Vehicle abnormal operation data processing method and device, equipment and medium

Abstract

The invention discloses a vehicle abnormal operation data processing method and device, equipment and a medium, and the method comprises the steps: calculating an arithmetic mean value and a standard deviation of vehicle operation data in a preset time interval, the vehicle operation data comprising mileage data and / or fuel consumption data; calculating a standard score of the vehicle operation data corresponding to each acquisition time according to the vehicle operation data of each acquisition time in the time interval, the arithmetic average value and the standard deviation; according to each standard score, identifying whether the corresponding vehicle operation data is the abnormal operation data, thereby realizing accurate identification of the abnormal operation data in the collected vehicle operation data such as mileage data and / or fuel consumption data, and replacing the abnormal operation data with the non-abnormal vehicle operation data. And the accuracy of an analysis result when the vehicle operation data is analyzed is ensured.

Description

Technical Field

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

[0002] When analyzing the mileage data and fuel consumption data collected by the vehicle, it was found that the collected data was abnormal due to various reasons, mainly manifested as: 1. Abnormal 0 value; 2. The offset of the collected mileage data / fuel consumption data over time exceeded the reasonable range. If the above abnormal data is not processed, it will have a great impact on the downstream fuel consumption analysis and other data analysis results, thereby affecting the optimization of the vehicle.

[0003] In the related art, the method for identifying and processing abnormal data is as follows: after sorting the mileage data and fuel consumption data according to the collection time, the data of each collection time is subtracted from the data of the previous collection time to obtain the mileage offset and fuel consumption offset corresponding to each collection time. When the mileage offset △mileage (m)>max vehicle speed (m / s)*△time (s), it is recognized that the mileage collected at the collection time has a jump; when the fuel consumption offset △fuel consumption (L)>max fuel consumption (L / s)*△time (s), it is recognized that the fuel consumption collected at the collection time has a jump.

[0004] Although this abnormal data recognition method can identify abnormal mileage and fuel consumption data in some scenarios, it has the following problems: First, when the vehicle's instrument is abnormal, the mileage / fuel consumption values ​​of multiple data may jump continuously. For example, the mileage is 100km at the collection time 10:00:00, and jumps to 10000km at the collection time 10:01:00-10:05:00, and returns to normal at 106km at 10:06:00. If the recognition is performed based on the difference between the previous and subsequent data, only the abnormality at 10:01:00 can be recognized, and the abnormality at 10:02:00-10:05:00 cannot be recognized, and the normal data at 10:06:00 will be misjudged as abnormal data; secondly, the abnormality of the instrument or TBOX may cause the mileage / fuel consumption data to appear as 0 (while the mileage / fuel consumption data in actual vehicle use is basically impossible to be 0), and the previous recognition mode will judge the next normal data after the abnormal data 0 value as abnormal; thirdly, when the vehicle replaces the instrument, the mileage / fuel consumption data will be reset to zero and recalculated, so the data at this moment seems to have jumped but is actually normal data, but the current recognition mode will recognize it as abnormal data.

[0005] Therefore, how to accurately identify and process vehicle operation data such as mileage data and fuel consumption data is a technical problem that needs to be solved urgently. Summary of the invention

[0006] The present application provides a method, device, and equipment medium for processing abnormal vehicle operation data, which can solve the problem in the prior art that it is impossible to accurately identify and process abnormal data in collected vehicle operation data such as mileage data and fuel consumption data.

[0007] In a first aspect, an embodiment of the present application provides a method for processing abnormal vehicle operation data, the method for processing abnormal vehicle operation data comprising:

[0008] Calculating an arithmetic mean and a standard deviation of vehicle operation data within a preset time interval, wherein the vehicle operation data includes mileage data and / or fuel consumption data;

[0009] Calculating a standard score of the vehicle operation data corresponding to each collection time according to the vehicle operation data at each collection time within the time interval, the arithmetic mean and the standard deviation;

[0010] Identify whether the corresponding vehicle operation data is abnormal operation data according to each standard score;

[0011] The abnormal operation data is replaced with vehicle operation data without abnormality.

[0012] In combination with the first aspect, in one implementation, the calculating the standard score of the vehicle operation data corresponding to each collection time according to the vehicle operation data at each collection time in the time interval, the arithmetic mean and the standard deviation respectively includes:

[0013] The arithmetic mean is subtracted from the vehicle operation data at each collection time to obtain a corresponding difference, and the difference is divided by the standard deviation to obtain a standard score of the vehicle operation data corresponding to each collection time.

[0014] In one embodiment, the step of identifying whether the corresponding vehicle operation data is abnormal operation data according to each standard score includes:

[0015] Determining whether the standard score is greater than a preset score threshold;

[0016] When the standard score is greater than the score threshold, calculating the absolute value of the difference between the corresponding vehicle operation data and the arithmetic mean;

[0017] If the absolute value of the difference is less than the preset absolute value threshold, it is determined that the corresponding vehicle operation data is normal;

[0018] If the absolute value of the difference is greater than or equal to the absolute value threshold, it is determined that the corresponding vehicle operating data is abnormal operating data.

[0019] In one implementation, replacing the abnormal operation data with vehicle operation data without abnormality includes:

[0020] Setting the abnormal operation data to a value of 0;

[0021] And fill the non-zero value of vehicle operation data before each zero value to the corresponding zero value.

[0022] In one embodiment, after filling the vehicle operation data with a non-zero value before each zero value to the corresponding zero value, the method further includes:

[0023] Calculating a first offset between the vehicle operation data at each collection time and the vehicle operation data at a previous collection time, and a second offset between the vehicle operation data at a next collection time;

[0024] If both the first offset and the second offset are greater than a preset maximum offset threshold, determining that the vehicle operation data at the corresponding collection time is abnormal data;

[0025] The vehicle operation data without abnormality before each abnormal data is filled into the corresponding abnormal data.

[0026] In one embodiment, if the vehicle operation data includes mileage data, the maximum offset threshold includes a maximum unit vehicle speed multiplied by a collection time interval;

[0027] If the vehicle operation data includes fuel consumption data, the maximum offset threshold includes the maximum unit fuel consumption multiplied by the collection time interval.

[0028] In one embodiment, before calculating the arithmetic mean and standard deviation of the vehicle operation data within the preset time interval, the method further includes:

[0029] The vehicle operation data are sorted according to the collection time, and the vehicle operation data at each collection time are deduplicated.

[0030] In a second aspect, an embodiment of the present application provides a device for processing abnormal vehicle operation data, the device for processing abnormal vehicle operation data comprising:

[0031] A first calculation module, which is used to calculate the arithmetic mean and standard deviation of vehicle operation data within a preset time interval, wherein the vehicle operation data includes mileage data and / or fuel consumption data;

[0032] A second calculation module, which is used to calculate the standard score of the vehicle operation data corresponding to each collection time according to the vehicle operation data at each collection time in the time interval, the arithmetic mean and the standard deviation;

[0033] An identification module, which is used to identify whether the corresponding vehicle operation data is abnormal operation data according to each standard score;

[0034] A replacement module is used to replace the abnormal operation data with vehicle operation data without abnormality.

[0035] In the third aspect, an embodiment of the present application provides a device for processing vehicle abnormal operation data, wherein the device for processing vehicle abnormal operation data comprises a processor, a memory, and a processing program for vehicle abnormal operation data stored in the memory and executable by the processor, wherein when the processing program for vehicle abnormal operation data is executed by the processor, the steps of the method for processing vehicle abnormal operation data as described in any one of the above items are implemented.

[0036] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a program for processing vehicle abnormal operation data is stored, wherein when the program for processing vehicle abnormal operation data is executed by a processor, the steps of the method for processing vehicle abnormal operation data as described in any one of the above items are implemented.

[0037] The embodiments of the present application provide a method, device, equipment and medium for processing abnormal vehicle operation data, by calculating the arithmetic mean and standard deviation of vehicle operation data within a preset time interval, wherein the vehicle operation data includes mileage data and / or fuel consumption data; calculating the standard score of the vehicle operation data corresponding to each collection time according to the vehicle operation data at each collection time within the time interval, the arithmetic mean and the standard deviation; identifying whether the corresponding vehicle operation data is abnormal operation data according to each standard score, thereby achieving accurate identification of abnormal operation data in the collected vehicle operation data such as mileage data and / or fuel consumption data, and replacing the abnormal operation data with vehicle operation data without abnormalities, thereby ensuring the accuracy of the analysis results when the downstream analyzes the vehicle operation data. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 This is a flow chart of an embodiment of a method for processing abnormal vehicle operation data of the present application;

[0039] Figure 2 A schematic diagram of a specific process of the method for processing abnormal vehicle operation data in this application;

[0040] Figure 3 This is a functional module diagram of an embodiment of a device for processing abnormal vehicle operation data of the present application;

[0041] Figure 4 This is a schematic diagram of the hardware structure of a device for processing abnormal vehicle operation data involved in an embodiment of the present application. DETAILED DESCRIPTION

[0042] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0043] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0044] In a first aspect, an embodiment of the present application provides a method for processing abnormal vehicle operation data. The method can be implemented in a vehicle operation data analysis platform.

[0045] In one embodiment, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the method for processing abnormal vehicle operation data of the present application. Figure 1 As shown, the method for processing abnormal vehicle operation data includes steps S101 to S104.

[0046] Step S101: Calculate the arithmetic mean and standard deviation of vehicle operation data within a preset time interval, wherein the vehicle operation data includes mileage data and / or fuel consumption data.

[0047] In addition to mileage data and / or fuel consumption data, the vehicle operation data in this embodiment may also be other data generated during the operation of the vehicle.

[0048] In one embodiment, if Figure 2 As shown, before calculating the arithmetic mean and standard deviation of the vehicle operation data, the method further includes: sorting the vehicle operation data according to the collection time, and removing duplicates from the vehicle operation data at each collection time.

[0049] It is worth noting that when the method for processing abnormal vehicle operation data provided in this embodiment is implemented on a vehicle operation data analysis platform, the vehicle-mounted terminal TBOX of each vehicle can obtain the vehicle operation data, and upload the vehicle operation data to the data warehouse original data layer of the vehicle operation data analysis platform with the vehicle identification number, so the data warehouse original data layer includes the operation data of multiple vehicles. The data warehouse original data layer can store the vehicle operation data in the form of a hive table.

[0050] Exemplarily, the time interval can be set according to demand. In this embodiment, the preset time interval is daily, that is, 24 hours. The time interval includes multiple collection times. In this embodiment, the interval of the collection time is 1 second. When processing abnormal vehicle operation data, the vehicle operation data of multiple vehicles in the previous day are extracted from the original data layer of the data warehouse. Then the vehicle operation data is aggregated according to the vehicle identification number, that is, the operation data of the same vehicle is processed independently. For each vehicle, the operation data is sorted according to the collection time, and the data is deduplicated according to the collection time.

[0051] In this embodiment, the operating data of multiple vehicles are extracted from the original data layer of the data warehouse at the same time, and the operating data of the same vehicle are aggregated according to the vehicle identification number. The operating data of the same vehicle is independently processed for exceptions, which enables the operating data of multiple vehicles to be processed in parallel at the same time, thereby improving processing efficiency.

[0052] For ease of understanding, this embodiment takes the vehicle operation data as mileage data as an example to illustrate an embodiment of the method for processing abnormal vehicle operation data of the present application.

[0053] Taking the vehicle operation data as mileage data as an example, the arithmetic mean of the vehicle operation data within the preset time interval calculated in step S101 is:

[0054] mean_mileage=(mileage1+mileage2+...+mileageN) / N

[0055] Wherein, mean_mileage is the arithmetic mean of the mileage data in the time interval, mileage1, mileage2...mileageN are the mileage data collected from the first collection time, the second collection time to the Nth collection time respectively, and N is the number of mileage data in the time interval.

[0056] Calculate the standard deviation of mileage data within the time interval std_mileage =:

[0057]

[0058] Among them, std_mileage is the standard deviation of mileage data in the time interval.

[0059] Step S102: Calculate the standard score of the vehicle operation data corresponding to each collection time according to the vehicle operation data at each collection time in the time interval, the arithmetic mean and the standard deviation.

[0060] The specific steps of step S102 include: subtracting the arithmetic mean from the vehicle operation data at each collection time to obtain a corresponding difference, dividing the difference by the standard deviation, and obtaining a standard score of the vehicle operation data corresponding to each collection time.

[0061] Exemplarily, the mileage data at each collection time is subtracted from the arithmetic mean of the mileage data to obtain the corresponding difference, and the difference is divided by the standard deviation of the mileage data to obtain the standard score of the mileage data corresponding to each collection time:

[0062] Z-score=(mileageX-mean_mileage) / std_mileage

[0063] Among them, mileageX is the mileage data at the Xth collection time, mean_mileage is the arithmetic mean of the mileage data in the time interval, std_mileage is the standard deviation of the mileage data in the time interval, and Z-score is the standard score of the mileage data corresponding to the Xth collection time.

[0064] Step S103: Identify whether the corresponding vehicle operation data is abnormal operation data according to each standard score.

[0065] Specifically, determine whether the standard score is greater than a preset score threshold; when the standard score is greater than the score threshold, calculate the absolute value of the difference between the corresponding vehicle operating data and the arithmetic mean; if the absolute value of the difference is less than the preset absolute value threshold, determine that the corresponding vehicle operating data is normal; if the absolute value of the difference is greater than or equal to the absolute value threshold, determine that the corresponding vehicle operating data is abnormal.

[0066] For example, in this embodiment, the score threshold is set to 3, and it is determined whether the standard score Z-score corresponding to the mileage data at each collection time is greater than 3. When the standard score is greater than 3, it means that the corresponding mileage data is a jump value of 0 or an abnormally large value, so it is considered that the mileage data may be abnormal.

[0067] Since there is too little driving data for a certain vehicle, it is easy to cause misjudgment when identifying abnormal operating data based on the standard score, so the absolute value of the difference between the mileage data with a standard score greater than the score threshold and the arithmetic mean of the mileage data is calculated. In this embodiment, the absolute value threshold can be set to the daily growth upper limit of the corresponding vehicle operating data. For example, when the vehicle operating data is mileage data, the absolute value threshold is set to 1000KM. Therefore, when the absolute value of the difference is less than 1000KM, it is considered that the result of determining whether the mileage data is abnormal mileage data based on the standard score is inaccurate, and it is considered that there is no jump in the mileage data and it is not marked as abnormal mileage data. When the absolute value of the difference is greater than or equal to 1000KM, it is considered that there is a jump in the mileage data and it is marked as abnormal mileage data.

[0068] When the vehicle operation data is fuel consumption data, the absolute value threshold may be set to 100L.

[0069] This embodiment uses the standard score of the vehicle operation data in combination with the difference between the vehicle operation data and the arithmetic mean value to identify abnormal operation data with extremely large and / or extremely small jumps.

[0070] Step S104: Replace the abnormal operation data with vehicle operation data without abnormality.

[0071] In one embodiment, step S104 specifically includes: setting the abnormal operation data to a value of 0; and filling a non-zero value of vehicle operation data before each zero value to the corresponding zero value.

[0072] It is worth noting that vehicle operating data such as mileage data and fuel consumption data will not be 0.0 under most normal operating conditions. Therefore, after identifying abnormal operating data, the abnormal operating data can be set to 0.0, and then after marking is completed, the 0.0 value can be uniformly filled.

[0073] The filling methods after setting the abnormal operation data to 0.0 include: when the 0.0 value appears once in the data, use the previous non-0 value of the vehicle operation data to fill it; when the 0.0 value appears continuously in the data, use the last non-0 value of the vehicle operation data before the 0.0 value to fill it.

[0074] Furthermore, after filling a non-zero value of vehicle operation data before each zero value to the corresponding zero value, it also includes: calculating a first offset between the vehicle operation data at each collection time and the vehicle operation data at the previous collection time, and a second offset between the vehicle operation data at the next collection time; if the first offset and the second offset are both greater than a preset maximum offset threshold, determining that the vehicle operation data at the corresponding collection time is abnormal data; and filling a non-abnormal vehicle operation data before each abnormal data to the corresponding abnormal data.

[0075] It is worth noting that if the vehicle operation data includes mileage data, the maximum offset threshold includes the maximum unit vehicle speed multiplied by the collection time interval. In this embodiment, the maximum unit vehicle speed is 0.2 KM / s.

[0076] If the vehicle operation data includes fuel consumption data, the maximum offset threshold includes the maximum unit fuel consumption multiplied by the collection time interval. In this embodiment, the maximum unit fuel consumption is 0.03 L / s.

[0077] The maximum offset threshold is the maximum offset within a reasonable range. When the offset between the vehicle transportation data at one collection time and the vehicle transportation data at the previous and next collection times is greater than the maximum offset threshold, it means that the offset exceeds the reasonable range, so it is identified as abnormal operation data, thereby accurately identifying small difference jumps in vehicle operation parameters. Replacing and filling the identified abnormal operation data is conducive to the accuracy of the analysis results when analyzing the vehicle operation data.

[0078] When the vehicle operation data is fuel consumption data or other operation data, the processing method and process are the same as those of the mileage data, so they will not be described in detail.

[0079] In a specific embodiment, if vehicle A performs a system time calibration at 12:00:00 on a certain day, and after running for 10 minutes, the tbox system time is 12:11:00, and after the time calibration is triggered, the tbox system time becomes 12:10:01, and the mileage data uploaded subsequently will show a small jump. For example, the original mileage data collected is shown in Table 1:

[0080] Table 1 Original mileage data under time calibration scenario

[0081] TBOX collection time Mileage (km) 12:10:00 1000.00 12:11:00 1002.00 12:10:01 1002.00 12:11:01 1004.00 12:12:01 1006.00

[0082] After sorting the mileage data according to the collection time, the mileage abnormal data judgment results obtained by using the abnormal data identification rules in the existing technology and the vehicle abnormal operation data processing method provided by this embodiment are shown in Table 2:

[0083] Table 2 Results of abnormal mileage data judgment under time calibration scenario

[0084]

[0085]

[0086] Since it is objectively difficult to completely eliminate the time error of the TBOX system, when judging abnormal data, it is necessary to tolerate occasional small setbacks or jumps in mileage or fuel consumption data.

[0087] For some vehicles with replaced instruments, the original mileage data is as follows: Figure 3 As shown:

[0088] Figure 3 Original mileage data for instrument replacement scenarios

[0089] TBOX collection time Mileage (km) 12:10:00 300000.00 12:11:00 300002.00 12:40:00 0.10 12:41:00 1.10 12:42:00 2.10

[0090] After the data is sorted according to the collection time, the mileage abnormal data judgment results made according to the abnormal data identification rules in the existing technology and the vehicle abnormal operation processing method provided by this embodiment are shown in Table 4:

[0091] Table 4 Results of abnormal mileage data judgment under the instrument replacement scenario

[0092] TBOX collection time Mileage (km) Jump (old rules) Jump (this embodiment) 12:10:00 300000.00 / / 12:11:00 300002.00 no no 12:40:00 0.10 yes no 12:41:00 1.10 no no 12:42:00 2.10 no no

[0093] It can be seen that the existing abnormal data jump scenario is mainly to sort the mileage / fuel consumption data by time, and compare whether the increment of the previous and next values ​​meets the vehicle speed multiplied by the maximum unit time offset during the vehicle's driving process. If it exceeds the threshold, it is judged as a jump. However, since there may not be only one jump value, misjudgment or missed judgment may occur in many cases. Compared with the existing technology, the identification of abnormal vehicle operation data in this embodiment is more accurate and more practical.

[0094] The method for processing abnormal vehicle operation data provided in this embodiment calculates the standard score of the vehicle operation data corresponding to each collection time according to the vehicle operation data at each collection time within the time interval, the arithmetic mean of the vehicle operation data and the standard deviation of the vehicle operation data, uses the standard score to identify the maximum and minimum jump data, and uses the unit data multiplied by the collection time interval to identify the small difference jump, which can accurately identify the abnormal data in the vehicle operation data such as mileage data and fuel consumption data, and reduce the misjudgment scenario. And based on the characteristics that the mileage data and fuel consumption data are not zero, after the abnormal data identification is completed, it can be directly set to 0.0, so that the vehicle operation data with a previous non-zero value can be used to uniformly replace and fill 0.0, which is conducive to the accuracy of the analysis results when analyzing the vehicle operation data.

[0095] In a second aspect, an embodiment of the present application also provides a device for processing abnormal vehicle operation data.

[0096] In one embodiment, referring to Figure 3 , Figure 3 This is a functional module diagram of an embodiment of a device for processing abnormal vehicle operation data of the present application. Figure 3 As shown, the vehicle abnormal operation data processing device includes:

[0097] A first calculation module, which is used to calculate the arithmetic mean and standard deviation of vehicle operation data within a preset time interval, wherein the vehicle operation data includes mileage data and / or fuel consumption data;

[0098] A second calculation module, which is used to calculate the standard score of the vehicle operation data corresponding to each collection time according to the vehicle operation data at each collection time in the time interval, the arithmetic mean and the standard deviation;

[0099] An identification module, which is used to identify whether the corresponding vehicle operation data is abnormal operation data according to each standard score;

[0100] A replacement module is used to replace the abnormal operation data with vehicle operation data without abnormality.

[0101] Furthermore, in one embodiment, the second calculation module is further configured to:

[0102] The arithmetic mean is subtracted from the vehicle operation data at each collection time to obtain a corresponding difference, and the difference is divided by the standard deviation to obtain a standard score of the vehicle operation data corresponding to each collection time.

[0103] Furthermore, in one embodiment, the identification module is also used for:

[0104] Determining whether the standard score is greater than a preset score threshold;

[0105] When the standard score is greater than the score threshold, calculating the absolute value of the difference between the corresponding vehicle operation data and the arithmetic mean;

[0106] If the absolute value of the difference is less than the preset absolute value threshold, it is determined that the corresponding vehicle operation data is normal;

[0107] If the absolute value of the difference is greater than or equal to the absolute value threshold, it is determined that the corresponding vehicle operating data is abnormal operating data.

[0108] Furthermore, in one embodiment, the replacement module is also used for:

[0109] Setting the abnormal operation data to a value of 0;

[0110] And fill the non-zero value of vehicle operation data before each zero value to the corresponding zero value.

[0111] Furthermore, in one embodiment, the replacement module is also used for:

[0112] Calculating a first offset between the vehicle operation data at each collection time and the vehicle operation data at a previous collection time, and a second offset between the vehicle operation data at a next collection time;

[0113] If both the first offset and the second offset are greater than a preset maximum offset threshold, determining that the vehicle operation data at the corresponding collection time is abnormal data;

[0114] The vehicle operation data without abnormality before each abnormal data is filled into the corresponding abnormal data.

[0115] Further, in one embodiment, if the vehicle operation data includes mileage data, the maximum offset threshold includes a maximum unit vehicle speed multiplied by a collection time interval;

[0116] If the vehicle operation data includes fuel consumption data, the maximum offset threshold includes the maximum unit fuel consumption multiplied by the collection time interval.

[0117] Furthermore, in one embodiment, the device further includes an extraction module, which is used to:

[0118] The vehicle operation data are sorted according to the collection time, and the vehicle operation data at each collection time are deduplicated.

[0119] Among them, the functional implementation of each module in the above-mentioned vehicle abnormal operation data processing device corresponds to the various steps in the above-mentioned vehicle abnormal operation data processing method embodiment, and its functions and implementation processes are no longer repeated here one by one.

[0120] On the third aspect, an embodiment of the present application provides a device for processing abnormal vehicle operation data, which can output the data to a device with data processing function such as a processing platform server.

[0121] Reference Figure 4 , Figure 4 The hardware structure diagram of the vehicle abnormal operation data processing device involved in the embodiment of the present application is shown in FIG. In the embodiment of the present application, the vehicle abnormal operation data processing device may include a processor, a memory, a communication interface, and a communication bus.

[0122] The communication bus may be of any type and is used to interconnect the processor, the memory, and the communication interface.

[0123] The communication interface includes an input / output (I / O) interface, a physical interface, and a logical interface, etc., which are used to interconnect the devices inside the vehicle abnormal operation data processing device, and an interface used to interconnect the vehicle abnormal operation data processing device with other devices (such as other computing devices or user devices). The physical interface can be an Ethernet interface, an optical fiber interface, an ATM interface, etc.; the user device can be a display, a keyboard, etc.

[0124] The memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.

[0125] The processor may be a general-purpose processor, and the general-purpose processor may call the processing program of the vehicle abnormal operation data stored in the memory, and execute the processing method of the vehicle abnormal operation data provided in the embodiment of the present application. For example, the general-purpose processor may be a central processing unit (CPU). The method executed when the processing program of the vehicle abnormal operation data is called may refer to the various embodiments of the processing method of the vehicle abnormal operation data of the present application, and will not be repeated here.

[0126] Those skilled in the art will understand that Figure 4The hardware structure shown in the figure does not constitute a limitation on the present application, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0127] In a fourth aspect, an embodiment of the present application also provides a computer-readable storage medium.

[0128] The computer-readable storage medium of the present application stores a program for processing abnormal vehicle operation data, wherein when the program for processing abnormal vehicle operation data is executed by a processor, the steps of the method for processing abnormal vehicle operation data as described above are implemented.

[0129] Among them, the method implemented when the vehicle abnormal operation data processing program is executed can refer to the various embodiments of the vehicle abnormal operation data processing method of the present application, and will not be repeated here.

[0130] It should be noted that the serial numbers of the above-mentioned embodiments of the present application are only for description and do not represent the advantages or disadvantages of the embodiments.

[0131] The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices. The terms "first", "second" and "third" are used to distinguish different objects, etc., and do not represent a sequence, nor do they limit "first", "second" and "third" to different types.

[0132] In the description of the embodiments of the present application, "exemplary", "for example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary", "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "for example" or "for example" is intended to present related concepts in a specific way.

[0133] In the description of the embodiments of the present application, unless otherwise specified, “ / ” means or, for example, A / B can mean A or B; the “and / or” in the text is merely a description of the association relationship of associated objects, indicating that three relationships may exist, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, “multiple” refers to two or more than two.

[0134] In some processes described in the embodiments of the present application, multiple operations or steps that appear in a specific order are included, but it should be understood that these operations or steps may not be executed in the order in which they appear in the embodiments of the present application or in parallel, and the sequence number of the operation is only used to distinguish the different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed in sequence or in parallel, and these operations or steps may be combined.

[0135] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, disk, CD) as described above, and includes a number of instructions for a terminal device to execute the methods described in each embodiment of the present application.

[0136] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for processing abnormal vehicle operation data, characterized in that: The method for processing abnormal vehicle operation data includes: Calculating an arithmetic mean and a standard deviation of vehicle operation data within a preset time interval, wherein the vehicle operation data includes mileage data and / or fuel consumption data; Calculating a standard score of the vehicle operation data corresponding to each collection time according to the vehicle operation data at each collection time within the time interval, the arithmetic mean and the standard deviation; Identify whether the corresponding vehicle operation data is abnormal operation data according to each standard score; The abnormal operation data is replaced with vehicle operation data without abnormality.

2. The method for processing abnormal vehicle operation data according to claim 1, characterized in that: The calculating the standard score of the vehicle operation data corresponding to each collection time according to the vehicle operation data at each collection time in the time interval, the arithmetic mean and the standard deviation includes: The arithmetic mean is subtracted from the vehicle operation data at each collection time to obtain a corresponding difference, and the difference is divided by the standard deviation to obtain a standard score of the vehicle operation data corresponding to each collection time.

3. The method for processing abnormal vehicle operation data according to claim 1, characterized in that: The step of identifying whether the corresponding vehicle operation data is abnormal operation data according to each standard score includes: Determining whether the standard score is greater than a preset score threshold; When the standard score is greater than the score threshold, calculating the absolute value of the difference between the corresponding vehicle operation data and the arithmetic mean; If the absolute value of the difference is less than the preset absolute value threshold, it is determined that the corresponding vehicle operation data is normal; If the absolute value of the difference is greater than or equal to the absolute value threshold, it is determined that the corresponding vehicle operating data is abnormal operating data.

4. The method for processing abnormal vehicle operation data according to claim 1, characterized in that: The replacing the abnormal operation data with vehicle operation data without abnormality includes: Setting the abnormal operation data to a value of 0; And fill the non-zero value of vehicle operation data before each zero value to the corresponding zero value.

5. The method for processing abnormal vehicle operation data according to claim 4, characterized in that: After filling the vehicle operation data with a non-zero value before each zero value to the corresponding zero value, the method further includes: Calculating a first offset between the vehicle operation data at each collection time and the vehicle operation data at a previous collection time, and a second offset between the vehicle operation data at a next collection time; If both the first offset and the second offset are greater than a preset maximum offset threshold, determining that the vehicle operation data at the corresponding collection time is abnormal data; The vehicle operation data without abnormality before each abnormal data is filled into the corresponding abnormal data.

6. The method for processing abnormal vehicle operation data according to claim 5, characterized in that: If the vehicle operation data includes mileage data, the maximum offset threshold includes the maximum unit vehicle speed multiplied by the collection time interval; If the vehicle operation data includes fuel consumption data, the maximum offset threshold includes the maximum unit fuel consumption multiplied by the collection time interval.

7. The method for processing abnormal vehicle operation data according to claim 1, characterized in that: Before calculating the arithmetic mean and standard deviation of the vehicle operation data within the preset time interval, it also includes: The vehicle operation data are sorted according to the collection time, and the vehicle operation data at each collection time are deduplicated.

8. A device for processing abnormal vehicle operation data, characterized in that: The vehicle abnormal operation data processing device comprises: A first calculation module, which is used to calculate the arithmetic mean and standard deviation of vehicle operation data within a preset time interval, wherein the vehicle operation data includes mileage data and / or fuel consumption data; A second calculation module, which is used to calculate the standard score of the vehicle operation data corresponding to each collection time according to the vehicle operation data at each collection time in the time interval, the arithmetic mean and the standard deviation; An identification module, which is used to identify whether the corresponding vehicle operation data is abnormal operation data according to each standard score; A replacement module is used to replace the abnormal operation data with vehicle operation data without abnormality.

9. A device for processing abnormal vehicle operation data, characterized in that: The vehicle abnormal operation data processing device includes a processor, a memory, and a vehicle abnormal operation data processing program stored in the memory and executable by the processor, wherein when the vehicle abnormal operation data processing program is executed by the processor, the steps of the vehicle abnormal operation data processing method as described in any one of claims 1 to 7 are implemented.

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

Images