Method, device and medium for adjusting settings of an intelligent cockpit

Abstract

The application relates to the technical field of intelligent automobiles, in particular to an intelligent cabin setting adjustment method, device and medium. In the method, physiological data of passengers are collected by using a multi-modal sensor array during a vehicle trip, a pre-training model is used to identify passenger states, target passengers in a preset attention state are screened out, and corresponding cabin adjustment strategies are generated in combination with the states, at least one of air conditioner temperature, air direction, seat angle, suspension hardness and power output mode of a position where the target passengers are located is adjusted in a targeted manner. Therefore, timely sensing and active intervention on the uncomfortable state of the passengers can be realized, real-time adaptation of the cabin setting to state changes can be improved, the burden of manual operation can be reduced, and the riding comfort in a multi-passenger scenario can be improved.

Description

Technical Field

[0001] This application relates to the field of intelligent vehicle technology, and in particular to a method, device and medium for adjusting intelligent cockpit settings. Background Technology

[0002] With the rapid development of intelligent vehicle technology, the intelligent cockpit has become a core area for enhancing the user's driving experience. In complex and ever-changing driving scenarios, passenger comfort needs exhibit highly personalized and dynamic characteristics. Currently, preset modes, voice commands, or physical buttons are typically used to control cabin parameters such as air conditioning and seats.

[0003] However, such solutions primarily rely on passenger feedback before adjustments are made, making it difficult to promptly reflect dynamic states such as fatigue, motion sickness, or changes in temperature, leading to response delays. Furthermore, they often rely on single-parameter adjustments, failing to effectively address diverse needs in multi-passenger scenarios, resulting in insufficient overall comfort and adaptability. Summary of the Invention

[0004] This application provides a method, device, and medium for adjusting smart cockpit settings to solve the aforementioned technical problems. This solution addresses application scenarios involving dynamic changes in passenger states during vehicle travel and the coexistence of diverse comfort needs among multiple passengers. It identifies the current state of passengers inside the vehicle and implements cockpit settings adjustments adapted to the specific state of each passenger, thereby improving the smart cockpit's responsiveness to changes in passenger states and its comfort adaptation level in multi-passenger scenarios.

[0005] In a first aspect, embodiments of this application provide a method for adjusting smart cockpit settings, the method comprising:

[0006] Physiological data of each passenger in the vehicle during the current journey is obtained by using a pre-set multimodal sensor array;

[0007] A pre-trained state determination model is used to determine the current state type of each passenger based on their corresponding physiological data.

[0008] Passengers whose status type is the first preset type are identified as target passengers;

[0009] The system generates cabin adjustment commands based on the target passenger's status type, and adjusts the cabin settings of the target passenger's cabin according to the cabin adjustment commands. The cabin settings include at least one of the following: air conditioning temperature, air conditioning direction, seat angle, suspension stiffness, and power output mode.

[0010] In one possible embodiment, the preset multimodal sensor array includes at least two of the following: a piezoelectric heart rate sensor, a millimeter-wave radar respiratory monitor, an infrared body temperature sensor, and a facial feature collector;

[0011] Physiological data include at least one of heart rate, respiratory rate, body temperature, and motion sickness index.

[0012] In one possible embodiment, it also includes:

[0013] Calculate the difference in heart rate data or respiratory rate between the piezoelectric heart rate sensor and the millimeter-wave radar respiratory monitor;

[0014] If the difference is greater than the corresponding preset deviation threshold, the data will be corrected based on the facial feature data.

[0015] In one possible embodiment, determining the state type includes:

[0016] Based on the physiological data ranges in the historical settings adjustment data for each passenger, determine the physiological data adjustment threshold for each passenger.

[0017] The threshold and physiological data of each passenger are adjusted to determine the current state type of each passenger.

[0018] In one possible embodiment, the pre-trained state determination model includes a time-series prediction module, the first preset type includes motion sickness, fatigue, excessive cold, and excessive heat, and further includes:

[0019] The time-series prediction module uses physiological data within a preset time window for each passenger to predict the probability of each passenger experiencing various types of states in the future.

[0020] In one possible embodiment, generating cockpit adjustment commands includes:

[0021] Obtain the corresponding adjustment strategy based on the target passenger's status type;

[0022] Based on the adjustment strategy, at least one of the following is generated: cockpit domain command, chassis domain command, and power domain command.

[0023] In one possible embodiment, it also includes:

[0024] When there are multiple target passengers with different status types, the existence of a highest priority passenger is determined according to the preset priority determination rules.

[0025] If such a situation exists, the adjustment strategy weight corresponding to the highest priority passenger is set higher than that of other target passengers, and a cabin adjustment command is generated.

[0026] In one possible embodiment, it also includes:

[0027] If not, the status type of each target passenger, the conflict point of the adjustment strategy, and at least two adjustment options will be displayed on the vehicle screen for the passenger to choose from.

[0028] Cockpit adjustment commands are generated based on user confirmation information.

[0029] Secondly, embodiments of this application provide an electronic device, including: a memory and a processor;

[0030] The memory stores instructions that the computer executes;

[0031] The processor executes computer execution instructions stored in memory, causing the processor to perform the methods described above.

[0032] Thirdly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the methods provided above.

[0033] The intelligent cockpit setting adjustment method, device, and medium provided in this application embodiment acquire physiological data corresponding to each passenger in the current vehicle journey through a preset multimodal sensor array. This comprehensive and accurate collection of basic data avoids signal loss and single-point interference issues compared to a single sensor, ensuring data integrity and reliability. A pre-trained state determination model is used to determine the current state type of each passenger based on their corresponding physiological data, enabling more timely and objective perception of passenger state changes during vehicle operation. Passengers with a first preset state type are then identified as target passengers, filtering out those requiring cockpit adaptation from the entire passenger pool, avoiding indiscriminate adjustments and achieving on-demand control. Cockpit adjustment commands are generated based on the target passenger's state type, adjusting at least one setting in the target passenger's cockpit, including air conditioning temperature, air conditioning direction, seat angle, suspension stiffness, and power output mode. This improves the real-time adaptability of the cockpit settings to individual passenger states, achieving adaptive adaptation between physiological state and the cockpit environment, transforming passive setting into active intelligent adjustment, and enhancing overall comfort and adaptability. Attached Figure Description

[0034] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0035] Figure 1 An application scenario diagram of an adjustment method for intelligent cockpit settings provided in this application;

[0036] Figure 2 A flowchart illustrating a method for adjusting smart cockpit settings according to an embodiment of this application;

[0037] Figure 3 A flowchart illustrating a method for adjusting smart cockpit settings according to another embodiment of this application;

[0038] Figure 4A schematic diagram of the structure of the adjustment device for a smart cockpit provided in an embodiment of this application;

[0039] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0040] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0041] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0042] It should be noted that in the embodiments of this application, certain software, components, models and other existing solutions in the industry may be mentioned. These should be regarded as exemplary and are only intended to illustrate the feasibility of implementing the technical solution of this application. However, it does not mean that the applicant has used or necessarily used the solution.

[0043] To clearly understand the technical solution of this application, the solutions of the prior art will be described in detail first.

[0044] With the continuous iteration and upgrading of intelligent connected vehicle technology, the intelligent cockpit, as the core carrier of the vehicle's intelligent experience, has become a key track for automakers to optimize the driving experience and enhance the core competitiveness of their products. Real-world driving scenarios involve complex and ever-changing road conditions, and the physical state and comfort needs of passengers change in real time with driving duration, road conditions, and the cabin environment. Furthermore, different passengers have significantly different tolerances and comfort preferences, making cockpit comfort adjustment needs dynamic, personalized, and differentiated. Currently, most mainstream intelligent cockpit comfort adjustment solutions rely on fixed preset comfort modes, in-car voice interaction, or physical buttons to manually adjust individual cabin hardware parameters such as air conditioning and seat angles. However, these adjustment methods depend entirely on the driver and passengers actively issuing control commands, making it impossible to seamlessly and in real-time collect changes in human physiological characteristics. It is difficult to anticipate subtle discomforts such as motion sickness, fatigue, and imbalances in body temperature, resulting in significant system lag and an inability to achieve proactive comfort intervention.

[0045] Therefore, when facing the technical problems of existing technologies, since traditional cabin adjustment solutions rely on passengers manually pressing buttons and actively controlling via voice, they cannot autonomously perceive the implicit physiological changes of the human body. Therefore, this solution utilizes an onboard multimodal sensor array to collect physiological data of all passengers in the vehicle without human intervention, achieving unobtrusive, all-weather, and real-time monitoring of the vital signs of drivers and passengers. A pre-trained state determination model is introduced to intelligently analyze and classify the chaotic raw physiological signals. Based on the criteria for judging human discomfort, it accurately classifies different physical and mental states of passengers, achieving rapid interpretation of physiological data and intelligent identification of passenger states. To solve the problems of uniform vehicle adjustment failing to adapt to the differentiated needs of multiple passengers and blindly adjusting the entire system, which reduces the driving and riding experience, this solution identifies target passengers in abnormal discomfort states and generates targeted cabin adjustment commands for each zone. It then links multiple vehicle parameters, including air conditioning, seats, suspension, and power modes, for personalized control, achieving independent zone adjustment, low interference, and precise adaptation of intelligent cabin adaptive comfort control.

[0046] Figure 1 This is an application scenario diagram illustrating the adjustment method for the smart cockpit settings provided in this application, such as... Figure 1 As shown in the diagram, the scenario corresponding to the intelligent cockpit setting adjustment method provided in this application includes: a first cockpit 101, a second cockpit 102, a third cockpit 103, and an intelligent adjustment device 104. The intelligent adjustment device 105 integrates an intelligent adjustment mechanism. It is understood that a vehicle may include multiple intelligent cockpits; this embodiment only demonstrates three cockpits as an example. The first cockpit 101, second cockpit 102, and third cockpit 103 are communicatively connected to the intelligent adjustment device 104; the intelligent adjustment device 104 is communicatively connected to each sensor in the multimodal sensor array.

[0047] It should be noted that each cabin is equipped with a multimodal sensor array to collect passengers' physiological data.

[0048] Specifically, after the multimodal sensor array collects the physiological data of passengers sitting in each cabin, it sends the data to the intelligent adjustment device 104. The intelligent adjustment device 104 uses a pre-trained state determination model to determine the current state type of each passenger based on their corresponding physiological data, and identifies passengers with a first preset state type as target passengers. Then, the intelligent adjustment device 104 generates cabin adjustment instructions based on the target passenger's state type and sends these instructions to the cabins requiring adjustment, such as the third cabin 103, so that the third cabin 103 adjusts its cabin settings according to the cabin adjustment instructions.

[0049] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0050] Figure 2 A flowchart illustrating an embodiment of the method for adjusting smart cockpit settings provided in this application is shown below. Figure 2 As shown, the execution subject of this embodiment is an adjustment device for the smart cockpit settings. This device can be implemented through a computer program, or through a medium storing the relevant computer program, such as a USB flash drive and / or optical disc, or through an electronic device integrating or installing the relevant computer program, such as a chip, server, or server cluster. The smart cockpit settings adjustment method provided in this embodiment includes the following steps:

[0051] S201. Obtain physiological data corresponding to each passenger in the current journey vehicle through a preset multimodal sensor array.

[0052] Among them, the preset multimodal sensor array is a combination array of various types of physiological detection sensors that are deployed at fixed points according to the layout of the vehicle cabin space and the passenger's seating position.

[0053] Optionally, the sensors can transmit data synchronously via an in-vehicle Ethernet network.

[0054] Physiological data refers to vital signs and parameters that are generated autonomously by the passenger's body and can directly reflect the body's comfort state and physiological fluctuations, such as heart rate and respiratory rate.

[0055] In practice, after the vehicle is powered on and starts driving, the pre-deployed multimodal sensor array simultaneously enters the wake-up and data collection state, establishing a correspondence between passenger identification and sensor data collection channels based on seat position. For example, facial features are collected through the in-vehicle camera and matched with user profiles stored on the vehicle's system, associating the physiological data of each seat with the corresponding passenger identity. If the passenger is a first-time traveler, a temporary user profile is automatically created, linking the physiological data and adjustment records of this trip.

[0056] In one possible embodiment, to ensure that data from different modalities can be used for subsequent unified analysis, preprocessing operations are performed on the acquired raw signals, and the data is organized and stored according to passenger, time slice, and data type. If data from a certain modality is abnormally acquired within the current time window, the abnormal data can be marked and the currently available set of physiological data can be output, thereby ensuring the continuous execution of subsequent state recognition processes.

[0057] S202. A pre-trained state determination model is used to determine the current state type of each passenger based on their corresponding physiological data.

[0058] Among them, the pre-trained state determination model refers to an intelligent human physiological state recognition model that has been pre-trained offline based on a massive dataset of real-world in-vehicle driving scenarios, with parameters already fixed. It is used to analyze the physiological data of each passenger and output the current state category of each passenger. Models such as random forests, support vector machines, long short-term memory networks, or other models capable of state recognition can be used.

[0059] For example, during the model training phase, physiological data samples from different road conditions, cabin environments, and groups of people are integrated to cover common riding conditions such as normal comfort, mild fatigue, severe fatigue, motion sickness, and body temperature imbalance. At the same time, the model learns the characteristics of vehicle interference signals such as vehicle bumps, in-vehicle noise, and small body movements of passengers.

[0060] Among them, the state type refers to the category of the passenger's real-time physical and mental comfort state based on the fluctuation range and frequency of the passenger's physiological indicators, such as overheating, overcooling, fatigue, motion sickness, and normal state.

[0061] In practice, the physiological data set of each passenger within the current time window is read from the data cache and input into the pre-trained state determination model deployed locally. The model performs deep feature extraction on the input raw physiological time-series data, compares and matches the extracted effective physiological features with the various state standard feature libraries stored during the training phase, and completes the independent classification and determination of each passenger's physiological state based on the built-in state classification and determination rules.

[0062] Optionally, for the implementation using a random forest model, the feature parameters are constructed into a feature vector and input into the model, which then outputs the current state type. For the implementation using a long short-term memory network, the feature sequences from multiple consecutive time slices are input into the model, which then outputs the current state type based on changes in physiological data.

[0063] In one possible embodiment, the training samples for the pre-trained state determination model are derived from labeled data collected from multiple passengers under different riding conditions, and the training labels are determined jointly by manual annotation results and objective measurement results.

[0064] S203. The passenger whose status type is the first preset type is identified as the target passenger.

[0065] The first preset type refers to a set of abnormal physiological states of passengers that are pre-defined and require cabin adaptive adjustment intervention. These include states such as motion sickness, physical fatigue, feeling too cold or too hot, and emotional agitation.

[0066] Understandably, a passenger in a relaxed and comfortable state with a stable heart rate and breathing is not considered to be in the first preset type and therefore does not require cabin adjustment.

[0067] Among them, the target passenger refers to the passenger whose cabin area needs to be adjusted according to the status type at the current moment.

[0068] Specifically, the system retrieves the passenger status type results from the model output and simultaneously matches them with the seat location information of each passenger, establishing a correlation between passenger seat number, real-time physiological state, and status type. Each passenger's actual status type is then compared and matched against a locally stored first preset type standard, performing tiered screening and judgment. If a passenger's current status type falls within the range of abnormal discomfort states covered by the first preset type, the passenger is determined to have a riding comfort deficiency and meets the cabin adjustment access conditions. If the passenger's status is a normal comfort state and does not match the first preset type, the passenger is directly excluded from subsequent adjustment services.

[0069] S204. Generate cabin adjustment instructions based on the target passenger's status type, and adjust the settings of the target passenger's cabin according to the cabin adjustment instructions. The cabin settings include at least one of the following: air conditioning temperature, air conditioning direction, seat angle, suspension stiffness, and power output mode.

[0070] Cabin adjustment commands refer to a standardized set of control commands generated according to preset adjustment rules based on the specific state of the target passenger. These commands may include the equipment to be adjusted, the direction of adjustment, the adjustment range, and the effective area; different passenger states correspond to different command contents.

[0071] Specifically, the system retrieves the identified target passenger information and its corresponding status type, while simultaneously matching the target passenger's location within the cabin. It then invokes pre-configured status-adjustment rules, matching corresponding adjustment logic to different abnormal states. For example, if a passenger feels too hot, the system lowers the air conditioning and adjusts the airflow direction; if a passenger is fatigued, it simultaneously adjusts the seat angle, vehicle suspension, and power mode. The adjustment range for each parameter is determined based on the severity of the status, and these are integrated into a complete cabin adjustment command according to a standardized format. This command is then linked to the target passenger's location area.

[0072] Furthermore, after the command is generated, it is sent to the cockpit domain controller, air conditioning controller, seat controller, chassis domain controller and powertrain domain controller respectively via the vehicle communication bus, and the corresponding execution components complete the parameter adjustment.

[0073] For example, after receiving instructions, the cockpit domain controller controls the air conditioning system to adjust the temperature, airflow direction, and air volume; controls the seat actuators to adjust the backrest angle and lumbar support position; and controls the ventilation or heating functions to start or stop. After receiving instructions, the chassis domain controller adjusts the shock absorber damping through the suspension control system to achieve suspension stiffness adjustment. After receiving instructions, the powertrain domain controller adjusts the throttle response curve and shift logic to achieve smooth mode switching.

[0074] Optionally, during the adjustment process, changes in passenger physiological data are monitored in real time. If the passenger's physiological parameters do not return to the comfort range within a preset time after adjustment, the parameter gradient of the optimization strategy is automatically adjusted. For example, if the passenger's body temperature does not drop after the air conditioning temperature is lowered, the temperature is further lowered or the air volume is increased until the passenger's physiological parameters return to the comfort range.

[0075] Understandably, different types of discomfort correspond to different cabin adjustment strategies. For example, when motion sickness is detected, the corresponding adjustment strategy is to soften the suspension, adjust the air conditioning vents to avoid the passenger, adjust the seat to a semi-reclined position, and adjust the power output to a smooth mode. When passenger fatigue is detected, the corresponding adjustment strategy is to lower the air conditioning temperature, adjust the air conditioning vents to blow on the passenger, adjust the seat to an upright position, and play refreshing music. When passenger overheating is detected, the corresponding adjustment strategy is to lower the air conditioning temperature, adjust the air conditioning vents to blow on the passenger, and adjust the seat to ventilation mode. When passenger overcooling is detected, the corresponding adjustment strategy is to raise the air conditioning temperature and adjust the seat to heating mode.

[0076] In one possible embodiment, after generating the initial adjustment scheme, constraint corrections are also made based on the vehicle's current operating state. The vehicle's current operating state may include vehicle speed, acceleration, road type, current driving mode, and actuator availability. For example, when the vehicle is cornering at high speed or on a continuously bumpy road, the available range of suspension adjustment by the chassis domain controller is limited by the vehicle stability strategy. In this case, the suspension damping adjustment range is limited to a safe threshold, while comfort needs are compensated by increasing seat angle adjustment or air conditioning parameter adjustment. When the powertrain is executing a driving mode explicitly set by the driver and the vehicle control strategy restricts automatic switching, the power output mode remains unchanged, and only air conditioning, air conditioning direction, and seat-related adjustment commands are issued.

[0077] Optionally, after each control command is generated, it is distributed into multiple frames according to the controlled object and sent to the corresponding controller via CAN, LIN, or vehicle Ethernet. After completing the execution, the controller sends back the execution status. If the feedback result shows that a certain actuator has not achieved the target value, an alternative adjustment command can be regenerated based on the currently available adjustment items and sent again.

[0078] The intelligent cockpit setting adjustment method provided in this application embodiment acquires physiological data corresponding to each passenger in the current journey vehicle through a preset multimodal sensor array. This comprehensive and accurate collection of basic data avoids signal loss and single-point interference issues compared to a single sensor, ensuring data integrity and reliability. A pre-trained state determination model is used to determine the current state type of each passenger based on their corresponding physiological data, enabling more timely and objective perception of passenger state changes during vehicle operation. Passengers with a first preset state type are then identified as target passengers, filtering out those requiring cockpit adaptation from the entire passenger pool, avoiding indiscriminate adjustments and achieving on-demand control. Based on the target passenger's state type, cockpit adjustment commands are generated to adjust at least one setting in the target passenger's cockpit, including air conditioning temperature, air conditioning direction, seat angle, suspension stiffness, and power output mode. This improves the real-time adaptability of the cockpit settings to individual passenger states, achieving adaptive adaptation between physiological state and the cockpit environment, transforming passive setting into active intelligent adjustment, and enhancing overall comfort and adaptability.

[0079] As an optional implementation, based on the above embodiments, the preset multimodal sensor array includes at least two of the following: a piezoelectric heart rate sensor, a millimeter-wave radar respiratory monitor, an infrared body temperature sensor, and a facial feature collector;

[0080] Physiological data include at least one of heart rate, respiratory rate, body temperature, and motion sickness index.

[0081] Optionally, the aforementioned sensors can be fixedly installed on the seat back, headrest, center console, or dashboard area, and connected to the same data link via the vehicle computing unit. Specific models can be selected based on the vehicle's layout space, sampling accuracy, and anti-interference requirements. In practical applications, other models of this component can also be selected, and this application embodiment does not limit this.

[0082] The motion sickness index is a comprehensive representation value obtained based on the fusion of multi-source features. The motion sickness index can be calculated by the amplitude of heart rate changes, the dispersion of respiratory rhythm, dizziness expression in facial features, and abnormal body temperature deviation, and can be mapped to discrete levels or continuous values.

[0083] Specifically, if equipped with a piezoelectric heart rate sensor, the sensor continuously captures the regular vibrations caused by the heartbeat based on the pressure deformation generated after the passenger sits down. The vibration signal is then simply filtered to remove noise caused by vehicle bumps and minor limb movements, ultimately outputting stable heart rate data. If equipped with a millimeter-wave radar respiratory monitor, the device continuously emits detection signals to track the periodic rise and fall of the passenger's chest, distinguishing breathing movements from other limb movements, and counting the number of breaths per unit time to obtain respiratory frequency data. If equipped with an infrared body temperature sensor, the device is aimed at the passenger's face or neck area, receiving the infrared radiation energy emitted by the human body and converting it into a body surface temperature value, thus completing the body temperature data collection. If equipped with a facial feature acquisition device, the device captures the passenger's facial images in real time, capturing facial expressions, eye states, facial muscle states, and other features. Combined with simultaneously acquired heart rate and respiratory frequency data, and according to a predetermined judgment logic, a comprehensive calculation is performed to derive the corresponding passenger's motion sickness index.

[0084] The intelligent cockpit setting adjustment method provided in this application embodiment synchronously collects the physiological state of passengers during cockpit operation, so that the identification of target passengers is based on multimodal data. It can maintain the integrity of passenger state input under different passenger numbers and different sensor configurations, and improve the matching accuracy of subsequent cockpit adjustments.

[0085] As an optional implementation, based on the above embodiments, it further includes:

[0086] Calculate the difference in heart rate data or respiratory rate between the piezoelectric heart rate sensor and the millimeter-wave radar respiratory monitor;

[0087] If the difference is greater than the corresponding preset deviation threshold, the data will be corrected based on the facial feature data.

[0088] Among them, the heart rate data difference refers to the difference between two sets of heart rate values ​​output by the piezoelectric heart rate sensor and the millimeter-wave radar respiratory monitor for the same passenger, which is used to measure the degree of deviation between the data collected by the two types of devices.

[0089] Among them, the respiratory rate difference refers to the difference between two sets of respiratory rate values ​​output by the piezoelectric heart rate sensor and the millimeter-wave radar respiratory monitor for the same passenger, which is used to determine whether there is a significant deviation in the detection results of the two types of devices.

[0090] Among them, the preset deviation threshold refers to the numerical limit set in advance, which is divided into two categories: heart rate deviation threshold and respiratory rate deviation threshold, which correspond to the allowable error range of heart rate and respiratory rate, respectively.

[0091] Among them, facial feature data refers to visual information such as passenger facial expressions, eye state, facial muscle changes, and facial movements acquired in real time by facial feature collectors.

[0092] Specifically, after acquiring the sampling results from the piezoelectric heart rate sensor and the millimeter-wave radar respiratory monitor, a corresponding difference calculation result is established based on the heart rate data or respiratory rate data within the same time window, and this difference is compared with a pre-stored deviation threshold. The preset deviation threshold can be generated from historical calibration data and set in combination with different passenger body types, sitting postures, and sensor installation positions. When the difference does not exceed the deviation threshold, the current acquisition result is directly used for subsequent status recognition. When the difference is greater than the corresponding threshold, the facial feature collector is invoked to acquire facial feature data, and the abnormal heart rate data or abnormal respiratory rate data is corrected based on the facial feature data. The correction method can be weighted compensation, interval substitution, or confidence reassessment of the abnormal sampling values, thereby outputting the corrected physiological data.

[0093] For example, when rear passengers wear thick clothing, causing errors in the breathing frequency monitored by millimeter-wave radar, the facial micro-expression recognition function of the facial feature collector is automatically invoked. By analyzing the amplitude and frequency of chest rise and fall, the breathing frequency data is corrected to ensure the accuracy of status recognition.

[0094] The intelligent cockpit setting adjustment method provided in this application utilizes two types of sensors based on different principles to collect the same physiological indicators and calculate the differences. This proactively detects data distortion caused by vehicle vibrations, passenger limb movements, and environmental interference from a single device, filtering out invalid and erroneous data at the source and preventing abnormal data from flowing into subsequent stages and causing misjudgments. When sensor data deviates, facial feature data is introduced as supplementary evidence, overcoming the limitations of single sensor data. By combining visual features to comprehensively reconstruct the passenger's true state, abnormal values ​​are reasonably corrected, significantly improving the accuracy and reliability of the final physiological data.

[0095] As an optional implementation, based on the above embodiments, determining the state type includes:

[0096] Based on the physiological data ranges in the historical settings adjustment data for each passenger, determine the physiological data adjustment threshold for each passenger.

[0097] The threshold and physiological data of each passenger are adjusted to determine the current state type of each passenger.

[0098] Among them, historical setting adjustment data refers to the retained records of passengers' cabin adjustments over the years. It includes all information such as the original physiological data, cabin adjustment actions, and parameter changes before and after each adjustment, and is a personalized historical data archive formed for each passenger.

[0099] Among them, the physiological data range refers to the range of values ​​obtained from the historical settings and adjustment data of each passenger. It corresponds to the normal range and abnormal range of various physiological data such as heart rate, respiratory rate and body temperature of the passenger under different cabin adjustment scenarios, which can reflect the individual physiological characteristics and physical sensations of the passenger.

[0100] Among them, the physiological data adjustment threshold refers to the critical value defined by combining the passenger's unique physiological data range. It serves as the dividing line between the passenger's normal state and the need to initiate cabin adjustments. Each passenger has an independent threshold, with different physiological indicators corresponding to their own adjustment thresholds.

[0101] In practice, historical setting adjustment data for each passenger in the vehicle is retrieved. For each physiological data point, such as heart rate, respiratory rate, body temperature, and motion sickness index, the numerical distribution formed by multiple past samplings is analyzed to divide the corresponding data intervals. A distinction is made between the normal value intervals when the passenger is in a comfortable state and the abnormal value intervals when the passenger feels uncomfortable and triggers cabin adjustments. Based on the divided physiological data intervals and pre-set judgment rules, physiological data adjustment thresholds are set for each passenger.

[0102] Furthermore, the current physiological data is compared with physiological data adjustment thresholds. If all real-time physiological data are within the normal range defined by the adjustment thresholds, the passenger is determined to be in a normal and comfortable state. If any one or more real-time physiological data exceed the corresponding adjustment threshold, the passenger's current abnormal state type is determined by combining the type of the exceeded indicator and the degree of deviation, thus ultimately determining the specific state type of each passenger.

[0103] The intelligent cockpit setting adjustment method provided in this application abandons the fixed judgment standard uniform throughout the vehicle, and generates exclusive adjustment thresholds based on passenger historical data. This method is tailored to the physiological characteristics and physical differences of different groups of people, avoids misjudgment of some groups by general thresholds, and improves the fit of state judgment.

[0104] As an optional implementation, based on the above embodiments, the pre-trained state determination model includes a time-series prediction module, the first preset type includes motion sickness, fatigue, excessive cold, and excessive heat, and also includes:

[0105] The time-series prediction module uses physiological data within a preset time window for each passenger to predict the probability of each passenger experiencing various types of states in the future.

[0106] The time-series prediction module is a functional unit of the pre-trained state determination model. It is used to process physiological data collected continuously in chronological order and to perform trend inference based on the data's changes over time. The time-series prediction module can be implemented using recurrent neural networks, long short-term memory networks, temporal convolutional networks, or combinations thereof. In practical applications, other models suitable for time-series modeling can also be selected for this module, and this application embodiment does not limit this.

[0107] The preset time window refers to a fixed time range defined in advance, used to extract continuous historical physiological data segments as analysis samples for time series prediction. The window duration remains fixed and can be configured in advance according to the vehicle usage scenario.

[0108] Among them, the probability of occurrence of a state refers to a reference value calculated by combining the changing patterns of time series data. It represents the likelihood that passengers will experience various states such as motion sickness, fatigue, excessive cold, and excessive heat in the following period of time. The higher the probability value, the more obvious the tendency of the corresponding state to occur.

[0109] In the specific implementation, after acquiring the physiological data of each passenger within a preset time window, the data of the same passenger collected by different sensors are aligned by timestamps to form a continuous time-series input vector. Then, the time-series prediction module performs feature extraction and correlation analysis on this input vector to obtain the probability value of each passenger experiencing motion sickness, fatigue, excessive cold, or excessive heat in the future. The probability value can be represented as a state confidence distribution and can be output as the state change trend at several predicted future times according to time granularity, thus providing a basis for subsequent state determination and cabin adjustment command generation.

[0110] For example, if the physiological data of a passenger collected for 10 consecutive minutes shows that the heart rate gradually increases, the respiratory rate gradually accelerates, and the body temperature rises slightly, the time-series prediction module predicts that the passenger has a high probability of experiencing overheating discomfort in the next 15 minutes, and triggers the heat discomfort regulation strategy in advance.

[0111] Optionally, during operation, the system continuously collects adjusted passenger physiological data and user feedback, iteratively optimizing the mapping relationship between model parameters and strategies. If a user repeatedly adjusts cabin settings within the same physiological parameter range, the system automatically updates the user's discomfort recognition threshold and corresponding optimization strategy, achieving personalized adaptation. For example, if a user proactively lowers the air conditioning temperature to a value lower than the general strategy each time mild fatigue is detected, the system learns this habit, and subsequently, when fatigue is detected, the system directly uses the user's preferred temperature parameters to generate optimization instructions, improving the user experience.

[0112] The intelligent cockpit setting adjustment method provided in this application no longer judges the current state solely based on current data. Instead, it predicts subsequent state changes through time-series analysis, enabling the detection of risks before passengers experience significant discomfort. Motion sickness, fatigue, and discomfort from temperature changes are all gradually developing states. The time-series module can accurately capture the gradual change process of data, significantly reducing the probability of missing sudden states compared to instantaneous data judgment, and improving the overall operational stability of the solution.

[0113] As an optional implementation, based on the above embodiments, cockpit adjustment commands are generated, including:

[0114] Obtain the corresponding adjustment strategy based on the target passenger's status type;

[0115] Based on the adjustment strategy, at least one of the following is generated: cockpit domain command, chassis domain command, and power domain command.

[0116] Among them, the adjustment strategy refers to a set of pre-configured control schemes corresponding to various passenger status types. For different states such as motion sickness, fatigue, excessive cold, and excessive heat, the rules for generating various control commands are based on clearly defining the on-board functions that need to be adjusted, the direction of parameter adjustment, and the reasonable adjustment range.

[0117] In a specific implementation, the target passenger's state type can be derived from the output of the aforementioned pre-trained state determination model. When the identification result is characterized as any of the following types: motion sickness, fatigue, excessive cold, or excessive heat, the adjustment strategy corresponding to that type is invoked, and the strategy is converted into control parameters that can be recognized by the vehicle domain controller.

[0118] Optionally, if the strategy involves adjusting in-cabin equipment, cabin domain commands can be generated according to rules to specify adjustments such as air conditioning temperature, airflow direction, and seat angle. If the strategy requires changing the suspension operating state, chassis domain commands can be generated to set suspension stiffness adjustment parameters. If the strategy requires switching driving characteristics, power domain commands can be generated to configure the power output mode. A single type of command can be generated based on actual needs, or multiple types of commands can be generated simultaneously.

[0119] It is understood that the cockpit domain controller, chassis domain controller, and powertrain domain controller can all receive and execute commands via in-vehicle Ethernet, CAN bus, or LIN bus. In practical applications, other models of the above controllers can also be selected, and this application embodiment does not limit this.

[0120] The intelligent cockpit setting adjustment method provided in this application splits the instructions according to the three major areas of vehicle cockpit, chassis and power, and matches the existing distributed control system architecture of the vehicle. The instructions can be accurately sent to the corresponding control system without interference, reducing the probability of errors in cross-system control.

[0121] As an optional implementation, based on the above embodiments, it further includes:

[0122] When there are multiple target passengers with different status types, the existence of a highest priority passenger is determined according to the preset priority determination rules.

[0123] If such a situation exists, the adjustment strategy weight corresponding to the highest priority passenger is set higher than that of other target passengers, and a cabin adjustment command is generated.

[0124] Among them, the preset priority determination rule refers to the pre-fixed passenger status priority ranking standard, such as the priority from high to low as elderly and children, driver's seat, and vehicle owner.

[0125] Among them, the highest priority passenger refers to the passenger with the most severe physical discomfort or the highest risk to driving safety, selected according to the preset priority judgment rules in a scenario where multiple target passengers in the vehicle have different status types.

[0126] In the specific implementation, after the identification of the status type of each target passenger is completed, the target passengers with inconsistent status types are input into the priority determination module. The priority determination module assigns a priority value to each target passenger based on a preset rule table, and selects the passenger with the highest priority value as the highest priority passenger.

[0127] Optionally, the rule table can be pre-stored in the vehicle configuration file, where response levels corresponding to states such as fatigue, motion sickness, overheating, and overcooling are encoded and combined with passenger identification, seating area, and historical adjustment records for joint judgment. If a unique highest value exists in the screening results, the existence of a highest priority passenger is confirmed. If the highest value corresponds to multiple passengers, a secondary judgment can be made based on seat proximity or the duration of the state.

[0128] Furthermore, the adjustment strategy weight corresponding to the highest priority passenger is set to a higher value than that of other target passengers, and the adjustment needs of each target passenger are integrated according to this weight to generate cabin adjustment commands for air conditioning, seats, suspension or power output.

[0129] For example, when the highest priority user needs to lower the air conditioning temperature, the seat heating temperature of other seats can be increased individually to balance the comfort needs of different passengers.

[0130] Optionally, car owners can temporarily adjust the priority order via voice commands, and the adjustment will be valid for the current trip.

[0131] The intelligent cockpit setting adjustment method provided in this application addresses the shortcomings of single-passenger adaptation strategies in complex scenarios where multiple passengers experience discomfort with varying degrees of discomfort. It adapts to all real-world driving scenarios by mitigating the need for comfort in low-priority passengers by reducing their adjustment weight. This ensures effective adjustments for core passengers while also considering the basic comfort of other passengers, avoiding adverse discomfort caused by extreme adjustments.

[0132] As an optional implementation, based on the above embodiments, it further includes:

[0133] If not, the status type of each target passenger, the conflict point of the adjustment strategy, and at least two adjustment options will be displayed on the vehicle screen for the passenger to choose from.

[0134] Cockpit adjustment commands are generated based on user confirmation information.

[0135] The in-vehicle infotainment screen can be integrated into the center console, rear armrest screen, or headrest display. The display interface can use color coding, regional columns, or strategy labels to differentiate conflicting information, allowing passengers to intuitively confirm the impact of different adjustment schemes on temperature, air conditioning direction, seat posture, or power response. User confirmation can be generated through touch selection, virtual button confirmation, or swipe confirmation, and will serve as the input basis for generating subsequent cabin adjustment commands.

[0136] Among them, the conflict point of adjustment strategy refers to the conflicting parameter content when multiple target passengers have the same priority but different status types, and the corresponding adjustment strategies of the cabin domain, chassis domain, and power domain are contradictory and cannot be executed simultaneously. For example, if one passenger is too hot and needs to increase the air conditioning air volume, while another passenger is too cold and needs to decrease the air conditioning air volume, or if a passenger is carsick and needs to soften the suspension, while a passenger is fatigued and needs to stiffen the suspension, the two opposite adjustment needs are the strategy conflict point.

[0137] In practical implementation, when conflicts arise between adjustment strategies triggered by the status types of multiple target passengers, corresponding candidate adjustment schemes will be generated based on the conflicting factors, and the cabin parameter combinations corresponding to each scheme will be displayed simultaneously on the screen. For example, when one side of the passengers is in an overheated state while the other side is in an overcooled state, schemes such as biased local air supply, dual-zone temperature distribution, and seat ventilation linkage can be displayed, with the adaptation results of each scheme to different target passenger states indicated. After the passenger completes the selection, the user confirmation information is read, the selected scheme is mapped to specific air conditioning domain, seat domain, or power domain control quantities, and then cabin adjustment commands are generated and output to the corresponding actuators to complete the adjustment of the cabin settings for the target passenger.

[0138] Optionally, passengers can confirm the final plan via voice or touch, and then perform the corresponding adjustment. If passengers do not confirm the plan within a preset time, an equal weighting strategy will be used by default, adjusting all cabin parameters to the median value of all passenger needs.

[0139] For example, in a family travel scenario, if a child in the back seat experiences motion sickness, the elderly and children are prioritized highest, and a motion sickness optimization strategy is automatically implemented. This involves softening the suspension, adjusting the rear air conditioning vents to avoid the child's face, and adjusting the child's seat to a semi-reclined position, while maintaining the front air conditioning temperature at its original setting to accommodate the comfort needs of the adults in the front. In a scenario where colleagues are traveling together, if front passengers feel too hot and rear passengers feel too cold, and there is no highest priority user, two adjustment options are displayed. After passenger confirmation, a zoned temperature control scheme is adopted, lowering the front temperature and raising the rear temperature to meet the needs of both parties.

[0140] The intelligent cockpit setting adjustment method provided in this application embodiment transforms conflict information into selectable adjustment schemes when there are policy conflicts and no highest priority passenger, and generates control commands based on the confirmation results, so that the cockpit adjustment is consistent with passenger preferences, improving the adjustment accuracy and response time in multi-passenger scenarios.

[0141] Figure 3 A flowchart illustrating a method for adjusting smart cockpit settings according to another embodiment of this application is shown below. Figure 3 As shown, the method for adjusting the smart cockpit settings provided in this embodiment includes the following steps:

[0142] S301. Obtain physiological data corresponding to each passenger in the current journey vehicle through a preset multimodal sensor array; the preset multimodal sensor array includes at least two of the following: a piezoelectric heart rate sensor, a millimeter-wave radar respiratory monitor, an infrared body temperature sensor, and a facial feature collector; the physiological data includes at least one of heart rate, respiratory rate, body temperature, and motion sickness index.

[0143] S302. Calculate the difference in heart rate data or respiratory rate between the piezoelectric heart rate sensor and the millimeter-wave radar respiratory monitor.

[0144] S303. If the difference is greater than the corresponding preset deviation threshold, the data is corrected based on the facial feature data.

[0145] S304. Based on the physiological data ranges in the historical settings adjustment data corresponding to each passenger, determine the physiological data adjustment threshold corresponding to each passenger.

[0146] S305. A pre-trained state determination model is used to adjust the threshold and physiological data according to the physiological data of each passenger to determine the current state type of each passenger.

[0147] S306. The time-series prediction module is used to predict the probability of each passenger experiencing various types of states in the future based on the physiological data within the preset time window corresponding to each passenger. The pre-trained state determination model includes the time-series prediction module, and the first preset type includes motion sickness, fatigue, excessive cold, and excessive heat.

[0148] S307. The passenger whose status type is the first preset type is identified as the target passenger.

[0149] S308. Obtain the corresponding adjustment strategy based on the target passenger's status type.

[0150] S309. When there are multiple target passengers with different status types, determine whether there is a highest priority passenger according to the preset priority determination rules.

[0151] S310. If it exists, set the adjustment strategy weight corresponding to the highest priority passenger to be higher than that of other target passengers, and generate a cabin adjustment command. The cabin adjustment command includes at least one of the cabin domain command, chassis domain command, and power domain command.

[0152] S311. If not, the status type of each target passenger, the conflict point of the adjustment strategy, and at least two adjustment schemes shall be displayed on the vehicle screen for the passenger to choose from.

[0153] S312. Generate cockpit adjustment commands based on user confirmation information.

[0154] It should be noted that the execution order of S304-S305 and S306 is not important; the execution order of S310 and S311-S312 is not important.

[0155] In this embodiment, the implementation method and technical effect of S301-S312 are similar to those of the corresponding solutions in the above embodiments, and will not be repeated here.

[0156] Figure 4 A schematic diagram of the adjustment device for the smart cockpit provided in this application is shown below. Figure 4 As shown, the road condition sensing device 40 provided in this embodiment includes: an acquisition module 41, a determination module 42, and a generation module 43.

[0157] The acquisition module 41 is used to acquire physiological data corresponding to each passenger in the current journey vehicle through a preset multimodal sensor array; the determination module 42 is used to determine the current state type of each passenger based on the physiological data corresponding to each passenger using a pre-trained state determination model; the determination module 42 is also used to determine the passenger whose state type is a first preset type as the target passenger; the generation module 43 is used to generate cabin adjustment instructions based on the state type of the target passenger, so as to adjust the settings of the cabin where the target passenger is located according to the cabin adjustment instructions, the cabin settings including at least one of air conditioning temperature, air conditioning direction, seat angle, suspension stiffness, and power output mode.

[0158] The intelligent cockpit setting adjustment device provided in this embodiment can perform... Figure 2 and Figure 3 The implementation principles and technical effects of the methods shown are similar, and will not be repeated here.

[0159] Optionally, the preset multimodal sensor array includes at least two of the following: a piezoelectric heart rate sensor, a millimeter-wave radar respiratory monitor, an infrared body temperature sensor, and a facial feature collector; the physiological data includes at least one of heart rate, respiratory rate, body temperature, and motion sickness index.

[0160] Optionally, the intelligent cockpit setting adjustment device provided in this embodiment further includes a calculation module and a correction module.

[0161] Correspondingly, the calculation module is used to calculate the difference in heart rate data or respiratory rate data collected by the piezoelectric heart rate sensor and the millimeter-wave radar respiratory monitor; the correction module is used to correct the data based on facial feature data if the difference is greater than the corresponding preset deviation threshold.

[0162] Optionally, the determining module 42, when determining the state type, is specifically used to: determine the physiological data adjustment threshold for each passenger based on each physiological data range in the historical setting adjustment data corresponding to each passenger; and determine the current state type of each passenger based on the physiological data adjustment threshold and physiological data corresponding to each passenger.

[0163] Optionally, the intelligent cockpit setting adjustment device provided in this embodiment also includes a prediction module.

[0164] Correspondingly, the pre-trained state determination model includes a time-series prediction module, the first preset types of which include motion sickness, fatigue, excessive cold, and excessive heat, and a prediction module, which uses the time-series prediction module to predict the probability of each passenger experiencing each type of state in the future based on the physiological data within the preset time window corresponding to each passenger.

[0165] Optionally, when generating cabin adjustment instructions, the generation module 43 is specifically used to: obtain the corresponding adjustment strategy based on the state type of the target passenger; and generate at least one of cabin domain instructions, chassis domain instructions, and power domain instructions according to the adjustment strategy.

[0166] Optionally, the determining module 42 is further configured to determine whether a highest priority passenger exists according to a preset priority determination rule when there are multiple target passengers with different status types; the generating module 43 is further configured to set the adjustment strategy weight corresponding to the highest priority passenger to be higher than that of other target passengers if such a passenger exists, and generate a cabin adjustment command.

[0167] Optionally, the intelligent cockpit setting adjustment device provided in this embodiment also includes a display module.

[0168] Correspondingly, the display module is used to display the status type of each target passenger, the conflict point of the adjustment strategy, and at least two adjustment schemes on the vehicle screen if they do not exist, so that passengers can choose from them; the generation module 43 is also used to generate cabin adjustment instructions based on user confirmation information.

[0169] Figure 5 A schematic diagram of the structure of the electronic device provided in this application. Figure 5 As shown, the electronic device 50 provided in this embodiment includes a processor 51 and a memory 52. ​​The processor 51 and the memory 52 are connected via a bus and communicate with each other.

[0170] In the specific implementation process, the processor 51 executes the computer execution instructions stored in the memory 52, causing the processor 51 to perform the above-described method.

[0171] The specific implementation process of processor 51 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0172] In the above embodiments, it should be understood that the processor 51 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0173] The memory 52 may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0174] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0175] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0176] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0177] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0178] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0179] The division of units is merely a logical functional division; 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 coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0180] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0181] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0182] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0183] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0184] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for adjusting intelligent cockpit settings, characterized in that, The method includes: Physiological data of each passenger in the vehicle during the current journey is obtained by using a pre-set multimodal sensor array; A pre-trained state determination model is used to determine the current state type of each passenger based on their corresponding physiological data. Passengers whose status type is the first preset type are identified as target passengers; The system generates cabin adjustment commands based on the target passenger's status type, and adjusts the cabin settings of the target passenger's cabin according to the cabin adjustment commands. The cabin settings include at least one of the following: air conditioning temperature, air conditioning direction, seat angle, suspension stiffness, and power output mode.

2. The method according to claim 1, characterized in that, The preset multimodal sensor array includes at least two of the following: a piezoelectric heart rate sensor, a millimeter-wave radar respiratory monitor, an infrared body temperature sensor, and a facial feature collector; Physiological data include at least one of heart rate, respiratory rate, body temperature, and motion sickness index.

3. The method according to claim 2, characterized in that, Also includes: Calculate the difference in heart rate data or respiratory rate between the piezoelectric heart rate sensor and the millimeter-wave radar respiratory monitor; If the difference is greater than the corresponding preset deviation threshold, the data will be corrected based on the facial feature data.

4. The method according to claim 1, characterized in that, Determine the state type, including: Based on the physiological data ranges in the historical settings adjustment data for each passenger, determine the physiological data adjustment threshold for each passenger. The threshold and physiological data of each passenger are adjusted to determine the current state type of each passenger.

5. The method according to claim 1, characterized in that, The pre-trained state determination model includes a time-series prediction module. The first preset types include motion sickness, fatigue, excessive cold, and excessive heat. It also includes: The time-series prediction module uses physiological data within a preset time window for each passenger to predict the probability of each passenger experiencing various types of states in the future.

6. The method according to claim 1, characterized in that, Generate cockpit adjustment commands, including: Obtain the corresponding adjustment strategy based on the target passenger's status type; Based on the adjustment strategy, at least one of the following is generated: cockpit domain command, chassis domain command, and power domain command.

7. The method according to claim 5, characterized in that, Also includes: When there are multiple target passengers with different status types, the existence of a highest priority passenger is determined according to the preset priority determination rules. If such a situation exists, the adjustment strategy weight corresponding to the highest priority passenger is set higher than that of other target passengers, and a cabin adjustment command is generated.

8. The method according to claim 7, characterized in that, Also includes: If not, the status type of each target passenger, the conflict point of the adjustment strategy, and at least two adjustment options will be displayed on the vehicle screen for the passenger to choose from. Cockpit adjustment commands are generated based on user confirmation information.

9. An electronic device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-8.

Images