Cabin environment adjusting method, medium, vehicle and product

Abstract

The invention provides a cabin environment adjusting method, a medium, a vehicle and a product, and relates to the technical field of vehicle control. The method comprises the following steps: determining comfort level state data of passengers in a target vehicle; performing target optimization processing by using the comfort level state data and the optimization target to obtain a cooperative adjustment instruction set of the cabin environment of the target vehicle; wherein the optimization target comprises a comfort degree maximization target; the collaborative adjustment instruction set comprises adjustment instructions for a plurality of execution ends in the cabin environment; and controlling a plurality of execution ends in the cabin environment to perform cooperative work according to each adjustment instruction in the cooperative adjustment instruction set. According to the technical scheme provided by the invention, when the execution ends are controlled to cooperatively work according to the cooperative adjustment instruction set, conflict or contradictory operation caused by independent control of the execution ends can be avoided, and the overall coordination is improved; meanwhile, the comfort level of the cabin environment is further improved, and more coordinated and comfortable riding experience is provided for passengers.

Description

Technical Field

[0001] This application relates to the field of vehicle control technology, specifically to a method, medium, vehicle, and product for adjusting the cabin environment. Background Technology

[0002] As vehicle functions continue to develop, users are demanding higher and higher levels of comfort and intelligence in the cabin environment.

[0003] Currently, for multiple actuators in a cockpit environment, adjustment rules are typically set for each actuator to allow for individual control according to their respective rules. However, this independent control approach may lead to conflicting and contradictory operations between different actuators, failing to provide a unified and coordinated comfort experience. Summary of the Invention

[0004] In view of this, the embodiments of this application aim to provide a cabin environment adjustment method, medium, vehicle and product to improve overall coordination and riding experience.

[0005] In a first aspect, one embodiment of this application provides a method for adjusting the cabin environment, comprising: determining the comfort state data of occupants in a target vehicle; using the comfort state data and an optimization target, performing target optimization processing to obtain a set of collaborative adjustment instructions for the cabin environment of the target vehicle; wherein the optimization target includes a comfort maximization target; the collaborative adjustment instruction set includes adjustment instructions for multiple execution terminals in the cabin environment; and controlling multiple execution terminals in the cabin environment to work collaboratively according to each adjustment instruction in the collaborative adjustment instruction set.

[0006] This application embodiment utilizes comfort state data and optimization objectives to perform objective optimization processing, obtaining a collaborative adjustment instruction set for the target vehicle cabin environment. This collaborative adjustment instruction set includes adjustment instructions for multiple actuators in the cabin environment, thus achieving collaborative optimization of multiple actuators in the cabin environment under the same optimization objective. Therefore, when controlling each actuator to work collaboratively according to the collaborative adjustment instruction set, conflicts or contradictory operations caused by individual control of each actuator can be avoided, improving overall coordination. At the same time, performing objective optimization processing with maximizing comfort as the optimization objective can further improve the comfort of the cabin environment, providing passengers with a more coordinated and comfortable riding experience.

[0007] In conjunction with the first aspect, in some implementations of the first aspect, the optimization objectives also include the energy efficiency maximization objective and / or the safety maximization objective; using comfort state data and optimization objectives, target optimization processing is performed to obtain a set of coordinated adjustment instructions for the cabin environment of the target vehicle, including: constructing an objective function based on comfort state data and optimization objectives; and using a multi-objective optimization algorithm to solve the objective function for multi-objective optimization to obtain a set of coordinated adjustment instructions for the cabin environment of the target vehicle.

[0008] This application's embodiments expand the optimization objective to multiple objectives and construct corresponding objective functions for multi-objective optimization solutions, achieving a balance between needs in different dimensions; it not only meets the comfort needs of passengers but also takes into account vehicle driving safety and energy efficiency, achieving more refined global optimization.

[0009] In conjunction with the first aspect, in some implementations of the first aspect, an objective function is constructed based on comfort state data and optimization objectives, including: determining the weight of each optimization objective based on the driving conditions of the target vehicle; the weight is used to reflect the importance of the optimization objective under the driving conditions; constructing sub-functions based on comfort state data and each optimization objective; and obtaining the objective function by weighted summation of the weights and sub-functions.

[0010] This application embodiment dynamically adjusts the weights of each optimization objective based on driving conditions and constructs an objective function accordingly. This allows the adjustment of the cabin environment to better match the actual driving scenarios of the vehicle and the immediate needs of the occupants, avoiding the problem of poor optimization results that may result from using a single adjustment strategy under different conditions.

[0011] In conjunction with the first aspect, in some implementations of the first aspect, determining the comfort state data of the occupants in the target vehicle includes: determining the target physiological data of the occupants in the target vehicle; inputting the target physiological data into the state determination model, performing the state determination operation to obtain the comfort state of the occupants in the target vehicle; and quantifying the comfort state to obtain comfort state data. This application embodiment, by inputting target physiological data into a state determination model, can more accurately determine the comfort state of occupants. Furthermore, through quantification, the comfort state is transformed into specific comfort state data, providing quantifiable foundational data for subsequent target optimization and helping to improve the accuracy of the collaborative adjustment instruction set. Simultaneously, by constructing an individual physiological baseline, the impact of individual differences on comfort perception is fully considered, ensuring that the determined comfort state data more closely reflects the actual feelings of each occupant.

[0012] In conjunction with the first aspect, in some implementations of the first aspect, determining the target physiological data of the occupants inside the target vehicle includes: acquiring image information of the occupants collected by an image acquisition device and point cloud data of the occupants collected by radar; determining the first physiological data of the occupants based on the image information; determining the second physiological data of the occupants based on the point cloud data; and fusing the first physiological data and the second physiological data to obtain the target physiological data of the occupants inside the target vehicle.

[0013] This application embodiment extracts first physiological data from image information and second physiological data from point cloud data, and then performs fusion processing to obtain target physiological data. This effectively combines the advantages of different modal data and avoids the problem of errors that may occur when data is collected from a single data source. At the same time, the weights of different physiological data during fusion are dynamically adjusted according to the data collection environment, which improves the accuracy and reliability of the fused target physiological data.

[0014] In conjunction with the first aspect, in some implementations of the first aspect, before fusing the first physiological data and the second physiological data to obtain the target physiological data of the occupant in the target vehicle, the method further includes: determining the confidence level between the first physiological data and the second physiological data; wherein the confidence level is used to reflect the degree of consistency between the first physiological data and the second physiological data; fusing the first physiological data and the second physiological data to obtain the target physiological data of the occupant in the target vehicle includes: fusing the first physiological data and the second physiological data to obtain the target physiological data of the occupant in the target vehicle when the confidence level exceeds a target confidence level threshold.

[0015] The embodiments of this application evaluate the confidence levels of the first and second physiological data before data fusion, and perform the fusion operation only when the confidence level exceeds the target confidence level threshold. This can effectively filter out data with large errors or interference, improve the accuracy of the target physiological data, and avoid unreliable data from participating in subsequent comfort state judgments.

[0016] In conjunction with the first aspect, in certain implementations of the first aspect, determining the confidence level between the first physiological data and the second physiological data includes: inputting the first physiological data into a first state classifier, determining the state reflected by the first physiological data, and obtaining a first classification result corresponding to the first physiological data; inputting the second physiological data into a second state classifier, determining the state reflected by the second physiological data, and obtaining a second classification result corresponding to the second physiological data; and determining the confidence level between the first physiological data and the second physiological data based on the first classification result and the second classification result.

[0017] This application embodiment determines the confidence level between the first physiological data and the second physiological data by comparing the consistency of the first state classification result of the first physiological data and the second state classification result of the second physiological data. This can more intuitively reflect whether the comfort states pointed to by the two physiological data are consistent from the perspective of state classification, making the correlation between the determined confidence level and the comfort state stronger. Therefore, when determining the comfort state based on the physiological data selected based on the confidence level, the accuracy of the comfort state is further improved.

[0018] Secondly, this application provides a cabin environment adjustment device, comprising: a state determination module for determining the comfort state data of occupants in a target vehicle; an optimization processing module for using the comfort state data and optimization objectives to perform target optimization processing to obtain a collaborative adjustment instruction set for the cabin environment of the target vehicle; wherein the optimization objectives include a comfort maximization objective; the collaborative adjustment instruction set includes adjustment instructions for multiple actuators in the cabin environment; and a control module for controlling multiple actuators in the cabin environment to work collaboratively according to the adjustment instructions in the collaborative adjustment instruction set.

[0019] Thirdly, one embodiment of this application provides a computer-readable storage medium storing a computer program for performing the method in the first aspect or any possible implementation of the first aspect.

[0020] Fourthly, one embodiment of this application provides a vehicle, the vehicle comprising: a processor; a memory for storing processor-executable instructions; the processor being configured to execute the method in the first aspect or any possible implementation thereof.

[0021] Fifthly, one embodiment of this application provides a computer program product including instructions that, when executed on a vehicle, cause the vehicle to implement the method in the first aspect or any possible implementation of the first aspect.

[0022] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 The diagram shown is a schematic of an existing cabin environment adjustment system.

[0025] Figure 2 The diagram shown is a flowchart illustrating a cabin environment adjustment method provided in an embodiment of this application.

[0026] Figure 3 The diagram shown is a schematic diagram of a cockpit environment system provided in an embodiment of this application.

[0027] Figure 4The diagram shown is a structural schematic of a cabin environment adjustment device provided in an embodiment of this application.

[0028] Figure 5 The diagram shown is a structural schematic of a vehicle provided in an embodiment of this application. Detailed Implementation

[0029] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0030] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. The singular forms “a,” “the,” and “the” used in the embodiments of this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0031] It should be understood that the term "and / or" used in this document 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, or B existing alone. Furthermore, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship. Additionally, the term "based on" used in this document is not limited to relying solely on one object. For example, determining B based on A can mean: determining B based solely on A, or determining B partially based on A.

[0032] It should be noted that the collection, gathering, updating, analysis, processing, use, transmission, and storage of user personal information involved in the technical solution of this application all comply with the provisions of relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. Necessary measures are taken to prevent unauthorized access to user personal information data and to safeguard user personal information security and network security.

[0033] Figure 1 The diagram shown is a schematic of an existing cabin environment adjustment system. Figure 1As shown, the cabin environment adjustment system includes multiple actuators, such as an entertainment control unit, a seat control unit, and an air conditioning control unit. The entertainment control unit responds to touchscreen or button triggers, controlling the speakers and display screen. The seat control unit controls the seat heating pads or ventilation fans based on pressure values ​​detected by seat pressure sensors and triggers of the heating buttons. The air conditioning control unit controls at least one of the blower, compressor, and damper actuators using information collected by temperature sensors and vehicle cameras. These actuators are independent of each other, and each actuator relies on a single factor for control. For example, the air conditioning control unit controls only the ambient temperature collected by the temperature sensor. The entertainment control unit relies on manual triggers by the user.

[0034] Each actuator operates using the aforementioned individual control method, which is highly prone to conflict. For example, when the occupant entertainment control unit increases the multimedia volume to ensure the occupant can hear the music clearly, the air conditioning control unit may automatically increase the blower airflow due to detecting an increase in ambient temperature, resulting in noise superposition. This could negatively impact the clarity of the music for the occupant, failing to provide a unified and coordinated comfortable experience.

[0035] Based on this, the present application provides a cockpit environment adjustment method that can coordinate the control of multiple actuators to solve the conflict problem caused by the independent control of each actuator in the prior art, thereby improving the overall comfort and coordination of the cockpit environment.

[0036] The following is combined with Figures 2 to 3 The cockpit environment adjustment method provided in the embodiments of this application will be described in detail.

[0037] Figure 2 The diagram shown is a flowchart illustrating a cabin environment adjustment method according to an embodiment of this application; as follows: Figure 2 As shown, the method includes the following steps.

[0038] Step S210: Determine the comfort status data of the occupants inside the target vehicle.

[0039] The target vehicle may contain multiple occupants, such as the driver, front-seat passengers, and rear-seat passengers. Comfort status data is used to reflect the comfort level of the occupants. For example, comfort status data can be represented numerically. For instance, within a score range of 0-100, a higher score indicates a higher level of occupant comfort; it can also be represented in a rating system, such as five levels: "very comfortable," "comfortable," "average," "uncomfortable," and "very uncomfortable," each corresponding to a different quantitative value.

[0040] In this embodiment, images of the occupants inside the target vehicle can be captured, reflecting information such as their posture and facial expressions. Image recognition technology is then used to analyze the captured images to determine the comfort level data of each occupant.

[0041] Step S220: Using comfort status data and optimization targets, perform target optimization processing to obtain a set of coordinated adjustment instructions for the cabin environment of the target vehicle.

[0042] The optimization objectives include maximizing comfort; the collaborative adjustment instruction set includes adjustment instructions for multiple actuators in the cockpit environment.

[0043] In some embodiments, the optimization objective can be set as a single objective or multiple objectives according to actual needs. When the optimization objective is to maximize comfort, a set of coordinated adjustment instructions for multiple actuators that maximize occupant comfort can be obtained through objective optimization processing. For example, the comfort maximization objective can be set to maximize the driver's comfort, or it can be to maximize the overall comfort of all occupants. For instance, different comfort weights for occupants can be set according to their priority to achieve weighted overall comfort maximization.

[0044] Furthermore, to accommodate the differences among occupants, personalized preference parameters can be pre-set for each occupant, and an objective function can be constructed using these parameters. Personalized preference parameters can be preferences regarding the control range of the actuators; for example, a preferred temperature range for the seat or a preferred range for the air conditioning fan speed. They can also be preferences regarding the order in which the actuators are controlled; for example, given the same "cold" state, occupant A might prioritize adjusting the temperature by turning on the seat heater, while occupant B might prioritize adjusting the temperature by controlling the air conditioning. By incorporating personalized preference parameters, the objective function can better align with the subjective needs of different occupants, avoiding situations where a uniform adjustment strategy leads to a poor experience for some occupants.

[0045] Step S230: Control multiple actuators in the cockpit environment to work collaboratively according to the adjustment instructions in the collaborative adjustment instruction set.

[0046] The actuators include the air conditioning control unit, seat control unit, audio control unit, ambient lighting control unit, window control unit, and fragrance generator.

[0047] In practice, each adjustment command can be sent to its corresponding execution terminal to control the terminal to operate according to the received command. For example, if the coordinated adjustment command set includes a first command to adjust the seat ventilation intensity to the medium level and a second command to reduce the audio volume by 3 decibels, the first command is sent to the seat control unit, and the second command is sent to the audio control unit. The seat control unit controls the power of the seat ventilation fan based on the first command to keep the ventilation intensity stable at the medium level; the audio control unit adjusts the output power of the amplifier module according to the second command to reduce the volume by 3 decibels from the current value, ensuring that the occupant can hear the audio content clearly while avoiding excessive volume that could interfere with the surrounding ambient sound.

[0048] This application embodiment utilizes comfort state data and optimization objectives to perform objective optimization processing, obtaining a collaborative adjustment instruction set for the target vehicle cabin environment. This collaborative adjustment instruction set includes adjustment instructions for multiple actuators in the cabin environment, thus achieving collaborative optimization of multiple actuators in the cabin environment under the same optimization objective. Therefore, when controlling each actuator to work collaboratively according to the collaborative adjustment instruction set, conflicts or contradictory operations caused by individual control of each actuator can be avoided, improving overall coordination. At the same time, performing objective optimization processing with maximizing comfort as the optimization objective can further improve the comfort of the cabin environment, providing passengers with a more coordinated and comfortable riding experience.

[0049] In some embodiments, determining the comfort state data of occupants in a target vehicle includes: determining target physiological data of occupants in the target vehicle; inputting the target physiological data into a state determination model, performing a state determination operation to obtain the comfort state of occupants in the target vehicle; and quantifying the comfort state to obtain comfort state data.

[0050] The target physiological data include at least one of heart rate, respiratory rate, and body surface temperature. In addition, based on heart rate, respiratory rate, and body surface temperature, temporal characteristics such as heart rate variation trends and respiratory rhythm can also be derived.

[0051] In practice, body surface temperature can be collected by temperature sensors deployed inside the seats. Heart rate and respiratory rate can be obtained by processing images collected by visual sensors. After determining the target physiological data, the target physiological data is input into a state determination model, which can then assess the comfort state of each occupant in the target vehicle. Comfort states include heat stress, coldness, tension, and drowsiness.

[0052] It is important to note that before defining the target physiological data for each passenger, a personal physiological baseline can be established and maintained for each passenger. This baseline reflects the range of physiological characteristics of the passenger under normal non-stress conditions. Examples include the normal resting heart rate range, the baseline respiratory rate range, and standard body surface temperature. The state determination model can determine the comfort state of each passenger based on their physiological baseline and target physiological data, fully considering individual differences and accurately determining the comfort state of each passenger.

[0053] For example, if passenger A's physiological baseline is a resting heart rate of 60-70 beats per minute, and their target physiological data center rate is 85 beats per minute, the state determination model can determine that they are in a state of mild stress or heat stress by combining this physiological baseline. However, for passenger B, whose physiological baseline is a fine heart rate of 75-85 beats per minute, if their target physiological data center rate is also 85 beats per minute, they may be judged to be in a normal state.

[0054] In some embodiments, the state determination model can be built based on a machine learning model. The output information of the model includes occupant identification and the state probability for each comfort state. The higher the state probability, the greater the likelihood that the occupant is in that state. For example, if the state determination model outputs an 85% probability of occupant A being in a "heat stress" state, a 10% probability of being in a "stress" state, and a 5% probability of being in a "comfortable" state, then "heat stress" can be identified as occupant A's current comfort state.

[0055] After determining the comfort state, the comfort state can be quantified based on the quantitative score corresponding to each comfort state to obtain comfort state data. For example, if the state determination model only outputs the single comfort state with the highest probability, then the quantitative score corresponding to that comfort state is directly taken as the comfort state data; for example, "heat stress" corresponds to 30 points, "stress" corresponds to 40 points, and "comfort" corresponds to 80 points. Therefore, when it is determined that occupant A is in a "heat stress" state, their comfort state data is 30 points. If the state determination model provides a probability distribution of multiple comfort states, then the comfort state data is determined by a probability-weighted summation based on the weight and corresponding quantitative score of each comfort state. For example, if the state determination model outputs that the probability of occupant A's "heat stress" state is 85%, the probability of "stress" state is 10%, and the probability of "comfort" state is 5%, and the weight of each state is 1, then the comfort state data is calculated as follows: 30×85%+40×10%+80×5%=33.5 points, thus obtaining the comfort state data of occupant A as 33.5 points.

[0056] This application embodiment, by inputting target physiological data into a state determination model, can more accurately determine the comfort state of occupants. Furthermore, through quantification, the comfort state is transformed into specific comfort state data, providing quantifiable foundational data for subsequent target optimization and helping to improve the accuracy of the collaborative adjustment instruction set. Simultaneously, by constructing an individual physiological baseline, the impact of individual differences on comfort perception is fully considered, ensuring that the determined comfort state data more closely reflects the actual feelings of each occupant.

[0057] To improve the accuracy of physiological data acquisition when determining the target physiological data of occupants inside a target vehicle, a multimodal information acquisition method can be used. Optionally, determining the target physiological data of occupants inside a target vehicle includes: acquiring image information of the occupants collected by an image acquisition device, and point cloud data of the occupants collected by radar; determining the first physiological data of the occupants based on the image information; determining the second physiological data of the occupants based on the point cloud data; and fusing the first and second physiological data to obtain the target physiological data of the occupants inside the target vehicle.

[0058] The image acquisition equipment may include cameras installed in different locations within the vehicle, such as a driver's seat camera above the dashboard, a front-row camera next to the rearview mirror, and a passenger camera on the rear roof, to comprehensively collect image information such as facial expressions, body movements, and postures of each occupant. The radar may employ millimeter-wave radar or lidar, and the point cloud data it collects can accurately reflect the occupant's chest movements, the relative positions of different body parts, and micro-movements. In other words, through the image acquisition equipment and radar, it is possible to acquire facial micro-vibration information and body surface micro-movement information of each occupant in a non-contact manner, and determine the occupant's target physiological data based on this information.

[0059] In practice, photoplethysmography is used to extract blood flow changes in facial skin from image information to determine heart rate and respiratory rate. For point cloud data acquired by radar, time-series analysis of point cloud data in the chest region is performed to capture the periodic undulations of the chest cavity, and the respiratory rate is calculated accordingly. Simultaneously, by analyzing the minute vibrations on the body surface caused by the heartbeat and combining them with the temporal characteristics of the point cloud data, the heart rate is extracted.

[0060] In addition, temperature sensors can be used to collect occupant body surface temperature. When the temperature sensor is in contact with the occupant's body surface or within a suitable sensing range, the temperature value of the occupant's body surface can be obtained. Body surface temperature, heart rate, and respiratory rate together constitute the occupant's physiological data. Among them, heart rate reflects the frequency of the occupant's heartbeat, respiratory rate represents the number of breaths the occupant takes per unit time, and together with body surface temperature, these three indicators quantify the occupant's physical condition from different physiological dimensions.

[0061] Furthermore, a fusion algorithm is used to perform multimodal data fusion on the first and second physiological data, and the fused data is used as the target physiological data of the occupants inside the target vehicle. For example, the fusion algorithm includes a Kalman filter algorithm. The Kalman filter algorithm is a recursive estimation algorithm based on the minimum mean square error criterion, capable of optimally estimating the state of a dynamic system in the presence of noise and uncertainty. It should be noted that during the data fusion process, considering the varying reliability of data acquired by image acquisition devices and radar under different acquisition environments, the reliability of the fused target physiological data is improved by dynamically adjusting the weights of the two data sources. For example, under good lighting conditions, the accuracy of image information is better, which can increase the weight of the first physiological data during fusion. Alternatively, in acquisition environments with vehicle vibration or large occupant movements, the radar signal has stronger anti-interference capabilities, which can increase the weight of the second physiological data during fusion.

[0062] This application embodiment extracts first physiological data from image information and second physiological data from point cloud data, and then performs fusion processing to obtain target physiological data. This effectively combines the advantages of different modal data and avoids the problem of errors that may occur when data is collected from a single data source. At the same time, the weights of different physiological data during fusion are dynamically adjusted according to the data collection environment, which improves the accuracy and reliability of the fused target physiological data.

[0063] To avoid biases in comfort state judgment due to data collection errors, before fusing the first and second physiological data to obtain the target physiological data of the occupants in the target vehicle, the process includes: determining the confidence level between the first and second physiological data; fusing the first and second physiological data to obtain the target physiological data of the occupants in the target vehicle, including: fusing the first and second physiological data to obtain the target physiological data of the occupants in the target vehicle when the confidence level exceeds the target confidence level threshold.

[0064] The confidence level reflects the degree of consistency between the first and second physiological data. A low degree of consistency indicates a significant data acquisition error or interference; conversely, a high degree of consistency indicates strong data reliability. Confidence levels can be categorized into high, medium, and low, and can also be quantified using specific numerical values.

[0065] In practice, the deviation between the first and second physiological data can be calculated to determine the confidence level between them. The smaller the deviation, the higher the confidence level; conversely, the larger the deviation, the lower the confidence level.

[0066] In some implementations, if the confidence level exceeds the target confidence threshold, it indicates that the first and second physiological data have a high degree of consistency, and a fusion operation can be performed. For example, if the target confidence threshold is set to 80%, and the heart rate in the first physiological data is 75 beats / minute and the heart rate in the second physiological data is 76 beats / minute, the deviation between the two is small, and the calculated confidence level is 92%, which exceeds the target confidence threshold of 80%. Therefore, the two heart rate data are fused.

[0067] If the confidence level does not exceed the target confidence threshold, it indicates a significant difference between the first and second physiological data, suggesting insufficient data reliability. In this case, the image acquisition equipment and radar can be retried to acquire new image information and point cloud data. Based on the new data, the first and second physiological data are recalculated, and their confidence levels are reassessed until the confidence level exceeds the target confidence threshold. Finally, the newly determined first and second physiological data are fused to obtain the target physiological data of the occupants inside the target vehicle. For example, if the heart rate in the first physiological data is 65 beats / minute and the heart rate in the second physiological data is 90 beats / minute, the deviation between the two is large, and the calculated confidence level is 55%, which does not reach the target confidence level threshold of 80%. In this case, the image acquisition device is controlled to re-capture the facial image, and the radar re-scans the chest area to obtain new image information and point cloud data. Then, based on the new data, the first and second physiological data are re-extracted. For example, if the new first physiological data shows a heart rate of 68 beats / minute and the new second physiological data shows a heart rate of 70 beats / minute, the deviation is reduced, and the confidence level is increased to 88%, which exceeds the target confidence level threshold. Then, the fusion operation can be performed.

[0068] The embodiments of this application evaluate the confidence levels of the first and second physiological data before data fusion, and perform the fusion operation only when the confidence level exceeds the target confidence level threshold. This can effectively filter out data with large errors or interference, improve the accuracy of the target physiological data, and avoid unreliable data from participating in subsequent comfort state judgments.

[0069] In other embodiments, the specific implementation of determining the confidence level between the first physiological data and the second physiological data may be as follows: inputting the first physiological data into a first state classifier, determining the state reflected by the first physiological data, and obtaining a first classification result corresponding to the first physiological data; inputting the second physiological data into a second state classifier, determining the state reflected by the second physiological data, and obtaining a second classification result corresponding to the second physiological data; and determining the confidence level between the first physiological data and the second physiological data based on the first classification result and the second classification result.

[0070] The first and second state classifiers can be trained by a deep learning network. The first state classifier is used to classify the state of the first physiological data and outputs the comfort state corresponding to the data as the first classification result; the second state classifier classifies the state of the second physiological data and outputs the comfort state corresponding to the data as the second classification result.

[0071] During the training of the state classifier, a sample dataset containing a large amount of labeled physiological data and corresponding actual comfort states can be used to train the classifier. For example, each sample in the dataset contains physiological data extracted from an image of a passenger and its corresponding actual comfort state label. These samples are used to train the first state classifier, enabling it to learn the mapping relationship from image physiological data to comfort states. Similarly, a sample dataset containing physiological data extracted from point cloud data and its corresponding actual comfort state labels is used to train the second state classifier. After training, when the first physiological data is input into the first state classifier, the first classification result indicated by the data is obtained; when the second physiological data is input into the second state classifier, the second classification result is obtained.

[0072] In practice, when the first and second classification results are consistent, the confidence level is determined to be high. If the classification results are inconsistent, it can be determined whether the first and second classification results belong to the same classification type, such as whether both are heat stress states. If the classification types are the same but the degrees are different, the confidence level is determined to be medium. For example, if the first classification result is "mild heat stress" and the second classification result is "moderate heat stress," the confidence level is medium. If the two classification results are different classification types, the confidence level is low; for example, if the first classification result is "heat stress" and the second classification result is "coldness," the confidence level is low.

[0073] This application embodiment determines the confidence level between the first physiological data and the second physiological data by comparing the consistency of the first state classification result of the first physiological data and the second state classification result of the second physiological data. This can more intuitively reflect whether the comfort states pointed to by the two physiological data are consistent from the perspective of state classification, making the correlation between the determined confidence level and the comfort state stronger. Therefore, when determining the comfort state based on the physiological data selected based on the confidence level, the accuracy of the comfort state is further improved.

[0074] During vehicle operation, to avoid impacting vehicle safety and energy efficiency due to adjustments in the cabin environment, optimization objectives also include maximizing energy efficiency and / or maximizing safety. Optionally, using comfort state data and optimization objectives, target optimization processing is performed to obtain a coordinated adjustment instruction set for the target vehicle's cabin environment. This includes: constructing an objective function based on comfort state data and optimization objectives; and using a multi-objective optimization algorithm to solve the objective function for multi-objective optimization, thereby obtaining the coordinated adjustment instruction set for the target vehicle's cabin environment.

[0075] Among them, multi-objective optimization algorithms can employ genetic algorithms; for example, the third-generation non-dominated sorting genetic algorithm, which can find a uniformly distributed and widely available Pareto optimal solution in the target space by performing non-dominated sorting and crowding calculation on the population, thereby providing multiple potential collaborative adjustment instruction set schemes for cabin environment adjustment.

[0076] In this embodiment, sub-functions can be constructed for safety, comfort, and energy efficiency, and the objective function is composed of these sub-functions. For example, a functional relationship between the energy consumption and adjustment parameters of the cabin environment adjustment system is established to obtain the energy efficiency sub-function. This sub-function selects the instruction set that minimizes changes to the current cabin environment settings and is most energy-efficient, thus maintaining environmental stability and reducing energy consumption. Based on comfort status data, a functional relationship between safety level and adjustment parameters is established to obtain the safety sub-function. The safety level can be determined based on factors such as driver fatigue, visibility, and emergency braking distance. Additionally, a functional relationship between comfort level and adjustment parameters is established based on comfort status data to obtain the comfort sub-function.

[0077] The constructed objective function is solved using a multi-objective optimization algorithm to obtain a set of coordinated adjustment instructions for the cabin environment of the target vehicle. This set of instructions can maximize passenger comfort and meet the vehicle's energy efficiency requirements while ensuring safety.

[0078] This application's embodiments expand the optimization objective to multiple objectives and construct corresponding objective functions for multi-objective optimization solutions, achieving a balance between needs in different dimensions; it not only meets the comfort needs of passengers but also takes into account vehicle driving safety and energy efficiency, achieving more refined global optimization.

[0079] It should be noted that the requirements for safety, comfort, and energy efficiency vary depending on the driving conditions. For example, in congested urban traffic, vehicle speeds are relatively slow, and the probability of emergencies is relatively low. However, passengers are prone to frustration due to long waits, and in this case, the demand for comfort may be greater. On the other hand, in highway driving conditions, vehicle speeds are high, so the requirements for safety are higher. Therefore, this application proposes a method for constructing an objective function based on different driving conditions to meet the actual needs under different driving conditions.

[0080] Optionally, the specific implementation of constructing the objective function based on comfort state data and optimization objectives includes: determining the weight of each optimization objective based on the driving conditions of the target vehicle; the weight is used to reflect the importance of the optimization objective under the driving conditions; constructing sub-functions based on comfort state data and each optimization objective; and obtaining the objective function by weighted summation of the weights and sub-functions.

[0081] Among them, driving conditions are used to reflect the current driving status characteristics of the target vehicle. For example, driving conditions may include urban congestion conditions, highway conditions, rural road conditions, night driving conditions, and long-distance driving conditions.

[0082] Different driving conditions correspond to different environmental conditions and safety requirements. Therefore, it is necessary to assign different weights to each optimization objective to reflect its importance under that driving condition. Specifically, the weights of each optimization objective under different driving conditions can be pre-set, thus establishing a mapping relationship between driving conditions and the weights of each optimization objective. For example, in urban congestion conditions, the weight of the comfort optimization objective is set to 0.6, the weight of the safety optimization objective is set to 0.2, and the weight of the energy efficiency optimization objective is set to 0.2 to improve passenger comfort. In highway conditions, the weight of the safety optimization objective is set to 0.5, the weight of the comfort optimization objective is set to 0.3, and the weight of the energy efficiency optimization objective is set to 0.2 to ensure driving safety.

[0083] In some embodiments, during the driving process of the target vehicle, the driving condition can be determined based on at least one of the following: the target vehicle's current speed, navigation information, real-time traffic data, and time information. For example, the current driving speed can be obtained in real time through the vehicle's speed sensor. When the speed is consistently below 30 km / h and the acceleration changes frequently within a preset time period, it can be determined as an urban congestion condition. Combined with navigation information, if the current driving route is a highway and the distance to the next exit is more than 5 kilometers, it is determined as a highway condition.

[0084] After determining the driving conditions of the target vehicle, the weights of the optimization objectives corresponding to the current driving conditions of the target vehicle can be determined based on the pre-set mapping relationship between the driving conditions and the weights of each optimization objective.

[0085] Furthermore, when constructing the objective function, sub-functions can be built based on comfort state data and each optimization objective; and the sub-functions are then weighted and summed using determined weights to obtain the objective function. For example, if the safety sub-function is F1 with weight ω1; the comfort sub-function is F2 with weight ω2; and the energy efficiency sub-function is F3 with weight ω3, then the objective function F can be expressed as: F = ω1 × F1 + ω2 × F2 + ω3 × F3 This application embodiment dynamically adjusts the weights of each optimization objective based on driving conditions and constructs an objective function accordingly. This allows the adjustment of the cabin environment to better match the actual driving scenarios of the vehicle and the immediate needs of the occupants, avoiding the problem of poor optimization results that may result from using a single adjustment strategy under different conditions.

[0086] The embodiments of the cabin environment adjustment method have been described in detail above. In order to enable those skilled in the art to further understand the technical solution of this method, the implementation of the method will be explained below in conjunction with the structure of the cabin environment adjustment system.

[0087] Figure 3 The diagram shown is a schematic representation of a cockpit environment system provided in one embodiment of this application. Figure 3 As shown, the cockpit environment adjustment system consists of several parts: a perception layer, a data fusion and processing layer, a decision-making layer, and an execution layer.

[0088] The perception layer is used to collect raw physiological signals from occupants. Collection devices may include image acquisition devices, radar, temperature sensors, and environmental sensors. For example, the image acquisition device includes a visual sensor for collecting facial micro-expression signals. The radar includes millimeter-wave radar for collecting micro-motion signals from the body surface. Based on the raw physiological signals collected by the visual sensor, first physiological data is generated; based on the raw physiological signals collected by the millimeter-wave radar, second physiological data is generated.

[0089] The perception layer sends the collected raw physiological signals and environmental changes to the data fusion and processing layer. The data fusion and processing layer, through a multimodal data fusion module, uses a Kalman filter algorithm to fuse the first and second physiological data to obtain high-confidence target physiological data. The target physiological data includes heart rate, respiratory rate, and body surface temperature.

[0090] Furthermore, the multimodal data fusion module sends the target physiological data to the state recognition module to determine the comfort state corresponding to the target physiological data based on the state determination model. The comfort state is then quantified to obtain comfort state data, which is sent to the decision layer. The decision layer uses this data, based on a multi-objective optimization algorithm and the comfort state data, to determine the globally optimal set of coordinated adjustment instructions. Therefore, this embodiment of the application, through physiological data, can detect early tendencies in the occupant's physiological condition and proactively intervene before the occupant experiences significant discomfort, upgrading cabin functionality from a passive response to proactive care.

[0091] Furthermore, the various adjustment commands in the coordinated adjustment command set are distributed to the corresponding execution terminals. The execution layer includes multiple execution terminals within the cabin environment. After receiving the adjustment command, each execution terminal adjusts the cabin physical environment according to the adjustment command. The execution terminals include the air conditioning control unit, seat control unit, entertainment control unit, and fragrance generator, etc. The air conditioning control unit performs zoned temperature control based on the adjustment commands. The seat control unit can adjust independent functions such as heating or ventilation based on the adjustment commands. The entertainment control unit can control audio and video output to assist in regulating the occupant's state. The fragrance generator adjusts the type and concentration of released odors.

[0092] Finally, after the cabin environment changes, the perception layer will re-collect the original physiological signals and environmental changes to start the next round of regulation cycle and achieve continuous adaptive optimization of the environment.

[0093] This application embodiment collects information through radar and image acquisition equipment, which can obtain effective information without physical contact, and realizes high-precision and high-reliability perception of the physiological status of all occupants in the vehicle; moreover, it replaces the traditional method of controlling each actuator separately, and generates a collaborative adjustment instruction set through a multi-objective optimization algorithm to ensure that each actuator works in coordination, avoids frequent adjustments or functional conflicts of a single device, and helps to improve the comfort of the occupants.

[0094] The above text combined Figures 1 to 3 The present application describes in detail the embodiments of the cabin environment adjustment method, and the following is in conjunction with... Figure 4 This application provides a detailed description of embodiments of the cabin environment adjustment device. It should be understood that the descriptions of the cabin environment adjustment method embodiments correspond to the descriptions of the cabin environment adjustment device embodiments; therefore, any parts not described in detail can be found in the preceding method embodiments.

[0095] Figure 4 The diagram shown is a structural schematic of a cabin environment adjustment device provided in an embodiment of this application. Figure 4 As shown, the cabin environment adjustment device 40 provided in this application embodiment includes: The state determination module 410 is used to determine the comfort state data of the occupants inside the target vehicle. The optimization processing module 420 is used to perform target optimization processing using comfort state data and optimization objectives to obtain a set of coordinated adjustment instructions for the cabin environment of the target vehicle; wherein, the optimization objective includes the goal of maximizing comfort; and the coordinated adjustment instruction set includes adjustment instructions for multiple execution ends in the cabin environment. The control module 430 is used to control multiple actuators in the cockpit environment to work collaboratively according to the adjustment instructions in the collaborative adjustment instruction set.

[0096] In one embodiment of this application, the optimization objectives further include an energy efficiency maximization objective and / or a safety maximization objective; the optimization processing module 420 is further configured to construct an objective function based on comfort state data and the optimization objectives; and to use a multi-objective optimization algorithm to perform multi-objective optimization solution on the objective function to obtain a set of coordinated adjustment instructions for the cabin environment of the target vehicle.

[0097] In one embodiment of this application, the optimization processing module 420 is further configured to: determine the weight of each optimization objective based on the driving conditions of the target vehicle; the weight is used to reflect the importance of the optimization objective under the driving conditions; construct a sub-function based on the comfort state data and each optimization objective; and obtain the objective function by weighted summation of the weights and sub-functions.

[0098] In one embodiment of this application, the state determination module 410 is further configured to: determine the target physiological data of the occupants in the target vehicle; input the target physiological data into the state determination model, perform the state determination operation to obtain the comfort state of the occupants in the target vehicle; and quantify the comfort state to obtain comfort state data. In one embodiment of this application, the state determination module 410 is further configured to: acquire image information of the occupant acquired by the image acquisition device and point cloud data of the occupant acquired by the radar; determine the first physiological data of the occupant based on the image information; determine the second physiological data of the occupant based on the point cloud data; and fuse the first physiological data and the second physiological data to obtain the target physiological data of the occupant in the target vehicle.

[0099] In one embodiment of this application, the state determination module 410 is further configured to determine the confidence level between the first physiological data and the second physiological data; and if the confidence level exceeds the target confidence level threshold, to fuse the first physiological data and the second physiological data to obtain the target physiological data of the occupant in the target vehicle. The confidence level is used to reflect the degree of consistency between the first physiological data and the second physiological data.

[0100] In one embodiment of this application, the state determination module 410 is further configured to: input first physiological data into a first state classifier, determine the state reflected by the first physiological data, and obtain a first classification result corresponding to the first physiological data; input second physiological data into a second state classifier, determine the state reflected by the second physiological data, and obtain a second classification result corresponding to the second physiological data; and determine the confidence level between the first physiological data and the second physiological data based on the first classification result and the second classification result.

[0101] This application embodiment utilizes comfort state data and optimization objectives to perform objective optimization processing, obtaining a collaborative adjustment instruction set for the target vehicle cabin environment. This collaborative adjustment instruction set includes adjustment instructions for multiple actuators in the cabin environment, thus achieving collaborative optimization of multiple actuators in the cabin environment under the same optimization objective. Therefore, when controlling each actuator to work collaboratively according to the collaborative adjustment instruction set, conflicts or contradictory operations caused by individual control of each actuator can be avoided, improving overall coordination. At the same time, performing objective optimization processing with maximizing comfort as the optimization objective can further improve the comfort of the cabin environment, providing passengers with a more coordinated and comfortable riding experience.

[0102] It is worth noting that in the embodiments of the above-mentioned cabin environment adjustment device, the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the scope of protection of the present invention.

[0103] Below, for reference Figure 5 To describe the vehicle according to embodiments of this application. Figure 5 The diagram shown is a structural schematic of a vehicle provided in an exemplary embodiment of this application.

[0104] like Figure 5 As shown, vehicle 50 includes one or more processors 501 and memory 502.

[0105] The processor 501 may be a central processing unit (CPU) or other form of processing unit with data processing and / or instruction execution capabilities, and may control other components in the vehicle 50 to perform desired functions.

[0106] The memory 502 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 501 may execute the program instructions to implement the cockpit environment adjustment methods of the various embodiments of this application described above, and / or other desired functions.

[0107] In one example, vehicle 50 may also include input device 503 and output device 504, which are interconnected via a bus system and / or other forms of connection mechanism (not shown).

[0108] The input device 503 may include, for example, a keyboard, a mouse, etc.

[0109] The output device 504 can output various information to the outside. The output device 504 may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0110] Of course, for the sake of simplicity, Figure 5 Only some of the components of the vehicle 50 relevant to this application are shown in this illustration; components such as buses, input / output interfaces, etc., are omitted. In addition, the vehicle 50 may include any other suitable components depending on the specific application.

[0111] In addition to the methods and devices described above, embodiments of this application may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform the steps in the cockpit environment adjustment methods according to various embodiments of this application as described above.

[0112] Computer program products can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this application. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0113] Furthermore, embodiments of this application may also be computer-readable storage media storing computer program instructions thereon, which, when executed by a processor, cause the processor to perform the steps in the cockpit environment adjustment methods according to various embodiments of this application described above.

[0114] Computer-readable storage media may take the form of any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may, for example, include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0115] The basic principles of this application have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this application are merely examples and not limitations, and should not be considered as essential features of each embodiment of this application. Furthermore, the specific details of the above application are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the application to the necessity of employing the aforementioned specific details for implementation.

[0116] The block diagrams of devices, apparatuses, devices, and systems involved in this application are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0117] It should also be noted that in the apparatus, equipment, and methods of this application, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered as equivalent solutions of this application.

[0118] The above description of the claimed aspects is provided to enable any person skilled in the art to make or use this application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of this application. Therefore, this application is not intended to be limited to the aspects shown herein, but rather to be applied within the widest scope consistent with the principles and novel features of this application.

[0119] The above description has been given for illustrative and descriptive purposes. Furthermore, this description is not intended to limit the embodiments of this application to the forms described herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. A method for adjusting the cabin environment, characterized in that, include: Determine the comfort status data of the occupants inside the target vehicle; Using the comfort status data and optimization objectives, target optimization processing is performed to obtain a set of coordinated adjustment instructions for the cabin environment of the target vehicle; wherein, the optimization objective includes a comfort maximization objective; and the coordinated adjustment instruction set includes adjustment instructions for multiple execution terminals in the cabin environment; According to the adjustment instructions in the coordinated adjustment instruction set, multiple execution terminals in the cockpit environment are controlled to work collaboratively.

2. The method according to claim 1, characterized in that, The optimization objectives also include the energy efficiency maximization objective and / or the safety maximization objective; The step of utilizing the comfort state data and optimization objectives to perform target optimization processing, and obtaining a set of coordinated adjustment instructions for the cabin environment of the target vehicle, includes: Based on the comfort state data and the optimization objective, an objective function is constructed; A multi-objective optimization algorithm is used to solve the objective function to obtain the collaborative adjustment instruction set for the cabin environment of the target vehicle.

3. The method according to claim 2, characterized in that, The objective function is constructed based on the comfort state data and the optimization objective, including: Based on the driving conditions of the target vehicle, a weight is determined for each optimization objective; the weight is used to reflect the importance of the optimization objective under the driving conditions. Based on the comfort state data and each of the optimization objectives, a sub-function is constructed; The objective function is obtained by weighting and summing the weights and sub-functions.

4. The method according to claim 1, characterized in that, The data used to determine the comfort status of occupants inside the target vehicle includes: Determine the target physiological data of the occupants inside the target vehicle; The target physiological data is input into the state determination model, and the state determination operation is performed to obtain the comfort state of the occupants in the target vehicle. The comfort state is quantified to obtain the comfort state data.

5. The method according to claim 4, characterized in that, The determination of the target physiological data of the occupants in the target vehicle includes: The image information of the occupant acquired by the image acquisition device and the point cloud data of the occupant acquired by the radar are obtained. Based on the image information, the first physiological data of the occupant are determined; Based on the point cloud data, the occupant's second physiological data is determined; The first physiological data and the second physiological data are fused to obtain the target physiological data of the occupant in the target vehicle.

6. The method according to claim 5, characterized in that, Before fusing the first physiological data and the second physiological data to obtain the target physiological data of the occupant in the target vehicle, the method further includes: Determine the confidence level between the first physiological data and the second physiological data; wherein the confidence level is used to reflect the degree of consistency between the first physiological data and the second physiological data; The step of fusing the first physiological data and the second physiological data to obtain the target physiological data of the occupant in the target vehicle includes: If the confidence level exceeds the target confidence level threshold, the first physiological data and the second physiological data are fused to obtain the target physiological data of the occupant in the target vehicle.

7. The method according to claim 6, characterized in that, Determining the confidence level between the first physiological data and the second physiological data includes: The first physiological data is input into the first state classifier to determine the state reflected by the first physiological data, and the first classification result corresponding to the first physiological data is obtained. The second physiological data is input into the second state classifier to determine the state reflected by the second physiological data, and the second classification result corresponding to the second physiological data is obtained. Based on the first classification result and the second classification result, the confidence level between the first physiological data and the second physiological data is determined.

8. A computer-readable storage medium, characterized in that, The storage medium stores a computer program for executing the cabin environment adjustment method according to any one of claims 1 to 7.

9. A vehicle, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is used to execute the cabin environment adjustment method according to any one of claims 1 to 7.

10. A computer program product, characterized in that, The computer program product includes instructions that, when executed on a vehicle, cause the vehicle to perform the cabin environment adjustment method according to any one of claims 1 to 7.

Images