Vehicle data extraction method, device, equipment and medium

Abstract

The present invention provides a vehicle data extraction method, device, equipment and medium. The vehicle data extraction method includes: obtaining the original data file of the vehicle through a user data automatic capture platform; classifying the original data file according to a preset dimension through an original data file classification platform to obtain a classified data file; cleaning the classified data file through a data cleaning platform to obtain a cleaned data file; extracting the cleaned data file through a data extraction platform according to pre-set data extraction requirements and evaluation criteria to obtain an extracted data file. Through the above scheme, the processing time of vehicle data can be reduced, the processing quality of data can be improved, and data extraction can be performed based on specific requirements, providing data basis for further function development, testing and evaluation.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a vehicle data extraction method, device, equipment and medium. Background Art

[0002] At present, the number of pure electric vehicles in my country has exceeded 3 million. Relying on the rapid development of Internet of Vehicles technology and the gradual maturity of local and enterprise vehicle monitoring platforms, the driving and use data of pure electric vehicles has formed a huge scale. The annual sales volume of electric vehicles reaches hundreds of thousands, and there are more than 200 upload signals on a single vehicle, with a single upload time interval of 10s. How to better use big data to analyze user habits and vehicle characteristics to guide the function development, testing and evaluation of pure electric vehicles is the current research and development focus.

[0003] However, the main problems currently faced are: 1. There is often noise information, interference information, invalid information and information interruption in the data. How to effectively clean it is of great significance to the next step of data extraction and analysis; 2. How to establish data extraction methods and algorithms based on specific business needs is also one of the current difficulties. Summary of the invention

[0004] The embodiments of the present invention provide a vehicle data extraction method, device, equipment and medium to solve the problem in the prior art that it is difficult to effectively extract vehicle data based on specific extraction requirements.

[0005] In order to solve the above technical problems, the embodiments of the present invention provide the following technical solutions:

[0006] An embodiment of the present invention provides a vehicle data extraction method, comprising:

[0007] Obtain the original data file of the vehicle through the user data automatic capture platform;

[0008] Classifying the original data files according to preset dimensions through the original data file classification platform to obtain classified data files;

[0009] Cleaning the classified data file through a data cleaning platform to obtain a cleaned data file;

[0010] The cleaned data file is extracted through the data extraction platform according to the pre-set data extraction requirements and evaluation criteria to obtain an extracted data file.

[0011] Optionally, obtaining the original data file of the vehicle through the user data automatic capture platform includes:

[0012] Establishing a connection with the vehicle user data platform and the software database through the user data automatic capture platform;

[0013] Acquire basic attribute information of the vehicle on the vehicle user data platform, and store the basic attribute information in the software database;

[0014] According to the preset basic attribute information and the preset target time range, the original data file of the vehicle is obtained.

[0015] Optionally, the raw data file is classified according to a preset dimension by the raw data file classification platform to obtain a classified data file, including:

[0016] Obtaining vehicle model information in the original data file through the original data file classification platform, creating a vehicle model folder in the original data file, and cutting original data files of the same vehicle model into the vehicle model folder;

[0017] In the vehicle model folder, the region information in the original data file is obtained, a region folder is created in the vehicle model folder, and the original data files of the same region are cut into the region folder.

[0018] Optionally, the cleaning of the classified data file by a data cleaning platform to obtain a cleaned data file includes:

[0019] Reading the vehicle data in the vehicle model folder and the region folder through the data cleaning platform;

[0020] Deleting data rows with missing signals in the vehicle data;

[0021] Deleting data rows whose data rows are less than a first set threshold or whose vehicle data existence time is less than a second set threshold;

[0022] Deleting data rows with obvious abnormalities in the vehicle data to obtain a cleaned data file;

[0023] The cleaning data in the cleaning data file is sent to the data extraction platform in the form of a matrix.

[0024] Optionally, the data extraction platform extracts the cleaned data file according to pre-set data extraction requirements and evaluation criteria to obtain the extracted data file, including:

[0025] Acquire the data extraction requirements and the evaluation criteria defined by the user and the data extraction feature variables configured by the user;

[0026] According to the data extraction characteristic variables, generating a characteristic data matrix related to the data extraction characteristic variables in the matrix of the cleaned data;

[0027] In the feature data matrix, according to the data extraction requirement and the evaluation criteria, a first row array and a second row array are generated, wherein under the data extraction requirement, the performance of the first row array is better than that of the second row array;

[0028] The extracted data file is generated according to the first row array and the second row array.

[0029] Optionally, the obtaining of the data extraction requirement and the evaluation criteria defined by the user and the data extraction feature variables configured by the user includes:

[0030] Obtaining data extraction requirements for evaluating the driving range of a vehicle, and obtaining driving range evaluation criteria indicators formulated according to the data extraction requirements for evaluating the driving range of a vehicle;

[0031] The driving range evaluation criterion indicator is defined as: within the preset deviation calculation time range variable, the deviation value obtained by subtracting the change value of the driving range calculated by the vehicle control unit from the change value of the vehicle's actual driving range;

[0032] Obtain data feature extraction variables of user driving conditions.

[0033] Optionally, extracting characteristic variables from the data and generating a characteristic data matrix related to the characteristic variables extracted from the data in the matrix of the cleaned data includes:

[0034] Extract variables according to the data features of the user's driving condition, find the signal column where the key switch signal and the vehicle mode signal are located in the first row of the matrix of the cleaned data, extract the signal column to generate a target data matrix;

[0035] In the signal column where the key switch signal of the target data matrix is ​​located, the data rows that cannot form the start and end arrays or the data rows that do not correspond to the driving mode signals in the signal column where the vehicle mode signal is located are eliminated, and a user driving condition data matrix is ​​generated.

[0036] Optionally, in the feature data matrix, generating a first row array and a second row array according to the data extraction requirement and the evaluation criteria includes:

[0037] In the user driving condition data matrix, a deviation value of the change value of the driving range calculated by the vehicle control unit minus the change value of the actual driving range of the vehicle is obtained within a preset deviation calculation time range variable;

[0038] The deviation value is compared with a set threshold value. If the deviation value is greater than or equal to the set threshold value, the first row array is generated. If the deviation value is less than the set threshold value, the second row array is generated.

[0039] Optionally, generating the extracted data file according to the first row array and the second row array includes:

[0040] In the first row array and the second row array, data rows under the signal column where the key switch signal and the vehicle mode signal are located are amplified according to a preset data amplification coefficient and a preset amplification direction to form a final extracted data matrix;

[0041] The extracted data file is generated according to the final extracted data matrix and with the vehicle identification number as the file name.

[0042] The embodiment of the present invention further provides a vehicle data extraction device, comprising:

[0043] The acquisition module is used to obtain the original data file of the vehicle through the user data automatic crawling platform;

[0044] A classification module, used to classify the original data file according to a preset dimension through an original data file classification platform to obtain a classified data file;

[0045] A cleaning module, used for cleaning the classified data file through a data cleaning platform to obtain a cleaned data file;

[0046] The extraction module is used to extract the cleaned data file through the data extraction platform according to the pre-set data extraction requirements and evaluation criteria to obtain the extracted data file.

[0047] Optionally, the acquisition module includes:

[0048] A connection unit, used to establish a connection with the vehicle user data platform and the software database through the user data automatic capture platform;

[0049] A storage unit, used to obtain basic attribute information of the vehicle on the vehicle user data platform, and store the basic attribute information in the software database;

[0050] The first acquisition unit is used to acquire the original data file of the vehicle according to preset basic attribute information and a preset target time range.

[0051] Optionally, the classification module includes:

[0052] A second acquisition unit is used to acquire vehicle model information in the original data file through the original data file classification platform, establish a vehicle model folder in the original data file, and cut the original data files of the same vehicle model into the vehicle model folder;

[0053] The second acquisition unit is used to acquire the region information in the original data file in the vehicle model folder, establish a region folder in the vehicle model folder, and cut the original data files of the same region into the region folder.

[0054] Optionally, the cleaning module includes:

[0055] A reading unit, used for reading the vehicle data information in the vehicle model folder and the regional folder through the data cleaning platform;

[0056] A first deleting unit, used to delete data rows with missing signals in the vehicle data;

[0057] A second deleting unit, used to delete data rows whose data rows are smaller than a first set threshold or whose vehicle data existence time is smaller than a second set threshold;

[0058] A third deleting unit is used to delete data rows with obvious abnormalities in the vehicle data to obtain a cleaned data file;

[0059] A sending unit is used to send the cleaning data in the cleaning data file to the data extraction platform in the form of a matrix.

[0060] Optionally, the extraction module includes:

[0061] A third acquisition unit, used to acquire the data extraction requirements and the evaluation criteria defined by the user and the data extraction feature variables configured by the user;

[0062] An extraction unit, configured to extract characteristic variables according to the data, and generate a characteristic data matrix related to the characteristic variables extracted from the data in the matrix of the cleaned data;

[0063] A first generating unit is used to generate a first row array and a second row array in the feature data matrix according to the data extraction requirement and the evaluation criteria, wherein under the data extraction requirement, the performance of the first row array is better than that of the second row array;

[0064] The second generating unit is used to generate the extracted data file according to the first row array and the second row array.

[0065] Optionally, the third acquiring unit is specifically used to:

[0066] Obtaining data extraction requirements for evaluating the driving range of a vehicle, and obtaining driving range evaluation criteria indicators formulated according to the data extraction requirements for evaluating the driving range of a vehicle;

[0067] The driving range evaluation criterion indicator is defined as: within the preset deviation calculation time range variable, the deviation value obtained by subtracting the change value of the driving range calculated by the vehicle control unit from the change value of the vehicle's actual driving range;

[0068] Obtain data feature extraction variables of user driving conditions.

[0069] Optionally, the extraction unit is specifically used for:

[0070] Extract variables according to the data features of the user's driving condition, find the signal column where the key switch signal and the vehicle mode signal are located in the first row of the matrix of the cleaned data, extract the signal column to generate a target data matrix;

[0071] In the signal column where the key switch signal of the target data matrix is ​​located, the data rows that cannot form the start and end arrays or the data rows that do not correspond to the driving mode signals in the signal column where the vehicle mode signal is located are eliminated, and a user driving condition data matrix is ​​generated.

[0072] Optionally, the first generating unit is specifically configured to:

[0073] In the user driving condition data matrix, a deviation value of the change value of the driving range calculated by the vehicle control unit minus the change value of the actual driving range of the vehicle is obtained within a preset deviation calculation time range variable;

[0074] The deviation value is compared with a set threshold value. If the deviation value is greater than or equal to the set threshold value, the first row array is generated. If the deviation value is less than the set threshold value, the second row array is generated.

[0075] Optionally, the second generating unit is specifically configured to:

[0076] In the first row array and the second row array, data rows under the signal column where the key switch signal and the vehicle mode signal are located are amplified according to a preset data amplification coefficient and a preset amplification direction to form a final extracted data matrix;

[0077] The extracted data file is generated according to the final extracted data matrix and with the vehicle identification number as the file name.

[0078] An embodiment of the present invention further provides a vehicle data extraction device, comprising: a processor, a memory, and a program stored in the memory and executable on the processor, wherein when the program is executed by the processor, the vehicle data extraction method as described in any one of the above items is implemented.

[0079] An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the vehicle data extraction method as described in any one of the above items is implemented.

[0080] The beneficial effects of the present invention are:

[0081] The present invention provides a vehicle data extraction method, comprising: obtaining the original data file of the vehicle through a user data automatic capture platform; classifying the original data file according to a preset dimension through an original data file classification platform to obtain a classified data file; cleaning the classified data file through a data cleaning platform to obtain a cleaned data file; extracting the cleaned data file through a data extraction platform according to pre-set data extraction requirements and evaluation criteria to obtain an extracted data file. Through the above scheme, the processing time of vehicle data can be reduced, the processing quality of data can be improved, and data extraction can be performed based on specific requirements, providing data basis for further function development, testing and evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0082] Figure 1 A flow chart showing a vehicle data extraction method provided by an embodiment of the present invention;

[0083] Figure 2 A schematic diagram showing the structure of a vehicle data extraction device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0084] In order to make the objectives, technical solutions and advantages of the present invention more clear, the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0085] The present invention aims to solve the problem in the prior art that it is difficult to effectively extract vehicle data based on specific extraction requirements, and provides a vehicle data extraction method, device, equipment and medium.

[0086] like Figure 1 As shown, an embodiment of the present invention provides a vehicle data extraction method, comprising:

[0087] S101: Obtaining the original data file of the vehicle through the user data automatic capture platform;

[0088] S102: Classifying the original data file according to a preset dimension through an original data file classification platform to obtain a classified data file;

[0089] S103: Cleaning the classified data file through a data cleaning platform to obtain a cleaned data file;

[0090] S104: extracting the cleaned data file through the data extraction platform according to pre-set data extraction requirements and evaluation criteria to obtain an extracted data file.

[0091] It should be noted that the vehicle data extraction method provided in this embodiment establishes a platform architecture, including: a user data automatic capture platform, an original data file classification platform, a data cleaning platform and a data extraction platform, to realize the automatic acquisition, cleaning and extraction of pure electric vehicle data. Through the establishment of this platform architecture, not only the processing time of vehicle data is greatly reduced, but also the processing quality of vehicle data can be improved, and data can be extracted based on specific needs, providing data basis for further function development, testing and evaluation, and providing more objective and market-oriented data basis for the optimization and evaluation of related businesses.

[0092] This embodiment is based on MySQL or python software, and completes the construction of the above method and platform architecture by using programming languages ​​such as c++ and java.

[0093] Optionally, obtaining the original data file of the vehicle through the user data automatic capture platform includes:

[0094] Establishing a connection with the vehicle user data platform and the software database through the user data automatic capture platform;

[0095] Acquire basic attribute information of the vehicle on the vehicle user data platform, and store the basic attribute information in the software database;

[0096] According to the preset basic attribute information and the preset target time range, the original data file of the vehicle is obtained.

[0097] It should be noted that a connection is established between the user automatic capture platform and the vehicle user data platform and the software database, wherein the vehicle user data platform is used to obtain and store all basic attribute information of the vehicle during use. The user automatic capture platform obtains the basic attribute information of the vehicle and the corresponding vehicle usage data on the vehicle user data platform, and stores the basic attribute information and the vehicle usage data one by one in the software database. Thereafter, according to the required basic attribute information of the vehicle and the preset target time range, the vehicle usage data corresponding to the basic attribute information of the vehicle within the target time range is automatically obtained, and an original data file is formed.

[0098] Optionally, the raw data file is classified according to a preset dimension by the raw data file classification platform to obtain a classified data file, including:

[0099] Obtaining vehicle model information in the original data file through the original data file classification platform, creating a vehicle model folder in the original data file, and cutting original data files of the same vehicle model into the vehicle model folder;

[0100] In the vehicle model folder, the region information in the original data file is obtained, a region folder is created in the vehicle model folder, and the original data files of the same region are cut into the region folder.

[0101] It should be noted that the raw data files captured by the user automatic crawling platform are classified according to preset vehicle models, regions or other defined dimensions through the raw data file classification platform to avoid large deviations in subsequent analysis results due to data mixing.

[0102] In this embodiment, the vehicle model information in the original data file is obtained through the original data file classification platform, and vehicle model folders corresponding to different vehicle models are automatically established under the path of the original data file, and the original data files of the same vehicle model are automatically cut into the vehicle model folder. After that, the directory is switched to the vehicle model folder, and the regional information in the original file is extracted. Regional folders corresponding to different regions are established in the vehicle model folder, which is accurate to the "city" level, and the original folders of the same region are automatically cut into the regional folders to complete the classification of the original data.

[0103] The method of classifying the original data according to other defined dimensions, such as battery model, nature of vehicle usage, including commercial vehicles, private cars, etc., also falls within the scope of protection of the present invention.

[0104] Optionally, the cleaning of the classified data file by a data cleaning platform to obtain a cleaned data file includes:

[0105] Reading the vehicle data in the vehicle model folder and the region folder through the data cleaning platform;

[0106] Deleting data rows with missing signals in the vehicle data;

[0107] Deleting data rows whose data rows are less than a first set threshold or whose vehicle data existence time is less than a second set threshold;

[0108] Deleting data rows with obvious abnormalities in the vehicle data to obtain a cleaned data file;

[0109] The cleaning data in the cleaning data file is sent to the data extraction platform in the form of a matrix.

[0110] It should be noted that, through the data cleaning platform, the classified data classified by the original data file classification platform is cleaned according to predefined cleaning rules to remove useless data or data that interferes with subsequent extraction and analysis.

[0111] Traverse the original data files of each vehicle model and each region, read the vehicle data information, find the data rows with missing signals in the vehicle data in each folder, delete them, find the data rows with values ​​less than the specified threshold, or the data rows with vehicle data existence time less than the specified time threshold, delete them, find the data rows in the vehicle data that are significantly different from other data rows, such as data rows with cliff-like changes or data rows that exceed the valid range, etc., delete them, and complete the cleaning of the classified original data. Send the cleaned vehicle data to the data extraction platform in the form of a data matrix.

[0112] Optionally, the data extraction platform extracts the cleaned data file according to pre-set data extraction requirements and evaluation criteria to obtain the extracted data file, including:

[0113] Acquire the data extraction requirements and the evaluation criteria defined by the user and the data extraction feature variables configured by the user;

[0114] According to the data extraction characteristic variables, generating a characteristic data matrix related to the data extraction characteristic variables in the matrix of the cleaned data;

[0115] In the feature data matrix, according to the data extraction requirement and the evaluation criteria, a first row array and a second row array are generated, wherein under the data extraction requirement, the performance of the first row array is better than that of the second row array;

[0116] The extracted data file is generated according to the first row array and the second row array.

[0117] It should be noted that the purpose of extracting vehicle data is to provide reliable and effective data support for subsequent data analysis.

[0118] Before data extraction, the data extraction platform obtains the extraction requirements defined by the user, and the evaluation rules and configuration data extraction feature variables formulated according to the extraction requirements defined by the user. According to the data extraction feature variables, a feature data matrix related to the data extraction feature variables is generated in the matrix of the cleaned data. In the feature data matrix, according to the data extraction requirements and the evaluation criteria, a first row array and a second row array are generated, wherein the first row array is a data row with better performance under the data extraction requirements, and the second row array is a data row with worse performance under the data extraction requirements. According to the first row array and the second row array, the final extraction data file is generated.

[0119] Optionally, the obtaining of the data extraction requirement and the evaluation criteria defined by the user and the data extraction feature variables configured by the user includes:

[0120] Obtaining data extraction requirements for evaluating the driving range of a vehicle, and obtaining driving range evaluation criteria indicators formulated according to the data extraction requirements for evaluating the driving range of a vehicle;

[0121] The driving range evaluation criterion indicator is defined as: within the preset deviation calculation time range variable, the deviation value obtained by subtracting the change value of the driving range calculated by the vehicle control unit from the change value of the vehicle's actual driving range;

[0122] Obtain data feature extraction variables of user driving conditions.

[0123] It should be noted that the user's extraction requirements, evaluation criteria and characteristic variables support user customization. In this embodiment, the user-defined data extraction requirement is to evaluate the vehicle's driving range. The evaluation criteria formulated based on the extraction requirement of evaluating the vehicle's driving range support user customization. In this embodiment, it is defined as the driving range evaluation criterion index, which is calculated according to the formula: d(CDR) / dt-d(ODO) / dt, where CDR represents the driving range calculated by the vehicle control unit (Caculated Drive Range, CDR), and ODO represents the actual total mileage (Odograph ， ODO), dt is the deviation calculation time range variable, d(CDR) / dt represents the change value of the driving range calculated by the vehicle control unit within the deviation calculation time range variable, and d(ODO) / dt represents the change value of the actual total mileage within the deviation calculation time range variable. Among them, the deviation calculation time range variable dt also supports user customization.

[0124] Optionally, extracting characteristic variables from the data and generating a characteristic data matrix related to the characteristic variables extracted from the data in the matrix of the cleaned data includes:

[0125] Extract variables according to the data features of the user's driving condition, find the signal column where the key switch signal and the vehicle mode signal are located in the first row of the matrix of the cleaned data, extract the signal column to generate a target data matrix;

[0126] In the signal column where the key switch signal of the target data matrix is ​​located, the data rows that cannot form the start and end arrays or the data rows that do not correspond to the driving mode signals in the signal column where the vehicle mode signal is located are eliminated, and a user driving condition data matrix is ​​generated.

[0127] It should be noted that the data extraction feature variables also support user-defined configuration. In this embodiment, the feature extraction variables for evaluating the vehicle's driving range are feature variables related to the user's driving conditions, such as the key switch signal and the vehicle mode signal. In the first row of the feature data matrix, that is, the signal name row, the signal column where the key switch signal and the vehicle mode signal are located is searched, and the corresponding signal column vector is extracted to generate the target data matrix. In the key switch signal column vector in the target data matrix, the (ON, OFF) values ​​that appear in pairs are searched, and the data rows corresponding to each "ON" and "OFF" value are extracted, and the two are combined to form a row array, that is, the data start row and end row corresponding to an ON gear driving cycle. If a row array cannot be formed, that is, a data row corresponding to a single "ON" value or "OFF" value appears, or the data row corresponding to the driving mode signal is not in the signal column where the vehicle mode signal is located, the data rows corresponding to the above two situations are deleted to form a user driving condition data matrix.

[0128] Optionally, in the feature data matrix, generating a first row array and a second row array according to the data extraction requirement and the evaluation criteria includes:

[0129] In the user driving condition data matrix, a deviation value of a change value of the driving range calculated by the vehicle control unit minus a change value of the vehicle's actual driving range is obtained within a preset deviation calculation time range variable;

[0130] The deviation value is compared with a set threshold value. If the deviation value is greater than or equal to the set threshold value, the first row array is generated. If the deviation value is less than the set threshold value, the second row array is generated.

[0131] It should be noted that, by traversing the above-mentioned user driving condition data matrix, within the data range corresponding to each row array, the values ​​of the driving range CDR calculated by the vehicle control unit and the actual total driving range ODO are extracted with the deviation calculation time range variable dt as the interval, and subtracted in chronological order, multiple sets of change values ​​d(CDR) / dt of the driving range calculated by the vehicle control unit within the deviation calculation time range variable, and the change values ​​d(ODO) / dt of the actual total driving range within the deviation calculation time range variable can be obtained. Subtracting according to the formula of the above-mentioned driving range evaluation criterion index, multiple sets of deviation values ​​are obtained, and each deviation value is compared with the set threshold value. When the deviation value is greater than or equal to the set threshold value, the row array corresponding to the deviation value is determined to be the first row array, that is, the data row corresponding to the data that the user's driving behavior is poor and the driving range algorithm performs poorly. If the deviation value is less than the set threshold value, the row array corresponding to the deviation value is determined to be the second row array, that is, the data row corresponding to the data that the user's driving behavior is good and the driving range algorithm performs well.

[0132] Optionally, generating the extracted data file according to the first row array and the second row array includes:

[0133] In the first row array and the second row array, data rows under the signal column where the key switch signal and the vehicle mode signal are located are amplified according to a preset data amplification coefficient and a preset amplification direction to form a final extracted data matrix;

[0134] The extracted data file is generated according to the final extracted data matrix and with the vehicle identification number as the file name.

[0135] It should be noted that in the first row array and the second row array, the values ​​of the time variables in the data rows under the signal columns of the key switch signal and the vehicle mode signal are extracted, and the data is amplified in the direction of smaller time according to the preset data amplification coefficient variable, so as to offset the time lag effect in the data transmission process and form the final extracted data matrix. According to the final extracted data matrix, a document in Excel and CSV format is generated with the vehicle identification number (Vehicle Identification Number, VIN) as the file name, which is the extracted data file.

[0136] Through the above-mentioned vehicle data extraction method, based on the data extraction requirements for evaluating the vehicle's driving range, the corresponding relationship between the user's driving behavior and the driving range algorithm can be analyzed based on the extracted data file, and typical driving conditions of different regions and user groups can be extracted, and related control strategy development can also be optimized. In addition, the invisible influencing factors of driving range are the remaining power and remaining life of the battery. Through the vehicle data extraction method proposed in this embodiment, relevant data support can also be provided for the prediction of battery life and health. The battery life can be improved through the subsequent corresponding algorithm optimization, greatly reducing the maintenance cost in the later stage.

[0137] like Figure 2 As shown, an embodiment of the present invention further provides a vehicle data extraction device, comprising:

[0138] The acquisition module 201 is used to acquire the original data file of the vehicle through the user data automatic capture platform;

[0139] The classification module 202 is used to classify the original data file according to a preset dimension through the original data file classification platform to obtain a classified data file;

[0140] A cleaning module 203 is used to clean the classified data file through a data cleaning platform to obtain a cleaned data file;

[0141] The extraction module 204 is used to extract the cleaned data file through the data extraction platform according to the pre-set data extraction requirements and evaluation criteria to obtain the extracted data file.

[0142] Optionally, the acquisition module 201 includes:

[0143] A connection unit, used to establish a connection with the vehicle user data platform and the software database through the user data automatic capture platform;

[0144] A storage unit, used to obtain basic attribute information of the vehicle on the vehicle user data platform, and store the basic attribute information in the software database;

[0145] The first acquisition unit is used to acquire the original data file of the vehicle according to preset basic attribute information and a preset target time range.

[0146] Optionally, the classification module 202 includes:

[0147] A second acquisition unit is used to acquire vehicle model information in the original data file through the original data file classification platform, establish a vehicle model folder in the original data file, and cut the original data files of the same vehicle model into the vehicle model folder;

[0148] The second acquisition unit is used to acquire the region information in the original data file in the vehicle model folder, establish a region folder in the vehicle model folder, and cut the original data files of the same region into the region folder.

[0149] Optionally, the cleaning module 203 includes:

[0150] A reading unit, used for reading the vehicle data information in the vehicle model folder and the regional folder through the data cleaning platform;

[0151] A first deleting unit, used to delete data rows with missing signals in the vehicle data;

[0152] A second deleting unit, used to delete data rows whose data rows are smaller than a first set threshold or whose vehicle data existence time is smaller than a second set threshold;

[0153] A third deleting unit is used to delete data rows with obvious abnormalities in the vehicle data to obtain a cleaned data file;

[0154] A sending unit is used to send the cleaning data in the cleaning data file to the data extraction platform in the form of a matrix.

[0155] Optionally, the extraction module 204 includes:

[0156] A third acquisition unit, used to acquire the data extraction requirements and the evaluation criteria defined by the user and the data extraction feature variables configured by the user;

[0157] An extraction unit, configured to extract characteristic variables according to the data, and generate a characteristic data matrix related to the characteristic variables extracted from the data in the matrix of the cleaned data;

[0158] A first generating unit is used to generate a first row array and a second row array in the feature data matrix according to the data extraction requirement and the evaluation criteria, wherein under the data extraction requirement, the performance of the first row array is better than that of the second row array;

[0159] The second generating unit is used to generate the extracted data file according to the first row array and the second row array.

[0160] Optionally, the third acquiring unit is specifically used to:

[0161] Obtaining data extraction requirements for evaluating the driving range of a vehicle, and obtaining driving range evaluation criteria indicators formulated according to the data extraction requirements for evaluating the driving range of a vehicle;

[0162] The driving range evaluation criterion indicator is defined as: within the preset deviation calculation time range variable, the deviation value obtained by subtracting the change value of the driving range calculated by the vehicle control unit from the change value of the vehicle's actual driving range;

[0163] Obtain data feature extraction variables of user driving conditions.

[0164] Optionally, the extraction unit is specifically used for:

[0165] Extract variables according to the data features of the user's driving condition, find the signal column where the key switch signal and the vehicle mode signal are located in the first row of the matrix of the cleaned data, extract the signal column to generate a target data matrix;

[0166] In the signal column where the key switch signal of the target data matrix is ​​located, the data rows that cannot form the start and end arrays or the data rows that do not correspond to the driving mode signals in the signal column where the vehicle mode signal is located are eliminated, and a user driving condition data matrix is ​​generated.

[0167] Optionally, the first generating unit is specifically configured to:

[0168] In the user driving condition data matrix, a deviation value of a change value of the driving range calculated by the vehicle control unit minus a change value of the vehicle's actual driving range is obtained within a preset deviation calculation time range variable;

[0169] The deviation value is compared with a set threshold value. If the deviation value is greater than or equal to the set threshold value, the first row array is generated. If the deviation value is less than the set threshold value, the second row array is generated.

[0170] Optionally, the second generating unit is specifically configured to:

[0171] In the first row array and the second row array, data rows under the signal column where the key switch signal and the vehicle mode signal are located are amplified according to a preset data amplification coefficient and a preset amplification direction to form a final extracted data matrix;

[0172] The extracted data file is generated according to the final extracted data matrix and with the vehicle identification number as the file name.

[0173] An embodiment of the present invention further provides a vehicle data extraction device, comprising: a processor, a memory, and a program stored in the memory and executable on the processor, wherein when the program is executed by the processor, the vehicle data extraction method as described in any one of the above items is implemented.

[0174] An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the vehicle data extraction method as described in any one of the above items is implemented.

[0175] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary personnel in this technical field, several improvements and modifications can be made without departing from the principles described in the present invention. These improvements and modifications are also within the scope of protection of the present invention.

Claims

1. A vehicle data extraction method, characterized in that: include: Obtain the original data file of the vehicle through the user data automatic capture platform; Classifying the original data files according to preset dimensions through the original data file classification platform to obtain classified data files; Cleaning the classified data file through a data cleaning platform to obtain a cleaned data file; Through the data extraction platform, according to the pre-set data extraction requirements and evaluation criteria, the cleaned data file is extracted to obtain an extracted data file; The data extraction platform extracts the cleaned data file according to the pre-set data extraction requirements and evaluation criteria to obtain the extracted data file, including: Acquire the data extraction requirements and the evaluation criteria defined by the user and the data extraction feature variables configured by the user; According to the data extraction characteristic variables, generating a characteristic data matrix related to the data extraction characteristic variables in the matrix of the cleaned data; In the feature data matrix, a first row array and a second row array are generated according to the data extraction requirement and the evaluation criteria, wherein under the data extraction requirement, the performance of the first row array is better than that of the second row array; Generate the extracted data file according to the first row array and the second row array; The step of generating the extracted data file according to the first row array and the second row array includes: In the first row array and the second row array, data rows under the signal column where the key switch signal and the vehicle mode signal are located are amplified according to a preset data amplification coefficient and a preset amplification direction to form a final extracted data matrix; The extracted data file is generated according to the final extracted data matrix and with the vehicle identification number as the file name.

2. The vehicle data extraction method according to claim 1, characterized in that: The method of obtaining the original data file of the vehicle through the user data automatic capture platform includes: Establishing a connection with the vehicle user data platform and the software database through the user data automatic capture platform; Acquire basic attribute information of the vehicle on the vehicle user data platform, and store the basic attribute information in the software database; According to the preset basic attribute information and the preset target time range, the original data file of the vehicle is obtained.

3. The vehicle data extraction method according to claim 1, characterized in that: The original data file classification platform is used to classify the original data file according to a preset dimension to obtain a classified data file, including: Obtaining vehicle model information in the original data file through the original data file classification platform, creating a vehicle model folder in the original data file, and cutting original data files of the same vehicle model into the vehicle model folder; In the vehicle model folder, the region information in the original data file is obtained, a region folder is created in the vehicle model folder, and the original data files of the same region are cut into the region folder.

4. The vehicle data extraction method according to claim 3, characterized in that: The classified data file is cleaned by the data cleaning platform to obtain a cleaned data file, including: Reading the vehicle data in the vehicle model folder and the region folder through the data cleaning platform; Deleting data rows with missing signals in the vehicle data; Deleting data rows whose data rows are less than a first set threshold or whose vehicle data existence time is less than a second set threshold; Deleting data rows with obvious abnormalities in the vehicle data to obtain a cleaned data file; The cleaning data in the cleaning data file is sent to the data extraction platform in the form of a matrix.

5. The vehicle data extraction method according to claim 4, characterized in that: The obtaining of the data extraction requirements and the evaluation criteria defined by the user and the data extraction feature variables configured by the user includes: Obtaining data extraction requirements for evaluating the driving range of a vehicle, and obtaining driving range evaluation criteria indicators formulated according to the data extraction requirements for evaluating the driving range of a vehicle; The driving range evaluation criterion indicator is defined as: within the preset deviation calculation time range variable, the deviation value obtained by subtracting the change value of the driving range calculated by the vehicle control unit from the change value of the vehicle's actual driving range; Obtain data feature extraction variables of user driving conditions.

6. The vehicle data extraction method according to claim 5, characterized in that: The step of extracting characteristic variables from the data and generating a characteristic data matrix related to the characteristic variables extracted from the data in the matrix of the cleaned data includes: Extract variables according to the data features of the user's driving condition, find the signal column where the key switch signal and the vehicle mode signal are located in the first row of the matrix of the cleaned data, extract the signal column to generate a target data matrix; In the signal column where the key switch signal of the target data matrix is ​​located, the data rows that cannot form the start and end arrays or the data rows that do not correspond to the driving mode signals in the signal column where the vehicle mode signal is located are eliminated, and a user driving condition data matrix is ​​generated.

7. The vehicle data extraction method according to claim 6, characterized in that: In the feature data matrix, according to the data extraction requirements and the evaluation criteria, a first row array and a second row array are generated, including: In the user driving condition data matrix, a deviation value of a change value of the driving range calculated by the vehicle control unit minus a change value of the vehicle's actual driving range is obtained within a preset deviation calculation time range variable; The deviation value is compared with a set threshold value. If the deviation value is greater than or equal to the set threshold value, the first row array is generated. If the deviation value is less than the set threshold value, the second row array is generated.

8. A vehicle data extraction device, characterized in that: include: The acquisition module is used to obtain the original data file of the vehicle through the user data automatic crawling platform; A classification module, used to classify the original data file according to a preset dimension through an original data file classification platform to obtain a classified data file; A cleaning module, used for cleaning the classified data file through a data cleaning platform to obtain a cleaned data file; An extraction module, used to extract the cleaned data file through a data extraction platform according to pre-set data extraction requirements and evaluation criteria to obtain an extracted data file; Wherein, the extraction module comprises: A third acquisition unit, used to acquire the data extraction requirements and the evaluation criteria defined by the user and the data extraction feature variables configured by the user; An extraction unit, configured to extract characteristic variables according to the data, and generate a characteristic data matrix related to the characteristic variables extracted from the data in the matrix of the cleaned data; A first generating unit is used to generate a first row array and a second row array in the feature data matrix according to the data extraction requirement and the evaluation criteria, wherein under the data extraction requirement, the performance of the first row array is better than that of the second row array; A second generating unit, configured to generate the extracted data file according to the first row array and the second row array; Wherein, the second generating unit is specifically used for: In the first row array and the second row array, data rows under the signal column where the key switch signal and the vehicle mode signal are located are amplified according to a preset data amplification coefficient and a preset amplification direction to form a final extracted data matrix; The extracted data file is generated according to the final extracted data matrix and with the vehicle identification number as the file name.

9. A vehicle data extraction device, characterized in that: include: A processor, a memory, and a program stored in the memory and executable on the processor, wherein when the program is executed by the processor, the vehicle data extraction method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the vehicle data extraction method according to any one of claims 1 to 7 is implemented.

Images