A data anomaly analysis method and system for electronic device detection

Abstract

The present invention relates to the technical field of data error detection, and specifically relates to a method and system for analyzing data anomalies for electronic device detection. Starting from the device data perception layer, the present invention performs error detection on the data at this layer; and, based on the first intelligent driving processing data and the first anomaly index, it obtains the second intelligent driving processing data from the device data processing layer, so that on the basis of the first anomaly index, second intelligent driving processing data with data relevance can be obtained from the first intelligent driving processing data; and on the basis of linking the first anomaly index, factors that cause data errors in the device data processing layer can be obtained more accurately than directly obtaining the second intelligent driving data; finally, a third anomaly index is obtained according to the first anomaly index and the second anomaly index, and the influence of data error detection of multiple factors in intelligent driving can be comprehensively considered, thereby significantly improving the data error detection ability of intelligent driving.

Description

Technical Field

[0001] The present invention relates to the technical field of data error detection, and in particular to a data anomaly analysis method and system for electronic device detection. Background Art

[0002] With the development of the times, the trend towards intelligent driving is becoming increasingly strong. Currently, due to the safety requirements of intelligent driving and the huge amount of data processing, intelligent driving is extremely dependent on data accuracy. Errors in the accuracy of intelligent driving data can lead to serious consequences. Currently, there are few methods for detecting errors in intelligent driving data, and the ability to detect errors in intelligent driving data is relatively poor. Summary of the Invention

[0003] In order to solve the technical problem of poor data error detection capability in intelligent driving, the purpose of the present invention is to provide a data anomaly analysis method for electronic device detection. The technical solution adopted is as follows:

[0004] Acquire first intelligent driving processing data from a device data perception layer;

[0005] Obtaining a first abnormality indicator according to the first intelligent driving processing data;

[0006] Based on the first intelligent driving processing data and the first abnormality indicator, obtaining second intelligent driving processing data from a device data processing layer;

[0007] Obtaining a second abnormality indicator according to the second intelligent driving processing data;

[0008] Obtaining a third abnormality indicator according to the first abnormality indicator and the second abnormality indicator;

[0009] Determine the data abnormality result of the intelligent driving system according to the third abnormality indicator.

[0010] According to the above aspect and any possible implementation, further provided is an implementation, wherein the step of obtaining the first intelligent driving processing data from the device data perception layer includes the following steps:

[0011] Determine the time node interval for single batch data collection;

[0012] In the time node interval, sensor data acquired by multiple sensors are collected based on time synchronization, wherein the type and quantity of data collected by the sensors in each time node interval are the same.

[0013] According to the above aspect and any possible implementation, further provided is an implementation, wherein obtaining a first abnormality indicator according to the first intelligent driving processing data comprises the following steps:

[0014] Obtain the preset standard batch sensing data volume, where the duration of the time node interval of the standard batch sensing data volume is the same as that of the time node interval corresponding to the batch to be compared, where the number of data acquisitions of the sensors of the standard batch sensing data volume is the same as that of the batch to be compared, and where the types of data acquisitions corresponding to the standard batch sensing data volume are the same as those of the sensors of the batch to be compared;

[0015] Obtain the data integrity corresponding to the comparison batch according to the ratio of the number of data acquisitions of the sensing data of the batch to be compared to the standard batch sensing data volume;

[0016] Obtain the degree of data deviation of the sensing data of the batch to be compared during continuous acquisition;

[0017] Obtain the correlation of the degree of difference between the data corresponding to different types of data acquisitions according to the degree of data deviation, and determine the data consistency according to the correlation of the degree of difference;

[0018] Obtain the first anomaly index according to the data integrity and the data consistency;

[0019] In the above aspects and any possible implementation manners, a further implementation manner is provided. The obtaining of the degree of data deviation of the sensing data of the batch to be compared during continuous acquisition includes the following steps:

[0020] Generate a data deviation comparison combination according to the types of data acquisitions of the batch to be compared, where each two different types of data acquisitions correspond to one data deviation comparison combination;

[0021] Obtain the difference set corresponding to the batch to be compared according to the data deviation comparison combination, where one difference set corresponds to one monitoring angle of the vehicle;

[0022] Determine the degree of data deviation according to the difference set;

[0023] In the above aspects and any possible implementation manners, a further implementation manner is provided. The obtaining of the correlation of the degree of difference between the data corresponding to different types of data acquisitions according to the degree of data deviation, and the determination of the data consistency according to the correlation of the degree of difference include the following steps:

[0024] Obtain the correlation of the degree of difference between the data corresponding to the types of data acquisitions according to the degree of data deviation and the monitoring angle of the vehicle;

[0025] Determine the data consistency according to the degree of correlation of the differences between the data corresponding to the data collection types and the number of data deviation comparison combinations.

[0026] In the above aspects and any possible implementation manners, a further implementation manner is provided. The obtaining the second anomaly index according to the second intelligent driving processing data includes the following steps:

[0027] Obtain a data delay anomaly index according to the second intelligent driving processing data;

[0028] Obtain a data transmission reliability index according to the second intelligent driving processing data;

[0029] Obtain the second anomaly index according to the data delay anomaly index and the data transmission reliability index.

[0030] In the above aspects and any possible implementation manners, a further implementation manner is provided. The obtaining the data delay anomaly index according to the second intelligent driving processing data includes the following steps:

[0031] Obtain a data quality set from the second intelligent driving data, where the data quality set is determined and obtained by the first anomaly index;

[0032] Obtain a data processing time set from the second intelligent driving data, where the data processing time set is used to reflect data transmission delay;

[0033] Obtain the data delay anomaly index according to the data quality set and the data processing time set.

[0034] In the above aspects and any possible implementation manners, a further implementation manner is provided. The obtaining the data transmission reliability index according to the second intelligent driving processing data includes the following steps:

[0035] Obtain, from the second intelligent driving processing data, a vehicle body attitude adjustment instruction and a vehicle body attitude adjustment vector in the device data processing layer;

[0036] Determine the executed vehicle body attitude adjustment vector according to the vehicle body attitude adjustment instruction and the vehicle body attitude adjustment vector;

[0037] Obtain the data transmission reliability index according to the vehicle body attitude adjustment instruction, the vehicle body attitude adjustment vector, and the executed vehicle body attitude adjustment vector.

[0038] In the above aspects and any possible implementation manners, a further implementation manner is provided;

[0039] After determining the data anomaly result of the intelligent driving system according to the third anomaly indicator, the method further includes the following steps:

[0040] Generate vehicle behavior adjustment data according to the data anomaly result;

[0041] Send the vehicle behavior adjustment data to the device data control layer to generate a vehicle behavior adjustment instruction according to the vehicle behavior adjustment data, and control the vehicle behavior according to the vehicle behavior adjustment instruction.

[0042] In addition, in a data anomaly analysis system for electronic device detection according to the present invention, the system includes:

[0043] A first data processing module for obtaining first intelligent driving processing data from the device data perception layer;

[0044] A second data processing module for obtaining a first anomaly indicator according to the first intelligent driving processing data;

[0045] A third data processing module for obtaining second intelligent driving processing data from the device data processing layer based on the first intelligent driving processing data and the first anomaly indicator;

[0046] A fourth data processing module for obtaining a second anomaly indicator according to the second intelligent driving processing data;

[0047] A fifth data processing module for obtaining a third anomaly indicator according to the first anomaly indicator and the second anomaly indicator;

[0048] A sixth data processing module for determining the data anomaly result of the intelligent driving system according to the third anomaly indicator.

[0049] Further, the first data processing module is further specifically used for:

[0050] Determine the time node interval for single-batch data collection;

[0051] Within the time node interval, collect sensing data obtained by multiple sensors based on time synchronization, where the types and quantities of data collected by the sensors within each time node interval are the same.

[0052] Further, the second data processing module is further specifically used for:

[0053] Obtain the preset standard batch sensing data volume, where the duration of the time node interval of the standard batch sensing data volume is the same as that of the time node interval corresponding to the batch to be compared, where the number of data acquisitions of the sensors for the standard batch sensing data volume is the same as that of the batch to be compared, and where the types of data acquisitions corresponding to the standard batch sensing data volume are the same as the types of data acquisitions of the sensors of the batch to be compared;

[0054] Obtain the data integrity corresponding to the comparison batch according to the ratio of the number of data acquisitions of the sensing data of the batch to be compared to the standard batch sensing data volume;

[0055] Obtain the degree of data deviation of the sensing data of the batch to be compared during continuous acquisition;

[0056] Obtain the correlation of the degree of difference between the corresponding data of different types of data acquisitions according to the degree of data deviation, and determine the data consistency according to the correlation of the degree of difference;

[0057] Obtain the first anomaly index according to the data integrity and the data consistency.

[0058] Furthermore, the second data processing module is further specifically configured to:

[0059] Generate a data deviation comparison combination according to the types of data acquisitions of the batch to be compared, where each two different types of data acquisitions correspond to one data deviation comparison combination;

[0060] Obtain the difference set corresponding to the batch to be compared according to the data deviation comparison combination, where one difference set corresponds to one monitoring angle of the vehicle;

[0061] Determine the degree of data deviation according to the difference set.

[0062] Furthermore, the second data processing module is further specifically configured to:

[0063] Obtain the correlation of the degree of difference between the corresponding data of the types of data acquisitions according to the degree of data deviation and the monitoring angle of the vehicle;

[0064] Determine the data consistency according to the correlation of the degree of difference between the corresponding data of the types of data acquisitions and the number of data deviation comparison combinations.

[0065] Furthermore, the fourth data processing module is further specifically configured to:

[0066] Obtain a data delay anomaly index according to the second intelligent driving processing data;

[0067] Obtain a data transmission reliability index according to the second intelligent driving processed data;

[0068] Obtain the second anomaly index according to the data delay anomaly index and the data transmission reliability index.

[0069] Furthermore, the fourth data processing module is further specifically configured to:

[0070] Obtain a data quality set from the second intelligent driving data, where the data quality set is determined and obtained by the first anomaly index;

[0071] Obtain a data processing time set from the second intelligent driving data, where the data processing time set is used to reflect data transmission delay;

[0072] Obtain the data delay anomaly index according to the data quality set and the data processing time set.

[0073] Furthermore, the fourth data processing module is further specifically configured to:

[0074] Obtain a body attitude adjustment instruction and a body attitude adjustment vector in the device data processing layer according to the second intelligent driving processed data;

[0075] Determine the executed body attitude adjustment vector according to the body attitude adjustment instruction and the body attitude adjustment vector;

[0076] Obtain the data transmission reliability index according to the body attitude adjustment instruction, the body attitude adjustment vector, and the executed body attitude adjustment vector.

[0077] Furthermore, the fourth data processing module is further specifically configured to:

[0078] Generate vehicle behavior adjustment data according to the data anomaly result;

[0079] Send the vehicle behavior adjustment data to the device data control layer to generate a vehicle behavior adjustment instruction according to the vehicle behavior adjustment data, and control the vehicle behavior according to the vehicle behavior adjustment instruction.

[0080] The present invention has the following beneficial effects: First, the present invention obtains the first intelligent driving processing data from the device data perception layer, starting from the device data perception layer to detect errors in the data of this layer; then, based on the first intelligent driving processing data, the first abnormal index is obtained, enabling the first factor causing data errors to be obtained at the perception layer level; after that, based on the first intelligent driving processing data and the first abnormal index, the second intelligent driving processing data is obtained from the device data processing layer, and on the basis of the first abnormal index, the second intelligent driving processing data with data relevance can be obtained from the first intelligent driving processing data; then, according to the second intelligent driving processing data, the second abnormal index is obtained, and on the basis of linking the first abnormal index, the factor causing data errors in the device data processing layer can be obtained more accurately than directly obtaining the second intelligent driving data; finally, the third abnormal index is obtained according to the first abnormal index and the second abnormal index, and the data abnormal result of the intelligent driving system is determined according to the third abnormal index, comprehensively considering the influence of data error detection of multiple factors in intelligent driving, thereby significantly improving the data error detection ability of intelligent driving. BRIEF DESCRIPTION OF THE DRAWINGS

[0081] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention 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, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0082] Figure 1 It is a flowchart of a data anomaly analysis method for electronic device detection provided by an embodiment of the present invention;

[0083] Figure 2 It is a flowchart in step S10 of a data anomaly analysis method for electronic device detection provided by an embodiment of the present invention;

[0084] Figure 3 It is a flowchart in step S20 of a data anomaly analysis method for electronic device detection provided by an embodiment of the present invention;

[0085] Figure 4 It is a flowchart in step S20 of another data anomaly analysis method for electronic device detection provided by an embodiment of the present invention;

[0086] Figure 5 It is a flowchart in step S20 of yet another data anomaly analysis method for electronic device detection provided by an embodiment of the present invention;

[0087] Figure 6The flowchart in step S40 of a data anomaly analysis method for electronic device detection provided by an embodiment of the present invention;

[0088] Figure 7 The flowchart in step S40 of another data anomaly analysis method for electronic device detection provided by an embodiment of the present invention;

[0089] Figure 8 The flowchart in step S40 of yet another data anomaly analysis method for electronic device detection provided by an embodiment of the present invention;

[0090] Figure 9 The flowchart in step S40 of yet another data anomaly analysis method for electronic device detection provided by an embodiment of the present invention;

[0091] Figure 10 The principle block diagram of a data anomaly analysis system for electronic device detection provided by an embodiment of the present invention;

[0092] Figure 11 The schematic diagram of a computer device provided by an embodiment of the present invention. Detailed implementation manners

[0093] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation manners, structures, features and effects of a data anomaly analysis method and system for electronic device detection proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0094] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0095] The following specifically describes the specific solutions of a data anomaly analysis method and system for electronic device detection provided by the present invention in conjunction with the accompanying drawings.

[0096] Please refer to Figure 1 , which shows the flowchart of a data anomaly analysis method for electronic device detection provided by an embodiment of the present invention, and specifically includes the following steps:

[0097] S10: Obtain the first intelligent driving processing data from the device data perception layer.

[0098] Among them, current intelligent driving can be divided into a device data perception layer, a device data processing layer, and a device data control layer. In the embodiments of the present invention, first intelligent driving processing data can be obtained from various types of sensors in the device data perception layer to perform error detection on the data under the device data perception layer.

[0099] S20: Obtain a first anomaly index according to the first intelligent driving processing data.

[0100] In one embodiment, the first anomaly index corresponds to the first intelligent driving processing data, and the first anomaly index reflects the anomaly of the internal data of the sensors existing in the device data perception layer.

[0101] S30; Based on the first intelligent driving processing data and the first anomaly index, obtain second intelligent driving processing data from the device data processing layer.

[0102] In one embodiment, the second intelligent driving processing data is obtained in the device data layer, and it should be noted that the second intelligent driving processing data also needs to be obtained based on the first anomaly index. That is to say, the second intelligent driving processing data and the first intelligent driving processing data are actually linked. The quality of the data in the first intelligent driving processing data will affect the structure of the second intelligent driving processing data. The advantage of such a linked design is that the data error problems that occur in the device data perception layer can be correctly transmitted and fed back to the device data control layer, so that the data problems of these two layers can be correctly combined to obtain a more accurate data detection result.

[0103] S40: Obtain a second anomaly index according to the second intelligent driving processing data.

[0104] In one embodiment, the second anomaly index corresponds to the second intelligent driving processing data, and the second anomaly index reflects the data delay and data processing anomaly existing in the device data processing layer under the precondition of data error in the device data perception layer.

[0105] S50; Obtain a third anomaly index according to the first anomaly index and the second anomaly index.

[0106] In one embodiment, by comprehensively considering the data anomaly problems existing in the first anomaly index and the second anomaly index, an overall anomaly index reflecting the intelligent driving system, that is, the third anomaly index, can be comprehensively obtained.

[0107] S60: Determine the data anomaly result of the intelligent driving system according to the third anomaly index.

[0108] Understandably, for the intelligent driving system, in the embodiments of the present invention, the monitoring data of multiple environmental detection devices are fused and processed to a certain extent, such as lidar, cameras, etc., which are all the most important data for intelligent driving. In this regard, the external environmental data collected by the intelligent driving system in real time can be obtained. During actual use, the relevant data inside the sensor will analyze and process the external monitoring data, and the relevant data such as current, voltage, temperature, and vibration inside it are also important indicators for evaluating the abnormality of the device. Therefore, it is also necessary to further collect and analyze these data.

[0109] In the field of automobile manufacturing, the device data perception layer is responsible for collecting external environmental data in real time through various sensors installed on the vehicle. The stability and persistence of data collection have a crucial impact on the accuracy and efficiency of subsequent planning and control processes. The device data processing layer is responsible for real-time analysis, judgment, and planning evaluation of the external environmental data collected by the device data perception layer, and its final planning result will be directly transmitted to the device data control layer to achieve precise control of the vehicle driving trajectory. The coherence and response speed of the overall data flow have a significant impact on the actual driving performance of the vehicle. Therefore, in order to ensure the stable operation of the intelligent driving system, it is necessary to conduct a comprehensive and in-depth analysis of the vehicle monitoring result data stream to evaluate possible data anomalies in the intelligent driving system and take corresponding measures for adjustment accordingly.

[0110] In the test stage of the intelligent driving system, a large amount of data will be generated at each data layer. To facilitate subsequent in-depth analysis, the primary task is data preprocessing. For the data of the device data perception layer, a time synchronization strategy can be adopted to ensure the consistency of sensor data, and then data cleaning is carried out to remove noise and redundancy, and multi-sensor data is fused to obtain more comprehensive and accurate information. After receiving the data collected by the device data perception layer, the device data processing layer can perform obstacle prediction and trajectory smoothing processing through corresponding data processing models, and then format the decision-making information to improve the planning efficiency and decision-making quality. In the device data control layer, data preprocessing focuses on the precise parsing of execution commands, the optimal setting of control parameters, and the filtering of feedback information to ensure the accurate execution of control instructions and the efficient and stable response of the system. As mentioned above, it can be seen that the specific division of labor in the intelligent driving system at different levels is different, and the amount of data involved is huge. How to ensure the accuracy of data is crucial for the intelligent driving system.

[0111] Understandably, when evaluating data anomalies in an automotive intelligent driving system, the primary task is to conduct a comprehensive and rigorous review of the various data collected by the device data perception layer. During the normal operation of the intelligent driving system, various built-in sensors continuously monitor and identify the surrounding environment in detail. However, once the sensors encounter faults or deviations during the identification process, the collected data may deviate from the normal range, thereby misleading the subsequent device data processing layer and device data control layer and triggering incorrect decision-making instructions. Similarly, the data under the device data processing layer also needs to be comprehensively and rigorously reviewed, and data errors in it may also result in incorrect decision-making instructions.

[0112] In steps S10 - S60, first, obtain the first intelligent driving processing data from the device data perception layer to detect errors in the data at the device data perception layer level; then, obtain the first anomaly index based on the first intelligent driving processing data, which can obtain the first factor that causes data errors at the perception layer level; after that, based on the first intelligent driving processing data and the first anomaly index, obtain the second intelligent driving processing data from the device data processing layer, and on the basis of the first anomaly index, obtain the second intelligent driving processing data with data relevance from the first intelligent driving processing data; then, obtain the second anomaly index according to the second intelligent driving processing data, and on the basis of linking the first anomaly index, more accurately obtain the factors that cause data errors in the device data processing layer compared to directly obtaining the second intelligent driving data; finally, obtain the third anomaly index according to the first anomaly index and the second anomaly index, and determine the data anomaly result of the intelligent driving system according to the third anomaly index, which can comprehensively consider the impact of data error detection of multiple factors in intelligent driving, thereby significantly improving the data error detection ability of intelligent driving.

[0113] In the embodiments of the present invention, in order to accurately evaluate the degree of data anomalies in the device data perception layer, two key indicators need to be focused on: one is the integrity level of the collected data, which is directly related to whether the data comprehensively and without omission reflects the environmental conditions; the other is the frequency of the appearance of high-difference data during the collection process, and this indicator can effectively reveal the degree of abnormal fluctuations in the data. By comprehensively using these two evaluation indicators, it is possible to more scientifically and systematically judge the abnormal conditions of data collection in the device data perception layer and provide solid data support for the stable operation of the intelligent driving system.

[0114] Figure 2 It is a flowchart of step S10 in a data anomaly analysis method for electronic device detection provided by an embodiment of the present invention.

[0115] Specifically, in step S10, that is, the step of obtaining the first intelligent driving processing data from the device data perception layer, specifically includes the following steps:

[0116] S11: Determine the time node interval for single - batch data acquisition.

[0117] S12: Within the time node interval, based on time synchronization, collect sensing data obtained from multiple sensors, where the types and quantities of data collected by sensors within each time node interval are the same.

[0118] The device data perception layer collects the monitoring data of multiple types of sensors. In the pre - processing stage, the monitoring data of each type of sensor can be time - synchronized, and the types and quantities of relevant sensor data within each time node should be kept consistent. Specifically, the data collected within a preset time period can be used as a single - batch acquisition.

[0119] Figure 3 This is the flowchart of step S20 in a data anomaly analysis method for electronic device detection provided by an embodiment of the present invention.

[0120] Further, in step S20, that is, in the step of obtaining the first anomaly index according to the first intelligent driving processing data, the following steps are specifically included:

[0121] S211: Obtain the preset standard - batch sensing data volume, where the duration of the time node interval of the standard - batch sensing data volume is the same as that of the time node interval corresponding to the batch to be compared, the quantity of data collected by the sensors of the standard - batch sensing data volume is the same as that of the batch to be compared, and the types of data collection corresponding to the standard - batch sensing data volume are the same as those of the sensors of the batch to be compared.

[0122] S212: Obtain the data integrity corresponding to the batch to be compared according to the ratio of the quantity of data collected by the sensing data of the batch to be compared to the standard - batch sensing data volume.

[0123] S213: Obtain the degree of data deviation of the sensing data of the batch to be compared during continuous acquisition.

[0124] S214: Obtain the correlation of the difference degree between data corresponding to different data collection types according to the degree of data deviation, and determine data consistency according to the correlation of the difference degree.

[0125] S215: Obtain the first anomaly index according to data integrity and data consistency.

[0126] Figure 4 This is the flowchart of step S20 in another data anomaly analysis method for electronic device detection provided by an embodiment of the present invention.

[0127] Further, in step S20, that is, the step of obtaining the first anomaly index according to the first intelligent driving processing data, the following steps are specifically included:

[0128] S221: Generate a data deviation comparison combination according to the data collection types of the batch to be compared, where each two different data collection types correspond to a data deviation comparison combination.

[0129] S222: Obtain the difference set set of the batch to be compared according to the data deviation comparison combination, where one difference set set corresponds to a monitoring angle of the vehicle.

[0130] S223: Determine the data deviation degree according to the difference set set.

[0131] Figure 5 It is a flowchart in step S20 of another data anomaly analysis method for electronic device detection provided by an embodiment of the present invention.

[0132] Further, in step S20, that is, the step of obtaining the first anomaly index according to the first intelligent driving processing data, the following steps are specifically included:

[0133] S231: Obtain the difference degree correlation between the data corresponding to the data collection types according to the data deviation degree and the monitoring angle of the vehicle.

[0134] S232: Determine the data consistency according to the difference degree correlation between the data corresponding to the data collection types and the number of data deviation comparison combinations.

[0135] Specifically, in each of the above steps for data anomaly analysis of the device data perception layer, it can be understood in combination with the following description.

[0136] In one embodiment, specifically, the data collected every second can be used as a collection batch, and the ratio of the amount of collected data in the current batch to be compared to the amount of collected data in the standard batch is used as the integrity of the data in the current collection batch, denoted as OT i 。

[0137] It can be understood that from the perspective of data integrity, the data in the same batch has been analyzed in detail. However, in the actual data collection process, if a certain sensor is subjected to strong external interference or fails itself, although the integrity of the data in its batch is maintained, significant differences will occur between the data it collects, which will have a certain impact on the subsequent analysis and recognition work. Therefore, it is necessary to carry out a consistency assessment work on the data collected in the same area of the device data perception layer.

[0138] For the consistency evaluation of data in the same batch, in-depth analysis is focused on multiple types of sensors within the same acquisition area. When the external monitoring environment changes, various sensors will all make corresponding responses. Given the differences in the data collected by different sensors, it is not feasible to directly compare different acquisition results to evaluate consistency. Therefore, in the embodiments of the present invention, the consistency of the data is indirectly judged by analyzing the deviation degree of the current batch of data to be compared during continuous acquisition and evaluating the correlation of the difference degrees among various types of data within this batch. Specifically, when the degree of correlation between the data is relatively high, it indicates that the consistency of the data collected within the same area is relatively ideal. Specifically, it can be expressed by the following formula:

[0139]

[0140] In the above formula, i represents the batch of the collected data, and n represents the monitoring angle of the current vehicle. HJ i,n represents the data consistency of the nth monitoring degree of the current ith batch of data. MS n represents the number of sensor types at the current nth monitoring angle. C(MS n , 2) represents the number of pairwise combinations at the nth monitoring angle. p 1,n represents the set of differences in one batch of the monitoring results of the first sensor in the pth combination at the nth monitoring angle. p 2,n represents the set of differences in one batch of the monitoring results of the second sensor in the pth combination at the nth monitoring angle. For the data at any monitoring angle, batch analysis is performed to obtain the differences in the continuous acquisition content of a single sensor within this batch, forming a set of differences. Cov(p 1,n , p 2,n ) represents the covariance of its two sets of differences. represents the standard deviation of the set of differences of p 1,n , represents the standard deviation of the set of differences of p 2,n .

[0141] Furthermore, represents the degree of correlation of the sets of differences of the data of any two sensors at the current arbitrary angle. When the external environment changes, any one sensor at the same angle will receive the signal data from the outside, and the degree of difference between the continuously acquired contents is similar, and for this, the data collected by its single sensor is used to construct a set of differences. By performing pairwise correlation evaluation on the sets of differences within its single batch according to the sensors, the larger the result, the higher the consistency of the sensors at the current single angle. For this, pairwise matching analysis is performed on multiple sensors at one angle within any batch, and then the degree of consistency of its data is obtained.

[0142] UJ iIndicates the degree of consistency of the current i-th batch of monitoring data. MO represents the number of monitoring angles of the current sensor. By averaging the data consistency of all monitoring angles within a batch, the overall data consistency degree of a batch can be obtained.

[0143] Understandably, by analyzing the data of a single batch in the device data perception layer, the integrity degree and consistency of the corresponding batch of data are obtained. When the integrity degree of the single-batch data is relatively high, the corresponding consistency degree also has a relatively good effect, and the data of this batch is considered to have relatively high quality. Subsequently, the evaluation of the overall collected data in the device data perception layer can be obtained by analyzing the overall quality situation and stability degree of all batches of data during the data collection stage.

[0144] Understandably, when the overall data quality is relatively high during the collection process, the abnormal index of the device data perception layer data is relatively low. When the data quality difference within consecutive batches is larger during the collection process, it indicates that the abnormal index of the device data perception layer data is higher at this time. According to the above description, the overall data abnormal index of the device data perception layer is obtained:

[0145]

[0146] In the above formula, FJ i is the set of batch data quality, representing the quality of the i-th batch of data (specifically, it can be represented by a percentage coefficient). UJ i represents the degree of consistency of the current i-th batch of monitoring data. OT i represents the degree of integrity of the current i-th batch of monitoring data. norm represents the normalization process. When the integrity degree of a batch of monitoring data is higher and the data consistency degree is higher, the current batch of data is considered to have higher quality.

[0147] GJ represents the abnormal index of the device data perception layer data. μ FJ represents the quality mean value of the monitoring data in the device data perception layer. That is, by adding FJ i from the i-th to the n-th and then taking the mean of the sum, it can be obtained. M represents the number of batches of monitoring data in the device data perception layer. ΔFJ i represents the difference in the data quality of the i-th batch compared to the previous data quality. For example, when i = 3, then ΔFJ3 represents the difference in the data quality of the 3rd batch compared to ΔFJ2 (i.e., the previous data quality). It means taking the average of the quality differences of the monitoring data for all its batches. Understandably, the larger the result, the greater the difference between the continuous data obtained by the current device data perception layer, and the abnormal index of the data will relatively increase. Finally, the ratio to the data quality average value can be used to obtain the difference degree of the data in the device data perception layer.

[0148] Figure 6 It is a flowchart in step S40 of a data anomaly analysis method for electronic device detection provided by an embodiment of the present invention.

[0149] Further, in step S40, that is, in the step of obtaining the second abnormal index according to the second intelligent driving processed data, the following steps are specifically included:

[0150] S411: Obtain the data delay anomaly index according to the second intelligent driving processed data.

[0151] S412: Obtain the data transmission reliability index according to the second intelligent driving processed data.

[0152] S413; Obtain the second abnormal index according to the data delay anomaly index and the data transmission reliability index.

[0153] Figure 7 It is a flowchart in step S40 of another data anomaly analysis method for electronic device detection provided by an embodiment of the present invention.

[0154] Further, in step S40, that is, in the step of obtaining the second abnormal index according to the second intelligent driving processed data, the following steps are specifically included:

[0155] S421: Obtain the data quality set from the second intelligent driving data, where the data quality set is determined and obtained by the first abnormal index.

[0156] S422; Obtain the data processing time set from the second intelligent driving data, where the data processing time set is used to reflect the data transmission delay.

[0157] S423: Obtain the data delay anomaly index according to the data quality set and the data processing time set.

[0158] Figure 8 It is a flowchart in step S40 of yet another data anomaly analysis method for electronic device detection provided by an embodiment of the present invention.

[0159] Further, in step S40, that is, in the step of obtaining the second abnormal index according to the second intelligent driving processed data, the following steps are specifically included:

[0160] S431: Acquire the vehicle body posture adjustment instruction and vehicle body posture adjustment vector in the data processing layer of the device according to the second intelligent driving processing data.

[0161] S432: Determine the executed vehicle posture adjustment vector according to the vehicle posture adjustment instruction and the vehicle posture adjustment vector.

[0162] S433: Obtain a data transmission reliability index according to the vehicle body posture adjustment instruction, the vehicle body posture adjustment vector, and the executed vehicle body posture adjustment vector.

[0163] Figure 9 This is a flowchart of step S40 of another data anomaly analysis method for electronic device detection provided by an embodiment of the present invention.

[0164] Furthermore, in step S40, i.e., the step of obtaining the second abnormality indicator according to the second intelligent driving processing data, the following steps are specifically included:

[0165] S441: Generate vehicle behavior adjustment data based on the data abnormality result.

[0166] S442: Send the vehicle behavior adjustment data to the device data control layer to generate a vehicle behavior adjustment instruction according to the vehicle behavior adjustment data, and control the vehicle behavior according to the vehicle behavior adjustment instruction.

[0167] Specifically, each step of the above data anomaly analysis for the device data processing layer can be understood in conjunction with the following description.

[0168] In the previous analysis of the first abnormal indicator, we conducted an in-depth study of the data captured by each acquisition device, and based on this, we evaluated the first abnormal indicator displayed by the data of the device data perception layer. It can be understood that the core function of the device data perception layer is to accept diverse data transmitted from the outside world. Once the data is successfully received, it lays a solid foundation for the subsequent in-depth analysis and instruction issuance of the device data processing layer and the device data control layer. It should be noted that, unlike the device data perception layer, the abnormal conditions of the data at the device data processing layer are often manifested in the delay phenomenon of the data processing and conversion process, the differences in the data synchronization process, and the irregular changes in the path device data processing layer.

[0169] In one embodiment, the present invention conducts an in-depth analysis of the time deviation of current data delays to accurately assess data anomalies at the data processing level of data devices. Significant data delays, understandably, reveal potential anomalies at the data processing level of data devices. Furthermore, the consistency of data transmission between various systems significantly impacts the actual performance of intelligent driving control systems.

[0170] In the intelligent driving system, the device data perception layer collects real-time data on the external environment and transmits the collected data to the device data processing layer for vehicle behavior analysis and determination. When the quality of the collected data is high, the overall difference in various types of monitoring data within a continuous time is small, and the data delay is relatively stable when analyzing and planning the vehicle trajectory. However, when the data transmitted by the device data perception layer has low quality within a continuous time, the device data processing layer needs to spend more time analyzing when planning and analyzing the vehicle trajectory, resulting in a relatively large delay.

[0171] In the process of evaluating the data delay difference, it is necessary to comprehensively consider the key factor of the data transmission quality of the device data perception layer. According to research and analysis, there is a clear correlation between data quality and delay: when the data quality reaches a high level, the delay time is usually short; conversely, when the data quality decreases, the delay time increases accordingly. However, it is worth noting that if a large delay is observed under high data quality conditions, this often indicates that there is some abnormal condition in the data. In view of this, a dual index of data delay and data quality is adopted for systematic analysis to accurately calculate the data delay anomaly index. The specific formula can be expressed as follows.

[0172]

[0173] In the above formula, CU represents the delay anomaly index of the current data device data processing layer. FJ i represents the batch data quality set, and YC i represents the set of processing times of batch data in the device data processing layer. Cov(FJ i , YC i ) represents the covariance of its data quality set and the set of processing times of the corresponding data. represents the standard deviation of the batch data quality. represents the standard deviation of the set of processing times of batch data in the device data processing layer.

[0174] Among them, represents the degree of correlation between the current data quality and the data processing time. When the data quality is higher, it is considered that its processing time is relatively lower. When the correlation result of these two sets of data is smaller, it indicates that the delay anomaly of the data device data processing layer is smaller. When the correlation result of the two sets of data is closer to 0, it indicates that the degree of correlation of the current two sets of data is lower, that is, the delay anomaly index of the data device data processing layer is higher.

[0175] In the data processing flow, the device data processing layer first processes the data and outputs specific instructions for vehicle body attitude adjustment based on the analysis and calculation results. Subsequently, these instructions are transmitted to the device data control layer, which further converts them into directly executable vehicle control commands. The vehicle then makes corresponding attitude adjustments according to these commands. In this process, the device data control layer plays a crucial role. It needs to accurately guide the adjustment of the vehicle body based on the instructions of the device data processing layer.

[0176] However, it is worth noting that abnormal situations such as potential failures in the data transmission link or incomplete actuator feedback signals may cause deviations or interruptions in the execution of instructions, thereby resulting in abnormal phenomena at the data level. To effectively address this issue, the present invention comprehensively evaluates the consistency and accuracy of data transmission by analyzing the deviation degree between the actual attitude change of the vehicle body and the expected attitude change of the device data processing layer.

[0177]

[0178] In the above formula, PL represents the current degree of consistency of data transmission. MZ represents the number of vehicle body attitude adjustment instructions issued by the device data processing layer. KZ m represents the vehicle body attitude adjustment vector under the device data processing layer, where the vehicle body attitude adjustment vector refers to the vector by which the vehicle body attitude needs to be adjusted compared to the previous moment. It can be understood that the movement angle of the vehicle body attitude adjustment can be specifically represented by a vector. GH m represents the vehicle body attitude adjustment vector when the actual m-th instruction execution is completed.

[0179] Among them, The cosine similarity between the expected adjustment result of the vehicle body attitude issued by the device data processing layer and the actual vehicle body attitude change result is evaluated. When the result is closer to 1, it indicates a higher current completion degree, that is, a higher degree of consistency of data transmission. For this, the completion situation of all vehicle body attitude adjustment instructions is evaluated, and the average of the results is obtained to obtain the degree of transmission consistency of the device data processing layer.

[0180] In the above process, the device data processing level of the data is deeply analyzed, and two key indicators, namely the data abnormal delay coefficient and the degree of consistency of data transmission, are successfully obtained. When there are relatively high data delay abnormal indicators in the intelligent driving control system, the system will face the risk of being unable to quickly respond to external changes. At the same time, if the degree of consistency in the data transmission process is low, this will lead to an increase in the deviation of the vehicle body attitude adjustment, which may in turn cause a series of problems. Based on the above detailed analysis results, further focus on the device data processing level of the data to obtain the abnormality degree of the current device data processing level. Specifically, it is reflected by the following formula:

[0181]

[0182] In the above formula, CJ represents the data anomaly index of the data processing layer of the data device. PL represents the current degree of consistency of data transmission. CU represents the delay anomaly index of the current data device data processing layer. norm represents normalization processing. When the delay anomaly index of the data device data processing layer is higher and the degree of consistency of data transmission is lower, it is considered that the data anomaly index of the current data device data processing layer is higher.

[0183] In the above process, for the two core links of the intelligent driving control system - data acquisition and data processing, a detailed analysis of data anomaly indexes was carried out. Specifically, focusing on the anomaly of the monitoring data related to electronic devices, the abnormal conditions of these data have a significant impact and potential interference on the safety of vehicle intelligent driving. Therefore, through the two dimensions of data acquisition and data processing respectively, the overall data anomaly index of the current vehicle intelligent driving system was comprehensively evaluated and obtained.

[0184] PJ = norm(CJ + GJ)

[0185] In the above formula, PJ represents the data anomaly index of the current intelligent driving control system. CJ represents the data anomaly index of the data processing layer of the data device. GJ represents the data anomaly index of the device data perception layer. norm represents normalization processing. Specifically, the anomalies of its data acquisition layer and data device data processing layer are evaluated respectively, and the corresponding anomaly indexes are obtained respectively.

[0186] In the present invention, in the process of rigorously constructing the test system of the intelligent driving system, its complex data processing process is scientifically divided into two major modules: the device data perception layer and the device data processing layer. For these two independent data levels, an accurate data flow acquisition strategy is implemented to ensure that all information flows within a single data layer can be accurately captured and stored in a specially designed database. Subsequently, by deeply analyzing the key data stored in the database, the anomaly indexes of the intelligent driving system are comprehensively evaluated, significantly improving the data error detection ability of the intelligent driving.

[0187] A data anomaly analysis system for electronic device detection according to the present invention, as Figure 10 shown, includes the following modules:

[0188] The first data processing module 10 is used to obtain the first intelligent driving processing data from the device data perception layer;

[0189] The second data processing module 20 is used to obtain the first anomaly index according to the first intelligent driving processing data;

[0190] The third data processing module 30 is used to obtain second intelligent driving processing data from the device data processing layer based on the first intelligent driving processing data and the first abnormal index;

[0191] The fourth data processing module 40 is used to obtain a second abnormal index according to the second intelligent driving processing data;

[0192] The fifth data processing module 50 is used to obtain a third abnormal index according to the first abnormal index and the second abnormal index;

[0193] The sixth data processing module 60 is used to determine the data abnormality result of the intelligent driving system according to the third abnormal index.

[0194] Furthermore, the first data processing module 10 is further specifically used for:

[0195] Determine the time node interval of single-batch data collection;

[0196] Within the time node interval, based on time synchronization, collect sensing data obtained by multiple sensors, where the types and quantities of sensor data collection within each time node interval are the same.

[0197] Furthermore, the second data processing module 20 is further specifically used for:

[0198] Obtain the preset standard batch sensing data volume, where the duration of the time node interval of the standard batch sensing data volume is the same as that of the time node interval corresponding to the batch to be compared, where the quantity of sensor data collection of the standard batch sensing data volume is the same as that of the batch to be compared, and the types of data collection corresponding to the standard batch sensing data volume are the same as those of the sensors of the batch to be compared;

[0199] Obtain the data integrity corresponding to the comparison batch according to the ratio of the quantity of sensor data collection of the batch to be compared to the standard batch sensing data volume;

[0200] Obtain the data deviation degree of the sensor data of the batch to be compared during continuous collection;

[0201] Obtain the difference degree correlation between data corresponding to different data collection types according to the data deviation degree, and determine the data consistency according to the difference degree correlation;

[0202] Obtain the first abnormal index according to the data integrity and the data consistency.

[0203] Furthermore, the second data processing module 20 is further specifically used for:

[0204] Generate a data deviation comparison combination according to the data collection types of the batch to be compared, where each two different data collection types correspond to a data deviation comparison combination;

[0205] Obtain the difference set of the batch to be compared according to the data deviation comparison combination, where one difference set corresponds to a monitoring angle of the vehicle;

[0206] Determine the data deviation degree according to the difference set.

[0207] Furthermore, the second data processing module 20 is further specifically configured to:

[0208] Obtain the correlation of the difference degree between the data corresponding to the data collection types according to the data deviation degree and the monitoring angle of the vehicle;

[0209] Determine the data consistency according to the correlation of the difference degree between the data corresponding to the data collection types and the number of data deviation comparison combinations.

[0210] Furthermore, the fourth data processing module 40 is further specifically configured to:

[0211] Obtain the data delay anomaly index according to the second intelligent driving processing data;

[0212] Obtain the data transmission reliability index according to the second intelligent driving processing data;

[0213] Obtain the second anomaly index according to the data delay anomaly index and the data transmission reliability index.

[0214] Furthermore, the fourth data processing module 40 is further specifically configured to:

[0215] Obtain the data quality set from the second intelligent driving data, where the data quality set is determined and obtained by the first anomaly index;

[0216] Obtain the data processing time set from the second intelligent driving data, where the data processing time set is used to reflect the data transmission delay;

[0217] Obtain the data delay anomaly index according to the data quality set and the data processing time set.

[0218] Furthermore, the fourth data processing module 40 is further specifically configured to:

[0219] Obtain the body attitude adjustment instruction and the body attitude adjustment vector in the device data processing layer according to the second intelligent driving processing data;

[0220] Determine the executed body attitude adjustment vector according to the body attitude adjustment instruction and the body attitude adjustment vector;

[0221] Obtain a data transmission reliability index according to a vehicle body attitude adjustment instruction, a vehicle body attitude adjustment vector, and an executed vehicle body attitude adjustment vector.

[0222] Furthermore, the sixth data processing module 60 is further specifically configured to:

[0223] Generate vehicle behavior adjustment data according to the data anomaly result;

[0224] Send the vehicle behavior adjustment data to the device data control layer to generate a vehicle behavior adjustment instruction according to the vehicle behavior adjustment data and control the vehicle behavior according to the vehicle behavior adjustment instruction.

[0225] In the present invention, first, obtain the first intelligent driving processing data from the device data perception layer to detect errors in the data at the device data perception layer level; then, obtain the first anomaly index according to the first intelligent driving processing data, and be able to obtain the first factor that causes data errors at the perception layer level; after that, based on the first intelligent driving processing data and the first anomaly index, obtain the second intelligent driving processing data from the device data processing layer, and on the basis of the first anomaly index, obtain the second intelligent driving processing data with data relevance from the first intelligent driving processing data; after that, obtain the second anomaly index according to the second intelligent driving processing data, and on the basis of linking the first anomaly index, obtain the factor that causes data errors in the device data processing layer more accurately than directly obtaining the second intelligent driving data; finally, obtain the third anomaly index according to the first anomaly index and the second anomaly index, and determine the data anomaly result of the intelligent driving system according to the third anomaly index, which can comprehensively consider the influence of data error detection of multiple factors in intelligent driving, thereby significantly improving the data error detection ability of intelligent driving.

[0226] The present invention also provides a computer-readable storage medium, which stores computer-readable instructions. When the computer-readable instructions are executed by a processor, the data anomaly analysis method for detecting an electronic device as described in the embodiment is implemented.

[0227] The present invention also provides a computer device. Figure 11 It is a schematic diagram of a computer device in an embodiment of the present invention. As Figure 11 shown, the computer device 110 includes a processor 111, a memory 112, and computer-readable instructions 113 stored in the memory 112 and executable on the processor 111. When the processor 111 executes the computer-readable instructions 113, each step of the data anomaly analysis method for detecting an electronic device is implemented.

[0228] Exemplarily, the computer-readable instructions 113 may be divided into one or more modules / units, which are stored in the memory 112 and executed by the processor 111 to implement the present invention. One or more modules / units may be a series of computer-readable instruction segments capable of performing specific functions, and these instruction segments are used to describe the execution process of the computer-readable instructions 113 in the computer device 110.

[0229] The computer device 110 may be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The computer device may include, but is not limited to, a processor 111 and a memory 112. Those skilled in the art can understand that Figure 11 merely examples of the computer device 110, which do not constitute a limitation on the computer device 110, may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, the computer device may also include input / output devices, network access devices, a bus, etc.

[0230] The so-called processor 111 may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits

[0231] (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0232] The memory 112 may be an internal storage unit of the computer device 110, such as the hard disk or memory of the computer device 110. The memory 112 may also be an external storage device of the computer device 110, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the computer device 110. Further, the memory 112 may also include both the internal storage unit and the external storage device of the computer device 110. The memory 112 is used to store computer-readable instructions and other programs and data required by the computer device. The memory 112 may also be used to temporarily store data that has been output or is to be output.

[0233] Embodiments of the present invention can acquire and process relevant data based on artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to obtain the best results.

[0234] Artificial intelligence basic technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, and mechatronics. Artificial intelligence software technologies mainly include several major directions such as computer vision technology, robotics, biometric technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0235] In embodiments of the present invention, the server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, Content Delivery Network (CDN), and big data and artificial intelligence platforms.

[0236] In addition, in each embodiment of the present invention, each functional unit can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0237] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above method embodiments of the present invention, it can also be completed by instructing relevant hardware through computer-readable instructions. The computer-readable instructions can be stored in a computer-readable storage medium. When the computer-readable instructions are executed by a processor, the steps of the above method embodiments can be implemented. Among them, the computer-readable instructions include computer-readable instruction codes, and the computer-readable instruction codes can be in the form of source code, object code, executable files, or some intermediate forms. The computer-readable medium can include: any entity or device that can carry the computer-readable instruction code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0238] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above.

[0239] It should be noted that: the above sequence of the embodiments of the present invention is only for description and does not represent the superiority or inferiority of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0240] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments.

Claims

1. A method for analyzing data anomalies for electronic device detection, characterized in that, The method includes: Obtaining first intelligent driving processing data from the device data perception layer; Obtaining a first anomaly metric based on the first intelligent driving processing data; Based on the first intelligent driving processing data and the first anomaly metric, obtaining second intelligent driving processing data from the device data processing layer; Obtaining a second anomaly metric based on the second intelligent driving processing data; Obtaining a third anomaly metric based on the first anomaly metric and the second anomaly metric; Determining a data anomaly result of the intelligent driving system based on the third anomaly metric; The obtaining of the first intelligent driving processing data from the device data perception layer includes the following steps: Determining a single-batch data collection time node interval; Within the time node interval, collecting sensing data obtained by multiple sensors based on time synchronization, where the types and quantities of data collected by the sensors within each time node interval are the same; The obtaining of the first anomaly metric based on the first intelligent driving processing data includes the following steps: Obtaining a preset standard batch sensing data volume, where the duration of the time node interval of the standard batch sensing data volume is the same as that of the time node interval corresponding to the batch to be compared, where the quantity of data collected by the sensors of the standard batch sensing data volume is the same as that of the batch to be compared, and where the types of data collection corresponding to the standard batch sensing data volume are the same as those of the sensors of the batch to be compared; Obtaining the data integrity corresponding to the batch to be compared based on the ratio of the quantity of data collected by the sensing data of the batch to be compared to the standard batch sensing data volume; Obtaining the degree of data deviation of the sensing data of the batch to be compared during continuous collection; Obtaining the correlation of the degree of difference between the data corresponding to different types of data collection based on the degree of data deviation, and determining data consistency based on the correlation of the degree of difference; Obtaining the first anomaly metric based on the data integrity and the data consistency.

2. The data anomaly analysis method for electronic device detection according to claim 1, wherein The obtaining of the degree of data deviation of the sensing data of the batch to be compared during continuous collection includes the following steps: Generating a data deviation comparison combination based on the types of data collection of the batch to be compared, where each two different types of data collection correspond to one data deviation comparison combination; Obtaining a difference set corresponding to the batch to be compared based on the data deviation comparison combination, where one difference set corresponds to one monitoring angle of the vehicle; Determining the degree of data deviation based on the difference set.

3. The data anomaly analysis method for electronic device detection according to claim 2, wherein The obtaining of the correlation of the degree of difference between the data corresponding to different types of data collection based on the degree of data deviation, and determining data consistency based on the correlation of the degree of difference includes the following steps: Obtaining the correlation of the degree of difference between the data corresponding to the types of data collection based on the degree of data deviation and the monitoring angle of the vehicle; Determining the data consistency based on the correlation of the degree of difference between the data corresponding to the types of data collection and the quantity of the data deviation comparison combination.

4. The data anomaly analysis method for electronic device detection according to claim 1, wherein Obtaining a second anomaly metric based on the second intelligent driving processed data includes the following steps: Obtaining a data latency anomaly index based on the second intelligent driving processed data; Obtaining a data transmission reliability index based on the second intelligent driving processed data; Obtaining the second anomaly metric based on the data latency anomaly index and the data transmission reliability index.

5. The data anomaly analysis method for electronic device detection according to claim 4, wherein Obtaining a data latency anomaly index based on the second intelligent driving processed data includes the following steps: Obtaining a data quality set from the second intelligent driving processed data, where the data quality set is determined and obtained by the first anomaly metric; Obtaining a data processing time set from the second intelligent driving processed data, where the data processing time set is used to reflect data transmission latency; Obtaining the data latency anomaly index based on the data quality set and the data processing time set.

6. The data anomaly analysis method for electronic device detection according to claim 4, wherein Obtaining a data transmission reliability index based on the second intelligent driving processed data includes the following steps: Obtaining a vehicle body attitude adjustment instruction and a vehicle body attitude adjustment vector in the device data processing layer based on the second intelligent driving processed data; Determining an executed vehicle body attitude adjustment vector based on the vehicle body attitude adjustment instruction and the vehicle body attitude adjustment vector; Obtaining the data transmission reliability index based on the vehicle body attitude adjustment instruction, the vehicle body attitude adjustment vector, and the executed vehicle body attitude adjustment vector.

7. The data anomaly analysis method for electronic device detection according to claim 1, wherein After determining the data anomaly result of the intelligent driving system based on the third anomaly metric, the method further includes the following steps: Generating vehicle behavior adjustment data based on the data anomaly result; Sending the vehicle behavior adjustment data to the device data control layer to generate a vehicle behavior adjustment instruction based on the vehicle behavior adjustment data and controlling vehicle behavior according to the vehicle behavior adjustment instruction.

8. A data anomaly analysis system for electronic device detection, the system is used to implement the method described in claim 1, characterized in that, The system includes: A first data processing module for obtaining first intelligent driving processed data from the device data perception layer; A second data processing module for obtaining a first anomaly metric based on the first intelligent driving processed data; A third data processing module for obtaining second intelligent driving processed data from the device data processing layer based on the first intelligent driving processed data and the first anomaly metric; A fourth data processing module for obtaining a second anomaly metric based on the second intelligent driving processed data; A fifth data processing module for obtaining a third anomaly metric based on the first anomaly metric and the second anomaly metric; A sixth data processing module for determining the data anomaly result of the intelligent driving system based on the third anomaly metric.

Images