A power management method and device, a vehicle and a storage medium

Abstract

The application relates to the field of vehicle data communication, in particular to a power management method and device, a vehicle and a storage medium. The method is applied to a processor of a vehicle; the processor comprises a trained power management model; the method comprises the following steps: obtaining driving data of a target user; inputting the driving data of the target user into the power management model to determine the identification of a first load which needs to be subjected to power management and the power management operation corresponding to the first load; generating a power management operation instruction based on the identification of the first load and the power management operation corresponding to the first load, and sending the power management operation instruction to a controller, so that the controller executes the power management operation on the first load according to the power management operation instruction. Thus, the problem that, in the related art, when a domain controller is used to perform power management on a vehicle, the awakening demand of a user for various loads in the vehicle in the actual driving process of the vehicle is ignored, and the user has a poor use experience can be solved.

Description

A power management method, apparatus, vehicle, and storage medium Technical Field

[0001] This application relates to the field of vehicle management, specifically to vehicle power management, sleep / wake-up, and static power consumption, and particularly to a power management method, device, vehicle, and storage medium. Background Technology

[0002] With the rapid development of vehicle intelligence and the continuous updating of vehicle usage scenarios, keeping all vehicle loads in a constantly active state under different usage scenarios will increase vehicle power consumption, thereby increasing load loss and battery consumption, and affecting vehicle range.

[0003] To address the aforementioned issues, a vehicle-specific sleep / wake-up method and system have been proposed in related technologies. While this method utilizes a domain controller to determine and handle the wake-up needs of various vehicle loads under different scenarios, reducing unnecessary power consumption during vehicle sleep / wake-up, it only handles vehicle wake-up based on a predefined mapping between usage scenarios and load wake-up lists. It ignores the actual wake-up needs of users for various loads within the vehicle during actual driving, resulting in a poor user experience. Summary of the Invention

[0004] This application provides a power management method, apparatus, vehicle, and storage medium to at least address the problem in related technologies where domain controllers are used for vehicle power management, neglecting the wake-up needs of various loads within the vehicle during actual driving, resulting in a poor user experience. The technical solution of this application is as follows:

[0005] According to a first aspect of this application, a power management method is provided, applied to a processor in a vehicle; the processor includes a trained power management model; the method includes: acquiring driving data of a target user; the driving data of the target user includes: operating parameters of various loads in the vehicle during the target user's driving process, the vehicle's passenger status, and the user's operation parameters on various loads in the vehicle; inputting the target user's driving data into the power management model, determining the identifier of a first load requiring power management, and the power management operation corresponding to the first load; wherein the power management operation is to switch the power state of the first load from a first state to a second state; generating a power management operation instruction based on the identifier of the first load and the power management operation corresponding to the first load, and sending it to a controller, so that the controller performs a power management operation on the first load according to the power management operation instruction.

[0006] Based on the aforementioned technical means, the method provided in this application acquires the user's driving data and inputs it into the power management model to generate a power management operation instruction based on the identifier of the first load and the corresponding power management operation, and performs a power management operation on the first load. This method can simultaneously manage the vehicle's power and meet the user's need to wake up various loads in the vehicle during actual driving, making the vehicle's power management solution more user-friendly and improving the user's driving experience.

[0007] In one possible implementation, after inputting the target user's driving data into the power management model, determining the identifier of the first load requiring power management, and the power management operation corresponding to the first load, the method further includes: within a first preset time period, detecting whether there is a correction event for the first load; the correction event is an event that contradicts the first power management operation corresponding to the first load; if there is a correction event for the first load, and the correction level of the correction event is greater than a preset level, adjusting the power management operation corresponding to the first load; wherein, the adjusted power management operation is to control the power state of the first load to remain in a first state.

[0008] Based on the above technical means, the method provided in this application, in addition to using a power management model to determine the power management operation corresponding to the first load, also detects whether there is a correction event for the first load within a first preset time period. This can make the power management scheme for the vehicle more refined and more suitable for the user's driving habits, while reducing the vehicle's power consumption and improving the vehicle's overall driving range.

[0009] In another possible implementation, the power state includes a power-on state and a power-off state; when the first state is the power-on state and the second state is the power-off state, the correction event includes an event in which the user has a demand for the first load.

[0010] Based on the aforementioned technical means, the method provided in this application can detect whether a correction event exists in the first load, and keep the power state of the first load in a powered-on state when the user has a need to use the first load, thereby improving the user experience, achieving refined power management of the vehicle, reducing load loss during vehicle operation, thereby reducing power battery consumption and improving the overall driving range of the vehicle.

[0011] In another possible implementation, the method further includes, before acquiring the target user's driving data:

[0012] Acquire user driving data; user driving data includes: operating parameters of various loads in the vehicle during the user's driving process, vehicle occupancy status, and user operation parameters of various loads in the vehicle; based on user driving data and power management scheme, train a power management model to obtain a trained power management model; the power management scheme includes: identification of loads requiring power management, and corresponding power management operations for the loads; wherein, the power management scheme is determined according to a preset correspondence, which is the correspondence between user driving data and the power status of various loads in the vehicle.

[0013] Based on the aforementioned technical means, compared to related technologies that directly manage vehicle power through relays or local area networks, which can easily lead to static losses in the vehicle's load and the inability to recommend personalized power management solutions for users, the method provided in this application improves the accuracy of vehicle power management by configuring a power management model on the vehicle and training the model based on the user's driving data. Simultaneously, it adapts to the user's driving habits, thereby reducing vehicle power consumption during driving while enhancing the user's driving experience.

[0014] In another possible implementation, a power management model is trained based on the user's driving data and power management scheme to obtain a trained power management model. This includes: constructing training samples based on the user's driving data and power management scheme; training the power management model based on the training samples to obtain a trained power management model; and using the power management model to determine the power status of each load in the vehicle.

[0015] Based on the aforementioned technical means, the method provided in this application constructs training samples using user driving data and power management schemes, and trains a power management model based on the training samples. This allows the power management model's recommendation results to better align with user driving habits, thereby reducing vehicle power consumption, implementing refined power management, and improving the user's driving experience.

[0016] According to a second aspect of this application, a power management device is provided, applied to a processor in a vehicle; the processor includes a trained power management model; the power management device includes: an acquisition module, used to acquire driving data of a target user; the target user's driving data includes: operating parameters of various loads in the vehicle during the target user's driving process, the vehicle's passenger status, and the user's operation parameters on various loads in the vehicle; a determination module, used to input the target user's driving data into the power management model, determine the identifier of a first load requiring power management, and the power management operation corresponding to the first load; wherein the power management operation is to switch the power state of the first load from a first state to a second state; and a generation module, used to generate a power management operation instruction based on the identifier of the first load and the power management operation corresponding to the first load, and send it to a controller, so that the controller performs a power management operation on the first load according to the power management operation instruction.

[0017] In one possible implementation, the power management device further includes: a detection module and an adjustment module; the detection module is used to detect whether a correction event exists in the first load within a first preset time period; the correction event is an event that contradicts the first power management operation corresponding to the first load; the adjustment module is used to adjust the power management operation corresponding to the first load when a correction event exists in the first load and the correction level of the correction event is greater than a preset level; wherein, the adjusted power management operation is to control the power state of the first load to remain in a first state.

[0018] In another possible implementation, the power state includes a power-on state and a power-off state; when the first state is the power-on state and the second state is the power-off state, the correction event includes an event in which the user has a demand for the first load.

[0019] In another possible implementation, the power management device further includes: a training module; an acquisition module, further configured to acquire user driving data; the user driving data includes: the operating parameters of various loads in the vehicle during the user's driving process, the vehicle's passenger status, and the user's operation parameters on various loads in the vehicle; the training module is configured to train a power management model based on the user's driving data and the power management scheme, to obtain a trained power management model; the power management scheme includes: the identifiers of the loads requiring power management, and the corresponding power management operations for the loads; wherein, the power management scheme is determined according to a preset correspondence, which is the correspondence between the user's driving data and the power status of various loads in the vehicle.

[0020] According to a third aspect of this application, a vehicle is provided, comprising: 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 first aspect described above and any possible implementation thereof.

[0021] According to a fourth aspect provided in this application, a computer-readable storage medium is provided that, when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, enables the electronic device to perform the method described in the first aspect and any possible implementation thereof.

[0022] Therefore, the above-mentioned technical features of this application have the following beneficial effects:

[0023] (1) The method provided in this application obtains the user's driving data and inputs it into the power management model to generate a power management operation instruction based on the identifier of the first load and the corresponding power management operation, and performs a power management operation on the first load. This can meet the user's need to wake up the various loads in the vehicle during actual driving while managing the vehicle's power, making the vehicle's power management scheme more suitable for the user and improving the user's driving experience.

[0024] (2) In addition to using a power management model to determine the power management operation corresponding to the first load, the method provided in this application also detects whether there is a correction event for the first load within a first preset time period. This can make the power management scheme for the vehicle more refined and more suitable for the user's driving habits, while reducing the power consumption of the vehicle and improving the overall driving range of the vehicle.

[0025] (3) The method provided in this application can detect whether there is a correction event in the first load, and keep the power state of the first load in the power-on state when the user has a need for the first load, so as to improve the user experience, achieve refined power management of the vehicle, reduce the load loss of the vehicle during driving, thereby reducing the consumption of the power battery and improving the overall driving range of the vehicle.

[0026] (4) Compared with the related technologies, which directly manage the power of the vehicle through relays or local network, the load in the vehicle is prone to static loss and cannot recommend personalized power management solutions for users. The method provided in this application improves the accuracy of power management of the vehicle by configuring a power management model on the vehicle and training the power management model based on the user's driving data. At the same time, it adapts to the user's driving habits, so as to improve the user's driving experience while reducing the power consumption of the vehicle during driving.

[0027] (5) The method provided in this application constructs training samples through user driving data and power management scheme, and trains the power management model based on the training samples. This makes the recommendation results of the power management model more in line with the user's driving habits, thereby reducing vehicle power consumption, performing refined power management of the vehicle, and improving the user's driving experience.

[0028] It should be noted that the technical effects of any of the implementation methods in the second to fourth aspects can be found in the technical effects of the corresponding implementation method in the first aspect, and will not be repeated here.

[0029] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0030] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application, and do not constitute an undue limitation of this application.

[0031] Figure 1 is a structural diagram of a power management system according to an exemplary embodiment;

[0032] Figure 2 is a flowchart illustrating a power management method according to an exemplary embodiment;

[0033] Figure 3 is a flowchart illustrating another power management method according to an exemplary embodiment;

[0034] Figure 4 is a flowchart illustrating another power management method according to an exemplary embodiment;

[0035] Figure 5 is a schematic diagram of an adaptive algorithm according to an exemplary embodiment;

[0036] Figure 6 is a flowchart illustrating another power management method according to an exemplary embodiment;

[0037] Figure 7 is a flowchart illustrating another power management method according to an exemplary embodiment;

[0038] Figure 8 is a flowchart illustrating another power management method according to an exemplary embodiment;

[0039] Figure 9 is a flowchart illustrating another power management method according to an exemplary embodiment;

[0040] Figure 10 is a structural diagram of a region controller according to an exemplary embodiment;

[0041] Figure 11 is a structural diagram of a power management device according to an exemplary embodiment;

[0042] Figure 12 is a structural diagram of a vehicle according to an exemplary embodiment.

[0043] The system includes a cloud server 100, a processor 200, a controller 300, a load 400, a power management device 500, an acquisition module 501, a determination module 502, a generation module 503, a detection module 504, an adjustment module 505, a training module 506, a vehicle 600, a processor 601, and a memory 602. Detailed Implementation

[0044] To enable those skilled in the art to better understand the technical solutions of this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0045] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0046] The following description, with reference to the accompanying drawings, illustrates a power management method, apparatus, vehicle, and storage medium according to embodiments of this application. Currently, in the field of vehicle load power supply, vehicle power management primarily involves analyzing the power flow and supplying power to the load end via the battery fuse box (some special loads have a relay added before the fuse) to manage the vehicle's power at different levels. However, this method has significant drawbacks: 1. Relays are large and occupy considerable vehicle space. Furthermore, the limited vehicle space indirectly restricts the number of relays, leading to situations where the same relay controls multiple loads, hindering precise control of vehicle power management; 2. Relay control of vehicle loads has a large delay, making it difficult to meet certain load performance indicators in the context of continuous intelligent and connected vehicle development; 3. Once the power supply components are determined, the logic cannot be updated, making it unsuitable for adapting to constantly evolving vehicle driving scenarios; 4. Loads not controlled by relays will continue to consume the vehicle's power after the vehicle is powered off. To address the aforementioned issues, related technologies have proposed a method that outputs power through a bypass power supply when the vehicle is in a low-power state, and outputs power through the main power circuit when a wake-up command is received. However, this method increases the number of interface lines in the vehicle's wiring, making the hardware design complex. Furthermore, it does not provide a detailed explanation of how to handle multiple combined operating conditions, making it unsuitable for application under dynamic vehicle operating conditions.

[0047] Therefore, to address the aforementioned issues, this application provides a power management method. By acquiring the user's driving data and inputting it into a power management model, a power management operation instruction is generated based on the identifier of the first load and the corresponding power management operation. The power management operation is then performed on the first load. This method can simultaneously manage the vehicle's power supply and meet the user's need to wake up various loads within the vehicle during actual driving. This makes the vehicle's power management solution more user-friendly and improves the user's driving experience.

[0048] For ease of understanding, the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0049] Figure 1 illustrates a power management system provided in an embodiment of this application. This power management system is applied in a network architecture using vehicle Ethernet or CAN as the medium. The power management system includes a cloud server 100, a processor 200, a controller 300, and a load 400. The cloud server 100 and processor 200 are communicatively connected; the controller 300 and processor 200 are communicatively connected; and the controller 300 and load 400 are electrically connected.

[0050] The Cloud Server 100 is used to host websites, applications, databases, and other applications, providing stable and reliable computing resources. In addition, the Cloud Server 100 can also be used to build testing environments, development environments, virtual desktops, and virtual private networks.

[0051] In some embodiments, the cloud server 100 is specifically used to build and manage a power management startup table. The table stores the mapping relationship between various loads within the vehicle and different functional scenarios of the vehicle.

[0052] For example, when a vehicle is in over-the-air (OTA) mode, it is necessary to remotely update the motor controller (IPU) and battery management system (BMS) in the vehicle. In this case, an OTA mode scenario will be added to the Table, and the OTA mode scenario will be matched with the IPU and BMS.

[0053] In some embodiments, the cloud server 100 is also used to update the Table when the vehicle has new features or the mapping relationship changes.

[0054] In some embodiments, the cloud server 100 is also used to import the Table into the processor 200 using Extensible Markup Language (XML), and when the Table is updated, to import the updated Table into the processor 200 in XML format.

[0055] The processor 200 is used for multimedia entertainment, satellite navigation, professional diagnosis of vehicle information and faults, and control of various modules inside the vehicle.

[0056] As one possible implementation, the processor 200 is specifically used to parse the Table after receiving it from the cloud server 100.

[0057] In some embodiments, the processor 200 is also used to identify the functional scenarios of the vehicle, obtain the load mapped to the functional scenario in the Table according to the identified functional scenario, and send the information of the load that needs to work under the functional scenario to the controller 300 via Ethernet or CAN.

[0058] For example, when the processor 200 recognizes the OTA mode signal of the vehicle's OTA MASTER, it determines that the current functional scenario of the vehicle is in OTA mode. The processor 200 obtains the load mapped to the OTA mode from the table and sends the information of the load that needs to work in OTA mode to the controller 300 via Ethernet or CAN.

[0059] In another possible implementation, the processor 200 is specifically used to acquire the target user's driving data, input the target user's driving data into the power management model, determine the identifier of the first load requiring power management, and the power management operation corresponding to the first load. Simultaneously, the processor 200 is also used to generate a power management operation instruction based on the identifier of the first load and the corresponding power management operation, and send it to the controller, so that the controller performs a power management operation on the first load according to the power management operation instruction.

[0060] In some embodiments, the processor 200 may be the vehicle's central computer.

[0061] The controller 300, after receiving the load information sent by the processor 200, controls the corresponding chip and peripheral circuits through the microcontroller unit (MCU) to enable the input / output (I / O) interface of the corresponding load, while disabling other unrelated loads.

[0062] In this embodiment of the application, there may be one or more controllers 300, and the number of controllers 300 is not limited in this embodiment of the application. For example, the number of controllers 300 may be 2 or M.

[0063] In some embodiments, controller 300 may be a vehicle area controller.

[0064] The 400 load is used to convert electrical energy provided by the vehicle into other forms of energy.

[0065] In this embodiment of the application, the load 400 can be one or more, and the number of loads 400 is not limited in this embodiment of the application. For example, the number of loads 400 can be 2 or N.

[0066] Understandably, the aforementioned power management system can determine the layout of the controller 300 and load 400 based on the vehicle's bill of materials (BOM), and connect the load 400 to the power supply of the controller 300 as close as possible according to the layout. Then, based on the operating characteristics of the load 400, the type of power supply chip for the controller 300 is selected.

[0067] For example, constant-power I / O resources are allocated to the source controller responsible for vehicle wake-up, such as near-field communication (NFC) sensors, Bluetooth (BLE) modules, and telematics boxes (TBOX). Controllable electrical I / O resources are allocated to other controllers, such as actuators like water pumps and oil pumps.

[0068] In particular, constant power resources should be avoided for loads that do not involve electricity, in order to avoid waste of resources and costs.

[0069] The principle of proximity can reduce the length of the vehicle's wiring harness and impedance power consumption.

[0070] Figure 2 illustrates a power management method provided in an embodiment of this application, applied to a vehicle processor; the processor includes a trained power management model; this method is a power management method for a vehicle during dynamic driving. The method includes steps S101-S103.

[0071] S101. Obtain the target user's driving data.

[0072] The target user's driving data includes: the operating parameters of various loads in the vehicle during the target user's driving process, the vehicle's passenger situation, and the user's operation parameters of various loads in the vehicle.

[0073] In some embodiments, the operating parameters of each load in the vehicle may be the usage duration, usage frequency, and power status of each load in the vehicle; the vehicle occupancy status may be whether each seat in the vehicle is occupied by a user; and the operating parameters of each load in the vehicle by the user may be the usage duration and usage frequency of each load in the vehicle by the user.

[0074] S102. Input the target user's driving data into the power management model, determine the identifier of the first load that needs power management, and the power management operation corresponding to the first load.

[0075] The power management operation involves switching the power state of the first load from the first state to the second state.

[0076] For example, taking the first load as a background entertainment screen, and the first state of the background entertainment screen as power-on, the above step S102 will be specifically explained.

[0077] First, the driving data of target user B is analyzed to obtain the usage parameter of the background entertainment screen as 0.1. Then, the usage parameter of the background entertainment screen is input into the power management model to determine the identifier of the first load that needs power management as YLP, and its corresponding power management operation is: power off.

[0078] S103. Generate a power management operation instruction based on the identifier of the first load and the power management operation corresponding to the first load, and send it to the controller so that the controller performs a power management operation on the first load according to the power management operation instruction.

[0079] In some embodiments, the first load may be the rear entertainment screen. Based on the identifier of the rear entertainment screen: YLP, and the corresponding power management operation: power down, a power management operation management instruction is generated, so that the controller performs a power management operation on the rear entertainment screen according to the power management operation instruction.

[0080] Understandably, as power management models continue to improve, the power management operations recommended by these models will become increasingly accurate, resulting in lower overall power consumption and improved overall vehicle range. Furthermore, by combining power management models with corrective events, the method provided in this application can adapt power management methods to the user based on the driver's driving characteristics and the user's operational behavior within the vehicle, improving the user's driving experience while optimizing the overall power consumption of the vehicle.

[0081] In some embodiments, as shown in FIG3, before step S101, the method further includes steps S201-S202.

[0082] S201. Obtain the user's driving data.

[0083] The user's driving data includes: the operating parameters of various loads in the vehicle, the passenger situation in the vehicle, and the user's operation parameters of various loads in the vehicle during the driving process.

[0084] In some embodiments, since multiple drivers may be operating the same vehicle, the in-vehicle cameras will identify each driver based on their facial recognition code. Each driver's identification code and driving data are packaged into a separate data packet. When a driver is driving the vehicle, that driver's driving data is stored in the data packet corresponding to their identification code.

[0085] As one possible implementation, when driver A powers on the vehicle and drives it, the in-vehicle camera performs facial recognition on driver A and obtains driver A's identification code 123. Then, the processor retrieves driver A's identification code 123. If the processor currently stores a data packet 123 corresponding to identification code 123, driver A's driving data can be obtained from data packet 123. At the same time, the processor can collect driver A's driving data during the driving process and store it in data packet 123 to expand data packet 123.

[0086] Another possible implementation involves the following steps: When driver A powers on the vehicle and begins driving, the in-vehicle camera performs facial recognition on driver A and obtains driver A's identification code 123. The processor then searches for driver A's identification code 123. If the processor does not currently store the data packet corresponding to driver A's identification code 123, it automatically creates a new data packet 123 for driver A. During the driving process, the processor collects driver A's driving data and stores it in data packet 123. At this point, driver A's driving data is acquired by the processor in real time. When driver A's driving time and mileage are sufficiently long, meaning that data packet 123 contains a sufficient amount of driving data, the processor can use the previously obtained driving data as the driving data required for the training samples described below.

[0087] S202. Based on the user's driving data and power management scheme, train the power management model to obtain a trained power management model.

[0088] In some embodiments, the power management scheme includes: an identifier of the load that needs power management, and the power management operation corresponding to the load.

[0089] For example, the power management scheme includes: a rear entertainment screen identifier: YLP; and a corresponding power management operation for the rear entertainment screen: power on. A lidar identifier: LD; and a corresponding power management operation for the lidar: power off.

[0090] In some embodiments, the power management scheme is determined based on a preset correspondence, which is the correspondence between the user's driving data and the power status of each load in the vehicle.

[0091] For example, the processor stores the aforementioned preset correspondence in advance. For instance, when the usage parameters of the rear entertainment screen are less than or equal to 0.3, the corresponding power management operation is: power off; when the usage parameters of the rear entertainment screen are greater than 0.3, the corresponding power management operation is: power on. As another example, when the usage parameters of the LiDAR are less than or equal to 0.4, the corresponding power management operation is: power off; when the usage parameters of the LiDAR are greater than 0.4, the corresponding power management operation is: power on.

[0092] For example, the processor analyzes the user's driving behavior and habits based on the user's driving data, and determines the usage parameters of the rear entertainment screen and the lidar.

[0093] For example, taking the usage parameters of the rear entertainment screen as an example, the processor stores an algorithm model that analyzes the user's driving data, and can analyze the usage parameters of the rear entertainment screen based on the user's driving data.

[0094] Specifically, when the user's weight in the rear seat meets the preset weight, the rear seat pressure sensor detects a low level; if the weight does not meet the preset weight, the rear seat pressure sensor detects a high level. The processor counts the duration of the high level signal from the rear seat pressure sensor. and low level duration This gives the percentage of time T1 spent using the rear seats during a single trip. The processor sends the percentage of rear seat usage time during each trip to the central computer. Based on this percentage across multiple trips, the central computer can calculate a more accurate estimate of the user's actual rear seat usage time as T. X = .

[0095] The processor filters the screen image output process of the rear entertainment screens, uses software scheduling, and timers to obtain the usage time t of the entertainment screens in a single trip. S and t S Total time t for a single trip DrvThe comparison yields the percentage of rear-seat entertainment screen usage time (t1) for a single trip. The processor sends this percentage to the central computer for each trip. The central computer can then calculate a more accurate percentage of actual user rear-seat entertainment screen usage time (T) based on these percentages from multiple trips. y = .

[0096] If the parameter for the rear entertainment screen is f0, the central computer will calculate the percentage of time the user spends using the rear seats, T. X And the percentage of time users spend using the rear entertainment screen (T) y The weighted calculation of the usage parameters for the rear entertainment screens is as follows: .

[0097] If the calculated usage parameter of the rear entertainment screen is 0.2, the corresponding power management operation for the rear entertainment screen is: power down. At this time, after confirming the power down command, the central computer sends this information to the area controller via the vehicle Ethernet. The area controller can map the power down command to the corresponding interface, and the MCU controls the corresponding chip to turn off the metal-oxide-semiconductor field-effect transistor (MOSFET) in the corresponding circuit, thus achieving the power down operation of the load.

[0098] Similarly, when the processor, based on the user's driving data, identifies that the user's frequency of using the adaptive cruise control function is low, and that the driver mainly uses the steering wheel and accelerator pedal for human-machine control while driving, and interacts with the vehicle through the central control screen, and when this data is sufficiently long in time and represents a sufficiently large proportion of vehicle usage, the central computer determines the LiDAR's usage parameter to be 0.1, and obtains the corresponding power management operation for the LiDAR: power down. At this point, after confirming the power down command, the central computer sends this information to the area controller via the vehicle's Ethernet. The area controller can then map the power down command to the corresponding interface, and the MCU controls the corresponding chip to turn off the metal-oxide-semiconductor field-effect transistor (MOSFET) in the corresponding circuit, thus achieving the power down operation of the load.

[0099] Understandably, when a vehicle leaves the factory, a power management model is deployed within the vehicle's central computer's high-performance computing platform. When this model hasn't been trained, it won't perform any specific actions but will instead run as a background program on the system-on-chip (SOC). Once the user powers on the vehicle, the power management model will automatically start running.

[0100] In some embodiments, as shown in FIG4, the above step S202 can be specifically implemented as: steps S2021-S2022.

[0101] Step S2021: Construct training samples based on user driving data and power management scheme;

[0102] In some embodiments, after collecting the user's driving data, the processor analyzes the user's driving behavior and habits based on the driving data to obtain the usage parameters of each load, and constructs training samples based on the power management scheme corresponding to the usage parameters of each load.

[0103] The parameter type used is the parameter type suitable for training the power management model.

[0104] Step S2022: Train the power management model based on the training samples to obtain the trained power management model.

[0105] The power management model is used to determine the power status of each load within the vehicle.

[0106] Optionally, the power management model can be trained using an adaptive management algorithm.

[0107] In some embodiments, based on the training samples constructed in step S2021 above, the power management model uses an adaptive management algorithm to perform self-training to obtain a trained power management model.

[0108] For example, as shown in Figure 5, user driving data, such as driving characteristics, frequency of function use, and vehicle sensor signals, can be input into an adaptive algorithm to output a corresponding power management scheme. The adaptive algorithm can automatically adjust the processing method, processing order, processing parameters, boundary conditions, or constraints based on the data characteristics during processing and analysis, adapting them to the statistical distribution and structural characteristics of the processed data to achieve the best processing results.

[0109] Optionally, the adaptive algorithm typically employs a gradient-based algorithm. In specific applications, the least mean square error algorithm, recursive least squares algorithm, or Kalman filter algorithm can be selected. This application does not limit the specific algorithm used.

[0110] In some embodiments, after step S102, as shown in FIG6, the method further includes steps S301-S302.

[0111] S301. Within a first preset time period, detect whether there is a correction event for the first load.

[0112] Among them, the correction event is an event that contradicts the first power management operation corresponding to the first load.

[0113] For example, the first preset time period can be 30 seconds.

[0114] In some embodiments, if the power management operation corresponding to the first load is power down, but the processor detects that the user uses the first load frequently, which contradicts the power management operation, then it is determined that a correction event exists for the first load.

[0115] For example, taking the rear entertainment screen as the first load. If the user's demand for and frequency of use of the rear entertainment screen is low, when the user's driving data is input into the power management model, the power management operation of the rear entertainment screen is: power off, that is, when the power of the rear entertainment screen needs to be turned off, if the processor detects that there is someone in the rear seat of the vehicle through the rear seat sensor, or the processor detects that the user has adjusted the height and backrest angle of the rear seat through the central control screen, the processor will determine the above events as correction events for the rear entertainment screen.

[0116] For example, taking LiDAR as the first load. If the user's frequency of using the intelligent driving function is low, that is, the user's demand for the LiDAR load is low, when the user's driving data is input into the power management model, the power management operation of the LiDAR is: power off, that is, the power of the LiDAR needs to be turned off. If the processor recognizes that the user clicked the intelligent driving sub-menu page through the central control screen, or the processor recognizes that the user clicked the assisted driving button on the steering wheel, the processor will identify the above events as LiDAR correction events.

[0117] S302. If a correction event exists in the first load and the correction level of the correction event is greater than the preset level, adjust the power management operation corresponding to the first load.

[0118] The adjusted power management operation controls the power state of the first load to remain in the first state.

[0119] In some embodiments, the power state includes: power-on state and power-off state;

[0120] When the first state is the power-on state and the second state is the power-off state, the corrective events include events where the user has a need to use the first load.

[0121] In some embodiments, each load has a corresponding preset level. For example, the preset level for the rear entertainment screen is 6, and the preset level for the LiDAR is 5.

[0122] Specifically, assuming the rear entertainment screen's initial state is "powered on," but the power management model's power management operation is to power off the rear entertainment screen; if the processor recognizes that the rear seat is "occupied," meaning the probability of the user using the rear entertainment screen intermittently is high, the correction event level for the rear entertainment screen can be 7, which is greater than the preset level 6. In this case, the processor will adjust the power management operation corresponding to the rear entertainment screen, that is, control the rear entertainment screen's power state to remain in the "powered on" state to meet the user's intermittent needs.

[0123] Assuming the first state of the LiDAR is power-on, but the power management model specifies a power-down operation for the LiDAR; at this time, the processor recognizes that the user has clicked on the intelligent driving submenu, but the user does not perform any further operations on the intelligent driving submenu's function pages within 30 seconds. In this case, the LiDAR's correction event level can be 3, which is less than the LiDAR's preset level 5. At this time, the processor will follow the power management operation given by the power management model to power down the LiDAR in order to reduce the overall power consumption level of the vehicle.

[0124] It is understood that, since correction events are random and uncertain, they can be classified into strong correction events and weak correction events according to their level. In different embodiments, the processor classifies correction events differently, and this application does not limit this classification.

[0125] It is understandable that each load may correspond to one or more correction events. When the power management model provides the corresponding power management operation, the processor can detect whether there is a correction event for the load, thereby meeting the user's irregular needs for the functions corresponding to certain loads and improving the user experience.

[0126] Understandably, the current industry standard for powering vehicle controllers generally uses through-hole fuses, while some OEMs employ external relays on PCB boards. However, under dynamic operating conditions, logic is often executed with all loads kept powered on. The method provided in this application, through a local power management scheme, can power off unrelated and unnecessary loads under dynamic operating conditions, reducing load losses during driving, thereby reducing battery consumption and improving the vehicle's overall driving range.

[0127] To facilitate understanding, the above power management method will be further explained below with examples.

[0128] As exemplified, Figure 7 shows a flowchart of the power management method provided in this application. Specifically,

[0129] Step a1: The driver enters the vehicle.

[0130] Step a2: Identify the driver's identity information and locate the data packet corresponding to the driver's identification code.

[0131] Step a3: Determine if there is a data packet in the database corresponding to the driver's identification code; if not, proceed to step a4; if yes, proceed to step a5.

[0132] Step a4: Create a new data package for the driver.

[0133] Step a5: Start the power management model.

[0134] Step a6: Collect the driver's driving data.

[0135] Step a7: Generate power management operation instructions.

[0136] As exemplified, Figure 8 shows a flowchart of the correction event judgment method provided in this application. Specifically,

[0137] Step b1: Send power management operation command.

[0138] Step b2: Determine if there is a correction event for the relevant load; if yes, proceed to step b3; if no, proceed to step b5.

[0139] Step b3: Determine whether the level of the correction event of the relevant load is greater than the preset level; if yes, proceed to step b4; if no, proceed to step b5.

[0140] Step b4: Update the power management operation instructions and end this judgment.

[0141] Step b5: Execute the power management operation command from step b1 above and end this judgment.

[0142] Understandably, due to the complex driving scenarios and numerous associated loads under dynamic operating conditions, it is difficult to capture users' driving habits and function usage tendencies during driving. The method provided in this application deploys a power management model on the vehicle's central computer to collect driving data from users in various usage scenarios such as daily commutes and long-distance travel. This data includes, but is not limited to, the frequency of adaptive cruise control activation, the intensity of in-vehicle monitoring function usage, and steering acceleration. These data are used as input parameters for the power management model. Once the model is mature, the central computer calculates the power management operation and sends it to the regional controller. Loads with low usage frequency and those unrelated to the current scenario are powered off, ensuring that the vehicle's energy consumption is always at an optimal level. This increases the driving range and alleviates range anxiety without increasing the capacity and cost of the power battery.

[0143] The above are embodiments of the power management method provided in this application under dynamic driving conditions. To manage the power of the vehicle under different operating conditions, as shown in Figure 9, the power management method provided in this application under static conditions is given below. The method includes steps S1-S3.

[0144] Step S1: After receiving external or internal function instructions and wake-up requests, the controller begins to execute the system function flow.

[0145] Step S2: The vehicle's central computer retrieves the load that needs to be powered on, mapped by the function corresponding to the controller, according to the function instruction mentioned above.

[0146] Specifically, the central computer queries Table 1 below to retrieve the loads that need to be powered on, as mapped by this function.

[0147] Function commands can be transmitted via CAN / Ethernet (ETH) channels.

[0148] Table 1, Table

[0149]

[0150] For example, as described in Table 1 above, the OTA (Over-The-Air) function maps the loads that need to be powered up to the LiDAR and the Advanced Driving Assistance System (ADAS) controller; the camera monitoring function maps the loads that need to be powered up to the panoramic camera; and the AC charging function maps the loads that need to be powered up to the battery and the motor.

[0151] In some embodiments, function identification codes can be assigned based on the group affiliation of the domains or the number of loads requiring power-on, according to the gradient of each function. One function identification code corresponds to one or more functions, that is, one function identification code corresponds to one or more loads requiring power-on.

[0152] For example, the OTA function, camera monitoring function and AC charging function all require 3 power-on loads, which means that the above three functions can be divided into one function identification code 111.

[0153] The controller is responsible for processing the enable flag of the corresponding function identification code, and after setting the enable flag to active, it sends it to the central computer.

[0154] For example, each function identification code corresponds to an enable flag. For instance, when the enable flag of function identification code 111 is 0, it indicates that the function corresponding to the function identification code should be in a dormant state; when the enable flag of function identification code 111 is 1, it indicates that the function corresponding to the function identification code should be in an active state.

[0155] Step S3: The central computer sends the load information that needs to be powered on to the area controller so that the load can be powered on.

[0156] Specifically, after the central computer identifies one or more loads that need to be powered on corresponding to the function identification code, it sends the information of the loads that need to be powered on to the area controller shown in Figure 10. The insulated gate bipolar transistor (IGBT) / metal-oxide-semiconductor field-effect transistor (MOSFET) of the corresponding interface on the area controller's MCU control board is turned on to enable the interface.

[0157] In order to ensure signal uniformity and avoid excessively increasing bus load, a one-dimensional array can be used to iterate through the enable status of all interfaces.

[0158] At this time, other loads unrelated to the function identification code are in a de-energized state. Compared with the related technologies that put other unrelated loads of the vehicle into a network sleep state, the method provided in this application embodiment reduces the static current consumption of unrelated loads, making the vehicle's performance indicators better. At the same time, since the power supply of the area controller itself is not enabled, the risk of non-associated area controllers being woken up due to network storms or area controller routing anomalies is avoided to a certain extent. While optimizing the vehicle's power consumption performance, the probability of the vehicle running out of power is also reduced.

[0159] In some embodiments, if the vehicle is in a combined state of multiple functional scenarios, that is, when one or more controllers send different function identification codes to the central computer, the central computer will perform algorithm fusion and merge, and finally calculate the fused loads that need to be powered on, and send the fused load information to the area controller so that the area controller can perform power-on operation on the relevant loads.

[0160] In some embodiments, when the vehicle is in a certain functional scenario, if other new functions need to be executed, the enable flag of the function identification code corresponding to the new function will be sent to the central computer in the manner shown in step S2 above. As shown in the table below, the central computer constructs a real-time running global variable process to continuously process the added or deleted power-on load information.

[0161] For example, when the central computer receives a function identification code corresponding to a new function with an enable flag of 1, it will retrieve the associated loads corresponding to Table 2 below based on the Table, and import them into the global variable process corresponding to Table 3 below for merging and combining, resulting in Table 4. At the same time, whenever the global variables change, the central computer broadcasts the latest load information that needs to be powered on to all area controllers, so that the area controllers can perform power-on or power-off operations on the loads.

[0162] Table 2. Associated Loads for New Features

[0163]

[0164] Table 3. Global Variable Process

[0165]

[0166] Table 4. Updated Global Variables Process

[0167]

[0168] Specifically, taking the Sentry Mode as an example of a functional scenario where the vehicle is running, the associated loads for Sentry Mode are the ADAS controller, camera, and battery management unit. At this time, the ADAS controller, camera, and battery management unit are all powered on. When the user turns on the remote air conditioning heating function through the mobile terminal, the corresponding load needs to be added to the global variable process.

[0169] The load corresponding to the remote air conditioning heating function is the motor air outlet and the compressor.

[0170] Therefore, while keeping the ADAS controller, camera, and battery management unit powered on, the global variable process also powers on the motor air outlet and compressor to obtain the fused output global variable process.

[0171] In some embodiments, taking the remote vehicle heating function as an example, after the controller receives an external cloud command, it sends the function identification code 222 of the remote vehicle heating function and its corresponding enable flag 1 to the central computer. Based on the function identification code 222, the central computer retrieves the associated loads from the Table: electric air vent, heater pump, and compressor, adds the corresponding loads to the global variable process, and sends the updated global variable process to the area controller, enabling the area controller to perform power-on or power-off operations on the loads.

[0172] The power interface that is currently powered on will be powered on again. Since the load itself has already been turned on, the load will not be affected after being powered on.

[0173] In some embodiments, when a single or multiple functional scenarios are completed or when the exit process is entered, the controller sets the enable flag corresponding to the function identification code to 0 and sends it to the central computer. Upon receiving the signal, the central computer performs a fusion comparison of the load associated with the function identification code.

[0174] The central computer can identify the operating status of the load by signal factors such as changes in signal flag bits and hardline level transitions.

[0175] Specifically, if the central computer determines that none of the associated loads corresponding to the function identification code are currently occupied by other functions, it will delete the load in the global variable process and send the updated result to the area controller, which will then perform the power-off operation on the corresponding load.

[0176] If the central computer determines that the load corresponding to the function identification code is in an occupied state, it will keep the occupied load powered on, delete the remaining unoccupied load in the global variable process, and send the updated result to the area controller, which will then perform the power-off operation on the corresponding load.

[0177] If the central computer determines that all loads corresponding to a function identification code are in an occupied state, it will keep all loads corresponding to that function identification code powered on and will not change the load information in the global variable process. When the area controller receives the global variable process, since the global variable process remains unchanged, the actual power-on state of each load does not change.

[0178] In some embodiments, when all functional scenarios of the vehicle have finished executing, the area controller sets the enable flag corresponding to the function identification code to 0 and sends it to the central computer. When the central computer calculates and finds that all control components are in an unoccupied state, it collectively releases the current global variable process and sends the result of the release to the area controller. After receiving the result, the area controller controls the peripheral circuit to shut down, and the vehicle will enter the lowest power consumption state.

[0179] Understandably, current energy consumption optimization solutions in the industry mainly adopt the automotive open system architecture (AUTOSAR). However, the local power management scheme used in this architecture has drawbacks such as limitations in controller chip selection, increased hardware costs, and increased software development workload. Furthermore, it heavily relies on network architecture and lacks scalability for vehicle upgrades. This application's embodiment uses a regional controller for local power management. Through semiconductor devices on the regional controller, power management of different loads is achieved to cope with constantly updated functions. This avoids the static losses and risks of unrelated loads being woken up during power management in related technologies. Especially in typical functional scenarios such as charging, it reduces vehicle power loss, shortens charging time, improves charging efficiency, and significantly optimizes the vehicle's static power consumption.

[0180] The foregoing primarily describes the solutions provided by the embodiments of this application from a methodological perspective. To achieve the aforementioned functions, the power management device or electronic device includes corresponding hardware structures and / or software modules for performing each function. Those skilled in the art should readily recognize that, based on the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0181] This application embodiment can, according to the above method, exemplarily divide a power management device or electronic device into functional modules. For example, the power management device or electronic device may include functional modules corresponding to each functional division, or two or more functions may be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. It should be noted that the module division in this application embodiment is illustrative and only represents one logical functional division; in actual implementation, there may be other division methods.

[0182] Figure 11 is a block diagram illustrating a power management device according to an exemplary embodiment, applied to a service device in a vehicle local area network (VLAN). The VLAN consists of multiple vehicle devices, including the service device; the service device communicates with any vehicle device via a topic subscription-publishing mode. The power management device 500 includes: an acquisition module 501, a determination module 502, a generation module 503, a detection module 504, an adjustment module 505, and a training module 506.

[0183] The acquisition module 501 is used to acquire the driving data of the target user. The driving data of the target user includes: the operating parameters of various loads in the vehicle, the passenger situation in the vehicle, and the operation parameters of the user on various loads in the vehicle during the driving process.

[0184] The determination module 502 is used to input the target user's driving data into the power management model, determine the identifier of the first load that needs to be managed by power, and the power management operation corresponding to the first load; wherein, the power management operation is to switch the power state of the first load from a first state to a second state.

[0185] The generation module 503 is used to generate a power management operation instruction based on the identifier of the first load and the power management operation corresponding to the first load, and send it to the controller so that the controller can perform a power management operation on the first load according to the power management operation instruction.

[0186] In one possible implementation, the detection module 504 is used to detect whether a correction event exists in the first load within a first preset time period; the correction event is an event that contradicts the first power management operation corresponding to the first load; the adjustment module 505 is used to adjust the power management operation corresponding to the first load when a correction event exists in the first load and the correction level of the correction event is greater than a preset level; wherein, the adjusted power management operation is to control the power state of the first load to remain in the first state.

[0187] In another possible implementation, the power state includes a power-on state and a power-off state; when the first state is a power-off state and the second state is a power-on state, the correction event includes an event indicating that the user has a demand for the first load.

[0188] In one possible implementation, the acquisition module 501 is further configured to acquire the user's driving data; the user's driving data includes: the operating parameters of various loads in the vehicle during the user's driving process, the vehicle's passenger status, and the user's operation parameters on various loads in the vehicle; the training module 506 is configured to train a power management model based on the user's driving data and the power management scheme, to obtain a trained power management model; the power management scheme includes: the identifiers of the loads that need power management, and the corresponding power management operations for the loads; wherein, the power management scheme is determined according to a preset correspondence, which is the correspondence between the user's driving data and the power status of various loads in the vehicle.

[0189] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0190] Figure 12 is a block diagram illustrating a vehicle according to an exemplary embodiment. As shown in Figure 12, the vehicle 600 includes, but is not limited to, a processor 601 and a memory 602.

[0191] The memory 602 described above is used to store the executable instructions of the processor 601. It is understood that the processor 601 is configured to execute instructions to implement the power management method in the above embodiments.

[0192] It should be noted that those skilled in the art will understand that the vehicle structure shown in Figure 12 does not constitute a limitation on the vehicle. A vehicle may include more or fewer components than those shown in Figure 12, or combine certain components, or have different component arrangements.

[0193] The processor 601 is the control center of the vehicle, connecting various parts of the vehicle through various interfaces and lines. It performs various vehicle functions and processes data by running or executing software programs and / or modules stored in the memory 602, and by calling data stored in the memory 602, thereby providing overall vehicle monitoring. The processor 601 may include one or more processing units. Optionally, the processor 601 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, while the modem processor mainly handles wireless communication. It is understood that the modem processor may also not be integrated into the processor 601.

[0194] The memory 602 can be used to store software programs and various data. The memory 602 may primarily include a program storage area and a data storage area. The program storage area may store the operating system, application programs required by at least one functional module (such as a determination unit, processing unit, etc.), etc. Furthermore, the memory 602 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0195] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as a memory 602 including instructions, which can be executed by a processor 601 of a vehicle 600 to implement the power management method in the above embodiments.

[0196] In actual implementation, the functions of the acquisition module 501, determination module 502, generation module 503, detection module 504, adjustment module 505, and training module 506 in Figure 11 can all be implemented by the processor 601 in Figure 12 calling the computer program stored in the memory 602. The specific execution process can be referred to the description of the power management method in the above embodiment, and will not be repeated here.

[0197] Optionally, the computer-readable storage medium may be a non-transitory computer-readable storage medium, such as a read-only memory (ROM), random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device.

[0198] In an exemplary embodiment, this application also provides a computer program product including one or more instructions, which can be executed by a vehicle processor 601 to perform the power management method in the above embodiments.

[0199] It should be noted that when one or more instructions in the computer-readable storage medium or computer program product are executed by the vehicle's processor, they implement the various processes of the above-described power management method embodiments and achieve the same technical effects as the above-described power management method. To avoid repetition, these will not be repeated here.

[0200] Through the above description of the embodiments, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0201] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another apparatus, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0202] The units described as separate components may or may not be physically separate. A component shown as a unit can be one or more physical units; that is, it can be located in one place or distributed in multiple different locations. Some or all of the classified units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0203] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0204] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiments of this application, essentially, or the part that contributes to the prior art, or a complete or partial classification of the technical solution, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0205] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A power management method, characterized in that, Processors used in vehicles; The processor includes a trained power management model; the method includes: acquiring driving data of a target user; the target user's driving data includes: operating parameters of various loads in the vehicle during the target user's driving, the vehicle's passenger status, and the user's operation parameters on the various loads in the vehicle; inputting the target user's driving data into the power management model to determine the identifier of a first load requiring power management, and the power management operation corresponding to the first load; wherein the power management operation is to switch the power state of the first load from a first state to a second state; generating a power management operation instruction based on the identifier of the first load and the power management operation corresponding to the first load, and sending it to the controller. The method further includes: enabling the controller to perform the power management operation on the first load according to the power management operation instruction; after inputting the target user's driving data into the power management model to determine the identifier of the first load requiring power management and the power management operation corresponding to the first load, the method further includes: detecting whether there is a correction event on the first load within a first preset time period; the correction event is an event that contradicts the power management operation corresponding to the first load; if the first load has the correction event and the correction level of the correction event is greater than a preset level, adjusting the power management operation corresponding to the first load; wherein the adjusted power management operation is to control the power state of the first load to remain in the first state.

2. The method according to claim 1, characterized in that, The power state includes a power-on state and a power-off state; when the first state is the power-on state and the second state is the power-off state, the correction event includes an event in which the user has a demand for the first load.

3. The method according to claim 1, characterized in that, Before acquiring the target user's driving data, the method further includes: acquiring the user's driving data; the user's driving data includes: the operating parameters of each load in the vehicle during the user's driving of the vehicle, the vehicle's passenger status, and the user's operation parameters on each load in the vehicle; training a power management model based on the user's driving data and a power management scheme to obtain a trained power management model; the power management scheme includes: the identifier of the load that needs power management, and the power management operation corresponding to the load; wherein, the power management scheme is determined according to a preset correspondence, the preset correspondence being the correspondence between the user's driving data and the power status of each load in the vehicle.

4. The method according to claim 3, characterized in that, The step of training a power management model based on the user's driving data and power management scheme to obtain a trained power management model includes: constructing training samples based on the user's driving data and power management scheme; training the power management model based on the training samples to obtain the trained power management model; the power management model is used to determine the power status of each load in the vehicle.

5. A power management device, characterized in that, Processors used in vehicles; The processor includes a trained power management model; The power management device includes: an acquisition module for acquiring driving data of a target user; the driving data of the target user includes: operating parameters of various loads in the vehicle, passenger status in the vehicle, and operating parameters of the user on various loads in the vehicle during the user's driving of the vehicle; a determination module for inputting the driving data of the target user into the power management model to determine the identifier of a first load requiring power management and the power management operation corresponding to the first load; wherein the power management operation is to switch the power state of the first load from a first state to a second state; a generation module for generating a power management operation instruction based on the identifier of the first load and the power management operation corresponding to the first load, and sending it to a controller so that the controller performs the power management operation on the first load according to the power management operation instruction; a detection module for detecting whether a correction event exists on the first load within a first preset time period; the correction event is an event that contradicts the power management operation corresponding to the first load; and an adjustment module for adjusting the power management operation corresponding to the first load when the first load has the correction event and the correction level of the correction event is greater than a preset level; wherein the adjusted power management operation is to control the power state of the first load to remain in the first state.

6. The apparatus according to claim 5, characterized in that, The power state includes a power-on state and a power-off state; when the first state is the power-on state and the second state is the power-off state, the correction event includes an event in which the user has a demand for the first load.

7. The apparatus according to claim 5, characterized in that, The power management device further includes: a training module; the acquisition module is further configured to acquire user driving data; the user driving data includes: the operating parameters of each load in the vehicle during the user's driving of the vehicle, the vehicle's passenger status, and the user's operation parameters on each load in the vehicle; the training module is configured to train a power management model based on the user's driving data and the power management scheme to obtain a trained power management model; the power management scheme includes: the identifier of the load that needs power management, and the power management operation corresponding to the load; wherein, the power management scheme is determined according to a preset correspondence, the preset correspondence being the correspondence between the user's driving data and the power status of each load in the vehicle.

8. The apparatus according to claim 7, characterized in that, The training module is specifically used to construct training samples based on the user's driving data and power management scheme; and to train the power management model based on the training samples to obtain the trained power management model. The power management model is used to determine the power status of each load within the vehicle.

9. 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 power management method as described in any one of claims 1 to 4.

10. A computer-readable storage medium, characterized in that, When the computer-executable instructions stored in the computer-readable storage medium are executed by the processor of the electronic device, the electronic device is able to perform the power management method as described in any one of claims 1 to 4.

Images