Vehicle power shortage early warning method and device, computer equipment and readable storage medium

Abstract

The invention relates to a vehicle electricity shortage early warning method and device, computer equipment and a readable storage medium. The method comprises the following steps: screening out a target vehicle of which the power lack scene meets a power lack model from a plurality of market vehicles; the power-lack model is used for describing a power-lack scene when the vehicle has a power-lack problem; according to the number of the target vehicles and the parking duration corresponding to the power shortage problem, performing early warning processing on the power shortage problem; the parking duration is the duration of the vehicle from flameout to power shortage. By adopting the method, the accuracy of electricity shortage early warning can be improved.

Description

Technical Field

[0001] The present application relates to the field of vehicle networking technology, and in particular to a vehicle low-battery warning method, device, computer equipment, computer-readable storage medium, and computer program product. Background Art

[0002] With the rapid development of the automotive industry and electronic technology and the diversification of people's demands for vehicle functions, more and more new electronic technologies have been introduced into the automotive industry. The complexity of the automotive architecture and the multitude of functions are accompanied by an increase in the possibility of failure. In the current social environment with the theme of automotive digitalization and safety, the timeliness of automobile fault identification and the convenience of maintenance methods have become urgent technical needs and safety guarantees. At the same time, in order to meet people's continuous pursuit of fresh experience, the cycle of automobile product updates and new product research and development has been continuously compressed, which has brought great challenges to the work of all links of automobile OEMs.

[0003] At present, the application of remote diagnosis technology in the automotive industry has brought new ideas to vehicle fault detection and maintenance. The automotive remote diagnosis system establishes communication between the vehicle and the cloud, solves the distance problem between the target vehicle and the technician, greatly improves the flexibility of the diagnostic service, and selectively collects and stores data of the target vehicle in real time. On the one hand, it can effectively assist in the troubleshooting of problems, and on the other hand, it can provide a data basis for improving the quality of vehicle research and development. However, when the vehicle has a low-power problem, it is often impossible to accurately identify the low-power problem, resulting in low accuracy of the low-power warning. Summary of the invention

[0004] Based on this, it is necessary to provide a vehicle low-battery warning method, device, computer equipment, computer-readable storage medium and computer program product that can improve the accuracy of low-battery warning in response to the above-mentioned technical problems.

[0005] In a first aspect, the present application provides a vehicle power shortage warning method, comprising:

[0006] Screening out target vehicles whose power-loss scenarios meet the power-loss model from multiple market vehicles; the power-loss model is used to describe the power-loss scenario when the vehicle has a power-loss problem;

[0007] According to the number of the target vehicles and the parking time corresponding to the power shortage problem, the power shortage problem is warned; the parking time is the time from the vehicle being turned off to the occurrence of the power shortage problem.

[0008] In one embodiment, before selecting a target vehicle whose low-battery scenario satisfies the low-battery model from a plurality of market vehicles, the method further includes:

[0009] Obtaining power-loss diagnostic information uploaded by a vehicle having the power-loss problem;

[0010] A power failure model for the power failure problem is constructed according to the power failure diagnosis information.

[0011] In one embodiment, constructing a power failure model for the power failure problem according to the power failure diagnosis information includes:

[0012] Acquire key vehicle information in the power-loss diagnosis information; the key vehicle information includes at least one of vehicle mode, power mode, vehicle lock status, vehicle battery voltage, vehicle battery power, and vehicle current consumption;

[0013] The key vehicle information is analyzed and modeled to construct a power shortage model for the power shortage problem.

[0014] In one embodiment, analyzing and modeling the key vehicle information to construct a power shortage model for the power shortage problem includes:

[0015] Analyze and model the key vehicle information to determine the vehicle's operating condition information, network behavior information, and power failure current when the power failure problem occurs;

[0016] A power failure model for the power failure problem is constructed according to the usage condition information, the network behavior information and the power failure current.

[0017] In one embodiment, screening out a target vehicle whose low-battery scenario satisfies the low-battery model from a plurality of market vehicles includes:

[0018] Determine the power failure controller that causes the power failure problem in the vehicle;

[0019] Obtaining vehicle-side data uploaded by each vehicle in the market that uses the same low-power controller;

[0020] When the vehicle-side data of the market vehicle matches the vehicle-side data recorded by the power-loss model, the market vehicle is taken as the target vehicle.

[0021] In one embodiment, the early warning processing of the power shortage problem according to the number of the target vehicles and the parking time corresponding to the power shortage problem includes:

[0022] Determine the scale of the power shortage problem according to the number of the target vehicles;

[0023] Determine the warning level of the power shortage problem according to the occurrence scale and the parking duration; the warning level is inversely proportional to the parking duration and directly proportional to the occurrence scale;

[0024] When the warning level is greater than the preset level threshold, a warning process is performed on the power shortage problem.

[0025] In one embodiment, the early warning processing of the power shortage problem includes:

[0026] Sending the power shortage warning result of the power shortage problem to the business cloud; the power shortage warning result is used to indicate that the power shortage problem is handled according to the power shortage warning result within a preset time period;

[0027] Among them, the business cloud includes R&D cloud, production cloud and after-sales cloud; the preset time is inversely proportional to the warning level.

[0028] In one embodiment, after sending the power shortage warning result of the power shortage problem to the business cloud, the method further includes:

[0029] Obtaining a power-loss processing feedback result returned by the business cloud in response to the power-loss warning result; the power-loss processing feedback result includes at least one of a first feedback result, a second feedback result, and a third feedback result; the first feedback result includes a result of the R&D cloud performing a software upgrade on a vehicle having the power-loss problem; the second feedback result includes a result of the production cloud performing a software upgrade on a production line vehicle; the third feedback result includes a result of the after-sales cloud performing monitoring on vehicle-side data uploaded by the vehicle having the power-loss problem;

[0030] According to the feedback result of the power shortage processing, the number of the target vehicles and the parking time corresponding to the power shortage problem are updated.

[0031] In a second aspect, the present application also provides a vehicle power shortage warning device, comprising:

[0032] A screening module is used to screen out target vehicles whose power-loss scenarios meet a power-loss model from multiple market vehicles; the power-loss model is used to describe the power-loss scenario in which the vehicle is in when the power-loss problem occurs;

[0033] The early warning module is used to perform early warning processing on the power shortage problem according to the number of the target vehicles and the parking time corresponding to the power shortage problem; the parking time is the time from the vehicle being turned off to the occurrence of the power shortage problem.

[0034] In a third aspect, the present application further provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0035] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the above method when executed by a processor.

[0036] In a fifth aspect, the present application also provides a computer program product, including a computer program, which implements the steps of the above method when executed by a processor.

[0037] The above-mentioned vehicle low-battery warning method, device, computer equipment, computer-readable storage medium and computer program product screen out target vehicles whose low-battery scenarios meet the low-battery model from multiple market vehicles. The low-battery model is used to describe the low-battery scenario in which the vehicle is in when the low-battery problem occurs; based on the number of target vehicles and the parking time corresponding to the low-battery problem, the low-battery problem is warned, and the parking time is the time from the vehicle being shut down to the occurrence of the low-battery problem. The low-battery model is used to accurately describe the low-battery scenario when the vehicle has a low-battery problem. Based on the modeling analysis of the low-battery scenario, it is possible to screen out target vehicles in the same low-battery scenario from multiple market vehicles, and determine whether the low-battery problem needs to be warned based on the number of target vehicles and the parking time of the low-battery problem, so that the corresponding processing strategy for the low-battery problem can be determined according to the severity of the low-battery problem, thereby improving the pertinence and accuracy of the low-battery warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0039] FIG1 is a diagram showing an application environment of a vehicle power shortage warning method in one embodiment;

[0040] FIG2 is a schematic diagram of a flow chart of a vehicle power shortage warning method in one embodiment;

[0041] FIG3 is a logic diagram of a vehicle power shortage warning method in one embodiment;

[0042] FIG4 is a schematic flow chart of a vehicle power shortage warning method according to another embodiment;

[0043] FIG5 is a structural block diagram of a vehicle power shortage warning device in one embodiment;

[0044] FIG. 6 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0046] The vehicle power shortage warning method provided in the embodiment of the present application can be applied in the application environment as shown in FIG1 . Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The server 104 can also integrate a power shortage warning system, which can be used to obtain the vehicle data uploaded by the vehicle, construct and analyze the power shortage model, perform power shortage identification and warning processing, etc.

[0047] The server 104 selects target vehicles whose power-loss scenarios meet the power-loss model from multiple market vehicles; the power-loss model is used to describe the power-loss scenario in which the vehicle is in when the power-loss problem occurs; the server 104 performs early warning processing on the power-loss problem based on the number of target vehicles and the parking time corresponding to the power-loss problem; the parking time is the time from the vehicle being turned off to the power-loss problem occurring. Among them, the terminal 102 can be a vehicle-mounted terminal, which is a terminal installed inside the vehicle, such as a remote diagnosis terminal, a vehicle-mounted communication module, a power management module, etc., which can be used to collect vehicle operation data and fault information and upload them to the server 104. The server 104 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0048] In an exemplary embodiment, as shown in FIG2 , a vehicle power shortage warning method is provided, which is described by taking the method applied to the server 104 in FIG1 as an example, including:

[0049] Step S202, selecting a target vehicle whose low-battery scenario satisfies the low-battery model from a plurality of vehicles on the market.

[0050] Among them, the low-battery model is used to describe the low-battery scenario when the vehicle has a low-battery problem.

[0051] Among them, the problem of low battery can be caused by the vehicle's power system (such as battery, controller, power management module, etc.) failing to properly manage power, resulting in rapid battery consumption and the vehicle failing to start or operate normally. Low battery problems are usually related to reasons such as decreased battery performance, abnormal operation of the controller, abnormal power consumption of electrical equipment, or the vehicle not entering sleep mode.

[0052] Among them, the low-battery scenario is used to reflect the vehicle scenario when the vehicle has a low-battery problem. For example, the low-battery scenario may include the vehicle operation mode (such as long-term parking, long-term non-sleep, frequent start, etc.), battery performance, controller working status, ambient temperature and other scenarios when the vehicle has a low-battery problem. For example, the low-battery scenario when the vehicle has a certain low-battery problem is that the vehicle has not been parked for a long time and the battery performance is poor.

[0053] Among them, the target vehicle is a market vehicle whose low-power scenario satisfies the low-power model. In other words, the similarity between the low-power scenario of the target vehicle and the low-power scenario described by the low-power model is higher than a certain threshold or is completely consistent.

[0054] Furthermore, if the power-loss scenarios of multiple vehicles are extremely similar or completely the same, it can be inferred that these vehicles all have the same power-loss problem. The same power-loss problem refers to a power-loss problem caused by the same power-loss reason. For example, if both vehicle A and vehicle B have power-loss problems due to a fault in controller C, it can be considered that vehicle A and vehicle B have the same power-loss problem.

[0055] Exemplarily, the low-battery model may be obtained by extracting data that can be used to describe the low-battery scenario from vehicle-side data uploaded when the vehicle has a low-battery problem, and constructing a model based on the data that is used to describe the low-battery scenario.

[0056] Among them, the market vehicle may be a vehicle that has been put on the market for users to use.

[0057] Optionally, the server may determine the model or vehicle production batch of the vehicle with the low-battery problem, and screen out a target vehicle whose low-battery scenario meets the low-battery model from multiple market vehicles with the same vehicle model or vehicle production batch.

[0058] In a specific implementation, the server can obtain the background data of multiple market vehicles, which may include vehicle-side data uploaded by market vehicles through vehicle-mounted terminals, which may include the battery status, controller behavior, operating conditions, etc. The server runs the power-loss model on the vehicle-side data of these market vehicles, compares the vehicle-side data of these market vehicles with the vehicle-side data recorded in the power-loss model, identifies which market vehicles meet the power-loss scenarios described by the power-loss model, and takes the market vehicles that meet the power-loss scenarios described by the power-loss model as target vehicles, summarizes the vehicle-side data of the target vehicles, and counts the number of target vehicles.

[0059] Exemplarily, the server compares the vehicle-side data of these market vehicles with the vehicle-side data recorded in the low-battery model. The comparison may be a multi-dimensional data comparison, such as comparing multiple data dimensions used to describe low-battery scenarios, such as voltage dimension, current dimension, controller status dimension, operating condition dimension, etc. in the vehicle-side data, and counting the number of dimensions with large differences. When the number is less than a certain threshold, it is determined that the low-battery scenario of the vehicle in this market meets the low-battery model.

[0060] Step S204, performing early warning processing on the power shortage problem according to the number of target vehicles and the parking time corresponding to the power shortage problem.

[0061] In the specific implementation, the server can evaluate the severity of the low-battery problem according to the number of target vehicles and the parking time corresponding to the low-battery problem, and perform corresponding early warning processing.

[0062] For example, the server determines the number of target vehicles by counting how many market vehicles are marked as target vehicles within a certain period of time (1 month or 2 months) in history, or by the number of market vehicles marked as target vehicles after they are put into use on the market. Different numbers of target vehicles reflect different degrees of severity of the power shortage problem. The more target vehicles there are, the more widespread and serious the power shortage problem is.

[0063] Among them, the parking time is the length of time from when the vehicle is turned off to when the power outage occurs. Different parking times reflect the different severity of the power outage problem. If the parking time is short, the vehicle will have a power outage in a short time after being turned off (such as 8 hours or 24 hours, etc.). In this case, the power outage problem is extremely serious, and there may be a very serious fault in the battery or controller. If the parking time is long, it means that the vehicle will have a power outage for a long time after being turned off (such as 30 hours or 48 hours, etc.). In this case, the power outage problem is more serious, and there may be a serious fault in the battery or controller.

[0064] As an example, the server may set a certain number threshold for the number of target vehicles, and a certain duration threshold for the parking duration corresponding to the power shortage problem. For example, if at least one of the number of target vehicles exceeds the number threshold and the parking duration is less than the duration threshold, the power shortage problem is warned. As another example, the server may perform a weighted calculation on the number of target vehicles and the parking duration, and determine whether it is necessary to perform a warning on the power shortage problem according to the weighted calculation result.

[0065] In a specific implementation, the server performs early warning processing on the low-battery problem, and may notify the vehicle manager or owner through text messages, vehicle system prompts, emails, etc., or may send the low-battery warning result of the low-battery problem to the business cloud to instruct the processing of the low-battery problem.

[0066] Further optionally, the server can determine the warning level of the power shortage problem according to the number of target vehicles and the parking time corresponding to the power shortage problem, and perform corresponding warning processing according to the warning level. For example, if the number of target vehicles is large and the power shortage occurs in a very short time, the warning level can be determined as a high warning level, and the power shortage problem can be immediately warned; if the number of target vehicles is large, but the power shortage occurs after a long time, the warning level can be determined as a medium warning level, and the power shortage problem can be warned within a certain period of time; if the number of target vehicles is small, the warning level can be determined as a low warning level, and the owner can be notified to perform vehicle maintenance.

[0067] In the above-mentioned vehicle low-battery warning method, target vehicles whose low-battery scenarios meet the low-battery model are screened out from multiple market vehicles. The low-battery model is used to describe the low-battery scenario in which the vehicle is in when the low-battery problem occurs; based on the number of target vehicles and the parking time corresponding to the low-battery problem, the low-battery problem is warned, and the parking time is the time from the vehicle being shut down to the occurrence of the low-battery problem. The low-battery model is used to accurately describe the low-battery scenario when the vehicle has a low-battery problem. Modeling analysis based on the low-battery scenario can screen out target vehicles in the same low-battery scenario from multiple market vehicles, and determine whether the low-battery problem needs to be warned based on the number of target vehicles and the parking time of the low-battery problem. Therefore, the corresponding handling strategy for the low-battery problem can be determined according to the severity of the low-battery problem, thereby improving the pertinence and accuracy of the low-battery warning.

[0068] In another embodiment, before selecting a target vehicle whose low-battery scenario satisfies a low-battery model from multiple vehicles on the market, it also includes: obtaining low-battery diagnostic information uploaded by the vehicle having the low-battery problem; and constructing a low-battery model for the low-battery problem based on the low-battery diagnostic information.

[0069] In the specific implementation, the on-board terminal inside the vehicle can collect the vehicle's operating data in real time, and determine whether the vehicle is in a driving state or a power-off state based on the vehicle's operating data, where the power-off state may include the vehicle entering an ignition-off state or a power-off state. If the vehicle is in a power-off state, and the duration of the power-off state exceeds a certain threshold, the low-power diagnostic logic will be triggered, which can rule out the situation where some vehicles are temporarily dormant. After the low-power diagnostic logic is triggered, the vehicle starts to collect data related to the low-power, and records the low-power diagnostic information and uploads it to the cloud server synchronously. The server can obtain the low-power diagnostic information uploaded by vehicles with low-power problems in real time.

[0070] Optionally, the low-battery diagnostic information may include vehicle model, time of low-battery, low-battery controller, reason for low-battery, number of low-battery times, etc. The low-battery diagnostic information may also include vehicle operating conditions, battery voltage, battery current, battery charge, controller status, etc.

[0071] Among them, the low-battery controller may include the electrical or electronic control module in the vehicle that causes the low-battery problem, that is, the control module responsible for managing and controlling the charging and discharging of the battery and power distribution, such as the air-conditioning controller, headlight controller, vehicle entertainment system controller, vehicle network controller, power management controller, etc.

[0072] In a specific implementation, the server may parse the low-battery diagnostic information, identify key vehicle information in the low-battery diagnostic information, and construct a low-battery model for the low-battery problem based on the key vehicle information.

[0073] In a specific implementation, the server may also perform data preprocessing on the low-battery diagnostic information, for example, encoding and converting the low-battery diagnostic information so as to convert the low-battery diagnostic information into a data format suitable for constructing a low-battery model, or time-aligning the data collected by various vehicle sensors in the low-battery diagnostic information so that various types of data in the low-battery diagnostic information have the same timestamp, thereby constructing a low-battery model for the low-battery problem based on the preprocessed low-battery diagnostic information.

[0074] In a specific implementation, the server can determine the power shortage problem corresponding to the power shortage diagnosis information based on the power shortage diagnosis information. The power shortage problem can be determined based on the power shortage cause, power shortage controller and other information in the power shortage diagnosis information. Then, the server can build a power shortage model for a specific power shortage problem. The power shortage model integrates and records the vehicle-side data of the vehicle based on the power shortage diagnosis information, and can describe the power shortage scenario when the vehicle has the power shortage problem. Through the power shortage scenario, it can be understood under what circumstances the vehicle is prone to power shortage. Optionally, the power shortage scenario may include the vehicle's operating mode (such as long-term parking, long-term non-sleep, frequent starting, etc.), battery performance degradation, abnormal controller operation, low temperature environment and other scenarios.

[0075] Optionally, the low-battery model may be a statistical model (such as a linear regression model, a multivariate regression model, a Bayesian model or other mathematical models), which predicts a low-battery scenario in which the vehicle has a low-battery problem through statistical features of low-battery diagnostic information.

[0076] The technical solution of this embodiment obtains the low-battery diagnostic information uploaded when the vehicle has a low-battery problem, and accurately constructs a low-battery model corresponding to the low-battery problem. Based on the modeled analysis of the low-battery scenario, it can screen out target vehicles in the same low-battery scenario from multiple market vehicles, and determine whether it is necessary to issue an early warning for the low-battery problem based on the number of target vehicles and the parking duration of the low-battery problem. Therefore, the corresponding processing strategy for the low-battery problem can be determined according to the severity of the low-battery problem, thereby improving the pertinence and accuracy of the low-battery warning.

[0077] In another embodiment, a low-battery model for the low-battery problem is constructed based on the low-battery diagnostic information, including: obtaining key vehicle information in the low-battery diagnostic information; the key vehicle information includes at least one of vehicle mode, power mode, vehicle lock status, vehicle battery voltage, vehicle battery charge, and vehicle current consumption; analyzing and modeling the key vehicle information to construct a low-battery model for the low-battery problem.

[0078] Among them, the vehicle mode can be used to describe the operating state of the vehicle, such as whether it is in driving, parking or off state; the power mode can be used to refer to the working state of the vehicle's power system, such as whether it is in charging or discharging state, whether it is in standby or low power mode; the vehicle lock state can be used to refer to whether the vehicle is locked. After locking the vehicle, the vehicle should enter the low power mode. If there is still a large amount of current consumption in the locked state, it may indicate a power shortage problem; the vehicle battery voltage can be used to detect whether the battery is working properly, such as the voltage drop rate can be used to determine power shortage; the vehicle battery power can be used to reflect the remaining battery power percentage, which can directly explain the battery power consumption; the vehicle consumption current can be used to monitor the current consumption of the vehicle in different working states, including the static power consumption in the power-off state.

[0079] In the specific implementation, the server can determine the power shortage problem corresponding to the key vehicle information based on the key vehicle information, and then the server can build a power shortage model for the specific power shortage problem. The power shortage model integrates and records the vehicle-side data of the vehicle based on the key vehicle information, and can describe the power shortage scenario in which the vehicle is in when the power shortage problem occurs.

[0080] The above-mentioned embodiment can focus on indicators that have a significant impact on the low-battery problem by extracting key vehicle information from the low-battery diagnostic information, avoid interference from irrelevant data, and improve the accuracy of building a low-battery model, thereby improving the accuracy of low-battery warning.

[0081] Furthermore, in another embodiment, key vehicle information is analyzed and modeled to construct a low-battery model for the low-battery problem, including: analyzing and modeling key vehicle information to determine the vehicle's operating condition information, network behavior information, and low-battery current when the low-battery problem occurs; constructing a low-battery model for the low-battery problem based on the operating condition information, network behavior information, and low-battery current.

[0082] Among them, the operating condition information can describe the operating status of the vehicle when the low-battery problem occurs, such as whether the vehicle is in driving, parking or off state, or the time the vehicle is parked after being turned off, or whether the vehicle is in charging, discharging or standby mode.

[0083] Among them, network behavior information may refer to the status of internal and external network communications in the vehicle, such as the working status of the controller local area network bus, the communication activities between the controller and the vehicle-mounted terminal, and whether it is connected to the external network.

[0084] Among them, the low-battery current can describe the current change of the vehicle when the low-battery problem occurs, including the low-battery current when the vehicle is parked or turned off.

[0085] Exemplarily, the server analyzes and models key vehicle information, and can determine the usage conditions when the power outage problem occurs, such as long-term parking, frequent starting and stopping, etc., based on the vehicle mode, vehicle lock status, power mode, etc. in the key vehicle information, and generate corresponding usage condition information. The server can determine the network behavior when the power outage problem occurs based on the power mode, network activity (such as communication rate), etc. in the key vehicle information, such as whether the vehicle is communicating with an external server when the power outage occurs, whether the in-vehicle entertainment module is in continuous network communication, etc. The server can determine the power outage current when the power outage problem occurs based on the vehicle battery voltage, vehicle battery power, etc. in the key vehicle information. For example, the vehicle still has a high current consumption when it is powered off, which may be an important reason for the power outage.

[0086] Based on the usage condition information, network behavior information and power-deficit current, the server can determine the power-deficit scenario in which the vehicle is in when the power-deficit problem occurs, and build a power-deficit model. The power-deficit model can be used to describe the power-deficit scenario in which the vehicle is in when the power-deficit problem occurs.

[0087] The above-mentioned embodiment analyzes and models the usage conditions, network behaviors and current patterns, so that the power shortage model can accurately describe the power shortage scenario when the power shortage problem occurs, thereby improving the accuracy of the power shortage warning.

[0088] In another embodiment, a target vehicle whose low-battery scenario meets a low-battery model is screened out from multiple market vehicles, including: determining a low-battery controller that causes the low-battery problem in the vehicle; obtaining vehicle-side data uploaded by each market vehicle using the same low-battery controller; and when the vehicle-side data of the market vehicle matches the vehicle-side data recorded by the low-battery model, taking the market vehicle as a target vehicle.

[0089] Among them, a low-power controller may refer to a controller that fails to enter a sleep or low-power state correctly after the vehicle is turned off, resulting in continuous current consumption, such as an air-conditioning controller, a light controller, an in-vehicle entertainment system controller, an in-vehicle network controller, a power management controller, etc.

[0090] In the specific implementation, the server can determine the low-power controller that causes the low-power problem of the vehicle based on the low-power diagnostic information uploaded by the vehicle, and accurately locate the low-power controller that causes the low-power problem; the server can obtain the vehicle-side data uploaded by each market vehicle using the same low-power controller. These vehicle-side data may include battery-related data such as battery voltage and current, controller working status, network communication data, etc. These vehicle-side data can reflect the current operating status of the market vehicle and the working status of the controller. The same low-power controller may include low-power controllers of the same model and the same production batch.

[0091] Among them, the vehicle-side data recorded by the power-loss model may include vehicle-side data used to reflect the power-loss scenario when the power-loss problem occurs. The server compares and matches the vehicle-side data of the market vehicle with the vehicle-side data recorded by the power-loss model, which can be used to determine whether the operating conditions match, whether the network behavior matches, whether the power-loss current matches, etc. If multiple data dimensions match, it can be determined that the power-loss scenario of the market vehicle matches the power-loss scenario described by the power-loss model, and the market vehicle is used as the target vehicle.

[0092] The above-mentioned embodiment can identify the specific controller that causes the low-battery problem, and by screening the vehicles in the market that use the same controller and matching the low-battery model, it can efficiently and batch identify vehicles with the same low-battery problem, thereby accurately and promptly performing early warning processing; through the matching mechanism of the model and the vehicle-side data, the target vehicles with low-battery problems can be accurately screened out.

[0093] In another embodiment, based on the number of target vehicles and the parking time corresponding to the low-power problem, early warning processing is performed on the low-power problem, including: determining the scale of the low-power problem based on the number of target vehicles; determining the early warning level of the low-power problem based on the scale and the parking time; the early warning level is inversely proportional to the parking time and directly proportional to the scale; when the early warning level is greater than a preset level threshold, early warning processing is performed on the low-power problem.

[0094] Among them, the scale of occurrence can be used to reflect the widespread degree of power shortage problem in the market. The more target vehicles there are, the larger the scale of power shortage problem.

[0095] As an example, the scale of occurrence may include small, medium and large. Small scale may refer to a small number of target vehicles, and the low battery problem may only be found in a few individual vehicles; medium scale may refer to the number of target vehicles reaching a certain threshold, and it may occur frequently in a specific model or a specific area; large scale may refer to a large number of target vehicles, and the low battery problem tends to be large-scale or batch-based.

[0096] As another example, the scale of occurrence may include batch power shortage scale and single vehicle power shortage scale, wherein the batch power shortage scale may refer to the number of target vehicles exceeding a certain number threshold, and the number of target vehicles is large; the single vehicle power shortage scale may refer to only individual target vehicles having power shortage problems, and the number of target vehicles is small.

[0097] In one embodiment, the server determines the scale of the power shortage problem based on the number of target vehicles, which may include: the server determines the proportion of the target vehicle in each market vehicle based on the ratio of the number of target vehicles to the number of each market vehicle, and determines the scale of the power shortage problem based on the proportion of the number. For example, if the proportion of the number is very low, only one in one hundred thousand, it means that the probability of the power shortage problem is very low, and the scale of the power shortage problem is the scale of single vehicle power shortage. There is no need for early warning processing, and it is only necessary to continue to track the vehicle-side data uploaded by the vehicle, or let the owner wait for the vehicle controller to automatically perform the next software update; if the proportion of the number is very high, for example, the proportion is more than 20%, it means that the probability of the power shortage problem is very high, and the scale of the power shortage problem is the scale of batch power shortage, and early warning processing is required for the power shortage problem.

[0098] Among them, the warning level is used to reflect the urgency and impact scope of the power shortage problem. The higher the warning level, the more serious the problem, the greater the impact, and the more urgent the required intervention measures.

[0099] The warning level is positively correlated with the scale of occurrence. The larger the number of target vehicles (i.e., the scale of the power shortage problem), the higher the warning level. This is because large-scale power shortage problems indicate that many vehicles are affected at the same time. The breadth and scale of the problem increase the urgency of the problem.

[0100] The warning level is inversely proportional to the parking time. The shorter the parking time, the higher the warning level. If the vehicle runs out of power in a short period of time, it means that the battery is consumed abnormally fast, which may be caused by an acute fault or the controller failing to sleep. If the vehicle runs out of power after a long parking time, the problem is relatively slow and the warning level is low.

[0101] In one of the embodiments, the server determines, based on the scale of occurrence and the parking duration, that when the scale of occurrence is greater than a scale threshold and the parking duration is less than a duration threshold, that the warning level of the power shortage problem is greater than a preset level threshold, and performs warning processing on the power shortage problem.

[0102] The preset level threshold may be a standard for triggering an early warning. If the early warning level exceeds the preset level threshold, an early warning process for the power shortage problem is required. The preset level threshold may be set according to different vehicle models, usage environments, or management strategies.

[0103] The above-mentioned embodiment can determine the warning level more accurately by combining the number of target vehicles and the parking duration, avoiding excessive warnings or missed reports; by combining the number of target vehicles and the parking duration, the warning level of the low-power problem is dynamically adjusted to ensure that appropriate warnings are issued according to the actual scale and urgency of the low-power risk, and accurate warnings are achieved through an intelligent judgment mechanism, thereby effectively improving the efficiency of vehicle low-power problem management and reducing the risks brought by low-power problems.

[0104] Furthermore, in another embodiment, early warning processing is performed on the power shortage problem, including: sending a power shortage early warning result of the power shortage problem to a business cloud; the power shortage early warning result is used to indicate that the power shortage problem is processed according to the power shortage early warning result within a preset time period; wherein, the business cloud includes a research and development cloud, a production cloud, and an after-sales cloud; the preset time period is inversely proportional to the warning level.

[0105] Among them, the R&D cloud can be used for vehicle technical research and development and design; the production cloud can be used for vehicle production and manufacturing; and the after-sales cloud can be used for vehicle after-sales service and maintenance.

[0106] Among them, the power shortage warning result may include a warning level used to reflect the urgency of the power shortage problem, and may also include the analysis results of the power shortage problem. Further optionally, the power shortage warning result may also include a solution to the power shortage problem, thereby instructing relevant personnel to deal with the power shortage problem. For example, the power shortage warning result sent to the R&D cloud can be used to indicate errors in R&D design (for example, the controller software fails to enter the low power mode correctly), and instruct relevant business personnel in the R&D cloud to update the software; the power shortage warning result sent to the production cloud can be used to indicate problems in the production stage (such as problems with a batch of controller hardware or software), and instruct relevant business personnel in the production cloud to inspect, upgrade or recall production line vehicles; the power shortage warning result sent to the after-sales cloud can be used to indicate vehicle battery aging or vehicle controller failure to work properly, and instruct relevant business personnel in the after-sales cloud to notify the owner for inspection and repair.

[0107] Among them, the preset time is that after the relevant personnel or departments receive the power shortage warning results through the business cloud, they must deal with the power shortage problem within the specified time. The preset time is inversely proportional to the warning level. For example, if the warning level is the highest warning level, the preset time may require that the power shortage problem be handled within 24 hours; if the warning level is the medium warning level, the preset time may require that the power shortage problem be handled within a few days or a week. The preset time is inversely proportional to the warning level, which means that the higher the warning level, the shorter the processing time, ensuring that the higher the urgency of the problem, the relevant personnel can handle it in the shortest time, thereby minimizing the impact of the power shortage problem.

[0108] In actual applications, for vehicles with batch power-loss problems, it can be calculated whether the vehicle ran out of power due to being parked overnight or for multiple days. If the vehicle ran out of power due to being parked overnight, the warning level will be the highest level. The warning information must be synchronized to the persons in charge of R&D, production, and after-sales service as soon as possible, so that the relevant persons in charge can obtain first-hand information in time and decide how to quickly deal with the power-loss problem.

[0109] The above-mentioned embodiment achieves rapid response and accurate handling of low-battery problems by sending low-battery warning results to the business cloud and setting a preset duration according to the warning level; through the division of labor and cooperation among different clouds, comprehensive coverage of vehicle research and development, production and after-sales is achieved, ensuring that low-battery problems can be solved in a timely manner within an appropriate time, thereby improving the efficiency and reliability of vehicle low-battery problem management.

[0110] Furthermore, in another embodiment, after sending the low-battery warning result of the low-battery problem to the business cloud, it also includes: obtaining the low-battery processing feedback result returned by the business cloud in response to the low-battery warning result; the low-battery processing feedback result includes at least one of the first feedback result, the second feedback result and the third feedback result; the first feedback result includes the result of the R&D cloud performing a software upgrade on the vehicle with the low-battery problem; the second feedback result includes the result of the production cloud performing a software upgrade on the production line vehicles; the third feedback result includes the result of the after-sales cloud monitoring the vehicle-side data uploaded by the vehicle with the low-battery problem; according to the low-battery processing feedback result, the number of target vehicles and the parking time corresponding to the low-battery problem are updated.

[0111] In specific implementation, after analyzing the power-out problem, the R&D cloud may remotely upgrade (OTA) or partially repair the controller software of the problem vehicle. The first feedback result may include whether the software upgrade is successful, whether the upgrade solves the power-out problem, and whether further improvement is needed.

[0112] The production cloud may perform software upgrades on vehicles that have not yet been delivered or are in production to ensure that newly produced vehicles will not have the same battery shortage problem. The second feedback result may include the number of upgraded vehicles, whether the upgrade was successful, and whether the production line vehicles have returned to normal.

[0113] The after-sales cloud may remotely monitor the problem vehicle, especially monitoring the vehicle's battery level, voltage changes, controller status, etc., to assess whether the power shortage problem still exists. The third feedback result may include changes in vehicle status found during the monitoring process, whether there is a further risk of power shortage, and whether physical inspection or maintenance is required.

[0114] The server obtains the power shortage processing feedback result returned by the business cloud in response to the power shortage warning result, and can understand the progress of the business departments in each cloud in handling the power shortage problem, and dynamically adjust the subsequent warning strategy. According to the power shortage processing feedback result, the server updates the number of target vehicles and the parking time corresponding to the power shortage problem. For example, if the power shortage problem of some market vehicles is solved after software upgrades or other repairs, these market vehicles are no longer target vehicles, and the number of target vehicles is reduced; for another example, if the parking time of the market vehicle with power shortage problem is extended after software upgrades or other repairs, the parking time can be increased.

[0115] The server in the above-mentioned embodiment tracks the progress of solving the low-battery problem in real time, thereby realizing full-process tracking from problem discovery to solution, and completing the closed loop of the low-battery problem; according to the number of these updated target vehicles and the parking time corresponding to the low-battery problem, the warning level is dynamically adjusted, thereby dynamically adjusting the warning processing strategy for the low-battery problem, which can flexibly respond to low-battery problems at different stages, and realize rapid positioning and resolution of low-battery problems through a feedback mechanism, thereby improving the efficiency and accuracy of vehicle low-battery warnings.

[0116] To facilitate the understanding of those skilled in the art, FIG3 exemplarily provides a logic diagram of a vehicle low-battery warning method. As shown in FIG3, the vehicle triggers the low-battery diagnostic logic and uploads the vehicle-side data to the cloud server. The low-battery warning system integrated in the cloud server can obtain the vehicle-side data of the vehicle in real time, and the vehicle-side data includes low-battery diagnostic information; the pre-diagnosis module in the low-battery warning system can determine the low-battery diagnostic information by parsing the vehicle-side data uploaded by the vehicle, and the low-battery diagnostic information includes the vehicle model, time point of low-battery, low-battery control controller, reason for low-battery, and number of low-battery times; the cloud server can determine the low-battery diagnostic information based on the vehicle mode, power mode, vehicle lock status, vehicle battery voltage, vehicle battery power, etc. The key vehicle information is analyzed and modeled to obtain a power-loss model, which can describe power-loss scenarios such as the conditions under which the user is using the power-loss model, the network behavior of the vehicle when the power-loss is low, and the power-loss current. The cloud server can call the power-loss model, and determine whether the power-loss problem is a single-vehicle power-loss problem or a batch power-loss problem through the vehicle-side data recorded in the power-loss model and the vehicle-side data uploaded by the market vehicle. If it is a batch power-loss problem, it is determined how long the vehicle has been parked before the power-loss problem occurs. If the power is lost after parking overnight, the highest level of power-loss warning is determined, and if the power is lost after being parked for many days, a high level of power-loss warning is determined. The cloud server synchronizes the power-loss warning results to the R&D cloud, production cloud, and after-sales cloud through the power-loss warning system. The R&D cloud remotely upgrades the software of the power-loss controller based on the power-loss warning results, and feeds back the OTA upgrade results to the power-loss warning system; the production cloud performs software breakpoints on the models of the production line based on the power-loss warning results, and feeds back the breakpoint information to the power-loss warning system; the after-sales cloud feeds back the information of the power-loss vehicles processed by the after-sales service to the power-loss warning system. The power shortage warning system will process the feedback collected from the R&D cloud, production cloud, and after-sales cloud, and update the warning results in real time until the power shortage problem is completely resolved and the closed loop is completed.

[0117] This technical solution can solve the problem of low battery in the vehicle caused by the vehicle not being in sleep mode during use, and can quickly analyze and locate low battery problems such as the user being unable to start the vehicle; the low battery warning system based on smart cloud technology, based on the low battery diagnosis logic on the vehicle side and the low battery model analysis on the cloud side, can effectively improve the efficiency of solving the low battery problem; and, this technical solution directly uses the vehicle's existing signals without increasing costs; the technical logic is highly portable and can be promoted on a platform; the human-computer interaction is friendly, and it is convenient for after-sales maintenance personnel to use it through the cloud server; it can not only improve the efficiency of solving low battery problems but also improve the software development quality of subsequent projects.

[0118] In another embodiment, as shown in FIG. 4 , a vehicle power shortage warning method is provided, which is described by taking the method applied to the server 104 in FIG. 1 as an example, and includes the following steps:

[0119] S402, obtaining low-battery diagnostic information uploaded by a vehicle having a low-battery problem.

[0120] S404, obtaining key vehicle information in the low-battery diagnosis information.

[0121] The key vehicle information includes at least one of vehicle mode, power mode, vehicle lock status, vehicle battery voltage, vehicle battery power, and vehicle current consumption.

[0122] S406, analyzing and modeling key vehicle information to construct a power shortage model for the power shortage problem.

[0123] In one of the embodiments, key vehicle information is analyzed and modeled to construct a low-battery model for the low-battery problem, including: analyzing and modeling key vehicle information to determine the vehicle's operating condition information, network behavior information, and low-battery current when the low-battery problem occurs; constructing a low-battery model for the low-battery problem based on the operating condition information, network behavior information, and low-battery current.

[0124] S408, determining the low-power controller that causes the low-power problem in the vehicle.

[0125] S410, obtaining vehicle-side data uploaded by various vehicles in the market that use the same low-power controller.

[0126] S412: When the vehicle-side data of the market vehicle matches the vehicle-side data recorded by the power-deficit model, the market vehicle is taken as the target vehicle.

[0127] The low-battery model is used to describe the low-battery scenario when a vehicle has a low-battery problem.

[0128] S414, determining the scale of the power shortage problem based on the number of target vehicles.

[0129] S416, determining the warning level of the power shortage problem according to the scale and parking duration.

[0130] The warning level is inversely proportional to the parking duration and directly proportional to the scale of occurrence.

[0131] S418, when the warning level is greater than the preset level threshold, the power shortage warning result of the power shortage problem is sent to the business cloud.

[0132] The power shortage warning result is used to indicate that the power shortage problem should be handled according to the power shortage warning result within a preset time; wherein, the business cloud includes the R&D cloud, the production cloud and the after-sales cloud; the preset time is inversely proportional to the warning level.

[0133] S420, obtaining a power shortage processing feedback result returned by the business cloud in response to the power shortage warning result.

[0134] The feedback results of low-battery processing include at least one of the first feedback result, the second feedback result and the third feedback result; the first feedback result includes the result of the R&D cloud performing a software upgrade on vehicles with low-battery problems; the second feedback result includes the result of the production cloud performing a software upgrade on production line vehicles; the third feedback result includes the result of the after-sales cloud performing monitoring of the vehicle-side data uploaded by vehicles with low-battery problems.

[0135] S422, based on the feedback result of the power shortage processing, the number of target vehicles and the parking time corresponding to the power shortage problem are updated.

[0136] It should be noted that the specific limitations of the above steps can refer to the specific limitations of a vehicle low-battery warning method mentioned above.

[0137] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0138] Based on the same inventive concept, the embodiment of the present application also provides a vehicle low-power warning device for implementing the vehicle low-power warning method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more vehicle low-power warning device embodiments provided below can refer to the limitations of the vehicle low-power warning method above, and will not be repeated here.

[0139] In an exemplary embodiment, as shown in FIG5 , a vehicle low-power warning device is provided, comprising:

[0140] The screening module 510 is used to screen out target vehicles whose low-battery scenarios satisfy a low-battery model from multiple vehicles on the market; the low-battery model is used to describe the low-battery scenario in which the vehicle is in when a low-battery problem occurs.

[0141] The early warning module 520 is used to perform early warning processing on the power shortage problem according to the number of the target vehicles and the parking time corresponding to the power shortage problem; the parking time is the time from the vehicle being turned off to the occurrence of the power shortage problem.

[0142] In one of the embodiments, the vehicle low-battery warning device also includes a construction module; the construction module is specifically used to obtain low-battery diagnostic information uploaded by the vehicle having the low-battery problem; and construct a low-battery model for the low-battery problem based on the low-battery diagnostic information.

[0143] In one embodiment, the construction module is specifically used to obtain key vehicle information in the low-battery diagnostic information; the key vehicle information includes at least one of vehicle mode, power mode, vehicle lock status, vehicle battery voltage, vehicle battery power, and vehicle current consumption; the key vehicle information is analyzed and modeled to construct a low-battery model for the low-battery problem.

[0144] In one of the embodiments, the construction module is specifically used to analyze and model the key vehicle information to determine the vehicle's operating condition information, network behavior information and power-deficit current when the power-deficit problem occurs; and to construct a power-deficit model for the power-deficit problem based on the operating condition information, the network behavior information and the power-deficit current.

[0145] In one of the embodiments, the screening module 510 is specifically used to determine the low-power controller that causes the low-power problem in the vehicle; obtain the vehicle-side data uploaded by each of the market vehicles using the same low-power controller; and when the vehicle-side data of the market vehicle matches the vehicle-side data recorded by the low-power model, use the market vehicle as the target vehicle.

[0146] In one of the embodiments, the early warning module 520 is specifically used to determine the scale of the power shortage problem according to the number of the target vehicles; determine the early warning level of the power shortage problem according to the scale and the parking duration; the early warning level is inversely proportional to the parking duration and directly proportional to the scale; when the early warning level is greater than a preset level threshold, early warning processing is performed on the power shortage problem.

[0147] In one of the embodiments, the early warning module 520 is specifically used to send the low-power warning result of the low-power problem to the business cloud; the low-power warning result is used to indicate that the low-power problem is handled according to the low-power warning result within a preset time period; wherein, the business cloud includes a research and development cloud, a production cloud and an after-sales cloud; the preset time period is inversely proportional to the warning level.

[0148] In one of the embodiments, the early warning module 520 is specifically used for sending the low-battery warning result of the low-battery problem to the business cloud, and the method also includes: obtaining the low-battery processing feedback result returned by the business cloud in response to the low-battery warning result; the low-battery processing feedback result includes at least one of the first feedback result, the second feedback result and the third feedback result; the first feedback result includes the result of the R&D cloud performing a software upgrade on the vehicle having the low-battery problem; the second feedback result includes the result of the production cloud performing a software upgrade on the production line vehicles; the third feedback result includes the result of the after-sales cloud performing monitoring on the vehicle-side data uploaded by the vehicle having the low-battery problem; according to the low-battery processing feedback result, the number of the target vehicles and the parking time corresponding to the low-battery problem are updated.

[0149] Each module in the above-mentioned vehicle power shortage warning device can be implemented in whole or in part by software, hardware and their combination. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0150] In an exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in FIG6. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store vehicle data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a vehicle power shortage warning method is implemented.

[0151] Those skilled in the art will understand that the structure shown in FIG. 6 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0152] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0153] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0154] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0155] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0156] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0157] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0158] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A vehicle power shortage warning method, characterized in that: The method comprises: Screening out target vehicles whose power-loss scenarios meet the power-loss model from multiple market vehicles; the power-loss model is used to describe the power-loss scenario when the vehicle has a power-loss problem; According to the number of the target vehicles and the parking time corresponding to the power shortage problem, the power shortage problem is warned; the parking time is the time from the vehicle being turned off to the occurrence of the power shortage problem.

2. The method according to claim 1, characterized in that Before selecting a target vehicle whose low-battery scenario satisfies the low-battery model from a plurality of market vehicles, the method further includes: Obtaining power-loss diagnostic information uploaded by a vehicle having the power-loss problem; A power failure model for the power failure problem is constructed according to the power failure diagnosis information.

3. The method according to claim 2, characterized in that The step of constructing a power failure model for the power failure problem according to the power failure diagnosis information includes: Acquire key vehicle information in the power-loss diagnosis information; the key vehicle information includes at least one of vehicle mode, power mode, vehicle lock status, vehicle battery voltage, vehicle battery power, and vehicle current consumption; The key vehicle information is analyzed and modeled to construct a power shortage model for the power shortage problem.

4. The method according to claim 3, characterized in that The analyzing and modeling of the key vehicle information to construct a power shortage model for the power shortage problem includes: Analyze and model the key vehicle information to determine the vehicle's operating condition information, network behavior information, and power failure current when the power failure problem occurs; A power failure model for the power failure problem is constructed according to the usage condition information, the network behavior information and the power failure current.

5. The method according to claim 1, characterized in that The step of selecting a target vehicle whose low-battery scenario satisfies the low-battery model from a plurality of vehicles on the market includes: Determine the power failure controller that causes the power failure problem in the vehicle; Obtaining vehicle-side data uploaded by each vehicle in the market that uses the same low-power controller; When the vehicle-side data of the market vehicle matches the vehicle-side data recorded by the power-loss model, the market vehicle is used as the target vehicle.

6. The method according to claim 1, characterized in that The step of performing early warning processing on the power shortage problem according to the number of the target vehicles and the parking duration corresponding to the power shortage problem includes: Determine the scale of the power shortage problem according to the number of the target vehicles; Determine the warning level of the power shortage problem according to the occurrence scale and the parking duration; the warning level is inversely proportional to the parking duration and directly proportional to the occurrence scale; When the warning level is greater than the preset level threshold, a warning process is performed on the power shortage problem.

7. The method according to claim 6, characterized in that The early warning process for the power shortage problem includes: Sending the power shortage warning result of the power shortage problem to the business cloud; the power shortage warning result is used to indicate that the power shortage problem is handled according to the power shortage warning result within a preset time period; Among them, the business cloud includes R&D cloud, production cloud and after-sales cloud; the preset time is inversely proportional to the warning level.

8. The method according to claim 7, characterized in that After sending the power shortage warning result of the power shortage problem to the business cloud, the method further includes: Obtaining a power-loss processing feedback result returned by the business cloud in response to the power-loss warning result; the power-loss processing feedback result includes at least one of a first feedback result, a second feedback result, and a third feedback result; the first feedback result includes a result of the R&D cloud performing a software upgrade on a vehicle having the power-loss problem; the second feedback result includes a result of the production cloud performing a software upgrade on a production line vehicle; the third feedback result includes a result of the after-sales cloud performing monitoring on vehicle-side data uploaded by the vehicle having the power-loss problem; According to the feedback result of the power shortage processing, the number of the target vehicles and the parking time corresponding to the power shortage problem are updated.

9. A vehicle power shortage warning device, characterized in that: The device comprises: A screening module is used to screen out target vehicles whose power-loss scenarios meet a power-loss model from multiple market vehicles; the power-loss model is used to describe the power-loss scenario in which the vehicle is in when the power-loss problem occurs; The early warning module is used to perform early warning processing on the power shortage problem according to the number of the target vehicles and the parking time corresponding to the power shortage problem; the parking time is the time from the vehicle being turned off to the occurrence of the power shortage problem.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

12. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images