Processing method and device for vehicle uploaded data

Abstract

The invention discloses a processing method and device for vehicle uploaded data, and relates to the technical field of data processing. The method comprises the following steps: acquiring historical data uploaded by a vehicle; determining a time correction factor according to the time characteristics of the delay time of the historical data at different times; performing clustering analysis on the historical data according to the vehicle characteristic indexes, and determining a target delay factor; integrating the time correction factor and the target delay factor, and determining corresponding delay time thresholds under different time characteristics and different vehicle characteristic indexes; calling a target delay time threshold matched with a time feature and a vehicle feature index corresponding to the current vehicle uploading data according to the received current vehicle uploading data; and according to the delay time of the data uploaded by the current vehicle and the target delay time threshold, analyzing whether the data uploaded by the current vehicle belongs to abnormal data, and processing the abnormal data. According to the embodiment, efficient and accurate abnormal data identification can be realized.

Description

Technical Field

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

[0002] To ensure vehicle safety, some vehicle-side data needs to be uploaded to the car company's cloud at regular intervals. However, the data upload process is affected by factors such as the vehicle's surrounding environment and the network environment, which can result in abnormal data being uploaded to the cloud (such as data that was not uploaded successfully in time, reissued data that was subsequently re-uploaded, or delayed data whose upload time exceeds the normal upload time). Currently, the method of distinguishing these abnormal data (reissued data and delayed data) from normal data generally uses a fixed time threshold judgment. For example, a fixed time threshold such as 3 days is determined, and data with an upload time greater than 3 days is regarded as abnormal data. This method relies on empirical data, but due to the influence of various factors, the upload time of reissued data and delayed data does not have a fixed distribution feature, resulting in this method of using a fixed time threshold to distinguish whether it is abnormal data. The method has the problem of low accuracy. Therefore, how to accurately identify abnormal data has become an urgent problem to be solved. Summary of the Invention

[0003] In view of this, an embodiment of the present invention provides a method and device for processing vehicle uploaded data, which can realize efficient and accurate identification of abnormal data.

[0004] To achieve the above object, according to one aspect of an embodiment of the present invention, a method for processing vehicle uploaded data is provided, comprising:

[0005] Get historical data uploaded by vehicles;

[0006] Determine a time correction factor based on the time characteristics of the delay time of the above historical data at different times;

[0007] Perform cluster analysis on the above historical data based on vehicle characteristic indicators to determine the target delay factor;

[0008] Combining the above time correction factor and the above target delay factor, determining the corresponding delay time threshold under different time characteristics and different vehicle characteristic indicators;

[0009] For the received current vehicle uploaded data, determining a time feature and a vehicle characteristic index corresponding to the current vehicle uploaded data, and calling a target delay time threshold that matches the time feature and the vehicle characteristic index corresponding to the current vehicle uploaded data;

[0010] According to the delay time of the data uploaded by the current vehicle and the target delay time threshold, it is analyzed whether the data uploaded by the current vehicle is abnormal data, and the abnormal data is processed.

[0011] Optionally, performing cluster analysis on the historical data according to vehicle characteristic indicators to determine the target delay factor includes:

[0012] Extract features of the historical delay time of historical data based on vehicle characteristic indicators and generate several feature vectors;

[0013] Clustering several of the above-mentioned feature vectors to obtain several clusters;

[0014] Calculating the median and median absolute deviation of the corresponding historical delay time for each of the above clusters, and setting a preset second quantile corresponding to each of the above clusters;

[0015] The target delay factor is determined according to the median and median absolute deviation corresponding to each of the clusters and the delay time corresponding to the preset second quantile.

[0016] Optionally, the above-mentioned time correction factor and the above-mentioned target delay factor are combined to determine the delay time threshold corresponding to different time characteristics and different vehicle characteristic indicators, including:

[0017] For each of the clusters, construct a first calculation relationship between the delay time threshold and the median corresponding to the cluster, the absolute deviation of the median corresponding to the cluster, the time correction factor, and the target delay factor;

[0018] Based on the first calculation relationship corresponding to each of the above clusters, the delay time thresholds corresponding to different time characteristics and different vehicle characteristic indicators are calculated.

[0019] Optionally, the analyzing whether the current vehicle uploaded data is abnormal data includes:

[0020] In response to the delay time of the data uploaded by the current vehicle being greater than the target delay time threshold, determining that the data uploaded by the current vehicle is abnormal data;

[0021] In response to the delay time of the current vehicle uploading data being less than or equal to the target delay time threshold, it is determined that the current vehicle uploading data is not abnormal data.

[0022] Optionally, the above method further includes:

[0023] In response to a preset time period elapsing or the amount of updated data reaching a preset data amount threshold, performing cluster analysis on the updated data according to vehicle characteristic indicators;

[0024] According to the clustering results, the updated data is assigned a cluster, and the median and median absolute deviation corresponding to each cluster are updated using the delay time of the updated data, and the target delay factor is tuned;

[0025] The above time correction factor and the tuned target delay factor are combined to re-determine the corresponding delay time threshold under different time characteristics and different vehicle characteristic indicators.

[0026] Optionally, the step of assigning a cluster to the updated data according to the clustering result includes:

[0027] Generate new clusters for the above updated data;

[0028] In the case where the vehicle characteristic index indicated by the new cluster is the same as the vehicle characteristic index indicated by the existing cluster, merging the new cluster into the existing cluster;

[0029] In the case that the vehicle characteristic index indicated by the new cluster is different from the vehicle characteristic index indicated by each existing cluster, the new cluster is added.

[0030] Optionally, the method further includes: setting a decay factor; the decay factor indicates that the delay time of the updated data of the cluster has a higher weight than the delay time of the historical data of the cluster;

[0031] The updating of the median and the median absolute deviation corresponding to each of the clusters includes: updating the median and the median absolute deviation corresponding to each of the clusters according to the attenuation factor and the delay time of the update data.

[0032] To achieve the above object, according to another aspect of an embodiment of the present invention, a device for processing vehicle uploaded data is provided, comprising:

[0033] Acquisition module, used to obtain historical data uploaded by vehicles;

[0034] A first determining module is used to determine a time correction factor according to time characteristics of the delay time of the historical data at different times;

[0035] A second determination module is used to perform cluster analysis on the historical data according to vehicle characteristic indicators to determine a target delay factor;

[0036] A third determination module is configured to combine the time correction factor and the target delay factor to determine a delay time threshold corresponding to different time characteristics and different vehicle characteristic indicators;

[0037] a calling module, configured to determine, for the received current vehicle uploaded data, a time feature and a vehicle characteristic index corresponding to the current vehicle uploaded data, and call a target delay time threshold that matches the time feature and vehicle characteristic index corresponding to the current vehicle uploaded data;

[0038] The processing module is used to analyze whether the data uploaded by the current vehicle is abnormal data according to the delay time of the data uploaded by the current vehicle and the target delay time threshold, and process the abnormal data.

[0039] To achieve the above-mentioned purpose, according to another aspect of an embodiment of the present invention, an electronic device for processing vehicle-uploaded data is provided, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement a method for processing vehicle-uploaded data according to an embodiment of the present invention.

[0040] To achieve the above objective, according to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided.

[0041] A computer-readable storage medium according to an embodiment of the present invention stores a computer program, which, when executed by a processor, implements a method for processing vehicle-uploaded data according to an embodiment of the present invention.

[0042] An embodiment of the above invention has the following advantages or beneficial effects: by determining the time correction factor based on the time characteristics of the delay time of historical data at different times, clustering analysis of historical data according to vehicle characteristic indicators to determine the target delay factor, and comprehensively combining the time correction factor and the above target delay factor to determine the corresponding delay time threshold under different time characteristics and different vehicle characteristic indicators, objectively and comprehensively considering the impact of time characteristics and vehicle characteristic indicators on the delay time of vehicle uploading data, by setting the time correction factor and the target delay factor, the delay time threshold corresponding to historical data under different time characteristics and different vehicle characteristic indicators can be determined more accurately.

[0043] Determine the time characteristics and vehicle characteristic indicators corresponding to the current vehicle uploaded data, call the matching target delay time threshold, determine whether the current vehicle uploaded data is abnormal data, and process the abnormal data if it is abnormal data, achieving efficient and accurate abnormal data identification, and can provide comprehensive and accurate reference data for vehicle remote diagnosis, data analysis and decision-making, network optimization and data cleaning.

[0044] By dynamically updating the delay time threshold, the delay time threshold can be updated according to the changing vehicle characteristic indicators, etc., thereby further ensuring the accuracy of the delay time threshold and improving the effectiveness of abnormal data judgment using the delay time threshold.

[0045] The further effects of the above-mentioned non-conventional optional manner will be described below in conjunction with specific embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The accompanying drawings are provided for a better understanding of the present invention and are not intended to limit the present invention.

[0047] Figure 1 is a flowchart of a method for processing vehicle uploaded data according to an embodiment of the present invention;

[0048] Figure 2 is a schematic diagram of a process for determining a target delay factor according to an embodiment of the present invention;

[0049] Figure 3 is a flowchart of a method for processing vehicle uploaded data according to another embodiment of the present invention;

[0050] Figure 4 is a schematic diagram of main modules of a device for processing vehicle uploaded data according to an embodiment of the present invention;

[0051] Figure 5 is an exemplary system architecture diagram in which embodiments of the present invention may be applied;

[0052] Figure 6 It is a structural diagram of a computer system of an automobile enterprise server suitable for implementing an embodiment of the present invention. DETAILED DESCRIPTION

[0053] The following description of exemplary embodiments of the present invention is made in conjunction with the accompanying drawings, in which various details of the embodiments of the present invention are included to facilitate understanding. These details should be considered as merely exemplary. Therefore, it should be appreciated by those skilled in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0054] It should be pointed out that, in the absence of conflict, the embodiments of the present invention and the technical features therein may be combined with each other.

[0055] It should be noted that the collection, collection, updating, analysis, processing, use, transmission, and storage of user personal information involved in the technical solutions disclosed herein all comply with relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. Necessary measures are taken with respect to user personal information to prevent unauthorized access to user personal information data and to safeguard the security of user personal information, network security, and national security.

[0056] Figure 1 FIG. 1 is a schematic diagram of the main steps of a method for processing vehicle uploaded data according to an embodiment of the present invention. Figure 1 As shown, the method for processing vehicle uploaded data according to the embodiment of the present invention mainly includes the following steps S101 to S106:

[0057] Step S101, obtaining historical data uploaded by the vehicle;

[0058] Whenever the cloud receives vehicle upload data, it can save it in the database for future use. Vehicle upload data that has been received, processed, and stored in the database is considered historical data. The processing time range for the historical data to be retrieved is pre-set to retrieve the corresponding historical data from the database. For example, if the processing time range is set to January 1, 2024, to December 31, 2024, the corresponding historical data will be retrieved from the database.

[0059] Step S102, determining a time correction factor based on the time characteristics of the delay time of the historical data at different times;

[0060] This historical data is uploaded by vehicles in different seasons or months, and there are systematic deviations in the data uploaded in different seasons or months. For example, the delay time of historical data in spring will differ from that in winter, and the delay time of historical data in December will differ from that in June. To accurately calculate the delay time threshold, a time correction factor can be determined based on the time characteristics of the delay time of the historical data, namely the season or month.

[0061] The time feature may be a seasonal feature or a monthly feature. Accordingly, when the time feature is a seasonal feature, the time correction factor may be a seasonal correction factor; when the time feature is a monthly feature, the time correction factor may be a monthly correction factor.

[0062] It should be noted that the delay time in the embodiment of the present invention refers to the time difference between the time when each piece of data uploaded by the vehicle is processed in the cloud and the time when it is generated on the vehicle side, as shown in the following formula 1:

[0063] Δt=Treceived -T generated Formula 1

[0064] Where Δt represents the delay time; T received Indicates the time it takes for data to be processed in the cloud; T generated Indicates the time when the data is generated on the vehicle side.

[0065] Step S103, performing cluster analysis on the above historical data based on vehicle characteristic indicators to determine a target delay factor;

[0066] When there are data of different data types in the historical data, cluster analysis is performed on the historical data of different data types based on vehicle characteristic indicators, where vehicle characteristic indicators refer to the vehicle's own characteristics, the vehicle's environmental data and scene data when each data is uploaded, etc., including but not limited to geographic location, network signal strength, vehicle model, etc.

[0067] The geographical location may be represented by a region code. The data types may include, but are not limited to, drive (E-Drive) data, battery (Battery) data, and warning (Warnings) data.

[0068] It is understood that different geographic locations, network signal strengths, vehicle models, and / or data types may all affect data latency. To accurately determine the latency threshold, it is necessary to comprehensively consider the impact of these factors on the latency of historical data. Cluster analysis of the historical data can be performed based on vehicle characteristic indicators to determine the target latency factor.

[0069] Step S104, combining the time correction factor and the target delay factor to determine the delay time threshold corresponding to different time characteristics and different vehicle characteristic indicators;

[0070] After determining the time correction factor and target delay factor, the delay time threshold can be determined by combining the two. The delay time threshold is different under different time characteristics and different vehicle characteristic indicators. For example, for vehicle upload data whose data type is battery data, when the delay time is in spring, the geographical location is G1, the network signal strength is medium, and the vehicle model is A2, the delay time threshold can be 3s; for vehicle upload data whose data type is drive data, when the delay time is in summer, the geographical location is G4, the network signal strength is weak, and the vehicle model is A2, the delay time threshold can be 5s.

[0071] After determining the delay time thresholds corresponding to all different time features and all different vehicle characteristic indicators in the historical data, all delay time thresholds can be summarized and stored according to the correlation relationship between time features, vehicle characteristic indicators and delay time thresholds, so as to be used later to determine whether the data uploaded by the current vehicle is abnormal data.

[0072] Step S105: determining the time characteristics and vehicle characteristic index corresponding to the received current vehicle uploaded data, and calling a target delay time threshold that matches the time characteristics and vehicle characteristic index corresponding to the current vehicle uploaded data;

[0073] According to the time characteristics and vehicle characteristic indicators of the current vehicle uploaded data, a delay time threshold that is the same as the time characteristics and vehicle characteristic indicators of the current vehicle uploaded data is called from the stored delay time thresholds as the target delay time threshold to determine whether the current vehicle uploaded data is abnormal data according to the target delay time threshold.

[0074] Step S106 , analyzing whether the data uploaded by the current vehicle is abnormal data based on the delay time of the data uploaded by the current vehicle and the target delay time threshold, and processing the abnormal data.

[0075] Specifically, in response to the delay time of the current vehicle uploading data being greater than the target delay time threshold, it is determined that the current vehicle uploading data is abnormal data; in response to the delay time of the current vehicle uploading data being less than or equal to the target delay time threshold, it is determined that the current vehicle uploading data is not abnormal data.

[0076] In the case that the current vehicle uploaded data is abnormal data, the current vehicle uploaded data can be further processed, marked as abnormal data, and the incremental update process is triggered. When obtaining the next batch of vehicle uploaded data, a more complete version of the abnormal data is obtained to reissue and improve the abnormal data. After improvement, the current vehicle uploaded data can be marked as the final version data.

[0077] At the same time, whenever a piece of currently uploaded vehicle data is identified as abnormal, the number of abnormal data is counted, and the proportion of abnormal data is counted based on a preset statistical time interval. If the proportion of abnormal data exceeds the preset ratio, it indicates that the delay time threshold is too strict or the vehicle characteristic indicators have changed significantly. This can trigger a cluster analysis of the updated vehicle uploaded data based on the vehicle characteristic indicators to re-determine the corresponding delay time threshold for different time characteristics and different vehicle characteristic indicators.

[0078] It is understandable that for the historical delay time Δt of historical data with the same time characteristics and the same vehicle characteristic index, a preset first quantile can be set, and the delay time corresponding to the preset first quantile is used as the delay time threshold of the historical data with the same time characteristics and the same vehicle characteristic index, referring to the following formula 2,

[0079] Q p (Δt) = M + αMAD Equation 2

[0080] Among them, Q p (Δt) represents the delay time threshold of historical data with the same time characteristics and the same vehicle characteristic indicators; M represents the median of the delay time of historical data with the same time characteristics and the same vehicle characteristic indicators; MAD represents the median absolute deviation of the delay time of historical data with the same time characteristics and the same vehicle characteristic indicators; α represents the delay factor.

[0081] When determining outlier data, compared to the mean and standard deviation, the median is only relevant to the order of historical data delays and is unaffected by extreme values. It can stably reflect the median position of historical data delays. The median absolute deviation uses the median as a benchmark to measure the dispersion of historical data delays. It is unaffected by extreme values ​​and can more reasonably reflect the data's dispersion. Therefore, the median and median absolute deviation are less or less affected by outliers, are more robust to long-tail distributions and extreme delays, and can more accurately characterize the characteristics of historical data delays, providing a more reliable basis for determining outlier data.

[0082] As an example, to reduce misjudgment of abnormal data, it is desirable to set the delay time threshold at a higher quantile of the delay time of the historical data. Therefore, the preset first quantile can be set to 99%. The delay time of the historical data with the same time characteristics and the same vehicle characteristic indicators is sorted by the size of the delay time data. The delay time of the historical data corresponding to the 99% quantile is determined as its delay time threshold. The median and median absolute deviation of the delay time of the historical data with the same time characteristics and the same vehicle characteristic indicators are calculated, and the delay factor can be determined according to the above formula 2.

[0083] It's understandable that the historical data delays in Equation 2 are categorized solely based on time characteristics and vehicle characteristic indicators, but the specific time characteristics and vehicle characteristic indicators are not considered during the calculation. Given that different time characteristics and vehicle characteristic indicators significantly impact the historical data delays, a time correction factor can be further determined based on the time characteristics of the historical data delays at different times. Cluster analysis of the historical data based on vehicle characteristic indicators can be used to determine the target delay factor, thereby enabling a more targeted and accurate determination of the delay threshold.

[0084] In an optional embodiment, determining the time correction factor according to the time characteristics of the delay time of the historical data at different times specifically includes:

[0085] When the time feature is a seasonal feature, determine the season in which the historical data delay time falls, calculate the median of the delay time of the historical data in that season and the median of the delay time of the historical data in the year in which the season falls, and determine the seasonal correction factor using the following formula 3:

[0086]

[0087] Where S(q) represents the seasonal correction factor of season q in the current year; M q represents the median of the lag time of historical data in season q; M qa Indicates the median of the lag time of the historical data in the year in which season q falls.

[0088] When the time feature is a monthly feature, determine the month in which the historical data delay time falls, calculate the median of the delay time of the historical data for that month and the median of the delay time of the historical data for the year in which the month falls, and determine the month correction factor using the following formula 4:

[0089]

[0090] Where S(m) represents the month correction factor of month m in the current year; M m Indicates the median of the delay time of historical data in month m; M ma Indicates the median of the delay time of the historical data in the year in which month m falls.

[0091] In an optional embodiment, as Figure 2 As shown, the above-mentioned cluster analysis of the historical data according to the vehicle characteristic index to determine the target delay factor includes the following steps S201 to S204:

[0092] Step S201, extracting features of historical delay time of historical data according to vehicle characteristic indicators to generate several feature vectors;

[0093] Step S202, clustering the above-mentioned feature vectors to obtain a number of clusters;

[0094] Step S203, calculating the median and median absolute deviation of the corresponding historical delay time for each of the above clusters, and setting a preset second quantile corresponding to each of the above clusters;

[0095] Step S204 : determining a target delay factor according to the median and median absolute deviation corresponding to each of the clusters and the delay time corresponding to the preset second quantile.

[0096] For historical data of different data types, the historical delay time of the historical data is extracted according to the vehicle characteristic index to obtain the feature vector X i As an example, X i =(Δt i ,E), where Δt i represents the historical delay time of historical data i, E represents the vehicle characteristic index corresponding to the historical delay time of historical data i, E = (G, Z, A, NQ), where G represents the geographical location of the historical delay time of historical data i, Z represents the month or season to which the historical delay time of historical data i belongs, A represents the vehicle type corresponding to historical data i; NQ represents the network signal strength when historical data i is uploaded.

[0097] A clustering algorithm is used to cluster the feature vectors to identify clusters with similar historical delay time distributions. Examples of such clustering algorithms include, but are not limited to, K-means clustering or Gaussian Mixture Model (GMM) clustering. It should be understood that for each data type, the historical data within each cluster has the same or similar vehicle characteristic indicators.

[0098] The median and median absolute deviation of the historical delay time are calculated for each cluster respectively, and the corresponding delay time is determined according to the preset second quantile, and used as the initial delay time threshold of the corresponding cluster, so as to determine the corresponding target delay factor for each cluster using Formula 2. For example, after clustering, four clusters are obtained, and the median and median absolute deviation of the corresponding historical delay time are calculated for each cluster respectively, and the delay time corresponding to the preset second quantile is determined as the initial delay time threshold of the cluster, and the target delay factor corresponding to the cluster is determined using Formula 2, and finally four target delay factors are obtained, namely, the target delay factor α1 corresponding to the first cluster, the target delay factor α2 corresponding to the second cluster, the target delay factor α3 corresponding to the third cluster, and the target delay factor α4 corresponding to the fourth cluster.

[0099] In an optional embodiment, the above-mentioned time correction factor and the above-mentioned target delay factor are combined to determine the delay time threshold corresponding to different time characteristics and different vehicle characteristic indicators, including:

[0100] For each of the clusters, construct a first calculation relationship between the delay time threshold and the median corresponding to the cluster, the absolute deviation of the median corresponding to the cluster, the time correction factor, and the target delay factor;

[0101] Based on the first calculation relationship corresponding to each of the above clusters, the delay time thresholds corresponding to different time characteristics and different vehicle characteristic indicators are calculated.

[0102] Determine the vehicle characteristic index, data type, and month or season of delay time corresponding to each cluster. After determining the target delay factor corresponding to each cluster, construct the first calculation relationship shown in Formula 5 for each cluster:

[0103] Threshold E,T(Z) =[M E,T(Z) +α E,T(Z) MAD E,T(Z) ]×S (Z) Formula 5

[0104] Among them, Threshold E,T(Z) Indicates the delay time threshold for vehicle data upload under the conditions of vehicle characteristic index E, data type T, and month or season Z; M E,T(Z) represents the median delay time of vehicle data upload under the vehicle characteristic index E, data type T, and month or season Z; α E,T(Z) Indicates the target delay factor for vehicle data upload under vehicle characteristic index E, data type T, and month or season Z; MAD E,T(z) S represents the median absolute deviation of the delay time of vehicle uploading data under the vehicle characteristic index E, data type T, and month or season Z; (Z) It is understood that when Z represents the month Z, S (Z) Indicates the correction factor for month Z in the current year; when Z indicates season Z, S (Z) Indicates the seasonal correction factor of season Z in the current year.

[0105] After determining the first calculation relationship, the delay time threshold corresponding to each cluster can be calculated based on the specific delay time median, delay time median absolute deviation, target delay factor, and time correction factor values ​​of each cluster.

[0106] Furthermore, the time characteristics, vehicle characteristic indicators and data types corresponding to the current vehicle uploaded data can be determined, and the delay time threshold that matches the time characteristics, vehicle characteristic indicators and data type of the current vehicle uploaded data can be called from the delay time thresholds corresponding to all cluster clusters as the target delay time threshold.

[0107] The delay of the current vehicle upload data is determined based on the time it was processed in the cloud and the time it was generated on the vehicle. The delay of the current vehicle upload data is compared with the target delay time threshold. If the delay of the current vehicle upload data is greater than the target delay time threshold, the current vehicle upload data is considered abnormal data. If the delay of the current vehicle upload data is less than or equal to the target delay time threshold, the current vehicle upload data is not considered abnormal data.

[0108] For example, when the time feature corresponding to the current vehicle upload data is July, the vehicle characteristic index is E, and the data type is battery data, Cluster II, with the same time feature as July, the vehicle characteristic index E, and the data type as battery data, can be called. The median delay of Cluster II is determined to be 2 days, the median absolute deviation is 0.5 days, and the second quantile is preset to 99%, with the delay corresponding to 99% being 3.5 days. Using Equation 2, the target delay factor corresponding to Cluster II is approximately 3, and the month correction factor is determined to be 1.2 using Equation 4. Using Equation 5, the delay threshold corresponding to Cluster II is calculated to be 4.2 days. The delay of the current vehicle upload data is 5 days. Since the delay of 5 days for the current vehicle upload data exceeds the delay threshold of 4.2 days, the current vehicle upload data can be determined to be abnormal.

[0109] In an optional embodiment, the above method further includes:

[0110] In response to a preset time period elapsing or the amount of updated data reaching a preset data amount threshold, performing cluster analysis on the updated data according to vehicle characteristic indicators;

[0111] According to the clustering results, the updated data is assigned a cluster, and the median and median absolute deviation corresponding to each cluster are updated using the delay time of the updated data, and the target delay factor is tuned;

[0112] The above time correction factor and the tuned target delay factor are combined to re-determine the corresponding delay time threshold under different time characteristics and different vehicle characteristic indicators.

[0113] It is understandable that due to the continuous increase in vehicle uploaded data, the delay time distribution of historical data may change with the network signal strength, vehicle model upgrades, etc. Therefore, after a preset time has passed or the amount of updated data is greater than the preset data volume threshold, the updated data can be clustered and analyzed. According to the results of the updated data clustering, the median and median absolute deviation of the delay time of the cluster cluster are updated, and the target delay factor is adjusted to achieve dynamic threshold update, so that the delay time threshold is updated with the changing vehicle characteristic indicators.

[0114] In an optional embodiment, allocating a cluster to the update data according to the clustering result includes:

[0115] Generate new clusters for the above updated data;

[0116] In the case where the vehicle characteristic index indicated by the new cluster is the same as the vehicle characteristic index indicated by the existing cluster, merging the new cluster into the existing cluster;

[0117] In the case that the vehicle characteristic index indicated by the new cluster is different from the vehicle characteristic index indicated by each existing cluster, the new cluster is added.

[0118] The new cluster of updated data includes updated data with the same or similar vehicle characteristic indicators and has a similar delay time distribution. It is determined whether the vehicle characteristic indicators indicated by the new cluster are the same as those indicated by the existing cluster. If the two are the same, the new cluster can be merged into the existing cluster; if the two are different, the new cluster can be added.

[0119] It should be noted that even if the two are different, if the two are similar and the data in the clusters have similar delay time distribution, the new cluster can be merged into the existing cluster.

[0120] In an optional embodiment, the method further includes: setting a decay factor, wherein the decay factor indicates that the delay time of the updated data of the cluster has a higher weight than the delay time of the historical data of the cluster.

[0121] The updating of the median and the median absolute deviation corresponding to each of the clusters includes: updating the median and the median absolute deviation corresponding to each of the clusters according to the attenuation factor and the delay time of the update data.

[0122] When a new cluster of updated data is merged with an existing cluster, the median and median absolute deviation of the delay time of the merged cluster are determined by the following equations 6 and 7, respectively:

[0123]

[0124] in, represents the median of the delay time of the merged clusters; λ represents the attenuation factor; Indicates the median delay time of the new cluster; Indicates the median delay time of the existing clusters; represents the median absolute deviation of the delay time of the merged clusters; The median absolute deviation of the delay time of the new clusters; Indicates the median absolute deviation of the latency of the existing clusters.

[0125] After updating the median and median absolute deviation of the latency of the merged clusters, the target latency factor of the merged clusters can be tuned using the following formula 8:

[0126]

[0127] in, represents the target delay factor of the merged clusters; Indicates the delay time corresponding to the preset second quantile of the merged cluster; α N Represents the delay factor to be determined during the tuning process. α is selected by optimization N , so that the delay time threshold of the merged cluster matches the delay time corresponding to the preset second quantile, and then determine This enables dynamic tuning of the target delay factor for the cluster, thereby updating the delay time threshold corresponding to the cluster.

[0128] The following describes a method for processing vehicle uploaded data in detail through a specific embodiment.

[0129] like Figure 3 As shown, the method for processing vehicle uploaded data according to the embodiment of the present invention includes the following steps S301 to S311:

[0130] Step S301, obtaining historical data uploaded by the vehicle;

[0131] Step S302: Determine a time correction factor using Formula 3 or Formula 4 based on the time characteristics of the delay time of the historical data at different times;

[0132] The time characteristics include monthly characteristics and seasonal characteristics, and accordingly, the time correction factor includes a monthly correction factor and a seasonal correction factor.

[0133] Step S303 , for historical data of different data types, feature extraction is performed on the historical delay time of the historical data according to vehicle feature indicators to obtain feature vectors Xi, and clustering is performed using a clustering algorithm to obtain a number of clusters;

[0134] Vehicle characteristic indicators include but are not limited to geographic location, network signal strength, vehicle model, month or season corresponding to the delay time, etc.

[0135] Step S304: calculating the median and median absolute deviation of the corresponding historical delay time for each of the above clusters, and setting a preset second quantile corresponding to each of the above clusters;

[0136] Step S305 , determining a target delay factor corresponding to each cluster using Formula 2 based on the median and median absolute deviation corresponding to each cluster and the delay time corresponding to the preset second quantile;

[0137] Step S306: for each of the clusters, construct a first calculation relationship as shown in Formula 5 for the cluster, and calculate the delay time threshold corresponding to the cluster;

[0138] Step S307: Determine the time characteristics, vehicle characteristic indicators, and data type corresponding to the data uploaded by the current vehicle, and select the delay time threshold that matches the time characteristics, vehicle characteristic indicators, and data type of the data uploaded by the current vehicle from the delay time thresholds corresponding to all clusters as the target delay time threshold;

[0139] Step S308, comparing the current vehicle data upload delay time with the target delay time threshold;

[0140] Step S309: If the delay time of the data uploaded by the current vehicle is greater than the target delay time threshold, the data uploaded by the current vehicle is abnormal data, and the data uploaded by the current vehicle is marked as abnormal data, and the abnormal data is incrementally updated;

[0141] Whenever a piece of data uploaded by a current vehicle is identified as abnormal, the number of abnormal data is counted, and the proportion of abnormal data is calculated based on a preset statistical interval. If the proportion of abnormal data exceeds a preset ratio, a cluster analysis of the updated vehicle uploaded data based on vehicle characteristic indicators is triggered to re-determine the corresponding delay time threshold for different time characteristics and different vehicle characteristic indicators.

[0142] Step S310: If the delay time of the data uploaded by the current vehicle is less than or equal to the target delay time threshold, the data uploaded by the current vehicle is not abnormal data;

[0143] Step S311: In response to the preset time or the amount of updated data reaching the preset data amount threshold, cluster analysis is performed on the updated data according to the vehicle characteristic index; based on the clustering results, cluster clusters are assigned to the above-mentioned updated data, and the delay time of the above-mentioned updated data is used to update the median and median absolute deviation corresponding to each of the above-mentioned clusters through Formulas 6 and 7, and the above-mentioned target delay factor is tuned through Formula 8; return to step S306, and re-determine the delay time threshold corresponding to different time characteristics and different vehicle characteristic indicators by combining the above-mentioned time correction factor and the tuned target delay factor.

[0144] According to an embodiment of the present invention, a method for processing vehicle uploaded data determines a time correction factor based on the time characteristics of the delay time of historical data at different times, performs cluster analysis on the historical data based on vehicle characteristic indicators, determines a target delay factor, and comprehensively determines the delay time threshold corresponding to different time characteristics and different vehicle characteristic indicators by combining the time correction factor and the above-mentioned target delay factor. This objectively and comprehensively considers the impact of the time characteristics and vehicle characteristic indicators on the delay time of vehicle uploaded data. By setting the time correction factor and the target delay factor, the delay time threshold corresponding to the historical data under different time characteristics and different vehicle characteristic indicators can be more accurately determined.

[0145] Determine the time characteristics and vehicle characteristic indicators corresponding to the current vehicle uploaded data, call the matching target delay time threshold, determine whether the current vehicle uploaded data is abnormal data, and process the abnormal data if it is abnormal data, achieving efficient and accurate abnormal data identification, and can provide comprehensive and accurate reference data for vehicle remote diagnosis, data analysis and decision-making, network optimization and data cleaning.

[0146] By dynamically updating the delay time threshold, the delay time threshold can be updated according to the changing vehicle characteristic indicators, etc., thereby further ensuring the accuracy of the delay time threshold and improving the effectiveness of abnormal data judgment using the delay time threshold.

[0147] Figure 4 FIG. 1 is a schematic diagram of the main modules of a processing device for vehicle uploaded data according to an embodiment of the present invention. Figure 4As shown, the processing device 400 for vehicle uploaded data of an embodiment of the present invention includes: an acquisition module 401, which is used to acquire historical data uploaded by the vehicle; a first determination module 402, which is used to determine the time correction factor according to the time characteristics of the delay time of the above historical data at different times; a second determination module 403, which is used to perform cluster analysis on the above historical data according to the vehicle characteristic index to determine the target delay factor; a third determination module 404, which is used to combine the above time correction factor and the above target delay factor to determine the corresponding delay time threshold under different time characteristics and different vehicle characteristic indicators; a calling module 405, which is used to determine the time characteristics and vehicle characteristic indicators corresponding to the current vehicle uploaded data received, and call the target delay time threshold that matches the time characteristics and vehicle characteristic indicators corresponding to the current vehicle uploaded data; a processing module 406, which is used to analyze whether the above current vehicle uploaded data is abnormal data according to the delay time of the above current vehicle uploaded data and the above target delay time threshold, and process the above abnormal data.

[0148] In an optional embodiment of the present invention, the above-mentioned second determination module 403 is also used to: extract features of the historical delay time of the historical data according to the vehicle characteristic indicators to generate a number of feature vectors; cluster the above-mentioned feature vectors to obtain a number of cluster clusters; calculate the median and median absolute deviation of the corresponding historical delay time for each of the above-mentioned cluster clusters, and set a preset second quantile corresponding to each of the above-mentioned cluster clusters; determine the target delay factor according to the median and median absolute deviation corresponding to each of the above-mentioned cluster clusters and the delay time corresponding to the above-mentioned preset second quantile.

[0149] In an optional embodiment of the present invention, the third determination module 404 is further used to: for each of the clusters, construct a first calculation relationship between the delay time threshold and the median corresponding to the cluster, the absolute deviation of the median corresponding to the cluster, the time correction factor and the target delay factor; based on the first calculation relationship corresponding to each of the clusters, calculate the delay time threshold corresponding to different time characteristics and different vehicle characteristic indicators.

[0150] In an optional embodiment of the present invention, the processing module 406 is further used to: in response to the delay time of the current vehicle uploading data being greater than the target delay time threshold, determine that the current vehicle uploading data is abnormal data; in response to the delay time of the current vehicle uploading data being less than or equal to the target delay time threshold, determine that the current vehicle uploading data is not abnormal data.

[0151] In an optional embodiment of the present invention, the above-mentioned processing device 400 for vehicle uploaded data also includes: a tuning module, which is used to: in response to the passage of a preset time or the data volume of the updated data reaching a preset data volume threshold, perform cluster analysis on the updated data according to vehicle characteristic indicators; according to the clustering results, assign cluster clusters to the above-mentioned updated data, and use the delay time of the above-mentioned updated data to update the median and median absolute deviation corresponding to each of the above-mentioned cluster clusters, and tune the above-mentioned target delay factor; and re-determine the delay time threshold corresponding to different time characteristics and different vehicle characteristic indicators by combining the above-mentioned time correction factor and the tuned target delay factor.

[0152] In an optional embodiment of the present invention, the above-mentioned tuning module is also used to: generate a new cluster for the above-mentioned updated data; when the vehicle characteristic index indicated by the above-mentioned new cluster is the same as the vehicle characteristic index indicated by the existing cluster, merge the above-mentioned new cluster into the existing cluster; when the vehicle characteristic index indicated by the above-mentioned new cluster is different from the vehicle characteristic index indicated by each existing cluster, add the above-mentioned new cluster.

[0153] In an optional embodiment of the present invention, the above-mentioned processing device 400 for vehicle uploaded data also includes: a setting module for setting an attenuation factor; the above-mentioned attenuation factor indicates that compared with the delay time of the historical data of the above-mentioned cluster, the delay time of the updated data of the above-mentioned cluster has a higher weight.

[0154] The tuning module is further configured to update the median and median absolute deviation corresponding to each of the clusters according to the attenuation factor and the delay time of the updated data.

[0155] According to an embodiment of the present invention, a processing device for vehicle uploaded data determines a time correction factor based on the time characteristics of the delay time of historical data at different times, performs cluster analysis on the historical data according to vehicle characteristic indicators, determines a target delay factor, and comprehensively determines the delay time threshold corresponding to different time characteristics and different vehicle characteristic indicators by combining the time correction factor and the above-mentioned target delay factor. The device objectively and comprehensively considers the impact of the time characteristics and vehicle characteristic indicators on the delay time of vehicle uploaded data. By setting the time correction factor and the target delay factor, the delay time threshold corresponding to the historical data under different time characteristics and different vehicle characteristic indicators is more accurately determined.

[0156] Determine the time characteristics and vehicle characteristic indicators corresponding to the current vehicle uploaded data, call the matching target delay time threshold, determine whether the current vehicle uploaded data is abnormal data, and process the abnormal data if it is abnormal data, achieving efficient and accurate abnormal data identification, and can provide comprehensive and accurate reference data for vehicle remote diagnosis, data analysis and decision-making, network optimization and data cleaning.

[0157] By dynamically updating the delay time threshold, the delay time threshold can be updated according to the changing vehicle characteristic indicators, etc., thereby further ensuring the accuracy of the delay time threshold and improving the effectiveness of abnormal data judgment using the delay time threshold.

[0158] Figure 5 An exemplary system architecture 500 is shown, to which a method for processing vehicle-uploaded data or an apparatus for processing vehicle-uploaded data according to an embodiment of the present invention may be applied.

[0159] like Figure 5 As shown, system architecture 500 may include vehicle computers 501, 502, and 503, a network 504, and a vehicle manufacturer server 505. Network 504 is used to provide a medium for communication links between vehicle computers 501, 502, and 503 and vehicle manufacturer server 505. Network 504 may include various connection types, such as wired or wireless communication links or fiber optic cables.

[0160] The vehicle computers 501 , 502 , 503 interact with the vehicle manufacturer's server 505 via the network 504 to receive or send data, etc.

[0161] The vehicle manufacturer server 505 may be a server that provides various services, such as a background management server that supports the current vehicle uploaded data sent by the vehicle computers 501, 502, and 503. The background management server may determine whether the acquired current vehicle uploaded data is abnormal data and process the abnormal data.

[0162] It should be noted that the method for processing vehicle uploaded data provided in the embodiment of the present invention is generally executed by the vehicle manufacturer server 505 , and accordingly, the processing device for vehicle uploaded data is generally set in the vehicle manufacturer server 505 .

[0163] It should be understood that Figure 5 The number of vehicle computers, networks, and vehicle enterprise servers in the embodiment is merely illustrative. Any number of vehicle computers, networks, and vehicle enterprise servers may be provided as required.

[0164] Reference below Figure 6 , which shows a structural diagram of a computer system 600 of a car enterprise server suitable for implementing an embodiment of the present invention. Figure 6The car enterprise server shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0165] like Figure 6 As shown, the computer system 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage portion 608 into a random access memory (RAM) 603. Various programs and data required for the operation of the computer system 600 are also stored in the RAM 603. The CPU 601, ROM 602, and RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0166] The following components are connected to the I / O interface 605: an input section 606 including a keyboard, a mouse, and the like; an output section 607 including devices such as a cathode ray tube (CRT), a liquid crystal display (LCD), and a speaker; a storage section 608 including a hard disk; and a communication section 609 including a network interface card such as a LAN card or a modem. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 610 as needed, so that computer programs read therefrom can be installed into the storage section 608 as needed.

[0167] In particular, according to the embodiments disclosed in the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 609, and / or installed from a removable medium 611. When the computer program is executed by the central processing unit (CPU) 601, the above-mentioned functions defined in the system of the present invention are performed.

[0168] It should be noted that the computer-readable medium described in the present invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media can include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. This propagated data signal can take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. Program code embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wireline, optical fiber cable, RF, or any suitable combination thereof.

[0169] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the above-mentioned module, program segment, or a part of 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 box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0170] The modules described in the embodiments of the present invention may be implemented in software or hardware. The modules described may also be provided in a processor. For example, they may be described as follows: a processor comprising an acquisition module, a first determination module, a second determination module, a third determination module, a calling module, and a processing module. The names of these modules do not, in some cases, limit the modules themselves. For example, the acquisition module may also be described as a "module for acquiring historical data uploaded by vehicles."

[0171] As another aspect, the present invention further provides a computer-readable medium, which may be included in the device described in the above embodiment; or may exist independently and not be assembled into the device. The computer-readable medium carries one or more programs, and when the one or more programs are executed by a device, the device includes: obtaining historical data uploaded by vehicles; determining a time correction factor based on the time characteristics of the delay time of the historical data at different times; performing cluster analysis on the historical data based on vehicle characteristic indicators to determine a target delay factor; combining the time correction factor and the target delay factor to determine a delay time threshold corresponding to different time characteristics and different vehicle characteristic indicators; for the received current vehicle uploaded data, determining the time characteristics and vehicle characteristic indicators corresponding to the current vehicle uploaded data, and calling a target delay time threshold that matches the time characteristics and vehicle characteristic indicators corresponding to the current vehicle uploaded data; analyzing whether the current vehicle uploaded data is abnormal data based on the delay time of the current vehicle uploaded data and the target delay time threshold, and processing the abnormal data.

[0172] According to the technical solution of the embodiment of the present invention, a time correction factor can be determined according to the time characteristics of the delay time of historical data at different times, and the historical data can be clustered and analyzed according to the vehicle characteristic indicators to determine the target delay factor. The time correction factor and the above-mentioned target delay factor are combined to determine the delay time threshold corresponding to different time characteristics and different vehicle characteristic indicators. The impact of the time characteristics and vehicle characteristic indicators on the delay time of vehicle uploading data is objectively and comprehensively considered. By setting the time correction factor and the target delay factor, the delay time threshold corresponding to the historical data under different time characteristics and different vehicle characteristic indicators can be determined more accurately.

[0173] Determine the time characteristics and vehicle characteristic indicators corresponding to the current vehicle uploaded data, call the matching target delay time threshold, determine whether the current vehicle uploaded data is abnormal data, and process the abnormal data if it is abnormal data, achieving efficient and accurate abnormal data identification, and can provide comprehensive and accurate reference data for vehicle remote diagnosis, data analysis and decision-making, network optimization and data cleaning.

[0174] By dynamically updating the delay time threshold, the delay time threshold can be updated according to the changing vehicle characteristic indicators, etc., thereby further ensuring the accuracy of the delay time threshold and improving the effectiveness of abnormal data judgment using the delay time threshold.

[0175] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A method for processing vehicle uploaded data, characterized in that: include: Get historical data uploaded by vehicles; determining a time correction factor according to time characteristics of the delay time of the historical data at different times; performing cluster analysis on the historical data according to vehicle characteristic indicators to determine a target delay factor; Combining the time correction factor and the target delay factor, determining a delay time threshold corresponding to different time characteristics and different vehicle characteristic indicators; For the received current vehicle uploaded data, determining a time feature and a vehicle characteristic index corresponding to the current vehicle uploaded data, and calling a target delay time threshold that matches the time feature and the vehicle characteristic index corresponding to the current vehicle uploaded data; According to the delay time of the current vehicle uploading data and the target delay time threshold, it is analyzed whether the current vehicle uploading data is abnormal data, and the abnormal data is processed.

2. The method for processing vehicle uploaded data according to claim 1, characterized in that: The performing cluster analysis on the historical data according to the vehicle characteristic index to determine the target delay factor includes: Extract features of the historical delay time of historical data based on vehicle characteristic indicators and generate several feature vectors; Clustering the plurality of feature vectors to obtain a plurality of clusters; Calculating the median and median absolute deviation of the corresponding historical delay time for each cluster, and setting a preset second quantile corresponding to each cluster; A target delay factor is determined according to the median and median absolute deviation corresponding to each cluster and the delay time corresponding to the preset second quantile.

3. The method for processing vehicle uploaded data according to claim 2, characterized in that: The step of combining the time correction factor and the target delay factor to determine the delay time threshold corresponding to different time characteristics and different vehicle characteristic indicators includes: For each cluster, construct a first calculation relationship between a delay time threshold and a median corresponding to the cluster, an absolute deviation of the median corresponding to the cluster, a time correction factor, and the target delay factor; Based on the first calculation relationship corresponding to each cluster, a delay time threshold corresponding to different time characteristics and different vehicle characteristic indicators is calculated.

4. The method for processing vehicle uploaded data according to claim 1, characterized in that: The analyzing whether the current vehicle uploaded data is abnormal data includes: In response to the delay time of the current vehicle uploading data being greater than the target delay time threshold, determining that the current vehicle uploading data is abnormal data; In response to the delay time of the current vehicle-uploaded data being less than or equal to the target delay time threshold, it is determined that the current vehicle-uploaded data is not abnormal data.

5. The method for processing vehicle uploaded data according to claim 1, characterized in that: The method further comprises: In response to a preset time period elapsing or the amount of updated data reaching a preset data amount threshold, performing cluster analysis on the updated data according to vehicle characteristic indicators; According to the clustering result, the updated data is assigned a cluster, and the median and median absolute deviation corresponding to each cluster are updated using the delay time of the updated data, and the target delay factor is tuned; The delay time threshold corresponding to different time characteristics and different vehicle characteristic indicators is re-determined by combining the time correction factor and the adjusted target delay factor.

6. The method for processing vehicle uploaded data according to claim 5, characterized in that: The step of allocating a cluster to the updated data according to the clustering result includes: Generating a new cluster for the updated data; In a case where the vehicle characteristic index indicated by the new cluster is the same as the vehicle characteristic index indicated by the existing cluster, merging the new cluster into the existing cluster; In a case where the vehicle characteristic index indicated by the new cluster is different from the vehicle characteristic index indicated by each existing cluster, the new cluster is added.

7. The method for processing vehicle uploaded data according to claim 5, characterized in that: The method further includes: setting a decay factor; the decay factor indicating that the delay time of the updated data of the cluster has a higher weight than the delay time of the historical data of the cluster; The updating of the median and the median absolute deviation corresponding to each cluster includes: updating the median and the median absolute deviation corresponding to each cluster according to the attenuation factor and the delay time of the update data.

8. A device for processing vehicle uploaded data, characterized in that: include: Acquisition module, used to obtain historical data uploaded by vehicles; A first determining module is configured to determine a time correction factor according to time characteristics of the delay time of the historical data at different times; a second determination module, configured to perform cluster analysis on the historical data based on vehicle characteristic indicators to determine a target delay factor; a third determination module, configured to determine a delay time threshold corresponding to different time characteristics and different vehicle characteristic indicators by combining the time correction factor and the target delay factor; a calling module, configured to determine, for the received current vehicle uploaded data, a time feature and a vehicle characteristic index corresponding to the current vehicle uploaded data, and call a target delay time threshold that matches the time feature and vehicle characteristic index corresponding to the current vehicle uploaded data; The processing module is used to analyze whether the data uploaded by the current vehicle is abnormal data according to the delay time of the data uploaded by the current vehicle and the target delay time threshold, and process the abnormal data.

9. An electronic device for processing vehicle uploaded data, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer-readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images