Vehicle safety management method and system based on cloud computing

Abstract

The invention relates to the technical field of vehicle safety management, in particular to a vehicle safety management method and system based on cloud computing. The method comprises the following steps: acquiring state data of a current running vehicle in real time; respectively calculating Euclidean distances between the state data and the plurality of clustering clusters; if the minimum Euclidean distance value is greater than a set threshold value, the state data is abnormal, and an alarm is given; according to the scheme of the invention, timely and safe management can be carried out on the vehicle.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle safety management, and more specifically, to a vehicle safety management method and system based on cloud computing. Background Art

[0002] With the rapid development of intelligent transportation systems and vehicle electronic technology, vehicle safety management has become an increasingly important issue in traffic management and road safety.

[0003] In this context, by introducing a cloud computing-based vehicle safety management system, companies can obtain and analyze comprehensive information about vehicles in real time, improve the immediacy of vehicle maintenance, and thus significantly reduce the accident rate and improve road safety. This transformation is not only in line with the trend of intelligent transportation development, but also lays a solid foundation for future driverless and intelligent traffic management.

[0004] In the prior art, for example, the patent document for a vehicle integrated management system based on cloud computing is disclosed in the authorization announcement number CN104732353B, in which the safety management is to analyze the driving safety level of the current vehicle according to the predicted results of the vehicle driving state and the detection results of surrounding targets as well as the positioning information of other vehicles in the cloud network, and give the result with reference to the preset level, and send it to the vehicle safety management unit.

[0005] The above scheme only determines the safety of the vehicle based on the current driving status and the preset level, and the preset level is generally set based on experience. Different vehicles have different judgment criteria due to differences in driving times, mileage, etc. Therefore, using a unified standard to judge different vehicles may be inaccurate, which in turn leads to inaccurate analysis of vehicle safety data. Summary of the invention

[0006] The purpose of the present invention is to propose a vehicle safety management method and system based on cloud computing to solve the problem in the prior art that vehicle safety data cannot be accurately analyzed, resulting in an inability to accurately determine whether the vehicle is safe; to this end, the present invention provides solutions in the following two aspects.

[0007] In a first aspect, the present invention provides a vehicle safety management method based on cloud computing, comprising: Obtain the status data of the currently traveling vehicle and the normalized new status data in real time; Calculate the Euclidean distance between the new state data and multiple clusters respectively; if the minimum Euclidean distance is greater than the set threshold, the state data is abnormal and an alarm is issued; The clusters are obtained by clustering the normalized historical status data of the vehicle at different driving times using a K-means algorithm; each historical status data includes multiple items of data; the same items of data at all times form a sequence from small to large; Among them, the distance in the clustering process is positively correlated with the difference between any two historical state data and the corresponding weight; the weight is the product of the impact sensitivity and importance of the corresponding item sequence; the importance is positively correlated with the fluctuation of each data in the corresponding sequence and the fluctuation of the safety index corresponding to each data; the safety index represents the speed fluctuation degree of the vehicle during each driving; Impact sensitivity for: ; is the extreme value of safety index, , Respectively The range of the item sequence, the number of data, , Respectively Item in the sequence , data, , , Respectively Item in the sequence The safety index, abnormality level, The security index of the data; Setting Thresholds for: ; To set the multiple, To obtain the average value of the Euclidean distance between all historical status data and the cluster center in the corresponding cluster cluster.

[0008] In the above scheme, the weight of each data is determined by comprehensively considering the correlation between each data and the degree of speed change of the vehicle during driving and the sensitivity of each data to the speed change during driving, and the difference of each data is weighted to finally obtain the distance between any two historical status data of driving, and clustering is performed, so that the clustering algorithm can better consider the impact of each data on the importance of vehicle safety, thereby making the classification of vehicle historical data more accurate; further, the present invention can make the analysis of vehicle safety data more accurate by comparing the current status data with the historical classified data of the vehicle, and improve the accuracy of the judgment of vehicle data during current driving; that is, compared with the conventional K-means clustering algorithm (when clustering, the distance measurement is directly based on the Euclidean distance between data points, without considering the importance of each data to vehicle safety and the sensitivity of influence), the scheme of the present invention improves the accuracy of the analysis of subsequent real-time vehicle status data.

[0009] At the same time, by using the average of the distances from the data in multiple clusters in the historical data of the vehicle to the cluster center to determine the set threshold, the accuracy of the vehicle status data judgment can be improved.

[0010] Optionally, the status data includes but is not limited to vehicle fuel level, average tire pressure, average vehicle speed, total years of vehicle use, frequency of brake use, and whether an accident has occurred.

[0011] The above scheme can provide more comprehensive data support for subsequent vehicle safety analysis by integrating data from multiple angles during the vehicle's driving process.

[0012] Optionally, the importance for: ; For the The first trip corresponds to Item data, , Respectively The mean and range of the item sequence, For the Safety index during driving, , is the range and average value of the safety index, and n is the historical driving times of the vehicle.

[0013] The above scheme can determine the importance of the corresponding data by combining the fluctuation of each data and the fluctuation of the safety index corresponding to each data.

[0014] Optionally, the distance for: ; Where N is the total number of historical status data items, For the The first trip corresponds to Item data, For the The first trip corresponds to Item data, For the The weight of the data item.

[0015] Since each data item has a different impact on the vehicle safety index, it is necessary to determine the weights of different data items to obtain a more accurate distance and perform more accurate clustering of the vehicle's historical status data.

[0016] Optionally, the safety index for: ; in, Indicates The extreme difference of the speed sequence during each trip, Indicates The speed sequence of the first driving Speed ​​value, Indicates The average value of the speed series during each trip, is an exponential function with the natural constant e as base, For the The total number of speeds in the speed sequence during each trip.

[0017] Optionally, the abnormality degree is obtained by performing abnormality detection on the safety index data using the LOF algorithm; the safety index data includes a plurality of safety indicators consisting of various data and corresponding safety indexes.

[0018] Optionally, the method for normalizing the state data includes maximum and minimum value normalization.

[0019] In a second aspect, a vehicle safety management system based on cloud computing includes: processor; A memory stores computer instructions for vehicle safety management based on cloud computing. When the computer instructions are executed by the processor, the system executes the above-mentioned vehicle safety management method based on cloud computing.

[0020] The beneficial effects of the present invention are: The solution of the present invention determines the experience data of the vehicle in its historical operation by analyzing the importance of each data in the historical status data of the vehicle, and compares the current status data with the vehicle's own experience data, so as to determine whether the current driving data of the vehicle is abnormal, thereby improving the accuracy of the analysis of the vehicle status data. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein: Figure 1 A flowchart schematically shows a method for managing vehicle safety based on cloud computing in this embodiment; Figure 2 The structural block diagram of a vehicle safety management system based on cloud computing in this embodiment is schematically shown. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0023] Specifically, taking a certain vehicle as an example, a vehicle safety management method based on cloud computing in this embodiment is introduced. Figure 1 As shown, the following steps are included: Step S1, obtaining the status data of the current driving vehicle in real time.

[0024] The safety management data of the current vehicle collected in this embodiment includes but is not limited to status data, wherein the status data includes multiple data, specifically vehicle fuel level, average tire pressure, average vehicle speed, total years of vehicle use, frequency of brake use, and whether an accident has occurred.

[0025] Specifically, during the driving process of the vehicle, the corresponding sensors are used to collect data such as the vehicle's fuel level (battery level), tire pressure, and driving speed; the total years of vehicle use are obtained based on the vehicle purchase date; and the frequency of vehicle brake use is monitored based on the brake system.

[0026] It should be noted that the above-mentioned average tire pressure and average vehicle speed are used to characterize the status data of the entire vehicle driving process; illustratively, after the vehicle has been driving for two hours, the driving speed and tire pressure are collected by setting the collection frequency, then, from the start of driving to the current moment, the present embodiment calculates the average tire pressure and the average driving speed to obtain partial status data of the vehicle driving.

[0027] In this embodiment, the state data is also normalized to obtain normalized new state data, wherein the normalization method is the maximum and minimum value method.

[0028] Step S2, respectively calculating the distances between the current state data and a plurality of clusters.

[0029] The multiple clusters in this embodiment are obtained by clustering the normalized historical status data of the vehicle at different driving times using a K-means algorithm.

[0030] Specifically, the process of clustering the acquired historical status data of the vehicle at different driving times using the K-means algorithm is as follows: First, multiple historical status data of the current vehicle are obtained and normalized respectively to obtain normalized historical status data, and the K value for clustering is set.

[0031] Specifically, each item of historical status data from the beginning to the end of each vehicle operation is obtained based on big data, including vehicle fuel (electricity), average tire pressure, average driving speed, frequency of brake use, total years of vehicle use and other data.

[0032] In this embodiment, the vehicle The status data of the first driving Item data is recorded as , the total number of historical driving times of the vehicle is recorded as , the total number of data items in each historical state data is recorded as .

[0033] The same data items under all driving times constitute a collection sequence, and the data in the collection sequence are sorted from small to large to obtain a sorted sequence. It should be noted that the number of the collection sequence and the sorted sequence is equal, only the arrangement of the data is different.

[0034] Secondly, K historical state data are randomly selected as the initial centers, the distance from each historical state data to each initial center is calculated, and each data point is assigned to the cluster corresponding to the centroid with the smallest distance.

[0035] Then, the cluster centers of the clusters are updated. Specifically, the cluster centers of the clusters are calculated based on all historical state data in each cluster to update the initial centers.

[0036] Finally, the distance from all historical state data to each cluster center is calculated again, and the clusters are redistributed according to the distance between each historical state data and the cluster center. This iteration is repeated until the cluster center no longer changes, and the clustering of the historical state data is completed.

[0037] The above-mentioned process of obtaining the medium distance includes steps S21 to S24, specifically: Step S21, calculate the safety index of the vehicle at each driving and the importance of each data to the vehicle safety. The safety of the vehicle during driving is mainly reflected in the change of speed. If the speed of the vehicle is relatively stable during a driving process, it means that the vehicle is relatively safe during this driving process and the overall driving state does not fluctuate too much; on the contrary, if the speed changes dramatically during the driving process, it means that the driving is not stable and safety problems may occur. Therefore, in this embodiment, the safety index of the vehicle is determined by the speed change of the vehicle at each driving.

[0038] For example, from the beginning to the end of each vehicle operation, the preset data collection frequency is 5s, and the vehicle speed data is collected every 5s to obtain the vehicle speed data at the first The speed sequence from the beginning to the end of the trip is recorded as , the total number of speeds contained in it is recorded as , among which The speed value is recorded as , calculate the vehicle Safety index during driving.

[0039] In one embodiment, the safety index is: ; in, Indicates Safety index during driving, Indicates The extreme difference of the speed sequence during each trip, Indicates The first speed sequence during the first trip Speed ​​value, Indicates The average value of the speed series of each vehicle operation, It is an exponential function with the natural constant e as its base.

[0040] The range is the difference between the maximum speed value and the minimum speed value in the speed sequence.

[0041] It should be noted that for any time in the vehicle's historical driving, it is necessary to obtain its safety index based on its speed change, that is, each time the vehicle drives, it corresponds to a safety index, and driving n times corresponds to n safety indexes.

[0042] In one embodiment, according to Data and security index, get the Importance of item data: ; in, Indicates The importance of the data item, Indicates The first trip corresponds to Item data, Indicates The average value of the collection sequence (or sorted sequence), Indicates The range of the item collection sequence (or sorted sequence), Indicates Safety index during driving, Represents the average value of all safety index data, It represents the extreme value of safety index, and n is the historical driving times of the vehicle.

[0043] For the importance formula, Indicates The first trip The difference between the item data and the average value; Indicates The difference between the safety index of the first trip and the average safety index, multiplying the two differences can better represent the The correlation between the data and the safety index, that is, The importance of the data to the safety index.

[0044] The reason for obtaining the importance of each item of historical status data to vehicle safety is that different items of data have different effects on vehicle safety. By obtaining the relevance of each item of data to vehicle safety, the importance of different items of data can be determined. That is, if the correlation between any item of data and vehicle safety is higher, the weight of the data should be appropriately increased in the process of clustering through distance measurement, otherwise the weight of the data should be reduced.

[0045] Step S22, calculating the sensitivity of each data item to vehicle safety.

[0046] Among them, for any data in the historical status data, the greater the impact of a certain degree of fluctuation on the safety index, the more obvious the impact of the data on the change of the safety index is. Therefore, the impact sensitivity of each data is obtained according to the relative change of the impact of each data on the safety index.

[0047] Specifically, the Arrange the data in ascending order and get the The sorted sequence of item data Obtain the impact sensitivity of each data item based on the corresponding relationship between the fluctuation of each data item and the safety index. for: ; in, is the extreme value of safety index, , Respectively The range of the item sequence, the number of data, , Respectively Item in the sequence , data, , , Respectively Item in the sequence The safety index, abnormality level, The security index of the data.

[0048] Among them, The number of data in the item sequence It is equal to the vehicle's historical driving times n.

[0049] The above abnormality degree is calculated by LOF algorithm. All data in the item sequence are detected for anomalies. Since the LOF (Local Outlier Factor) algorithm is an existing technology, it will not be described here.

[0050] As the most preferred implementation, for any data, the reliability of the data itself may be low due to special circumstances, so it is necessary to perform anomaly detection on the safety index data composed of the data and the safety index to obtain the degree of anomaly and improve the reliability of calculation. All data in the item sequence and the corresponding safety index constitute the The safety index data is analyzed by LOF algorithm. Detect anomalies in the security indicator data and obtain the Item in the sequence The degree of abnormality of the data.

[0051] It should be noted that the above The safety index data includes multiple safety indicators consisting of various data and corresponding safety indexes.

[0052] in Indicates the extreme and first The larger the ratio is, the larger the value of the numerator is relative to the denominator. It is the ratio of the difference between the two security indexes corresponding to the two adjacent data in the sorted sequence to the difference between the two adjacent data. This ratio can reflect the The degree to which the gap between two adjacent data in the item sequence causes the safety index data to change. That is, when the gap between the two safety indexes corresponding to two adjacent data is fixed, the smaller the gap between the two adjacent data, The larger the value of The greater the sensitivity of the item data to the safety index data.

[0053] The above impact sensitivity represents the magnitude of the impact of the change in each data on the security index according to the change in the security index corresponding to the change in the data.

[0054] At the same time, the formula It can reduce the reference degree of sensitivity of data with lower reliability to influence.

[0055] It should be noted that the importance represents the correlation between each data and the safety index data, while the impact sensitivity analyzes the degree of change in the safety index data caused by the change of each data. Therefore, in the process of weighting the distance measurement of each data, it is necessary to comprehensively consider the importance and impact sensitivity of each data.

[0056] Step S23, calculating the weight of each item of data.

[0057] Specifically, the product of the importance and impact sensitivity of each data item is used as the weight of the data item, that is, The weight of the item data is: , in, For the The weight of the data item, Indicates The impact sensitivity of the data item, Indicates Step S24: weight the difference between the corresponding items of data in any two historical state data using the weight to obtain the distance.

[0058] For example, when When the historical status data corresponding to the first trip is the initial center or cluster center, The distance from the historical state data of the first trip to the initial center (or cluster center) for: ; Where N is the total number of historical status data items, For the The first trip corresponds to Item data, For the The first trip corresponds to Item data.

[0059] In the above process of clustering vehicle safety data by K-Means clustering algorithm, since each data has different impact on the vehicle safety index, it is necessary to weight the distance measurement between any two driving historical status data accordingly to obtain a more accurate distance measurement, so as to cluster the vehicle's historical status data more accurately.

[0060] After obtaining multiple clusters, in this embodiment, the Euclidean distances between the state data of the current driving vehicle and the cluster centers of the multiple clusters need to be calculated respectively.

[0061] Step S3: When the minimum distance is greater than a set threshold, it is considered that the vehicle data is abnormal and an early warning is issued.

[0062] In this embodiment, the minimum value of the Euclidean distance between the current state data and the cluster center of each cluster is selected as the evaluation value of the current state data.

[0063] When the minimum distance value is greater than the set threshold, it proves that the current state data may be abnormal.

[0064] In one embodiment, the size of the threshold can be determined according to actual conditions.

[0065] Of course, as another implementation method, setting a threshold The size is: ;in, To set the multiple, To obtain the average value of the Euclidean distance between all data points and the cluster center in their corresponding clusters.

[0066] The multiple is set to 1.3 times, and of course it can be adjusted according to actual conditions.

[0067] In this embodiment, when the distance between the minimum distance value and the nearest cluster center is greater than a set threshold, it is considered that the current vehicle safety data is abnormal, requiring timely warning and timely inspection or maintenance of the vehicle.

[0068] At the same time, as the historical status data of the vehicle increases, the set threshold may also change accordingly.

[0069] The solution of the present invention improves the accuracy of the analysis of the subsequent vehicle status data acquired in real time by analyzing the importance of each item of data in the vehicle status data.

[0070] The present invention also provides a vehicle safety management system based on cloud computing. Figure 2 As shown, the system includes a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a vehicle safety management method based on cloud computing according to the present invention is implemented.

[0071] The management system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and the configuration and functions of these components are known in the art, so they will not be described in detail here.

[0072] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of a device or accessible or connectable to a device. Any application or module described in the present invention may be implemented using computer-readable / executable instructions that may be stored or otherwise maintained by such a computer-readable medium.

[0073] In the description of this specification, “plurality” means at least two, such as two, three or more, etc., unless otherwise clearly and specifically defined.

[0074] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

Claims

1. A vehicle safety management method based on cloud computing, characterized in that: include: Obtain the status data of the currently traveling vehicle and the normalized new status data in real time; Calculate the Euclidean distance between the new state data and multiple clusters respectively; if the minimum Euclidean distance is greater than the set threshold, the state data is abnormal and an alarm is issued; The clusters are obtained by clustering the normalized historical status data of the vehicle at different driving times using a K-means algorithm; each historical status data includes multiple items of data; the same items of data at all times form a sequence from small to large; The distance in the clustering process is positively correlated with the difference between any two historical state data and the corresponding weight; the weight is the product of the impact sensitivity and importance of the corresponding item sequence; the importance is positively correlated with the fluctuation of each data in the corresponding sequence and the fluctuation of the safety index corresponding to each data; the safety index represents the speed fluctuation degree of the vehicle during each driving; the impact sensitivity for: ; is the extreme value of safety index, , Respectively The range of the item sequence, the number of data, , Respectively Item in the sequence , data, , , Respectively Item in the sequence The safety index, abnormality level, The security index of the data; Setting Thresholds for: ; To set the multiple, To obtain the average value of the Euclidean distance between all historical status data and the cluster center in the corresponding cluster cluster.

2. The vehicle safety management method based on cloud computing according to claim 1, characterized in that: The status data includes, but is not limited to, the vehicle's oil level, average tire pressure, average vehicle speed, total years of vehicle use, frequency of brake use, and whether an accident has occurred.

3. The vehicle safety management method based on cloud computing according to claim 1, characterized in that: The importance for: ; For the The first trip corresponds to Item data, , Respectively The mean and range of the item sequence, For the Safety index during driving, , is the range and average value of the safety index, and n is the historical driving times of the vehicle.

4. The vehicle safety management method based on cloud computing according to claim 3 is characterized in that: The distance for: ； Where N is the total number of historical status data items, For the The first trip corresponds to Item data, For the The first trip corresponds to Item data, For the The weight of the data item.

5. The vehicle safety management method based on cloud computing according to claim 4 is characterized in that: The safety index for: ; in, Indicates The extreme difference of the speed sequence during each trip, Indicates The first speed sequence during the first trip Speed ​​value, Indicates The average value of the speed series during each trip, is an exponential function with the natural constant e as base, For the The total number of speeds in the speed sequence during each trip.

6. The vehicle safety management method based on cloud computing according to claim 1, characterized in that: The abnormality degree is obtained by performing abnormality detection on the safety index data using the LOF algorithm; the safety index data includes a plurality of safety indexes consisting of various data and corresponding safety indexes.

7. The vehicle safety management method based on cloud computing according to claim 1, characterized in that: The method for normalizing the state data includes maximum and minimum value normalization.

8. A vehicle safety management system based on cloud computing, characterized in that: include: processor; A memory storing computer instructions for cloud computing-based vehicle safety management, wherein when the computer instructions are executed by the processor, the system executes a cloud computing-based vehicle safety management method according to any one of claims 1-7.

Images