Seat self-learning method and vehicle

Abstract

The application provides a seat self-learning method and a vehicle, comprising: decomposing a seat self-learning task into multiple sub-tasks, and sequentially executing each sub-task, each sub-task corresponding to controlling a seat motor to move to a limit position direction to complete limit learning of the limit position direction; when detecting an interruption event during execution of each sub-task, controlling the seat motor to stop moving, and saving current learning progress information as a learning snapshot to a preset storage space; in response to a recovery event for the interruption event, reading the learning snapshot from the preset storage space, and continuing to execute an unfinished sub-task according to learning progress information recorded in the learning snapshot to complete the seat self-learning task. Thus, the problem of "progress loss after interruption and starting from the beginning" in the prior art is avoided, and the completion rate and efficiency of self-learning are improved.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and more particularly to a seat self-learning method and a vehicle. Background Technology

[0002] Seat self-learning is a crucial foundation for vehicle seat memory functions. After the seat is manufactured, it needs to acquire the limit position parameters in each direction of movement through a self-learning task, enabling precise adjustment and memorization of the seat position during user operation.

[0003] Currently, mainstream seat self-learning solutions typically employ a one-time completion strategy. Specifically, after triggering the learning conditions, the system sequentially controls the physical limit movements in two directions along each motion axis, and records the current Hall count value when the movement reaches the limit and stalls. After all motion directions have completed learning, the recorded Hall count values ​​are saved as baseline data.

[0004] However, if an interruption event occurs during the execution of the above self-learning task (such as the user operating the seat adjustment switch, the vehicle starting to move, etc.), the system will be forced to interrupt the learning, and the completed learning progress will be lost after the interruption. When self-learning is triggered again, the system can only start the complete self-learning task from the beginning. Summary of the Invention

[0005] This application provides a seat self-learning method and vehicle to solve the problem in the prior art that when a seat self-learning interruption event occurs, the system will be forced to interrupt learning, the completed learning progress will be lost after the interruption, and when self-learning is triggered again, the system can only start the complete self-learning task from scratch.

[0006] Firstly, this application provides a seat self-learning method, including: The seat self-learning task is decomposed into multiple sub-tasks, and each sub-task is executed in sequence. Each sub-task corresponds to controlling the seat motor to move in a limit direction to complete the limit learning in the limit direction. When an interruption event is detected during the execution of each of the sub-tasks, the seat motor is controlled to stop moving, and the current learning progress information is saved as a learning snapshot to a preset storage space; In response to a recovery event for the interruption event, the learning snapshot is read from the preset storage space, and the seat self-learning task is resumed based on the learning progress information recorded in the learning snapshot.

[0007] In one possible implementation, the sequential execution of each of the subtasks includes: Determine the positional dependencies between the mechanical structures corresponding to each of the aforementioned limiting directions; Based on the positional dependencies, determine the execution order of each subtask; Each of the subtasks is executed sequentially according to the execution order described.

[0008] In one possible implementation, before controlling the seat motor to stop moving, the method further includes: Determine the interrupt type corresponding to the interrupt event; When the interrupt type is a user-triggered interrupt type, the steps of controlling the seat motor to stop moving and saving the current learning progress information as a learning snapshot to the preset storage space are executed to interrupt the seat self-learning task and execute the user-triggered seat adjustment command. When the interrupt type is a safety event interrupt type, the seat self-learning task is terminated, and the learning snapshots saved in the preset storage space are deleted. When the interrupt type is neither a user-triggered interrupt type nor a safety event interrupt type, the steps of controlling the seat motor to stop moving and saving the current learning progress information as a learning snapshot to the preset storage space are executed.

[0009] In one possible implementation, the learning snapshots are stored in a first storage area and a second storage area within the preset storage space, respectively. The step of reading the learning snapshot from the preset storage space includes: When the learning snapshot is stored in the first storage area, the learning snapshot is read from the first storage area; If the learning snapshot is not stored in the first storage area, the learning snapshot is read from the second storage area; If the learning snapshot is not stored in either the first storage area or the second storage area, it is confirmed that reading the learning snapshot from the preset storage space has failed.

[0010] In one possible implementation, the method further includes: During the execution of each of the subtasks, the execution status of each subtask is monitored; When the execution status of any subtask indicates that the number of consecutive execution failures of the subtask has reached a preset threshold, it is determined that the seat has a mechanical fault. The seat self-learning task is terminated, and a fault message is output.

[0011] In one possible implementation, the method further includes: During the execution of each of the sub-tasks, the learning progress information of the seat self-learning task is displayed; When the interruption event is detected, the interruption event and the corresponding interruption reason are displayed; When the seat self-learning task is resumed, a resumption prompt message is displayed.

[0012] In one possible implementation, the method further includes: During the execution of each of the sub-tasks, learning status information broadcast by other seats associated with the seat is received; Based on the learning status information, determine whether there is a risk of motion interference between the other seats and this seat; When there is a risk of motion interference between the other seats and this seat, the execution of the current subtask is suspended until the risk of motion interference is eliminated.

[0013] In one possible implementation, the method further includes: Determine whether the current state corresponding to the seat self-learning task meets the preset recovery conditions. The recovery conditions include: there is a verified learning snapshot in the preset storage space; the seat self-learning task is in an incomplete state; the current vehicle state is in a preset running state; there are currently no user operation requests; there are currently no safety risk events; and the current temperature of the seat control system is within a preset temperature range. When the recovery conditions are met, the recovery event is triggered.

[0014] In one possible implementation, the method further includes: The timer starts from the time the interruption event occurs; If the current state corresponding to the seat self-learning task does not meet the recovery conditions when the preset time is reached, the judgment criterion of at least one parameter in the recovery conditions will be lowered. Alternatively, if the current state corresponding to the seat self-learning task does not meet the recovery conditions when the timer reaches the preset duration, a prompt message is output to remind the user to manually trigger the recovery.

[0015] Secondly, this application provides a seat self-learning device, comprising: The decomposition module is used to decompose the seat self-learning task into multiple sub-tasks and execute each sub-task in sequence. Each sub-task corresponds to controlling the seat motor to move in a limit direction to complete the limit learning in the limit direction. The saving module is used to control the seat motor to stop moving when an interruption event is detected during the execution of each of the sub-tasks, and to save the current learning progress information as a learning snapshot to a preset storage space; An execution module is configured to, in response to a recovery event for the interruption event, read the learning snapshot from the preset storage space and, based on the learning progress information recorded in the learning snapshot, resume the seat self-learning task.

[0016] In one possible implementation, the decomposition module is specifically used for: Determine the positional dependencies between the mechanical structures corresponding to each of the aforementioned limiting directions; Based on the positional dependencies, determine the execution order of each subtask; Each of the subtasks is executed sequentially according to the execution order described.

[0017] In one possible implementation, the apparatus further includes a determining module for: Determine the interrupt type corresponding to the interrupt event; When the interrupt type is a user-triggered interrupt type, the steps of controlling the seat motor to stop moving and saving the current learning progress information as a learning snapshot to the preset storage space are executed to interrupt the seat self-learning task and execute the user-triggered seat adjustment command. When the interrupt type is a safety event interrupt type, the seat self-learning task is terminated, and the learning snapshots saved in the preset storage space are deleted. When the interrupt type is neither a user-triggered interrupt type nor a safety event interrupt type, the steps of controlling the seat motor to stop moving and saving the current learning progress information as a learning snapshot to the preset storage space are executed.

[0018] In one possible implementation, the learning snapshots are stored in a first storage area and a second storage area within the preset storage space, respectively. The execution module is specifically used for: When the learning snapshot is stored in the first storage area, the learning snapshot is read from the first storage area; If the learning snapshot is not stored in the first storage area, the learning snapshot is read from the second storage area; If the learning snapshot is not stored in either the first storage area or the second storage area, it is confirmed that reading the learning snapshot from the preset storage space has failed.

[0019] In one possible implementation, the device further includes a monitoring module for: During the execution of each of the subtasks, the execution status of each subtask is monitored; When the execution status of any subtask indicates that the number of consecutive execution failures of the subtask has reached a preset threshold, it is determined that the seat has a mechanical fault. The seat self-learning task is terminated, and a fault message is output.

[0020] In one possible implementation, the device further includes a display module for: During the execution of each of the sub-tasks, the learning progress information of the seat self-learning task is displayed; When the interruption event is detected, the interruption event and the corresponding interruption reason are displayed; When the seat self-learning task is resumed, a resumption prompt message is displayed.

[0021] In one possible implementation, the device further includes a receiving module for: During the execution of each of the sub-tasks, learning status information broadcast by other seats associated with the seat is received; Based on the learning status information, determine whether there is a risk of motion interference between the other seats and this seat; When there is a risk of motion interference between the other seats and this seat, the execution of the current subtask is suspended until the risk of motion interference is eliminated.

[0022] In one possible implementation, the device further includes a determination module for: Determine whether the current state corresponding to the seat self-learning task meets the preset recovery conditions. The recovery conditions include: there is a verified learning snapshot in the preset storage space; the seat self-learning task is in an incomplete state; the current vehicle state is in a preset running state; there are currently no user operation requests; there are currently no safety risk events; and the current temperature of the seat control system is within a preset temperature range. When the recovery conditions are met, the recovery event is triggered.

[0023] In one possible implementation, the device further includes a timing module for: The timer starts from the time the interruption event occurs; If the current state corresponding to the seat self-learning task does not meet the recovery conditions when the preset time is reached, the judgment criterion of at least one parameter in the recovery conditions will be lowered. Alternatively, if the current state corresponding to the seat self-learning task does not meet the recovery conditions when the timer reaches the preset duration, a prompt message is output to remind the user to manually trigger the recovery.

[0024] Thirdly, this application provides a vehicle, including: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; When the processor executes a program stored in memory, it implements the seat self-learning method described in any of the first aspects above.

[0025] Fourthly, this application provides a storage medium storing one or more programs that can be executed by one or more processors to implement the seat self-learning method described in any one aspect.

[0026] Fifthly, this application provides a computer program product containing instructions that, when run on a computer, causes the computer to execute any of the seat self-learning methods described above.

[0027] Compared with the prior art, the technical solution provided in this application has the following advantages: First, the method provided in this application decomposes the complete seat self-learning task into multiple sub-tasks and executes them sequentially, so that the learning progress can be divided into multiple independently recordable nodes, laying the foundation for breakpoint resumption. Based on this, when an interruption event is detected during the execution of each sub-task, the method does not exit directly, but first controls the seat motor to stop moving, and then saves the current learning progress information as a learning snapshot to a preset storage space to record the learning position at the time of the interruption. Finally, in response to a recovery event for the interruption event, the previously saved learning snapshot is read from the preset storage space, and the seat self-learning task is directly resumed from the interruption point based on the learning progress information recorded therein. Through the above method, when the seat self-learning task is interrupted, the learning progress can be completely preserved, and accurate resumption can be achieved during recovery based on the saved learning progress information, thereby effectively avoiding the problem of "progress loss after interruption, requiring starting from the beginning" in the prior art, and significantly improving the completion rate and efficiency of self-learning. Attached Figure Description

[0028] 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.

[0029] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0030] One or more embodiments are illustrated by way of example with reference numerals in the accompanying drawings. These illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements. Unless otherwise stated, the figures in the drawings are not to be limited by scale.

[0031] Figure 1 A flowchart illustrating an embodiment of a seat self-learning method provided in this application; Figure 2 A flowchart illustrating another embodiment of the seat self-learning method provided in this application; Figure 3 A flowchart illustrating another embodiment of the seat self-learning method provided in this application; Figure 4 A flowchart illustrating another embodiment of the seat self-learning method provided in this application; Figure 5 A block diagram illustrating an embodiment of a seat self-learning device provided in this application; Figure 6 This is a structural schematic diagram of a vehicle provided in an embodiment of this application. Detailed Implementation

[0032] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0033] The following disclosure provides numerous different embodiments or examples for implementing various structures of this application. To simplify the disclosure, specific examples of components and arrangements are described below. These are merely examples and are not intended to limit the scope of this application. Furthermore, reference numerals and / or letters may be repeated in different examples. Such repetition is for simplification and clarity and does not in itself indicate a relationship between the various embodiments and / or arrangements discussed.

[0034] Seat self-learning is a crucial foundation for vehicle seat memory functions. After seat manufacturing, a self-learning task is required to acquire the limit position parameters of the seat in each direction of movement, enabling precise adjustment and memorization of the seat position during user operation. Currently, mainstream seat self-learning solutions typically employ a one-time completion strategy. Specifically, after triggering the learning conditions, the system sequentially controls the physical limit movements in two directions along each movement axis. When a stall occurs at the limit, the current Hall count value is recorded. Once all movement directions have been learned, the recorded Hall count values ​​are saved as baseline data.

[0035] However, if an interruption event occurs during the execution of the above self-learning task (such as the user operating the seat adjustment switch, the vehicle starting to move, etc.), the system will be forced to interrupt the learning, and the completed learning progress will be lost after the interruption. When self-learning is triggered again, the system can only start the complete self-learning task from the beginning.

[0036] To address the aforementioned shortcomings, this application proposes a core inventive concept that decomposes the self-learning task into subtasks, saves snapshots during interruptions, and resumes from the breakpoint upon recovery: The complete seat self-learning task is decomposed into multiple subtasks and executed sequentially; when an interruption event is detected, motor movement is stopped and the current learning progress information is saved as a learning snapshot; when the recovery conditions are met, the saved learning snapshot is read, and the unfinished subtasks are continued from the interruption point until the entire self-learning task is completed. In this way, when the seat self-learning task is interrupted, the learning progress can be fully preserved, and accurate resumption can be achieved upon recovery, effectively avoiding the problem of "progress loss after interruption, requiring starting from the beginning" in existing technologies.

[0037] Based on the above inventive concept, such as Figure 1 The diagram shown is a schematic representation of the implementation process of a seat self-learning method provided in this application embodiment. This method is applied to vehicles and specifically includes the following steps: S101. The seat self-learning task is decomposed into multiple sub-tasks, and each sub-task is executed in sequence. Each sub-task corresponds to controlling the seat motor to move in a limit direction to complete the limit learning in the limit direction.

[0038] Seat self-learning task: After the seat is manufactured, the controller controls the physical limit movement of the seat motor in each direction of movement, and obtains the limit position parameters of the seat in each direction of movement by detecting the Hall pulse count value at the moment of stall.

[0039] Subtask: refers to the smallest indivisible execution unit in the self-learning task. Each subtask corresponds to controlling the seat motor to move in a limit direction and completing the limit learning in that direction.

[0040] Limit direction: refers to one direction of movement of the seat motor on a single motion axis. Each motion axis includes two limit directions, positive and negative.

[0041] Limit learning: refers to the process by which the controller controls the seat motor to move in a limit direction. When the motor moves to the physical limit and stalls, the Hall pulse count value at that moment is recorded and used as the limit position parameter in that direction.

[0042] In this embodiment, the seat self-learning task typically includes multiple motion axes such as slide rail movement, height adjustment movement, and backrest movement, with each motion axis including two limit directions (positive and negative). The controller pre-decomposes the complete self-learning task into multiple independent sub-tasks according to each motion axis and its limit direction, such as slide rail front limit learning, slide rail rear limit learning, height adjustment upper limit learning, height adjustment lower limit learning, backrest front limit learning, and backrest rear limit learning. After decomposition, the controller determines the execution order according to the logical dependencies between the sub-tasks, for example, executing each sub-task sequentially in the order of slide rail first, then height adjustment, and finally backrest. When executing each sub-task, the controller controls the seat motor to move in the corresponding limit direction. When the motor stalls at the physical limit, the Hall pulse count value at that moment is recorded, thus completing the limit learning in that direction. This step, by decomposing the complete seat self-learning task into multiple independently executable sub-tasks and executing them sequentially, lays a granular foundation for subsequent interrupt saving and breakpoint resumption.

[0043] S102. When an interruption event is detected during the execution of each of the sub-tasks, the seat motor is controlled to stop moving, and the current learning progress information is saved as a learning snapshot to a preset storage space.

[0044] Interruption events: refer to external events that force the seat self-learning task to be interrupted, including but not limited to: user operation of seat adjustment switch (user active interruption), vehicle speed changing from zero to greater than zero or gear changing from parking to non-parking (vehicle driving interruption), any door changing from closed to open (door status interruption), vehicle power changing from accessory power-on mode to power-off mode (power mode interruption), collision sensor triggering or airbag status abnormality (safety event interruption), abnormal resistance detected during the learning process (obstacle interruption).

[0045] Learning progress information: This indicates the completed subtasks of the current seat self-learning task and the execution progress within the current subtask. Completed subtasks are represented by a 16-bit bitmap of completed steps, with each bit corresponding to one subtask. Completed bits are marked as 1, and incomplete bits are marked as 0. The current execution step number records the subtask being executed when the interrupt occurred. The execution progress records the detailed execution position within the subtask, such as the proportion of Hall pulse counts indicating motor movement relative to the total travel in that direction.

[0046] Learning snapshot: refers to a data set formed based on the current learning progress information and stored in a preset storage space.

[0047] Preset storage space: refers to the non-volatile memory area used to save learning snapshots. It can be electrically erasable programmable read-only memory (EEPROM) or flash memory area that is analog to electrically erasable programmable read-only memory.

[0048] In this embodiment, when the controller detects an interruption event during the execution of subtask S101, the system must immediately interrupt the learning process for safety and user experience reasons. At this time, the controller first cuts off the enable signal of the seat motor driver and applies reverse braking (i.e., active short circuit) to the moving motor to stop it as quickly as possible. Subsequently, the controller collects the current learning progress information and assembles it into a learning snapshot according to a preset data structure. This data structure includes at least: a snapshot identifier to identify whether a valid snapshot exists in the storage area; a completed step bitmap to mark whether each subtask has been completed; a current execution step number to record the subtask being executed at the time of the interruption; an execution progress value to record the detailed execution position within the current subtask, such as the proportion of the Hall pulse count value of the moved motor to the total travel in that direction; and a data integrity check code to detect whether the snapshot data is corrupted. After assembly, the controller writes the learning snapshot to a preset storage space for storage. Through this step, even if the learning process is interrupted, the complete learning progress at the time of the interruption is persistently saved and will not be lost due to the interruption.

[0049] S103. In response to the recovery event for the interruption event, read the learning snapshot from the preset storage space and restore the seat self-learning task according to the learning progress information recorded in the learning snapshot.

[0050] Recovery Event: This refers to the event that triggers the resumption of the self-learning task. There are two triggering methods: automatic and manual. Automatic triggering means the system automatically triggers the resumption when preset recovery conditions are met; manual triggering means it is triggered directly based on user commands, without waiting for the preset recovery conditions to be met. The preset recovery conditions are a set of criteria pre-defined by the system to determine whether automatic resumption is allowed, such as requirements regarding the validity of the learning snapshot, the completion status of self-learning, vehicle operating status, user operation status, safety status, and system temperature status.

[0051] In this embodiment, under automatic triggering, the controller checks whether the current state meets preset recovery conditions at preset check times (e.g., after the vehicle is powered on, after the vehicle gear is switched to parking and the speed drops to zero, after the user operation ends and a period of inactivity has passed, after the door is closed, etc.). When all conditions are met, a recovery event is automatically triggered. Under manual triggering, the user actively issues a recovery command through the interactive interface, and the system responds to the command by directly triggering a recovery event. In response to the recovery event (whether automatically or manually triggered), the controller reads the previously saved learning snapshot from the preset storage space. First, it performs a data integrity check on the learning snapshot. After the check passes, it parses the learning progress information, which is used to determine the interruption point, i.e., which subtasks have been completed, which subtasks have not been completed, and their internal execution progress. The controller determines the interruption point based on the learning progress information and resumes execution of unfinished subtasks from that point. Specifically, it jumps to the unfinished subtask and resumes execution from the corresponding position within that subtask, controlling the seat motor to move towards the corresponding limit direction to complete the subtask. This process continues with subsequent unfinished subtasks until the entire seat self-learning task is completed. After all subtasks are completed, the controller clears the learning snapshot from the preset storage space, updates the system status to "learning complete," and enables the full functionality of the seat (including seat memory and comfort functions). Furthermore, the controller can notify the user of the completion of self-learning via the in-vehicle screen and voice announcement. This step avoids repetitive work by precisely resuming the learning process from the interruption point, thus improving self-learning efficiency, as the system does not need to start the entire self-learning task from scratch.

[0052] The technical solution provided in this application firstly decomposes the complete seat self-learning task into multiple sub-tasks and executes them sequentially. This allows the learning progress to be broken down into multiple independently recordable nodes, laying the foundation for resuming interrupted learning. Based on this, when an interruption event is detected during the execution of each sub-task, the method does not exit directly. Instead, it first controls the seat motor to stop moving, and then saves the current learning progress information as a learning snapshot to a preset storage space to record the learning position at the moment of interruption. Finally, in response to a recovery event for the interruption event, the previously saved learning snapshot is read from the preset storage space, and the seat self-learning task is directly resumed from the interruption point based on the learning progress information recorded therein. Through this method, the learning progress can be fully preserved when the seat self-learning task is interrupted, and accurate resumption can be achieved upon recovery based on the saved learning progress information. This effectively avoids the problem of "progress loss after interruption, requiring starting from scratch" in existing technologies, significantly improving the completion rate and efficiency of self-learning.

[0053] Figure 2 A flowchart illustrating another embodiment of the seat self-learning method provided in this application. Figure 2 The process shown is in Figure 1 Based on the illustrated process, the following steps are included: S201. Determine the positional dependency between the mechanical structures corresponding to each of the limiting directions; S202. Determine the execution order of each subtask based on the positional dependency relationship; S203. Execute each of the subtasks in the order described above.

[0054] For ease of understanding, the following provides a unified explanation of S201-S203: Positional dependence refers to the spatial relationships and constraints between the mechanical structures corresponding to the various motion axes of a seat. For example, the slide rail controls the fore-and-aft position of the seat, which directly affects the range of motion and motion reference of the height adjustment mechanism and the backrest mechanism; the height adjustment controls the seat's height adjustment, which affects the backrest's tilt reference point. Therefore, the slide rail position is the basis for height adjustment and backrest movement, and the height adjustment position is the basis for backrest movement.

[0055] In this embodiment, after the seat self-learning task is decomposed into multiple sub-tasks in S101, the controller needs to determine the execution order of each sub-task. Specifically, the controller first identifies the positional dependencies between the mechanical structures (such as the slide rail mechanism, the height adjustment mechanism, and the backrest mechanism) corresponding to each limiting direction, that is, analyzes which mechanical structure position changes will affect the range of motion or motion reference of other mechanical structures. Based on this positional dependency, the controller determines the execution order of the sub-tasks: sub-tasks corresponding to the dependent mechanical structures are executed first, and sub-tasks that depend on other mechanical structures are executed last. Specifically, sub-tasks corresponding to mechanical structures that are depended on by other mechanical structures are executed first (such as the sub-task corresponding to the slide rail mechanism), mechanical structures that do not depend on other mechanical structures but are depended on by other mechanical structures are executed second (such as the sub-task corresponding to the height adjustment mechanism), and mechanical structures that depend on other mechanical structures are executed last (such as the sub-task corresponding to the backrest mechanism). In this way, when performing high-adjustment limit learning, the slide rail mechanism is already in a definite reference position; when performing backrest limit learning, both the slide rail mechanism and the high-adjustment mechanism are already in definite reference positions, thus avoiding limit learning errors caused by the uncertain positions of other mechanical structures.

[0056] Through the above steps, this application can reasonably determine the execution order of each sub-task based on the positional dependency relationship between the mechanical structures corresponding to each limiting direction. This ensures that the execution order of each sub-task in the seat self-learning task conforms to the internal logic of the mechanical structure, thereby improving the accuracy and reliability of limiting learning.

[0057] In one embodiment, before "controlling the seat motor to stop moving" in S102, the following steps may be included: determining the interrupt type corresponding to the interrupt event; when the interrupt type is a user-triggered interrupt type, executing the step of controlling the seat motor to stop moving and saving the current learning progress information as a learning snapshot to a preset storage space to interrupt the seat self-learning task and execute the user-triggered seat adjustment command; when the interrupt type is a safety event interrupt type, terminating the seat self-learning task and deleting the learning snapshot already saved in the preset storage space; when the interrupt type is neither a user-triggered interrupt type nor a safety event interrupt type, executing the step of controlling the seat motor to stop moving and saving the current learning progress information as a learning snapshot to a preset storage space.

[0058] Interruption type: refers to the category of the event that causes the seat self-learning task to be interrupted, including: interruption type triggered by user operation (interruption triggered by user operation of seat adjustment switch), interruption type of safety event (interruption triggered by collision sensor or airbag status abnormality, etc.), and other interruption types (i.e., types that are not interrupted by user operation and are not interrupted by safety event, including vehicle driving interruption, door status interruption, power mode interruption, obstacle interruption, etc.).

[0059] In this embodiment, before executing "controlling the seat motor to stop moving" in S102, the controller first identifies the interrupt type based on the source characteristics of the interrupt event. For example, if the seat adjustment switch is detected to be operated, it is identified as an interrupt type triggered by user operation; if a collision sensor is detected to be triggered or the airbag status is abnormal, it is identified as a safety event interrupt type; if the vehicle speed is greater than zero, the gear is disengaged from parking gear, the door is opened, the power mode changes, or abnormal resistance occurs during the learning process, it is identified as another interrupt type.

[0060] If the interrupt type is a user-triggered interrupt, the controller stops the seat motor, saves the current learning progress information as a learning snapshot to the preset storage space, interrupts the execution of the seat self-learning task, and immediately responds to the user-triggered seat adjustment command to ensure that the user operation receives priority response. If the interrupt type is a safety event interrupt, the controller immediately terminates the seat self-learning task and deletes the learning snapshot already saved in the preset storage space to prevent continued learning or accidental recovery under safety risks. The user will need to manually re-trigger the learning process afterward. If the interrupt type is another type (i.e., vehicle driving interruption, door status interruption, power mode interruption, or obstacle interruption), the controller executes the steps described in S102 to stop the seat motor and save the current learning progress information as a learning snapshot to the preset storage space, thereby preserving the learning progress during the interruption and enabling continuation from the interruption point when the recovery conditions are met.

[0061] Through the above steps, this application can perform differentiated processing for different types of interruptions, ensuring the priority of user operation response and vehicle safety while maximizing the retention of learning progress, avoiding unnecessary progress loss, and improving the robustness of the seat self-learning task and user experience.

[0062] In another embodiment, the learning snapshots are stored in a first storage area and a second storage area in the preset storage space, respectively. In this case, "reading the learning snapshot from the preset storage space" in S103 may specifically include the following steps: when the learning snapshot is stored in the first storage area, read the learning snapshot from the first storage area; when the learning snapshot is not stored in the first storage area, read the learning snapshot from the second storage area; when the learning snapshot is not stored in either the first storage area or the second storage area, confirm that reading the learning snapshot from the preset storage space has failed.

[0063] First storage area and second storage area: These refer to two independent storage regions within a predefined storage space, used to store copies of the learning snapshots respectively. The two storage areas are physically or logically isolated from each other, so that if data in one storage area is corrupted, the copy in the other storage area may still remain intact.

[0064] In this embodiment, the controller saves the learning snapshot to the first storage area and the second storage area in the preset storage space in S102, that is, it saves two redundant copies of the same learning snapshot. Based on this, when "reading the learning snapshot from the preset storage space" in S103, the controller first determines whether a learning snapshot is stored in the first storage area; if so, it reads the learning snapshot from the first storage area; if not, it determines whether a learning snapshot is stored in the second storage area. If a learning snapshot is stored in the second storage area, it reads the learning snapshot from the second storage area; if neither the first nor the second storage area stores a learning snapshot, it is confirmed that reading the learning snapshot from the preset storage space has failed.

[0065] In a preferred embodiment of this application, after reading the learning snapshot, data integrity verification can be performed on the read learning snapshot. Specifically, the controller verifies the learning snapshot read from the first storage area; if the verification passes, it indicates that the learning snapshot data is complete and valid, and the learning snapshot is used (i.e., the learning progress information in it is parsed to determine the interruption point and resume execution); if the verification fails, it indicates that the learning snapshot may be corrupted, and the controller continues to determine whether a learning snapshot is stored in the second storage area. If so, it reads from the second storage area and verifies it. If the learning snapshots in both storage areas fail to be verified, it is also confirmed that there is no usable learning snapshot in the preset storage space. At this time, it is impossible to resume from the interruption point, and the system needs to prompt the user to re-trigger the complete seat self-learning task.

[0066] Through the aforementioned dual-zone redundant storage mechanism, this application effectively improves the reliability of learning snapshot storage. Even if the data in one storage zone is damaged due to storage medium aging, power abnormality, or other reasons, a valid learning snapshot can still be recovered from the other storage zone, thereby avoiding the loss of learning progress due to single-point storage failure and further enhancing the robustness of the self-learning process.

[0067] Figure 3 A flowchart illustrating another embodiment of the seat self-learning method provided in this application. Figure 3 The process shown is in Figure 1 Based on the illustrated process, the following steps are included: S301. During the execution of each of the sub-tasks, monitor the execution status of each of the sub-tasks; S302. When the execution status of any subtask indicates that the number of consecutive execution failures of the subtask has reached a preset threshold, it is determined that the seat has a mechanical fault. S303. Terminate the seat self-learning task and output a fault prompt message.

[0068] For ease of understanding, S301-S303 are explained uniformly below: Execution status: This refers to the result information of the subtask during execution, including execution success, execution failure, reason for failure, number of failures, etc. Execution failure may manifest as abnormal motor stall, abnormal Hall sensor signal, abnormal motor drive current, or motion timeout.

[0069] Preset threshold: This refers to the upper limit of the number of consecutive failures preset by the system, such as 3 or 5 times. When the number of consecutive failures of the same subtask reaches this threshold, the system determines that there is a mechanical fault.

[0070] Mechanical failure: refers to abnormalities in the mechanical structure of the seat or the motor drive system, such as stuck slide rails, deformation of the high adjustment mechanism, damage to the backrest transmission mechanism, motor overload, etc.

[0071] In this embodiment, during the execution of the sub-tasks decomposed in S101, the controller continuously monitors the execution status of each sub-task and records the execution result of each sub-task. When a sub-task fails, the controller records the failure and continues to attempt to re-execute the sub-task. If the number of consecutive failures of the sub-task reaches a preset threshold (e.g., three consecutive failures), the controller determines that the seat has a mechanical fault. At this time, the controller immediately terminates the entire seat self-learning task and stops executing subsequent sub-tasks. Simultaneously, it outputs fault information through one or more of the following methods: displaying fault information on the in-vehicle screen, issuing an alarm via voice broadcast, displaying a fault indication color through ambient lighting, or illuminating a fault indicator light on the instrument panel, to inform the user that the seat has a mechanical abnormality and needs to be repaired.

[0072] Through the above steps, this application can promptly identify mechanical faults in the seat, avoid infinite self-learning loops or erroneous limit learning results caused by faults, and provide users with clear fault prompts to facilitate quick problem location and repair, thereby improving the intelligence and reliability of the self-learning task.

[0073] In one embodiment, the method may further include the following steps: during the execution of each of the sub-tasks, displaying the learning progress information of the seat self-learning task; when the interruption event is detected, displaying the interruption event and the corresponding interruption reason; and when the seat self-learning task is resumed, displaying a resumption prompt message.

[0074] Display: The process of outputting information to the user can be achieved through one or more methods such as in-vehicle screens, dashboards, ambient lighting, and voice broadcasts, so that the user can intuitively understand the current status of the self-learning task.

[0075] Interruption Reason: This refers to the specific event type that caused the self-learning interruption and its triggering reason. For example, if the interruption event is "user-initiated interruption", the corresponding interruption reason is "user operation of seat adjustment switch"; if the interruption event is "vehicle driving interruption", the corresponding interruption reason is "vehicle speed is greater than zero" or "gear disengaged from parking gear".

[0076] Resumption prompt message: This refers to the notification message sent to the user when self-learning resumes execution from the interruption point. It is used to inform the user that self-learning is about to continue or is in the process of resuming, such as "Resuming learning from the interruption point" or "Self-learning will continue soon".

[0077] In this embodiment, during the execution of each sub-task, the controller displays the learning progress information of the seat self-learning task to the user through interactive interfaces such as the in-vehicle screen, dashboard, or central control display, in the form of text, progress bars, or percentages. This includes the name of the currently executing sub-task (e.g., "Learning the front limit of the slide rail") and the overall completion progress (e.g., "Completed 3 / 6"). When an interruption event is detected, the controller displays the interruption event and the corresponding interruption reason through the in-vehicle screen or dashboard, such as "Self-learning interrupted: User operated the seat adjustment switch" or "Self-learning interrupted: Vehicle started driving," so that the user understands the specific reason for the interruption. When the seat self-learning task is resumed, the controller displays prompts such as "Resuming learning" on the in-vehicle screen and issues a voice notification "Self-learning will continue soon" to inform the user that self-learning has resumed.

[0078] Through the aforementioned multimodal user interaction methods, this application enables users to understand the execution status, interruption reasons, and recovery progress of the self-learning task in real time, eliminating blind spots in user cognition and preventing users from misjudging seat function malfunctions due to a lack of understanding of the learning status, thereby improving user experience and reducing after-sales inquiries caused by misjudgments.

[0079] Figure 4 A flowchart illustrating another embodiment of the seat self-learning method provided in this application. Figure 4 The process shown is in Figure 1 Based on the illustrated process, the following steps are included: S401. During the execution of each of the sub-tasks, receive learning status information broadcast by other seats associated with the seat; S402. Determine whether there is a risk of motion interference between the other seats and this seat based on the learning status information; S403. When there is a risk of motion interference between the other seats and this seat, suspend the execution of the current subtask until the risk of motion interference is eliminated.

[0080] For ease of understanding, S401-S403 are explained uniformly below: Learning status information: This refers to the status data broadcast to the network by the seat during the execution of a self-learning task. It includes at least the sub-task the seat is currently performing, the direction of motion involved, the seat's current position, and the range of motion. Other seats receiving this information can use it to determine if there is a risk of motion interference.

[0081] Motion interference risk: This refers to the possibility that when multiple seats perform self-learning simultaneously, the overlapping or mutual influence of their range of motion may lead to collisions or mutual obstruction between two or more seats. For example, when the front seats move backward, they may collide with the rear seats moving forward, or adjacent seats moving towards the middle simultaneously may squeeze each other.

[0082] In this embodiment, for a vehicle with multiple seats (such as a front driver's seat, a front passenger seat, and rear seats), each seat's controller broadcasts its learning status information via the vehicle network (such as a controller area network bus) during the execution of its respective sub-task. This information includes the currently executing sub-task, the direction of movement, the seat's current position, and the range of movement. Simultaneously, each seat's controller receives learning status information broadcast by other seats in the vehicle network. Based on the received learning status information from other seats, and considering the direction and range of movement corresponding to the sub-task currently to be executed by the current seat, the controller determines whether there is a risk of motion interference between the current seat and other seats. For example, if the current seat (front seat) needs to move backward to complete the rear seat limit learning, while the received information indicates that the rear seat is moving forward to perform the front seat limit learning, there is a risk of collision. If a risk of motion interference is determined, the current seat's controller suspends the execution of the currently scheduled sub-task until the risk is eliminated. This can be achieved by waiting for a preset duration (such as 2 seconds) before reassessing whether the risk has been eliminated, or by waiting for other seats to complete their sub-tasks before resuming execution.

[0083] Through the aforementioned multi-seat coordination mechanism, this application can effectively avoid the collision risk caused by motion interference when multiple seats perform self-learning at the same time, improve the safety and reliability of the self-learning process of multi-seat vehicles, and avoid deadlock caused by mutual waiting, thus ensuring the smooth completion of the self-learning tasks of each seat.

[0084] In one embodiment, the method may further include the following steps: determining whether the current state corresponding to the seat self-learning task meets preset recovery conditions, the recovery conditions including: there is a verified learning snapshot in the preset storage space; the seat self-learning task is in an incomplete state; the current vehicle state is in a preset running state; there is no user operation request; there is no safety risk event; the temperature of the current seat control system is within a preset temperature range; when the recovery conditions are met, the recovery event is triggered.

[0085] Preset recovery conditions: These refer to a set of pre-defined criteria used by the system to determine whether automatic recovery of the self-learning task is allowed. Multiple conditions must be met simultaneously to trigger automatic recovery. In this application, the preset recovery conditions include: the existence of a verified learning snapshot in the preset storage space; the seat self-learning task being incomplete; the current vehicle status being in a preset operating state; no user operation requests; no security risk events; and the current temperature of the seat control system being within a preset temperature range.

[0086] Preset operating status: refers to the operating status in which the vehicle is allowed to perform self-learning, including at least zero vehicle speed, the gear being in parking or neutral, and the battery voltage being normal.

[0087] User operation request: refers to the seat adjustment command issued by the user through the seat adjustment switch. When a user operation request exists, the system should respond to the user operation first, rather than performing self-learning recovery.

[0088] Safety risk events: refer to abnormal situations that may endanger the safety of the vehicle or its occupants, such as the triggering of collision sensors or airbag system malfunctions.

[0089] Preset temperature range: This refers to the temperature range within which the seat controller can operate normally, such as -40℃ to 85℃. When the controller temperature exceeds this range, it may affect the stability and accuracy of the self-learning process.

[0090] In this embodiment, the controller determines whether the current state corresponding to the seat self-learning task meets the preset recovery conditions. Specifically, the controller verifies the following six conditions one by one: First, whether there is a valid learning snapshot (i.e., a valid snapshot saved during a previous interruption) in the preset storage space; Second, whether the seat self-learning task is not yet completed, i.e., the bitmap of completed steps recorded in the snapshot is not full and there are still unexecuted subtasks; Third, whether the current vehicle state is in a preset operating state, including zero vehicle speed, the gear being in parking or neutral, and normal battery voltage; Fourth, whether there is currently no user operation request, i.e., the seat adjustment switch is in a static state (e.g., static for more than two seconds); Fifth, whether there are currently no safety risk events, i.e., no collision warning, no airbag malfunction, or other safety anomalies; Sixth, whether the current temperature of the seat control system is within the preset normal operating range. When all six conditions are met, the controller determines that the recovery conditions are met and automatically triggers the recovery event, thereby executing the snapshot reading and breakpoint resume steps in S103.

[0091] Through the above-mentioned automatic recovery condition judgment mechanism, this application can ensure that the self-learning task can be automatically recovered only under the premise that the vehicle is in a safe state, the system is in a normal state, and there is effective learning progress. This avoids the safety risks or learning errors caused by incorrect recovery under unsuitable conditions (such as when the vehicle is in motion, when the user is operating, or when the system temperature is abnormal), and improves the safety and intelligence of the self-learning task.

[0092] In another embodiment, the method may further include the following steps: starting a timer from the time the interruption event occurs; if the current state corresponding to the seat self-learning task does not meet the recovery conditions when the timer reaches a preset duration, then lowering the judgment criterion of at least one parameter in the recovery conditions; or, if the current state corresponding to the seat self-learning task does not meet the recovery conditions when the timer reaches a preset duration, outputting a prompt message to prompt the user to manually trigger the recovery.

[0093] Timing start point: This refers to the moment when the interruption event occurs and the learning snapshot is saved. This timing is used to monitor the duration for which recovery conditions are not met.

[0094] Preset duration: This refers to the pre-set waiting time threshold of the system, such as 24 hours. If the recovery conditions are not met within this duration, the system determines that "the recovery conditions cannot be met for an extended period" and triggers the corresponding response strategy.

[0095] Lowering the judgment criteria: This refers to relaxing the original requirements of at least one parameter in the recovery conditions to make the recovery conditions easier to meet. For example, the original requirement of "vehicle speed is zero" can be relaxed to "vehicle speed is less than 3 km / h", or the original requirement of "seat adjustment switch being stationary for more than two seconds" can be relaxed to "stationary for more than 0.5 seconds", or the requirements for parameters such as battery voltage and system temperature can be lowered.

[0096] Manually triggered recovery: This refers to the user actively issuing a recovery command through the interactive interface (such as the central control screen) to directly trigger the recovery event without waiting for the automatic recovery conditions to be met.

[0097] In this embodiment, the controller starts timing from the moment the interruption event occurs and the learning snapshot is saved, continuously monitoring whether the recovery conditions are met within a preset time period (e.g., 24 hours). If the recovery conditions are met ahead of schedule within the preset time period, the system triggers the recovery event normally, without needing to execute the response strategy in this embodiment. If the current state corresponding to the seat self-learning task still does not meet the recovery conditions when the preset time period is reached (e.g., the vehicle has been in motion and has never stopped, causing the condition of zero speed to never be met), the controller executes at least one of the following response strategies: First, the judgment criteria for at least one parameter in the recovery conditions are lowered, for example, the requirement of "zero speed" is relaxed to "vehicle speed is less than 3 km / h", or the requirements for parameters such as battery voltage and system temperature are lowered, so that the recovery conditions are easier to meet; Second, a prompt message is output to prompt the user to manually trigger the recovery, for example, "self-learning is not completed, please manually recover" is displayed on the in-vehicle screen, or a prompt is issued through voice broadcast. After seeing the prompt, the user can actively issue a recovery command through the central control screen or other interactive interface to directly trigger the recovery event without waiting for the automatic recovery conditions to be met.

[0098] Through the above mechanism, this application can effectively deal with scenarios where recovery conditions cannot be met for a long time due to the vehicle being in a driving state for a long time or other reasons. By lowering the judgment criteria, the recovery conditions are more easily met, or a manual recovery method is provided to users, avoiding the extreme situation where the self-learning task can never be completed, and further improving the completion rate of the self-learning task and the user experience.

[0099] Figure 5 This is a block diagram illustrating an embodiment of a seat self-learning device provided in this application. Figure 5 As shown, the device includes: The decomposition module 51 is used to decompose the seat self-learning task into multiple sub-tasks and execute each sub-task in sequence. Each sub-task corresponds to controlling the seat motor to move in a limit direction to complete the limit learning in the limit direction. The storage module 52 is used to control the seat motor to stop moving when an interruption event is detected during the execution of each of the sub-tasks, and to save the current learning progress information as a learning snapshot to a preset storage space; The execution module 53 is configured to, in response to a recovery event for the interruption event, read the learning snapshot from the preset storage space and, based on the learning progress information recorded in the learning snapshot, resume the seat self-learning task.

[0100] In one possible implementation, the decomposition module is specifically used for: Determine the positional dependencies between the mechanical structures corresponding to each of the aforementioned limiting directions; Based on the positional dependencies, determine the execution order of each subtask; Each of the subtasks is executed sequentially according to the execution order described.

[0101] In one possible implementation, the apparatus further includes a determining module for: Determine the interrupt type corresponding to the interrupt event; When the interrupt type is a user-triggered interrupt type, the steps of controlling the seat motor to stop moving and saving the current learning progress information as a learning snapshot to the preset storage space are executed to interrupt the seat self-learning task and execute the user-triggered seat adjustment command. When the interrupt type is a safety event interrupt type, the seat self-learning task is terminated, and the learning snapshots saved in the preset storage space are deleted. When the interrupt type is neither a user-triggered interrupt type nor a safety event interrupt type, the steps of controlling the seat motor to stop moving and saving the current learning progress information as a learning snapshot to the preset storage space are executed.

[0102] In one possible implementation, the learning snapshots are stored in a first storage area and a second storage area within the preset storage space, respectively. The execution module is specifically used for: When the learning snapshot is stored in the first storage area, the learning snapshot is read from the first storage area; If the learning snapshot is not stored in the first storage area, the learning snapshot is read from the second storage area; If the learning snapshot is not stored in either the first storage area or the second storage area, it is confirmed that reading the learning snapshot from the preset storage space has failed.

[0103] In one possible implementation, the device further includes a monitoring module for: During the execution of each of the subtasks, the execution status of each subtask is monitored; When the execution status of any subtask indicates that the number of consecutive execution failures of the subtask has reached a preset threshold, it is determined that the seat has a mechanical fault. The seat self-learning task is terminated, and a fault message is output.

[0104] In one possible implementation, the device further includes a display module for: During the execution of each of the sub-tasks, the learning progress information of the seat self-learning task is displayed; When the interruption event is detected, the interruption event and the corresponding interruption reason are displayed; When the seat self-learning task is resumed, a resumption prompt message is displayed.

[0105] In one possible implementation, the device further includes a receiving module for: During the execution of each of the sub-tasks, learning status information broadcast by other seats associated with the seat is received; Based on the learning status information, determine whether there is a risk of motion interference between the other seats and this seat; When there is a risk of motion interference between the other seats and this seat, the execution of the current subtask is suspended until the risk of motion interference is eliminated.

[0106] In one possible implementation, the device further includes a determination module for: Determine whether the current state corresponding to the seat self-learning task meets the preset recovery conditions. The recovery conditions include: there is a verified learning snapshot in the preset storage space; the seat self-learning task is in an incomplete state; the current vehicle state is in a preset running state; there are currently no user operation requests; there are currently no safety risk events; and the current temperature of the seat control system is within a preset temperature range. When the recovery conditions are met, the recovery event is triggered.

[0107] In one possible implementation, the device further includes a timing module for: The timer starts from the time the interruption event occurs; If the current state corresponding to the seat self-learning task does not meet the recovery conditions when the preset time is reached, the judgment criterion of at least one parameter in the recovery conditions will be lowered. Alternatively, if the current state corresponding to the seat self-learning task does not meet the recovery conditions when the timer reaches the preset duration, a prompt message is output to remind the user to manually trigger the recovery.

[0108] like Figure 6 As shown in the figure, this application embodiment provides a vehicle, including a processor 111, a communication interface 112, a memory 113, and a communication bus 114, wherein the processor 111, the communication interface 112, and the memory 113 communicate with each other through the communication bus 114. Memory 113 is used to store computer programs; In one embodiment of this application, when the processor 111 executes the program stored in the memory 113, it implements the seat self-learning method provided in any of the foregoing method embodiments, including: The seat self-learning task is decomposed into multiple sub-tasks, and each sub-task is executed in sequence. Each sub-task corresponds to controlling the seat motor to move in a limit direction to complete the limit learning in the limit direction. When an interruption event is detected during the execution of each of the sub-tasks, the seat motor is controlled to stop moving, and the current learning progress information is saved as a learning snapshot to a preset storage space; In response to a recovery event for the interruption event, the learning snapshot is read from the preset storage space, and the seat self-learning task is resumed based on the learning progress information recorded in the learning snapshot.

[0109] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the seat self-learning method provided in any of the foregoing method embodiments.

[0110] This application also provides a computer program product containing instructions that, when run on a computer, cause the computer to execute any of the seat self-learning methods described in the above embodiments.

[0111] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0112] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented using software plus a general-purpose hardware platform, or of course, using hardware. Based on this understanding, the above technical solutions, in essence or the parts that contribute to the related technology, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0113] It should be understood that the terminology used herein is for the purpose of describing particular exemplary embodiments only and is not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms “a,” “an,” and “described” as used herein may also include the plural forms. The terms “comprising,” “including,” “containing,” and “having” are inclusive and therefore indicate the presence of the stated features, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, elements, components, and / or combinations thereof. The method steps, processes, and operations described herein are not construed as requiring them to be performed in a particular order described or illustrated unless the order of performance is explicitly indicated. It should also be understood that additional or alternative steps may be used.

[0114] The above description is merely a specific embodiment of this application, enabling those skilled in the art to understand or implement this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A seat self-learning method, characterized in that, The method includes: The seat self-learning task is decomposed into multiple sub-tasks, and each sub-task is executed in sequence. Each sub-task corresponds to controlling the seat motor to move in a limit direction to complete the limit learning in the limit direction. When an interruption event is detected during the execution of each of the sub-tasks, the seat motor is controlled to stop moving, and the current learning progress information is saved as a learning snapshot to a preset storage space; In response to a recovery event for the interruption event, the learning snapshot is read from the preset storage space, and the seat self-learning task is resumed based on the learning progress information recorded in the learning snapshot.

2. The method according to claim 1, characterized in that, The sequential execution of each of the subtasks includes: Determine the positional dependencies between the mechanical structures corresponding to each of the aforementioned limiting directions; Based on the positional dependencies, determine the execution order of each subtask; Each of the subtasks is executed sequentially according to the execution order described.

3. The method according to claim 1, characterized in that, Before controlling the seat motor to stop moving, the method further includes: Determine the interrupt type corresponding to the interrupt event; When the interrupt type is a user-triggered interrupt type, the steps of controlling the seat motor to stop moving and saving the current learning progress information as a learning snapshot to the preset storage space are executed to interrupt the seat self-learning task and execute the user-triggered seat adjustment command. When the interrupt type is a safety event interrupt type, the seat self-learning task is terminated, and the learning snapshots saved in the preset storage space are deleted. When the interrupt type is neither a user-triggered interrupt type nor a safety event interrupt type, the steps of controlling the seat motor to stop moving and saving the current learning progress information as a learning snapshot to the preset storage space are executed.

4. The method according to claim 1, characterized in that, The learning snapshots are respectively stored in the first storage area and the second storage area of ​​the preset storage space. The step of reading the learning snapshot from the preset storage space includes: When the learning snapshot is stored in the first storage area, the learning snapshot is read from the first storage area; If the learning snapshot is not stored in the first storage area, the learning snapshot is read from the second storage area; If the learning snapshot is not stored in either the first storage area or the second storage area, it is confirmed that reading the learning snapshot from the preset storage space has failed.

5. The method according to claim 1, characterized in that, The method further includes: During the execution of each of the subtasks, the execution status of each subtask is monitored; When the execution status of any subtask indicates that the number of consecutive execution failures of the subtask has reached a preset threshold, it is determined that the seat has a mechanical fault. The seat self-learning task is terminated, and a fault message is output.

6. The method according to claim 1, characterized in that, The method further includes: During the execution of each of the sub-tasks, the learning progress information of the seat self-learning task is displayed; When the interruption event is detected, the interruption event and the corresponding interruption reason are displayed; When the seat self-learning task is resumed, a resumption prompt message is displayed.

7. The method according to claim 1, characterized in that, The method further includes: During the execution of each of the sub-tasks, learning status information broadcast by other seats associated with the seat is received; Based on the learning status information, determine whether there is a risk of motion interference between the other seats and this seat; When there is a risk of motion interference between the other seats and this seat, the execution of the current subtask is suspended until the risk of motion interference is eliminated.

8. The method according to claim 1, characterized in that, The method further includes: Determine whether the current state corresponding to the seat self-learning task meets the preset recovery conditions. The recovery conditions include: there is a verified learning snapshot in the preset storage space; the seat self-learning task is in an incomplete state; the current vehicle state is in a preset running state; there are currently no user operation requests; there are currently no safety risk events; and the current temperature of the seat control system is within a preset temperature range. When the recovery conditions are met, the recovery event is triggered.

9. The method according to claim 8, characterized in that, The method further includes: The timer starts from the time the interruption event occurs; If the current state corresponding to the seat self-learning task does not meet the recovery conditions when the preset time is reached, the judgment criterion of at least one parameter in the recovery conditions will be lowered. Alternatively, if the current state corresponding to the seat self-learning task does not meet the recovery conditions when the timer reaches the preset duration, a prompt message is output to remind the user to manually trigger the recovery.

10. A vehicle, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, when executing a program stored in memory, implements the method described in any one of claims 1-9.

Images