Vehicle tail door control method, vehicle and electronic equipment

Abstract

The invention provides a control method of a vehicle tail door, a vehicle and electronic equipment, and relates to the technical field of intelligent vehicles, the method comprises the following steps: firstly, in response to a user entering a preset distance range, obtaining multi-dimensional data, the multi-dimensional data is used for representing user operation related information, external environment related information, vehicle state related information and emergency related information; secondly, based on the multi-dimensional data, a decision-making scene is generated, and the decision-making scene is used for representing an adaptive logic type needed by vehicle tail gate control; then, based on the decision-making scene and the multi-dimensional data, a control instruction for the tail door of the vehicle is generated; and finally, based on the control instruction, the tail door of the vehicle is controlled. The technical problem that in the prior art, the vehicle tail door is poor in convenience and user-friendly experience is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent vehicles, in particular to a control method of a vehicle tailgate, a vehicle and an electronic device. BACKGROUND

[0002] Current vehicle tailgate control technology mainly focuses on single-point optimization of basic opening functions, with the core focusing on the basic adaptation of interactive triggering methods and execution mechanisms. Various technical paths such as air conduction voice control, infrared kick sensing, and button triggering have been formed. The development of technology in this field focuses on meeting the basic needs of users to open / close the tailgate, and has made preliminary explorations in the diversity of interaction methods and the stability of execution actions. However, the overall technology still remains within the framework of user-initiated triggering and system-passive response, and has not formed a comprehensive adaptation system for complex usage scenarios, diverse user needs, and emergency safety demands.

[0003] Currently, the existing vehicle tailgate control technology has significant common defects, specifically manifested as: insufficient environmental adaptability, relying on a single interaction method and lacking anti-interference design, in complex environments such as high noise, rain, or mud, the command recognition success rate is significantly reduced, and stable use cannot be guaranteed; missing load scene adaptation, when the user loads heavy objects, the tailgate opening angle and surrounding lighting need to be manually adjusted, which is cumbersome and inefficient.

[0004] In summary, the existing technology has the technical problem of insufficient convenience and humanization experience of vehicle tailgates. SUMMARY

[0005] In view of the above problems, the present application provides a control method of a vehicle tailgate, a vehicle and an electronic device to overcome or at least partially solve the problem of insufficient convenience and humanization experience of current vehicle tailgates. The technical solution is as follows: A control method of a vehicle tailgate, the method comprising: in response to a user entering a preset distance range, obtaining multi-dimensional data, the multi-dimensional data being used to represent user operation related information, external environment related information, vehicle state related information and emergency related information; based on the multi-dimensional data, generating a decision scenario, the decision scenario being used to represent the adaptation logic type required for vehicle tailgate control; based on the decision scenario and the multi-dimensional data, generating a control instruction for the vehicle tailgate; based on the control instruction, controlling the vehicle tailgate.

[0006] In this way, a complete closed-loop control process of multi-dimensional data acquisition-scene generation-control instruction output-tailgate control execution is constructed, breaking through the limitation of the prior art which only focuses on the basic opening function of the tailgate and lacks full-dimensional adaptive logic. By synchronously collecting multi-dimensional data such as user operation, external environment, vehicle state and emergency-related information, comprehensive perception of complex use scenarios is realized, providing data support for subsequent scene judgment and differential instruction generation, fundamentally solving the core problems of passive response and single adaptation scene of the prior art, laying a foundation for intelligent and adaptive tailgate control, while taking into account the multi-dimensional needs of regular use, emergency rescue and special population adaptation, significantly improving the comprehensive adaptation capability of tailgate control.

[0007] Optionally, in response to the user entering a preset distance range, multi-dimensional data is acquired, the multi-dimensional data being used to represent user operation-related information, external environment-related information, vehicle state-related information and emergency-related information; Based on the multi-dimensional data, a decision scene is generated, the decision scene being used to represent the type of adaptive logic required for vehicle tailgate control; Based on the decision scene and the multi-dimensional data, a control instruction for the vehicle tailgate is generated; Based on the control instruction, the vehicle tailgate is controlled.

[0008] In this way, based on the core features of multi-dimensional data, the judgment logic of three types of decision scenes, i.e., regular adaptation, emergency linkage and special population adaptation, is established, solving the defects of the prior art such as no explicit scene classification and chaotic adaptive logic. Through the combination judgment of multi-dimensional conditions such as emergency features, operation instruction types, environment and vehicle state, the accuracy of scene recognition is ensured, effectively distinguishing different demand scenes such as daily operation, emergency rescue and special population use, and avoiding the problem that a single scene control logic cannot adapt to complex demands. The explicit definition of preset emergency features provides a key basis for triggering the emergency linkage scene, and realizes full-scene coverage, laying a key foundation for subsequent generation of targeted control instructions and solving the pain points of insufficient scene adaptation of the prior art.

[0009] Optionally, the generation of the control instruction for the vehicle tailgate based on the decision scene and the multi-dimensional data comprises: In response to the decision scene being a regular adaptation scene, a first control instruction is generated based on the multi-dimensional data, the first control instruction being an instruction for controlling the tailgate to perform a regular opening or closing action corresponding to a general operation instruction; In response to the decision scene being an emergency linkage scene, a second control instruction is generated based on the multi-dimensional data, the second control instruction being a linkage control instruction for controlling the tailgate to perform an emergency full-opening action with the highest priority and synchronously triggering at least one vehicle-level emergency response function. In response to the decision scenario being a special population adaptation scenario, third control instructions are generated based on the multi-dimensional data, the third control instructions being to execute tail gate control actions corresponding to preset non-contact operation instructions.

[0010] In this way, differentiated control instructions are generated for the three types of decision scenarios, solving the problem of single control instructions in the prior art that cannot adapt to the core needs of different scenarios. The regular opening / closing instructions for the regular adaptation scenario ensure the convenience and stability of daily use; the highest priority linkage instructions for the emergency linkage scenario ensure that the tail gate is quickly fully opened and the vehicle emergency function is synchronously responded in a sudden situation, filling the gap between the tail gate control and the rescue system in the prior art, and improving the safety guarantee capability in an emergency scenario; the non-contact instruction response for the special population adaptation scenario specially adapts to the operation needs of groups such as the disabled, reduces the use threshold of special populations, and realizes full population coverage. The three types of instructions have different focuses and complement each other, significantly improving the humanization and intelligence level of tail gate control.

[0011] Optionally, in response to the decision scenario being a regular adaptation scenario, first control instructions are generated based on the multi-dimensional data, including: In response to the decision scenario being the regular adaptation scenario, an identification confidence of the general operation instruction is determined based on an environmental parameter in the external environment related information, the identification confidence being used to represent the identification reliability of the general operation instruction; A target speed and a target angle of tail gate movement are determined based on load data in the vehicle state related information; The first control instructions are generated based on the identification confidence, the target speed, and the target angle.

[0012] In this way, in the regular adaptation scenario, the operation instruction identification confidence is determined based on the environmental parameter, the tail gate movement parameters are determined based on the load data, and then the first control instructions are generated by fusion, solving the problem of weak environmental anti-interference capability in the prior art regular operation and the need for manual adjustment in the load scenario. The identification confidence adjustment based on the environmental parameter can dynamically adapt to complex environments such as noise and precipitation, ensuring the reliability of the operation instruction identification and improving the use stability in extreme scenarios; the target speed and angle adaptation based on the load data realizes the automatic optimization of the tail gate parameters with the load state, avoiding the tedious operation of manual adjustment by the user, and especially improving the loading and unloading efficiency and convenience in the heavy load scenario. The instruction generation logic of multi-parameter fusion takes into account the fluency of regular operation and the adaptability of complex scenarios, further improving the adaptive control capability in the regular scenario.

[0013] Optionally, in response to the decision scenario being an emergency linkage scenario, second control instructions are generated based on the multi-dimensional data, including: In response to the decision scenario being the emergency linkage scenario, based on a voiceprint feature recognition result in emergency-related information in the multi-dimensional data, an emergency event type and an emergency level grade are determined; Based on the emergency event type and the emergency level grade, a first group of execution parameters and a second group of execution parameters are determined, the first group of execution parameters at least including a target opening speed, a target opening angle and a target opening duration of the tailgate, and the second group of execution parameters at least including a type, a trigger sequence and a duration of a vehicle-level emergency response function to be triggered; Based on the first group of execution parameters, a first sub-control instruction for controlling the tailgate to perform an emergency full opening action is generated; Based on the second group of execution parameters, a second sub-control instruction for triggering the vehicle-level emergency response function is generated; The first sub-control instruction and the second sub-control instruction are encapsulated according to a preset timing logic to obtain the second control instruction.

[0014] In this way, for the emergency linkage scenario, the instruction generation logic is constructed, solving the problem of disconnection between tailgate control and rescue function and response delay in the prior art emergency scenario. The emergency event type and the emergency level grade are determined through the voiceprint feature recognition result, ensuring the accuracy of emergency response; the tailgate operation and the emergency function execution parameters are defined separately, and then the instructions are encapsulated in sequence, realizing the synchronous linkage of the tailgate emergency full opening and the vehicle emergency response function, ensuring the rapid unobstructedness of the rescue passage and the timely triggering of the external warning and rescue signal. The logic design ensures the efficiency of emergency response, greatly shortens the response time in the emergency scenario, fills the gap in the tailgate emergency rescue linkage in the prior art, and significantly improves the rescue convenience and safety in emergency situations.

[0015] Optionally, in response to the decision scenario being a special population adaptation scenario, based on the multi-dimensional data, a third control instruction is generated, including: In response to the decision scenario being the special population adaptation scenario, based on user operation-related information in the multi-dimensional data, an operation intention and an operation intensity contained in the preset non-contact operation instruction are analyzed; Based on the operation intention and the operation intensity, tailgate execution parameters are determined; Based on the tailgate execution parameters, the third control instruction is generated.

[0016] In this way, in the special population adaptation scene, the operation intention and operation intensity of the preset non-contact operation instruction are analyzed to determine the tail door execution parameter, solving the problem that the prior art does not design exclusive control logic for special populations and the operation threshold is high. The analysis of the operation intention ensures that the tail door control action is highly matched with the actual needs of special populations, and the association design of the operation intensity realizes fine adaptation of the tail door action, avoiding the unfriendliness of general operation instructions to special populations; the non-contact instruction response mode adapts to the operation ability of the disabled and other groups, effectively reducing the use difficulty. The design fills the gap of the prior art in special population adaptation, realizes full-population coverage of the tail door control, and improves the universality and humanization level of the technology.

[0017] Optionally, multi-source data related to the user historical operation process is acquired, and the multi-source data at least includes user identification, operation trigger time, operation trigger position, environment state at the operation trigger time, and vehicle state; Feature extraction and correlation analysis are performed on the multi-source data to identify high-frequency operation modes, spatio-temporal laws, and state preferences of the user; Based on the high-frequency operation modes, the spatio-temporal laws, and the state preferences, a pre-judgment rule is generated, which specifies the time, place, and condition for activating the detection process in advance.

[0018] In this way, by collecting multi-source data of user historical operations, extracting core features, and generating pre-judgment rules, the operation redundancy problem of the prior art tail door control user active trigger + passive response is solved, and active adaptation of the tail door control is realized. The multi-dimensional historical data collected provides comprehensive data support for personalized pre-judgment; the rule generation logic based on high-frequency operation modes, spatio-temporal laws, and state preferences ensures the accuracy of the pre-judgment rule, which can activate the detection process in advance, trigger interaction when the user approaches the vehicle in a high-frequency use scenario, reduce redundant operation steps, and realize the use experience of non-sensing opening. At the same time, the personalized property of the pre-judgment rule enables it to adapt to the use habits of different users, changes the passive response logic of the prior art, and significantly improves the intelligence and convenience of the tail door control.

[0019] Optionally, when multiple decision scenarios are generated based on the multi-dimensional data, the control instruction for the vehicle tail door is generated based on the decision scenario and the multi-dimensional data, including: The multiple decision scenarios are prioritized based on preset priority rules, and one with the highest priority is selected as the dominant decision scenario; The control instruction for the vehicle tail door is generated based on the dominant decision scenario and the multi-dimensional data.

[0020] Thus, for the case of simultaneous triggering of multiple decision scenarios, a dominant scenario selection mechanism based on priority rules is established, solving the problem that the prior art has no scene conflict processing logic, which may cause functional failure or response delay. By presetting priority rules to sort multiple decision scenarios, the priority response of core demand scenarios such as emergency rescue and special population use can be ensured, and the interference of regular operation scenarios on high-priority scenarios is avoided; the control instruction of the highest-priority dominant scenario is generated, effectively avoiding the problem of tailgate operation confusion or emergency function response delay caused by multiple instruction conflicts, and ensuring the stability of system operation. The design further perfects the logical closed loop of full-scene adaptive control, strengthens the control reliability in complex use scenarios, ensures the priority landing of core functions, and improves the safety and experience of user use.

[0021] A control device of a vehicle tailgate, the device comprising: an acquisition module configured to acquire multi-dimensional data in response to a user entering a preset distance range, the multi-dimensional data being used to represent user operation related information, external environment related information, vehicle state related information, and emergency related information; a first generation module configured to generate a decision scenario based on the multi-dimensional data, the decision scenario being used to represent an adaptive logic type required for control of the vehicle tailgate; a second generation module configured to generate a control instruction for the vehicle tailgate based on the decision scenario and the multi-dimensional data; a control module configured to control the vehicle tailgate based on the control instruction.

[0022] Optionally, the first generation module is further configured to: in response to the multi-dimensional data not detecting a preset emergency feature in the emergency related information, the user operation related information being a general operation instruction, and the external environment related information satisfying a regular interaction condition and the vehicle state related information having a load data lower than a preset load threshold, generate a regular adaptive scenario, the preset emergency feature being used to represent an information mode predefined for triggering the vehicle to enter a safe emergency linkage mode; in response to the multi-dimensional data detecting a preset emergency feature in the emergency related information, generate an emergency linkage scenario; in response to the multi-dimensional data having the user operation related information being a preset non-contact operation instruction, generate a special population adaptive scenario.

[0023] Optionally, the second generation module is further configured to: in response to the decision scenario being a regular adaptive scenario, generate a first control instruction based on the multi-dimensional data, the first control instruction being an instruction for controlling the tailgate to perform a regular opening or closing action corresponding to the general operation instruction; in response to the decision scenario being the emergency linkage scenario, generating, based on the multi-dimensional data, a second control instruction, the second control instruction being a linkage control instruction for controlling the tailgate to perform an emergency full opening action with the highest priority and synchronously triggering at least one vehicle-level emergency response function; in response to the decision scenario being the special population adaptation scenario, generating, based on the multi-dimensional data, a third control instruction, the third control instruction being a tailgate control action corresponding to a preset non-contact operation instruction.

[0024] Optionally, the second generation module is further configured to: in response to the decision scenario being the regular adaptation scenario, determining, based on an environmental parameter in the external environment related information, an identification confidence of the general operation instruction, the identification confidence being used to represent an identification reliability of the general operation instruction; determining a target speed and a target angle of tailgate movement of the vehicle based on load data in the vehicle state related information; generating the first control instruction based on the identification confidence, the target speed, and the target angle.

[0025] Optionally, the second generation module is further configured to: in response to the decision scenario being the emergency linkage scenario, determining, based on a voiceprint feature recognition result in emergency related information in the multi-dimensional data, an emergency event type and an emergency level grade; determining a first group of execution parameters and a second group of execution parameters based on the emergency event type and the emergency level grade, the first group of execution parameters at least including a target opening speed, a target opening angle, and a target opening duration of the tailgate, and the second group of execution parameters at least including a type, a triggering sequence, and a duration of a vehicle-level emergency response function to be triggered; generating a first sub-control instruction for controlling the tailgate to perform an emergency full opening action based on the first group of execution parameters; generating a second sub-control instruction for triggering the vehicle-level emergency response function based on the second group of execution parameters; encapsulating the first sub-control instruction and the second sub-control instruction according to a preset timing logic to obtain the second control instruction.

[0026] Optionally, the second generation module is further configured to: in response to the decision scenario being the special population adaptation scenario, analyzing, based on user operation related information in the multi-dimensional data, an operation intention and an operation intensity contained in the preset non-contact operation instruction; determining tailgate execution parameters based on the operation intention and the operation intensity; Generate the third control instruction based on the tailgate execution parameter.

[0027] Optionally, the control device of the vehicle tailgate further comprises a first acquisition module: The first acquisition module is configured to acquire multi-source data related to the user historical operation process, wherein the multi-source data at least includes user identification, operation trigger time, operation trigger position, environment state at the operation trigger time, and vehicle state. Feature extraction and correlation analysis are performed on the multi-source data to identify high-frequency operation mode, space-time law, and state preference of the user. Based on the high-frequency operation mode, the space-time law, and the state preference, a pre-judgment rule is generated, which specifies the time, location, and condition for activating the detection process in advance.

[0028] Optionally, the control module is further configured to: Based on the preset priority rule, the multiple decision-making scenarios are prioritized, and one with the highest priority is selected as the dominant decision-making scenario. Based on the dominant decision-making scenario and the multi-dimensional data, a control instruction for the vehicle tailgate is generated.

[0029] An electronic device includes a memory, a processor, and a computer program stored on the memory. When the processor executes the computer program, it implements any of the above optional control methods for the vehicle tailgate.

[0030] A vehicle includes a vehicle that implements any of the above optional control methods for the vehicle tailgate.

[0031] By means of the technical scheme, the control method of the vehicle tail door provided by the application first acquires multi-dimensional data in response to the user entering a preset distance range, the multi-dimensional data being used to represent user operation related information, external environment related information, vehicle state related information and emergency related information; secondly, a decision-making scene is generated based on the multi-dimensional data, the decision-making scene being used to represent an adaptive logic type required for vehicle tail door control; then, a control instruction for the vehicle tail door is generated based on the decision-making scene and the multi-dimensional data; and finally, the vehicle tail door is controlled based on the control instruction. In this way, by fusing multi-dimensional data such as user operation, external environment, vehicle state and emergency information, a targeted decision-making scene and adaptive control instruction are generated accordingly, realizing a fundamental change from passive response to active intelligent adaptation of the vehicle tail door, significantly improving the precision and scene adaptability of control, and ensuring reliable and safe operation under complex environments, various loads and sudden emergency conditions; at the same time, through personalized scene prediction and multi-modal interaction design, the convenience and fluency of user operation are greatly optimized, and the use threshold of various users (including special groups) is reduced; in addition, based on data-driven decision-making and hardware reuse strategy, the overall cost and energy consumption are effectively controlled while enhancing the system function integration, realizing the synergistic optimization of performance, experience and economic benefits.

[0032] The above description is only a summary of the technical scheme of the application. In order to enable the technical means of the application to be more clearly understood, and to be implemented in accordance with the content of the description, and in order to enable the above and other purposes, features and advantages of the application to be more apparent and easy to understand, the following specific embodiments of the application are described. BRIEF DESCRIPTION OF DRAWINGS

[0033] Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The accompanying drawings are included to provide a description of the preferred embodiments and are not meant to limit the scope of the application. Furthermore, the same reference numerals are used throughout the several views of the drawings to designate the same or similar parts. In the drawings: Figure 1 A structural schematic diagram of a control system of a vehicle tail door provided by an embodiment of the application is shown; Figure 2 A flowchart of a control method of a vehicle tail door provided by an embodiment of the application is shown; Figure 3 A flowchart of a control method of a vehicle tail door provided by an embodiment of the application is shown; Figure 4 A flowchart of a control method of a vehicle tail door provided by an embodiment of the application is shown; Figure 5Fig. 4 shows a flowchart of a fourth control method of a vehicle tailgate according to an embodiment of the present application; Figure 6 Fig. 6 shows a flowchart of a sixth control method of a vehicle tailgate according to an embodiment of the present application; Figure 7 Fig. 7 shows a structural diagram of a control device of a vehicle tailgate according to an embodiment of the present application. DETAILED DESCRIPTION

[0034] Exemplary embodiments of the present application will be described in greater detail below with reference to the accompanying drawings. Although exemplary embodiments of the present application are shown in the drawings, it is understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided so that the present application can be more thoroughly understood, and the scope of the present application can be accurately conveyed to those skilled in the art.

[0035] The present application provides a control system of a vehicle tailgate, Figure 1 Fig. 1 shows a structural diagram of a control system of a vehicle tailgate according to an embodiment of the present application. Figure 1 As shown, the control system 100 of the vehicle tailgate includes a bone conduction interaction module 101, a positioning module 102, an environment perception module 103, a habit learning unit 104, a core innovation module 105, an emergency voiceprint recognition unit 106, a core control module 107, an execution module 108, and a feedback module 109.

[0036] The bone conduction interaction module 101 is applied to a noise-resistant interaction component of vehicle tailgate control, supports voice command recognition + head movement recognition dual-mode contactless interaction, and is different from single solutions such as air conduction voice and infrared kicking. The bone conduction interaction module 101 is linked with the environment perception module, and when detecting complex environments such as noise ≥ 80 dB and rainfall ≥ 5 mm / h, the recognition sensitivity is automatically enhanced, and at the same time, the interaction mode susceptible to interference is disabled, to ensure the interaction reliability in extreme scenarios.

[0037] The positioning module 102, which can also be referred to as an Ultra-Wideband (UWB) sub-centimeter positioning module, has dual core functions: one is to achieve high-precision distance detection ≤ 0.5 cm, and the other is to complete user identity verification simultaneously. Unlike low-precision positioning solutions, the sub-centimeter accuracy can capture the trigger condition that the user is within ≤ 1 m of the vehicle, while taking into account the low-power consumption feature (standby power consumption ≤ 1 mA) to avoid high-power loss.

[0038] The environmental perception module 103 collects key parameters of the vehicle's surrounding environment in real time, including noise intensity, rainfall size, etc., to provide environmental data support for interaction adaptation and scene decision-making. The environmental perception module 103 does not function alone, but forms an environmental-interaction linkage logic with the bone conduction interaction module 101, dynamically adjusts the interaction recognition strategy through environmental parameters, and avoids the defects of single interaction mode without noise resistance design in existing technologies.

[0039] The habit learning unit 104 is a system-specific intelligent learning module that continuously records user historical operation multi-source data (including user identification, operation trigger time, trigger location, operation environment state, and vehicle state), and through feature extraction and correlation analysis, identifies user high-frequency operation patterns, spatio-temporal laws, and state preferences, and finally generates personalized pre-judgment wake-up rules, which overturns the traditional logic of user active triggering + system passive response, and can wake up the positioning module 102 10-30 seconds in advance to realize the inattentive experience of triggering interaction as the user approaches.

[0040] The core innovation module 105, also known as ESP (Electronic Stability Program), is a multipurpose load perception module that is a core support module for low-cost and high-adaptation systems. Its core logic is to reuse the existing ESP load sensor of the vehicle, without additional hardware costs, to collect vehicle load data and build a linkage control logic for load data, tailgate angle, and lighting brightness. Unlike designs without load collection functions or additional independent load sensors (high cost and poor adaptation), it achieves zero-cost load adaptation through hardware reuse. For example, when the detected load is ≥20 kg, the tailgate opening angle is automatically increased by 20%-30%, and the surrounding lighting brightness is increased by 50%.

[0041] The emergency voiceprint recognition unit 106 is a rescue linkage module with a built-in dedicated emergency voiceprint library. Its core function is to identify preset emergency voiceprint features related to personnel distress, such as falling, in real time. Once such features are detected, the system will trigger the highest priority response immediately. Unlike conventional voiceprint recognition solutions that are only used for ordinary instruction interaction, it focuses on emergency scenarios and builds a deep linkage logic between tailgate control and vehicle emergency systems.

[0042] The core control module 107 is the adaptive center of the whole scene of the system, integrates four core adaptive units, special population adaptation unit 1071, environment / load adaptation unit 1072, low-power wake-up unit 1073, and emergency linkage unit 1074, is responsible for receiving the collected data of all front-end modules such as the bone conduction interaction module 101, the positioning module 102, and the environment perception module 103, intelligent analysis, scene decision, and generation of control instructions, and coordinates the tail door execution mechanism and the feedback module to complete the operation landing and user feedback. Its core value lies in multi-dimensional data fusion decision-making, which can determine the regular adaptation scene, emergency linkage scene, and special population adaptation scene according to the front-end module data, and call the corresponding adaptation logic to realize one scene with one control scheme.

[0043] The execution module 108 can also be called a tail door execution mechanism, which is the action execution terminal of the vehicle tail door control, is responsible for receiving the control instructions output by the core control module 107, converting the instructions into actual operations of the tail door, and core realizing the control of the tail door opening / closing action, including motion speed, opening angle, action timing, and synchronous execution of related functions (such as lighting). This module has the ability to self-adapt parameters and can dynamically adjust the execution parameters according to the needs of different decision-making scenes. Based on hardware reuse logic, it directly reuses the original tail door execution mechanism of the vehicle (such as motor, angle sensor), and only needs to upgrade the software to adapt to new control instructions without adding special execution hardware.

[0044] The feedback module 109 is a two-way interaction bridge between the system and the user, responsible for outputting multi-dimensional feedback information in the whole process of tail door execution operation, ensuring that the user (especially special population) can clearly perceive the tail door operation progress, function status and potential risks. It adopts voice + tactile dual-mode feedback design, and the feedback content is deeply bound with the decision-making scene to solve the pain points of special population (the visually impaired and the disabled) who cannot effectively perceive the operation status.

[0045] The control system 100 of the vehicle tail door realizes the whole-process automatic control of pre-judgment wake-up, position detection, multi-source collection, intelligent decision-making, execution feedback, and data iteration through the closed-loop architecture of "overall planning by the core control module 107 + data collection by each front-end module + landing by the execution / feedback module". It not only solves the defects of the prior art through the combination of bone conduction + UWB + ESP reuse + habit learning + emergency voiceprint recognition, but also reduces the cost of a single set and improves the vehicle model adaptation rate through hardware reuse + standardized interface design, balancing the intelligence, safety, universality and economy.

[0046] In order to solve the technical problems of insufficient convenience and humanization experience of the vehicle tail door in the prior art, in combination with the above-mentioned control system of the vehicle tail door, the application provides a control method of a vehicle tail door, as shown in Figure 2 Figure 2 ​is a schematic flowchart of a control method of a vehicle tailgate provided by an embodiment of the present application, and the method comprises: S11, in response to a user entering a preset distance range, acquiring multi-dimensional data.

[0047] The multi-dimensional data is used to represent user operation related information, external environment related information, vehicle state related information, and emergency related information.

[0048] Specifically, the trigger condition is defined as the user entering the preset distance range to realize the transition from passive waiting triggering to active proximity sensing, and the four core dimensions of data collection are also defined, i.e., user operation (instruction demand), external environment (adaptation basis), vehicle state (load adaptation), and emergency related (safety guarantee). Through the synchronous collection and cross-validation of multi-dimensional data, the integrity and accuracy of scene perception are ensured, and the decision deviation caused by single data is avoided.

[0049] For example, the distance detection is realized by a UWB sub-centimeter positioning module, the preset distance range is ≤1m, and the module also has an identity verification function, which only triggers data collection for authorized users to avoid false triggering. The user operation related information is collected by a bone conduction interaction module, including general voice instructions and special group head movement instructions. The external environment related information is collected by an environment perception module, and the core parameters are noise and rainfall, which provide data support for noise-resistant adaptation. The vehicle state related information is collected by an ESP multiplexing load sensing unit without additional cost, including load data, and the heavy load loading scene is captured. The emergency related information is collected by an emergency voiceprint recognition unit, and the core is the preset emergency voiceprint features such as falling down, which provides a trigger basis for emergency linkage.

[0050] In this embodiment, the user proximity triggering is taken as the logical starting point, and through the collection of all-dimensional key data related to tailgate control, the overall perception of use scenarios, user demand, environment state, and safety risk is realized, which lays a data foundation for subsequent adaptation to different use demands. The core is to break through the limitations of single data collection and incomplete scene perception in the prior art.

[0051] S12, generating a decision-making scene based on the multi-dimensional data.

[0052] The decision-making scene is used to represent the adaptation logic type required for vehicle tailgate control.

[0053] Specifically, the generation of the decision-making scene is based on the feature combination of the four-dimensional data: the safety emergency and non-emergency demand are distinguished through the emergency related information, the general operation and special group operation demand are distinguished through the user operation information, the regular adaptation and special condition adaptation demand are distinguished through the external environment / vehicle state information, and finally the full-scene classification covering daily, emergency, and special groups is formed.

[0054] For example, a conventional adaptation scenario: multi-dimensional data meets emergency-related information, no preset emergency voiceprint features are detected, user operation information is a general voice instruction, an external environment meets a conventional interaction condition, and load data, the adaptation logic is environmental noise resistance adaptation and load parameter optimization; an emergency linkage scenario: the preset emergency feature is detected in the multi-dimensional data by an emergency voiceprint recognition unit, and the adaptation logic is the highest priority, a tailgate, and vehicle emergency system linkage; a special population adaptation scenario: the user operation information is a head motion instruction recognized by a bone conduction module, and the adaptation logic is touchless operation and multi-dimensional feedback.

[0055] In this embodiment, based on multi-dimensional data features, decision scenarios adapted to different use requirements are generated through classification recognition, one set of adaptation logic is realized for one type of scenario, and the core is to solve the defect that a single control logic in the prior art cannot cover complex requirements.

[0056] S13, generating a control instruction for the vehicle tailgate based on the decision scenario and the multi-dimensional data.

[0057] Specifically, the generation of the control instruction follows the scene direction determination and data parameter determination principle: the decision scenario determines the core function of the instruction (conventional switching, emergency linkage, and special population operation), the multi-dimensional data determines the specific execution parameters of the instruction (such as tailgate opening angle, speed, linkage function, and feedback mode), and the adaptability and reliability of the instruction are ensured through parameter optimization.

[0058] In this embodiment, the decision scenario is taken as the core orientation, and the specific features of the multi-dimensional data are combined to generate differentiated control instructions, realizing deep adaptation of scene requirements-instruction parameters, and the core is to break through the limitation of a single instruction in the prior art that cannot meet multiple scenarios.

[0059] S14, controlling the vehicle tailgate based on the control instruction.

[0060] Specifically, the core dimensions of control execution include: execution of tailgate switching action, dynamic adjustment of motion parameters (speed and angle), synchronous linkage of associated functions (lighting and emergency system), and real-time output of multi-dimensional feedback (voice and touch), and through the cooperation of the execution module and the feedback module, the stability, safety, and user perception of the control operation are ensured.

[0061] In this embodiment, the generated differentiated control instructions are converted into actual operations, realizing the matching of tailgate control and scene requirements and user requirements, and ensuring the control effect through the feedback mechanism, and the core is to realize instruction landing and function closed loop, and to improve the intelligence, safety, and convenience of tailgate control.

[0062] In the above scheme, by fusing multi-dimensional data such as user operation, external environment, vehicle state and emergency information, a targeted decision-making scenario and adaptive control instruction are generated, realizing a fundamental change from passive response to active intelligent adaptation of the vehicle tailgate, significantly improving the precision and scene adaptability of the control, and ensuring reliable and safe operation in complex environments, various loads and emergency situations. At the same time, through personalized scene prediction and multi-modal interaction design, the convenience and fluency of user operation are greatly optimized, and the use threshold of various users (including special groups) is reduced. In addition, based on data-driven decision-making and hardware reuse strategy, the overall cost and energy consumption are effectively controlled while enhancing the system function integration, realizing the coordinated optimization of performance, experience and economic benefits.

[0063] In some embodiments, as shown in Figure 3 Based on multi-dimensional data, a decision-making scenario is generated, including: S121, in response to the multi-dimensional data, if the emergency-related information does not detect a preset emergency feature, the user operation-related information is a general operation instruction, the external environment-related information meets the general interaction condition, and the vehicle state-related information has a load data lower than a preset load threshold, a general adaptive scenario is generated.

[0064] The preset emergency feature is used to represent a predefined information mode that triggers the vehicle to enter a safe emergency linkage mode.

[0065] Specifically, the generation of the general adaptive scenario is based on the positive satisfaction and reverse exclusion of four-dimensional data: reverse exclusion of emergency risk (no detection of preset emergency feature), positive matching of general operation demand (general operation instruction), adaptation of environmental conditions (satisfaction of general interaction requirements), and low load state (load data lower than threshold), and the four conditions are indispensable to ensure the accuracy of scenario determination.

[0066] For example, no preset emergency feature is detected: detected by the emergency voiceprint recognition unit, the preset emergency feature is a personnel distress-related voiceprint mode such as "falling down" and "help" in the built-in emergency voiceprint library, and the condition is satisfied if such voiceprints are not recognized; the user operation-related information is a general operation instruction: collected by the bone conduction interaction module, the general operation instruction refers to a general voice instruction (such as "open the tailgate" and "close the tailgate"), which is distinguished from the head movement instruction of special groups; the external environment-related information meets the general interaction condition: the core parameters are collected by the environment perception module, and the determination standard is "noise < 80 dB + rainfall < 5 mm / h", ensuring that the interaction environment has no strong interference; the load data in the vehicle state-related information is lower than the preset load threshold: collected by the core innovation module, the load data accuracy is ±1 kg, and the preset threshold is <20 kg (corresponding to daily empty load or light load scenarios).

[0067] In this embodiment, the non-emergency, general demand, and regular condition are taken as the core basis for judgment, and a decision type suitable for the daily basic use scene is generated through the combination verification of multi-dimensional data characteristics. The core is to realize the stable adaptation to the user's regular operation demand, avoid the interference of special scene logic on daily use, and fill the gap of the single control logic of the prior art which cannot distinguish between regular and special scenes.

[0068] S122, in response to the detection of a preset emergency feature in the multi-dimensional data, an emergency linkage scene is generated.

[0069] Specifically, the generation of the emergency linkage scene adopts a logic of single core condition triggering without other condition restrictions, and the core triggering condition is to detect a preset emergency feature without relying on other data such as operation instructions, environmental state, or vehicle load, thereby ensuring the timeliness and priority of emergency response. The scene target focuses on safety rescue, and the core is to activate the highest priority linkage control logic to realize the rapid opening of the tailgate and the synchronous triggering of the vehicle emergency function, thereby solving the problem of the prior art that there is no special judgment logic for emergency scenes and the rescue response is delayed.

[0070] For example, the emergency-related information collection and feature recognition: the surrounding voiceprint data is collected in real time by the emergency voiceprint recognition unit, and is accurately matched with the built-in emergency voiceprint library. Once the preset emergency features such as "falling down" are identified, the scene generation is triggered immediately.

[0071] In this embodiment, the emergency risk identification is taken as the core triggering condition to generate the safety rescue type decision scene with the highest priority, and the core is to realize the deep linkage of the tailgate control and the vehicle emergency system, thereby breaking the limitation of the separation of the tailgate function and rescue in the prior art, and providing scene support for quickly building a rescue passage and triggering a rescue signal in an emergency.

[0072] S123, in response to the user operation-related information in the multi-dimensional data being a preset non-contact operation instruction, a special population adaptation scene is generated.

[0073] Specifically, the core of the generation of the special population adaptation scene is the exclusive identification of the operation instruction, which does not rely on additional conditions such as environmental state and load data (to avoid the restriction of complex conditions on the operation of special populations), and only takes the preset non-contact operation instruction as the only triggering basis, thereby solving the problem of the prior art that there is no special population exclusive scene and the operation threshold is high.

[0074] For example, the preset non-contact operation instruction collection: the bone conduction interaction module performs identification, and the instruction is specifically a head movement instruction customized for the disabled (such as "2 times of continuous nodding = opening the tailgate" and "1 time of left and right shaking = closing the tailgate"), which is different from the general voice instruction of ordinary users and can be triggered without body contact.

[0075] In the embodiment, a special population exclusive operation instruction is taken as a core trigger condition, a decision scene adapted to the needs of the weak groups such as the disabled and the visually impaired is generated, and the core is to break the limitation of the general interaction of the prior art, to provide a tailgate control scheme with low threshold and safe adaptation for special populations through exclusive scenes, and to realize full population coverage.

[0076] In the above scheme, S121 locks the daily low-risk and conventional demand scene based on the four combinations of emergency features, general operation instructions, environmental conditions and load data, provides clear guidance for subsequent environmental noise adaptation and load adaptive control, and improves the extreme environment recognition success rate and light load scene use stability; S122 takes emergency voiceprint feature recognition as a core single trigger condition, gives the emergency scene the highest priority judgment logic, ensures the quick activation of the rescue channel in emergency conditions, and realizes emergency response; S123 takes the special population preset non-contact operation instruction as the exclusive trigger basis, does not need to rely on other environmental or vehicle state conditions, reduces the operation threshold of the weak groups, and guarantees the special population use satisfaction. The three cooperate to form a full-scene judgment closed loop covering daily, emergency and special population, which not only ensures the accuracy of scene recognition through multi-dimensional condition verification, but also lays a solid foundation for subsequent differentiated control instruction generation through clear adaptation logic guided by core needs.

[0077] In some embodiments, as shown in Figure 4 based on the decision scene and the multi-dimensional data, a control instruction for the tailgate of the vehicle is generated, including: S131, in response to the decision scene being a conventional adaptation scene, a first control instruction is generated based on the multi-dimensional data.

[0078] The first control instruction is an instruction for controlling the tailgate to perform a conventional opening or closing action corresponding to the general operation instruction.

[0079] In response to the decision scene being a conventional adaptation scene, an identification confidence of the general operation instruction is determined based on the environmental parameters in the external environment related information, the identification confidence is used to represent the identification reliability of the general operation instruction; the target speed and the target angle of the tailgate movement of the vehicle are determined based on the load data in the vehicle state related information; the first control instruction is generated based on the identification confidence, the target speed and the target angle.

[0080] Specifically, the generation of the first control instruction follows multi-data fusion and adaptive logic: dynamically adjusting the instruction recognition reliability based on the environmental parameters (to ensure effective interaction), optimizing the tailgate movement parameters based on the load data (to ensure operation adaptation), and then synergistically fusing the recognition confidence, target speed, and target angle to form a regular control instruction that takes into account the interaction stability and operation adaptability, thereby avoiding the insufficient adaptation caused by the fixed instructions and rigid parameters in the prior art, and ensuring the convenience of use in different environments and load states in regular scenarios.

[0081] In this embodiment, the stability and adaptability of regular adaptation scenarios are taken as the core targets, and personalized regular control instructions are generated by fusing multi-dimensional data such as environmental, load, and instruction recognition reliability. The core is to solve the defects of weak environmental anti-interference and manual adjustment in load scenarios in the prior art regular operation, to realize self-adaptation and manual intervention-free in daily use, and to fill the gap of single regular instruction in the prior art that cannot adapt to complex daily scenarios.

[0082] S132, in response to the decision scenario being an emergency linkage scenario, generating a second control instruction based on multi-dimensional data.

[0083] Among them, the second control instruction is a linkage control instruction for controlling the tailgate to perform an emergency full opening action with the highest priority, and synchronously triggering at least one vehicle-level emergency response function.

[0084] In response to the decision scenario being an emergency linkage scenario, based on the voiceprint feature recognition result in the emergency-related information in the multi-dimensional data, the type of emergency event and the level of emergency are determined; based on the type of emergency event and the level of emergency, a first group of execution parameters and a second group of execution parameters are determined, the first group of execution parameters at least including the target opening speed, the target opening angle and the target opening time length of the tailgate, and the second group of execution parameters at least including the type, the trigger sequence and the duration of the vehicle-level emergency response function to be triggered; based on the first group of execution parameters, a first sub-control instruction for controlling the tailgate to perform an emergency full opening action is generated; based on the second group of execution parameters, a second sub-control instruction for triggering the vehicle-level emergency response function is generated; the first sub-control instruction and the second sub-control instruction are encapsulated according to a preset timing logic to obtain the second control instruction.

[0085] Specifically, the generation of the second control instruction follows the recognition, hierarchical adaptation, and linkage encapsulation logic: first, the type of emergency event and the level of emergency are identified through emergency-related data, then the two groups of execution parameters of tailgate operation and emergency function are split according to the level (clear speed, angle, linkage function, timing, etc.), and the sub-instructions are generated and encapsulated according to the preset logic, to ensure that the priority of the instruction is the highest, the response is the fastest, and the linkage is the most complete, thereby solving the problems of no emergency exclusive instruction and delayed rescue response in the prior art, and ensuring the safety and rescue efficiency in emergency scenarios.

[0086] For example, emergency event recognition and level determination: the voiceprint data is collected by the emergency voiceprint recognition unit, matched with the built-in emergency voiceprint library (containing features such as "falling down" and "help"), and if the voiceprint matching degree is greater than or equal to 95%, it is determined as an effective emergency event; based on the voiceprint feature intensity and the event type, the emergency level is divided (such as "falling down" as first-class emergency, "help" as second-class emergency); execution parameter determination: the first group of execution parameters (tailgate operation): when the first-class emergency occurs, the target opening speed is 1.5 times or more of the regular scene (the fastest speed), the target opening angle is maximized (to ensure the rescue passage is smooth), and the target opening time is "continuous opening until the rescue is completed"; when the second-class emergency occurs, the opening speed and angle are executed according to the first-class standard, and the opening time is 30 minutes by default (which can be manually closed); the second group of execution parameters (emergency function): the default trigger is "emergency light flashing + SOS rescue signal sending", the trigger sequence is "0.5 seconds after the tailgate opening operation is started, the second control instruction is generated based on the first group of parameters "tailgate emergency full opening" first sub-control instruction, and the second group of parameters "emergency function linkage" second sub-control instruction is generated, and the second control instruction is encapsulated according to the time sequence logic of "tailgate operation first, emergency function following".

[0087] In this embodiment, the emergency rescue is taken as the core target, the instruction is given the highest priority, the tailgate emergency operation and the vehicle emergency function are deeply linked, and the integrated emergency control instruction is generated. The core is to break the limitation of the separation of the tailgate control and the emergency system in the prior art.

[0088] S133, in response to the decision scenario being a special population adaptation scenario, generating a third control instruction based on multi-dimensional data.

[0089] The third control instruction is an execution tailgate control action corresponding to a preset non-contact operation instruction.

[0090] In response to the decision scenario being a special population adaptation scenario, based on the user operation related information in the multi-dimensional data, the operation intention and operation intensity contained in the preset non-contact operation instruction are analyzed; based on the operation intention and operation intensity, the tailgate execution parameters are determined; and based on the tailgate execution parameters, the third control instruction is generated.

[0091] Specifically, the third control instruction takes the special population preset non-contact operation instruction as input, analyzes the operation intention (opening / closing the tailgate) and operation intensity (action amplitude / force) behind the instruction, and then determines the adapted tailgate execution parameters (speed, angle, feedback mode) based on the intention and intensity, so as to ensure that the instruction is highly matched with the operation ability and use demand of the special population, and solve the problem of high operation threshold and insufficient safety of the general instruction in the prior art.

[0092] In this embodiment, the core target is low threshold and high safety for special groups. For the use needs of the disadvantaged groups such as the disabled and the visually impaired, exclusive non-contact control instructions are generated. The core is to break through the limitations of the general interaction of the existing technology, realize the full population coverage of the tailgate control, and fill the short board of the insufficient adaptation of the special population in the existing technology.

[0093] In the above scheme, S131 dynamically adjusts the general operation instruction recognition confidence based on the environmental parameters, optimizes the tailgate movement speed and angle in combination with the ESP multiplexing load data, realizes the effect of extreme environment recognition success rate and heavy load efficiency, solves the problem of poor environmental adaptability and lack of load adaptation in the existing technology; S132 determines the emergency level relying on the emergency voiceprint recognition result, realizes the synchronous linkage of the tailgate emergency full opening and the emergency light, SOS system through double-group execution parameter splitting and time sequence packaging, and breaks through the defect of the fragmented emergency function in the existing technology; S133 analyzes the intention and intensity of the special population preset non-contact operation instruction, matches the adaptive tailgate execution parameters and links the voice and touch dual-mode feedback, fills the short board of the insufficient adaptation of the special population in the existing technology. The three cooperations form an instruction system covering all scenarios and all populations, upgrade the tailgate control from traditional single function execution to intelligent service of full-scene precise adaptation, and the technology combination and actual effect are unique innovations not covered by the existing patents.

[0094] In some embodiments, as shown in Figure 5 the control method of the vehicle tailgate further includes: S15, acquiring multi-source data related to the user historical operation process.

[0095] The multi-source data at least includes user identification, operation trigger time, operation trigger position, environmental state at the time of operation trigger, and vehicle state.

[0096] Specifically, the collection of multi-source data focuses on five core dimensions directly related to tailgate control: different authorized users are distinguished through user identification (to avoid confusion of multi-user habits), the spatiotemporal characteristics of user behavior are captured through operation trigger time / position, the scene adaptation conditions are associated through environmental state, and the operation requirements such as load are matched through vehicle state. The core is to establish an associated data pool of user behavior and multi-dimensional scene factors, ensure that the collected data have the value of analysis and reuse, and lay a foundation for subsequent identification of user habit rules and generation of prediction rules.

[0097] In this embodiment, the core target is personalized prediction, and key associated data in the user historical operation process is collected comprehensively to build a full-dimensional data foundation covering users, time, space, environment, and vehicles. The core is to break through the limitations of single data collection in the existing technology, which cannot support active adaptation, and to provide sufficient data support for subsequent user behavior feature extraction and prediction rule generation.

[0098] S16, feature extraction and correlation analysis are performed on the multi-source data to identify high-frequency operation modes, spatio-temporal laws and state preferences of the user.

[0099] Specifically, the feature extraction and correlation analysis follow a multi-dimensional cross and law extraction logic: for high-frequency operation modes, the occurrence frequency of different operation scenarios is counted, and the core scenario with the highest proportion is selected; for spatio-temporal laws, operation time and location data are correlated to identify strong correlation behaviors at fixed times and fixed locations; for state preferences, the correspondence between environmental state, vehicle state and operation instruction type is cross-analyzed to capture the operation habits of the user in different scenarios, and data analysis is avoided to be superficial, thereby providing core support for subsequent generation of prediction rules.

[0100] In the embodiment, by deep mining and correlation analysis of multi-source historical data, core behavior characteristics of user tailgate operation are extracted, and the core is to strip out regularized information that can be used for prediction from massive data, to provide logical basis for realizing active adaptation of tailgate control, and to break the limitation of no user habit recognition capability in the prior art.

[0101] S17, based on high-frequency operation modes, spatio-temporal laws and state preferences, prediction rules are generated.

[0102] The prediction rules specify the time, location and conditions for activating the detection process in advance.

[0103] Specifically, the core of the prediction rules includes three elements: the time (based on the time law of high-frequency operation) for activating the detection process in advance, the location (based on the location characteristics of high-frequency operation) for activating the detection process in advance, and the condition (based on the environmental state and vehicle state preference) for activating the detection process in advance, to ensure that the rules can match the user habits, and when the time, location and conditions specified by the rules are met, the system automatically wakes up the detection process in advance, and the user can trigger subsequent interaction without active operation, thereby significantly improving the convenience of use.

[0104] In the embodiment, based on the extracted user behavior characteristics, exclusive prediction wake-up rules are generated, and the core is to realize the activation of the system in advance and the user's non-perception interaction, thereby solving the pain point of operation redundancy in high-frequency scenarios.

[0105] In the above scheme, S15 collects multi-dimensional historical data such as user identification, operation trigger time / position, environment state and vehicle state by multiplexing existing hardware such as UWB sub-centimeter positioning module, environment perception module, ESP multiplexing load perception unit, etc., without adding hardware cost, thereby building a full-dimensional data foundation covering users, space-time, scene and vehicles, and providing high-value input for subsequent habit analysis; S16 identifies high-frequency operation mode, space-time law and state preference of the user through feature extraction and correlation analysis, and extracts regularized information that can be used for prediction from massive data, thereby solving the problem of isolated and worthless data in the prior art; S17 generates exclusive prediction wake-up rules based on the extracted behavior characteristics, and determines the time of activating the detection process, the commonly used operation location and the adaptation condition 10-30 seconds in advance, thereby realizing precise pre-wakeup of UWB from low-power standby state in high-frequency scenes, triggering interaction directly when the user approaches the vehicle, overturning the passive response logic of the prior art, reducing the active operation steps of the user in high-frequency scenes, achieving the use experience of opening without feeling, and continuously iterating and optimizing the rules through new data in the habit learning unit, thereby ensuring that the user habit changes are always adapted in long-term use, and filling the gap in active adaptation of user habits for vehicle tailgate control.

[0106] In some embodiments, as shown in Figure 6 When multiple decision-making scenes are generated based on multi-dimensional data, a control instruction for the tailgate of the vehicle is generated based on the decision-making scene and the multi-dimensional data, including: S18, based on a preset priority rule, priority sorting is performed on the multiple decision-making scenes, and one with the highest priority is selected as the dominant decision-making scene.

[0107] Specifically, the priority rule is set with the core principles of safety first, demand adaptation and consideration of the basis, and the value weight of different decision-making scenes is determined: the emergency rescue scene involving life safety is set as the highest priority, the special population adaptation scene for protecting the use of vulnerable groups is set as the second highest priority, and the regular adaptation scene for meeting the daily basic needs is set as the basic priority. By quantitatively sorting multiple scenes triggered at the same time (such as emergency and regular, special population and regular), the logical interference of low-priority scenes is excluded, the core adaptation logic of the dominant scene is ensured not to be diluted, the problems of instruction confusion, response delay or core function failure caused by multiple scene superposition are solved, and the stability and pertinence of system decision-making are ensured.

[0108] In this embodiment, a systematic solution mechanism for multiple decision-making scene conflicts is established, and multiple scenes triggered at the same time are hierarchically divided by preset priority rules, and the highest priority scene is locked as the dominant one, and the core is to ensure that the core needs such as emergency rescue and special population use are met in priority, thereby solving the defects of the prior art that there is no scene conflict processing logic and high-priority needs are disturbed by regular operations.

[0109] S19, generating a control instruction for the vehicle tailgate based on the dominant decision-making scene and the multi-dimensional data.

[0110] Specifically, the dominant decision-making scene specifies the core functional target of the instruction (such as "quick door opening + linkage rescue" for emergency rescue, "low threshold operation + strong feedback" for special groups, and "stable and convenient" for regular scenarios), and the multi-dimensional data (environmental parameters, load data, operation instructions, etc.) optimizes the specific execution parameters of the instruction (such as opening speed, angle, linkage function, feedback mode), ensuring that the instruction not only meets the core needs of the dominant scene, but also adapts to the current use conditions, avoiding the rigidity of the instruction or the disconnection with the actual scene.

[0111] In this embodiment, the dominant decision-making scene is taken as the core orientation, multi-dimensional data features are deeply integrated, and a control instruction matching the dominant demand is generated, solving the problem of instruction confusion and disconnection between function and demand under multi-scene conflict, and ensuring the efficient landing of core scenes (emergency, special groups) while considering the adaptability and reliability of the instruction.

[0112] In the above scheme, S18 takes the preset priority rule of prioritizing emergency safety, followed by special group adaptation, and then regular demand, ensuring that core needs such as emergency linkage scenes and special group adaptation scenes are prioritized, avoiding interference from regular operations on key scenes such as life safety rescue and use by vulnerable groups, and filling the gap in existing technology in multi-scene conflict processing; S19, based on the dominant scene, specifies the core functional orientation, and integrates multi-dimensional data to optimize execution parameters, ensuring that in emergency scenes, the tailgate is quickly opened and the rescue function is synchronously linked, in special group scenes, non-contact operation and multi-dimensional feedback are accurately adapted, and in regular scenes, environmental noise resistance and load adaptation are stably landed, enabling the system to upgrade from single function execution to core demand priority and full-scene adaptation intelligent service, and completely breaking through the limitations of existing technology in multi-scene function confusion and core value guarantee.

[0113] In addition, as shown in Figure 7 , a structure diagram of a vehicle tailgate control device 700 provided by an embodiment of the present application is shown, which comprises: Figure 7 An acquisition module 701 is configured to acquire multi-dimensional data in response to a user entering a preset distance range, the multi-dimensional data being used to represent user operation related information, external environment related information, vehicle state related information, and emergency related information. A first generation module 702 is configured to generate a decision-making scene based on the multi-dimensional data, the decision-making scene being used to represent the adaptive logic type required for vehicle tailgate control. A second generation module 703 is configured to generate a control instruction for the vehicle tailgate based on the decision-making scene and the multi-dimensional data. ​The control module 704 is configured to control the vehicle tail door based on the control instruction.

[0114] In the above scheme, by fusing multi-dimensional data such as user operation, external environment, vehicle state and emergency information, a targeted decision-making scenario and adaptive control instruction are generated, realizing a fundamental change from passive response to active intelligent adaptation of the vehicle tail door, significantly improving the precision and scene adaptability of the control, and ensuring reliable and safe operation in complex environments, various loads and emergency situations. At the same time, through personalized scene prediction and multi-modal interaction design, the convenience and fluency of user operation are greatly optimized, and the use threshold of various users (including special groups) is reduced. In addition, based on data-driven decision-making and hardware reuse strategy, the overall cost and energy consumption are effectively controlled while enhancing the system function integration, realizing the synergistic optimization of performance, experience and economic benefits.

[0115] In one embodiment, the first generation module 702 is further configured to: In response to the emergency-related information in the multi-dimensional data not detecting a preset emergency feature, the user operation-related information being a general operation instruction, and the external environment-related information satisfying the general interaction condition and the vehicle state-related information having load data lower than a preset load threshold, a general adaptive scenario is generated. The preset emergency feature is used to represent a predefined information mode that triggers the vehicle to enter a safe emergency linkage mode. In response to the emergency-related information in the multi-dimensional data detecting a preset emergency feature, an emergency linkage scenario is generated. In response to the user operation-related information in the multi-dimensional data being a preset non-contact operation instruction, a special group adaptive scenario is generated.

[0116] In one embodiment, the second generation module 703 is further configured to: In response to the decision-making scenario being a general adaptive scenario, based on the multi-dimensional data, a first control instruction is generated, the first control instruction being an instruction for controlling the tail door to perform a general opening or closing action corresponding to the general operation instruction; In response to the decision-making scenario being an emergency linkage scenario, based on the multi-dimensional data, a second control instruction is generated, the second control instruction being a linkage control instruction for controlling the tail door to perform an emergency full opening action with the highest priority and synchronously triggering at least one vehicle-level emergency response function; In response to the decision-making scenario being a special group adaptive scenario, based on the multi-dimensional data, a third control instruction is generated, the third control instruction being an instruction for performing a tail door control action corresponding to the preset non-contact operation instruction.

[0117] In one embodiment, the second generation module 703 is further configured to: In response to the decision scenario being a regular adaptation scenario, an identification confidence of the general operation instruction is determined based on an environmental parameter in the external environment related information, and the identification confidence is used to represent the identification reliability of the general operation instruction. Based on the load data in the vehicle state related information, a target speed and a target angle of the vehicle tailgate movement are determined. Based on the identification confidence, the target speed and the target angle, a first control instruction is generated.

[0118] In one specific embodiment, the second generation module 703 is further configured to: In response to the decision scenario being an emergency linkage scenario, an emergency event type and an emergency level are determined based on a voiceprint feature identification result in the emergency related information in the multi-dimensional data. Based on the emergency event type and the emergency level, a first group of execution parameters and a second group of execution parameters are determined, the first group of execution parameters at least including a target opening speed, a target opening angle and a target opening duration of the tailgate, and the second group of execution parameters at least including a type, a trigger sequence and a duration of a vehicle-level emergency response function to be triggered. Based on the first group of execution parameters, a first sub-control instruction for controlling the tailgate to execute an emergency full opening action is generated. Based on the second group of execution parameters, a second sub-control instruction for triggering the vehicle-level emergency response function is generated. The first sub-control instruction and the second sub-control instruction are encapsulated according to a preset timing logic to obtain the second control instruction.

[0119] In one specific embodiment, the second generation module 703 is further configured to: In response to the decision scenario being a special population adaptation scenario, an operation intention and an operation intensity contained in a preset non-contact operation instruction are parsed based on user operation related information in the multi-dimensional data. Based on the operation intention and the operation intensity, tailgate execution parameters are determined. Based on the tailgate execution parameters, a third control instruction is generated.

[0120] In one specific embodiment, the control device 700 of the vehicle tailgate further includes a first acquisition module: The first acquisition module is configured to acquire multi-source data related to a user historical operation process, the multi-source data at least including a user identifier, an operation trigger time, an operation trigger location, an environmental state at the operation trigger time and a vehicle state. The multi-source data is subjected to feature extraction and correlation analysis to identify a high-frequency operation mode, a spatio-temporal law and a state preference of the user. Based on the high-frequency operation mode, the spatio-temporal law and the state preference, a pre-judgment rule is generated, and the pre-judgment rule specifies a time, a place and a condition for activating the detection process in advance.

[0121] In one specific embodiment, the control module 704 is further configured to: prioritize the plurality of decision scenarios based on preset priority rules, and select one with the highest priority as a dominant decision scenario; generate a control instruction for the tailgate of the vehicle based on the dominant decision scenario and the multi-dimensional data.

[0122] As to the apparatus in the above embodiments, the specific manners in which the units perform operations have been described in detail in the embodiments of the method, and thus will not be described in detail here.

[0123] The embodiments also provide an electronic device including a memory, a processor, and a computer program stored in the memory. When the processor executes the computer program, the control method of the tailgate of the vehicle is implemented, and thus the same effects as the above-mentioned implementation method can be achieved.

[0124] The embodiments also provide a vehicle including the vehicle executing the control method of the tailgate of the vehicle.

[0125] The above embodiments have the beneficial effects as described above in the corresponding method, which will not be described here.

[0126] From the above description of the embodiments, those skilled in the art can understand that, for the convenience and brevity of description, only the division of the above functional modules is taken as an example for illustration. In actual application, the above functions can be completed by different functional modules according to needs, i.e., the internal structure of the apparatus is divided into different functional modules to complete all or part of the above-described functions.

[0127] In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented by other means. For example, the apparatus embodiments described above are only illustrative. For example, the division of modules or units is only a logical function division. In actual implementation, another division manner can be used, for example, a plurality of units or components can be combined or integrated into another apparatus, or some features can be omitted or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed units can be indirect coupling or communication connection through some interfaces, apparatuses or units, which can be electrical, mechanical or other forms.

[0128] In the description of the present application, it needs to be understood that, if the orientation or position relationship indicated by the terms "upper", "lower", "front", "back", "left" and "right" and the like is based on the orientation or position relationship shown in the drawings, it is only for the convenience of describing the present application and simplifying the description, and does not indicate or imply that the position or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation of the present application.

[0129] It should be noted that, in this document, the terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between the entities or operations. It should also be noted that the terms "include", "contain" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or equipment including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or equipment. Without more limitations, the element defined by the statement "including a" does not exclude the presence of other identical elements in the process, method, article or equipment including the element.

[0130] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement and the like within the spirit and principle of the present application shall be included in the scope of claims of the present application.

Claims

1. A method for controlling a vehicle tailgate, characterized in that, The method includes: In response to a user entering a preset distance range, multi-dimensional data is acquired. The multi-dimensional data is used to characterize user operation-related information, external environment-related information, vehicle status-related information, and emergency-related information. Based on the multi-dimensional data, a decision scenario is generated, which is used to characterize the type of adaptation logic required for vehicle tailgate control. Based on the decision-making scenario and the multi-dimensional data, a control command for the vehicle's tailgate is generated. The vehicle tailgate is controlled based on the control command.

2. The control method according to claim 1, characterized in that, The generation of decision-making scenarios based on the multi-dimensional data includes: In response to the fact that no preset emergency features were detected in the emergency-related information in the multi-dimensional data, the user operation-related information is a general operation command, the external environment-related information meets the normal interaction conditions, and the load data in the vehicle status-related information is lower than the preset load threshold, a normal adaptation scenario is generated. The preset emergency features are used to characterize the predefined information pattern that triggers the vehicle to enter the safety emergency linkage mode. In response to the detection of preset emergency features in the emergency-related information in the multi-dimensional data, an emergency response scenario is generated. In response to the user operation-related information in the multi-dimensional data as preset non-contact operation instructions, a scenario adapted to special groups is generated.

3. The control method according to claim 2, characterized in that, The step of generating control commands for the vehicle tailgate based on the decision-making scenario and the multi-dimensional data includes: In response to the decision scenario being a conventional adaptation scenario, a first control command is generated based on the multi-dimensional data. The first control command is a command to control the tailgate to perform a conventional opening or closing action corresponding to a general operation command. In response to the decision scenario being an emergency linkage scenario, a second control command is generated based on the multi-dimensional data. The second control command is to control the tailgate to perform an emergency full opening action with the highest priority, and simultaneously trigger at least one vehicle-level emergency response function linkage control command. In response to the decision scenario being a scenario adapted to a special population, a third control command is generated based on the multi-dimensional data. The third control command is to execute the tailgate control action corresponding to the preset non-contact operation command.

4. The control method according to claim 3, characterized in that, The response to the decision scenario is a conventional adaptation scenario. Based on the multi-dimensional data, a first control command is generated, including: In response to the decision scenario being the conventional adaptation scenario, the recognition confidence of the general operation command is determined based on the environmental parameters in the external environment-related information. The recognition confidence is used to characterize the reliability of the recognition of the general operation command. Based on the load data in the vehicle status-related information, the target speed and target angle of the vehicle tailgate movement are determined. The first control command is generated based on the recognition confidence level, the target speed, and the target angle.

5. The control method according to claim 3, characterized in that, The response to the decision-making scenario being an emergency response scenario involves generating a second control command based on the multi-dimensional data, including: In response to the decision-making scenario being the emergency response scenario, the type of emergency event and the level of urgency are determined based on the voiceprint feature recognition results in the emergency-related information in the multi-dimensional data. Based on the type of emergency event and the level of urgency, a first set of execution parameters and a second set of execution parameters are determined. The first set of execution parameters includes at least the target opening speed, target opening angle and target opening duration of the tailgate. The second set of execution parameters includes at least the type, triggering order and duration of the vehicle-level emergency response function to be triggered. Based on the first set of execution parameters, a first sub-control command is generated to control the tailgate to perform an emergency full opening action; Based on the second set of execution parameters, a second sub-control command is generated to trigger the vehicle-level emergency response function; The first sub-control instruction and the second sub-control instruction are encapsulated according to a preset timing logic to obtain the second control instruction.

6. The control method according to claim 3, characterized in that, In response to the decision-making scenario being a scenario adapted to a special population, a third control command is generated based on the multi-dimensional data, including: In response to the decision scenario being a scenario adapted to the special population, the operation intent and operation intensity contained in the preset non-contact operation command are analyzed based on the user operation-related information in the multi-dimensional data. Based on the stated operational intent and the stated operational intensity, determine the tailgate execution parameters; The third control command is generated based on the tailgate execution parameters.

7. The control method according to claim 1, characterized in that, The method further includes: Acquire multi-source data related to the user's historical operation process. The multi-source data includes at least the user identifier, operation trigger time, operation trigger location, environmental state at the time of operation trigger, and vehicle state. Feature extraction and correlation analysis are performed on the multi-source data to identify users' high-frequency operation patterns, spatiotemporal patterns, and state preferences; Based on the high-frequency operation mode, the spatiotemporal patterns, and the state preferences, a prediction rule is generated, which specifies the time, location, and conditions for activating the detection process in advance.

8. The control method according to claim 1, characterized in that, When multiple decision scenarios are generated based on the multi-dimensional data, the step of generating control commands for the vehicle tailgate based on the decision scenarios and the multi-dimensional data includes: Based on preset priority rules, the multiple decision scenarios are prioritized and the one with the highest priority is selected as the dominant decision scenario. Based on the dominant decision-making scenario and the multi-dimensional data, control commands for the vehicle's tailgate are generated.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory, characterized in that, When the processor executes the computer program, it implements the vehicle tailgate control method as described in any one of claims 1 to 8.

10. A vehicle, characterized in that, The method includes controlling the vehicle tailgate as described in any one of claims 1 to 8.

Images