Migration method of vehicle cabin environment, vehicle and readable medium

Abstract

The application provides a vehicle cabin environment migration method, a vehicle and a readable medium, and relates to the technical field of vehicle-mounted intelligent cabins. The method comprises the following steps: acquiring destination information and a remaining journey time in navigation information of a target vehicle; determining a target scene type based on the destination information; determining a starting time point of cabin environment migration based on the remaining journey time and a migration duration; the migration duration is used to control the duration of the change of cabin environment parameters from a current state to a target scene state; at the starting time point, controlling multiple cabin environment parameters of the target vehicle to migrate to a target cabin environment parameter set based on the migration duration, so as to adjust the cabin environment of the target vehicle to transition from the current state to the target scene state, fit the natural change rule of the user's psychological state, effectively avoid the psychological discomfort problem caused by instantaneous switching, and improve the user's vehicle cabin use experience.

Description

Technical Field

[0001] This application relates to the field of in-vehicle intelligent cockpit technology, and more specifically, to a method for migrating a vehicle cockpit environment, a vehicle, and a readable medium. Background Technology

[0002] With the rapid development of automotive intelligence, intelligent cockpits have become a standard feature in existing models, and vehicles now have multi-dimensional environmental adjustment capabilities such as seat adjustment, fragrance / ambient lighting control, music control, and air conditioning control, in order to provide users with a comfortable driving experience.

[0003] Currently, most mainstream high-end models are equipped with preset scene modes, which users can manually select such as "rest mode", "cinema mode" and "children mode". The vehicle control system will automatically adjust the parameters of the seats, fragrance / ambient lighting, music, air conditioning and other settings to the preset state.

[0004] However, since existing technologies are mostly statically preset and passively triggered, users need to manually switch modes after arriving at their destination or when parking. They cannot combine the estimated time of arrival (ETA) provided by the vehicle navigation system to initiate the environmental transition process in advance during the journey. Their mode switching is mostly completed instantly, lacking a dynamic gradual process, which can easily cause discomfort to users and reduce the user experience. Summary of the Invention

[0005] The vehicle cabin environment migration method, vehicle, and readable medium provided in this application, at the start time, based on the migration duration, control multiple cabin environment parameters of the target vehicle to gradually migrate to the target cabin environment parameter set, so as to adjust the cabin environment of the target vehicle to smoothly transition from the current state to the target scene state, which conforms to the natural change law of the user's psychological state, effectively avoids the psychological discomfort caused by instant switching, and improves the user's vehicle cabin experience.

[0006] Firstly, a method for migrating a vehicle cabin environment is provided. This method includes: acquiring destination information and remaining travel time from the navigation information of the target vehicle; determining the target scenario type based on the destination information; determining the start time point for cabin environment migration based on the remaining travel time and migration duration; the migration duration is used to control the time it takes for cabin environment parameters to change from the current state to the target scenario state; at the start time point, based on the migration duration, controlling multiple cabin environment parameters of the target vehicle to migrate to a target cabin environment parameter set, so as to adjust the cabin environment of the target vehicle to transition from the current state to the target scenario state; both the target cabin environment parameter set and the target scenario state correspond to the target scenario type.

[0007] In the above technical solution, the destination information and remaining travel time from the navigation information of the target vehicle are first obtained; based on the destination information, the target scenario type is determined; and the target cabin environment parameter set and target scenario state corresponding to the target scenario type are also simultaneously matched and determined. Then, combined with the remaining travel time and the migration time used to control the cabin environment parameters to complete the change from the current state to the target scenario state, the start time point of the cabin environment migration is determined, so as to realize the proactive and predictive triggering of the cabin environment transition process, breaking the limitation of the passive triggering of the existing technology. The environment transition can be started in advance during the trip without the user's manual operation; finally, at the start time point, based on the migration time, multiple cabin environment parameters of the target vehicle are controlled to gradually migrate to the target cabin environment parameter set, so as to adjust the cabin environment of the target vehicle to smoothly transition from the current state to the target scenario state, which conforms to the natural change law of the user's psychological state, effectively avoids the psychological discomfort caused by instant switching, and improves the user's vehicle cabin experience.

[0008] Secondly, a vehicle cabin environment migration device is provided, comprising: an acquisition module for acquiring destination information and remaining travel time from the navigation information of a target vehicle; a first determination module for determining a target scenario type based on the destination information; a second determination module for determining the start time of cabin environment migration based on the remaining travel time and migration duration; the migration duration is used to control the time for cabin environment parameters to change from the current state to the target scenario state; and a migration module for controlling multiple cabin environment parameters of the target vehicle to migrate to a target cabin environment parameter set at the start time based on the migration duration, so as to adjust the cabin environment of the target vehicle from the current state to the target scenario state; the target cabin environment parameter set and the target scenario state both correspond to the target scenario type.

[0009] Thirdly, a vehicle is provided, including a memory and a processor. The memory is used to store executable program code, and the processor is used to call and run the executable program code from the memory, causing the vehicle to perform the methods described in the first aspect or any possible implementation thereof.

[0010] Fourthly, a computer-readable storage medium is provided that stores a program or instructions that cause a computer to perform the methods described in the first aspect or any possible implementation thereof.

[0011] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and in order to make the above and other objects, features and advantages of this application more easily understood, specific embodiments of this application are given below. Attached Figure Description

[0012] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the scope of this application. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 A schematic diagram of the structure of a vehicle provided in an embodiment of this application; Figure 2 A flowchart illustrating a method for migrating a vehicle cabin environment provided in this application embodiment. Figure 1 ; Figure 3 A flowchart illustrating a method for migrating a vehicle cabin environment provided in this application embodiment. Figure 2 ; Figure 4 A flowchart illustrating a method for migrating a vehicle cabin environment provided in this application embodiment. Figure 3 ; Figure 5 A flowchart illustrating a method for migrating a vehicle cabin environment provided in this application embodiment. Figure 4 ; Figure 6 A flowchart illustrating a method for migrating a vehicle cabin environment provided in this application embodiment. Figure 5 ; Figure 7 This is a schematic diagram of a vehicle cabin environment migration device provided in an embodiment of this application. Detailed Implementation

[0013] The technical solutions in this application will be clearly and thoroughly described below with reference to the accompanying drawings. In the description of the embodiments of this application, unless otherwise stated, " / " means "or," for example, A / B can mean A or B. "And / or" in the text is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Furthermore, in the description of the embodiments of this application, "multiple" refers to two or more than two.

[0014] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature.

[0015] With the rapid development of automotive intelligence, intelligent cockpits have become standard equipment in vehicles, possessing multi-dimensional environmental adjustment capabilities such as seats, fragrance / ambient lighting, music, and air conditioning. Mainstream models also feature manually selectable preset scene modes that can automatically adjust various cockpit environmental parameters to preset states. However, existing technical solutions are all static presets and passively triggered, requiring users to manually switch modes after arriving at their destination or when parking. They cannot utilize the estimated arrival time (ETA) of the vehicle navigation system to initiate the cockpit environment transition process in advance during the journey. Furthermore, mode switching is often instantaneous, lacking a dynamic gradual transition process, which can easily cause user discomfort and reduce the driving experience. Therefore, this application proposes a vehicle cockpit environment migration scheme. The following detailed description, in conjunction with the accompanying drawings and multiple embodiments, illustrates the vehicle cockpit environment migration method, vehicle, and readable medium of this application.

[0016] Figure 1 This is a schematic diagram of the structure of a vehicle provided in an embodiment of this application. Figure 1 As shown, the vehicle 100 may include a processor 10 and a memory 120.

[0017] The memory 120 stores machine-executable instructions that can be executed by the processor 10. When the vehicle 100 is running, these machine-executable instructions are executed. The processor 10 and the memory 120 communicate via a bus. The processor 10 can execute these machine-executable instructions to implement a method for migrating the vehicle's cockpit environment.

[0018] The memory 120, processor 10, and various bus components are electrically connected directly or indirectly to enable data transmission or interaction. For example, these components can be electrically connected to each other via one or more communication buses or signal lines. The memory 120 includes at least one software functional module, which is stored or embedded in the vehicle's operating system (OS) in the form of software or firmware. This software functional module includes an executable module. The processor 10 is used to execute the executable module stored in the memory 120, such as the software functional modules and computer programs included in the vehicle cabin environment migration method.

[0019] The memory 120 may be, but is not limited to, random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), etc.

[0020] The vehicle 100 can be selected according to actual needs; for example, the vehicle 100 can be selected as a computer device. Furthermore, the vehicle 100 has software capable of executing methods for migrating the vehicle's cabin environment.

[0021] The vehicle cabin environment migration method provided in this application embodiment can be executed by the processor in the vehicle 100. The vehicle cabin environment migration method provided in this application embodiment will be explained further below. Figure 2 A flowchart illustrating a method for migrating a vehicle cabin environment provided in this application embodiment. Figure 1 .like Figure 2 As shown, the method may include: S210: Obtain the destination information and remaining travel time from the navigation information of the target vehicle.

[0022] In one possible implementation, the vehicle control system would be directly connected to the target vehicle's onboard navigation system to obtain navigation information in real time. The destination information in the navigation information is the basic input source for determining the target scene type. It can be extracted from the map service provider's API (Application Programming Interface) through the in-vehicle navigation system and includes at least the destination name and POI (Point of Interest) category (such as company, restaurant, fitness center, court, upscale coffee shop, etc.). The remaining travel time (ETA) in the navigation information is the basic data for realizing dynamic gradual migration. It is calculated in real time from the current vehicle position to the target destination (or target scene switching node) through the in-vehicle positioning system, real-time traffic condition collection module and path planning algorithm. This time is a dynamically updated value and will be dynamically adjusted according to real-time traffic conditions (such as congestion, smooth traffic) and driving speed to ensure the accuracy of the remaining travel time. It provides time dimension data support through operations such as calculating the start time point T_start and planning multi-parameter collaborative gradual trajectory curve through the atmosphere migration control engine. Moreover, the remaining travel time (ETA) can be updated dynamically through the in-vehicle navigation system in real time and adjusted synchronously with changes in driving conditions to ensure the timeliness and accuracy of subsequent operations.

[0023] S220. Based on destination information, determine the target scenario type.

[0024] In one possible implementation, since destination information is directly related to the user's travel purpose, different destinations correspond to different target emotional states and scenario needs required by the user after arrival. For example, if the destination is a business office scenario, it corresponds to the target scenarios of formal business and business leisure; if the destination is a fitness center, it corresponds to the target scenario of sports and vitality; if the destination is a family-related location or a high-end leisure scenario, it corresponds to the target scenarios of returning home, family gathering or romantic date, respectively. Therefore, only by determining the matching target scenario type based on destination information can we provide the data prerequisite for subsequently retrieving the corresponding target cabin environment parameter set from the scenario template library. This also lays the foundation for the atmosphere migration control engine to calculate the start time T_start and the multi-parameter collaborative gradual trajectory curve based on the target scenario. Ultimately, this enables the target vehicle's cabin system to provide targeted environmental and mood guidance around the user's travel purpose, achieving a smooth and dynamic transition of the cabin environment from the driving state to the target state corresponding to the destination. This helps users complete psychological preparation and precise emotional state transition before arriving at their destination, upgrading cabin environment adjustment from simple functional / safety adaptation to psychological / emotional adaptation that meets the user's actual needs. This resolves the disconnect between physical movement and psychological state transition, ultimately achieving a seamless intelligent cabin experience and enhancing the user experience. The target cabin environment parameter set includes at least: fragrance type and concentration, multi-zone lighting hue / color temperature / brightness, music genre / rhythm / volume, air conditioning temperature / airflow / air delivery mode, seat posture / massage intensity, and display screen content theme.

[0025] S230. Based on the remaining travel time and migration duration, determine the start time for the cabin environment migration.

[0026] The migration duration controls the time required for the cabin environment parameters to change from the current state to the target scenario state. The migration duration is a preset duration corresponding to the target scenario type. Specifically, for each pre-defined target scenario type, a specific fixed migration duration is assigned after scenario adaptability verification and time benchmark calibration, taking into account factors such as the actual migration operation difficulty, the scale of the migration data / objects, the required hardware and software resources, and past measured migration time data. This migration duration is then associated and stored with the corresponding target scenario type, forming a migration duration preset parameter library. For example, if the target scenario type is a business meeting, the migration duration is set to 5-10 minutes; if the target scenario type is returning home, the migration duration is set to 3 minutes.

[0027] In one possible implementation, since the migration duration is the overall cycle of environmental parameters transitioning from the current state to the parameter set corresponding to the target scenario, the remaining travel time (ETA) provides a travel time benchmark for the cabin environment migration. Using these two factors to determine the start time (T_start) allows the cabin environment migration process to precisely match the final stage of the journey, ensuring that the migration process is completed precisely when the vehicle arrives at its destination. This transforms cabin environment adjustment from the passive, manual triggering of existing technologies to proactive, predictive triggering based on navigation, allowing cabin environment migration to start in advance during the journey rather than being manually operated after the user arrives, achieving seamless interaction for cabin environment adjustment and making the experience more intelligent and smooth. Furthermore, it allows each cabin environment parameter to smoothly transition according to a unified, collaborative gradual transition curve, rather than switching instantaneously. This dynamic design in the time dimension perfectly aligns with the physiological laws of the user's psychological state transitioning from a driving state to the emotional state corresponding to the target scenario, effectively avoiding the abruptness of mode switching, significantly improving the effect of mood guidance, and ultimately helping the user gradually complete psychological preparation at the end of the journey, entering an emotional state that matches the target scenario precisely upon arrival at the destination.

[0028] S240. At the start time, based on the migration duration, control multiple cabin environment parameters of the target vehicle to migrate to the target cabin environment parameter set, so as to adjust the cabin environment of the target vehicle from the current state to the target scene state.

[0029] The target cabin environment parameter set and target scene status both correspond to the target scene type. The scene template library stores a unique target cabin environment parameter set for each target scene type, covering a full range of cabin environment parameters such as fragrance type and concentration, multi-zone lighting hue / color temperature / brightness, music genre / rhythm / volume, air conditioning temperature / airflow / air delivery mode, seat posture / massage intensity, and display screen content theme.

[0030] In one possible implementation, since the start time T_start is determined by combining the navigation ETA with the user's real-time physiological calmness, and the migration duration is also scenario-specifically calibrated according to the target scenario type and supports personalized online learning optimization, the environmental parameter migration based on this is not an instantaneous switch as in existing technologies. Instead, it allows for a coordinated and gradual change in multi-dimensional cabin environmental parameters such as fragrance, lighting, music, and temperature control. This process conforms to the physiological laws of changes in the user's psychological state, effectively avoiding the abruptness of mode switching and resulting in a better mood guidance effect. Simultaneously, because the target cabin environmental parameter set is a pre-set exclusive parameter combination for different target scenario types, the migration of multiple cabin environmental parameters to it is a multi-mode process. The intelligent cockpit achieves a deep integration of regulation and control, rather than single-point or loose parameter adjustments. This creates an immersive cabin atmosphere that is highly compatible with the target scenario, rather than simply adding functions. Ultimately, it aims to guide users to a target emotional state, allowing the cabin environment to smoothly transition from the current state to the target scenario state at the end of the journey. This helps users prepare psychologically and shift their mindset before arriving at their destination, achieving a seamless and intelligent interactive experience. Users can enter the optimal state matching the target scenario type as soon as they get off the vehicle. This results in a qualitative change for the intelligent cockpit, from responding to commands to anticipating needs, and from adjusting the environment to shaping a state. At the same time, it also helps users better manage their emotions in various situations corresponding to the target scenario.

[0031] The vehicle cabin environment migration method provided in this application first obtains the destination information and remaining travel time from the navigation information of the target vehicle; based on the destination information, the target scene type is determined; and the target cabin environment parameter set and target scene state corresponding to the target scene type are also simultaneously matched and determined. Then, combined with the remaining travel time and the migration time used to control the cabin environment parameters to complete the change from the current state to the target scene state, the start time point of the cabin environment migration is determined, so as to realize the proactive and predictive triggering of the cabin environment transition process, breaking the limitation of the passive triggering of the prior art. The environment transition can be started in advance during the trip without the user's manual operation; finally, at the start time point, based on the migration time, multiple cabin environment parameters of the target vehicle are controlled to gradually migrate to the target cabin environment parameter set, so as to adjust the cabin environment of the target vehicle to smoothly transition from the current state to the target scene state, which conforms to the natural change law of the user's psychological state, effectively avoids the psychological discomfort caused by instant switching, and improves the user's vehicle cabin experience.

[0032] Figure 3 A flowchart illustrating a method for migrating a vehicle cabin environment provided in this application embodiment. Figure 2 .like Figure 3 As shown, the above method determines the start time of cabin environment migration based on the remaining travel time and migration duration, including: S310. Determine the reference start time based on the remaining travel time and the migration duration.

[0033] In a possible implementation, determine the travel time weight coefficient k based on the migration duration. That is, the travel time weight coefficient k is not a fixed constant, and its value is completely determined by the length of the migration duration. That is, the longer the migration duration, the larger the corresponding travel time weight coefficient k; the shorter the migration duration, the smaller the corresponding travel time weight coefficient k, to ensure that the migration process can be completed within the remaining travel time ETA and avoid the situation where the vehicle arrives at the target node (or end point) before the migration ends. Since the migration duration is the fixed time consumption corresponding to the target scenario, if the migration duration is long, it means that a longer preparation time is required to start the migration. Therefore, it is necessary to increase the travel time weight coefficient k to advance the reference start time (that is, start the migration earlier); if the migration duration is short, the required preparation time is shorter. Therefore, the travel time weight coefficient k can be reduced to appropriately delay the reference start time, which not only ensures the completion of the migration but also avoids wasting system resources caused by starting the migration too early. Among them, the typical value range of the travel time weight coefficient k is [0.15, 0.4]. That is, for a remaining travel of 10 minutes, the standard migration time is between 1.5 minutes and 4 minutes. For example: the travel time weight coefficient k in the business scenario is 0.25, which means that the migration duration is long, facilitating a smooth transition from a tense driving state to a professional state; the travel time weight coefficient k in the home scenario is 0.15, which means that the migration duration is short, facilitating a direct transition from the driving state to a relaxed state; the travel time weight coefficient k in the sports scenario is 0.20, which means that the migration duration is medium, used to mobilize the state.

[0034] Then, based on the determined travel time weight coefficient k and the remaining travel time ETA, determine the reference start time through the above formula (1).

[0035] Reference start time = k × ETA Formula (1) Among them, the value range of the travel time weight coefficient k has been calibrated in advance according to the migration duration of different scenarios. Each preset migration duration corresponds to a unique travel time weight coefficient k value, and the value range of the travel time weight coefficient k value is limited to 0 < k ≤ 1, ensuring that the reference start time is always less than or equal to the remaining travel time ETA, fundamentally ensuring that the migration process can be completed within the remaining travel time.

[0036] It should be noted that if the user frequently manually switches before the migration is completed, the travel time weight coefficient k value of this scenario is reduced (for example, subtract 0.02 each time, and the lower limit is 0.15); on the contrary, if the user does not intervene and gives positive feedback afterwards, the travel time weight coefficient k value can be slightly increased (for example, the upper limit is 0.4).

[0037] S320: Obtain the target user's current calmness rating.

[0038] The calmness score S_calm is used to characterize the target user's current level of psychological calmness. It typically takes a value between 0 and 1.

[0039] In one possible implementation, physiological signals are collected via hardware sensors, such as a steering wheel capacitive sensor or a photoplethysmography (PPG) sensor built into the seat (placed in the buttock pressure area of ​​the seat cushion or the backrest contact area), to obtain the user's heart rate and HRV in real time. The time and frequency domain parameters of this HRV are key quantitative indicators for measuring the driver's stress and relaxation level, and are more sensitive than simple heart rate detection. Based on the built-in Driver Monitoring System (DMS) camera, a localized preset AI model is used to analyze the driver's facial feature points in real time without storing images, and outputs the probability distribution of emotional states in dimensions such as tension and focus, realizing the recognition of facial micro-expressions and eye movements. When the driver makes in-vehicle calls or engages in voice interaction, the in-vehicle voice module analyzes the driver's tone, speech rate, and pause frequency in real time, and provides auxiliary input for the determination of emotional state through voice biomarker analysis. Among them, the HRV index can be selected from three data that are most sensitive to emotional changes. For example, a 1-minute sliding window can be used to carry out real-time calculation: RMSSD (unit: ms) is a direct indicator of parasympathetic nerve (relaxation system) activity. Its value increases to correspond to a relaxed state at the physiological level; LF / HF ratio is the core indicator of sympathetic-vagal nerve balance. An increase in this ratio indicates that the sympathetic nerve is in an excited state, corresponding to emotional expressions such as tension, excitement, and stress; pNN50 (unit: %) refers to the proportion of adjacent PP intervals with a difference greater than 50ms. It is a highly sensitive indicator reflecting parasympathetic nerve tension. The HRV index is used to calculate the physiological arousal score. The physiological arousal score S_arousal is calculated by the following formula (2): S_arousal = 0.6 × normalize (LF / HF) - 0.4 × normalize (RMSSD) Formula (2) Specifically, a physiological arousal score (S_arousal) > 0.5 indicates a high arousal state, which may manifest as tension or excitement; a score < -0.3 indicates a low arousal state, which may manifest as relaxation or fatigue. It should be noted that the HRV index cannot distinguish valence alone; the determination of tension and excitement requires integration with other modalities for analysis.

[0040] The visual modality determines the state by extracting facial expression features based on facial action units (AUs). For example, if the frown intensity (AU4) is greater than 0.35, it is judged as tension / focus; if the zygomatic muscle activity (AU12) is greater than 0.4 and the periorbital activity (AU6) is greater than 0.2, it is judged as pleasure; at the same time, blinking frequency is considered, with a blinking frequency greater than 25 times / minute indicating tension and a blinking frequency less than 12 times / minute indicating high focus.

[0041] Among these, speech modality is determined by extracting acoustic features (i.e., speech biomarker analysis) during a call. For example, if the fundamental frequency standard deviation is >20Hz, it indicates tension / excitement; if the speech rate increases by >15% compared to the individual's baseline, it indicates tension / excitement.

[0042] The user's tension level is determined based on the physiological arousal score S_arousal, facial micro-expressions and eye movements, and voice biomarker analysis. For example, if the physiological arousal score S_arousal > 0.5, and the facial motion unit AU4 > 0.35 or the blink frequency > 25, the tension level is calculated using the following formula (3).

[0043] Tension = 0.7 × W_hrv + 0.3 × (W_vis + W_voc) Formula (3) If only the physiological arousal score S_arousal > 0.5 is met, but the driver's face is calm, then the tension level is directly assigned a value of 0.4. This situation indicates high HRV arousal but good facial expression management, which is likely an excited state.

[0044] In other cases, the determination of facial expressions and voice signals is the main basis, and the tension can be calculated using the following formula (4).

[0045] Tension = 0.2 × W_hrv + 0.8 × (W_vis + W_voc) Formula (4) Among them, W_hrv, W_vis, and W_voc in the above formulas (3) and (4) are three dynamic reliability weights. The three change in real time and satisfy the condition that the sum is 1. They are used as the credibility of the three types of signals: physiological, visual, and speech. They are used as the basis for the weighted average of the judgment results of each modality, and finally the emotional state (tension) is obtained. Among them, W_hrv is the physiological signal weight of heart rate variability (HRV), which is assigned a value of 0.5 when the signal quality is good and drops to 0.2 when there is motion interference. The signal reliability is high in scenarios such as the user sitting still and driving smoothly, while the reliability decreases in scenarios such as the user's hand being removed from the sensor or on bumpy roads due to high noise. W_vis is the visual signal weight of facial recognition by the vehicle camera (DMS), which is assigned a value of 0.4 when the lighting is good and the face is facing forward, and drops to 0.1 in other cases. The reliability is high when the light is sufficient and the driver is facing the camera directly, and the reliability decreases in scenarios such as at night, wearing sunglasses, or looking out the window. W_voc is the voice signal weight of microphone voice emotion analysis, which is assigned a value of 0.3 only during calls / voice interactions and 0 in other cases. It is only activated when the user is making in-vehicle calls or interacting with the voice, and does not participate when the user is driving silently.

[0046] In formulas (3) and (4), a tension level > 0.65 indicates a high-tension state, which will trigger strong relaxation intervention; a tension level < 0.25 and a heart rate variability index (RMSSD) higher than the individual baseline by 10% indicate an ideal relaxation state, achieving the mental goal of going home / relaxation. When the blinking frequency < 15 and the physiological arousal score (S_arousal) is in the range of [0, 0.4], it indicates a focused state, achieving the mental goal of business meetings.

[0047] Finally, based on the inverse correlation between tension and physiological arousal (S_arousal), the current calmness score (S_calm) is quantified. For example, the closer the calmness score (S_calm) is to 1, the closer the user is to an ideal calm state, with physiological arousal (S_arousal) ≤ 0.3, tension ≤ 0.25, and relaxation characteristics such as increased RMSSD and decreased LF / HF ratio in the HRV index. Conversely, the lower the calmness score (S_calm) is, the worse the user's psychological calmness, and the closer they are to a state of high arousal (tension / excitement) (physiological arousal (S_arousal) > 0.5, tension > 0.65). In other words, the calmness score (S_calm) is not derived from a single physiological indicator, but rather integrates multimodal judgment results from heart rate / HRV, facial micro-expressions, and voice biomarkers. Furthermore, as a dynamically changing quantitative value, it reflects the user's psychological state changes in real time during the journey.

[0048] It should be noted that a mood baseline can be established based on users' stress-free physiological data during their daily commutes, serving as a quantitative reference benchmark for the calmness score S_calm.

[0049] S330. Based on the current calmness score and the preset maximum / minimum time window, the baseline start time is compensated and constrained to obtain the start time point of the cabin environment migration.

[0050] The preset maximum / minimum time windows T_min and T_max are pre-defined minimum and maximum start-up time windows for migration, respectively, which limit the range of the final start-up time point T_start. Both the minimum and maximum start-up time windows T_min and T_max can be selected according to actual conditions; for example, the minimum start-up time window T_min can be selected as 2 minutes, and the maximum start-up time window T_max can be selected as 15 minutes.

[0051] In one possible implementation, because the baseline start time is only a basic time reference for cabin environment migration and does not incorporate adaptive adjustments based on the real-time physical and mental state of the occupants, directly using it as the start time point could easily lead to a mismatch with the occupants' current physical and mental perception, resulting in the cabin environment migration being too early or too late, affecting the occupants' cabin experience. The current calmness score S_calm reflects the occupants' current state of calm and is the core criterion for determining whether the timing of cabin environment migration is suitable for the occupants' physical experience. Compensating the baseline start time based on this current calmness score S_calm allows the cabin environment migration start time T_start to align with the occupants' real-time physical and mental needs, achieving a match between environmental control and occupants' physical experience. Simultaneously, a preset maximum / minimum time window is used. The system can define the effective time range of the calmness score S_calm, avoiding interference from invalid or abnormal scores in extreme time dimensions on the start-up time compensation. Furthermore, by constraining the compensation process of the baseline start-up time through the preset maximum and minimum time window, it can limit the adjustment boundary of the start-up time point T_start, preventing the start-up time from deviating from the reasonable range due to over-compensation. This ensures that the adjustment of the cabin environment migration start-up time point T_start is always within a controllable and reasonable time range. Ultimately, the obtained cabin environment migration start-up time point T_start can not only adapt to the current calmness state of the occupants, but also has temporal rationality and stability, ensuring the scientific nature and comfort of the cabin environment migration process and improving the accuracy of cabin environment control.

[0052] The vehicle cabin environment migration method provided in this application first determines the baseline start time for cabin environment migration based on the remaining travel time and migration duration; then, it obtains the target user's current calmness score; subsequently, based on the current calmness score and a preset maximum / minimum time window, it performs targeted compensation and range constraints on the baseline start time, and finally determines the actual start time of cabin environment migration. This ensures that the start time setting not only fits the objective duration of the trip but also dynamically adapts to the user's personalized psychological state, effectively avoiding unnecessary interference caused by starting migration too early or insufficient transition of mood caused by starting too late. This lays a time foundation for the smooth transition of the cabin environment to the target state and the steady guidance of the user's mood.

[0053] Optionally, the above method compensates for and constrains the baseline start-up time based on the current calmness score and a preset maximum / minimum time window to obtain the start-up time point of the cabin environment migration, including: Calculate the difference between the current calmness score and the preset ideal calmness score.

[0054] The preset ideal calmness score can be selected according to the actual situation. For example, the preset ideal calmness score can be selected as 1.

[0055] In one possible implementation, the difference between the current calmness score S_calm and the preset ideal calmness score is calculated using the above formula (5) based on the current calmness score S_calm and the preset ideal calmness score.

[0056] Difference = 1 - S_calm (Formula 5) This difference reflects the gap between the user's current calmness and the ideal calmness. The larger the difference, the greater the deviation, and the smaller the difference, the less the deviation.

[0057] The compensation time is obtained by multiplying the difference by the preset state compensation coefficient.

[0058] The preset state compensation coefficient β represents the additional time compensation required due to user agitation. When the user is completely agitated (i.e., the current calmness score S_calm is 1), it adds an extra time to the baseline start time. This determines the level of intervention from the vehicle control system in response to the user's current unfavorable state. The typical value of the preset state compensation coefficient β is [1.0, 5.0] (unit: minutes). This means that if the user is extremely stressed, the vehicle control system can initiate the migration process 1 to 5 minutes earlier, providing more time for calming and guidance. For example, a preset state compensation coefficient β of 3.0 to 5.0 for sensitive users indicates a high need for emotional guidance and requires a longer adjustment time; a preset state compensation coefficient β of 1.0 to 2.0 for stable users indicates strong self-regulation ability and only requires mild intervention.

[0059] It should be noted that if the user remains unsettled despite a considerable amount of time, the preset state compensation coefficient β should be increased in the next similar scenario to provide earlier and longer intervention. Conversely, if the user calms down quickly, the preset state compensation coefficient β can be appropriately decreased to avoid unnecessary premature interruption.

[0060] In one possible implementation, the difference between the current calmness score obtained from the above steps and the preset ideal calmness score is multiplied by the preset state compensation coefficient β after personalized calibration for the current user. The product obtained by the following formula (6) is the compensation time amount.

[0061] Compensation time amount = difference × β = (1 - S_calm) × β Formula (6) The amount of compensation time is positively correlated with the degree of calmness deviation. That is, the more the user's current calmness deviates from the ideal state, the greater the amount of compensation time. The purpose is to reserve more time for users whose calmness does not meet the standard to adjust their mood and cabin environment.

[0062] The first start time is obtained by summing the baseline start time and the compensation time.

[0063] In one possible implementation, the first start time is obtained by first calculating the sum of the baseline start time and the compensation time using the following formula (7).

[0064] First startup time = Baseline startup time + Compensation time = k × ETA + β × (1 - S_calm) Formula (7) Based on the preset maximum and minimum time window, the first start time is compensated and constrained to obtain the start time point of the cabin environment migration.

[0065] In one possible implementation, the first start time T_start of the cabin environment migration is obtained by compensating and constraining the first start time based on a preset maximum and minimum time window using the following formula (8).

[0066] T_start = max(T_min, min(T_max, k × ETA + β × (1 - S_calm))) Formula (8) According to the above formula (8), the first start time is limited to the preset minimum start time window T_min (e.g., 2 minutes) and maximum start time window T_max (e.g., 15 minutes). The final value that meets the interval limit is the actual compensated start time T_start when the cabin environment parameters migrate from the current state to the target cabin environment parameter set.

[0067] The vehicle cabin environment migration method provided in this application first calculates the difference between the current calmness score and the preset ideal calmness score; then, it multiplies this difference with a preset state compensation coefficient to obtain the compensation time; next, it obtains the first start time based on the sum of the baseline start time and the compensation time; finally, it compensates and constrains the first start time based on the preset maximum and minimum time window to obtain the start time point of cabin environment migration. Thus, this application uses the quantitative difference in calmness scores as the basis for compensation, combined with a preset state compensation coefficient, to achieve accurate calculation of the compensation time. Simultaneously, it effectively constrains the compensated first start time based on the preset maximum and minimum time window. This ensures that the start timing of cabin environment migration is highly compatible with the current actual calmness state, while avoiding the problem of the start time deviating from a reasonable range due to excessively large or small compensation time, effectively improving the scientific and intelligent level of determining the start timing of cabin environment migration.

[0068] Figure 4 A flowchart illustrating a method for migrating a vehicle cabin environment provided in this application embodiment. Figure 3 .like Figure 4 As shown, the above method also includes: S410. During the migration of multiple cockpit environmental parameters to the target cockpit environmental parameter set, determine whether there is a perception conflict in the gradual trajectory of the multiple cockpit environmental parameters.

[0069] Perceptual conflict is defined as the moderating effect of at least two cabin environmental parameters on the same emotional dimension in opposite directions (such as cancellation or interference). For example, playing upbeat music to invigorate versus releasing relaxing aromatherapy to soothe emotions.

[0070] In one possible implementation, during the gradual adjustment of various cabin environmental parameters from their current values ​​to the target values ​​corresponding to the target cabin environmental parameter set, the gradual trajectory curves of all participating cabin environmental parameters are detected and judged. Specifically, the gradual trajectory curves are used as the detection object to determine whether there is a perception conflict within them, thus obtaining a judgment result indicating whether a perception conflict exists. Here, the gradual trajectory curve refers to the curve showing the path and process of each cabin environmental parameter gradually adjusting from its current value to its target value.

[0071] For example, the influence weight of music intensity on tension is +0.7, and the influence weight of relaxing aromatherapy on tension is -0.6. When the influence weights of these two environmental parameters (such as music and aromatherapy) on the same mood dimension (such as tension) have opposite signs, it is determined whether the sum of the absolute values ​​of the influence weights of individual environmental parameters on the same mood dimension (such as |+0.7|+|-0.6|) is greater than 0.3. If the sum of the absolute values ​​is greater than 0.3, it is judged as a potential perceptual conflict.

[0072] S420. If a perception conflict exists, determine the adjustment strategy for the cockpit environment parameters in conflict based on the parameter priority defined by the target scenario type.

[0073] The priority of parameters defined by the target scene type can be found in Table 1 below.

[0074] Table 1 shows the parameter priorities defined for the target scene type.

[0075] In this context, the first priority parameter refers to the parameter that most directly affects the target's emotional dimension (such as focus, relaxation, or excitement) and has the least interference. The second priority parameter refers to the parameter that can enhance the effect of the first priority parameter or compensate for its shortcomings. Auxiliary parameters refer to parameters that provide background support and enhance immersion.

[0076] In one possible implementation, if there is a perception conflict in the gradual trajectory of multiple cockpit environmental parameters, then for the cockpit environmental parameters that have a perception conflict, based on the parameter priority defined by the target scenario type, that is, different target scenario types have pre-set cockpit environmental parameter priority rules, a corresponding adjustment strategy is formulated for these conflicting cockpit environmental parameters, and finally a specific adjustment strategy scheme for conflicting cockpit environmental parameters is obtained.

[0077] S430, based on the adjustment strategy, executes a gradual trajectory of the conflicting cabin environment parameters.

[0078] In one possible implementation, based on a defined adjustment strategy, the original gradual trajectory curve is adapted and adjusted. The adjusted gradual trajectory curve is then executed, allowing the cabin environment parameters that have experienced perceptual conflicts to continue migrating to the target cabin environment parameter set according to the adjusted gradual trajectory curve. The entire process revolves around the cabin environment parameters corresponding to the perceptual conflicts, with the adjustment strategy as the execution criterion, ultimately achieving the orderly migration of the cabin environment parameters corresponding to the perceptual conflicts to the target parameter set.

[0079] For example, when migrating from commuting to a formal business setting, the user is currently under stress, and the goal is to reduce the user's stress and increase their focus.

[0080] The initial instructions of the vehicle control system are as follows: the music switch is to soothing classical music to reduce tension (weight -0.5), the fragrance releases refreshing cedar scent to improve focus (weight +0.4, or slightly increase tension +0.1), and the lights increase the color temperature to cool white to improve focus (weight +0.3). It is determined that there is a slight perceptual conflict between music and fragrance in terms of "tension" (i.e., -0.5 vs +0.1).

[0081] Based on the priority rules for formal business scenarios in Table 1 above, the auditory field (music) has the first priority, and the visual field (lighting) has the second priority. The vehicle control system then arbitrates and makes a decision: ensuring a smooth transition to soothing classical music; due to the minor conflict in perceived tension, the fragrance scheme is still implemented but at a 50% lower concentration to mitigate its potential impact on increasing tension, while retaining its invigorating effect; and the lighting color temperature adjustment is executed as planned. Ultimately, the vehicle control system completes the execution of commands across all scenarios in a manner that prioritizes the auditory field and supplements the olfactory field with limitations, achieving a smooth transition of the user's overall mood to the target state.

[0082] It should be noted that the perceptual conflicts mentioned above also include two other typical conflicts in practical applications: resource conflicts and security conflicts. These three types of conflicts together constitute the main conflict types in relevant applications. Resource conflicts refer to conflicts arising from multiple parameter adjustment actions vying for the same physical resource. The corresponding resource conflict threshold is determined based on physical constraints such as bus load and actuator response time. For example, increasing ventilation to diffuse fragrance versus decreasing ventilation to maintain music clarity creates a conflict due to competition for the physical resource of ventilation. Security conflicts refer to conflicts arising from parameter adjustment actions that may endanger driving safety. Examples include situations where lights are too dim, music suddenly becomes too loud, or fragrances cause discomfort to passengers.

[0083] For example, a three-level arbitration process is set up. First, it determines whether there is a safety conflict. If there is a safety conflict, the safety cockpit environmental parameters take unconditional priority, and related dangerous operations are prohibited or significantly reduced. If there is no safety conflict, it then determines whether there is a perception conflict. If there is a perception conflict, it first checks whether the cockpit environmental parameters corresponding to the perception conflict involve the environmental carrier of the current scene. If one is an environmental carrier and the other is not, the environmental carrier wins, and the non-environmental carrier is adjusted to a neutral value or delayed. If both are environmental carriers or neither is an environmental carrier, it enters the arbitration stage of maximizing the objective function, calculates the tracking error of each cockpit environmental parameter set to the ideal mental path, and selects the scheme with the smallest tracking error for execution. If there is no perception conflict, it finally determines whether there is a resource conflict. If there is a resource conflict, it is handled by time slicing or phased execution. For example, the environmental carrier is adjusted and resources are occupied in the first 30 seconds, and the auxiliary parameters are adjusted in the last 30 seconds. Among them, the ideal mental path refers to the path that the vehicle control system predefines for each type of scenario template. For example, the ideal path for a formal business setting is: the tension level gradually decreases from the initial value to a moderately low level, and the focus level gradually increases.

[0084] The vehicle cabin environment migration method provided in this application performs perceptual conflict determination on the gradual change trajectory curves of each current cabin environment parameter during the migration of multiple cabin environment parameters to a target cabin environment parameter set. Specifically, perceptual conflict refers to at least two cabin environment parameters having opposite regulatory effects on the same emotional dimension. If a perceptual conflict is determined, an adjustment strategy for the conflicting cabin environment parameters is specifically determined based on the parameter priority defined by the target scene type. The gradual change trajectory of the corresponding conflicting parameters is then executed according to the adjustment strategy. This effectively avoids the problem of user emotional experience fragmentation caused by perceptual conflict during parameter gradual change migration, ensures the matching degree between cabin environment parameter regulation and the emotional adaptation requirements of the target scene, and makes the gradual change process of cabin environment parameters more reasonable and scientific, ultimately improving the user's cabin environment experience quality.

[0085] Figure 5 A flowchart illustrating a method for migrating a vehicle cabin environment provided in this application embodiment. Figure 4 .like Figure 5 As shown, the method described above determines the target scene type based on destination information, including: S510. Based on destination information, determine the corresponding multiple information sources.

[0086] In one possible implementation, based on destination information and using that destination information as a matching benchmark, multiple information sources suitable for the destination information are filtered, identified, and selected through preset association rules, scene matching logic, or information source mapping relationships. These multiple information sources include at least: navigation POIs, calendar / schedule semantics, user historical behavior models, and manual tags. Navigation POIs include at least: the destination name and POI category, where the POI category is obtained from the map service provider's API, such as "company," "restaurant," or "fitness center." Calendar / schedule semantics include at least: the destination time, the calendar event title matching the location, the description, and the participants. The user historical behavior model refers to the scene patterns that the user manually selected or successfully applied by the system when arriving at this location or similar locations in the past. Manual tags are the "expected atmosphere" that the user actively selects via voice or on-screen buttons after navigation settings.

[0087] The analysis of navigation POIs involves several steps. First, based on the POI-scene mapping table, the POI category is converted into the corresponding initial scene probability. For example, a law firm can be mapped to {Business Formal: 0.85, Business Casual: 0.10, Other: 0.05}. Then, the base confidence score C_poi for the navigation POI source is set. This base confidence score C_poi can be dynamically adjusted according to the actual situation. For example, the base confidence score C_poi is generally set to 0.8. If the POI category is broad (such as a building), the base confidence score C_poi is reduced by 0.7 times; if the POI is the location of a user's home, the base confidence score C_poi is increased by 1.2 times because the base confidence score C_poi for home scenarios has a higher weight.

[0088] The analysis of calendar / schedule semantics involves several steps: First, a local NLP (Natural Language Processing) model is used to analyze the semantic text of the calendar / schedule. Then, keyword matching is performed based on a pre-defined dictionary. For example, "interview" and "negotiation" are matched as formal business scenarios; "dinner" and "birthday" are matched as family / social scenarios; and "fitness" is matched as sports scenarios. Participant analysis is also conducted, assigning differentiated weights to different scenarios such as internal meetings and client visits. Furthermore, a baseline confidence level C_cal is set for the calendar / schedule semantic source. The criteria are: 0.9 for exact matching calendar events; 0.6 for fuzzy matching or events with similar times; and 0.1 for no relevant events, in which case the information source hardly participates in the decision-making process.

[0089] Among them, the user's historical behavior model is analyzed: a unique historical scene selection distribution is maintained for each location or POI category. For example, in the valid records of a user's past 10 visits to "XX Fitness Center", the "Sports Vitality" mode was selected 8 times and the "Leisure" mode was selected 2 times. The corresponding scene selection probability vector {Sports Vitality: 0.8, Leisure: 0.2} is generated for this location; the basic confidence C_hist of the corresponding user historical behavior model source is calculated according to the following formula (9): C_hist = min(0.95, log10(N+1) × 0.3) Formula (9) Where N represents the number of valid historical records for that location.

[0090] The baseline confidence level C_hist increases with the increase of valid historical data for a location, and is capped at 0.95. For locations visited for the first time, since there are no valid historical records, the corresponding baseline confidence level C_hist will be at a very low level.

[0091] The analysis of manual labels involves converting the expected atmosphere selected via voice or on-screen buttons into a deterministic probability vector. For example, if "relax" is selected, the corresponding probability vector is {relax: 1.0}. The base confidence level C_manual of the manual label source is fixed at the highest priority of 1.0. Once this base confidence level C_manual exists, it will cover and dominate all other sources.

[0092] S520: Based on multiple information sources, obtain probability data corresponding to each candidate scenario type.

[0093] In one possible approach, all candidate scenario types to be evaluated are first identified. Then, for each candidate scenario type, probability data corresponding to that candidate scenario type under each information source is obtained from multiple selected information sources through data extraction, collection, mining, or quantitative analysis. That is, each candidate scenario type will be matched with a set of probability data output by multiple information sources. The probability data is a quantitative representation of the correlation and matching degree of each information source with the candidate scenario type. The core of the whole process is to complete the data collection and association of the correspondence between information sources and "candidate scenario type-probability data".

[0094] S530. Weighted fusion of probability data from multiple information sources corresponding to each candidate scenario type is performed to obtain the evaluation probability of each candidate scenario type.

[0095] In one possible approach, for a single candidate scenario type, its probability data from all associated information sources is first aggregated to form an independent dataset. Then, based on the preset weights of each information source, a weighted fusion rule is formulated, and weighted calculation and fusion processing are performed on the multiple sets of probability data for the candidate scenario type. The above weighted fusion process is completed independently for all candidate scenario types. After processing, each candidate scenario type will obtain a unique evaluation probability that integrates data from multiple information sources, thus obtaining a comprehensive evaluation value for each candidate scenario type.

[0096] For example, the evaluation probability P_final(scene) for each candidate scene type is calculated step by step according to the priority rules: If manual intervention is the highest priority, and the basic confidence level C_manual of the manually labeled source is 1.0, the vector manually selected by the user is directly assigned to the evaluation probability P_final of each candidate scene type, and the scene probability decision ends. If there is no manual intervention, the multi-source weighted fusion method is used to calculate using the following formula (10).

[0097] W_i = C_i × F_i formula (10) Wherein, W_i is the weight of each information source i, and this weight is not fixed, but is determined by its base source confidence C_i and information freshness F_i. The information freshness F_i of historical data can be obtained by the following formula (11).

[0098] F_i = exp(-λ × Δt) Formula (11) Where Δt is the time (in months) since the last record, and λ is the decay factor (e.g., 0.2), used to achieve weight decay of long-term historical data.

[0099] Based on this, the final evaluation probability is obtained through conflict resolution and weighted averaging. That is, for each candidate scene_k, its final evaluation probability P_final(scene_k) is the sum of the products of the weights of all information sources and the corresponding evaluation probabilities, divided by the sum of the weights of all information sources. It can be calculated by the following formula (12): P_final(scene_k) = Σ [ W_i × P_i(scene_k) ] / Σ W_i formula (12) S540. Calculate the preset threshold range where the maximum difference between the evaluation probabilities of each candidate scene type lies, and obtain the decision mode of the target scene type.

[0100] The preset threshold range can be selected according to the actual situation.

[0101] In one possible implementation, after calculating the evaluation probability P_final for each candidate scenario type, the vehicle control system enters the final decision stage. In this decision stage, the evaluation probabilities P_final of multiple candidate scenario types are first screened to obtain the highest and second highest evaluation probabilities P_final. Then, based on the highest and second highest evaluation probabilities P_final, the decision confidence Conf_decision is calculated using the following formula (13).

[0102] Conf_decision = P_final_max - P_final_2nd formula (13) Where P_final_max is the highest evaluation probability; P_final_2nd is the second highest evaluation probability.

[0103] The decision confidence score (Conf_decision) characterizes the reliability of the vehicle control system's decisions. A higher Conf_decision score indicates greater consistency among information sources, thus higher decision reliability.

[0104] Then, based on multiple different threshold intervals preset by the vehicle control system, the calculated maximum difference is numerically matched and interval determined with each preset threshold interval to determine the specific threshold interval into which the maximum difference falls. At the same time, the system presets a one-to-one correspondence between "threshold intervals and decision modes". Based on the determined threshold intervals, the corresponding decision mode for the target scenario type is matched and obtained. The core of the whole action is to select the decision mode by analyzing the numerical difference of the probability assessment and combining it with the preset threshold intervals.

[0105] S550: Based on the decision-making model, determine the target scenario type.

[0106] In one possible implementation, the mapping relationship between the preset decision mode and the scene type determination rule in the vehicle control system is first retrieved (i.e., different decision modes correspond to different candidate scene type selection logic). Then, according to the scene type selection rule that matches the currently determined decision mode in the mapping relationship, the evaluation probability of all candidate scene types is analyzed and processed in a targeted manner. For example, the selection rule can be "take the candidate scene type corresponding to the maximum value of the evaluation probability" or "take the candidate scene type whose evaluation probability falls into the preset effective range". Finally, a unique target scene type is selected and determined from all candidate scene types.

[0107] The vehicle cabin environment migration method provided in this application first determines multiple information sources based on destination information, ensuring the richness and comprehensiveness of scenario probability data acquisition through the dimensionality of multiple information sources. Then, based on these multiple information sources, it acquires probability data corresponding to each candidate scenario type. Subsequently, it performs weighted fusion on the probability data from multiple information sources for each candidate scenario type, effectively avoiding the bias problem of a single information source and improving the accuracy of probability assessment, thereby obtaining the assessment probability of each candidate scenario type. Next, it calculates the maximum difference between the assessment probabilities of each candidate scenario type and determines the preset threshold range in which the maximum difference lies, thus obtaining the decision mode of the target scenario type. By matching the quantitative difference with the threshold range, the scenario decision has a clear quantitative basis, realizing the scientific and standardized determination of the decision mode. Finally, based on this decision mode, it determines the target scenario type and outputs accurate target scenario type results based on the standardized decision mode, significantly improving the reliability, accuracy, and adaptability of scenario type determination.

[0108] Optionally, the above method determines the target scenario type based on decision-making patterns, including: If the decision-making model is that the maximum difference is greater than or equal to the first threshold, then the candidate scenario type with the highest evaluation probability is determined as the target scenario type.

[0109] The maximum difference is the decision confidence level Conf_decision; the first threshold can be selected according to the actual situation, for example, the first threshold can be selected as 0.4.

[0110] In one possible implementation, the obtained maximum difference (i.e., decision confidence Conf_decision) is compared with a selected first threshold (e.g., 0.4). When the comparison result shows that the maximum difference (i.e., decision confidence Conf_decision) is greater than or equal to the first threshold (e.g., 0.4), this numerical comparison result is the currently triggered decision mode. After determining that the current decision mode meets the condition of "maximum difference greater than or equal to the first threshold", the subsequent target scene type determination action is continued. First, from all candidate scene types to be screened, the candidate scene type with the highest evaluation probability value obtained in the previous evaluation stage (i.e., the highest evaluation probability P_final_max) is extracted. Then, the candidate scene type with the highest evaluation probability is formally determined as the target scene type finally required for this scene determination.

[0111] For example, when in a high-confidence interval (i.e., Conf_decision ≥ 0.4), the vehicle control system will perform the following operations: run silently throughout, automatically select the scene mode corresponding to the highest evaluation probability P_final_max, and simultaneously initiate the atmosphere transition process. For instance, if the destination is "court," the calendar shows "court hearings," and past court visits have consistently matched "business formal," then if the highest evaluation probability P_final_max is {business formal: 0.92, others: 0.08} and Conf_decision = 0.84, the high-confidence interval determination condition is met, and the vehicle control system will execute the operation according to the above rules.

[0112] If the decision mode is that the maximum difference is less than the first threshold and greater than or equal to the second threshold, a confirmation prompt will be generated and output before the start time. After receiving the confirmation response from the target user, the candidate scenario type with the highest evaluation probability will be determined as the target scenario type.

[0113] The second threshold can be selected according to the actual situation; for example, the second threshold can be selected as 0.2.

[0114] In one possible implementation, the vehicle control system determines that the maximum difference (i.e., the decision confidence Conf_decision) is less than a first threshold (e.g., 0.4), and simultaneously satisfies the dual condition that the value is greater than or equal to a second threshold (e.g., 0.2). At this point, the corresponding decision mode is triggered, and the vehicle control system will perform the target scenario type determination action in two steps: First, the vehicle control system needs to actively generate the corresponding confirmation prompt information before the preset start time T_start arrives, and output the confirmation prompt information to the interactive terminal that the target user can perceive; Second, the vehicle control system remains in a waiting state until it receives the confirmation response from the target user for the confirmation prompt, and then performs the target scenario type determination action, identifying the candidate scenario type with the highest evaluation probability value (i.e., the highest evaluation probability P_final_max) among all candidate scenario types as the final target scenario type.

[0115] For example, the criterion for the medium confidence interval is 0.2 ≤ Conf_decision < 0.4. Under this interval, the vehicle control system will execute the scenario mode corresponding to the highest evaluation probability P_final_max and complete the confirmation through lightweight interaction. Specifically, a non-modal prompt will be displayed on the instrument panel or HUD (Heads-Up Display), such as "Preparing a business leisure atmosphere for you?". This prompt will disappear automatically after 3 seconds. Users can also quickly confirm with a "OK" gesture. For example, in scenarios where the destination is "high-end coffee shop", there are no relevant events on the calendar and little historical data, the highest evaluation probability P_final_max is {Business leisure: 0.55, Romantic date: 0.35, Other: 0.10}, and Conf_decision takes a value of 0.20, which means that the operation rules of this medium confidence interval apply.

[0116] If the decision mode is that the maximum difference is less than the second threshold, a selection interface is generated and output, and the candidate scene type selected by the user in the selection interface is determined as the target scene type.

[0117] In one possible implementation, when the vehicle control system determines that the maximum difference (i.e., the decision confidence Conf_decision) is less than a second threshold (e.g., 0.2), it triggers the corresponding decision mode. The vehicle control system will then perform the target scenario type determination action in two steps: First, the vehicle control system actively generates a selection interface containing candidate scenario types and outputs this interface to the interactive terminal that the target user can operate; second, the vehicle control system no longer uses the evaluation probability as the basis for judgment, but instead obtains the candidate scenario type result that the target user independently selects in the selection interface, and directly recognizes the candidate scenario type selected by the user as the final target scenario type.

[0118] For example, the criterion for determining a low-confidence interval is Conf_decision < 0.2. In this interval, the vehicle control system will proactively initiate a query, explicitly providing the user with 2-3 options with the highest probabilities via voice or a pop-up window on the central screen. For instance, in a scenario where the destination is a public park and the travel time is a weekend afternoon, the highest estimated probability P_final_max is {family leisure: 0.40, sports activity: 0.35, romantic date: 0.25}, and Conf_decision is 0.05, which meets the low-confidence interval criterion. Based on this, the vehicle control system will ask: "Is your trip for family fun, sports and fitness, or something else? Please select." The vehicle cabin environment migration method provided in this application matches the corresponding decision mode based on the comparison results of the maximum difference with the first threshold and the second threshold, thereby differentiating the target scenario type determination strategy: If the decision mode is that the maximum difference is greater than or equal to the first threshold, the candidate scenario type with the highest evaluation probability is determined as the target scenario type, realizing rapid automatic decision-making of cabin scenario type and effectively improving the execution efficiency of scenario matching; If the decision mode is that the maximum difference is less than the first threshold but greater than or equal to the second threshold, a confirmation prompt is generated and output before the start time, and after receiving the confirmation response from the target user, the candidate scenario type with the highest evaluation probability is determined as the target scenario type. Through the secondary confirmation mechanism of human-computer interaction, the efficiency of scenario decision-making and matching accuracy are taken into account, avoiding the misjudgment problem caused by single probability evaluation; If the decision mode is that the maximum difference is less than the second threshold, a selection interface is generated and output, and the candidate scenario type selected by the user in the selection interface is determined as the target scenario type. In the case where there is no obvious optimal solution in the probability evaluation, the user's autonomous selection permission is opened up, ensuring the personalization and rationality of cabin scenario selection.

[0119] Figure 6 A flowchart illustrating a method for migrating a vehicle cabin environment provided in this application embodiment. Figure 5 .like Figure 6 As shown, the above method also includes: S610: During the migration of multiple cockpit environmental parameters to the target cockpit environmental parameter set, acquire the target user's emotional perception signal.

[0120] In one possible implementation, migrating to the target cabin environment parameter set refers to the process by which the cabin domain controller or vehicle controller (VCU) gradually adjusts and dynamically transitions the cabin environment parameters from the current actual operating state to the preset target parameter set corresponding to the target scenario, according to the preset target scenario type (such as commuting, rest, entertainment, fatigue relief, etc.). This process is a continuous dynamic adjustment process, rather than a one-time parameter switch. Throughout this dynamic migration process, the vehicle control system relies on real-time data acquisition from multi-dimensional sensing devices deployed within the cabin. These sensing devices include sensors for collecting physiological signals (such as heart rate sensors, skin conductance sensors, electroencephalogram sensors, and respiratory rate sensors, which can be integrated into the steering wheel, seats, seat belts, etc.), cameras for collecting visual signals (capturing the target user's facial micro-expressions, eye state, facial muscle relaxation, etc.), and microphones for collecting voice signals (collecting the target user's voice tone, speech rate, and intonation, etc.). The "target user" refers to the core user in the cabin (usually the driver, but can also be selected as the front passenger or rear passenger depending on system settings). "Emotional perception signals" refer to the raw data or pre-processed characteristic signals collected by the aforementioned sensing devices that can directly or indirectly reflect the target user's real-time emotional state. The vehicle control system continuously and in real-time acquires these signals during the parameter migration process to ensure dynamic monitoring of the user's emotions.

[0121] S620: Based on the difference between the emotion perception signal and the target emotion perception signal corresponding to the target scene type, adjust at least one of the multiple cockpit environment parameters.

[0122] In one possible implementation, since the core objective of adjusting cabin environment parameters is to achieve precise adaptation between the cabin environment and the target scenario, and the target emotion perception signal is a quantitative representation of the emotional state that the user should match in the target scenario, while the user's actual emotion perception signal directly reflects their current true emotional state, the difference between the two essentially represents a deviation between the user's current emotional state and the matching emotional state required by the target scenario. If the cabin environment parameters are not adjusted to address this deviation, the cabin mode (such as business leisure, romantic date, etc.) executed by the vehicle control system based on the scenario will not truly match the user's experience. Emotional needs in the target scenario are difficult to match with the value of a scenario-based cabin environment. However, by identifying the differences between the two and adjusting at least one cabin environment parameter accordingly, the discrepancy between the user's current emotion and the emotion appropriate for the target scenario can be accurately bridged. This guides the user's emotional state to gradually align with the target emotional state corresponding to the target scenario, creating a dual match between the cabin environment parameter settings, the target scenario, and the user's actual emotions. This ensures the scientific and precise control of the cabin environment while also enhancing the humanization and adaptability of the scenario-based cabin experience. Ultimately, it ensures that the cabin modes implemented in different target scenarios meet the user's actual emotional perception and scenario experience needs.

[0123] The vehicle cabin environment migration method provided in this application acquires the target user's emotional perception signal in real time during the migration of multiple cabin environment parameters to a target cabin environment parameter set. This emotional perception signal is then compared with the target emotional perception signal corresponding to the target scene type. Based on the difference, at least one parameter among the multiple cabin environment parameters is dynamically adjusted. This method enables real-time capture and precise response to user emotional perception during the cabin environment parameter migration stage, effectively avoiding perceptual conflicts caused by the mismatch between environmental changes and the user's actual emotional perception during parameter migration. This makes the adjustment of cabin environment parameters more aligned with the user's real emotional needs, improving the dual adaptability of the cabin environment to the target scene and user emotions. Simultaneously, it ensures the dynamic rationality and humanization of cabin environment parameter migration, thereby optimizing the user's cabin experience.

[0124] Optionally, in the above method, based on the difference between the emotion perception signal and the target emotion perception signal corresponding to the target scene type, at least one of the multiple cockpit environment parameters is adjusted, including: The target emotion dimension is determined based on the difference between the emotion perception signal and the target emotion perception signal corresponding to the target scene type.

[0125] Among them, the emotion perception signal is a signal (such as physiological electrical signal, facial expression signal, voice emotion signal, etc.) that is collected in real time and can reflect the current emotional state of the people in the cabin (such as the driver and passengers); the target emotion perception signal is a standard perception signal that is pre-set according to different scenario types (such as commuting scenario, rest scenario, business scenario, etc.) and corresponds to the most suitable emotion of the people in the cabin in that scenario. Each target scenario type corresponds to a unique or a set of matching target emotion perception signals.

[0126] In one possible implementation, the current emotion perception signal is first acquired through in-cabin acquisition devices (such as physiological sensors, cameras, and microphones). Then, based on the current target scene type, the target emotion perception signal corresponding to that scene is retrieved from a pre-set database. Subsequently, signal processing algorithms (such as difference calculation and feature comparison) are used to calculate the specific differences (such as signal amplitude differences and feature parameter deviations) between the current emotion perception signal and the target emotion perception signal. Finally, based on this difference, the specific dimension in which the current emotion deviates from the target emotion is determined, i.e., the target emotion dimension is identified. This emotion dimension can include: pleasure, arousal, and tension. For example, if the difference is reflected in the current arousal being lower than the target arousal, then the target emotion dimension is arousal.

[0127] Based on the target scenario type and target emotion dimension, at least one target adjustment cabin environment parameter and corresponding adjustment direction are determined from the preset adjustment rules.

[0128] Among them, the preset adjustment rules are a set of rules that are pre-established and stored in the control system, covering all scene types, emotional dimensions and cabin environment parameter adjustment logic. The set of rules clearly defines different combinations of "target scene type + target emotional dimension" and the corresponding cabin environment parameters that need to be adjusted (cabin environment parameters may include temperature, brightness, volume, fragrance type, seat angle, ambient light color, etc.) and the adjustment direction of the parameter (such as increasing the temperature, decreasing the brightness, decreasing the volume, switching to a soothing fragrance, etc.).

[0129] In one possible implementation, based on a defined target scenario type (such as commuting or rest) and target emotional dimension (such as arousal or pleasure), these two parameters are used as search criteria to perform precise matching within a pre-defined adjustment rule base, filtering out all adjustable cabin environment parameters corresponding to the scenario type and emotional dimension. Finally, at least one cabin environment parameter is selected as the target adjustment from the filtered parameters. This selection can be based on parameter priority, adjustment feasibility, etc. Simultaneously, the adjustment direction corresponding to this cabin environment parameter (i.e., the adjustment trend of the corresponding target adjustment parameter (such as increasing, decreasing, or switching types)) is obtained.

[0130] Based on the differences, determine the intensity adjustment amount of the cabin environmental parameters for the target adjustment.

[0131] Among them, the intensity adjustment amount refers to the specific range, size or level of the target adjustment parameter that needs to be adjusted (such as temperature adjustment of 1℃, brightness adjustment of 20%, volume adjustment of 10dB, fragrance concentration adjustment of 3 levels, etc.), which is used to clarify the degree of adjustment and avoid under-adjustment or over-adjustment.

[0132] In one possible implementation, the calculated difference data (such as difference amplitude, deviation ratio, etc.) is first called, and then the difference data is converted into specific intensity adjustment amounts according to the preset "difference-intensity correspondence" (this correspondence can be stored in the vehicle control system in advance; for example, the larger the difference, the larger the intensity adjustment amount; the smaller the difference, the smaller the intensity adjustment amount, which can be achieved through linear mapping, step correspondence, and other algorithms). The correspondence logic between difference and intensity adjustment amount needs to be preset, and the difference must be strictly used as the sole basis to ensure that the determination of intensity adjustment amount is directly related to the degree of emotional deviation.

[0133] Based on the adjustment direction and intensity adjustment amount, at least one of the multiple cabin environment parameters is adjusted.

[0134] In one possible implementation, a defined adjustment direction and intensity adjustment amount are first invoked, and these two parameters are integrated into a specific control command (e.g., "Temperature adjustment direction: Increase, Intensity adjustment amount: 1℃" or "Brightness adjustment direction: Dim, Intensity adjustment amount: 20%"). Then, among all the adjustable cabin environment parameters in the current cabin, the parameter that matches the target adjustment parameter (i.e., the parameter that needs to be adjusted) is selected. Subsequently, the cabin control system (e.g., vehicle control unit, cabin domain controller, etc.) sends a control command to the actuator corresponding to the target adjustment parameter (e.g., air conditioning actuator, lighting controller, audio equipment, fragrance device, seat adjustment motor, etc.), which explicitly includes the adjustment direction and intensity adjustment amount. Finally, the actuator precisely adjusts the current cabin environment parameters according to the control command to ensure that the adjusted cabin environment parameters reach the target values ​​corresponding to the "adjustment direction and intensity adjustment amount".

[0135] For example, if the ideal control path requires the tension level to drop from 0.7 to 0.4 within 5 minutes, but the system receives feedback after 2 minutes showing that the tension level is still maintained at 0.65, the controller will actively increase the intervention intensity, specifically by adjusting the light tone, slowing down the music rhythm, and slightly increasing the concentration of the refreshing fragrance.

[0136] The vehicle cabin environment migration method provided in this application first accurately determines the target emotion dimension based on the difference between the real-time collected emotion perception signal and the target emotion perception signal corresponding to the target scene type; then, combining the target scene type and the determined target emotion dimension, it matches at least one cabin environment parameter to be adjusted and its corresponding adjustment direction from preset adjustment rules; simultaneously, based on the above signal differences, it quantifies and determines the intensity adjustment amount of each target cabin environment parameter; finally, according to the adjustment direction and intensity adjustment amount, it implements precise control on at least one of the multiple environmental parameters of the current cabin, so as to achieve dual adaptation of cabin environment parameters with user emotions and usage scenarios, making cabin environment adjustment more personalized and precise, and effectively improving the user's cabin experience comfort and scene adaptability.

[0137] To facilitate understanding of the above-described method for migrating the vehicle cabin environment, this application also provides an example of the process of the method for migrating the vehicle cabin environment.

[0138] Example 1: In a fragrance mixing device and 3D spatial audio system, the fragrance mixing device adopts a core structure of "three chambers, one core, and one atomizer." It is equipped with three base oil chambers, each containing a single fragrance (A for alertness, B for relaxation, and C for warmth). The core microfluidic mixing chip is equipped with a piezoelectric ceramic-driven micropump, enabling nanoliter (nL) level oil pumping with an accuracy of ±5%. The chip's Y-shaped mixing channel has herringbone grooves on its inner wall, allowing the three oil paths to achieve near-instantaneous mixing through laminar flow segmentation and recombination. The mixture is uniformly mixed, and the mixed oil drips directly from the chip outlet to the center of the atomizing plate. The piezoelectric atomizing plate of the fragrance mixing device vibrates at a high frequency of 110kHz to atomize the oil into an ultra-fine dry mist of 1-5 microns. Finally, the dry mist is blown into the air outlet duct of the central control panel of the air conditioning system by a micro fan. The working process is as follows: after receiving the control command (such as A:B=7:3), micro pumps A and B respectively draw 70nl and 30nl of oil, mix it through the Y-shaped flow channel, drip and atomize it, and then send the dry mist into the air conditioning duct. The 3D spatial audio system is based on object-based audio rendering and can access ordinary stereo music and metadata (such as the position coordinates of the "lead singer" sound image). The in-vehicle speakers adopt a 6+ channel layout, including at least a center speaker, left and right tweeters, left and right headrests, and left and right subwoofers. The system's audio processor (DSP) can achieve real-time rendering. Through sound image positioning algorithms, it calculates the volume ratio and microsecond latency of each sound object, such as vocals and drum beats, to each speaker based on metadata. It also presets three scenario modes: business, cinema, and relaxation. The business mode concentrates the sound field to the center speaker and headrests to create a private and focused "head-in-the-head effect." The cinema mode expands the sound field to surround the entire vehicle, enhancing the sense of immersion. The relaxation mode allows the sound to mainly come from the far fields on both sides, creating a relaxed atmosphere. It also supports dynamic migration function. When the scene changes from "driving" to "coming home," the vehicle control system can smoothly move the sound image from a state surrounding the driver to a state that evenly fills the entire vehicle space within 500 milliseconds.

[0139] Example 2: Taking "heading to an important business meeting" as an example, when the navigation is set to a company headquarters and the calendar is associated with the "quarterly report" event, the system triggers scene recognition and determines that the target scene is "formal business". Then, it loads the target parameters of the scene from the template library. Specifically, the fragrance is selected to be refreshing cedar scent, the lights are set to uniform white temperature and high brightness, the music is matched with soothing classical music or wordless electronic ambient music, and the air conditioning is set to a slightly lower temperature and medium fan speed. When the vehicle is 8 minutes away from the destination ETA, the vehicle control system officially starts the cabin environment migration adjustment. At this time, the current state of the car is that the user is listening to dynamic pop music and the lights are warm yellow. The vehicle control system performs multi-dimensional gradual adjustment accordingly: the music volume is gradually reduced, while classical music gradually enters and smoothly transitions to the main volume; the lights are slowly and evenly adjusted from warm yellow to bright white; the fragrance is handled according to the situation. For example, if there is no odor in the car, a light cedar scent is released; if there is a food smell, ventilation is activated first and then the fragrance is released; the air conditioning temperature is gradually reduced by 1-2 degrees Celsius. During the adjustment process, the vehicle control system detected an increase in the user's heart rate and determined that the user might be in a state of anxiety. It then made adaptive adjustments, switching the music to a more relaxed track and further slowing down the gradient of the lights. Finally, when the vehicle arrived at the parking lot, the cabin environment perfectly matched the template requirements of "business formality," and the user's heart rate became stable and calm, successfully achieving the mental transition from "travel fatigue" to "professional meeting."

[0140] Based on the same inventive concept, this application also provides a vehicle cabin environment migration device. Since the principle of the device in this application is similar to the vehicle cabin environment migration method described above in this application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be described again.

[0141] Figure 7 This is a structural schematic diagram of a vehicle cabin environment migration device provided in an embodiment of this application. Figure 7 As shown, the vehicle cabin environment relocation device 700 may include: The acquisition module 701 is used to acquire the destination information and remaining travel time from the navigation information of the target vehicle; The first determining module 702 is used to determine the target scene type based on the destination information; The second determining module 703 is used to determine the start time of the cockpit environment migration based on the remaining travel time and the migration duration; the migration duration is used to control the time it takes for the cockpit environment parameters to change from the current state to the target scene state. The migration module 704 is used to control multiple cabin environment parameters of the target vehicle to migrate to the target cabin environment parameter set at the startup time based on the migration duration, so as to adjust the cabin environment of the target vehicle from the current state to the target scene state; the target cabin environment parameter set and the target scene state are both corresponding to the target scene type.

[0142] In one optional implementation, the second determining module 703 is specifically used to: determine the baseline start time based on the remaining travel time and migration duration; obtain the target user's current calmness score; the calmness score is used to characterize the target user's current psychological calmness; and compensate and constrain the baseline start time based on the current calmness score and a preset maximum / minimum time window to obtain the start time point of the cabin environment migration.

[0143] In one optional implementation, the second determining module 703 is specifically used to: calculate the difference between the current calmness score and the preset ideal calmness score; calculate the product between the difference and the preset state compensation coefficient to obtain the compensation time amount; calculate the sum of the baseline start time and the compensation time amount to obtain the first start time; and compensate and constrain the first start time based on the preset maximum and minimum time window to obtain the start time point of the cabin environment migration.

[0144] In an optional implementation, the vehicle cabin environment migration device 700 is further configured to: determine whether there is a perceptual conflict in the gradual trajectory of the multiple cabin environment parameters during the migration of multiple cabin environment parameters to a target cabin environment parameter set; the perceptual conflict is defined as at least two cabin environment parameters having opposite regulatory effects on the same emotional dimension; if a perceptual conflict exists, determine an adjustment strategy for the conflicting cabin environment parameters based on the parameter priority defined by the target scene type; and execute the gradual trajectory of the conflicting cabin environment parameters based on the adjustment strategy.

[0145] In one optional implementation, the first determining module 702 is specifically used for: determining multiple information sources based on destination information; acquiring probability data corresponding to each candidate scenario type based on the multiple information sources; weighting and fusing the probability data of the multiple information sources corresponding to each candidate scenario type to obtain the evaluation probability of each candidate scenario type; calculating the preset threshold range where the maximum difference between the evaluation probabilities of each candidate scenario type is located to obtain the decision mode of the target scenario type; and determining the target scenario type based on the decision mode.

[0146] In one optional implementation, the first determining module 702 is specifically configured to: if the decision mode is that the maximum difference is greater than or equal to a first threshold, then determine the candidate scenario type with the highest evaluation probability as the target scenario type; if the decision mode is that the maximum difference is less than the first threshold but greater than or equal to a second threshold, then generate and output a confirmation prompt before the start time point, and after receiving the confirmation response from the target user, determine the candidate scenario type with the highest evaluation probability as the target scenario type; if the decision mode is that the maximum difference is less than the second threshold, then generate and output a selection interface, and determine the candidate scenario type selected by the user in the selection interface as the target scenario type.

[0147] In an optional implementation, the vehicle cabin environment migration device 700 is further configured to: acquire the target user's emotional perception signal during the migration of multiple cabin environment parameters to a target cabin environment parameter set; and adjust at least one of the multiple cabin environment parameters based on the difference between the emotional perception signal and the target emotional perception signal corresponding to the target scene type.

[0148] In one optional implementation, the vehicle cabin environment migration device 700 is specifically used to: determine a target emotion dimension based on the difference between the emotion perception signal and the target emotion perception signal corresponding to the target scene type; determine at least one target-adjusted cabin environment parameter and its corresponding adjustment direction from preset adjustment rules based on the target scene type and the target emotion dimension; determine the intensity adjustment amount of the target-adjusted cabin environment parameter based on the difference; and control at least one cabin environment parameter among multiple cabin environment parameters to be adjusted based on the adjustment direction and intensity adjustment amount.

[0149] It should be noted that for details not disclosed in the vehicle cabin environment migration device of this application embodiment, please refer to the details disclosed in the vehicle cabin environment migration method of this application embodiment, which will not be repeated here.

[0150] These modules can be one or more integrated circuits configured to implement the above methods, such as one or more Application Specific Integrated Circuits (ASICs), one or more microprocessors, or one or more Field Programmable Gate Arrays (FPGAs). Alternatively, when a module is implemented using processing element scheduler code, the processing element can be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor capable of calling program code. Furthermore, these modules can be integrated together as a system-on-a-chip (SOC).

[0151] Optionally, embodiments of this application also provide a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the processor performs the steps of the vehicle cabin environment migration method for the removable storage medium described in the above embodiments. The specific implementation and technical effects are similar and will not be repeated here.

[0152] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the functional units in the various embodiments of this application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The integrated unit described above can be implemented in hardware or in the form of hardware plus software functional units.

[0153] Optionally, this embodiment also provides a computer program product that, when run on a computer, causes the computer to perform the aforementioned related steps to realize the vehicle cabin environment migration method provided in the above embodiment.

[0154] In this embodiment, the device, computer-readable storage medium, computer program product, or chip are all used to execute the corresponding methods provided above. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods provided above, and will not be repeated here.

[0155] Through the above description of the embodiments, those skilled in the art will understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0156] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another apparatus, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0157] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for migrating the vehicle cabin environment, characterized in that, include: Obtain the destination information and remaining travel time from the navigation information of the target vehicle; Based on the destination information, the target scenario type is determined; Based on the remaining travel time and migration duration, the start time of the cockpit environment migration is determined; the migration duration is used to control the time it takes for the cockpit environment parameters to change from the current state to the target scene state. At the start time, based on the migration duration, multiple cabin environment parameters of the target vehicle are controlled to migrate to the target cabin environment parameter set, so as to adjust the cabin environment of the target vehicle from the current state to the target scene state; the target cabin environment parameter set and the target scene state both correspond to the target scene type.

2. The method according to claim 1, characterized in that, The determination of the start time for cabin environment migration based on the remaining travel time and migration duration includes: The baseline start time is determined based on the remaining travel time and the migration duration; Obtain the target user's current calmness score; the calmness score is used to characterize the target user's current level of psychological calmness. Based on the current calmness score and the preset maximum / minimum time window, the baseline start time is compensated and constrained to obtain the start time point of the cabin environment migration.

3. The method according to claim 2, characterized in that, The process of compensating and constraining the baseline start-up time based on the current calmness score and a preset maximum / minimum time window to obtain the start-up time point for cabin environment migration includes: Calculate the difference between the current calmness score and the preset ideal calmness score; The product of the difference and the preset state compensation coefficient is calculated to obtain the compensation time. The first startup time is obtained by summing the baseline startup time and the compensation time. Based on the preset maximum and minimum time window, the first start time is compensated and constrained to obtain the start time point of the cabin environment migration.

4. The method according to claim 1, characterized in that, The method further includes: During the migration of the multiple cabin environment parameters to the target cabin environment parameter set, it is determined whether there is a perceptual conflict in the gradual trajectory of the multiple cabin environment parameters; the perceptual conflict is when at least two cabin environment parameters have opposite regulatory effects on the same emotional dimension. If a perception conflict exists, an adjustment strategy for the cabin environment parameters in conflict is determined based on the parameter priority defined by the target scenario type. Based on the adjustment strategy, a gradual trajectory for the conflicting cabin environment parameters is executed.

5. The method according to claim 1, characterized in that, Determining the target scene type based on the destination information includes: Based on the destination information, multiple corresponding information sources are identified; Based on the multiple information sources, obtain probability data corresponding to each candidate scenario type; The probability data from multiple information sources corresponding to each candidate scene type are weighted and fused to obtain the evaluation probability of each candidate scene type; Calculate the preset threshold range where the maximum difference between the evaluation probabilities of each candidate scene type lies to obtain the decision mode of the target scene type; Based on the decision-making model, the target scenario type is determined.

6. The method according to claim 5, characterized in that, Determining the target scenario type based on the decision-making model includes: If the decision mode is that the maximum difference is greater than or equal to the first threshold, then the candidate scene type with the highest evaluation probability is determined as the target scene type; If the decision mode is that the maximum difference is less than the first threshold and greater than or equal to the second threshold, then a confirmation prompt is generated and output before the start time point, and after receiving the confirmation response from the target user, the candidate scenario type with the highest evaluation probability is determined as the target scenario type. If the decision mode is that the maximum difference is less than the second threshold, then a selection interface is generated and output, and the candidate scene type selected by the user in the selection interface is determined as the target scene type.

7. The method according to claim 1, characterized in that, The method further includes: During the migration of the multiple cabin environment parameters to the target cabin environment parameter set, the emotional perception signal of the target user is acquired; Based on the difference between the emotion perception signal and the target emotion perception signal corresponding to the target scene type, at least one of the multiple cabin environment parameters is adjusted.

8. The method according to claim 7, characterized in that, The step of adjusting at least one of the plurality of cabin environment parameters based on the difference between the emotion perception signal and the target emotion perception signal corresponding to the target scene type includes: The target emotion dimension is determined based on the difference between the emotion perception signal and the target emotion perception signal corresponding to the target scene type; Based on the target scene type and the target emotion dimension, at least one target adjustment cabin environment parameter and corresponding adjustment direction are determined from the preset adjustment rules; Based on the differences, the intensity adjustment amount of the target-adjusted cabin environment parameters is determined; Based on the adjustment direction and the intensity adjustment amount, at least one of the plurality of cabin environment parameters is adjusted.

9. A vehicle, characterized in that, The vehicles include: Memory, used to store executable program code; A processor for calling and running the executable program code from the memory, causing the vehicle to perform the method as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a program or instructions that cause a computer to perform the method as described in any one of claims 1 to 8.

Images