Battery power shortage reminding method and device, vehicle and storage medium

Abstract

The application relates to the technical field of Internet of Vehicles, in particular to a storage battery power shortage reminding method and device, a vehicle and a storage medium, wherein the method comprises the following steps: acquiring real-time vehicle data of a current vehicle; inputting the real-time vehicle data into a pre-trained power shortage cause recognition model to obtain a power shortage prediction result of the current vehicle, wherein the pre-trained power shortage cause recognition model is obtained by training a target neural network by using to-be-trained vehicle data; if the power shortage prediction result is storage battery power shortage, obtaining a power shortage cause from the power shortage prediction result, generating reminding information based on the power shortage cause, and sending the reminding information to a preset mobile terminal. Thus, the problems of the related art, such as great energy consumption and low accuracy of the storage battery power shortage analysis method, are solved, power shortage is recognized through Internet of Vehicles big data, the process and timeliness of power shortage disposal are optimized, and therefore the user's vehicle use experience is improved.

Description

Technical Field

[0001] This application relates to the field of vehicle networking technology, and in particular to a method, device, vehicle, and storage medium for reminding a battery to be low on power. Background Technology

[0002] Whether it's a new energy vehicle or a gasoline-powered vehicle, a depleted vehicle battery can severely impact normal use. When the battery is severely depleted, the vehicle may not be able to start. There are many reasons for a depleted vehicle battery, such as the vehicle controller remaining active after the car is locked, prolonged use of the air conditioning or main unit while the car is parked, and repeated battery drains reducing battery life.

[0003] In related technologies, the following steps are typically used to analyze the causes of vehicle battery depletion: First, observe whether any electrical appliances continue to operate after the vehicle has been put into sleep mode, such as the outdoor lighting system, cabin lighting system, and body accessory system. Second, listen for the clicking sound of relays or solenoid switches when starting the engine to ensure their normal response, and check whether the air conditioning blower continues to operate after sleep mode. Then, inquire with the user about vehicle usage status and frequency. Finally, conduct a comprehensive analysis based on the collected information to make a preliminary judgment on the cause of battery depletion.

[0004] However, the aforementioned methods for analyzing vehicle battery depletion mainly focus on investigating users' driving habits, assessing battery condition, and considering factors such as climate temperature and assembly. These methods require a lot of effort to determine the cause of depletion and have low accuracy, so they urgently need improvement. Summary of the Invention

[0005] This application provides a method, device, vehicle, and storage medium for reminding users of low battery power, in order to solve the problems of high effort consumption and low accuracy in related technologies for analyzing low battery power.

[0006] The first aspect of this application provides a method for reminding users of low battery power, including the following steps:

[0007] Obtain real-time vehicle data for the current vehicle;

[0008] The real-time vehicle data is input into a pre-trained battery drain cause identification model to obtain the current battery drain prediction result for the vehicle, wherein the pre-trained battery drain cause identification model is obtained by training a target neural network using vehicle data to be trained; and

[0009] If the battery depletion prediction result indicates that the battery is depleted, the cause of the depletion is obtained from the prediction result, a reminder message is generated based on the cause of the depletion, and the reminder message is sent to a preset mobile terminal.

[0010] According to one embodiment of this application, the cause of power loss includes at least one of controller abnormal retention, controller abnormal wake-up, and user misuse.

[0011] According to one embodiment of this application, generating a reminder message based on the cause of the low battery and sending the reminder message to a preset mobile terminal includes:

[0012] If the reason for the power loss is that the controller is abnormally holding or abnormally waking up, then the reminder message is a controller optimization reminder message;

[0013] Send the controller optimization reminder message to the after-sales center of the current vehicle.

[0014] According to one embodiment of this application, generating a reminder message based on the cause of the low battery and sending the reminder message to a preset mobile terminal includes:

[0015] If the reason for the low battery is improper use by the user, then the reminder message is an engine start reminder.

[0016] The engine start reminder is sent to the vehicle's infotainment system so that the engine start reminder can be displayed on the infotainment system.

[0017] According to one embodiment of this application, before inputting the real-time vehicle data into the pre-trained battery drain cause identification model, the method further includes:

[0018] Acquire offline vehicle data for multiple vehicles with depleted battery power within a first preset time period before the battery depletes.

[0019] Based on the offline vehicle data, the training vehicle data that meets the preset training conditions is selected.

[0020] Multiple target neural networks are trained using the vehicle data to be trained, resulting in a controller abnormal hold / wake-up model, a user misuse model, a battery depletion and health correlation model, and a frequent start-up behavior and health correlation model.

[0021] When the model identification results of the controller abnormal hold / wake-up model, the user misuse model, the power loss and health correlation model, and the frequent startup behavior and health correlation model are all greater than the preset results, the pre-trained power loss cause identification model is obtained based on the models of the controller abnormal hold / wake-up model, the user misuse model, the power loss and health correlation model, and the frequent startup behavior and health correlation model.

[0022] According to one embodiment of this application, the real-time vehicle data includes at least one of vehicle status data, battery status data, electrical component status, and current ambient temperature.

[0023] According to the battery depletion alert method provided in this application, real-time vehicle data is input into a pre-trained battery depletion cause identification model to obtain the current battery depletion prediction result. If the prediction result indicates battery depletion, the cause of the depletion is obtained, an alert message is generated, and the alert message is sent to a preset mobile terminal. This solves the problems of high effort consumption and low accuracy in related technologies for battery depletion analysis. By using vehicle network big data for depletion identification, the process and timeliness of depletion handling are optimized, thereby improving the user's driving experience.

[0024] A second aspect of this application provides a battery low-power reminder device, comprising:

[0025] The acquisition module is used to acquire real-time vehicle data for the current vehicle.

[0026] The prediction module inputs the real-time vehicle data into a pre-trained battery drain cause identification model to obtain the current battery drain prediction result for the vehicle. The pre-trained battery drain cause identification model is obtained by training a target neural network using the vehicle data to be trained.

[0027] The reminder module is used to obtain the cause of battery depletion from the battery depletion prediction result if the battery depletion prediction result is that the battery is depleted, generate reminder information based on the cause of battery depletion, and send the reminder information to a preset mobile terminal.

[0028] According to one embodiment of this application, the cause of power loss includes at least one of controller abnormal retention, controller abnormal wake-up, and user misuse.

[0029] According to one embodiment of this application, the reminder module is used for:

[0030] If the reason for the power loss is that the controller is abnormally holding or abnormally waking up, then the reminder message is a controller optimization reminder message;

[0031] Send the controller optimization reminder message to the after-sales center of the current vehicle.

[0032] According to one embodiment of this application, the reminder module is used for:

[0033] If the reason for the low battery is improper use by the user, then the reminder message is an engine start reminder.

[0034] The engine start reminder is sent to the vehicle's infotainment system so that the engine start reminder can be displayed on the infotainment system.

[0035] According to one embodiment of this application, before inputting the real-time vehicle data into the pre-trained battery drain cause identification model, the prediction module is further configured to:

[0036] Acquire offline vehicle data for multiple vehicles with depleted battery power within a first preset time period before the battery depletes.

[0037] Based on the offline vehicle data, the training vehicle data that meets the preset training conditions is selected.

[0038] Multiple target neural networks are trained using the vehicle data to be trained, resulting in a controller abnormal hold / wake-up model, a user misuse model, a battery depletion and health correlation model, and a frequent start-up behavior and health correlation model.

[0039] When the model identification results of the controller abnormal hold / wake-up model, the user misuse model, the power loss and health correlation model, and the frequent startup behavior and health correlation model are all greater than the preset results, the pre-trained power loss cause identification model is obtained based on the models of the controller abnormal hold / wake-up model, the user misuse model, the power loss and health correlation model, and the frequent startup behavior and health correlation model.

[0040] According to one embodiment of this application, the real-time vehicle data includes at least one of vehicle status data, battery status data, electrical component status, and current ambient temperature.

[0041] According to the battery low-power reminder device provided in this application embodiment, real-time vehicle data is input into a pre-trained low-power cause identification model to obtain the current battery low-power prediction result. If the low-power prediction result indicates that the battery is low-power, the cause of the low-power is obtained, a reminder message is generated, and the reminder message is sent to a preset mobile terminal. This solves the problems of high effort consumption and low accuracy in related technologies for battery low-power analysis. By using vehicle network big data for low-power identification, the process and timeliness of low-power handling are optimized, thereby improving the user's driving experience.

[0042] A third aspect of this application provides a vehicle, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the battery low-power reminder method as described in the above embodiments.

[0043] A fourth aspect of this application provides a computer-readable storage medium storing computer instructions for causing the computer to execute the battery low-power reminder method as described in the above embodiments.

[0044] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0045] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0046] Figure 1 This is a flowchart of a battery low-power reminder method provided according to an embodiment of this application;

[0047] Figure 2 This is a flowchart of a method for identifying battery depletion and common causes according to an embodiment of this application;

[0048] Figure 3 This is a communication diagram of a battery low-power reminder according to one embodiment of this application;

[0049] Figure 4 This is a block diagram of a battery low-power reminder system according to an embodiment of this application;

[0050] Figure 5 This is a block diagram of a battery low-power reminder device according to an embodiment of this application;

[0051] Figure 6 This is a schematic diagram of the vehicle structure provided in an embodiment of this application. Detailed Implementation

[0052] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0053] The following description, with reference to the accompanying drawings, outlines a battery low-power warning method, apparatus, vehicle, and storage medium according to embodiments of this application. Addressing the issues of high effort consumption and low accuracy in battery low-power analysis methods mentioned in the background art, this application provides a battery low-power warning method. In this method, real-time vehicle data is input into a pre-trained low-power cause identification model to obtain a current battery low-power prediction result. If the prediction result indicates battery low-power, the cause of the low-power condition is identified, a warning message is generated, and the warning message is sent to a preset mobile terminal. This solves the problems of high effort consumption and low accuracy in related battery low-power analysis methods.

[0054] Specifically, Figure 1This is a schematic flowchart illustrating a battery low-power reminder method provided in an embodiment of this application.

[0055] like Figure 1 As shown, this battery low-charge reminder method includes the following steps:

[0056] In step S101, real-time vehicle data of the current vehicle is obtained.

[0057] In some embodiments, real-time vehicle data includes at least one of vehicle status data, battery status data, electrical component status, and current ambient temperature.

[0058] Specifically, embodiments of this application can obtain real-time vehicle data of the current vehicle through vehicle-to-everything (V2X) technology. It should be noted that the above-described method of obtaining real-time vehicle data of the current vehicle through V2X technology is merely exemplary and not intended to limit this application. Those skilled in the art can adopt other methods to obtain real-time vehicle data of the current vehicle according to actual circumstances; to avoid redundancy, these methods will not be elaborated upon here.

[0059] It should be noted that the accumulation of real vehicle data should be longer than a certain period of time to ensure that the recognition output of subsequent modeling can reflect the actual situation of the vehicle.

[0060] In step S102, real-time vehicle data is input into a pre-trained battery drain cause identification model to obtain the current battery drain prediction result of the vehicle. The pre-trained battery drain cause identification model is obtained by training the target neural network with the vehicle data to be trained.

[0061] In some embodiments, the cause of power loss includes at least one of controller abnormal retention, controller abnormal wake-up, and improper user use.

[0062] Specifically, the vehicle may experience abnormal controller hold or abnormal controller wake-up due to overvoltage, overcurrent or overheating. Improper user operation may involve the user using high-power components such as air conditioning and audio-visual equipment for extended periods of time while the vehicle is in the ignition off state.

[0063] Therefore, by using a pre-trained model, real-time vehicle data can be quickly analyzed and identified to obtain accurate battery drain prediction results. This allows users or after-sales centers to take timely measures to avoid or resolve battery drain issues. Because the neural network learns a large number of data patterns and features during training, it has high reliability and can provide efficient and accurate prediction results. Furthermore, the battery drain prediction results can be integrated with downstream systems to address battery drain issues promptly and reduce their subsequent impact.

[0064] Furthermore, in some embodiments, before inputting real-time vehicle data into the pre-trained battery drain cause identification model, the method further includes: acquiring offline vehicle data of multiple vehicles with low battery levels within a first preset time period before the battery drains; filtering out vehicle data to be trained based on the offline vehicle data that meets preset training conditions; training multiple target neural networks using the vehicle data to be trained to obtain a controller abnormal hold / wake-up model, a user misuse model, a battery drain and health correlation model, and a frequent start behavior and health correlation model; when the model identification results of the controller abnormal hold / wake-up model, the user misuse model, the battery drain and health correlation model, and the frequent start behavior and health correlation model are all greater than preset results, obtaining the pre-trained battery drain cause identification model based on the models of the controller abnormal hold / wake-up model, the user misuse model, the battery drain and health correlation model, and the frequent start behavior and health correlation model.

[0065] The first preset time can be a time pre-set by those skilled in the art, a time obtained through a limited number of experiments, or a time obtained through a limited number of computer simulations; no specific limitation is made here. Offline vehicle data may include battery voltage, temperature, charge level, health status, frequency of battery depletion, ignition key status, generator status, engine status, drive motor status (for new energy vehicles), intelligent charging status (for new energy vehicles), air conditioning status, vehicle application status, controller network status, etc.

[0066] Preferably, the preset result can be F1 score = 70%, but no specific limitation is made here.

[0067] Optionally, in this embodiment of the application, vehicle recording data can be retrieved according to three temperature ranges: low (<5℃), medium ([5℃, 35℃]), and high (>35℃), based on the battery model and the vehicle system model.

[0068] Specifically, offline vehicle data is acquired and the vehicle data to be trained is selected. Multiple target neural networks are trained using the vehicle data to meet the fitting criteria, and then migrated to the big data real-time application cluster for real-time power depletion identification and scene recognition.

[0069] Furthermore, such as Figure 2 As shown, the controller abnormal hold / wake-up model in this embodiment can adopt a conventional logic decision model to identify situations where "the ignition key is OFF, but the controller signal abnormally holds / wakes up for 30 minutes" within 24 hours before the vehicle's battery is depleted. Controllers are arranged from high to low in terms of duration and frequency, and the battery professional team is coordinated to check whether the controller hold / wake-up logic is reasonable, and propose optimization requirements for unreasonable ones. When it is identified that the controller is not in sleep mode, it should be determined whether it is abnormal hold or abnormal wake-up, and the main controller should be identified according to the situation to facilitate the R&D team to optimize the controller settings.

[0070] Furthermore, the user misuse model in this application embodiment can employ a conventional logical decision-making model to identify situations where "the engine is off, but the air conditioner / vehicle infotainment system continues to run for 30 minutes" within 72 hours prior to the vehicle running out of power. Electrical devices are arranged from highest to lowest frequency and duration. For devices that frequently cause power loss, application or vehicle infotainment system prompts are added to remind the user to turn on the engine or turn off the electrical device. When identifying user misuse, the primary direction of power consumption should be determined to set battery usage tags, facilitating personalized tag management for each customer.

[0071] Furthermore, when the model identification results of the controller abnormal hold / wake-up model, user misuse model, power loss and health correlation model, and frequent start-up behavior and health correlation model are all greater than the preset results, the identification results are comprehensively summarized and used as input for the multi-classification identification model of power loss causes. The relationship between the fitted data and each power loss cause is used to train and construct the power loss cause identification model, thereby supporting the optimization of the battery technology system.

[0072] It should be noted that the model can only reflect the vehicle characteristics of the data used. When the KS (Kolmogorov-Smirnov, a model evaluation metric) value is less than 20%, it means that the model can no longer stably identify the corresponding scene, and the model parameters no longer have the ability to represent the scene logic. Therefore, it is necessary to continuously iterate the model. Especially for battery scenarios where seasons, temperatures, and usage habits change, the embodiments of this application can test the model every 3 months. At this time, it is necessary to use the data of the most recent 3 months for retraining and optimize the training parameters. When the data accumulation meets the conditions, training iteration can be carried out according to seasons and geographical regions to ensure the quality and stability of the model.

[0073] In step S103, if the battery power loss prediction result is that the battery is low on power, the cause of the power loss is obtained from the power loss prediction result, and a reminder message is generated based on the cause of the power loss and sent to a preset mobile terminal.

[0074] The preset mobile terminal includes mobile phones or other handheld communication devices with shortwave radio communication capabilities, without specific limitations.

[0075] Specifically, the cause of battery depletion is obtained from the predicted depletion results without manual intervention or analysis, saving time and manpower costs. Furthermore, the alerts generated based on the cause of depletion can be tailored to the specific condition of each battery, improving accuracy and usability. By promptly sending alerts to preset mobile terminals and providing reasonable suggestions, users can understand the battery status and potential problems anytime, anywhere, thereby better managing device usage, optimizing user habits, and improving the user experience.

[0076] Furthermore, in some embodiments, generating a reminder message based on the cause of battery depletion and sending the reminder message to a preset mobile terminal includes: if the cause of battery depletion is abnormal controller hold or abnormal controller wake-up, then the reminder message is a controller optimization reminder message; and sending the controller optimization reminder message to the after-sales center of the current vehicle.

[0077] Specifically, such as Figure 3 As shown, if the cause of the power loss is abnormal controller hold or abnormal controller wake-up, the vehicle body / vehicle system / gateway / hybrid / battery management system controller uploads signals to the vehicle communication system, which then summarizes and reports the information to the cloud. The cloud then sends controller optimization reminder information to the after-sales system.

[0078] Therefore, the controller optimization reminder information is sent to the after-sales center of the current vehicle, so that the after-sales center can understand the vehicle's operating status and controller abnormalities in a timely manner, and take corresponding measures for repair and optimization, thereby improving the timeliness and effectiveness of after-sales service.

[0079] Furthermore, in some embodiments, generating a reminder message based on the cause of battery depletion and sending the reminder message to a preset mobile terminal includes: if the cause of battery depletion is improper user operation, the reminder message is an engine start reminder; sending the engine start reminder to the vehicle's infotainment system so that the engine start reminder can be displayed through the infotainment system.

[0080] For example, if the battery drain is caused by improper user operation, the after-sales team will be contacted to notify the user through the vehicle's infotainment system or application: "Using the air conditioner or infotainment system for an extended period after turning off the engine will cause the battery to drain. For your driving experience, please turn on the engine or charge the battery in time. Thank you!"

[0081] Therefore, by sending engine start reminders and guiding customers to keep the ignition on when using high-electrical-consumption components such as air conditioning and audio-visual equipment through vehicle system displays, applications, or customer service calls, users can be promptly reminded to pay attention to starting the engine, helping them avoid battery drain due to improper use, increasing users' awareness of vehicle battery usage, cultivating and optimizing users' driving habits, and improving the user's driving experience.

[0082] Furthermore, in the embodiments of this application, when the battery is depleted, the system can connect with the after-sales team to notify the user through the vehicle system or application that "the depletion of the battery will cause your vehicle battery health to decline. Please charge it in time, thank you." At the same time, the system can connect with the battery team to generate a report analyzing the cause of the depletion and optimize subsequent battery calibration.

[0083] To facilitate a clearer and more intuitive understanding of the battery low-power reminder method of the embodiments of this application by those skilled in the art, the following is combined with... Figure 4 Please provide a detailed explanation.

[0084] Specifically, Figure 4 This is a block diagram of a battery low-power reminder system according to an embodiment of the present application. The system may include a big data back-end decision platform 1, a vehicle network back-end 2, an in-vehicle communication module 3, a CAN (Controller Area Network) bus 4, a body controller 5, an in-vehicle infotainment system 6, a central gateway 7, a hybrid power control unit 8, and a battery management system controller 9.

[0085] The system comprises several components: a big data backend decision platform 1, based on big data technology, responsible for collecting, analyzing, and processing various vehicle data to determine if the battery charge is too low and making corresponding decisions, such as sending a reminder to the driver or triggering other operations; a vehicle network backend 2, receiving data from the vehicle communication module 3 and transmitting it to the big data backend decision platform 1 for further analysis and processing; a vehicle communication module 3 transmitting vehicle data to the vehicle network backend 2 via a wireless network or other communication methods; a CAN bus 4 connecting the vehicle communication module 3, body controller 5, vehicle infotainment system 6, and hybrid power control unit 8, enabling data transmission and communication between these devices; a body controller 5 controlling the operation of various electronic devices in the vehicle; a vehicle infotainment system 6 integrating various functions such as navigation, entertainment, and communication; a central gateway 7 connecting the body controller 5, vehicle infotainment system 6, and battery management system controller 9 for data transmission and communication; and a hybrid power control unit 8 communicating with the battery management system controller to obtain battery charge information. The battery management system controller 9 can provide battery power information to other devices and communicate with the body controller 5, hybrid power control unit 8, etc.

[0086] Therefore, the battery low-power reminder system involved in the battery low-power reminder method of one embodiment of this application realizes real-time monitoring of vehicle batteries, timely reminders to users of low battery power, cultivates and optimizes users' driving habits, and extends the service life of batteries.

[0087] The battery depletion alert method proposed in this application involves inputting real-time vehicle data into a pre-trained battery depletion cause identification model to obtain a current battery depletion prediction result. If the prediction result indicates battery depletion, the cause of the depletion is identified, an alert message is generated, and the message is sent to a preset mobile terminal. This solves the problems of high effort consumption and low accuracy in related battery depletion analysis methods. By using vehicle network big data for depletion identification, the process and timeliness of depletion handling are optimized, thereby improving the user's driving experience.

[0088] Next, the battery low-power reminder device according to the embodiments of this application is described with reference to the accompanying drawings.

[0089] Figure 4 This is a block diagram of the battery low-power reminder device 10 according to an embodiment of this application.

[0090] like Figure 4 As shown, the battery low-power reminder device 10 includes: an acquisition module 100, a prediction module 200, and a reminder module 300.

[0091] The system includes an acquisition module 100 for acquiring real-time vehicle data of the current vehicle; a prediction module 200 for inputting the real-time vehicle data into a pre-trained battery drain cause identification model to obtain a battery drain prediction result for the current vehicle, wherein the pre-trained battery drain cause identification model is obtained by training a target neural network from the vehicle data to be trained; and a reminder module 300 for obtaining the battery drain cause from the battery drain prediction result if the battery drain prediction result is that the battery is drained, generating a reminder message based on the battery drain cause, and sending the reminder message to a preset mobile terminal.

[0092] Furthermore, in some embodiments, the cause of power loss includes at least one of controller abnormal hold, controller abnormal wake-up, and user misuse.

[0093] Furthermore, in some embodiments, the reminder module 300 is used to: if the cause of the power loss is abnormal controller hold or abnormal controller wake-up, then the reminder information is a controller optimization reminder information; and send the controller optimization reminder information to the after-sales center of the current vehicle.

[0094] Furthermore, in some embodiments, the reminder module 300 is used to: if the reason for the low battery is due to improper use by the user, then the reminder message is an engine start reminder; and send the engine start reminder to the vehicle's infotainment system so that the engine start reminder can be displayed through the infotainment system.

[0095] Furthermore, in some embodiments, before inputting real-time vehicle data into the pre-trained power loss cause identification model, the prediction module 200 is further configured to: acquire offline vehicle data of multiple vehicles with power loss within a first preset time period before power loss; based on the offline vehicle data, filter out vehicle data to be trained that meets preset training conditions; train multiple target neural networks using the vehicle data to be trained to obtain a controller abnormal hold / wake-up model, a user misuse model, a power loss and health correlation model, and a frequent start behavior and health correlation model; when the model identification results of the controller abnormal hold / wake-up model, the user misuse model, the power loss and health correlation model, and the frequent start behavior and health correlation model are all greater than preset results, obtain the pre-trained power loss cause identification model based on the models of the controller abnormal hold / wake-up model, the user misuse model, the power loss and health correlation model, and the frequent start behavior and health correlation model.

[0096] Furthermore, in some embodiments, real-time vehicle data includes at least one of vehicle status data, battery status data, electrical component status, and current ambient temperature.

[0097] It should be noted that the foregoing explanation of the battery low-power reminder method embodiment also applies to the battery low-power reminder device of this embodiment, and will not be repeated here.

[0098] According to the battery low-power reminder device proposed in this application, real-time vehicle data is input into a pre-trained low-power cause identification model to obtain the current battery low-power prediction result. If the low-power prediction result indicates that the battery is low-power, the cause of the low-power is obtained, a reminder message is generated, and the reminder message is sent to a preset mobile terminal. This solves the problems of high effort consumption and low accuracy in related technologies for battery low-power analysis. By using vehicle network big data for low-power identification, the process and timeliness of low-power handling are optimized, thereby improving the user's driving experience.

[0099] Figure 6 A schematic diagram of the structure of a vehicle provided in an embodiment of this application. The vehicle may include:

[0100] The memory 601, the processor 602, and the computer program stored on the memory 601 and capable of running on the processor 602.

[0101] When the processor 602 executes the program, it implements the battery low power reminder method provided in the above embodiments.

[0102] Furthermore, the vehicle also includes:

[0103] Communication interface 603 is used for communication between memory 601 and processor 602.

[0104] The memory 601 is used to store computer programs that can run on the processor 602.

[0105] The memory 601 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0106] If the memory 601, processor 602, and communication interface 603 are implemented independently, then the communication interface 603, memory 601, and processor 602 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 6 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0107] Optionally, in a specific implementation, if the memory 601, processor 602, and communication interface 603 are integrated on a single chip, then the memory 601, processor 602, and communication interface 603 can communicate with each other through an internal interface.

[0108] The processor 602 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0109] This embodiment also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described battery low-power reminder method.

[0110] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0111] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0112] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0113] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0114] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0115] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0116] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0117] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A method for reminding users of low battery power, characterized in that, Includes the following steps: Obtain real-time vehicle data for the current vehicle; The real-time vehicle data is input into a pre-trained battery drain cause identification model to obtain the current battery drain prediction result for the vehicle, wherein the pre-trained battery drain cause identification model is obtained by training a target neural network using vehicle data to be trained; and If the battery depletion prediction result is that the battery is depleted, then the cause of the depletion is obtained from the battery depletion prediction result, and a reminder message is generated based on the cause of the depletion, and the reminder message is sent to a preset mobile terminal; Before inputting the real-time vehicle data into the pre-trained battery depletion cause identification model, the method further includes: Acquire offline vehicle data for multiple vehicles with depleted battery power within a first preset time period before the battery depletes. Based on the offline vehicle data, the training vehicle data that meets the preset training conditions is selected. Multiple target neural networks are trained using the vehicle data to be trained, resulting in a controller abnormal hold / wake-up model, a user misuse model, a battery depletion and health correlation model, and a frequent start-up behavior and health correlation model. When the model identification results of the controller abnormal hold / wake-up model, the user misuse model, the power loss and health correlation model, and the frequent startup behavior and health correlation model are all greater than the preset results, the pre-trained power loss cause identification model is obtained based on the models of the controller abnormal hold / wake-up model, the user misuse model, the power loss and health correlation model, and the frequent startup behavior and health correlation model.

2. The method according to claim 1, characterized in that, The reasons for power loss include at least one of the following: abnormal controller hold-up, abnormal controller wake-up, and improper user operation.

3. The method according to claim 2, characterized in that, The step of generating a reminder message based on the cause of the power depletion and sending the reminder message to a preset mobile terminal includes: If the reason for the power loss is that the controller is abnormally holding or abnormally waking up, then the reminder message is a controller optimization reminder message; Send the controller optimization reminder message to the after-sales center of the current vehicle.

4. The method according to claim 2, characterized in that, The step of generating a reminder message based on the cause of the power depletion and sending the reminder message to a preset mobile terminal includes: If the reason for the low battery is improper use by the user, then the reminder message is an engine start reminder. The engine start reminder is sent to the vehicle's infotainment system so that the engine start reminder can be displayed on the infotainment system.

5. The method according to any one of claims 1-4, characterized in that, The real-time vehicle data includes at least one of the following: vehicle status data, battery status data, electrical component status, and current ambient temperature.

6. A battery low-charge reminder device, characterized in that, include: The acquisition module is used to acquire real-time vehicle data for the current vehicle. The prediction module inputs the real-time vehicle data into a pre-trained battery drain cause identification model to obtain the current battery drain prediction result for the vehicle. The pre-trained battery drain cause identification model is obtained by training a target neural network using the vehicle data to be trained. The reminder module is used to obtain the cause of battery depletion from the battery depletion prediction result if the battery depletion prediction result is that the battery is depleted, generate reminder information based on the cause of battery depletion, and send the reminder information to a preset mobile terminal. Before inputting the real-time vehicle data into the pre-trained battery depletion cause identification model, the method further includes: Acquire offline vehicle data for multiple vehicles with depleted battery power within a first preset time period before the battery depletes. Based on the offline vehicle data, the training vehicle data that meets the preset training conditions is selected. Multiple target neural networks are trained using the vehicle data to be trained, resulting in a controller abnormal hold / wake-up model, a user misuse model, a battery depletion and health correlation model, and a frequent start-up behavior and health correlation model. When the model identification results of the controller abnormal hold / wake-up model, the user misuse model, the power loss and health correlation model, and the frequent startup behavior and health correlation model are all greater than the preset results, the pre-trained power loss cause identification model is obtained based on the models of the controller abnormal hold / wake-up model, the user misuse model, the power loss and health correlation model, and the frequent startup behavior and health correlation model.

7. The apparatus according to claim 6, characterized in that, The reasons for power loss include at least one of the following: abnormal controller hold-up, abnormal controller wake-up, and improper user operation.

8. A vehicle, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the battery low-power reminder method as described in any one of claims 1-5.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the battery low-power reminder method as described in any one of claims 1-5.

Images