A method and device for handling abnormality of vehicle sensor

Abstract

The embodiment of the present invention provides a method and device for handling vehicle sensor anomalies, the method comprising: obtaining vehicle sensor data collected within a target time period; for each sub-time period within the target time period, combining the vehicle sensor data collected within the sub-time period with the vehicle sensor data collected within other sub-time periods, performing an anomaly analysis; and feeding back the anomaly analysis result of the vehicle sensor within the target time period to a user. Through the embodiment of the present invention, it is possible to analyze vehicle sensor anomalies in advance in combination with the collected vehicle sensor data, avoiding the feedback of vehicle sensor anomalies only by lighting up a fault light after the vehicle sensor has failed, thereby ensuring vehicle driving safety.

Description

Technical Field

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

[0002] At present, vehicles are usually equipped with a large number of sensors. Vehicle sensors can be divided into two categories: environmental monitoring and body perception. Environmental monitoring sensors are used to detect and perceive the surrounding environment. They are necessary sensors for realizing autonomous driving. Body perception sensors are used to obtain vehicle sensor data, such as tire pressure, oil pressure, vehicle speed, etc. They are basic sensors necessary to maintain normal, stable and safe driving of the car, and are widely used in engine, chassis, body and other systems.

[0003] In the prior art, usually after a vehicle sensor has failed, a corresponding fault light is turned on on the vehicle dashboard to prompt the user to repair the sensor in time. However, if the user needs to drive to a repair shop or urgently needs the vehicle or is in transit, he or she may continue to drive the vehicle after the vehicle sensor has failed, which may affect driving safety during the driving process. Summary of the invention

[0004] In view of the above problems, a method and device for handling abnormality of a vehicle sensor is proposed to overcome the above problems or at least partially solve the above problems, which may include:

[0005] A method for handling an abnormality of a vehicle sensor, the method may include:

[0006] Obtain vehicle sensor data collected within a target time period;

[0007] For each sub-time period within the target time period, combining the vehicle sensor data collected in the sub-time period with the vehicle sensor data collected in other sub-time periods, performing anomaly analysis;

[0008] Feedback to users the abnormal analysis results of vehicle sensors during the target time period.

[0009] Optionally, for each sub-time period within the target time period, combining the vehicle sensor data collected in the sub-time period with the vehicle sensor data collected in other sub-time periods, performing anomaly analysis may include:

[0010] For each sub-time period within the target time period, determining an average deviation value between the vehicle sensor data collected in the sub-time period and the vehicle sensor data collected in other sub-time periods;

[0011] According to the average deviation value, anomaly analysis is performed.

[0012] Optionally, the vehicle sensor data includes sensor voltage data. Before determining, for each sub-time period within the target time period, an average deviation value between the vehicle sensor data collected in the sub-time period and the vehicle sensor data collected in other sub-time periods, the following may also be included:

[0013] Determine an average voltage value of each sub-time period according to the sensor voltage data collected in each sub-time period within the target time period;

[0014] For each sub-time period within the target time period, determining an average deviation value between vehicle sensor data collected in the sub-time period and vehicle sensor data collected in other sub-time periods may include:

[0015] For each sub-time period within the target time period, determine a deviation value of a first average voltage value of the sub-time period and a second average voltage value of other sub-time periods;

[0016] Based on the multiple deviation values, an average deviation value is determined.

[0017] Optionally, after determining the average voltage value of each sub-time period according to the sensor voltage data collected in each sub-time period within the target time period, the method may further include:

[0018] According to the vehicle gateway ID and the vehicle sensor ID, the average voltage value of each sub-time period is grouped and stored as an array type.

[0019] Optionally, based on the average deviation value, an abnormality analysis may include:

[0020] Determine a target deviation value from multiple deviation values;

[0021] When the difference between the average deviation value and the target deviation value is greater than the difference threshold, it is determined that an abnormality exists in the sub-time period.

[0022] Optionally, the target deviation value may be a median value among multiple deviation values.

[0023] Optionally, before performing abnormality analysis for each sub-time period within the target time period, combining the vehicle sensor data collected in the sub-time period with the vehicle sensor data collected in other sub-time periods, the following may also be included:

[0024] Data filtering and / or data filling are performed on the vehicle sensor data collected within a target time period.

[0025] A vehicle sensor abnormality processing device, the device may include:

[0026] A vehicle sensor data acquisition module is used to acquire vehicle sensor data collected within a target time period;

[0027] An anomaly analysis module, for performing an anomaly analysis for each sub-time period within the target time period, combining the vehicle sensor data collected within the sub-time period with the vehicle sensor data collected within other sub-time periods;

[0028] The abnormal analysis result feedback module is used to feedback the abnormal analysis results of the vehicle sensor in the target time period to the user.

[0029] An electronic device includes a processor, a memory, and a computer program stored in the memory and capable of running on the processor. When the computer program is executed by the processor, the above-mentioned vehicle sensor abnormality processing method can be implemented.

[0030] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned vehicle sensor exception handling method can be implemented.

[0031] The embodiments of the present invention have the following advantages:

[0032] In an embodiment of the present invention, by acquiring vehicle sensor data collected within a target time period, for each sub-time period within the target time period, an abnormality analysis is performed in combination with the vehicle sensor data collected within the sub-time period and the vehicle sensor data collected within other sub-time periods, and the abnormality analysis results of the vehicle sensors in the target time period are fed back to the user, thereby achieving early analysis of vehicle sensor abnormalities in combination with the collected vehicle sensor data, avoiding feedback of vehicle sensor abnormalities only by lighting up a fault light after the vehicle sensor has failed, and ensuring vehicle driving safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solution of the present invention, the accompanying drawings required for use in the description of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0034] Figure 1 It is a flowchart of the steps of a method for handling an abnormality of a vehicle sensor provided by an embodiment of the present invention;

[0035] Figure 2 is a flowchart of another method for handling an abnormality of a vehicle sensor provided by an embodiment of the present invention;

[0036] Figure 3 is a flowchart of another method for handling an abnormality of a vehicle sensor provided by an embodiment of the present invention;

[0037] Figure 4is a schematic diagram of an abnormality handling example of a vehicle sensor provided by an embodiment of the present invention;

[0038] Figure 5 The present invention is a structural block diagram of an abnormality processing device for a vehicle sensor provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0039] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0040] Reference Figure 1 , shows a flowchart of a method for handling an abnormality of a vehicle sensor provided by an embodiment of the present invention, which may specifically include the following steps:

[0041] Step 101, obtaining vehicle sensor data collected within a target time period.

[0042] Among them, the vehicle sensor data may include sensor voltage data.

[0043] In the vehicle, a network for communicating with the Internet of Vehicles can be deployed, such as communicating through a SIM card. After obtaining the vehicle sensor data, the vehicle can send the vehicle sensor data to the Internet of Vehicles platform through the network, and then store the vehicle sensor data in a relational database (such as a postgresql database).

[0044] For data stored in a relational database, a data acquisition tool (such as the data acquisition tool can be a sqoop tool) can be used to filter it to obtain subsequent usable data, such as filtering out sensor voltage data from vehicle sensor data, and then importing the filtered data into a big data platform for subsequent big data analysis in the big data platform.

[0045] In one example, the vehicle may upload sensor data to the vehicle network according to a preset duration, such as 1 hour.

[0046] Step 102 : For each sub-time period within the target time period, an abnormality analysis is performed by combining the vehicle sensor data collected in the sub-time period with the vehicle sensor data collected in other sub-time periods.

[0047] In the big data platform, anomaly analysis can be performed according to a target time period of fixed length, such as a week or a month. The target time period can be composed of multiple sub-time periods of the same length, such as a day or a week. Of course, it can also be other lengths.

[0048] For a target time period, such as the most recent week, an abnormality analysis may be performed on each sub-time period. Specifically, an abnormality analysis may be performed on vehicle sensor data collected in the sub-time period and vehicle sensor data collected in other sub-time periods.

[0049] It should be noted that the abnormality analysis in the embodiment of the present invention is different from the fault analysis in the prior art in which the fault light is turned on after a vehicle sensor fails. In the prior art, the analysis is performed after the fault, while in the embodiment of the present invention, the abnormality analysis is performed before the vehicle sensor fails and the fault light is turned on. Through the early abnormality analysis, it is possible to avoid feedback of vehicle sensor abnormalities only by turning on the fault light after the vehicle sensor has failed, thereby ensuring the safety of vehicle driving.

[0050] In one example, the Hive data engine can be used to perform data calculations to improve rapid development efficiency, or the Spark computing engine or Flink computing engine can be switched to perform memory computing to improve operating efficiency. When the Flink computing engine is used, the data of the relational database in the Internet of Vehicles (such as the relational database can be a postgresql database) is read to establish catalog information, and then the Hive function information can be imported, and the Flinksql calculation is used to write the result set into the Hive table.

[0051] In one embodiment of the present invention, step 102 may include:

[0052] Sub-step 11: for each sub-time period within the target time period, determine an average deviation value between the vehicle sensor data collected in the sub-time period and the vehicle sensor data collected in other sub-time periods.

[0053] Since there are multiple sub-time periods, for each sub-time period within the target time period, the average deviation value between the vehicle sensor data collected in the sub-time period and the vehicle sensor data collected in other sub-time periods (multiple) can be determined, that is, the average value of the deviation values.

[0054] In an embodiment of the present invention, the vehicle sensor data may include sensor voltage data, and before sub-step 11, the following may also be included:

[0055] According to the sensor voltage data collected in each sub-time period within the target time period, an average voltage value of each sub-time period is determined.

[0056] After obtaining the sensor voltage data collected in each sub-time period, the sensor voltage data may be averaged to obtain an average voltage value in each sub-time period, such as an average voltage value per day.

[0057] In one embodiment of the present invention, after determining the average voltage value of each sub-time period according to the sensor voltage data collected in each sub-time period within the target time period, the following method may be further included:

[0058] According to the vehicle gateway ID and the vehicle sensor ID, the average voltage value of each sub-time period is grouped and stored as an array type.

[0059] Among them, the vehicle gateway identifier is used to distinguish which specific vehicle it is, and the vehicle sensor identifier is used to distinguish which specific vehicle sensor in the vehicle.

[0060] Since the big data platform corresponds to multiple vehicles and each vehicle has multiple vehicle sensors, the amount of sensor data collected is large. In order to facilitate data storage and use, the average voltage value of each sub-time period can be grouped and stored as an array type according to the vehicle gateway ID and vehicle sensor ID and combined with the time granularity. For example, the collect_listover function can be used for processing.

[0061] For example, the target time period is one week, and the sub-time period is each day from Monday to Sunday, then the array stores the average voltage value of each day from Monday to Sunday.

[0062] When performing an abnormality analysis on a vehicle sensor in a vehicle, the corresponding array can be found through the vehicle gateway identifier and the vehicle sensor identifier.

[0063] In one embodiment of the present invention, sub-step 11 may include:

[0064] For each sub-time period within the target time period, a deviation value between a first average voltage value of the sub-time period and second average voltage values ​​of other sub-time periods is determined; and an average deviation value is determined based on the multiple deviation values.

[0065] For each sub-time period within the target time period, the first average voltage value of the sub-time period can be determined, and the second average voltage values ​​of other sub-time periods (multiple) can be determined, and then the deviations from the multiple second average voltage values ​​can be calculated respectively to obtain multiple deviation values.

[0066] After obtaining multiple deviation values, the average of the multiple deviation values ​​can be calculated, that is, the sum of the multiple deviation values ​​divided by the number of deviation values ​​can be used to obtain the average deviation value.

[0067] For example, the target time period is one week, and the sub-time period is each day from Monday to Sunday. yy[] is an array storing average voltage values, which stores the average voltage values ​​of each day from Monday to Sunday. Then yy[0] to yy[6] are the average voltage values ​​of each day from Monday to Sunday, respectively. a1 is the average voltage value on Monday. For the average deviation value w1 on Monday, the following formula can be used:

[0068] w1=abs(a1-yy[1]+a1-yy[2]+a1-yy[3]+a1-yy[4]+a1-yy[5]+a1-yy[6]) / 6

[0069] Sub-step 12, performing anomaly analysis based on the average deviation value.

[0070] After the average deviation value is obtained, it can be compared with a value, and then an abnormality analysis can be performed according to the comparison result to obtain the abnormality analysis result of the vehicle sensor in the sub-time period.

[0071] In one embodiment of the present invention, sub-step 12 may include:

[0072] A target deviation value is determined from the multiple deviation values; when the difference between the average deviation value and the target deviation value is greater than a difference threshold, it is determined that an abnormality exists in the sub-time period.

[0073] The target deviation value may be a median value among multiple deviation values.

[0074] In a specific implementation, a target deviation value may be determined from a plurality of deviation values, such as a target deviation value being a median value among the plurality of deviation values. Of course, the target deviation value may also be a preset value.

[0075] When the difference between the average deviation value and the target deviation value is greater than the difference threshold, such as the difference threshold is 20% of the target deviation value, it is determined that there is an abnormality in the sub-time period. When the difference between the average deviation value and the target deviation value is less than or equal to the difference threshold, it is determined that there is no abnormality in the sub-time period.

[0076] In an embodiment of the present invention, before step 102, the following steps may also be included:

[0077] Data filtering and / or data filling are performed on the vehicle sensor data collected within a target time period.

[0078] In practical applications, since the vehicle may not be started during the target time period, the time point when the vehicle is not started, that is, the vehicle sensor data is null, can be filtered out. Of course, it can also be filled with previous data.

[0079] In one example, after data filtering and / or data filling, the with function can be used to store the data in memory and make it into a view format to facilitate subsequent data use.

[0080] Step 103: Feedback the abnormal analysis results of the vehicle sensors in the target time period to the user.

[0081] For each sub-time period in the target time period, an abnormal analysis result is obtained. The abnormal analysis results of each sub-time period can be summarized and fed back to the user. Feedback can be given once for each target time period. For example, if the target time period is one week, feedback will be given to the user every Sunday, and the user can be prompted to repair the vehicle sensor with abnormalities.

[0082] In one example, the abnormal analysis result can be fed back to the user via SMS, or an http link can be generated and the abnormal analysis result can be stored in the link. After the user logs in using the mobile phone number, the abnormal analysis result can be viewed.

[0083] In an embodiment of the present invention, by acquiring vehicle sensor data collected within a target time period, for each sub-time period within the target time period, an abnormality analysis is performed in combination with the vehicle sensor data collected within the sub-time period and the vehicle sensor data collected within other sub-time periods, and the abnormality analysis results of the vehicle sensors in the target time period are fed back to the user, thereby achieving early analysis of vehicle sensor abnormalities in combination with the collected vehicle sensor data, avoiding feedback of vehicle sensor abnormalities only by lighting up a fault light after the vehicle sensor has failed, and ensuring vehicle driving safety.

[0084] Reference Figure 2 , shows a flowchart of another method for handling an abnormality of a vehicle sensor provided by an embodiment of the present invention, which may specifically include the following steps:

[0085] Step 201, obtaining vehicle sensor data collected within a target time period.

[0086] Among them, the vehicle sensor data may include sensor voltage data.

[0087] In the vehicle, a network for communicating with the Internet of Vehicles can be deployed, such as communicating through a SIM card. After obtaining the vehicle sensor data, the vehicle can send the vehicle sensor data to the Internet of Vehicles platform through the network, and then store the vehicle sensor data in a relational database (such as a postgresql database).

[0088] For data stored in a relational database, a data acquisition tool (such as the data acquisition tool can be a sqoop tool) can be used to filter it to obtain subsequent usable data, such as filtering out sensor voltage data from vehicle sensor data, and then importing the filtered data into a big data platform for subsequent big data analysis in the big data platform.

[0089] In one example, the vehicle may upload sensor data to the vehicle network according to a preset duration, such as 1 hour.

[0090] Step 202 : for each sub-time period within the target time period, determine an average deviation value between the vehicle sensor data collected in the sub-time period and the vehicle sensor data collected in other sub-time periods.

[0091] Since there are multiple sub-time periods, for each sub-time period within the target time period, the average deviation value between the vehicle sensor data collected in the sub-time period and the vehicle sensor data collected in other sub-time periods (multiple) can be determined, that is, the average value of the deviation values.

[0092] Step 203, determining a target deviation value from the multiple deviation values.

[0093] The target deviation value may be a median value among multiple deviation values.

[0094] In a specific implementation, a target deviation value may be determined from a plurality of deviation values, such as a target deviation value being a median value among the plurality of deviation values. Of course, the target deviation value may also be a preset value.

[0095] Step 204: When the difference between the average deviation value and the target deviation value is greater than the difference threshold, it is determined that an abnormality exists in the sub-time period.

[0096] When the difference between the average deviation value and the target deviation value is greater than the difference threshold, such as the difference threshold is 20% of the target deviation value, it is determined that there is an abnormality in the sub-time period. When the difference between the average deviation value and the target deviation value is less than or equal to the difference threshold, it is determined that there is no abnormality in the sub-time period.

[0097] Step 205: Feedback the abnormal analysis results of the vehicle sensors in the target time period to the user.

[0098] For each sub-time period in the target time period, an abnormal analysis result is obtained. The abnormal analysis results of each sub-time period can be summarized and fed back to the user. Feedback can be given once for each target time period. For example, if the target time period is one week, feedback will be given to the user every Sunday, and the user can be prompted to repair the vehicle sensor with abnormalities.

[0099] In one example, the abnormal analysis result can be fed back to the user via SMS, or an http link can be generated and the abnormal analysis result can be stored in the link. After the user logs in using the mobile phone number, the abnormal analysis result can be viewed.

[0100] In an embodiment of the present invention, by acquiring vehicle sensor data collected within a target time period, for each sub-time period within the target time period, an average deviation value between the vehicle sensor data collected within the sub-time period and the vehicle sensor data collected within other sub-time periods is determined, and a target deviation value is determined from multiple deviation values. When the difference between the average deviation value and the target deviation value is greater than a difference threshold, it is determined that an abnormality exists in the sub-time period, and the abnormality analysis result of the vehicle sensor in the target time period is fed back to the user, thereby realizing early analysis of vehicle sensor abnormalities according to the deviation values ​​of vehicle sensor data in different time periods, avoiding feedback of vehicle sensor abnormalities only by turning on a fault light after the vehicle sensor has failed, and ensuring vehicle driving safety.

[0101] Reference Figure 3 , shows a flowchart of another method for handling an abnormality of a vehicle sensor provided by an embodiment of the present invention, which may specifically include the following steps:

[0102] Step 301 : Acquire vehicle sensor data collected within a target time period, where the vehicle sensor data includes sensor voltage data.

[0103] In the vehicle, a network for communicating with the Internet of Vehicles can be deployed, such as communicating through a SIM card. After obtaining the vehicle sensor data, the vehicle can send the vehicle sensor data to the Internet of Vehicles platform through the network, and then store the vehicle sensor data in a relational database (such as a postgresql database).

[0104] For data stored in a relational database, a data acquisition tool (such as the data acquisition tool can be a sqoop tool) can be used to filter it to obtain subsequent usable data, such as filtering out sensor voltage data from vehicle sensor data, and then importing the filtered data into a big data platform for subsequent big data analysis in the big data platform.

[0105] In one example, the vehicle may upload sensor data to the vehicle network according to a preset duration, such as 1 hour.

[0106] Step 302: Determine the average voltage value of each sub-time period according to the sensor voltage data collected in each sub-time period within the target time period.

[0107] After obtaining the sensor voltage data collected in each sub-time period, the sensor voltage data may be averaged to obtain an average voltage value in each sub-time period, such as an average voltage value per day.

[0108] Step 303 : group the average voltage value of each sub-time period according to the vehicle gateway identifier and the vehicle sensor identifier and store them in an array type.

[0109] Among them, the vehicle gateway identifier is used to distinguish which specific vehicle it is, and the vehicle sensor identifier is used to distinguish which specific vehicle sensor in the vehicle.

[0110] Since the big data platform corresponds to multiple vehicles and each vehicle has multiple vehicle sensors, the amount of sensor data collected is large. In order to facilitate data storage and use, the average voltage value of each sub-time period can be grouped and stored as an array type according to the vehicle gateway ID and vehicle sensor ID and combined with the time granularity. For example, the collect_listover function can be used for processing.

[0111] For example, the target time period is one week, and the sub-time period is each day from Monday to Sunday, then the array stores the average voltage value of each day from Monday to Sunday.

[0112] When performing an abnormality analysis on a vehicle sensor in a vehicle, the corresponding array can be found through the vehicle gateway identifier and the vehicle sensor identifier.

[0113] Step 304 : for each sub-time period within the target time period, determine a deviation between a first average voltage value of the sub-time period and second average voltage values ​​of other sub-time periods.

[0114] For each sub-time period within the target time period, the first average voltage value of the sub-time period can be determined, and the second average voltage values ​​of other sub-time periods (multiple) can be determined, and then the deviations from the multiple second average voltage values ​​can be calculated respectively to obtain multiple deviation values.

[0115] Step 305: determine an average deviation value according to the multiple deviation values.

[0116] After obtaining multiple deviation values, the average of the multiple deviation values ​​can be calculated, that is, the sum of the multiple deviation values ​​divided by the number of deviation values ​​can be used to obtain the average deviation value.

[0117] For example, the target time period is one week, and the sub-time period is each day from Monday to Sunday. yy[] is an array storing average voltage values, which stores the average voltage values ​​of each day from Monday to Sunday. Then yy[0] to yy[6] are the average voltage values ​​of each day from Monday to Sunday, respectively. a1 is the average voltage value on Monday. For the average deviation value w1 on Monday, the following formula can be used:

[0118] w1=abs(a1-yy[1]+a1-yy[2]+a1-yy[3]+a1-yy[4]+a1-yy[5]+a1-yy[6]) / 6

[0119] Step 306: Perform an abnormality analysis based on the average deviation value.

[0120] After the average deviation value is obtained, it can be compared with a value, and then an abnormality analysis can be performed according to the comparison result to obtain the abnormality analysis result of the vehicle sensor in the sub-time period.

[0121] Step 307: Feedback the abnormal analysis results of the vehicle sensors in the target time period to the user.

[0122] For each sub-time period in the target time period, an abnormal analysis result is obtained. The abnormal analysis results of each sub-time period can be summarized and fed back to the user. Feedback can be given once for each target time period. For example, if the target time period is one week, feedback will be given to the user every Sunday, and the user can be prompted to repair the vehicle sensor with abnormalities.

[0123] In one example, the abnormal analysis result can be fed back to the user via SMS, or an http link can be generated and the abnormal analysis result can be stored in the link. After the user logs in using the mobile phone number, the abnormal analysis result can be viewed.

[0124] In an embodiment of the present invention, vehicle sensor data collected within a target time period is acquired through steps, an average voltage value of each sub-time period is determined according to sensor voltage data collected within each sub-time period within the target time period, the average voltage value of each sub-time period is grouped according to a vehicle gateway identifier and a vehicle sensor identifier and stored as an array type, for each sub-time period within the target time period, a deviation value between a first average voltage value of the sub-time period and a second average voltage value of other sub-time periods is determined, an average deviation value is determined according to multiple deviation values, an abnormality analysis is performed according to the average deviation value, and the abnormality analysis result of the vehicle sensor in the target time period is fed back to the user, thereby realizing early analysis of vehicle sensor abnormalities according to the deviation value of the average voltage value of the vehicle sensor in different time periods, avoiding feedback of vehicle sensor abnormalities only by turning on a fault light after the vehicle sensor has failed, and ensuring vehicle driving safety.

[0125] The following combination Figure 4 The present invention is exemplified in real time:

[0126] In one approach, the following may be used:

[0127] The vehicle uploads the vehicle sensor data to the IoV platform → the IoV platform transfers the data to the relational database PostgreSQL → uses spark to directly read the data → uses sparksql to perform calculations and writes the calculation result set to hive → performs abnormal analysis on the sensor voltage data. Among them, the abnormal analysis of the sensor voltage data can be performed using the hive engine, or it can be switched to the spark engine or the flink engine → the abnormal analysis results are fed back to the user

[0128] In another approach, the following can be adopted:

[0129] The vehicle uploads the vehicle sensor data to the IoV platform → the IoV platform transfers the data to the relational database PostgreSQL → sqoop is used to collect the data in PostgreSQL to hive → sensor voltage data is analyzed for anomalies. The sensor voltage data can be analyzed for anomalies using the hive engine, or it can be switched to the spark engine or the flink engine → the anomaly analysis results are fed back to the user

[0130] It should be noted that, for the sake of simplicity, the method embodiments are described as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0131] Reference Figure 5 , shows a schematic diagram of the structure of an abnormality processing device for a vehicle sensor provided by an embodiment of the present invention, which may specifically include the following modules:

[0132] The vehicle sensor data acquisition module 501 may be used to acquire vehicle sensor data collected within a target time period.

[0133] The abnormality analysis module 502 may be used to perform abnormality analysis on each sub-time period within the target time period by combining the vehicle sensor data collected in the sub-time period with the vehicle sensor data collected in other sub-time periods.

[0134] The abnormal analysis result feedback module 503 may be used to feed back the abnormal analysis result of the vehicle sensor in the target time period to the user.

[0135] In one embodiment of the present invention, the abnormality analysis module 502 may include:

[0136] The average deviation value determination submodule may be used to determine, for each sub-time period within the target time period, an average deviation value between the vehicle sensor data collected within the sub-time period and the vehicle sensor data collected within other sub-time periods.

[0137] The average deviation value anomaly analysis submodule can be used to perform anomaly analysis based on the average deviation value.

[0138] In one embodiment of the present invention, the vehicle sensor data may include sensor voltage data, and may also include:

[0139] The average voltage value determination module can be used to determine the average voltage value of each sub-time period according to the sensor voltage data collected in each sub-time period within the target time period.

[0140] The average deviation value determination submodule may include:

[0141] The deviation value determination submodule may be used to determine, for each sub-time period within the target time period, a deviation value between a first average voltage value of the sub-time period and second average voltage values ​​of other sub-time periods.

[0142] The deviation value averaging submodule can be used to determine an average deviation value based on multiple deviation values.

[0143] In one embodiment of the present invention, the method may further include:

[0144] The array storage module can be used to group the average voltage value of each sub-time period according to the vehicle gateway identifier and the vehicle sensor identifier and store them as an array type.

[0145] In one embodiment of the present invention, the average deviation value abnormality analysis submodule may include:

[0146] Combined with the target deviation value judgment submodule, it can be used to determine the target deviation value from multiple deviation values; when the difference between the average deviation value and the target deviation value is greater than the difference threshold, it is determined that there is an abnormality in the sub-time period.

[0147] In one embodiment of the present invention, the target deviation value may be a median value among a plurality of deviation values.

[0148] In one embodiment of the present invention, the method may further include:

[0149] The data preprocessing module can be used to filter and / or fill in the vehicle sensor data collected within a target time period.

[0150] In an embodiment of the present invention, by acquiring vehicle sensor data collected within a target time period, for each sub-time period within the target time period, an abnormality analysis is performed in combination with the vehicle sensor data collected within the sub-time period and the vehicle sensor data collected within other sub-time periods, and the abnormality analysis results of the vehicle sensors in the target time period are fed back to the user, thereby achieving early analysis of vehicle sensor abnormalities in combination with the collected vehicle sensor data, avoiding feedback of vehicle sensor abnormalities only by lighting up a fault light after the vehicle sensor has failed, and ensuring vehicle driving safety.

[0151] An embodiment of the present invention further provides an electronic device, which may include a processor, a memory, and a computer program stored in the memory and capable of running on the processor. When the computer program is executed by the processor, the above-mentioned vehicle sensor exception handling method is implemented.

[0152] An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned vehicle sensor exception handling method is implemented.

[0153] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0154] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0155] Those skilled in the art will appreciate that the embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the embodiments of the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the embodiments of the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0156] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0157] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0158] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0159] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0160] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0161] The above is a detailed introduction to the abnormality handling method and device for a vehicle sensor provided. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for general technicians in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for handling abnormality of a vehicle sensor, characterized in that: The method comprises: Obtain vehicle sensor data collected within a target time period; For each sub-time period within the target time period, combining the vehicle sensor data collected in the sub-time period with the vehicle sensor data collected in other sub-time periods, performing anomaly analysis; For each sub-time period within the target time period, determining an average deviation value between the vehicle sensor data collected in the sub-time period and the vehicle sensor data collected in other sub-time periods; Determine an average voltage value of each sub-time period according to the sensor voltage data collected in each sub-time period within the target time period; For each sub-time period within the target time period, determining a deviation value of a first average voltage value of the sub-time period and a second average voltage value of another sub-time period; Determine an average deviation value based on the plurality of deviation values; Performing anomaly analysis according to the average deviation value; Feedback the abnormal analysis result of the vehicle sensor in the target time period to the user.

2. The method according to claim 1, characterized in that After determining the average voltage value of each sub-time period according to the sensor voltage data collected in each sub-time period within the target time period, the method further includes: According to the vehicle gateway ID and the vehicle sensor ID, the average voltage value of each sub-time period is grouped and stored as an array type.

3. The method according to claim 2, characterized in that The performing of abnormality analysis according to the average deviation value comprises: Determining a target deviation value from the plurality of deviation values; When the difference between the average deviation value and the target deviation value is greater than a difference threshold, it is determined that an abnormality exists in the sub-time period.

4. The method according to claim 3, characterized in that The target deviation value is a median value among the multiple deviation values.

5. The method according to claim 1, characterized in that Before performing abnormal analysis for each sub-time period within the target time period by combining the vehicle sensor data collected in the sub-time period with the vehicle sensor data collected in other sub-time periods, the method further includes: Data filtering and / or data filling are performed on the vehicle sensor data collected within a target time period.

6. An electronic device, characterized in that: The invention comprises a processor, a memory and a computer program stored in the memory and capable of running on the processor, wherein when the computer program is executed by the processor, the abnormality handling method of the vehicle sensor as claimed in any one of claims 1 to 5 is implemented.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the abnormality handling method for a vehicle sensor according to any one of claims 1 to 5 is implemented.

Images