculated according to the fitness value; The vehicle speed cluster center is updated to the latest cluster center, and the step of dividing each kinematic segment into the vehicle speed cluster corresponding to the nearest vehicle speed cluster center is continued until the kinematic segments included in each vehicle speed cluster no longer change or the number of executions reaches a preset value.

6. The method according to claim 1, characterized in that The seasonal clusters corresponding to each seasonal category under each vehicle speed category are used to construct a multi-dimensional driving condition, including: Obtain seasonal requirements for working condition construction; Extracting a seasonal cluster that meets the seasonal requirements from the seasonal clusters corresponding to each seasonal category under each vehicle speed category; Sampling the kinematic segments in the extracted seasonal clusters to obtain a plurality of kinematic samples that meet the seasonal requirements; The multiple kinematic samples are spliced ​​together to obtain a multi-dimensional driving condition.

7. A driving condition construction device, characterized in that: The device comprises: An acquisition module, used to acquire vehicle driving data, wherein the vehicle driving data includes vehicle speed dimension data, electric drive dimension data and season dimension data collected at each collection time; A division module, used for dividing the vehicle driving data into a plurality of kinematic segments; A clustering processing module is used to perform clustering processing on the multiple kinematic segments in the vehicle speed dimension according to the pre-extracted speed dimension features, so as to obtain a vehicle speed cluster corresponding to each vehicle speed category; for the vehicle speed cluster corresponding to each vehicle speed category, the kinematic segments in the vehicle speed cluster corresponding to the current vehicle speed category are clustered in the season dimension according to the pre-extracted season dimension features, so as to obtain a season cluster corresponding to each season category under the current vehicle speed category; The construction module is used to construct multi-dimensional driving conditions based on the seasonal clusters corresponding to each seasonal category under each vehicle speed category.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images