New energy vehicle abnormal state data processing method, device and equipment

Abstract

The invention relates to the technical field of new energy vehicles, in particular to an abnormal state data processing method, device and equipment of a new energy vehicle, and the method comprises the steps: analyzing vehicle state data uploaded by the vehicle to obtain a first timestamp and a current latitude and longitude corresponding to the vehicle state data; and then data screening is performed on the vehicle state data based on the first timestamp and the current longitude and latitude, so that the application processing amount of the cloud server on the vehicle state data is reduced, abnormal group data is eliminated through the trained unsupervised data processing model, the effective data proportion is improved, the data application effect of the vehicle state data is improved, and the vehicle state data processing efficiency is improved. The technical problems that in the prior art, when the vehicle uploads the abnormal state data, the data processing time is long, and the data application effect is poor are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of new energy vehicles, and particularly to a method, device and equipment for processing abnormal state data of new energy vehicles. Background Art

[0002] During the driving process of new energy vehicles, in order to provide good assisted driving functions for the vehicles, it is necessary to ensure long-term and frequent data intercommunication between the vehicles and the cloud server. However, due to the reasons of the vehicle surrounding environment or the vehicle's own equipment, a large amount of invalid data exists in the data uploaded by the vehicle, such as: time disorder, data garbling, etc. After the cloud server receives these data, it increases the data processing time, extends the assisted response process for the vehicle, and reduces the application effect of the vehicle state data.

[0003] The above content is only used to assist in understanding the technical solution of the present invention, and does not represent an admission that the above content is prior art. Summary of the Invention

[0004] The main purpose of the present invention is to provide a method, device and equipment for processing abnormal state data of new energy vehicles, aiming to solve the technical problems of long data processing time and poor data application effect when the vehicle uploads abnormal state data in the prior art.

[0005] To achieve the above purpose, the present invention provides a method for processing abnormal state data of new energy vehicles, the method comprising the following steps:

[0006] Receiving vehicle state data uploaded by a new energy vehicle;

[0007] Parsing the vehicle state data to obtain a first timestamp and the current longitude and latitude of the vehicle state data;

[0008] Filtering the vehicle state data based on the first timestamp and the current longitude and latitude to obtain target vehicle state data;

[0009] Removing abnormal outlier data in the target vehicle state data through a trained unsupervised data processing model to obtain effective vehicle state data.

[0010] Optionally, the parsing the vehicle state data to obtain a first timestamp and the current longitude and latitude of the vehicle state data includes:

[0011] Obtaining the reception time of receiving the vehicle state data, and generating a second timestamp according to the reception time;

[0012] Extracting the data packet header identifier of the vehicle state data;

[0013] Determine the data format and decryption strategy of the vehicle status data according to the data packet header identifier;

[0014] Based on the data format and the decryption strategy, perform data parsing on the vehicle status data to obtain the first timestamp and the current longitude and latitude when the new energy vehicle uploads the vehicle status data;

[0015] Perform timing analysis according to the first timestamp and the second timestamp;

[0016] When the first timestamp is earlier than the second timestamp, output the first timestamp and the current longitude and latitude.

[0017] Optionally, the screening of the vehicle status data based on the first timestamp and the current longitude and latitude to obtain target vehicle status data includes:

[0018] Extract the third timestamp corresponding to the previous vehicle status data and the longitude and latitude of the previous time period;

[0019] Detect the timing relationship between the third timestamp and the first timestamp;

[0020] When the third timestamp is earlier than the first timestamp, calculate the average longitude and latitude of the longitude and latitude of the previous time period;

[0021] Calculate the longitude and latitude difference between the average longitude and latitude and the longitude and latitude of the previous time period;

[0022] Screen the vehicle status data according to the longitude and latitude difference to obtain target vehicle status data.

[0023] Optionally, the abnormal outlier data in the target vehicle status data is removed through a trained unsupervised data processing model to obtain effective vehicle status data, including:

[0024] Construct a historical data cluster sample based on historical vehicle status data, and the historical data cluster sample includes normal status data uploaded by the target vehicle within a historical period;

[0025] Calculate the KNN feature parameters between the target vehicle status data and the historical data cluster sample through a trained unsupervised data processing model;

[0026] Perform outlier analysis on the target vehicle status data based on the KNN feature parameters to obtain abnormal outlier data;

[0027] Remove the abnormal outlier data in the target vehicle status data to obtain effective vehicle status data.

[0028] Optionally, the KNN feature parameters at least include: a truncation distance and a KNN density parameter, where the truncation distance is used to characterize the maximum distance between the target vehicle state parameter and the historical normal state data in the historical data cluster samples;

[0029] Performing outlier analysis on the target vehicle state data based on the KNN feature parameters to obtain abnormal outlier data, including:

[0030] Determining a membership degree parameter of the target vehicle state data with respect to the historical data cluster samples through a preset membership degree statistical model;

[0031] Selecting a plurality of adjacent state data from the historical data cluster samples based on the target vehicle state data;

[0032] Calculating the KNN average density according to the KNN density parameter and the plurality of adjacent state data;

[0033] Calculating a KNN density factor according to the KNN density parameter and the KNN average density;

[0034] Calculating an outlier reference value of the target vehicle state data based on the KNN density factor and the membership degree parameter;

[0035] Screening out abnormal outlier data in the target vehicle state data according to the outlier reference value and a preset outlier filtering threshold.

[0036] Optionally, the method for processing abnormal state data of the new energy vehicle further includes:

[0037] Statistically analyzing the trained unsupervised data processing model, removing abnormal outlier data in the target vehicle state data, and obtaining the data processing duration of the effective vehicle state data;

[0038] Setting the data flow rate of the greedy sampling model according to the data upload period of the target vehicle;

[0039] Correcting the data processing time consumption of the greedy sampling model according to the data processing duration and the data flow rate to obtain a target greedy sampling model;

[0040] Collecting new vehicle state data through the target greedy sampling model, and returning to the step of parsing the vehicle state data to obtain the first timestamp and the current longitude and latitude of the vehicle state data.

[0041] In addition, to achieve the above object, the present invention also proposes an apparatus for processing abnormal state data of a new energy vehicle, where the apparatus for processing abnormal state data of the new energy vehicle includes:

[0042] A receiving module, configured to receive vehicle status data uploaded by a new energy vehicle;

[0043] An analysis module, configured to analyze the vehicle status data to obtain a first timestamp and current longitude and latitude of the vehicle status data;

[0044] A screening module, configured to screen the vehicle status data based on the first timestamp and the current longitude and latitude to obtain target vehicle status data;

[0045] An elimination module, configured to eliminate abnormal outlier data in the target vehicle status data through a trained unsupervised data processing model to obtain valid vehicle status data.

[0046] In addition, to achieve the above object, the present invention further provides an abnormal status data processing device for a new energy vehicle. The abnormal status data processing device for a new energy vehicle includes: a memory, a processor, and an abnormal status data processing program for a new energy vehicle stored on the memory and executable on the processor. The abnormal status data processing program for a new energy vehicle is configured to implement the steps of the abnormal status data processing method for a new energy vehicle as described above.

[0047] In addition, to achieve the above object, the present invention further provides a storage medium. An abnormal status data processing program for a new energy vehicle is stored on the storage medium. When the abnormal status data processing program for a new energy vehicle is executed by a processor, the steps of the abnormal status data processing method for a new energy vehicle as described above are implemented.

[0048] In addition, to achieve the above object, the present application further provides a computer program product. The computer program product includes a computer program. When the computer program is executed by a processor, the steps of the abnormal status data processing method for a new energy vehicle as described above are implemented.

[0049] The present invention discloses a method for processing abnormal state data of a new energy vehicle. The method for processing abnormal state data of the new energy vehicle includes: receiving vehicle state data uploaded by the new energy vehicle; parsing the vehicle state data to obtain the first timestamp and the current longitude and latitude of the vehicle state data; screening the vehicle state data based on the first timestamp and the current longitude and latitude to obtain target vehicle state data; and removing abnormal outlier data from the target vehicle state data through a trained unsupervised data processing model to obtain effective vehicle state data. By parsing the vehicle state data uploaded by the vehicle, the present invention obtains the first timestamp and the current longitude and latitude corresponding to the vehicle state data, and then screens the vehicle state data based on the first timestamp and the current longitude and latitude, reducing the amount of application processing of the vehicle state data by the cloud server. Moreover, by removing abnormal outlier data through the trained unsupervised data processing model, the proportion of effective data is increased, and the data application effect of the vehicle state data is improved, avoiding the technical problems of long data processing time and poor data application effect when the vehicle uploads abnormal state data in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The accompanying drawings are incorporated herein and form a part of this specification, showing embodiments consistent with the present application and, together with the specification, are used to explain the principles of the present application.

[0051] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0052] Figure 1 It is a schematic flowchart of the first embodiment of the method for processing abnormal state data of the new energy vehicle of the present invention;

[0053] Figure 2 It is a schematic flowchart of the second embodiment of the method for processing abnormal state data of the new energy vehicle of the present invention;

[0054] Figure 3 It is a structural block diagram of the first embodiment of the device for processing abnormal state data of the new energy vehicle of the present invention;

[0055] Figure 4 It is a schematic structural diagram of the device for processing abnormal state data of the new energy vehicle in the hardware operating environment related to the solution of the embodiment of the present invention.

[0056] The implementation, functional features and advantages of the objectives of the present invention will be further described in conjunction with the embodiments with reference to the accompanying drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0057] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not used to limit the present application.

[0058] To better understand the technical solutions of the present application, the following will be described in detail in conjunction with the accompanying drawings of the specification and specific implementation manners.

[0059] Based on this, an embodiment of the present invention provides a method for processing abnormal state data of a new energy vehicle. Referring to Figure 1 , Figure 1 is a schematic flowchart of the first embodiment of a method for processing abnormal state data of a new energy vehicle according to the present invention.

[0060] In this embodiment, the method for processing abnormal state data of the new energy vehicle includes:

[0061] Step S10: Receive vehicle state data uploaded by the new energy vehicle.

[0062] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication, and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device, a cloud server, etc. that can implement the above functions. Hereinafter, the cloud server will be taken as an example to illustrate this embodiment and the following embodiments.

[0063] In this embodiment, the vehicle state data at least includes: vehicle longitude and latitude, vehicle speed, battery power, driving state, electronic component operation state, etc. information. And in order to improve the efficiency of vehicle data upload, the vehicle state data in this embodiment is generally uploaded to the cloud server in the form of a packaged message. During the packaging process, the data upload time will be added to the message to facilitate abnormal data analysis and improve data utilization.

[0064] Step S20: Parse the vehicle state data to obtain the first timestamp and the current longitude and latitude of the vehicle state data.

[0065] It can be understood that the process of parsing the vehicle state data can be operations such as unpacking and decrypting the message data uploaded by the vehicle to obtain the string recorded in the message, so as to obtain the first timestamp representing the data upload time and the longitude and latitude of the vehicle when uploading the data.

[0066] In a specific implementation, both the first timestamp and the longitude and latitude are used to determine whether there is a time sequence disorder or a positioning disorder in the data uploaded by the vehicle, which will affect the service functions such as navigation, weather, and entertainment provided by the cloud server to the vehicle and reduce the user experience.

[0067] Furthermore, the parsing the vehicle state data to obtain the first timestamp and the current longitude and latitude of the vehicle state data includes:

[0068] Obtain the reception time when the vehicle status data is received, and generate a second timestamp based on the reception time;

[0069] Extract the data packet header identifier of the vehicle status data;

[0070] Determine the data format and decryption strategy of the vehicle status data according to the data packet header identifier;

[0071] Based on the data format and the decryption strategy, perform data parsing on the vehicle status data to obtain the first timestamp and the current longitude and latitude when the new energy vehicle uploads the vehicle status data;

[0072] Perform timing analysis according to the first timestamp and the second timestamp;

[0073] When the first timestamp is earlier than the second timestamp, output the first timestamp and the current longitude and latitude.

[0074] In a specific implementation, due to the process of vehicle data uploading, data transmission takes a certain amount of time. Therefore, theoretically, the reception time when the cloud server receives the vehicle status data should be slightly later than the time when the vehicle status data is uploaded and encapsulated. Therefore, in this embodiment, timing analysis is performed on the first timestamp of data uploading and the second timestamp when the cloud server receives the vehicle status data, so as to determine whether there is a time disorder situation, and thus determine whether the data is abnormal data.

[0075] In this embodiment, if the first timestamp of data uploading is earlier than the second timestamp when the cloud server receives the vehicle status data, it means that the data timing is normal. However, since data encapsulation and encryption are used during data uploading, in order to obtain the accurate first timestamp and the current longitude and latitude, this embodiment can extract the data packet header identifier of the vehicle status data, determine the data format and decryption strategy of the vehicle status data according to the data packet header identifier, and finally perform data unpacking and decryption on the vehicle status data based on the data format and the decryption strategy to obtain the first timestamp and the current longitude and latitude when the new energy vehicle uploads the vehicle status data.

[0076] Step S30: Screen the vehicle status data based on the first timestamp and the current longitude and latitude to obtain target vehicle status data.

[0077] In this embodiment, the process of screening the vehicle status data refers to comparing the position and timing of the vehicle status data based on the first timestamp and the vehicle status data cached in the cloud server history, so as to screen out abnormal data in the two dimensions of position and timing, and reduce the amount of ineffective processing in subsequent data processing.

[0078] Further, screening the vehicle status data based on the first timestamp and the current longitude and latitude to obtain target vehicle status data includes:

[0079] Extracting the third timestamp corresponding to the previous vehicle status data and the longitude and latitude of the previous time period;

[0080] Detecting the timing relationship between the third timestamp and the first timestamp;

[0081] When the third timestamp is earlier than the first timestamp, calculating the average longitude and latitude of the longitude and latitude of the previous time period;

[0082] Calculating the longitude and latitude difference between the average longitude and latitude and the longitude and latitude of the previous time period;

[0083] Screening the vehicle status data according to the longitude and latitude difference to obtain target vehicle status data.

[0084] In a specific implementation, the previous vehicle status data refers to the normal vehicle status data cached last time within the historical acquisition period. The third timestamp is the upload time when the vehicle uploads the previous vehicle status data. The longitude and latitude of the previous time period refers to multiple longitude and latitude data of the vehicle within the previous acquisition period. To improve the accuracy of vehicle longitude and latitude positioning, in this embodiment, instead of directly using the previous longitude and latitude corresponding to the previous vehicle status data, the average longitude and latitude within the historical time period is calculated to estimate the driving state of the vehicle, so as to determine whether there is an abnormal change in the position of the vehicle when the currently received vehicle status data is obtained.

[0085] In a specific implementation, screening the vehicle status data according to the longitude and latitude difference specifically includes: obtaining the vehicle status data of the previous time period, and performing power consumption analysis on the target vehicle according to the vehicle status data of the previous time period to obtain the historical power consumption and power consumption value of the target vehicle in the previous time period; performing reliability evaluation on the longitude and latitude difference according to the historical power consumption and the power consumption value; when the reliability evaluation passes, obtaining the target vehicle status data; when the reliability evaluation fails, rejecting the vehicle status data.

[0086] Specifically, there is a certain mapping relationship between the power consumption data and the power consumption value of the vehicle within the historical period and the driving mileage of the vehicle within the historical period, and since the battery health does not change significantly in a short period of time, therefore, in this embodiment, through the power consumption value and the power consumption data of the vehicle within the historical period, it is judged whether the longitude and latitude difference between the currently received longitude and latitude and the previous longitude and latitude conforms to the power consumption range, so as to improve the reliability of the vehicle driving mileage and the reliability of the vehicle status data.

[0087] Step S40: Eliminate the abnormal outlier data in the target vehicle status data through the trained unsupervised data processing model to obtain the effective vehicle status data.

[0088] In this embodiment, the trained unsupervised data processing model uses a data processing model based on the fuzzy clustering algorithm. Since the data transmission between the vehicle and the cloud server generally uses periodic interconnection, but in some special cases, the vehicle will also actively upload status data in multiple dimensions. Due to factors such as aging of the network transmission medium, equipment failure, environmental changes, and human operation errors, there will inevitably be outliers in the data stream, which will inevitably have a negative impact on the performance of clustering analysis.

[0089] Based on this, in this embodiment, clustering analysis is performed on the received target vehicle status data in combination with the historical vehicle status data, so as to eliminate the abnormal outlier data in some dimensions of the target vehicle status data and obtain the effective vehicle status data.

[0090] In this embodiment, by analyzing the vehicle status data uploaded by the vehicle, the first timestamp and the current longitude and latitude corresponding to the vehicle status data are obtained. Then, based on the first timestamp and the current longitude and latitude, data screening is performed on the vehicle status data, reducing the amount of application processing of the vehicle status data by the cloud server. And the abnormal outlier data is eliminated through the trained unsupervised data processing model, improving the proportion of effective data and the data application effect of the vehicle status data, and avoiding the technical problems of long data processing time and poor data application effect when the vehicle uploads abnormal status data in the prior art.

[0091] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar content as in the above-mentioned first embodiment can be referred to the above introduction and will not be repeated hereinafter. On this basis, please refer to Figure 2 , step S40, includes:

[0092] Step S401: Construct a historical data cluster sample based on the historical vehicle status data, and the historical data cluster sample includes the normal status data uploaded by the target vehicle within the historical period.

[0093] Step S402: Calculate the KNN feature parameters between the target vehicle status data and the historical data cluster sample through the trained unsupervised data processing model.

[0094] Step S403: Perform outlier analysis on the target vehicle status data based on the KNN feature parameters to obtain the abnormal outlier data.

[0095] Step S404: Eliminate the abnormal outlier data in the target vehicle status data to obtain the effective vehicle status data.

[0096] It should be noted that the characteristic parameters of the K-Nearest Neighbors (KNN) algorithm at least include: the truncation distance and the KNN density parameter. The truncation distance is used to characterize the maximum distance between the target vehicle state parameters and the historical normal state data in the historical data cluster samples; the KNN density parameter is used to characterize the local spatial information of the historical data cluster samples.

[0097] In a specific implementation, the calculation formulas for the truncation distance and the KNN density parameter between the target vehicle state data and the historical data cluster samples are as follows:

[0098] ε = max(D(x i , KNN(x i , k)))

[0099]

[0100] where ε is the truncation distance, k is the number of characteristic samples in each dimension of the historical data cluster samples, xi is the characteristic dimension data of the target vehicle state data, and D(x i , KNN(x i , k)) can adopt at least one of the Euclidean distance, Manhattan distance, and Minkowski distance in this embodiment, and this embodiment does not make specific limitations on this.

[0101] Taking the Manhattan distance as an example of the truncation distance:

[0102]

[0103] where k is the number of characteristic samples in each dimension of the historical data cluster samples, and xi is the characteristic dimension data of the target vehicle state data.

[0104] Furthermore, performing outlier analysis on the target vehicle state data based on the KNN characteristic parameters to obtain abnormal outlier data includes:

[0105] Determining the membership degree parameter of the target vehicle state data compared to the historical data cluster samples through a preset membership degree statistical model;

[0106] Selecting multiple adjacent state data from the historical data cluster samples based on the target vehicle state data;

[0107] Calculating the KNN average density according to the KNN density parameter and the multiple adjacent state data;

[0108] Calculating the KNN density factor according to the KNN density parameter and the KNN average density;

[0109] Calculate the outlier reference value of the target vehicle state data based on the KNN density factor and the membership parameter;

[0110] Filter out the abnormal outlier data in the target vehicle state data according to the outlier reference value and the preset outlier filtering threshold.

[0111] It should be noted that when dividing the similarity of the feature data clusters of each dimension in the target vehicle state data and the historical data clusters, if there are abnormal data in the target vehicle state data, there must be a dimension of data with a low membership degree to the data clusters of each dimension in the historical data clusters. However, for normal data, there must be a dimension of data with a low membership degree to a certain dimension data cluster in the historical data clusters, but a high membership degree to another dimension data cluster in the historical data clusters. In this case, to avoid misjudgment, in this embodiment, the membership values are sorted in descending order, and the difference between the two largest values is used as the division of suspected outliers.

[0112] Since the membership degree can only reflect the membership relationship and cannot reflect the local spatial information, in order to reduce the number of redundant suspected outliers and improve the distinguishability between clustering members and outliers, in this embodiment, the KNN density factor is also added to improve the screening accuracy of abnormal data. The corresponding calculation formula of the KNN density factor is:

[0113]

[0114] Among them, ρ i,j is the KNN average density, θ is the KNN density factor, k is the number of selected adjacent state data of each dimension of the feature samples in the historical data cluster samples, KNND(x i , k) is the KNN density parameter, and Nj is the total number of target vehicle state data participating in the calculation.

[0115] Furthermore, in order to improve the data processing efficiency of the vehicle state data, the abnormal state data processing method of the new energy vehicle further includes:

[0116] Statistically calculate the trained unsupervised data processing model, eliminate the abnormal outlier data in the target vehicle state data, and obtain the data processing duration of the effective vehicle state data;

[0117] Set the data flow rate of the greedy sampling model according to the data upload period of the target vehicle;

[0118] Correct the data processing time consumption of the greedy sampling model according to the data processing duration and the data flow rate to obtain the target greedy sampling model;

[0119] New vehicle status data is collected through a target greedy sampling model, and the step of parsing the vehicle status data to obtain a first timestamp and current longitude and latitude of the vehicle status data is returned.

[0120] In the specific implementation, in order to improve the processing efficiency of the cloud server for abnormal outlier data, this embodiment also sets a greedy sampling model in the cloud server, and sets the data flow of the greedy sampling model based on the data upload period of the target vehicle, as well as the data processing time for historical processing of abnormal outlier data, and adjusts the collection of new vehicle status data. In this way, when a vehicle uploads abnormal data, the vehicle status data can be actively re-collected in time to avoid data loss caused by periodic uploads of the vehicle, thereby affecting the various functional services provided by the cloud server.

[0121] This embodiment constructs a historical data cluster sample based on historical vehicle status data, wherein the historical data cluster sample includes normal status data uploaded by the target vehicle within a historical period; calculates the KNN feature parameters between the target vehicle status data and the historical data cluster sample through a trained unsupervised data processing model; performs outlier analysis on the target vehicle status data based on the KNN feature parameters to obtain abnormal outlier data; eliminates abnormal outlier data in the target vehicle status data to obtain valid vehicle status data, and analyzes the sample differences between the historical vehicle status data and the target vehicle status data from features of multiple dimensions through clustering to improve the recognition rate of abnormal outlier data.

[0122] This application also provides an abnormal state data processing device for new energy vehicles, please refer to Figure 3 , the abnormal state data processing device of the new energy vehicle comprises:

[0123] The receiving module 10 is used to receive vehicle status data uploaded by the new energy vehicle.

[0124] The parsing module 20 is used to parse the vehicle status data to obtain a first timestamp and current longitude and latitude of the vehicle status data.

[0125] The screening module 30 is used to screen the vehicle status data based on the first timestamp and the current longitude and latitude to obtain target vehicle status data.

[0126] The elimination module 40 is used to eliminate abnormal outlier data in the target vehicle status data through a trained unsupervised data processing model to obtain valid vehicle status data.

[0127] In this embodiment, the vehicle status data uploaded by the vehicle is parsed to obtain the first timestamp and the current longitude and latitude corresponding to the vehicle status data. Then, based on the first timestamp and the current longitude and latitude, the vehicle status data is screened to reduce the amount of application processing of the vehicle status data by the cloud server. Moreover, the trained unsupervised data processing model is used to eliminate abnormal data, improve the proportion of valid data, enhance the data application effect of the vehicle status data, and avoid the technical problems of long data processing time and poor data application effect when the vehicle uploads abnormal status data in the prior art.

[0128] In one embodiment, the parsing module 20 is further configured to obtain the reception time when the vehicle status data is received, and generate a second timestamp according to the reception time; extract the data packet header identifier of the vehicle status data; determine the data format and decryption strategy of the vehicle status data according to the data packet header identifier; perform data parsing on the vehicle status data based on the data format and the decryption strategy to obtain the first timestamp and the current longitude and latitude when the new energy vehicle uploads the vehicle status data; perform time series analysis according to the first timestamp and the second timestamp; and output the first timestamp and the current longitude and latitude when the first timestamp is earlier than the second timestamp.

[0129] In one embodiment, the screening module 30 is further configured to extract the third timestamp and the longitude and latitude of the previous time period corresponding to the previous vehicle status data; detect the time series relationship between the third timestamp and the first timestamp; when the third timestamp is earlier than the first timestamp, calculate the average value of the longitude and latitude of the previous time period; calculate the longitude and latitude difference between the average value of the longitude and latitude and the longitude and latitude of the previous time period; and screen the vehicle status data according to the longitude and latitude difference to obtain the target vehicle status data.

[0130] In one embodiment, the eliminating module 40 is further configured to construct a historical data cluster sample based on the historical vehicle status data, where the historical data cluster sample includes the normal status data uploaded by the target vehicle within a historical period; calculate the KNN feature parameter between the target vehicle status data and the historical data cluster sample through the trained unsupervised data processing model; perform outlier analysis on the target vehicle status data based on the KNN feature parameter to obtain abnormal outlier data; and eliminate the abnormal outlier data in the target vehicle status data to obtain valid vehicle status data.

[0131] In one embodiment, the rejection module 40 is further configured to determine a membership parameter of the target vehicle state data with respect to the historical data cluster samples through a preset membership degree statistical model; select a plurality of adjacent state data from the historical data cluster samples based on the target vehicle state data; calculate the KNN average density according to the KNN density parameter and the plurality of adjacent state data; calculate a KNN density factor according to the KNN density parameter and the KNN average density; calculate an outlier reference value of the target vehicle state data based on the KNN density factor and the membership parameter; and screen out abnormal outlier data in the target vehicle state data according to the outlier reference value and a preset outlier filtering threshold.

[0132] In one embodiment, the rejection module 40 is further configured to count the data processing duration of the trained unsupervised data processing model, reject abnormal outlier data in the target vehicle state data to obtain effective vehicle state data; set the data flow rate of the greedy sampling model according to the data upload period of the target vehicle; correct the data processing time consumption of the greedy sampling model according to the data processing duration to obtain a target greedy sampling model; collect new vehicle state data through the target greedy sampling model, and return to the step of parsing the vehicle state data to obtain the first timestamp and the current longitude and latitude of the vehicle state data.

[0133] The present application provides an abnormal state data processing device for a new energy vehicle. The abnormal state data processing device for a new energy vehicle includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the abnormal state data processing method for a new energy vehicle in the first embodiment above.

[0134] The following refers to Figure 4 , which shows a schematic structural diagram of an abnormal state data processing device for a new energy vehicle suitable for implementing the embodiments of the present application. The abnormal state data processing device for a new energy vehicle in the embodiments of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), in-vehicle terminals (such as in-vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 4The abnormal state data processing device of the new energy vehicle shown is merely an example and should not impose any limitation on the functions and scope of use of the embodiments of the present application.

[0135] As Figure 4 shown, the abnormal state data processing device of the new energy vehicle may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM: Read Only Memory) 1002 or the program loaded from the storage device 1003 into the random access memory (RAM: Random Access Memory) 1004. In the RAM 1004, various programs and data required for the operation of the abnormal state data processing device of the new energy vehicle are also stored. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other through a bus 1005. The input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems may be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the abnormal state data processing device of the new energy vehicle to communicate with other devices wirelessly or wiredly to exchange data. Although the figure shows the abnormal state data processing device of the new energy vehicle with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or had alternatively.

[0136] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program codes for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device, or installed from the storage device 1003, or installed from the ROM 1002. When the computer program is executed by the processing device 1001, the above functions defined in the method of the embodiments disclosed in the present application are executed.

[0137] The abnormal state data processing device for new energy vehicles provided by this application adopts the abnormal state data processing method for new energy vehicles in the above-mentioned embodiments, and can solve the technical problem of abnormal state data processing for new energy vehicles. Compared with the prior art, the beneficial effects of the abnormal state data processing device for new energy vehicles provided by this application are the same as those of the abnormal state data processing method for new energy vehicles provided by the above-mentioned embodiments, and other technical features in the abnormal state data processing device for new energy vehicles are the same as those disclosed in the method of the previous embodiment, which will not be elaborated here.

[0138] It should be understood that each part disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in a suitable manner in any one or more embodiments or examples.

[0139] The above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed in this application can easily think of changes or substitutions, which should all be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

[0140] This application provides a computer-readable storage medium with computer-readable program instructions (i.e., computer programs) stored thereon, and the computer-readable program instructions are used to execute the abnormal state data processing method for new energy vehicles in the above-mentioned embodiments.

[0141] The computer-readable storage medium provided by the present application can be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or components, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM) or flash memory, optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this embodiment, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device, or component. The program code contained on the computer-readable storage medium can be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0142] The above computer-readable storage medium can be included in the abnormal state data processing device of a new energy vehicle; it can also exist independently without being assembled into the abnormal state data processing device of a new energy vehicle.

[0143] The above computer-readable storage medium carries one or more programs. When the one or more programs are executed by the abnormal state data processing device of a new energy vehicle, the abnormal state data processing device of the new energy vehicle performs abnormal state data processing of the new energy vehicle.

[0144] Computer program code for performing the operations of this application can be written in one or more programming languages or combinations thereof. The above-mentioned programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, by using an Internet service provider to connect through the Internet).

[0145] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of the code, and this module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order from that marked in the accompanying drawings. For example, two consecutively represented blocks may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, as well as the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0146] The modules described in the embodiments of this application can be implemented in software or in hardware. Among them, the name of the module does not constitute a limitation on the unit itself in some cases.

[0147] The readable storage medium provided in this application is a computer-readable storage medium, and the computer-readable storage medium stores computer-readable program instructions (i.e., computer programs) for performing the above-mentioned abnormal state data processing method of new energy vehicles, which can solve the technical problem of abnormal state data processing of new energy vehicles. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the abnormal state data processing method of new energy vehicles provided in the above embodiments, and will not be elaborated here.

[0148] The present application also provides a computer program product, including a computer program which, when executed by a processor, implements the steps of the method for processing abnormal state data of a new energy vehicle as described above.

[0149] The computer program product provided by the present application can solve the technical problem of processing abnormal state data of a new energy vehicle. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as those of the method for processing abnormal state data of a new energy vehicle provided in the above embodiments, and will not be elaborated herein.

[0150] The above are only partial embodiments of the present application, and thus do not limit the patent scope of the present application. Any equivalent structural transformation made under the technical concept of the present application by using the content of the specification and drawings of the present application, or any direct / indirect application in other related technical fields, is included in the patent protection scope of the present application.

Claims

1. A method for processing abnormal state data of a new energy vehicle, characterized in that: The abnormal state data processing method of the new energy vehicle includes: Receive vehicle status data uploaded by new energy vehicles; Parsing the vehicle status data to obtain a first timestamp and current longitude and latitude of the vehicle status data; Filter the vehicle status data based on the first timestamp and the current longitude and latitude to obtain target vehicle status data; By using the trained unsupervised data processing model, abnormal outlier data in the target vehicle status data is eliminated to obtain valid vehicle status data.

2. The abnormal state data processing method of a new energy vehicle according to claim 1, characterized in that: The step of parsing the vehicle status data to obtain a first timestamp and a current longitude and latitude of the vehicle status data includes: Acquire a receiving time of the vehicle status data, and generate a second timestamp according to the receiving time; Extracting a data message header identifier of the vehicle status data; Determine the data format and decryption strategy of the vehicle status data according to the data message header identifier; Parsing the vehicle status data based on the data format and the decryption strategy to obtain a first timestamp and a current longitude and latitude of the new energy vehicle uploading the vehicle status data; Performing timing analysis according to the first timestamp and the second timestamp; When the first timestamp is earlier than the second timestamp, the first timestamp and the current longitude and latitude are output.

3. The abnormal state data processing method of a new energy vehicle according to claim 1, characterized in that: The filtering the vehicle status data based on the first timestamp and the current longitude and latitude to obtain target vehicle status data includes: Extract the third timestamp corresponding to the last vehicle status data and the latitude and longitude of the last period; Detecting a timing relationship between the third timestamp and the first timestamp; When the third timestamp is earlier than the first timestamp, calculating the average longitude and latitude of the previous time period; Calculate the longitude and latitude difference between the longitude and latitude average and the longitude and latitude of the previous period; The vehicle status data is screened according to the longitude and latitude difference to obtain target vehicle status data.

4. The abnormal state data processing method of a new energy vehicle according to claim 1, characterized in that: The trained unsupervised data processing model is used to remove abnormal outlier data in the target vehicle status data to obtain valid vehicle status data, including: Constructing a historical data cluster sample based on historical vehicle status data, wherein the historical data cluster sample includes normal status data uploaded by the target vehicle in a historical period; Calculate the KNN feature parameters between the target vehicle state data and the historical data cluster samples through the trained unsupervised data processing model; Performing outlier analysis on the target vehicle state data based on the KNN feature parameters to obtain abnormal outlier data; Abnormal outlier data in the target vehicle status data is eliminated to obtain valid vehicle status data.

5. The abnormal state data processing method of a new energy vehicle according to claim 4, characterized in that: The KNN characteristic parameters include at least: a cutoff distance and a KNN density parameter, wherein the cutoff distance is used to characterize the maximum distance between the target vehicle state parameter and the historical normal state data in the historical data cluster sample; The performing outlier analysis on the target vehicle state data based on the KNN feature parameters to obtain abnormal outlier data includes: Determining the membership parameter of the target vehicle state data compared to the historical data cluster sample by a preset membership statistical model; Selecting a plurality of adjacent state data from the historical data cluster samples based on the target vehicle state data; Calculate the KNN average density according to the KNN density parameter and the plurality of adjacent state data; Calculate a KNN density factor according to the KNN density parameter and the KNN average density; Calculating an outlier reference value of the target vehicle state data based on the KNN density factor and the membership parameter; The abnormal outlier data in the target vehicle state data is filtered out according to the outlier reference value and a preset outlier filtering threshold.

6. The abnormal state data processing method of a new energy vehicle according to claim 4, characterized in that: The abnormal state data processing method of the new energy vehicle further includes: Counting the trained unsupervised data processing model, eliminating abnormal outlier data in the target vehicle status data, and obtaining the data processing time of the valid vehicle status data; Setting the data flow rate of the greedy sampling model according to the data upload period of the target vehicle; Correct the data processing time consumption of the greedy sampling model according to the data processing time and the data flow rate to obtain a target greedy sampling model; New vehicle status data is collected through a target greedy sampling model, and the step of parsing the vehicle status data to obtain a first timestamp and current longitude and latitude of the vehicle status data is returned.

7. An abnormal state data processing device for new energy vehicles, characterized in that: The abnormal state data processing device of the new energy vehicle comprises: A receiving module, used to receive vehicle status data uploaded by new energy vehicles; A parsing module, used for parsing the vehicle status data to obtain a first timestamp and a current longitude and latitude of the vehicle status data; A screening module, configured to screen the vehicle status data based on the first timestamp and the current longitude and latitude to obtain target vehicle status data; The elimination module is used to eliminate abnormal outlier data in the target vehicle status data through a trained unsupervised data processing model to obtain valid vehicle status data.

8. An abnormal state data processing device for new energy vehicles, characterized in that: The abnormal state data processing device of the new energy vehicle includes: a memory, a processor, and an abnormal state data processing program of the new energy vehicle stored in the memory and executable on the processor, wherein the abnormal state data processing program of the new energy vehicle is configured to implement the abnormal state data processing method of the new energy vehicle as described in any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium stores an abnormal state data processing program for a new energy vehicle, and when the abnormal state data processing program for a new energy vehicle is executed by a processor, the abnormal state data processing method for a new energy vehicle as described in any one of claims 1 to 6 is implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the abnormal state data processing method for a new energy vehicle as claimed in any one of claims 1 to 6 are implemented.

Images