Vehicle early warning method, device, electronic device and storage medium

Abstract

The present application provides a vehicle early warning method, device, electronic device and storage medium, belonging to the field of vehicle technology. The method includes: obtaining the vehicle-connected data of the current vehicle, the vehicle-connected data including the MCU fault code of the current vehicle; dividing the vehicle-connected data into multiple travel data; in the multiple travel data, simultaneously determining the target travel data in which the MCU fault code appears as a first preset fault code in a parallel processing manner; if the number of times the first preset fault code appears in the target travel data is greater than the preset number, outputting a warning signal. Using the vehicle early warning method, device, electronic device and storage medium provided by the present application, it is possible to issue early warnings for vehicle component failures to reduce the probability of traffic accidents.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of vehicle technology, and specifically, to a vehicle early warning method, device, electronic device, and storage medium. Background Art

[0002] New energy vehicles have excellent performance such as environmental protection and energy saving, and their market share has gradually increased. However, since new energy vehicle technology is still immature, there are major problems with battery safety.

[0003] When problems occur with some components on a vehicle, some of the vehicle's functions may fail, leading to traffic accidents.

[0004] For example, a vehicle is equipped with a CPLD (Complex Programmable Logic Device) chip, which is a diagnostic chip used to diagnose voltage, current, and drive faults. When a drive fault or status fault occurs in the CPLD chip on a vehicle, the vehicle will lose its forward momentum and can only slide forward by inertia, which can easily lead to traffic accidents. Summary of the Invention

[0005] The present application provides a vehicle early warning method, device, electronic device and storage medium, which are intended to provide early warning of component failures on a vehicle to reduce the probability of traffic accidents.

[0006] A first aspect of the present application provides a vehicle early warning method, the method comprising:

[0007] Obtaining vehicle-connected data of the current vehicle, wherein the vehicle-connected data includes the MCU fault code of the current vehicle;

[0008] Splitting the vehicle-connected data into multiple pieces of travel data;

[0009] Among the plurality of travel data, simultaneously determining target travel data in which the MCU fault code is a first preset fault code in a parallel processing manner;

[0010] When the number of times the first preset fault code appears in the target travel data is greater than a preset number, a warning signal is output.

[0011] Optionally, the vehicle-connected data is divided into multiple pieces of travel data, including:

[0012] Using a trained early warning model, multiple MCU fault codes in the connected vehicle data are identified;

[0013] Identify abnormal values ​​in multiple MCU fault codes;

[0014] The vehicle-connected data is divided into multiple travel data using the abnormal value as a segmentation point.

[0015] Optionally, determine abnormal values ​​in multiple MCU fault codes, including:

[0016] Calculate the interval between two adjacent MCU fault codes in the vehicle-connected data;

[0017] When the interval duration is longer than a preset duration, the MCU fault code with the later timestamp among two adjacent MCU fault codes is used as the abnormal value.

[0018] Optionally, among the multiple pieces of travel data, simultaneously determining target travel data in which the MCU fault code is a first preset fault code in a parallel processing manner includes:

[0019] Among the plurality of travel data, simultaneously determining, in a parallel processing manner, invalid travel data in which the MCU fault code is a second preset fault code;

[0020] Eliminating the invalid travel data from the plurality of travel data to obtain valid travel data;

[0021] From the plurality of valid travel data, target travel data in which the MCU fault code is a first preset fault code is determined.

[0022] Optionally, when the number of times the first preset fault code appears in the target travel data is greater than a preset number, outputting a warning signal includes:

[0023] When the number of times the first preset fault code appears in the target travel data is greater than a preset number, recording the current vehicle status information, the status information including: chassis number, number of times the drive fault signal value appears, motor number, and drive type;

[0024] When the status information is consistent with the preset status information, an early warning signal is output.

[0025] Optionally, the early warning model is trained by the following method:

[0026] The model is trained based on the vehicle-connected data of multiple vehicles and the corresponding multiple travel data to obtain the early warning model.

[0027] Optionally, the model is trained based on the connected vehicle data of multiple vehicles and their corresponding multiple trip data, including:

[0028] Cleaning abnormal data in the vehicle-connected data of the plurality of vehicles to obtain cleaned vehicle-connected data;

[0029] The model is trained based on the cleaned vehicle-connected data and the corresponding multiple travel data to obtain the early warning model.

[0030] A second aspect of the present application provides a vehicle warning device, the device comprising:

[0031] An acquisition module is used to acquire vehicle-connected data of the current vehicle, wherein the vehicle-connected data includes an MCU fault code of the current vehicle;

[0032] A segmentation module, configured to segment the vehicle-connected data into multiple pieces of travel data;

[0033] a target travel data determination module, configured to determine, among the plurality of travel data, target travel data in which the MCU fault code is a first preset fault code, where the first preset fault code is used to indicate a CPLD fault;

[0034] The early warning module is used to simultaneously determine, in a parallel processing manner, target travel data in which the MCU fault code is a first preset fault code from among the multiple travel data.

[0035] A third aspect of an embodiment of the present application provides an electronic device, including:

[0036] one or more processors; and

[0037] One or more machine-readable media having instructions stored thereon, when executed by the one or more processors, enable the electronic device to execute the vehicle warning method as described in the first aspect of the embodiment of the present application.

[0038] A fourth aspect of an embodiment of the present application provides one or more machine-readable storage media having instructions stored thereon, which, when executed by one or more processors, enable the processors to execute the vehicle warning method as described in the first aspect of the embodiment of the present application.

[0039] The vehicle early warning method provided in this application can determine that a component of the current vehicle is faulty if a first preset fault code appears more than a preset number of times in target trip data, and then output a warning signal, thereby notifying the user in advance of the fault. After receiving the warning signal, the user can repair the current vehicle, thereby reducing the occurrence of traffic accidents. For example, when a CPLD chip on a vehicle is faulty, a warning signal will be output, notifying the user that the CPLD has a driver failure and that the vehicle is at risk of losing forward power. After the user is aware of the risk of losing forward power, the vehicle can be repaired in a timely manner.

[0040] In addition, since there are a large number of vehicles on the market that have components such as chips, if manual monitoring of chip failures is used to issue early warnings, it will undoubtedly increase labor costs. The present application can automatically determine the component failure of the current vehicle and issue an early warning when it detects that the number of times the first preset fault code appears in the target travel data is greater than the preset number, without the need for manual monitoring and early warning, which greatly reduces labor costs.

[0041] In addition, the present application can also divide the vehicle-connected data of the current vehicle into multiple travel data, and then process each travel data in parallel, and simultaneously determine the target travel data from each travel data to determine whether the components of the current vehicle have failed, and finally issue an early warning. This method of processing each travel data in parallel can output the early warning signal faster and improve the early warning speed. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0043] Figure 1 This is a flowchart of the steps of a vehicle warning method proposed in Example 1 of the present application;

[0044] Figure 2 Schematic diagram of the MCU fault signal curve proposed in Example 1 of the present application;

[0045] Figure 3 This is the structural feature of a vehicle warning device proposed in Example 2 of this application. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0047] Example 1

[0048] See also Figure 1As shown, the present application provides a vehicle early warning method, which can be used in an early warning model to provide early warnings for components on the vehicle. For example, it can provide early warnings for CPLD chip driver failures on the vehicle, and it can also provide early warnings for battery depletion on the vehicle. The method specifically includes the following steps:

[0049] Step 101: Acquire vehicle-connected data of the current vehicle, where the vehicle-connected data includes the MCU fault code of the current vehicle.

[0050] In this application, vehicle-connected data is established by associating a vehicle-connected data table with a vehicle information table. The vehicle-connected data table is vehicle data related to the current vehicle status uploaded via CAN signals; vehicle information is used to indicate the type of vehicle, for example, whether the vehicle is a Shanghai-driven or honeycomb-driven vehicle. Shanghai-driven refers to fuel cell electric vehicles and pure electric cars produced by Shanghai Electric Drive Company; honeycomb-driven refers to fuel cell electric vehicles and pure electric cars produced by Honeycomb Electric Drive Company. Therefore, the integrated vehicle-connected data includes not only vehicle data related to the current vehicle, but also the vehicle type of the vehicle.

[0051]

[0052] Table 1

[0053] Specifically, this application obtains the chassis number, real-time registration date of the data, standard registration date of the data, MCU (Microcontroller Unit) fault code and data source type related to the current vehicle from the vehicle information table; obtains the motor number and sales status related to the current vehicle from the vehicle information table, and finally integrates them to form the vehicle information data shown in Table 1.

[0054]

[0055] Table 2

[0056] Each vehicle has a unique chassis number, which uniquely identifies the current vehicle. The standard registration date of the data refers to the exact registration date when the data source is registered in the vehicle-connected data table. The real-time registration date of the data refers to the current registration date when the data source is registered in the vehicle-connected data table. As shown in Table 2, an MCU fault code of 35 indicates a CPLD status fault; an MCU fault code of 39 indicates a CPLD driver fault; an MCU fault code of 40 indicates an MCU overcurrent fault; an MCU fault code of 41 indicates an MCU overvoltage fault; and an MCU fault code of 45 or 127 indicates a low battery fault in the MCU. The data source type refers to the data in the vehicle-connected data table, which represents the current vehicle's driving status, such as the vehicle's login status (just started), heartbeat status (steady driving status), and engine-off status.

[0057] Among them, the motor number is used to identify the vehicle type of the vehicle, for example, whether the vehicle is Shanghai drive or honeycomb drive; the sales status is used to indicate the actual sales quantity of the current vehicle.

[0058] Step 102: Segment the vehicle-connected data into multiple pieces of travel data.

[0059] In this application, during the current vehicle driving process, each data in the vehicle-connected data is data that changes in a curve, for example, see Figure 2 As shown, multiple black dots are used to identify multiple MCU fault codes. The multiple MCU fault codes in the vehicle-connected data are curved and continuous. However, since the current vehicle has a long driving time and a long engine-off time during a day's use, it is necessary to divide the vehicle-connected data into trips to split the vehicle-connected data into multiple trip data.

[0060] Each piece of travel data is data generated when the current vehicle is traveling in different time periods, and the intervals between travel data are intervals generated when the vehicle is turned off in different time periods.

[0061] Specifically, a continuous MCU fault signal curve in the vehicle-connected data is divided into multiple travel data, and the time interval between each travel data is longer than the preset time. The preset time can be 15 minutes or 20 minutes, which is set according to the specific actual situation and is not limited by this application. Each black dot on the MCU fault signal curve represents a different signal value. When the signal value is 35 or 39, it indicates that the CPLD has a driver failure.

[0062] For example, see Figure 2As shown, the interval between MCU fault code A at the end of the first trip data and MCU fault code B at the beginning of the second trip data is 15 minutes, which is exactly equal to and exceeds the preset duration. Therefore, the vehicle is currently in a stalled state between 20 and 35 minutes. At this time, the curve before the stall phase can be divided into one trip data, and the curve after the stall phase can be divided into one trip data. Subsequent trip data are judged using this logic, ultimately segmenting a continuous MCU fault signal curve into multiple trip data.

[0063] Since a vehicle may be used frequently by users within a day (or a week or a month), and a large amount of data will be generated each time the vehicle is used, if all the vehicle data is processed one by one, that is, the number of times the MCU fault code is the first preset fault code is counted one by one, the final warning signal will undoubtedly be slower.

[0064] In order to improve the warning speed, this application divides the data generated by the current vehicle in a day into multiple travel data; and then processes each travel data in parallel, that is, using a parallel processing method, each travel data is synchronously processed through step 103 and step 104, without using a serial processing method to process the MCU fault codes generated by the current vehicle one by one, so that it can quickly determine whether a component of the current vehicle has a fault and quickly issue a warning.

[0065] Step 103: Among the multiple pieces of travel data, target travel data in which the MCU fault code is the first preset fault code is simultaneously determined in a parallel processing manner.

[0066] In the present application, the first preset fault code may be a fault code used to characterize a fault in the vehicle's CPLD chip, or may be used to characterize a low-battery fault in the vehicle, etc. The first preset fault code of the present application is determined according to actual conditions.

[0067] For example, the first preset fault code may be 35 or 39, which indicates that the CPLD of the current vehicle has a drive fault or a status fault. Among the divided multiple travel data, the multiple travel data with the MCU fault code 35 or 39 may be used as the multiple target travel data.

[0068] See also Figure 2In the two travel data shown (the curve before point A is the first travel data, and the curve after point B is the second travel data), the first preset fault code 35 appears in the second travel data. Therefore, the second travel data can be used as the target travel data. Similarly, multiple target travel data with 35 or 39 appearing in a complete MCU fault signal curve are finally counted.

[0069] Step 104: When the number of times the first preset fault code appears in the target travel data is greater than a preset number, output a warning signal.

[0070] In the present application, when the number of times the first preset fault code appears in the target travel data is greater than the preset number, it indicates that a component of the current vehicle has failed. Therefore, a warning signal can be output to provide an early warning.

[0071] For example, when the number 35 or 39 appears more than the preset number of times among multiple target travel data, it indicates that the vehicle has a CPLD drive failure or CPLD status failure. Therefore, an early warning signal will be output to remind the user that the vehicle may lose forward power, so as to provide an early warning.

[0072] For example, when the number of times 48 and 127 appear in multiple target travel data is greater than the preset number, it indicates that the vehicle's battery is low on power. Therefore, an early warning signal will be output to remind the user that the vehicle's power supply capacity is insufficient and to charge in advance.

[0073] Specifically, after determining multiple target travel data items, the number of times a first preset fault code appears in each of the multiple target travel data items can be counted simultaneously. The number of times the first preset fault code appears in each of the target travel data items can then be compared with each other, and the number with the largest value can be compared with the preset number. If the largest number is less than or equal to the preset number, it indicates that the determination of a component fault in the current vehicle may be misjudged, and in this case, no warning signal may be output. If the largest number is greater than the preset number, it can be accurately determined that a drive fault exists in a component of the vehicle, and in this case, a warning signal can be output to provide an early warning of the component fault in the current vehicle.

[0074] Among them, the preset number can be 2 or 3, which is set according to the specific situation of the vehicle and is not limited in this application.

[0075] The following example illustrates steps 101 to 104, with a preset number of times being two. A user uses the vehicle between 8:00 AM and 8:30 AM, between 12:00 PM and 1:00 PM, and between 6:00 PM and 6:50 PM. The vehicle generates a continuous stream of connected vehicle data over the course of the day. This data is then divided into three segments: morning, midday, and evening.

[0076] After monitoring, it is determined that the first preset fault code appears in the morning, noon and evening travel data. Therefore, the morning, noon and evening travel data are all determined as target travel data.

[0077] Finally, determine that the number of times the first preset fault code appears in the morning, noon, and evening travel data is 1, 2, and 3 respectively, and then compare the largest value 3 with the preset number. Since 3 is greater than the preset number 2, it is determined that there is a fault in the current vehicle component. At this time, a warning signal can be output to provide an early warning of the fault of the current vehicle component.

[0078] For example, taking a CPLD chip as an example, after monitoring, it is determined that the fault code 35 or 39 appears in the morning, midday, and evening travel data. Therefore, the morning, midday, and evening travel data are all determined as target travel data. Finally, the number of times 35 or 39 appears in the morning, midday, and evening travel data is determined to be 1, 2, and 3, respectively. The largest value, 3, is then compared with the preset number of times. Since 3 is greater than the preset number of times 2, it is determined that the vehicle's CPLD is faulty. At this time, a warning signal can be output to alert the user that the vehicle may be at risk of losing forward power. After the user is informed, the vehicle can be repaired in a timely manner.

[0079] For example, taking a battery as an example, after monitoring, it is determined that the fault code 45 or 127 appears in the morning, noon, and evening travel data. Therefore, the morning, noon, and evening travel data are all determined as target travel data. Finally, the number of times 45 or 127 appears in the morning, noon, and evening travel data is determined to be 1, 2, and 3, respectively. The largest value, 3, is then compared with the preset number of times. Since 3 is greater than the preset number of times 2, it is determined that the current vehicle's battery is low. In this case, a warning signal can be output to alert the user of the low battery, allowing the user to charge the vehicle in a timely manner.

[0080] By adopting a vehicle warning method provided by the present application, when the number of times a first preset fault code appears in the target travel data is greater than the preset number, it can be determined that there is a fault in a component of the current vehicle, and then a warning signal can be output, thereby informing the user in advance that a component of the current vehicle has failed. After knowing the warning signal, the user can repair the current vehicle to reduce the occurrence of traffic accidents.

[0081] In addition, since there are a large number of vehicles on the market that have components such as chips, if manual monitoring of chip failures is used to issue early warnings, it will undoubtedly increase labor costs. The present application can automatically determine the component failure of the current vehicle and issue an early warning when it detects that the number of times the first preset fault code appears in the target travel data is greater than the preset number, without the need for manual monitoring and early warning, which greatly reduces labor costs.

[0082] In addition, the present application can also divide the vehicle-connected data of the current vehicle into multiple travel data, and then process each travel data in parallel, and simultaneously determine the target travel data from each travel data to determine whether the components of the current vehicle have failed, and finally issue an early warning. This method of processing each travel data in parallel can output the early warning signal faster and improve the early warning speed.

[0083] Optionally, the above step 102 may further include the following steps:

[0084] Step 201: using a trained early warning model to identify multiple driving fault signal values ​​in the vehicle-connected data.

[0085] In this step, the model can be trained based on the vehicle-connected data of multiple vehicles and their corresponding multiple travel data to obtain the early warning model.

[0086] Specifically, the model can be trained using continuous vehicle-connected data as input and multiple trip data as output to obtain an early warning model. The obtained early warning model has the ability to divide a continuous vehicle-connected data into trips.

[0087] Before training the model, the vehicle-connected data input into the model needs to be cleaned of abnormal data to ensure that the data input into the model is accurate and valid data that the model can recognize.

[0088] Specifically, abnormal data in the vehicle-connected data of the multiple vehicles can be cleaned to obtain cleaned vehicle-connected data; based on the cleaned vehicle-connected data and its corresponding multiple travel data, a model is trained to obtain the early warning model.

[0089] As shown in Table 1, abnormal data includes: a real-time registration date (tid) that is inconsistent with the standard registration date (dt) of the data, and inaccurate invalid data uploaded to the vehicle data. Invalid data refers to the situation where data from the previous moment is mistakenly uploaded to the vehicle data when uploading the current moment's data. In this case, the previous moment's data is invalid.

[0090] Before inputting the connected vehicle data into the model, this abnormal data can be screened out to ensure that the data input into the model is accurate and valid.

[0091] In addition, when inputting vehicle-connected data into the model, the upload frequency of data for each field may be different. For example, for field A, it is uploaded once every 1S, and for field B, it is uploaded once every 10S. When uploading vehicle-connected data, field A and field B need to be uploaded accordingly at each moment. Since the upload frequency of field B is lower, it is necessary to compensate for the missing data in the middle of field B and upload the compensated field B to ensure the correspondence between the data, so that data of different fields are uploaded at each moment, and finally each output vehicle-connected data has its own corresponding data at the same time.

[0092] Step 202: Determine abnormal values ​​among multiple MCU fault codes.

[0093] In this step, when dividing a continuous MCU fault signal curve into travel data, the division can be based on the abnormal values ​​in multiple MCU fault codes, and the multiple MCU fault codes before the abnormal value are regarded as one section of travel data, and the multiple MCU fault codes after the abnormal value are regarded as another section of travel data. This can be repeated and so on, and a continuous MCU fault signal curve can be divided into multiple travel data.

[0094] Specifically, the following sub-steps may be included:

[0095] Sub-step A1: Calculate the interval between each two adjacent MCU fault codes in the vehicle-connected data.

[0096] See also Figure 2 The MCU fault signal curve shown is composed of multiple MCU fault codes. In this step, the interval duration between each two adjacent MCU fault codes is calculated. In this way, it can be determined whether the interval duration between which two MCU fault codes exceeds the preset duration.

[0097] Specifically, the time interval between two adjacent MCU fault codes can be obtained by subtracting the time stamp of the previous MCU fault code from the time stamp of the next MCU fault code.

[0098] Sub-step A2: When the interval duration is longer than a preset duration, the MCU fault code with the later timestamp among two adjacent MCU fault codes is used as the abnormal value.

[0099] See also Figure 2 As shown, among the multiple MCU fault codes in the first segment of travel data and the second segment of travel data, the interval between each two adjacent MCU fault codes is less than 15 minutes; and the interval between the last MCU fault code A in the first segment of travel data and the initial MCU fault code B in the second segment of travel data is 15 minutes, which is just above the preset duration of 15 minutes. Therefore, the initial MCU fault code B will be regarded as an abnormal value.

[0100] Step 203: Using the abnormal value as a segmentation point, the vehicle-connected data is segmented into multiple travel data.

[0101] After determining the initial MCU fault code as the abnormal value, the multiple MCU fault codes before the abnormal value are regarded as a section of travel data, and the multiple MCU fault codes after the abnormal value are regarded as another section of travel data. This process is repeated and analogous, and a coherent MCU fault signal curve can be divided into multiple travel data.

[0102] For example, using the initial MCU fault code of the second segment of trip data as an outlier, the multiple MCU fault codes before the initial MCU fault code B are considered the first segment of trip data, and the multiple MCU fault codes after the initial MCU fault code B are considered the second segment of trip data. This method can also be used for subsequent data with timestamps later than the second segment of trip data to segment a continuous MCU fault signal curve into multiple segments of trip data.

[0103] Optionally, when the vehicle component for warning is a CPLD chip, the vehicle will also output a warning signal when a battery low power failure is detected in multiple travel data. However, the battery low power failure will not cause the vehicle to lose forward power. If a warning signal is output at this time, it will mislead the user into thinking that the vehicle has lost forward power, affecting the warning effect.

[0104] Therefore, in the process of warning the CPLD chip failure, the phenomenon of battery power failure may falsely report the CPLD failure. In order to filter out the phenomenon of battery power failure, step 103 further includes the following steps:

[0105] Step 301: Determine whether invalid travel data, in which the MCU fault code is a second preset fault code, appears in the plurality of travel data.

[0106] In this step, the second preset fault code is used to represent a battery low power fault. For example, when the second preset fault code 45 or 127 appears in the trip data, the current trip data is determined to be invalid trip data.

[0107] The invalid travel data refers to the travel data in which the battery is low on power.

[0108] Step 302: Eliminate the invalid travel data from the plurality of travel data to obtain valid travel data.

[0109] In this step, invalid travel data can be eliminated from multiple travel data to obtain valid travel data. The valid travel data is travel data with a first preset fault code, or travel data with an overcurrent fault, or travel data with an overvoltage fault.

[0110] Among them, since invalid travel data will affect the warning effect, the invalid travel data can be eliminated from multiple travel data to ensure that the remaining valid travel data does not contain invalid travel data that affects the warning effect, thereby ensuring that the warning given by this application is a CPLD failure, thereby avoiding the occurrence of warning errors.

[0111] Step 303: Determine target travel data in which the MCU fault code is a first preset fault code from multiple valid travel data.

[0112] The vehicle warning method provided by this application allows the target trip data to be determined from the remaining valid trip data. On the one hand, since the remaining valid trip data does not contain invalid trip data that could affect the warning effect, the warning provided by this application is guaranteed to be a CPLD failure, thus avoiding the occurrence of false warnings. On the other hand, when determining the target trip data from multiple valid trip data items, the amount of valid trip data is greatly reduced because the valid trip data has been screened. Therefore, when determining the target trip data from the smaller amount of valid trip data, the amount of data processing is greatly reduced, alleviating the computational load.

[0113] Optionally, when the developer obtains the warning signal, he only knows that the vehicle's CPLD is faulty, but does not know other status information of the vehicle. Therefore, he cannot improve the current vehicle or notify the owner of the CPLD fault of the current vehicle based solely on the vehicle's CPLD fault. In order to facilitate the developer to accurately locate the current vehicle and obtain some information about the current vehicle, step 104 further includes the following steps:

[0114] Step 401: When the number of times the first preset fault code appears in the target travel data is greater than a preset number, record the status information of the current vehicle, the status information including: chassis number, number of times the first preset fault code appears, motor number and drive type.

[0115] In this step, when the maximum number of occurrences of the first preset fault code in the plurality of target travel data is greater than the preset number, the current vehicle status information is obtained from the vehicle-connected data and recorded.

[0116] For example, the number of times the first preset fault code appears in the morning, afternoon, and evening travel data is 1, 2, and 3 respectively. Since the maximum number 3 is greater than the preset number 2, the current vehicle status information can be obtained from the vehicle-connected data at this time.

[0117] Among them, the vehicle's chassis number is used to uniquely identify a current vehicle, which is used to facilitate developers to uniquely identify a current vehicle from multiple vehicles; the number of times the first preset fault code appears is used to facilitate developers to determine the degree of component failure of the current vehicle. The more times the first preset fault code appears, the higher the degree of component failure of the current vehicle; the motor number and drive type are used to drive whether the current vehicle is Shanghai drive or honeycomb drive, so that developers can narrow the scope to find the current vehicle.

[0118] Step 402: When the status information is consistent with the preset status information, output a warning signal.

[0119] The developer's platform stores the preset status information of each vehicle. When a component of the current vehicle fails, the status information of the current vehicle will be sent to the developer's platform. The platform will then verify the status information of the current vehicle. When the verified status information is consistent with the preset status information, it will generate an early warning signal for the current vehicle and push it to the developer. Since the early warning signal carries the status information of the current vehicle, the developer can determine which vehicle component has failed and the severity of the component failure based on the current vehicle status information.

[0120] For example, when the motor number, chassis number, and drive type of the current vehicle correspond one-to-one with the motor number, chassis number, and drive type of a certain vehicle on the platform, a warning signal for the current vehicle is output on the platform; after the developer learns of the warning signal, he or she can notify the owner to repair and inspect the vehicle based on the warning signal.

[0121] Example 2

[0122] Based on the same inventive concept, an embodiment of the present application further provides a vehicle warning device, which includes:

[0123] An acquisition module is used to acquire vehicle-connected data of the current vehicle, wherein the vehicle-connected data includes an MCU fault code of the current vehicle;

[0124] A segmentation module, configured to segment the vehicle-connected data into multiple pieces of travel data;

[0125] a target trip data determination module, configured to simultaneously determine, from the plurality of trip data, target trip data in which the MCU fault code is a first preset fault code, in a parallel processing manner;

[0126] The early warning module is used to output an early warning signal when the number of times the first preset fault code appears in the target travel data is greater than a preset number, and the early warning signal is used to indicate that a driving fault occurs in the current vehicle.

[0127] Optionally, the segmentation module includes:

[0128] An acquisition submodule is used to identify multiple MCU fault codes in the vehicle-connected data using a trained early warning model;

[0129] An abnormal value determination module, used to determine abnormal values ​​among multiple MCU fault codes;

[0130] The segmentation submodule is used to segment the vehicle-connected data into multiple travel data using the abnormal value as a segmentation point.

[0131] Optionally, the outlier determination module includes:

[0132] An interval duration calculation module, configured to calculate the interval duration between each two adjacent MCU fault codes in the vehicle-connected data;

[0133] The abnormal value determination submodule is used to use the MCU fault code with the later timestamp among two adjacent MCU fault codes as the abnormal value when the interval duration is longer than a preset duration.

[0134] Optionally, the target travel data determination module includes:

[0135] an invalid trip data determining module, configured to simultaneously determine, in a parallel processing manner, invalid trip data in which the MCU fault code is a second preset fault code from among the plurality of trip data;

[0136] a valid travel data determining module, configured to remove the invalid travel data from the plurality of travel data to obtain valid travel data;

[0137] The target travel data determination submodule is used to determine the target travel data in which the MCU fault code is the first preset fault code from multiple valid travel data.

[0138] Optionally, the early warning module includes:

[0139] a recording module, configured to record the current vehicle status information when the first preset fault code appears in the target travel data more than a preset number of times, the status information including: a chassis number, the number of times the drive fault signal value appears, a motor number, and a drive type;

[0140] The early warning submodule is used to output an early warning signal when the status information is consistent with the preset status information.

[0141] Optionally, the device further comprises:

[0142] The training module is used to train the model based on the vehicle-connected data of multiple vehicles and their corresponding multiple travel data to obtain the early warning model.

[0143] Optionally, the training module includes:

[0144] a cleaning module, configured to clean abnormal data in the vehicle-connected data of the plurality of vehicles to obtain cleaned vehicle-connected data;

[0145] The training submodule is used to train the model based on the cleaned vehicle-connected data and the corresponding multiple travel data to obtain the early warning model.

[0146] Based on the same inventive concept, the present application also provides an electronic device, including:

[0147] one or more processors; and

[0148] One or more machine-readable media having instructions stored thereon, when executed by the one or more processors, enable the electronic device to execute the vehicle warning method provided in Example 1 of the present application.

[0149] Based on the same inventive concept, the present application also provides one or more machine-readable storage media on which instructions are stored, which, when executed by one or more processors, enable the processor to execute the vehicle warning method as described in Example 1 of the present application.

[0150] 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.

[0151] 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.

[0152] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, devices, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0153] The embodiments of the present application 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 application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes 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 produce 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 steps in the process. 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.

[0154] These computer program instructions may also be stored in a computer readable memory that can direct 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 The function specified in one or more boxes.

[0155] 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.

[0156] Although 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 become aware of the basic inventive concepts. 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.

[0157] Finally, it should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or terminal device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or terminal device that includes the element.

[0158] The above is a detailed introduction to the vehicle warning method, device, electronic device and storage medium provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for general technical personnel in this field, based on the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A vehicle early warning method, characterized in that: The method comprises: Obtaining vehicle-connected data of the current vehicle, wherein the vehicle-connected data includes the MCU fault code of the current vehicle; Splitting the vehicle-connected data into multiple pieces of travel data; Among the plurality of travel data, simultaneously determining target travel data in which the MCU fault code is a first preset fault code in a parallel processing manner; outputting a warning signal when the first preset fault code appears in the target travel data for a number greater than a preset number; The vehicle-connected data is divided into multiple travel data, including: Using a trained early warning model, multiple MCU fault codes in the connected vehicle data are identified; Identify abnormal values ​​in multiple MCU fault codes; The vehicle-connected data is divided into multiple travel data using the abnormal value as a segmentation point.

2. The method according to claim 1, characterized in that Identify abnormal values ​​in multiple MCU fault codes, including: Calculate the interval between two adjacent MCU fault codes in the vehicle-connected data; When the interval duration is longer than a preset duration, the MCU fault code with the later timestamp among two adjacent MCU fault codes is used as the abnormal value.

3. The method according to claim 1, characterized in that Among the plurality of travel data, simultaneously determining target travel data in which the MCU fault code is the first preset fault code in a parallel processing manner includes: Among the plurality of travel data, simultaneously determining, in a parallel processing manner, invalid travel data in which the MCU fault code is a second preset fault code; Eliminating the invalid travel data from the plurality of travel data to obtain valid travel data; From the plurality of valid travel data, target travel data in which the MCU fault code is a first preset fault code is determined.

4. The method according to claim 1, wherein When the number of times the first preset fault code appears in the target travel data is greater than a preset number, outputting a warning signal includes: When the number of times the first preset fault code appears in the target travel data is greater than a preset number, recording the current vehicle status information, the status information including: chassis number, number of times the drive fault signal value appears, motor number, and drive type; When the status information is consistent with the preset status information, an early warning signal is output.

5. The method according to claim 1, characterized in that The early warning model is trained by the following method: The model is trained based on the vehicle-connected data of multiple vehicles and the corresponding multiple travel data to obtain the early warning model.

6. The method according to claim 5, characterized in that The model is trained based on the connected vehicle data of multiple vehicles and their corresponding multiple trip data, including: Cleaning abnormal data in the vehicle-connected data of the plurality of vehicles to obtain cleaned vehicle-connected data; The model is trained based on the cleaned vehicle-connected data and the corresponding multiple travel data to obtain the early warning model.

7. A vehicle warning device, characterized in that: The device comprises: An acquisition module is used to acquire vehicle-connected data of the current vehicle, wherein the vehicle-connected data includes an MCU fault code of the current vehicle; A segmentation module, configured to segment the vehicle-connected data into multiple pieces of travel data; a target trip data determination module, configured to simultaneously determine, from the plurality of trip data, target trip data in which the MCU fault code is a first preset fault code, in a parallel processing manner; an early warning module, configured to output an early warning signal when the first preset fault code appears in the target travel data more than a preset number of times, the early warning signal being used to indicate that a driving fault has occurred in the current vehicle; Wherein, the segmentation module includes: An acquisition submodule is used to identify multiple MCU fault codes in the vehicle-connected data using a trained early warning model; An abnormal value determination module, used to determine abnormal values ​​among multiple MCU fault codes; The segmentation submodule is used to segment the vehicle-connected data into multiple travel data using the abnormal value as a segmentation point.

8. An electronic device, characterized in that: include: one or more processors; and One or more machine-readable media having instructions stored thereon, when executed by the one or more processors, enable the electronic device to execute the vehicle warning method according to any one of claims 1 to 6.

9. One or more machine-readable storage media, characterized in that Instructions are stored thereon, which, when executed by one or more processors, enable the processors to execute the vehicle warning method according to any one of claims 1 to 6.

Images