A multi-source perception-based intelligent health regulation method and system for a vehicle-mounted air conditioner

Abstract

This invention provides a method and system for intelligent health control of in-vehicle air conditioning based on multi-source sensing, belonging to the field of intelligent control and health monitoring technology for in-vehicle air conditioning. The method acquires occupant facial images, physiological parameters, in-vehicle temperature and humidity, clothing thickness, and vehicle location information through a sensing layer, and uploads this multi-source data to a data processing layer at a preset frequency. The data processing layer sequentially performs occupant type identification, calculation of perceived temperature based on temperature, humidity, and vapor pressure, motion state correction, and physiological parameter health level assessment to obtain three core state quantities: occupant type, perceived temperature, and health level. The system selects a suitable temperature zone based on occupant type and generates a target temperature command by combining perceived temperature deviation and health status. This method enables precise temperature control through multi-source data fusion, provides intelligent intervention and rescue assistance in cases of health abnormalities, and improves the comfort, safety, and intelligence level of the in-vehicle air conditioning system.

Description

Technical Field

[0001] This invention relates to the field of intelligent control and health monitoring technology for vehicle air conditioning, and in particular to an intelligent health regulation method and system for vehicle air conditioning based on multi-source sensing. Background Technology

[0002] With the development of vehicle air conditioning technology and vehicle electronic systems, vehicles are gradually equipped with functions such as multi-temperature zone control, intelligent air volume adjustment, and remote preset, and the level of precision in controlling the in-vehicle environment is constantly improving.

[0003] However, the control logic of existing vehicle air conditioning systems mainly relies on a single temperature sensor or simplified environmental information, making it difficult to achieve personalized and precise temperature adjustment based on the physiological characteristics, physical sensations, and health conditions of different occupants. In particular, in situations where there are infants, the elderly, occupants with sensitive constitutions, or occupants who have just finished exercising, traditional air conditioning systems cannot effectively identify occupant differences, often leading to problems such as uncomfortable temperature control, localized overcooling or overheating, and affecting ride comfort.

[0004] On the other hand, in recent years, the application of various sensing hardware such as wearable devices, in-vehicle cameras, and environmental sensors in vehicles has gradually become widespread, but there is still a lack of a unified fusion mechanism between multi-source data. Existing systems usually design facial recognition, health parameter monitoring, or air conditioning adjustment functions separately, lacking a multi-channel linkage mode, making it difficult to achieve adaptive air conditioning control strategies through comprehensive analysis of occupant identity, physiological parameters, and environmental sensing data. Therefore, we propose a method and system for intelligent health control of in-vehicle air conditioning based on multi-source sensing.

[0005] The information disclosed in the background section is only intended to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0006] The purpose of this invention is to address the shortcomings of existing technologies by providing a method and system for intelligent health control of vehicle air conditioning based on multi-source sensing, thereby solving the technical problems mentioned in the background section.

[0007] To achieve the above objectives, the present invention provides the following technical solution:

[0008] A method for intelligent health control of in-vehicle air conditioning based on multi-source sensing includes the following steps:

[0009] S1. After the system is powered on, a wireless connection is established between the vehicle and the wearable device. The face recognition unit is activated to collect images inside the vehicle and complete the initial identification of the occupants. At the same time, the ambient temperature, humidity and clothing thickness sensors are activated, and the system enters the data collection state.

[0010] S2. Collect facial recognition data, wearable device body temperature and heart rate physiological parameters, temperature and humidity data of various areas inside the vehicle and passenger clothing thickness data synchronously according to the preset sampling frequency, and upload the physiological parameter data to the data processing module.

[0011] S3. Determine the occupant type based on the facial recognition results, calculate the corresponding perceived temperature using temperature and humidity, clothing thickness and movement status, and classify and evaluate the occupant's health status according to physiological parameters and health thresholds to obtain occupant type information, perceived temperature information and health status information.

[0012] S4. Based on the basic temperature range corresponding to the occupant type, combined with the perceived temperature and health status, generate a target temperature command; adjust the compressor speed, heating power and damper opening according to the target temperature command to bring the interior temperature to the target temperature range.

[0013] S5. Implement graded intervention based on health status level. When the health status is abnormal, activate the audible and visual alarm and output health prompt information. When the health status is severely abnormal, automatically trigger the rescue call and control the vehicle to slow down, pull over, and stop, thus achieving a safe response in the case of abnormal health status.

[0014] S1 specifically includes:

[0015] The vehicle power module supplies power to the perception layer, data processing layer, control execution layer and interaction layer in sequence, and completes the power-on self-test of each module.

[0016] The wearable device interaction unit initiates Bluetooth scanning, searches for smart bracelets and watches within a preset range, completes pairing, and sends a connection success notification to the interaction layer.

[0017] The face recognition unit activates the camera, captures the first frame of image inside the vehicle, and uploads the pre-processed image to the data processing layer for initial identity recognition.

[0018] The ambient temperature and humidity sensor, clothing thickness sensor, and positioning module enter the data acquisition state, complete basic calibration, and wait for periodic data acquisition to be triggered.

[0019] S2 specifically includes:

[0020] The in-vehicle images are updated at preset time intervals to extract occupant facial features and provide occupant identity input data.

[0021] Wearable devices upload body temperature, heart rate, blood pressure and exercise status data in real time, and send the data to the data processing layer after data verification;

[0022] Temperature and humidity data for each area are collected at the rated frequency, and the thickness of occupants' clothing is obtained using infrared sensors.

[0023] The positioning module continuously acquires vehicle location and wearable device location information, and all collected data is uniformly aggregated to the data processing layer cache.

[0024] S3 specifically includes:

[0025] The system matches facial image features with a pre-defined occupant feature database to output information on adult, infant, and elderly types.

[0026] The perceived temperature is calculated based on temperature, humidity, clothing thickness, and movement status, and then dynamically corrected using a perceived temperature correction factor to obtain the corrected perceived temperature result.

[0027] The wearable device collects body temperature and heart rate parameters and compares them with health thresholds to output normal, abnormal, and severely abnormal health levels.

[0028] The occupant type, perceived temperature, and health level are compiled into temperature control decision input parameters and sent to the temperature control decision module. Based on the basic temperature control range and perceived temperature status corresponding to the occupant type, the target temperature inside the vehicle is calculated, and a temperature control command to be executed is generated.

[0029] S4 specifically includes:

[0030] The data processing layer sends target temperature, compressor adjustment commands, and damper adjustment commands to the air conditioning controller.

[0031] When the target temperature is lower than the current temperature, cooling is performed by increasing the compressor speed; when the target temperature is higher than the current temperature, heating is performed by increasing the heating power.

[0032] The stepper motor adjusts the damper tilt angle according to the command, directing the airflow to the cooling or heating channel and maintaining the preset opening; it collects the current temperature periodically and compares it with the target temperature, and automatically corrects the PWM duty cycle when the deviation exceeds the threshold until the temperature stabilizes.

[0033] S5 specifically includes:

[0034] The data processing layer continuously updates the health level and sends the status information to the safety intervention unit in real time;

[0035] When an abnormal level is detected, an audible and visual alarm is triggered, health tips are displayed, and the reminder is read aloud by the voice module.

[0036] When a severe anomaly is detected, the rescue process is initiated, including automatically dialing the rescue hotline and uploading the vehicle's location information;

[0037] The automatic parking controller sends commands to the vehicle control system to decelerate, activate hazard lights, and pull over to the side of the road based on severe abnormal conditions, so that the vehicle can automatically stop in a safe area and unlock the doors.

[0038] A vehicle air conditioning intelligent health control system based on multi-source sensing, employing the aforementioned vehicle air conditioning intelligent health control method based on multi-source sensing, includes:

[0039] The perception layer is used to acquire multi-source raw data on vehicle occupants and the environment.

[0040] The data processing layer is used to fuse and analyze the data uploaded by the sensing layer; the data processing layer sends the target temperature command to the control execution layer and the health status signal to the safety intervention execution unit;

[0041] The control execution layer is used to execute the vehicle air conditioning adjustment according to the instructions generated by the temperature control decision module, and to perform hierarchical feedback correction based on the deviation between the current temperature and the target temperature to achieve stable temperature control.

[0042] A safety intervention execution unit is used to perform health interventions based on the health status.

[0043] The interaction layer is used to display in-vehicle environmental information and health status information, and output voice prompts, while also receiving manual adjustment commands from users for the target temperature.

[0044] The vehicle power module is used to supply power to the perception layer, data processing layer, control execution layer, interaction layer, and safety intervention execution unit.

[0045] The beneficial effects of this invention are as follows:

[0046] This invention collects multi-dimensional data such as occupant facial features, physiological parameters, ambient temperature and humidity, and clothing thickness, and uses a body temperature model as the core to achieve dynamic temperature calculation. Compared with traditional air conditioning systems that rely on a single area temperature sensor, it can provide a more personalized temperature control strategy based on the differences in physical condition and real-time status of different occupants, making the temperature in each area of ​​the vehicle more accurate and comfortable, and effectively avoiding local overheating or undercooling.

[0047] This invention can automatically identify adult, infant and elderly passengers, and adjust the perceived temperature based on clothing thickness and movement status. It generates target temperatures according to the appropriate temperature zone corresponding to the age group of the passengers, realizing differentiated temperature control for multiple passengers and multiple areas. It is especially suitable for temperature-sensitive groups such as infants and elderly passengers, improving safety and comfort.

[0048] This invention utilizes wearable devices to collect real-time data such as body temperature, heart rate, and blood pressure. It then uses threshold judgments to achieve a graded assessment of health levels and links health status with air conditioning adjustment logic. When occupants experience fever, abnormal heart rate, or other conditions, the system can automatically adjust air conditioning parameters within the specified temperature range to create an environment that better meets health needs, thereby reducing health risks.

[0049] In response to detected "abnormal" conditions, the system automatically triggers audible and visual alarms and visual cues to enhance occupants' health awareness. In response to "severe abnormal" conditions, the system further automatically dials preset emergency numbers, uploads vehicle location information, and triggers a complete safety response process, including vehicle deceleration, activation of hazard lights, automatic lane changing and parking, and unlocking of doors, significantly improving emergency response efficiency in the event of a sudden health incident.

[0050] Traditional air conditioning systems and health monitoring equipment are separate entities, while this invention unifies multi-source sensing, motion estimation, air conditioning control, and health intervention into a single system. Through unified decision-making at the data processing layer, it achieves closed-loop control across the entire chain, enabling the vehicle to have optimal environmental adjustment and safety handling capabilities in various states, including normal, abnormal, and severe abnormalities.

[0051] This invention highly integrates technologies such as image recognition, environmental perception, wearable devices, and dual-mode positioning to automatically complete occupant identification, status assessment, temperature control adjustment, and safety intervention. This allows the vehicle to maintain a suitable environment and safe status in real time without the need for manual intervention from the occupants, significantly improving the intelligent experience of the vehicle's air conditioning system. Attached Figure Description

[0052] Figure 1 This is a schematic diagram of an intelligent health control method for vehicle air conditioning based on multi-source sensing according to the present invention;

[0053] Figure 2 This is a schematic diagram of the framework of an intelligent health control system for vehicle air conditioning based on multi-source sensing according to the present invention. Detailed Implementation

[0054] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0055] Example 1: As Figure 1 As shown, this embodiment provides a method for intelligent health control of in-vehicle air conditioning based on multi-source sensing, including the following steps:

[0056] S1. After the system is powered on, a wireless connection is established between the vehicle and the wearable device. The face recognition unit is activated to collect images inside the vehicle and complete the initial identification of the occupants. At the same time, the ambient temperature, humidity and clothing thickness sensors are activated, and the system enters the data collection state.

[0057] S2. Collect facial recognition data, wearable device body temperature and heart rate physiological parameters, temperature and humidity data of various areas inside the vehicle and passenger clothing thickness data synchronously according to the preset sampling frequency, and upload the physiological parameter data to the data processing module.

[0058] S3. Determine the occupant type based on the facial recognition results, calculate the corresponding perceived temperature using temperature and humidity, clothing thickness and movement status, and classify and evaluate the occupant's health status according to physiological parameters and health thresholds to obtain occupant type information, perceived temperature information and health status information.

[0059] S4. Based on the basic temperature range corresponding to the occupant type, combined with the perceived temperature and health status, generate a target temperature command; adjust the compressor speed, heating power and damper opening according to the target temperature command to bring the interior temperature to the target temperature range.

[0060] S5. Implement graded intervention based on health status level. When the health status is abnormal, activate the audible and visual alarm and output health prompt information. When the health status is severely abnormal, automatically trigger the rescue call and control the vehicle to slow down, pull over, and stop, thus achieving a safe response in the case of abnormal health status.

[0061] S1. After the system powers on, a wireless connection is established between the vehicle and the wearable device. The face recognition unit is activated to collect images inside the vehicle and complete the initial identification of the occupants. At the same time, the ambient temperature, humidity, and clothing thickness sensors are activated, and the system enters the data collection state. The specific steps include the following:

[0062] S110. Equipment power-on and module startup: After the vehicle is powered on, the on-board power module supplies power to the perception layer, data processing layer, control execution layer and interaction layer in sequence, and each unit automatically executes the startup self-test program.

[0063] Once each module returns a normal status code to the main controller, the initialization process begins.

[0064] The camera completes parameter settings during the startup phase, including setting the exposure time to 50ms and initializing the resolution to 1080p to ensure the consistency of the basic data for subsequent image recognition.

[0065] S120, Wearable device connection establishment: The wearable device interaction unit activates the Bluetooth scanning function to search for wearable device signals within a radius of 10m;

[0066] The Bluetooth scan timeout is set to 5 seconds. If no wearable device is detected within the timeout period, a repeat scan will be performed automatically to ensure connection stability.

[0067] Once the Bluetooth module detects the wearable device and completes pairing, the data verification chip verifies the connection status. If successful, it sends a "connection successful" message to the interaction layer. The wearable device then enters a preparation state for real-time uploading of physiological parameters.

[0068] S130, Face Recognition Unit Initialization: The face recognition unit activates the high-definition camera to capture an initial image inside the vehicle (1080p resolution), and then performs format correction and noise suppression processing on the image through a preprocessing chip.

[0069] The processed initial image is uploaded to the data processing layer as initial identification input data to establish a baseline for occupant facial features.

[0070] S140. Environmental and Positioning Sensor Preparation: Temperature sensor, humidity sensor, infrared clothing thickness sensor, and GPS / BeiDou dual-mode positioning module are initialized sequentially; after each sensor completes self-test and returns to the initialization completion flag, it enters the data acquisition state so that it can work at the preset sampling frequency in the subsequent data acquisition stage.

[0071] S2. Synchronously collect facial recognition data, wearable device body temperature and heart rate physiological parameters, temperature and humidity data of various areas inside the vehicle, and passenger clothing thickness data according to a preset sampling frequency, and upload the physiological parameter data to the data processing module; specifically including the following sub-steps:

[0072] S210, Face Recognition Image Acquisition: The face recognition unit continuously acquires images inside the vehicle at a frequency of 2 seconds / frame; each acquired frame is obtained at 1080p resolution and undergoes brightness correction and noise suppression by the image preprocessing chip.

[0073] After each image update, the system automatically extracts facial feature points of the occupants (including eye distance, nose width, facial contour, etc.) and generates corresponding feature vectors. These feature vectors are transmitted to the data processing layer via CAN bus and used as real-time input for occupant identification and type determination.

[0074] S220, Physiological parameters and motion status acquisition:

[0075] Wearable devices upload physiological measurement data in real time via Bluetooth, including body temperature, heart rate, blood pressure, and exercise status; the above data is continuous streaming data with no fixed sampling interval.

[0076] The data verification chip at the receiving end performs a legality check on each set of raw physiological parameters, including numerical range checks (e.g., body temperature 35–42℃, heart rate 30–200 beats / minute) and Bluetooth data packet integrity checks;

[0077] Once the verification is successful, the data is sent to the data processing layer in real time via the CAN bus for immediate analysis by the health assessment module.

[0078] S230, Environmental parameters and clothing thickness data collection:

[0079] Temperature and humidity sensors collect temperature and humidity data in three areas inside the vehicle (above the center console in the front row, left side of the rear row, and right side of the rear row) at a frequency of 1 second, and generate environmental parameter sequences for each area.

[0080] The infrared clothing thickness sensor collects the optical path difference at 1 second interval and calculates the clothing thickness using the following formula:

[0081] ;

[0082] Among them: the optical path difference is measured by the infrared reflection time difference; the body surface distance is the basic distance of the occupant's body surface obtained by sensor calibration. All environmental parameters and clothing thickness data are integrated by the regional data acquisition unit and then uniformly sent to the data processing layer via CAN bus.

[0083] S240, Vehicle and Wearable Device Positioning Information Collection: The GPS module and Beidou module receive satellite signals in real time and generate vehicle position information (accuracy ≤10m), and the Bluetooth module estimates the position of the wearable device relative to the vehicle based on signal strength.

[0084] The dual-mode positioning fusion chip performs timestamp synchronization and outlier removal on the two types of positioning data to generate a fused positioning result of the vehicle location and the wearable device location.

[0085] The final merged location data, along with the multi-source data from S210–S230, is aggregated into the data processing layer cache, serving as the basic input for subsequent identity recognition, body temperature calculation, and health assessment.

[0086] S3. Determine the occupant type based on facial recognition results, calculate the corresponding perceived temperature using temperature and humidity, clothing thickness, and movement status, and classify and assess the occupant's health status according to physiological parameters and health thresholds to obtain occupant type information, perceived temperature information, and health status information; specifically including the following sub-steps:

[0087] S310, Occupant type recognition processing: The feature vector uploaded by the face recognition unit in S210 is received by the identity recognition module of the data processing layer;

[0088] This module calls a pre-set occupant feature library to compare facial key point parameters (including eye distance, nose width, facial contour curvature, etc.) and determines the corresponding category through the nearest neighbor matching algorithm.

[0089] The identified passenger types include three categories: adults, infants, and the elderly.

[0090] The recognition results serve as input parameters for subsequent calculation of perceived temperature and temperature control decisions.

[0091] S320, Perceived Temperature Calculation and Processing: The data processing layer calculates the occupant's perceived temperature based on the ambient temperature T, relative humidity RH, clothing thickness d provided in S230, and the motion status in S220. This specifically includes the following three sub-steps:

[0092] Water vapor pressure calculation: Based on the current temperature and humidity parameters of the area, calculate the air water vapor pressure e using the following formula:

[0093] ;

[0094] Where: RH: relative humidity (unit: %); T: ambient temperature (unit: ℃); e: water vapor pressure (unit: kPa);

[0095] Initial perceived temperature calculation: Based on the water vapor pressure e, ambient temperature T, and fixed wind speed v inside the vehicle (taken as 0.5 m / s), the initial perceived temperature is calculated using the following formula. :

[0096] ;

[0097] This formula is used to characterize the temperature perceived by the human body in the current environment.

[0098] Motion state correction: Based on the motion state detected by the wearable device, [the system / mechanism] adjusts the motion state accordingly. Corrections are applied: if the object is at rest, the correction factor is 1.0; if the object is in motion, the correction factor is 0.8.

[0099] The final corrected perceived temperature result is obtained as follows:

[0100] ;

[0101] Where k is the motion correction coefficient. The corrected perceived temperature serves as one of the inputs to the temperature control decision module.

[0102] S330, Physiological Parameter Health Level Assessment: The data processing layer compares the physiological parameters such as body temperature, heart rate, and blood pressure uploaded by the wearable device with the health thresholds set by the system and completes the health level determination.

[0103] The system health thresholds are as follows:

[0104] A body temperature higher than 37.3℃ is considered abnormal.

[0105] Heart rate below 60 beats / minute or above 100 beats / minute → considered abnormal

[0106] If any of the following severe abnormal conditions are met: body temperature ≥39℃; heart rate ≥110 beats / minute; → it is judged as a severe abnormality; the assessment module outputs three health levels: normal, abnormal, and severe abnormality, which are used for safety intervention and temperature control strategy adjustment.

[0107] S340. Control input data generation: The data processing layer will structure and organize the following three types of results:

[0108] S310 occupant type; S320 final perceived temperature Ts_final; S330 health level;

[0109] A unified temperature control decision input package is formed and submitted to the temperature control decision module as the basis for generating the target temperature.

[0110] S350, Temperature Control Target Temperature Generation: The temperature control decision module calculates the final target temperature based on the input occupant type, perceived temperature, and health level. The process is as follows:

[0111] Select the base temperature range based on the occupant type:

[0112] Adults: 18–20℃

[0113] Infants / elderly: 20–22℃

[0114] If the perceived temperature Ts_final deviates from the baseline temperature range, the target temperature is calculated in the direction of the deviation to ensure that the perceived temperature is consistent with the occupant's suitable temperature range.

[0115] If the health level is abnormal or severely abnormal, increase the weight of ambient temperature and add health protection factors to the temperature control strategy to make the temperature zone more conservative and comfortable.

[0116] The final output target temperature serves as the temperature control command for the control execution layer, which is used for subsequent compressor adjustment, heating power adjustment, and damper opening adjustment.

[0117] S4 generates a target temperature command based on the baseline temperature range corresponding to the occupant type, combined with perceived temperature and health status; it then adjusts the compressor speed, heating power, and damper opening according to the target temperature command to bring the interior temperature to the target temperature range; this includes the following sub-steps:

[0118] S410 Temperature control command issuance: The data processing layer sends the temperature control command to the air conditioning controller via the CAN bus based on the target temperature output by S350.

[0119] The instructions include:

[0120] Target temperature (unit: °C);

[0121] Cooling / Heating mode selection signal;

[0122] Compressor speed control parameters (initial value of PWM duty cycle);

[0123] Damper opening and direction adjustment commands (cooling duct / heating duct).

[0124] Upon receiving the instruction, the air conditioning controller immediately enters the execution state and establishes control channels for the compressor, heater, and damper stepper motor respectively.

[0125] S420, Cooling and Heating Control Execution:

[0126] The air conditioning controller reads the current interior temperature in real time, compares it with the target temperature, and executes cooling or heating control according to the following rules:

[0127] Cooling control logic (current temperature > target temperature)

[0128] If the current temperature is higher than the target temperature, the system will enter cooling mode.

[0129] Based on the temperature difference ΔT = current temperature − target temperature, the PWM duty cycle is increased according to the following rules:

[0130] When ΔT ≥ 1℃:

[0131] ;

[0132] That is, for every 1°C decrease, the duty cycle increases by 10%.

[0133] The compressor increases its speed based on the increased duty cycle, providing stronger cooling capacity.

[0134] The damper stepper motor automatically adjusts to the direction of the cooling air duct and sets the opening to 60% to maintain a stable air volume.

[0135] Heating control logic (current temperature < target temperature): If the current temperature is lower than the target temperature, the system enters heating mode.

[0136] Based on the temperature difference ΔT = target temperature − current temperature, adjust the heating power according to the following rules:

[0137] When ΔT ≥ 1℃:

[0138] ;

[0139] That is, for every 1°C increase, the heater PWM increases by 8%. The heater power increases with the increase of PWM. The damper stepper motor is adjusted to the direction of the heating air duct and set to a fixed opening of 60%.

[0140] S430, Precise adjustment of damper opening: The damper adjustment unit executes actions based on the airflow direction and airflow control commands output by S410 and S420:

[0141] After receiving the opening command, the stepper motor adjusts the damper shaft to the specified angle with a fixed step distance; both cooling and heating modes use a standard opening of 60% to ensure uniform airflow; when entering the dynamic temperature difference correction process (see S440), the damper angle can be finely adjusted in 5% steps to assist in rapid temperature convergence.

[0142] The damper adjustment result is returned to the damper position sensor and transmitted back to the data processing layer via the CAN bus as closed-loop feedback information.

[0143] S440 Temperature Deviation Feedback Correction Adjustment: The air conditioning controller collects the current temperature every 2 seconds and calculates the real-time deviation with the target temperature.

[0144] Based on the degree of deviation, the following graded correction strategy is adopted:

[0145] Small deviation correction (0.5℃≤ΔT≤1℃): When the temperature difference ΔT falls within the small deviation range, the system executes a fine-tuning strategy.

[0146] ;

[0147] This means the duty cycle is increased by 5% (in either cooling or heating direction) for minor correction. Simultaneously, the damper opening can be finely adjusted by 5% (±5%) to accelerate local temperature stabilization.

[0148] Large Deviation Correction (ΔT>1℃): If the temperature difference exceeds 1℃, the system executes a fast correction strategy.

[0149] ;

[0150] This means that a 10% increase in duty cycle corresponds to rapid cooling or heating.

[0151] The damper opening is maintained at 60% of the baseline, and rapid temperature convergence is achieved primarily through increased compressor / heater capacity.

[0152] Steady state maintenance (ΔT < 0.5℃): When the temperature difference is less than 0.5℃, the system determines that the temperature control has reached a steady state: PWM no longer adjusts; the damper maintains its current opening; the system enters a low-power mode for monitoring until the deviation exceeds the threshold again.

[0153] S5. Implement tiered intervention based on health status level. When the health status is abnormal, activate the audible and visual alarm and output health prompt information; when the health status is severely abnormal, automatically trigger a rescue call and control the vehicle to slow down, pull over, and stop, achieving a safe response in abnormal health situations; specifically including the following sub-steps:

[0154] S510, Health Status Monitoring Output: Based on the health level assessment results (normal / abnormal / severely abnormal) of S330, the data processing layer sends real-time health status signals to the safety intervention execution unit at a frequency of 1 second / time.

[0155] The system simultaneously transmits the following parameters: current body temperature (°C); current heart rate (beats / minute); health level (normal / abnormal / severely abnormal); timestamp information; and the health status signal serves as the sole criterion for triggering subsequent steps S520–S540, thus forming a complete health intervention input chain.

[0156] S520, Abnormal Level Health Intervention Execution: When the health level is determined to be "abnormal" (e.g., body temperature > 37.3℃, or heart rate < 60 or > 100 beats / minute), the system executes secondary intervention measures, specifically including:

[0157] Audible and visual alarm execution: The audible and visual alarm enters abnormal alarm mode: the LED light flashes at a frequency of 1Hz; the buzzer sounds intermittently at a rhythm of 0.5 seconds on and 0.5 seconds off; the alarm signal and health status are displayed synchronously on the interactive layer.

[0158] Visualized health alerts: The in-vehicle display screen shows the occupants' health data in real time and pops up a message: "Your body temperature is high. We recommend seeking medical attention promptly." The display content refreshes every second to ensure synchronization with sensor data collection.

[0159] Voice broadcast reminder: The voice module plays health reminders at a volume 10dB higher than the current in-vehicle audio, including alerts for elevated body temperature and precautions.

[0160] The goal of S520 is to alert occupants / drivers to health abnormalities without affecting the vehicle's current driving behavior.

[0161] S530, Severe Abnormality Level Health Intervention Execution: When the health level is "Severe Abnormality" (e.g., body temperature ≥ 39℃ or heart rate ≥ 110 beats / minute), the system automatically enters the Level 3 intervention mode and executes the following actions:

[0162] Audible and visual alarm upgrade: The audible and visual alarm enters the severe abnormality mode: the LED light flashes rapidly (2Hz); the buzzer sounds continuously for 1 second and stops for 0.2 seconds; the alarm intensity is higher than the abnormality level, used to quickly remind the occupants.

[0163] Automatically dial emergency numbers: The vehicle communication module automatically dials the following preset numbers: the family member's number linked to the vehicle; and the 120 emergency medical center.

[0164] It will automatically broadcast the following voice messages: serious health information of the occupant (such as "body temperature 39.1℃"); real-time vehicle location coordinates (provided by the positioning module); current vehicle status (driving / parking); and automatically redial once if the dialing fails.

[0165] Upload location information: The system uploads the vehicle's location and health status to the cloud / emergency contact person every 3 seconds, so that external rescue parties can continuously monitor the vehicle's status.

[0166] S540 Automatic Safe Parking Control Execution: When S530 is triggered, the Automatic Safe Parking Controller starts to work in conjunction with the vehicle's ESP system to achieve a complete closed-loop control process from driving state to safe parking.

[0167] Deceleration control: The vehicle automatically executes a deceleration strategy: gradually reducing the vehicle speed to 30km / h; maintaining smooth deceleration to prevent discomfort to passengers or vehicle instability; the ESP module is responsible for ensuring the stability of the deceleration process.

[0168] Warning lights activated: The system automatically activates the hazard lights to alert vehicles behind that the vehicle is in an emergency; right lane scanning and safe zone recognition.

[0169] The vehicle's sensors scan the right lane to identify a safe, vacant area suitable for parking. The criteria for this judgment include: distance to static obstacles; gaps between vehicles; and whether the lane width meets the requirements for safe parking. If no safe area is detected, the vehicle continues to slow down and scan.

[0170] Automatic lane changing and parallel parking: When a safe area is detected, the controller performs the following actions: automatically steers to the right to enter the target lane; automatically decelerates to 0 km / h; and maintains the parking state after stopping.

[0171] Engage the electronic parking brake (if the vehicle has one).

[0172] Automatic door unlocking: After the vehicle comes to a complete stop, the onboard system automatically unlocks the doors, facilitating rescue personnel to board and passengers to escape.

[0173] Example 2: This example provides a vehicle air conditioning intelligent health control system based on multi-source sensing, including:

[0174] The perception layer is used to acquire multi-source raw data on vehicle occupants and the environment, including:

[0175] The face recognition unit is used to acquire occupant images at a preset frame rate and output facial feature data;

[0176] The wearable device interaction unit is used to receive physiological data such as body temperature, heart rate, blood pressure and exercise status uploaded by the wearable device in real time.

[0177] The environmental sensing unit is used to collect temperature, humidity, and the thickness of occupants' clothing in various areas inside the vehicle.

[0178] The positioning unit is used to acquire the positioning information of the vehicle and wearable devices; the above units communicate with the data processing layer through a bus.

[0179] The data processing layer is used to perform fusion analysis on the data uploaded by the perception layer, including:

[0180] The identity recognition module is used to match passenger types based on facial features;

[0181] The perceived temperature calculation module is used to calculate the perceived temperature based on temperature, humidity, clothing thickness, and movement status, and to make corrections based on the movement status.

[0182] The health status assessment module is used to classify the health status of passengers as normal, abnormal, or severely abnormal based on physiological parameters and set thresholds.

[0183] The temperature control decision module is used to generate air conditioning target temperature commands and mode adjustment commands based on occupant type, perceived temperature, and health level.

[0184] The data processing layer sends the target temperature command to the control execution layer and the health status signal to the safety intervention execution unit.

[0185] The control execution layer, used to execute vehicle air conditioning adjustments according to the instructions generated by the temperature control decision module, includes:

[0186] The compressor control unit is used to adjust the compressor speed based on the PWM duty cycle to achieve cooling or heating.

[0187] The heating control unit is used to adjust the heater power according to the duty cycle;

[0188] The damper adjustment unit is used to drive the stepper motor to adjust the direction and opening of the damper;

[0189] It also performs graded feedback correction based on the deviation between the current temperature and the target temperature to achieve stable temperature control.

[0190] A safety intervention execution unit, configured to perform health interventions based on the stated health status, includes:

[0191] When the health status is abnormal, an audible and visual alarm is triggered and a health prompt is output.

[0192] When the vehicle's health status is severely abnormal, it automatically dials the preset rescue number, uploads the vehicle's location information, and controls the vehicle to perform a safety response process that includes deceleration, activation of hazard lights, scanning for empty areas in the right lane, automatic parking, and automatic unlocking of the doors.

[0193] The interaction layer is used to display in-vehicle environmental information and health status information, and output voice prompts, while also receiving manual adjustment commands from users for the target temperature.

[0194] The vehicle power module is used to supply power to the perception layer, data processing layer, control execution layer, interaction layer, and safety intervention execution unit.

[0195] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters and thresholds in the formulas are set by those skilled in the art according to the actual situation.

[0196] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0197] Those skilled in the art will recognize that the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0198] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and modules described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0199] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules 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 through some interfaces; the indirect coupling or communication connection between apparatuses or modules may be electrical, mechanical, or other forms.

[0200] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0201] In addition, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0202] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion 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 described in the various embodiments of this application. 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.

[0203] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0204] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A multi-source perception-based intelligent health regulation method for a vehicle-mounted air conditioner, characterized in that, Includes the following steps: S1. After the system is powered on, a wireless connection is established between the vehicle and the wearable device. The face recognition unit is activated to collect images inside the vehicle and complete the initial identification of the occupants. At the same time, the ambient temperature, humidity and clothing thickness sensors are activated, and the system enters the data collection state. S2. Collect facial recognition data, wearable device body temperature and heart rate physiological parameters, temperature and humidity data of various areas inside the vehicle and passenger clothing thickness data synchronously according to the preset sampling frequency, and upload the physiological parameter data to the data processing module. S3. Determine the occupant type based on the facial recognition results, calculate the corresponding perceived temperature using temperature and humidity, clothing thickness and movement status, and classify and evaluate the occupant's health status according to physiological parameters and health thresholds to obtain occupant type information, perceived temperature information and health status information. S4. Based on the basic temperature range corresponding to the occupant type, combined with the perceived temperature and health status, generate a target temperature command; adjust the compressor speed, heating power and damper opening according to the target temperature command to bring the interior temperature to the target temperature range. S1 specifically includes: the vehicle power module supplies power to the perception layer, data processing layer, control execution layer and interaction layer in sequence, and completes the power-on self-test of each module; the wearable device interaction unit starts Bluetooth scanning, searches for smart bracelets and watches within a preset range and completes pairing, and sends a connection success prompt to the interaction layer; S2 specifically includes: updating in-vehicle images at preset time intervals, extracting occupant facial features and providing occupant identity input data; wearable devices uploading body temperature, heart rate, blood pressure and movement status data in real time, which are then sent to the data processing layer after data verification; collecting temperature and humidity data of each area at a rated frequency, and using infrared sensors to obtain the thickness of occupant clothing; the positioning module continuously acquiring vehicle location and wearable device positioning information, and all collected data are uniformly summarized to the data processing layer buffer; S3 specifically includes: matching facial image features with a preset occupant feature library to output information on adult, infant, and elderly types; calculating perceived temperature based on temperature, humidity, clothing thickness, and movement status, and dynamically correcting it using a perceived temperature correction coefficient to obtain the corrected perceived temperature result; comparing body temperature and heart rate parameters collected by wearable devices with health thresholds to output normal, abnormal, and severely abnormal health levels. S4 specifically includes: the data processing layer sending target temperature, compressor adjustment commands, and damper adjustment commands to the air conditioning controller; when the target temperature is lower than the current temperature, cooling is performed by increasing the compressor speed; when the target temperature is higher than the current temperature, heating is performed by increasing the heating power; the stepper motor adjusts the damper tilt angle according to the commands, so that the air duct flows to the cooling or heating channel and maintains the preset opening; the current temperature is collected periodically and compared with the target temperature, and the PWM duty cycle is automatically corrected when the deviation exceeds the threshold until the temperature stabilizes.

2. The intelligent health control method for vehicle air conditioning based on multi-source sensing according to claim 1, characterized in that, It also includes S5, which performs graded intervention based on the health status level. When the health status is abnormal, it activates an audible and visual alarm and outputs health prompt information; when the health status is severely abnormal, it automatically triggers a rescue call and controls the vehicle to slow down, pull over, and stop, thus achieving a safe response in the case of abnormal health.

3. The intelligent health control method for vehicle air conditioning based on multi-source sensing according to claim 1, characterized in that, S1 also includes: The face recognition unit activates the camera, captures the first frame of image inside the vehicle, and uploads the pre-processed image to the data processing layer for initial identity recognition. The ambient temperature and humidity sensor, clothing thickness sensor, and positioning module enter the data acquisition state, complete basic calibration, and wait for periodic data acquisition to be triggered.

4. The intelligent health control method for vehicle air conditioning based on multi-source sensing according to claim 1, characterized in that, S3 also includes: The occupant type, perceived temperature, and health level are compiled into temperature control decision input parameters and sent to the temperature control decision module. Based on the occupant type, the corresponding basic temperature control range, and the perceived temperature, the target temperature inside the vehicle is calculated, and a temperature control command to be executed is generated.

5. The intelligent health control method for vehicle air conditioning based on multi-source sensing according to claim 2, characterized in that, S5 specifically includes: The data processing layer continuously updates the health level and sends the status information to the safety intervention unit in real time; When an abnormal level is detected, an audible and visual alarm is triggered, health tips are displayed, and the reminder is read aloud by the voice module. When a severe anomaly is detected, the rescue process is initiated, including automatically dialing the rescue hotline and uploading the vehicle's location information; The automatic parking controller sends commands to the vehicle control system to decelerate, activate hazard lights, and pull over to the side of the road based on severe abnormal conditions, so that the vehicle can automatically stop in a safe area and unlock the doors.

6. A vehicle air conditioning intelligent health control system based on multi-source sensing, employing the vehicle air conditioning intelligent health control method based on multi-source sensing as described in any one of claims 1 to 5, characterized in that, include: The perception layer is used to acquire multi-source raw data on vehicle occupants and the environment. The data processing layer is used for fusion analysis of the data uploaded by the perception layer; The data processing layer sends the target temperature command to the control execution layer and the health status signal to the safety intervention execution unit; The control execution layer is used to execute the vehicle air conditioning adjustment according to the instructions generated by the temperature control decision module, and to perform hierarchical feedback correction based on the deviation between the current temperature and the target temperature to achieve stable temperature control. A safety intervention execution unit is used to perform health interventions based on the health status. The interaction layer is used to display in-vehicle environmental information and health status information, and output voice prompts, while also receiving manual adjustment commands from users for the target temperature. The vehicle power module is used to supply power to the perception layer, data processing layer, control execution layer, interaction layer, and safety intervention execution unit.

Images