Methods, devices, electronic equipment and storage media for identifying abnormal vehicle data

Abstract

The application discloses an abnormal data identification method and device of a vehicle, an electronic device and a storage medium. The abnormal data identification method of the vehicle comprises the following steps: acquiring at least one set of to-be-identified arrays corresponding to a preset to-be-identified time period; comparing the to-be-identified arrays, determining the array difference degrees corresponding to each to-be-identified array; and if a target array with an array difference degree exceeding a preset difference degree threshold is detected in each to-be-identified array, determining the data in the target array as abnormal data. The application solves the technical problem of low accuracy of abnormal data identification in the prior art.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method, apparatus, electronic device and storage medium for identifying abnormal data of vehicles. Background Technology

[0002] With the increasing popularity of new energy vehicles, the government and vehicle manufacturers have put forward higher requirements for the supervision of new energy vehicle operation data. Accurately identifying abnormal data from massive amounts of operation data is one of the keys to improving the safety early warning capabilities of new energy vehicles.

[0003] Currently, for time-series data such as battery pack temperature and individual cell voltage, the main method is to calculate the difference between the data detected by different cells at the same time and identify abnormal data based on whether the difference exceeds a preset threshold. However, since the numerical fluctuation range of abnormal data is large, the accuracy of this method is low. If the difference threshold is set too high, abnormal data with abnormal fluctuations within a small range may be missed, posing a safety hazard. On the other hand, if the difference threshold is set too low, a large number of non-abnormal deviations may be falsely reported as abnormal data, affecting the user experience. Summary of the Invention

[0004] The main objective of this application is to provide a method, device, electronic device, and storage medium for identifying abnormal data of vehicles, aiming to solve the technical problem of low accuracy in identifying abnormal data in the prior art.

[0005] To achieve the above objectives, this application provides a method for identifying abnormal vehicle data, the method comprising:

[0006] Obtain at least one set of arrays to be identified corresponding to the preset time period to be identified;

[0007] The arrays to be identified are compared to each other to determine the array difference degree of each array to be identified.

[0008] If, in each of the arrays to be identified, a target array is detected whose array difference exceeds a preset difference threshold, then the data in the target array is determined to be abnormal data.

[0009] Optionally, the array difference degree includes the rate of change difference degree, and the step of comparing each of the arrays to be identified and determining the array difference degree corresponding to each of the arrays to be identified includes:

[0010] Determine the rate of change array corresponding to each of the arrays to be identified;

[0011] The Euclidean distance between the various rate of change arrays is determined by comparing the arrays.

[0012] Based on the Euclidean distances described, the rate of change difference corresponding to each of the arrays to be identified is determined.

[0013] Optionally, the step of determining the rate of change difference corresponding to each of the arrays to be identified based on the Euclidean distances includes:

[0014] Calculate the first average value of the Euclidean distance corresponding to each of the aforementioned rate of change arrays, and the second average value of each of the first average values;

[0015] The difference between the first average value and the second average value corresponding to each of the rate of change arrays is determined as the rate of change difference degree corresponding to each of the rate of change arrays.

[0016] Optionally, the step of determining the rate of change array corresponding to each of the arrays to be identified includes:

[0017] Obtain the preceding and following sub-data of two adjacent frames in each of the arrays to be identified, as well as the time difference between the following and preceding sub-data.

[0018] The ratio of the difference between the subsequent frame sub-data and the previous frame sub-data to the time difference is calculated to obtain the rate of change sub-data. The rate of change array consists of at least one rate of change sub-data.

[0019] Optionally, before the step of obtaining at least one set of arrays to be identified corresponding to a preset time period, the method further includes:

[0020] Obtain at least one current operating data of the vehicle;

[0021] Detect whether there is any suspected abnormal data in each of the current running data that exceeds the corresponding preset first threshold range;

[0022] If suspected abnormal data exceeding the corresponding preset first threshold range is detected in each of the current operating data, then a preset time period to be identified is determined based on the suspicious time point corresponding to the suspected abnormal data.

[0023] Optionally, the step of determining a preset time period to be identified based on the suspicious time point corresponding to the suspected abnormal data if suspected abnormal data exceeding the corresponding preset first threshold range is detected in each of the current running data includes:

[0024] If suspected abnormal data exceeding the corresponding preset first threshold range is detected in each of the current running data, then it is determined whether the suspected abnormal data exceeds the preset second threshold range.

[0025] If the suspected abnormal data exceeds the preset second threshold range, then the suspected abnormal data is determined to be abnormal data;

[0026] If the suspected abnormal data does not exceed the preset second threshold range, then the preset time range from the suspected time point corresponding to the suspected abnormal data is determined as the preset time period to be identified.

[0027] Optionally, the method for identifying abnormal vehicle data further includes:

[0028] When abnormal data is detected, an alarm message corresponding to the abnormal data is generated and output.

[0029] This application also provides an abnormal data identification device, the abnormal data identification device comprising:

[0030] The acquisition module is used to acquire at least one set of arrays to be identified corresponding to a preset time period;

[0031] The difference determination module is used to compare the arrays to be identified and determine the array difference degree of each array to be identified.

[0032] The abnormal data determination module is used to determine the data in the target array as abnormal data if a target array with an array difference exceeding a preset difference threshold is detected in each of the arrays to be identified.

[0033] This application also provides an electronic device, which is a physical device, comprising: a memory, a processor, and a program for the vehicle anomaly data identification method stored in the memory and executable on the processor. When the program for the vehicle anomaly data identification method is executed by the processor, it can implement the steps of the vehicle anomaly data identification method as described above.

[0034] This application also provides a storage medium, which is a computer-readable storage medium, on which a program for implementing a method for identifying abnormal vehicle data is stored. When the program for identifying abnormal vehicle data is executed by a processor, it implements the steps of the method for identifying abnormal vehicle data as described above.

[0035] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the vehicle abnormal data identification method described above.

[0036] This application provides a method, device, electronic device, and storage medium for identifying abnormal vehicle data. By acquiring at least one set of arrays to be identified corresponding to a preset time period, comparing the arrays to determine the difference degree of each array, the method achieves the comparison of differences between arrays. Furthermore, if a target array with an array difference degree exceeding a preset difference degree threshold is detected in any of the arrays to be identified, the data in the target array is determined to be abnormal data. This achieves abnormal data identification based on the difference degree between arrays. Compared to the difference between individual data points at a single moment, the difference degree between arrays not only includes the difference in numerical value but also reflects the difference in data changes across different arrays. Therefore, abnormal data can be determined from both numerical value and data change perspectives. Regardless of whether the fluctuation range of abnormal data is large or small, the abnormal fluctuation of data can be accurately identified by combining the data change situation, overcoming the technical problem of low accuracy in abnormal data identification in existing technologies. Attached Figure Description

[0037] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0038] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0039] Figure 1 A schematic diagram of the curve of the data to be identified changing over time, provided for this application;

[0040] Figure 2 A schematic diagram of another data to be identified over time provided for this application;

[0041] Figure 3 A flowchart illustrating an embodiment of abnormal data identification for the vehicle in this application;

[0042] Figure 4 This is a schematic diagram of an abnormal data identification scenario provided in this embodiment;

[0043] Figure 5 A flowchart illustrating another embodiment of abnormal data identification for the vehicle in this application;

[0044] Figure 6 A schematic diagram of the array to be identified in one possible implementation method provided in this application;

[0045] Figure 7 A schematic diagram of the rate of change array corresponding to the array to be identified in one possible implementation of this application;

[0046] Figure 8 A schematic diagram of the array to be identified in another possible implementation provided in this application;

[0047] Figure 9 A schematic diagram of the rate of change array corresponding to the array to be identified in another possible implementation provided in this application;

[0048] Figure 10 A schematic diagram of the Euclidean distance corresponding to the array to be identified in one possible implementation of this application;

[0049] Figure 11 A schematic diagram of the Euclidean distance corresponding to the array to be identified in another possible implementation provided in this application;

[0050] Figure 12 This is a schematic diagram of the device structure of the hardware operating environment involved in the abnormal data identification method for vehicles in this application embodiment.

[0051] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0052] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0053] With the increasing popularity of new energy vehicles, the government and vehicle manufacturers have put forward higher requirements for the supervision of new energy vehicle operation data. Accurately identifying abnormal data from massive amounts of operation data is one of the keys to improving the safety early warning capabilities of new energy vehicles.

[0054] Currently, for time-series data such as battery pack temperature and cell voltage, the main method is to calculate the difference between the data detected by different cells at the same time and identify abnormal data based on whether the difference exceeds a preset threshold. However, since the numerical fluctuation range of abnormal data is large, the accuracy of this method is low. If the difference threshold is set too high, abnormal data with abnormal fluctuations in a small range will be missed, posing a safety hazard. To ensure safety, the difference threshold is usually set too low. However, the states of individual sensors within a vehicle (such as individual battery cells and temperature probes) are not entirely identical, which may cause deviations in the magnitude of the monitored data. However, under the same overall operating conditions of the vehicle, the differences in data trends should be small. For example, a new energy vehicle's battery pack may include one or more battery modules, each containing one or more individual battery cells. Temperature probes are typically placed at different locations within the battery pack, and the distance between each location and the heat source may be the same or different. Uneven temperature distribution within the battery pack may cause differences in the temperature detected by each probe at the same time. In another example, the SOC (state of charge) of each individual battery cell in a new energy vehicle's battery pack may also be the same or different, leading to differences in the voltage detected by the individual cells at the same time. Since these differences are essentially non-abnormal deviations, if the difference threshold is set too low, a large number of non-abnormal deviations will be falsely reported as abnormal data, affecting the user experience. For example... Figure 1 This application provides a schematic diagram of the curve of the data to be identified changing over time, such as... Figure 1 As shown, Figure 1 The data includes curves showing the temperature changes over time for 28 temperature probes numbered T1 to T28. The horizontal axis represents time, and the vertical axis represents temperature. Within the area indicated by the box, the difference between the highest and lowest temperatures detected by the various probes at the same time exceeds 10°C. If anomaly identification were based solely on whether a single data point at a single moment exceeds a threshold, it would be very easy to classify this as abnormal data. However, from… Figure 1 The overall trend of each temperature curve can be understood. Figure 1 The temperature difference may be due to uneven temperature field distribution; temperature probes closer to the high-temperature region have higher temperatures, while those farther away have lower temperatures. Figure 1 The data detected in the area indicated by the box is not anomalous. Current technology, which compares the differences between individual data points at a single moment, will likely detect similar... Figure 1 Non-abnormal deviations in the area indicated by the square box are identified as abnormal data, generating a large number of false alarms and affecting user experience.

[0055] Commonly observed outlier data typically exhibits frequent fluctuations in value within a certain timeframe. Figure 2 Another schematic diagram of the time-varying curve of the data to be identified provided for this application, such as... Figure 2 As shown, Figure 2 The graph includes temperature curves over time for 28 temperature probes numbered T1 to T28, where the horizontal axis represents time and the vertical axis represents temperature. Temperature probe T18 detected abnormal data. Figure 2 As can be seen, the abnormal data exhibits typical characteristics of frequent numerical fluctuations.

[0056] To address this issue, this application provides a method, apparatus, electronic device, and storage medium for identifying abnormal vehicle data. By acquiring at least one set of arrays to be identified corresponding to a preset time period, comparing each array to determine its respective array difference degree, the method achieves this comparison. Furthermore, if a target array with an array difference degree exceeding a preset difference degree threshold is detected among the arrays to be identified, the data in that target array is identified as abnormal data. This achieves abnormal data identification based on the difference degree between arrays. Compared to the difference between individual data points at a single moment, the difference degree between arrays not only includes the difference in numerical value but also reflects the difference in data variation across different arrays. Therefore, abnormal data can be determined from both numerical value and data variation perspectives. Regardless of whether the fluctuation range of abnormal data is large or small, the method can accurately identify abnormal fluctuations in the data by combining the data variation situation, overcoming the technical problem of low accuracy in abnormal data identification in existing technologies.

[0057] This application provides a method for identifying abnormal vehicle data. In the first embodiment of this method, referring to... Figure 3 The method for identifying abnormal vehicle data includes:

[0058] Step S10: Obtain at least one set of identification arrays corresponding to the preset identification time period;

[0059] In this embodiment, it should be noted that the vehicle anomaly data identification method can be applied to a vehicle monitoring platform. This platform is one that collects, monitors, and stores vehicle operation data, including automotive company monitoring platforms or national monitoring platforms. The vehicle anomaly data identification method can also be applied to in-vehicle terminals. For ease of reading and understanding, the following text will use the aforementioned vehicle monitoring platform as the executing entity of the vehicle anomaly data identification method in this application to specifically illustrate this embodiment. Figure 4 , Figure 4This is a schematic diagram of an abnormal data identification scenario provided in this embodiment. The vehicle monitoring platform receives the operating data uploaded by the vehicle and performs abnormal data identification on the operating data.

[0060] In one feasible approach, the vehicle anomaly data identification method is used to identify anomalies in the time-series data of the new energy vehicle's operating data. The time-series data is collected at different times and describes the changes in a phenomenon over time. The time-series data in the new energy vehicle's operating data includes battery pack temperature, individual cell voltage, tire pressure, etc. To ensure the safety of the new energy vehicle, such as battery safety and vehicle driving safety, multiple detection units are installed on the new energy vehicle to detect vehicle operating data. These include, for example, multiple temperature probes located at different positions within the battery pack, and detection units that detect the voltage of each individual cell. The onboard terminal can periodically acquire the operating data detected by each of these detection units and upload it to the vehicle monitoring platform for data analysis and fault monitoring.

[0061] Specifically, at least one set of identification arrays corresponding to a preset identification time period is obtained from the vehicle's on-board terminal. The identification arrays are composed of individual data points detected by the detection unit in the on-board terminal at a single moment within the preset identification time period, arranged in chronological order. Each identification array corresponds to a different detection unit. That is, the sub-data in each set of identification arrays are data detected by the same detection unit. For example, if there are three temperature probes A1, A2, and A3, and each temperature probe detects 5 temperature values ​​within t1 to t2 minutes, then the identification array a1 corresponding to temperature probe A1, the identification array a2 corresponding to temperature probe A2, and the identification array a3 corresponding to temperature probe A3 can be obtained. The identification array a1 consists of 5 temperature values ​​detected by temperature probe A1 within t1 to t2 minutes, the identification array a2 consists of 5 temperature values ​​detected by temperature probe A2 within t1 to t2 minutes, and the identification array a3 consists of 5 temperature values ​​detected by temperature probe A3 within t1 to t2 minutes.

[0062] It should be noted that the preset time period to be identified can be determined based on actual needs or test results, etc. This embodiment does not limit this. For example, the preset time period to be identified can be used as the time interval for each acquisition of the array to be identified. The array to be identified is acquired once every preset time period to identify abnormal data. Alternatively, based on the pre-identified suspected abnormal data, a certain time range corresponding to the suspected abnormal data can be determined as the preset time period to be identified.

[0063] Optionally, before the step of obtaining at least one set of arrays to be identified corresponding to a preset time period, the method further includes:

[0064] Step A10: Obtain at least one current operating data of the vehicle;

[0065] In this embodiment, the current operating data detected by each detection unit in the vehicle is obtained in real time from the vehicle's on-board terminal. For example, at least one piece of current operating data of the vehicle can be obtained by consuming real-time streaming data from Kafka (an open-source stream processing platform), Flume (a log collection system), etc.

[0066] Step A20: Detect whether there is any suspected abnormal data in each of the current running data that exceeds the corresponding preset first threshold range;

[0067] In this embodiment, it should be noted that the operational data that can be detected at any given time includes various data such as battery pack temperature, cell voltage, and tire pressure. Each type of operational data can have its own corresponding threshold range. The preset first threshold range corresponding to each type of operational data can be determined based on big data and actual test results. It can be a fixed numerical range or it can change dynamically with the specific value of each current operational data. This embodiment does not impose any restrictions on this. For example, the preset first threshold range can be determined based on the average value and / or standard deviation of each current operational data. For instance, the range between a value c1 less than the average value of each current operational data and a value c2 greater than the average value of each current operational data can be used as the first threshold range. Alternatively, the first threshold range can be determined based on the Z-score (standard score) model.

[0068] Specifically, each of the current running data is compared with a preset first threshold range, and it is determined whether each of the current running data exceeds the preset first threshold range. If target running data exceeding the preset first threshold range is detected in each of the current running data, the target running data is regarded as suspected abnormal data. If no target running data exceeding the preset first threshold range is detected in each of the current running data, it can be determined that there is no suspected abnormal data in each of the current running data, or it can also be determined that there is no abnormal data in each of the current running data.

[0069] In one feasible approach, after the step of detecting whether there is suspected abnormal data exceeding the corresponding preset first threshold range in each of the current operating data, the method further includes: if suspected abnormal data exceeding the corresponding preset first threshold range is detected in each of the current operating data, then the target detection unit corresponding to the suspected abnormal data is determined, and all data detected by the target detection unit after the current time is regarded as suspected abnormal data, until it is determined that the suspected abnormal data is normal data, that is, it is determined that the suspected abnormal data is not abnormal data. Since abnormal data is usually caused by faults, if the fault is not resolved after it occurs, the detection unit will continue to detect abnormal data. If the suspected abnormal data is an abnormal CNC, since the fault has been discovered, the subsequent continuous detection process is an unnecessary repetitive detection process, which occupies unnecessary time and computing resources. Therefore, all data detected by the target detection unit after detecting the suspected data is regarded as suspected abnormal data. This suspected abnormal data can also be stored for analysis. When it is determined that the suspected abnormal data is not abnormal data, the abnormal data identification of the data detected by the detection unit can be resumed, thereby effectively reducing the overall load pressure of the vehicle monitoring platform.

[0070] Step A30: If suspected abnormal data exceeding the corresponding preset first threshold range is detected in each of the current running data, then a preset time period to be identified is determined based on the suspicious time point corresponding to the suspected abnormal data.

[0071] In this embodiment, specifically, if suspected abnormal data exceeding the corresponding preset first threshold range is detected in each of the current running data, a suspicious time point corresponding to the suspected abnormal data is determined, and the preset time range to which the suspicious time point belongs is determined as a preset time period to be identified. If no suspected abnormal data exceeding the corresponding preset first threshold range is detected in each of the current running data, it is determined that there is no abnormal data in each of the current running data. The preset time range can be determined based on big data and actual test results, etc. The length of the preset time range can be determined by combining timeliness and computational complexity, for example, 7 minutes, 10 minutes, 12 minutes, etc. This embodiment does not limit this. For example, the suspicious time point and a period of time before the suspicious time point can be determined as the preset time period to be identified, the suspicious time point and a period of time after the suspicious time point can be determined as the preset time period to be identified, or the time range between the suspicious time point and a certain moment before the suspicious time point to a certain moment after the suspicious time point can be determined as the preset time period to be identified.

[0072] Optionally, the step of determining a preset time period to be identified based on the suspicious time point corresponding to the suspected abnormal data if suspected abnormal data exceeding the corresponding preset first threshold range is detected in each of the current running data includes:

[0073] Step A31: If suspected abnormal data exceeding the corresponding preset first threshold range is detected in each of the current running data, then determine whether the suspected abnormal data exceeds the preset second threshold range.

[0074] In this embodiment, specifically, if suspected abnormal data exceeding the corresponding preset first threshold range is detected in each of the current running data, the suspected abnormal data is compared with a preset second threshold range to determine whether the suspected abnormal data exceeds the preset second threshold range. The preset second threshold range is greater than the preset first threshold range. The preset second threshold range can be determined based on large datasets and actual test results, and can be a fixed numerical range or dynamically change with the specific values ​​of each of the current running data. This embodiment does not impose any limitations on this. For example, the preset second threshold range can be determined based on the average value and / or standard deviation of each of the current running data. For instance, the range between values ​​c3 (less than the average value of each of the current running data) and c4 (greater than the average value of each of the current running data) can be used as the second threshold range. Alternatively, the second threshold range can be determined based on a Z-score (standard score) model.

[0075] Step A32: If the suspected abnormal data exceeds the preset second threshold range, then the suspected abnormal data is determined to be abnormal data;

[0076] In this embodiment, specifically, if the suspected abnormal data exceeds the preset second threshold range, the suspected abnormal data is determined to be abnormal data. For data whose values ​​are already far beyond the reasonable range and are unlikely to be misjudged, there is no need to perform difference judgment between arrays; it can be directly determined as abnormal data. This can effectively reduce the resources and time consumed by difference judgment between arrays while ensuring accuracy.

[0077] Step A33: If the suspected abnormal data does not exceed the preset second threshold range, then the preset time range from the suspected time point corresponding to the suspected abnormal data is determined as the preset time period to be identified.

[0078] In this embodiment, specifically, if the suspected abnormal data does not exceed the preset second threshold range, then the suspicious time point corresponding to the suspected abnormal data is determined, and the preset time range to which the suspicious time point belongs is determined as the preset time period to be identified.

[0079] In this embodiment, by prioritizing the comparison of numerical values, the current running data is initially screened. Compared to comparing the differences between arrays, comparing the numerical values ​​requires less computation, is faster, and can acquire and detect the current running data in real time, resulting in higher timeliness. This allows for the timely screening of potentially abnormal data. Then, based on the suspected abnormal data, the time period to be identified is determined, and the arrays to be identified corresponding to the time period are compared for differences between arrays. Since further differences comparisons will be performed on suspected abnormal data, the threshold range for the numerical value comparison process can be set larger to ensure safety as much as possible. False alarms can be avoided through subsequent differences between arrays, thus improving the overall accuracy of abnormal data identification.

[0080] Step S20: Compare the arrays to be identified to determine the array difference degree of each array to be identified.

[0081] In this embodiment, specifically, the differences between the arrays to be identified are compared to determine the differences between each array. The differences between the arrays include numerical differences in the numerical dimension and / or differences in the rate of change in the numerical change dimension.

[0082] For example, the comparison method for the difference between the arrays can be to compare the numerical values ​​of the sub-data corresponding to the same time in each of the arrays to be identified to determine the numerical difference; calculate and determine the rate of change of each sub-data in each of the arrays to be identified, compare the magnitudes of the rates of change of the sub-data corresponding to the same time in each of the arrays to be identified to determine the rate of change difference; and jointly determine the numerical difference and the rate of change difference as the difference between the arrays.

[0083] Step S30: If a target array with an array difference exceeding a preset difference threshold is detected in each of the arrays to be identified, then the data in the target array is determined to be abnormal data.

[0084] In this embodiment, specifically, the difference degree of each array is compared with a preset difference degree threshold to detect whether the difference degree of each array exceeds the preset difference degree threshold. If a target array with an array difference degree exceeding the preset difference degree threshold is detected in each of the arrays to be identified, the data in the target array is determined to be abnormal data. If no target array with an array difference degree exceeding the preset difference degree threshold is detected in each of the arrays to be identified, it is determined that there is no abnormal data in each of the arrays to be identified.

[0085] In one feasible approach, if there is more than one array difference degree, each array difference degree corresponds to a difference degree threshold. If, in each of the arrays to be identified, a target array is detected where the difference degree of each array exceeds a preset difference degree threshold, then the data in the target array is determined to be abnormal data. For example, if the array difference degree includes numerical difference degree and rate of change difference degree, then the numerical difference degree corresponds to the numerical difference degree threshold, and the rate of change difference degree corresponds to the rate of change difference degree threshold. If, in each of the arrays to be identified, a target array is detected where the numerical difference degree exceeds a preset numerical difference degree threshold, and the rate of change difference degree exceeds a preset rate of change difference degree threshold, then the target array is determined to be abnormal data.

[0086] Optionally, the method for identifying abnormal vehicle data further includes:

[0087] When abnormal data is detected, an alarm message corresponding to the abnormal data is generated and output.

[0088] In this embodiment, specifically, when abnormal data is detected at any stage of the vehicle abnormal data identification method, the abnormal data information corresponding to the abnormal data is determined, and a corresponding alarm information is generated based on the abnormal data information. The alarm information is then output to the electronic device of the user or relevant monitoring personnel. The alarm information includes the abnormal data information, which includes the specific value of the abnormal data, the time information corresponding to the abnormal data, the number of the detection unit corresponding to the abnormal data, the location information of the detection unit corresponding to the abnormal data, and / or the vehicle information corresponding to the abnormal data. The output form of the alarm information can be SMS, telephone, indicator light, prompt message, alarm sound, etc.

[0089] In this embodiment, by acquiring at least one set of arrays to be identified corresponding to a preset time period, comparing each array to determine the array difference degree corresponding to each array, the comparison of array differences is realized. Then, if a target array with an array difference degree exceeding a preset difference degree threshold is detected in each array to be identified, the data in the target array is identified as abnormal data. This realizes the identification of abnormal data based on the difference degree between arrays. Compared with the difference between individual data corresponding to a single moment, the difference degree between arrays not only includes the difference in the numerical value between arrays, but also reflects the difference in the data change of different arrays. Therefore, abnormal data can be judged from both the numerical value and the data change. Regardless of whether the fluctuation range of abnormal data is large or small, the abnormal fluctuation of data can be accurately identified by combining the data change, overcoming the technical problem of low accuracy of abnormal data identification in the prior art.

[0090] Furthermore, referring to Figure 5Based on the above embodiments of this application, in another embodiment of this application, the same or similar content as the above embodiments can be referred to the above description, and will not be repeated hereafter. In this regard, the array difference degree includes the rate of change difference degree, and the step of comparing each of the arrays to be identified to determine the array difference degree corresponding to each of the arrays to be identified includes:

[0091] Step S21: Determine the rate of change array corresponding to each of the arrays to be identified;

[0092] In this embodiment, it should be noted that the array difference degree includes the rate of change difference degree, which is the difference between the rate of change of data in the array and the rate of change of data in other arrays. The rate of change array is composed of the rate of change corresponding to each sub-data in the group. The rate of change corresponding to each sub-data in the group can be determined by a preset rate of change algorithm or by first-order derivative.

[0093] Specifically, the rate of change corresponding to each sub-data in each of the arrays to be identified is determined, and one or more rates of change corresponding to the same array to be identified are combined into a rate of change array to obtain the rate of change array corresponding to each of the arrays to be identified.

[0094] Optionally, the step of determining the rate of change array corresponding to each of the arrays to be identified includes:

[0095] Step S211: Obtain the previous frame sub-data and the next frame sub-data of two adjacent frames in each of the arrays to be identified, as well as the time difference between the next frame sub-data and the previous frame sub-data.

[0096] Step S212: Calculate the ratio of the difference between the next frame sub-data and the previous frame sub-data to the time difference to obtain the rate of change sub-data. The rate of change array consists of at least one rate of change sub-data.

[0097] In this embodiment, specifically, the preceding and following frame sub-data of two adjacent frames in each of the arrays to be identified are obtained, as well as the time difference between the following and preceding frame sub-data. The difference between the following and preceding frame sub-data is calculated, and the ratio of the difference to the time difference is used as the rate of change sub-data corresponding to the following frame sub-data. The rate of change sub-data corresponding to some or all of the sub-data in each array to be identified is calculated and determined. The rate of change sub-data corresponding to the same array to be identified are arranged sequentially to form a rate of change array, thus obtaining the rate of change array corresponding to each array to be identified.

[0098] In one feasible approach, refer to Figure 6 and Figure 7 , Figure 6This application provides a schematic diagram of the array to be identified in one possible implementation. Figure 6 In the table, T1, T2, T3, and T4 are the temperature probe numbers, and t1, t2, t3, t4, and t5 are sequentially arranged time points. The time difference between each time point and its adjacent time point is one time unit, where t1 is the earliest time point and t5 is the latest time point. Each column in the table represents a set of arrays to be identified, and each value is the temperature detected by the corresponding temperature probe at the corresponding time point. The rate of change for each time point is obtained by subtracting the temperature of the previous time point from the temperature at each time point and dividing by the time difference. The calculated rate of change of temperature in each of the identified arrays is as follows: Figure 7 As shown, Figure 7 A schematic diagram of the rate of change array corresponding to the array to be identified in one possible implementation of this application. Figure 7 In the table, T1, T2, T3, and T4 are the numbers of the temperature probes, and t2, t3, t4, and t5 are the time points arranged in sequence, with t2 being the earliest time point and t5 being the latest time point. Each column in the table is an array of rates of change, and each value is the rate of change of the temperature at the corresponding time point compared to the temperature at the previous time point.

[0099] In another feasible approach, refer to Figure 8 and Figure 9 , Figure 8 A schematic diagram of the array to be identified in another possible implementation provided in this application. Figure 8 In the table, V1, V2, V3, and V4 are the cell numbers, and t1, t2, t3, t4, t5, t6, and t7 are sequentially arranged time points. The time difference between each time point and its adjacent time point is one time unit, where t1 is the earliest time point and t7 is the latest time point. Each column in the table represents a group of cells to be identified, and each value is the voltage of the corresponding cell. The rate of change at each time point is obtained by subtracting the voltage difference from the previous time point and dividing by the time difference. The calculated rate of change of voltage in each of the identified groups is as follows: Figure 9 As shown, Figure 9 A schematic diagram of the rate of change array corresponding to the array to be identified in another possible implementation provided in this application. Figure 9 V1, V2, V3, and V4 are the cell numbers, and t2, t3, t4, t5, t6, and t7 are the time points arranged in sequence, with t2 being the earliest time point and t7 being the latest time point. Each column in the table is an array of rates of change, and each value is the rate of change of the voltage at the corresponding time point compared to the voltage at the previous time point.

[0100] Step S22: Compare the various rate of change arrays to determine the Euclidean distance between them;

[0101] In this embodiment, specifically, the various rate of change arrays are compared between the arrays to calculate and determine the Euclidean distance between them. The specific calculation method of the Euclidean distance is similar to that of the prior art and will not be described in detail here.

[0102] In one feasible manner, Figure 7 The table shown illustrates how the Euclidean distance between the rate of change arrays corresponding to each temperature probe and the rate of change arrays corresponding to each temperature probe can be calculated to obtain the following result: Figure 10 The results shown Figure 10 This is a schematic diagram illustrating the Euclidean distance corresponding to the array to be identified in one possible implementation of this application. Figure 10 In this context, T1, T2, T3, and T4 are the numbers of the temperature probes. The Euclidean distance between the rate of change arrays corresponding to any two determined temperature probes is calculated as follows: Figure 10 As shown in the image.

[0103] In another feasible approach, Figure 9 The table shown illustrates how calculating the Euclidean distance between the rate of change arrays corresponding to each individual cell and the rate of change arrays corresponding to each individual cell yields the following result: Figure 11 The results shown Figure 11 A schematic diagram of the Euclidean distance corresponding to the array to be identified in another possible implementation provided in this application. Figure 11 V1, V2, V3, and V4 are the cell numbers of individual cells. The Euclidean distance between the rate of change arrays corresponding to any two individual cells is calculated as follows: Figure 11 As shown in the image.

[0104] Step S23: Determine the rate of change difference of each of the arrays to be identified according to the Euclidean distances.

[0105] In this embodiment, specifically, the rate of change difference of each of the arrays to be identified is determined according to the Euclidean distances.

[0106] For example, the array difference can be the difference between each of the arrays to be identified and other arrays to be identified besides itself, or it can be the difference between each array to be identified and the average level of all arrays to be identified.

[0107] For example, the method of determining the array difference degree corresponding to each of the arrays to be identified based on each of the Euclidean distances can be to compare each of the Euclidean distances with a preset standard Euclidean distance, and use the difference between each of the Euclidean distances and the preset standard Euclidean distance as the array difference degree corresponding to each of the arrays to be identified. The standard Euclidean distance can be determined based on big data and actual testing, or it can be the average value of each of the Euclidean distances.

[0108] Optionally, the step of determining the rate of change difference corresponding to each of the arrays to be identified based on the Euclidean distances includes:

[0109] Step S231: Calculate the first average value of the Euclidean distance corresponding to each of the rate of change arrays, and the second average value of each of the first average values;

[0110] In this embodiment, specifically, the first average value of the Euclidean distance corresponding to each of the rate of change arrays is calculated, and the average value of each of the first average values ​​is calculated to obtain the second average value, which is the average Euclidean distance of all Euclidean distances corresponding to the preset time period to be identified.

[0111] In one feasible approach, refer to Figure 10 , Figure 10 The values ​​in the rows corresponding to DiAvg are the first average of the Euclidean distances for each of the aforementioned rate of change arrays. DiAvg for T1 is the average Euclidean distance between the rate of change array corresponding to T1 and the corresponding rate of change arrays for T1, T2, T3, and T4. DiAvg for T2 is the average Euclidean distance between the rate of change array corresponding to T2 and the corresponding rate of change arrays for T1, T2, T3, and T4. DiAvg for T3 is the average Euclidean distance between the rate of change array corresponding to T3 and the corresponding rate of change arrays for T1, T2, T3, and T4. DiAvg for T4 is the average Euclidean distance between the rate of change array corresponding to T4 and the corresponding rate of change arrays for T1, T2, T3, and T4. Figure 10 The values ​​in the row corresponding to Avg are the second average values.

[0112] In another feasible approach, refer to Figure 11 , Figure 11The values ​​in the rows corresponding to DiAvg are the first average of the Euclidean distances for each of the aforementioned rate of change arrays. DiAvg for V1 is the average Euclidean distance between the rate of change array corresponding to V1 and the respective rate of change arrays corresponding to V1, V2, V3, and V4. DiAvg for V2 is the average Euclidean distance between the rate of change array corresponding to V2 and the respective rate of change arrays corresponding to V1, V2, V3, and V4. DiAvg for V3 is the average Euclidean distance between the rate of change array corresponding to V3 and the respective rate of change arrays corresponding to V1, V2, V3, and V4. DiAvg for V4 is the average Euclidean distance between the rate of change array corresponding to V4 and the respective rate of change arrays corresponding to V1, V2, V3, and V4. Figure 11 The values ​​in the row corresponding to Avg are the second average values.

[0113] Step S232: The difference between the first average value and the second average value corresponding to each of the rate of change arrays is determined as the rate of change difference degree corresponding to each of the rate of change arrays.

[0114] In this embodiment, specifically, the difference between the first average value and the second average value corresponding to each of the rate of change arrays is calculated and determined, and the difference between the first average value and the second average value corresponding to each of the rate of change arrays is determined as the rate of change difference degree corresponding to each of the rate of change arrays.

[0115] In one feasible approach, refer to Figure 10 By calculating the difference between DiAvg and Avg for T1, T2, T3 and T4 respectively, the degree of difference in the rate of change for each of T1, T2, T3 and T4 can be obtained.

[0116] In another feasible approach, refer to Figure 11 By calculating the difference between DiAvg and Avg for V1, V2, V3 and V4 respectively, the degree of difference in the rate of change for each of V1, V2, V3 and V4 can be obtained.

[0117] In this embodiment, by detecting the difference in the rate of change, false alarms of non-abnormal numerical deviations caused by differences in the state of the detected individual can be effectively avoided, and abnormal data with frequent fluctuations in value can be accurately identified. Compared with the method of comparing the numerical difference of a single data point, this method can effectively improve the accuracy of abnormal data identification.

[0118] Furthermore, embodiments of this application also provide an abnormal data identification device, which is applied to an abnormal data identification equipment, and the abnormal data identification device includes:

[0119] The acquisition module is used to acquire at least one set of arrays to be identified corresponding to a preset time period;

[0120] The difference determination module is used to compare the arrays to be identified and determine the array difference degree of each array to be identified.

[0121] The abnormal data determination module is used to determine the data in the target array as abnormal data if a target array with an array difference exceeding a preset difference threshold is detected in each of the arrays to be identified.

[0122] Optionally, the difference determination module is further configured to:

[0123] Determine the rate of change array corresponding to each of the arrays to be identified;

[0124] The Euclidean distance between the various rate of change arrays is determined by comparing the arrays.

[0125] Based on the Euclidean distances described, the rate of change difference corresponding to each of the arrays to be identified is determined.

[0126] Optionally, the difference determination module is further configured to:

[0127] Calculate the first average value of the Euclidean distance corresponding to each of the aforementioned rate of change arrays, and the second average value of each of the first average values;

[0128] The difference between the first average value and the second average value corresponding to each of the rate of change arrays is determined as the rate of change difference degree corresponding to each of the rate of change arrays.

[0129] Optionally, the difference determination module is further configured to:

[0130] Obtain the preceding and following sub-data of two adjacent frames in each of the arrays to be identified, as well as the time difference between the following and preceding sub-data.

[0131] The ratio of the difference between the subsequent frame sub-data and the previous frame sub-data to the time difference is calculated to obtain the rate of change sub-data. The rate of change array consists of at least one rate of change sub-data.

[0132] Optionally, the abnormal data identification device further includes a time period determination module, which is used to:

[0133] Obtain at least one current operating data of the vehicle;

[0134] Detect whether there is any suspected abnormal data in each of the current running data that exceeds the corresponding preset first threshold range;

[0135] If suspected abnormal data exceeding the corresponding preset first threshold range is detected in each of the current operating data, then a preset time period to be identified is determined based on the suspicious time point corresponding to the suspected abnormal data.

[0136] Optionally, the module for determining the time period to be identified is further configured to:

[0137] If suspected abnormal data exceeding the corresponding preset first threshold range is detected in each of the current running data, then it is determined whether the suspected abnormal data exceeds the preset second threshold range.

[0138] If the suspected abnormal data exceeds the preset second threshold range, then the suspected abnormal data is determined to be abnormal data;

[0139] If the suspected abnormal data does not exceed the preset second threshold range, then the preset time range from the suspected time point corresponding to the suspected abnormal data is determined as the preset time period to be identified.

[0140] Optionally, the abnormal data identification device further includes an alarm module, and the time period to be identified determination module is used for:

[0141] When abnormal data is detected, an alarm message corresponding to the abnormal data is generated and output.

[0142] The abnormal data identification device provided by this invention employs the vehicle abnormal data identification method in the above embodiments, solving the technical problem of low accuracy in abnormal data identification in the prior art. Compared with the prior art, the beneficial effects of the abnormal data identification device provided by this invention are the same as those of the vehicle abnormal data identification method provided in the above embodiments, and other technical features in this abnormal data identification device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0143] Furthermore, embodiments of the present invention provide an electronic device, the electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the vehicle abnormal data identification method described in the above embodiments.

[0144] The following is for reference. Figure 12The diagram illustrates a structural schematic of an electronic device suitable for implementing embodiments of the present disclosure. The electronic devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 12 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0145] like Figure 12 As shown, an electronic device may include a processing unit (such as a central processing unit, graphics processing unit, etc.) that can perform various appropriate actions and processes based on a program stored in read-only memory (ROM) or a program loaded from a storage device into random access memory (RAM). The RAM also stores various programs and arrays required for the operation of the electronic device. The processing unit, ROM, and RAM are interconnected via a bus. Input / output (I / O) interfaces are also connected to the bus.

[0146] Typically, the following systems can be connected to the I / O interface: input devices including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices including, for example, magnetic tapes, hard disks, etc.; and communication devices. Communication devices allow electronic devices to communicate wirelessly or wiredly with other devices to exchange arrays. Although electronic devices with various systems are shown in the figures, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems may be implemented alternatively.

[0147] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device, or installed from a ROM. When the computer program is executed by a processing device, it performs the functions defined above in the methods of embodiments of this disclosure.

[0148] The electronic device provided by this invention employs the vehicle anomaly data identification method in the above embodiments, solving the technical problem of low accuracy in anomaly data identification in the prior art. Compared with the prior art, the beneficial effects of the electronic device provided by the embodiments of this invention are the same as those of the vehicle anomaly data identification method provided in the above embodiments, and other technical features in this electronic device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0149] It should be understood that various parts of this disclosure can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics may be combined in any suitable manner in one or more embodiments or examples.

[0150] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

[0151] Furthermore, this embodiment provides a computer-readable storage medium having computer-readable program instructions stored thereon, the computer-readable program instructions being used to execute the vehicle abnormal data identification method in the above embodiment.

[0152] The computer-readable storage medium provided in this embodiment of the invention may be, for example, a USB flash drive, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0153] The aforementioned computer-readable storage medium may be included in an electronic device or may exist independently without being assembled into an electronic device.

[0154] The aforementioned computer-readable storage medium carries one or more programs. When the aforementioned one or more programs are executed by an electronic device, the electronic device causes the electronic device to: acquire at least one set of arrays to be identified corresponding to a preset time period to be identified; compare the arrays to be identified among themselves to determine the array difference degree corresponding to each array to be identified; and if a target array with an array difference degree exceeding a preset difference degree threshold is detected in each of the arrays to be identified, then the data in the target array is determined to be abnormal data.

[0155] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0156] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0157] The modules described in the embodiments of this disclosure can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0158] The computer-readable storage medium provided by this invention stores computer-readable program instructions for executing the above-described vehicle anomaly data identification method, thereby solving the technical problem of low accuracy in anomaly data identification in the prior art. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this invention are the same as those of the vehicle anomaly data identification method provided in the above-described embodiments, and will not be repeated here.

[0159] Furthermore, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the vehicle abnormal data identification method described above.

[0160] The computer program product provided in this application solves the technical problem of low accuracy in identifying abnormal data in the prior art. Compared with the prior art, the beneficial effects of the computer program product provided in the embodiments of this invention are the same as the beneficial effects of the vehicle abnormal data identification method provided in the above embodiments, and will not be repeated here.

[0161] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent scope of this application.

Claims

1. An abnormal data identification method for a vehicle, characterized by, The vehicle abnormal data identification method comprises the following steps: Obtaining at least one set of to-be-identified arrays corresponding to a preset to-be-identified time period; Comparing each to-be-identified array with each other to-be-identified array to determine the array difference degree corresponding to each to-be-identified array; If a target array with an array difference degree exceeding a preset difference degree threshold is detected in each to-be-identified array, the data in the target array is determined as abnormal data; The array difference degree comprises a change rate difference degree, and the step of comparing each to-be-identified array with each other to-be-identified array to determine the array difference degree corresponding to each to-be-identified array comprises: Determining a change rate array corresponding to each to-be-identified array, wherein the to-be-identified array is arranged in time sequence according to single data at a single time point detected by a detection unit in a vehicle terminal in a preset to-be-identified time period, and the detection unit is a plurality of temperature probes at different positions in a battery pack or a detection unit for voltage detection of each single battery cell; Comparing each change rate array with each other change rate array to determine the Euclidean distance between each change rate array; According to each Euclidean distance, the change rate difference degree corresponding to each to-be-identified array is determined.

2. The abnormal data identification method of a vehicle according to claim 1, characterized by, The step of determining the change rate difference degree corresponding to each to-be-identified array according to each Euclidean distance comprises: Calculating the first average value of the Euclidean distance corresponding to each change rate array, and the second average value of each first average value; The difference between the first average value and the second average value corresponding to each change rate array is determined as the change rate difference degree corresponding to each change rate array.

3. The abnormal data identification method of a vehicle according to claim 1, characterized by, The step of determining the change rate array corresponding to each to-be-identified array comprises: Obtaining the previous frame sub-data and the next frame sub-data of adjacent two frames in each to-be-identified array, and the time difference between the next frame sub-data and the previous frame sub-data; The ratio of the difference between the next frame sub-data and the previous frame sub-data to the time difference is calculated to obtain a change rate sub-data, and the change rate array is composed of at least one change rate sub-data.

4. The abnormal data identification method of a vehicle according to claim 1, characterized by, Before the step of obtaining at least one set of to-be-identified arrays corresponding to a preset to-be-identified time period, the following steps are further included: Obtaining at least one current running data of the vehicle; Detecting whether there is suspected abnormal data exceeding a preset first threshold range in each current running data; If suspected abnormal data exceeding a preset first threshold range is detected in each current running data, a preset to-be-identified time period is determined according to the suspicious time point corresponding to the suspected abnormal data.

5. The abnormal data identification method of a vehicle according to claim 4, characterized by, The step of determining a preset to-be-identified time period according to the suspicious time point corresponding to the suspected abnormal data if suspected abnormal data exceeding a preset first threshold range is detected in each current running data comprises: If suspected abnormal data exceeding a preset first threshold range is detected in each current running data, it is judged whether the suspected abnormal data exceeds a preset second threshold range; If the suspected abnormal data exceeds a preset second threshold range, the suspected abnormal data is determined as abnormal data. If the suspected abnormal data does not exceed the preset second threshold range, a preset time range from a suspicious time point corresponding to the suspected abnormal data is determined as a preset to-be-identified time period.

6. The abnormal data identification method for vehicle according to any one of claims 1 to 5, characterized by, The abnormal data identification method of the vehicle further includes: When abnormal data is detected, alarm information corresponding to the abnormal data is generated and output.

7. An abnormal data identifying device characterized by comprising: The abnormal data identification device includes: An acquisition module is configured to acquire at least one set of to-be-identified arrays corresponding to a preset to-be-identified time period. A difference degree determination module is configured to compare each of the to-be-identified arrays with each other to determine an array difference degree corresponding to each of the to-be-identified arrays. An abnormal data determination module is configured to determine data in a target array as abnormal data if the array difference degree of the target array exceeds a preset difference degree threshold in each of the to-be-identified arrays. The difference degree determination module is further configured to: determine a change rate array corresponding to each of the to-be-identified arrays, wherein the to-be-identified array is arranged in time sequence according to single data at a single moment detected by a detection unit in a vehicle terminal in a preset to-be-identified time period, the detection unit is a plurality of temperature probes at different positions in a battery pack or a detection unit for voltage detection of each single battery cell; compare each of the change rate arrays with each other to determine an Euclidean distance between the change rate arrays; and determine a change rate difference degree corresponding to each of the to-be-identified arrays according to each of the Euclidean distances.

8. An electronic device, comprising: The electronic device includes: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the steps of the abnormal data identification method of the vehicle according to any one of claims 1 to 6.

9. A storage medium, characterized by The storage medium is a computer readable storage medium, and the computer readable storage medium stores a program for implementing the abnormal data identification method of the vehicle, and the program is executed by the processor to implement the steps of the abnormal data identification method of the vehicle according to any one of claims 1 to 6.

Images